CN110310086A - Auxiliary recites based reminding method, equipment and storage medium - Google Patents
Auxiliary recites based reminding method, equipment and storage medium Download PDFInfo
- Publication number
- CN110310086A CN110310086A CN201910490557.0A CN201910490557A CN110310086A CN 110310086 A CN110310086 A CN 110310086A CN 201910490557 A CN201910490557 A CN 201910490557A CN 110310086 A CN110310086 A CN 110310086A
- Authority
- CN
- China
- Prior art keywords
- user
- reciting
- content
- next period
- prompt
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 10
- 230000008569 process Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 101100096895 Mus musculus Sult2a2 gene Proteins 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 101100096893 Mus musculus Sult2a1 gene Proteins 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000001550 time effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
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 present invention provide it is a kind of auxiliary recite based reminding method, equipment and storage medium.This method comprises: determining the prompt strategy in next period according to the degree-of-difficulty factor for reciting content for reciting state and next period of user;Within next period, the user is prompted according to the prompt strategy.The method of the embodiment of the present invention state and recites the degree-of-difficulty factor of content by reciting for user, and the prompt strategy determined more meets the demand of user, can timely and effectively provide the user with prompt, and user can be improved and practice the effect recited, raising user experience.
Description
Technical field
Based reminding method, equipment and storage is recited the present invention relates to field of artificial intelligence more particularly to a kind of auxiliary to be situated between
Matter.
Background technique
The study or during self-teaching in school, people generally require to recite article or a certain paragraph, but
It is that method efficiency is very low for traditional reciting, verification to the process of reciting and management are inconvenient, cause to recite and are unable to get well
Feedback and reinforcing.
With the combination of the development of artificial intelligence technology, especially voice technology and deep learning, so that being known by voice
Other technology auxiliary user, which recites, to be possibly realized.In the related technology, user selects the content to be recited, then back of the equipment to user
It reads aloud and records, after the completion of user recites or real-time detection recites correctness, and will recite result and be shown.
In above scheme, prompt can not be timely and effectively provided the user with, so that the effect that user's practice is recited is poor.
Summary of the invention
The present invention provide it is a kind of auxiliary recite based reminding method, equipment and storage medium, with realize timely and effectively give user
Prompt is provided, user experience is improved.
In a first aspect, the present invention provide it is a kind of auxiliary recite based reminding method, comprising:
According to the degree-of-difficulty factor for reciting content for reciting state and next period of user, the prompt plan in next period is determined
Slightly;
Within next period, the user is prompted according to the prompt strategy.
In one possible implementation, the difficulty for reciting content for reciting state and next period according to user
It spends before coefficient, further includes:
According to reminding number information and reciting accuracy information, determine that the user's recites state.
In one possible implementation, described according to reminding number information and reciting accuracy information, determine described in
User's recites state, comprising:
According to the prompting number information, it is described recite accuracy information and state influence factor, determine the user
Recite state;The state influence factor, which includes at least one of the following:, currently recites volume, interference sound information and word speed.
In one possible implementation, it is described according to the prompting number information, it is described recite accuracy information with
And state influence factor, determine that the user's recites state, comprising:
It to the prompting number information, recites accuracy information and state influence factor is weighted processing, obtains first
Weighted value;What first weighted average was used to measure user recites state;Wherein, the weight for reminding number information is
It is determined according to the prompting number information, the weight for reciting accuracy information is that accuracy information is recited according to is true
Fixed.
In one possible implementation, before the prompt strategy in the determination next period, further includes:
According to the uncommon word frequency for reciting content in next period, determine next period recites content
Degree-of-difficulty factor.
In one possible implementation, described that frequency is occurred according to the rarely used word for reciting content in next period
Rate determines the degree-of-difficulty factor for reciting content in next period, comprising:
Content is recited according to the uncommon word frequency for reciting content in next period and next period
Corresponding difficulty factor determines the degree-of-difficulty factor for reciting content in next period;The difficulty factor include it is following at least
One Xiang Yinsu: the user's recites textbook belonging to content, the works classification for reciting content of the user, the user
Recite the length of content, the context for reciting content of the user.
In one possible implementation, according to the uncommon word frequency for reciting content in next period and
Next period recites the corresponding difficulty factor of content, determines the degree-of-difficulty factor for reciting content in next period, packet
It includes:
The uncommon word frequency for reciting content and next period to next period recite content pair
The difficulty factor answered is weighted processing, obtains the second weighted value, and using second weighted value as next period
Recite the degree-of-difficulty factor of content;Wherein, the corresponding weight of uncommon word frequency for reciting content in next period is root
It is determined according to the uncommon word frequency for reciting content in next period.
In one possible implementation, according to the difficulty system for reciting content for reciting state and next period of user
Number, determines the prompt strategy in next period, comprising:
According to the degree-of-difficulty factor for reciting content for reciting state and next period of the user, to current time threshold
It is adjusted, obtains corresponding time threshold of next period;
According to next period corresponding time threshold, the prompt strategy in next period is determined.
In one possible implementation, the time threshold includes: first time threshold, in next period
It is interior, the user is prompted according to the prompt strategy, comprising:
If what the user recited gets stuck duration more than first time threshold, the first prompt information, institute are exported to user
The first prompt information is stated for inquiring whether the user needs to prompt;The duration that gets stuck is in the back for detecting the user
Start recording when reading aloud voice and reciting the text information mismatch of content;
If receiving the prompt response message of user, the adjacent content of text of text information at the current place of getting stuck of output,
To prompt the user.
In one possible implementation, the time threshold further include: second time threshold, the method are also wrapped
It includes:
If receiving the instruction information without prompt of user's triggering, continue to record the duration that gets stuck;
If in the adjacent text of text information that the duration that gets stuck more than second time threshold, exports place of currently getting stuck
Hold information, to prompt the user.
In one possible implementation, the time threshold includes third time threshold, the method also includes:
Record the user recites the time started;
If the difference for reciting the time started described in current time distance is more than third time threshold, output the second prompt letter
Breath, second prompt information is for prompting user to recite time-out.
Second aspect, the embodiment of the present invention provide a kind of computer readable storage medium, are stored thereon with computer program,
Method described in any one of first aspect is realized when the computer program is executed by processor.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, comprising:
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured that
According to the degree-of-difficulty factor for reciting content for reciting state and next period of user, the prompt plan in next period is determined
Slightly;
Within next period, the user is prompted according to the prompt strategy.
In one possible implementation, processor is configured that
According to reminding number information and reciting accuracy information, determine that the user's recites state.
In one possible implementation, processor is configured that
According to the prompting number information, it is described recite accuracy information and state influence factor, determine the user
Recite state;The state influence factor, which includes at least one of the following:, currently recites volume, interference sound information and word speed.
In one possible implementation, processor is configured that
It to the prompting number information, recites accuracy information and state influence factor is weighted processing, obtains first
Weighted value;What first weighted average was used to measure user recites state;Wherein, the weight for reminding number information is
It is determined according to the prompting number information, the weight for reciting accuracy information is that accuracy information is recited according to is true
Fixed.
In one possible implementation, processor is configured that
According to the uncommon word frequency for reciting content in next period, determine next period recites content
Degree-of-difficulty factor.
In one possible implementation, processor is configured that
Content is recited according to the uncommon word frequency for reciting content in next period and next period
Corresponding difficulty factor determines the degree-of-difficulty factor for reciting content in next period;The difficulty factor include it is following at least
One Xiang Yinsu: the user's recites textbook belonging to content, the works classification for reciting content of the user, the user
Recite the length of content, the context for reciting content of the user.
In one possible implementation, processor is configured that
The uncommon word frequency for reciting content and next period to next period recite content pair
The difficulty factor answered is weighted processing, obtains the second weighted value, and using second weighted value as next period
Recite the degree-of-difficulty factor of content;Wherein, the corresponding weight of uncommon word frequency for reciting content in next period is root
It is determined according to the uncommon word frequency for reciting content in next period.
In one possible implementation, processor is configured that
According to the degree-of-difficulty factor for reciting content for reciting state and next period of the user, to current time threshold
It is adjusted, obtains corresponding time threshold of next period;
According to next period corresponding time threshold, the prompt strategy in next period is determined.
In one possible implementation, processor is configured that
If what the user recited gets stuck duration more than first time threshold, the first prompt information, institute are exported to user
The first prompt information is stated for inquiring whether the user needs to prompt;The duration that gets stuck is in the back for detecting the user
Start recording when reading aloud voice and reciting the text information mismatch of content;
If receiving the prompt response message of user, the adjacent content of text of text information at the current place of getting stuck of output,
To prompt the user.
In one possible implementation, processor is configured that
If receiving the instruction information without prompt of user's triggering, continue to record the duration that gets stuck;
If in the adjacent text of text information that the duration that gets stuck more than second time threshold, exports place of currently getting stuck
Hold information, to prompt the user.
In one possible implementation, processor is configured that
Record the user recites the time started;
If the difference for reciting the time started described in current time distance is more than third time threshold, output the second prompt letter
Breath, second prompt information is for prompting user to recite time-out.
Auxiliary provided in an embodiment of the present invention recites based reminding method, equipment and storage medium, recites state according to user
With the degree-of-difficulty factor for reciting content in next period, the prompt strategy in next period is determined;Within next period, according to institute
It states prompt strategy to prompt the user, the degree-of-difficulty factor of content and is recited at state by reciting for user, is determined
Prompt strategy more meets the demand of user, can timely and effectively provide the user with prompt, can be improved what user's practice was recited
Effect improves user experience.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Fig. 1 is the flow diagram provided by the invention for assisting reciting one embodiment of based reminding method;
Fig. 2 is the structural schematic diagram of electronic equipment embodiment provided by the invention.
Through the above attached drawings, it has been shown that the specific embodiment of the disclosure will be hereinafter described in more detail.These attached drawings
It is not intended to limit the scope of this disclosure concept by any means with verbal description, but is by referring to specific embodiments
Those skilled in the art illustrate the concept of the disclosure.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Term " includes " in description and claims of this specification and the attached drawing and " having " and they appoint
What is deformed, it is intended that is covered and non-exclusive is included.Such as contain the process, method, system, production of a series of steps or units
Product or equipment are not limited to listed step or unit, but optionally further comprising the step of not listing or unit, or
Optionally further comprising the other step or units intrinsic for these process, methods, product or equipment.
Application scenarios according to the present invention are introduced first:
Auxiliary provided in an embodiment of the present invention recites based reminding method, in the scene recited applied to auxiliary user, to realize
Prompt is timely and effectively provided the user with, user is improved and practices the effect recited.
The method of the embodiment of the present invention is suitable for electronic equipment, for example including mobile phone, tablet computer, wearable device (example
Such as smartwatch, Intelligent bracelet), intelligent sound box, all kinds of learning machines, private tutor's machine terminal device.
Further, electronic equipment can also include display screen, for showing that user recites content.
Method provided by the invention can execute corresponding software code realization by electronic equipment such as processor, can also be by the electricity
Sub- equipment is realized while executing corresponding software code by carrying out data interaction with server, as server executes
Part operation carrys out controlling electronic devices and executes the auxiliary to recite based reminding method.
Technical solution of the present invention is described in detail with specific embodiment below.These specific implementations below
Example can be combined with each other, and the same or similar concept or process may be repeated no more in some embodiments.
Fig. 1 is the flow diagram provided by the invention for assisting reciting one embodiment of based reminding method.As shown in Figure 1, this reality
The method that example offer is provided, comprising:
Step 101, the degree-of-difficulty factor for reciting content for reciting state and next period according to user, determine next period
Prompt strategy.
Step 102, within next period, the user is prompted according to prompt strategy.
Further, the method for the present embodiment, further includes:
It after receiving the operational order of user, records to the voice of reciting of the user, the operational order is used
In instruction, the user starts to recite;Or,
Voice is recited according to the user detected, determines that the user's recites content.
Specifically, user such as is loaded with application program when carrying out auxiliary using electronic equipment and reciting in electronic equipment
(APP), realize that auxiliary recites the function of prompting by the APP.User can open the APP for example click in APP start by
Button starts to execute and recites prompting function, and that detects user recites voice, records to voice is recited, by reciting voice, really
Determine the content of reciting of user, e.g. which paragraph of which article.
Alternatively, user can first select the content to be recited after entering APP, such as refer in the operation that input starts recording
After order, start to record to the voice of reciting of user, starts to execute and recite prompting function.
Voice is recited and in reciting according to the state of reciting for reciting speech analysis user of user, such as according to user
Hold the accuracy of reciting that corresponding text information obtains user, user recite that accuracy can measure user recite state,
Recite that the accuracy the high, user to recite state better.
When user recites, it can analyze user and recite the degree-of-difficulty factor of content, such as recite rarely used word in content and occur
Frequency it is higher, then degree-of-difficulty factor is bigger;Or, context is simpler, degree-of-difficulty factor is smaller;Or, reciting textbook belonging to content, example
Such as certain grade of primary school period or certain grade of Junior, corresponding degree-of-difficulty factor is different.
Degree-of-difficulty factor is directed to the different sentences for reciting content or paragraph and can be different, therefore user can be with when reciting
It is divided into the different periods, different prompt strategies can be used in the different periods.
Therefore, next week can be determined according to the degree-of-difficulty factor for reciting content for reciting state and next period of user
The prompt strategy of phase.Wherein, the different periods can be prompted using identical or different prompt strategy.Current period makes
User is prompted with the prompt strategy of current period.It is right using the prompt strategy in updated next period in next period
User prompts.
It should be noted that next period can recite the text size division period of content according to user, or according to
Time divides the period, such as is backward next period from current time every time using current time as boundary.
Prompt strategy for example may include the instruction when prompted, or the mode comprising prompt, such as
By voice or the prompting mode of text, or content of prompt, such as prompt a word, a word etc. can also be included.
Further, user recites finish after, the situation of reciting of user can also be evaluated and tested, the side of the present embodiment
Method, further includes:
If detect the user recited it is described the voice of reciting of the user is evaluated and tested when reciting content,
And export evaluation result.
Specifically, recite finish after the voice of reciting of user can be evaluated and tested, evaluation result can also be opened up
Show, such as entirely reciting the accuracy of reciting of process is 80%, those contents recite mistake, what etc. be correct content be.With
Family can also playback the audio for reciting voice of oneself.
Further, the method for the present embodiment, further includes:
Show the text information for reciting voice of the user, the text information for reciting content of the user, Yi Jisuo
State the distinctive information of the text information for reciting content of the text information and the user of reciting voice.
Specifically, can show the text for reciting voice in the operation interface of the display screen of electronic equipment during reciting
This information, recite content original text text information and the two comparative information, further can be in display reminding
Appearance and other prompt informations etc..
The method of the present embodiment is determined according to the degree-of-difficulty factor for reciting content for reciting state and next period of user
The prompt strategy in next period;Within next period, the user is prompted according to the prompt strategy, passes through use
Reciting for family and recites the degree-of-difficulty factor of content at state, and the prompt strategy determined more meets the demand of user, can have in time
Effect provides the user with prompt, and user can be improved and practice the effect recited, improve user experience,
On the basis of the above embodiments, further, it can also proceed as follows before step 101:
According to reminding number information and reciting accuracy information, determine that the user's recites state.
Specifically, the state of reciting of user can be measured by reminding number information and reciting accuracy information, if back
It is higher to read aloud accuracy, reminds number fewer, to recite state better then current.If recited, accuracy is lower, reminds number
It is more, illustrate that current to recite state poorer.
Further, it is also contemplated that other influences factor, such as currently recite volume, interference sound information and word speed
It, specifically can be with Deng, i.e. step " number information and reciting accuracy information according to reminding, determine that the user's recites state "
It realizes in the following way:
According to the prompting number information, it is described recite accuracy information and state influence factor, determine the user
Recite state;The state influence factor, which includes at least one of the following:, currently recites volume, interference sound information and word speed.
Further, the state of reciting for determining user, can specifically be accomplished in that
It to the prompting number information, recites accuracy information and state influence factor is weighted processing, obtains first
Weighted value;What first weighted average was used to measure user recites state;Wherein, the weight for reminding number information is
It is determined according to the prompting number information, the weight for reciting accuracy information is that accuracy information is recited according to is true
Fixed.
Specifically, reminding the corresponding weight of number information that can recite accuracy according to reminding number information to be adjusted
The corresponding weight of information can also be adjusted according to accuracy information is recited, other corresponding weights of state influence factor are for example
It can be determined, or can be determined according to other information by empirical value, the embodiment of the present invention does not limit this.
In other embodiments of the invention, for example, can also by by above-mentioned prompting number information, recite accuracy letter
In the input neural network scheduling algorithm model such as breath and state influence factor, obtain measuring the output result that user recites state.
Further, for same subscriber, reciting accuracy information may include: currently to recite accuracy and go through
History averagely recites accuracy, and reminding number information may include: that current prompting number and history averagely remind number, it can
The historical data of identical content is recited with reference to the user, it should be noted that history averagely recites accuracy and history is averagely reminded
Number each means average value of the same subscriber when reciting content identical with content is currently recited.It is described currently to recite accuracy
Accuracy is recited from recite start time to current time for user;The current prompting number be user since reciting when
It is carved into the prompting number at current time.
In another embodiment of the invention, reciting accuracy information can only include currently reciting accuracy;It reminds secondary
Number information can only include: current prompting number, i.e., do not consider the influence of historical information.
It in one embodiment of this invention, can be according to the ratio for currently reciting accuracy and history and averagely reciting accuracy
Value and the current ratio for reminding number and history averagely to remind number, that measures user recites state.
If currently recite accuracy averagely recited with history accuracy ratio it is bigger, it is current to remind number and history flat
Remind the ratio of number smaller, to recite state better then current.Conversely, explanation it is current to recite state poorer.
When weighting processing, can specifically realize in the following way:
Calculate it is described currently recite accuracy and history averagely recites the ratio of accuracy, obtain the first ratio;
The current ratio for reminding number and the history averagely to remind number is calculated, the second ratio is obtained;
Processing is weighted to first ratio, the second ratio and state influence factor, obtains first weighted value;
Wherein, the weight of first ratio can be determined according to accuracy is currently recited, or can also be according to current
It recites accuracy and history and averagely recites accuracy determination;The weight of second ratio can remind number true according to current
Fixed, or can also remind number and history that number is averagely reminded to determine according to current.
Illustratively, it is referred to following formula (1), calculates the first weighted value, indicate to use by first weighted value
Recite state in family.
Wherein, Sta1 indicates first weighted value, and p is currently to recite accuracy, and P is that history averagely recites accuracy, and n is
Current to remind number, N is that history averagely reminds number.Vol is currently to recite volume, Vol value can be by sound transducer
It obtains, volume is bigger, illustrates that current to recite state better.Noi indicates interference sound information, such as currently other people interference
Sound or other noise jammings, such as barking, vehicle whistle sound, by sound interference, the state of reciting of user will receive shadow
Sound may be deteriorated, and for example can indicate noiseless sound with 0 in formula (1), use 1 indicates interference sound.
Illustratively, it is referred to following formula (2), calculates the first weighted value, indicate to use by first weighted value
Recite state in family.
Sta2=wop-w1n+k2Vol-k3Noi (2)
Wherein, Sta2 indicates first weighted value, and p is currently to recite accuracy, and n is current prompting number.Vol is current
Volume is recited, Vol value can be obtained by sound transducer, and volume is bigger, illustrate that current to recite state better.Noi table
Show interference sound information, such as currently other people interference sound or other noise jammings, such as barking, vehicle whistle sound,
By sound interference, the state of reciting of user will receive influence and may be deteriorated, and can for example be indicated with 0 without dry in formula (1)
Sound is disturbed, use 1 indicates interference sound.
When user is when reciting, and detects the sound of non-user, can ask the user whether to continue to recite, such as
Export a text or speech prompt information.Linear discriminant analysis can be used in the sound for distinguishing user voice and non-user
(Probabilistic Linear Discriminant Analysis, abbreviation PLDA) algorithm is realized, passes through acquisition user's
The sound of sound and non-user trains voice recognition model, goes the sound for judging current detection to be by voice recognition model
The no sound for user.
Wherein, k2、k3It can determine based on experience value.
Reciting accuracy and remind that number is main feedback index due to user, in order to more preferable in the embodiment of the present invention
Reflection it is current recite state, w0、w1Value be real-time update.If current accuracy is higher, current that number is reminded to get over
Few, then state is better for current reciting, then current, to recite state by the two factor effects be also lower
's.If current accuracy is lower, current prompting number is more, illustrate it is current to recite state poorer, then reciting shape at this time
State is also bigger by the two factor effects.
W in above-mentioned formula (1) and formula (2)0、w1It can be obtained by following formula:
w0=e-p+k0
w1=loga(n+1)+k1
Wherein, k0、k1It can determine based on experience value, the value of a is the constant greater than preset frequency threshold value Thr2.
In one embodiment of this invention, different modes of reciting can be set in the electronic device, different recites mould
Formula determines that the mode for reciting state of user is different.Such as selection individual recites mode, it can going through the user under the mode
History averagely recites accuracy, history and averagely the factors such as number is reminded to take into account, i.e., will record and recite when user recites every time
The case where, for next time as reference.Such as it is also an option that commonality schemata, without considering the historical data of user under the mode.
In one embodiment of this invention, if monitoring, the user's currently recites accuracy less than preset accuracy
Threshold value, and/or, the current prompting number is greater than preset frequency threshold value, then exports third prompt information, the third prompt
Information is for prompting user to terminate to recite.
Specifically, meeting real-time monitoring user currently recites accuracy and current prompting is secondary during detection user recites
Number is greater than frequency threshold value Thr2, meeting less than accuracy threshold value Thr1 or current prompting number when user currently recites accuracy
It is too poor that directly prompt user was current recites state, it is proposed that and user still first reads several reattempt to again after text and recites, and
End is this time recited.
It, can be by reminding number, reciting the state of reciting that the factors such as accuracy determine user, Jin Ertong in the present embodiment
Cross reciting for user and state and recite the degree-of-difficulty factor of content, the prompt strategy determined more meets the demand of user, can and
When effectively provide the user with prompt, user can be improved and practice the effect recited, improve user experience.
On the basis of the above embodiments, further, it can also proceed as follows before step 101:
According to the uncommon word frequency for reciting content in next period, the difficulty system for reciting content in next period is determined
Number.
Specifically, uncommon word frequency is bigger, then the degree-of-difficulty factor for reciting content is bigger.
Further, in addition to considering uncommon word frequency, for the accuracy of degree-of-difficulty factor, it is also contemplated that other are difficult
Degree factor, such as recite the length of content, recite textbook belonging to content, recite the works classification of content, recite the language of content
Border etc., it is determined that the degree-of-difficulty factor for reciting content in next period can be accomplished in that
The corresponding difficulty of content is recited according to the uncommon word frequency for reciting content in next period and next period
Degree factor determines the degree-of-difficulty factor for reciting content in next period;Difficulty factor includes at least one of following factor: the back of user
Read aloud textbook belonging to content, the works classification for reciting content of user, the length for reciting content of user, user recite content
Context.
In one embodiment of this invention, can specifically degree-of-difficulty factor be determined as follows:
The uncommon word frequency for reciting content and next period to next period recite content pair
The difficulty factor answered is weighted processing, obtains the second weighted value, and using second weighted value as next period
Recite the degree-of-difficulty factor of content;Wherein, the corresponding weight of uncommon word frequency for reciting content in next period is root
It is determined according to the uncommon word frequency for reciting content in next period.
It in other embodiments of the invention, such as can also be by by above-mentioned uncommon word frequency and other difficulty
Factor etc. inputs in neural network scheduling algorithm model, obtains the output result for measuring degree-of-difficulty factor.
Illustratively, the degree-of-difficulty factor Dif for reciting content in next period can be determined by following formula (3):
Dif=w '0Fre+k’1Con+k’2Len+k’3Tex+k’4Typ (3)
Wherein, Fre indicates uncommon word frequency, and frequency is bigger, and will reciting content, (reciting for i.e. next period is interior
Hold) difficulty it is bigger, i.e., degree-of-difficulty factor is bigger.Con is the context for reciting content, and context is simpler, recites difficulty with regard to smaller,
I.e. degree-of-difficulty factor is smaller.Tex is to recite textbook belonging to content, and the senior class of primary school period may be belonged to by reciting content, can also
The junior one of middle school period can be belonged to, the different phase difficulty for reciting content not of the same grade is different, and grade is bigger, and difficulty is got over
Height, Tex can be measured by a numerical value.Typ is the works classification for reciting content, and works classification is temporarily divided into poem song, classical Chinese
Text and writings in the vernacular, such as the writing in classical Chinese recite difficulty maximum, and writings in the vernacular take second place, and poem song is easiest to, alternatively, can also pass through history
Error rate statistic obtains the corresponding difficulty of works classification, and Typ can be measured by a numerical value.Len is the length for reciting content,
Length is longer, and the difficulty recited is bigger, i.e., degree-of-difficulty factor is bigger.
Context recites personage described in content, plot or environment.One or one section of article think expression
Content is that perhaps things perhaps environment or has the plot that mixes of these types to people nothing but.So it is considered that language
Border is simpler, and the difficulty recited is smaller.Language ambience information can embody the overall difficulty information for reciting content, can be by that will recite
Text or current reciting text full text input neural network model obtain the score of language ambience information.
Wherein, k '1、k’2、k’3、k’4It can determine based on experience value.
Wherein, the corresponding weight of uncommon word frequency is referred to following formula and obtains:
w’0=eFre-1+k’0
Wherein, k '0It can determine based on experience value.
Wherein, above-mentioned uncommon word frequency can specifically obtain in the following way:
Textbook belonging to content is recited according to next period, determines rarely used word range;
Content is recited according to the rarely used word range and next period, is determined in the reciting of next period
The uncommon word frequency held.
So-called " rarely used word " is currently not no standard, refers herein to uncommon word in textbook, and not the same year
The rarely used word range of grade is also different, and wherein grade is lower, and rarely used word range is bigger;Grade is higher, and rarely used word range is smaller.
In the embodiment of the present invention the corresponding life of each grade can be tentatively formulated by collecting each grade text in the whole country
Rare word range.When reciting, first basis recites content and determines rarely used word range, then determines that next period recites the life of content
The rare word frequency of occurrences.
In the present embodiment, the difficulty system for reciting content can be determined by uncommon word frequency and other difficulty factors
Number, and then the degree-of-difficulty factor of content and is recited at state by reciting for user, the prompt strategy determined more meets the need of user
It asks, can timely and effectively provide the user with prompt, user can be improved and practice the effect recited, improve user experience.
On the basis of the above embodiments, further, the degree-of-difficulty factor of user recited state and recite content, it is main
It is used to adjust the several time thresholds for reciting prompt strategy.In step 101, determine that the prompt strategy in next period specifically can be with
In the following way:
According to the degree-of-difficulty factor for reciting content for reciting state and next period of the user, to current time threshold
It is adjusted, obtains corresponding time threshold of next period;
According to next period corresponding time threshold, the prompt strategy in next period is determined.
It further, can also be first according to the difficulty system for reciting content for reciting state and next period of the user
Number, determines regulation coefficient;
According to the time interval of regulation coefficient and adjustment, current time threshold is adjusted, obtains next period pair
The time threshold answered.
Such as time threshold includes first time threshold and second time threshold, first time threshold can be inquiry user
The time threshold for whether needing to prompt, second time threshold can be directly to the time threshold with user's suggestion content.
For example,
T′1=T1+a1*Δt1
T’2=T2+a2*Δt2
First time threshold T '1, second time threshold T '2It is the time threshold for the prompt that next period uses after adjusting, T1
And T2For currently used first time threshold and second time threshold.Wherein coefficient a1、a2Value indicates regulation coefficient, Δ t1、Δ
t2Indicate the time interval adjusted every time.
a1、a2The relationship of value and the degree-of-difficulty factor of user recited state and recite content may be expressed as:
a1=ln (Sta+1)+e-Dif;a2=ln (Sta+1)+e-Dif
Wherein, Sta indicates the state of reciting of user, and Dif indicates to recite the degree-of-difficulty factor of content.
It can be effectively according to the difficulty of user recited state and recite content by adjusting the time threshold of prompt
Coefficient adjustment prompt strategy.
Further, step 102 can specifically be realized in the following way:
If what the user recited gets stuck duration more than first time threshold, the first prompt information, institute are exported to user
The first prompt information is stated for inquiring whether the user needs to prompt;The duration that gets stuck is in the back for detecting the user
Start recording when reading aloud voice and reciting the text information mismatch of content;
If receiving the prompt response message of user, the adjacent content of text of text information at the current place of getting stuck of output,
To prompt the user.
In other embodiments of the invention, if receiving the instruction information without prompt of user's triggering, continue pair
The duration that gets stuck is recorded;
If in the adjacent text of text information that the duration that gets stuck more than second time threshold, exports place of currently getting stuck
Hold information, to prompt the user.
The duration specifically, timing at the time of " getting stuck " since user, i.e. record are got stuck.About " getting stuck ", citing
For, after user has correctly recited one section, the voice that analysis detection arrives is mismatched with the text for reciting content, then from having recited
Correct the last character terminates to start timing.
When getting stuck, duration is more than first time threshold, then can inquire whether the user needs to prompt, if user needs to prompt, then
It can be input operation instruction to equipment, specific content presentation can not needed to prompt by equipment to user, such as user, can also be to
Instruction information of the equipment input without prompt, then equipment will continue to match the recording of reciting of user, and to the duration that gets stuck
It is recorded.
When the duration that gets stuck is more than second time threshold, i.e. user does not recite out correct content also, and equipment will can directly be worked as
Before get stuck and locate adjacent word content information alert to user, such as can be by way of voice or image, prompting is got stuck
Locate adjacent word content, it, can root perhaps close to the explanation content of text or close to the core word etc. in text sentence
It is set according to demand.
Further, get stuck duration described in record, comprising:
If the text information successful match reciting voice and having recited with the user, stops recording described get stuck
Duration;
Voice is recited and the user does not recite the text information successful match of content if described, by the duration that gets stuck
It resets;
If it is described recite voice and text information that the user has recited it fails to match, and described recite voice and institute
It states user not reciting the text information of content it fails to match, then continues the duration that gets stuck described in record.
Specifically, reciting in view of user can jump, or the content recited is repeated, is recited when equipment detection obtains
Voice and recite content text it is unmatched when, can by the text of user recited voice and recited with front completion, and
The text (what i.e. entire chapter recited content does not recite text) that do not recite below scans for matching, and recites before being matched to interior
It not will be updated the duration that gets stuck when appearance, when being matched to the content that user does not recite, the duration that gets stuck is reset, and past since the content
After detected.
On the basis of the above embodiments, further, time threshold includes third time threshold, the side of the present embodiment
Method, further includes:
Record the user recites the time started;
If the difference for reciting the time started described in current time distance is more than third time threshold, output the second prompt letter
Breath, second prompt information is for prompting user to recite time-out.
Specifically, user is when reciting, what equipment can recorde user recites the time started, if the whole process recited
Duration, that is, the interval for reciting time started and current time is more than third time threshold, then prompts user to recite time-out, can be incited somebody to action
This result recited is recorded as reciting unsuccessfully.
Wherein, third time threshold also may include that by the state of reciting and can recite content in prompt strategy
Degree-of-difficulty factor determines.
Wherein, the adjustment mode of third time threshold is referred to the adjustment side of first time threshold and second time threshold
Formula.For example,
T’3=T3+a3*Δt3
a3=ln (Sta+1)+e-DifAbove-mentioned third time threshold T '3It is the time for the prompt that next period uses after adjusting
Threshold value, T3It is currently used third time threshold.Wherein coefficient a3Value indicates the ratio of adjustment, Δ t3What expression adjusted every time
Time interval.
Further in addition to that can actively can also initiate prompt by user by prompting strategy to prompt user and ask
It asks and user is prompted, the method for the present embodiment, further includes:
If receiving the prompt request of the user, according to the content of the prompt request, the 4th prompt information is exported,
To prompt the user.
Fig. 2 is the structure chart of electronic equipment embodiment provided by the invention, as shown in Fig. 2, the electronic equipment includes:
Processor 201, and, the memory 202 of the executable instruction for storage processor 201.
Above-mentioned component can be communicated by one or more bus.
Wherein, processor 201 is configured that
According to the degree-of-difficulty factor for reciting content for reciting state and next period of user, the prompt plan in next period is determined
Slightly;
Within next period, the user is prompted according to the prompt strategy.
In one possible implementation, processor 201 is configured that
According to reminding number information and reciting accuracy information, determine that the user's recites state.
In one possible implementation, processor 201 is configured that
According to the prompting number information, it is described recite accuracy information and state influence factor, determine the user
Recite state;The state influence factor, which includes at least one of the following:, currently recites volume, interference sound information and word speed.
In one possible implementation, processor 201 is configured that
It to the prompting number information, recites accuracy information and state influence factor is weighted processing, obtains first
Weighted value;What first weighted average was used to measure user recites state;Wherein, the weight for reminding number information is
It is determined according to the prompting number information, the weight for reciting accuracy information is that accuracy information is recited according to is true
Fixed.
In one possible implementation, processor 201 is configured that
According to the uncommon word frequency for reciting content in next period, determine next period recites content
Degree-of-difficulty factor.
In one possible implementation, processor 201 is configured that
Content is recited according to the uncommon word frequency for reciting content in next period and next period
Corresponding difficulty factor determines the degree-of-difficulty factor for reciting content in next period;The difficulty factor include it is following at least
One Xiang Yinsu: the user's recites textbook belonging to content, the works classification for reciting content of the user, the user
Recite the length of content, the context for reciting content of the user.
In one possible implementation, processor 201 is configured that
The uncommon word frequency for reciting content and next period to next period recite content pair
The difficulty factor answered is weighted processing, obtains the second weighted value, and using second weighted value as next period
Recite the degree-of-difficulty factor of content;Wherein, the corresponding weight of uncommon word frequency for reciting content in next period is root
It is determined according to the uncommon word frequency for reciting content in next period.
In one possible implementation, processor 201 is configured that
According to the degree-of-difficulty factor for reciting content for reciting state and next period of the user, to current time threshold
It is adjusted, obtains corresponding time threshold of next period;
According to next period corresponding time threshold, the prompt strategy in next period is determined.
In one possible implementation, processor 201 is configured that
If what the user recited gets stuck duration more than first time threshold, the first prompt information, institute are exported to user
The first prompt information is stated for inquiring whether the user needs to prompt;The duration that gets stuck is in the back for detecting the user
Start recording when reading aloud voice and reciting the text information mismatch of content;
If receiving the prompt response message of user, the adjacent content of text of text information at the current place of getting stuck of output,
To prompt the user.
In one possible implementation, processor 201 is configured that
If receiving the instruction information without prompt of user's triggering, continue to record the duration that gets stuck;
If in the adjacent text of text information that the duration that gets stuck more than second time threshold, exports place of currently getting stuck
Hold information, to prompt the user.
In one possible implementation, processor 201 is configured that
Record the user recites the time started;
If the difference for reciting the time started described in current time distance is more than third time threshold, output the second prompt letter
Breath, second prompt information is for prompting user to recite time-out.
In one possible implementation, which can also include display screen or audio component, display screen example
It can such as show that the text for reciting content and prompt information, audio component can be with the prompt informations etc. of output audio signal.
The electronic equipment of the present embodiment is corresponding in preceding method embodiment to execute via the executable instruction is executed
Method, specific implementation process may refer to preceding method embodiment, and details are not described herein again.
A kind of computer readable storage medium is also provided in the embodiment of the present invention, is stored thereon with computer program, it is described
Realize that corresponding method in preceding method embodiment, specific implementation process may refer to when computer program is executed by processor
Preceding method embodiment, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.The present invention is directed to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claims are pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by appended claims
System.
Claims (13)
1. a kind of auxiliary recites based reminding method characterized by comprising
According to the degree-of-difficulty factor for reciting content for reciting state and next period of user, the prompt strategy in next period is determined;
Within next period, the user is prompted according to the prompt strategy.
2. the method according to claim 1, wherein the back for reciting state and next period according to user
Before the degree-of-difficulty factor for reading aloud content, further includes:
According to reminding number information and reciting accuracy information, determine that the user's recites state.
3. according to the method described in claim 2, it is characterized in that, described believe according to prompting number information with accuracy is recited
Breath, determines that the user's recites state, comprising:
According to the prompting number information, it is described recite accuracy information and state influence factor, determine the back of the user
Read aloud state;The state influence factor, which includes at least one of the following:, currently recites volume, interference sound information and word speed.
4. according to the method described in claim 3, it is characterized in that, it is described according to the prompting number information, described recite just
True rate information and state influence factor, determine that the user's recites state, comprising:
It to the prompting number information, recites accuracy information and state influence factor is weighted processing, obtains the first weighting
Value;What first weighted average was used to measure user recites state;Wherein, the weight for reminding number information is basis
Described that number information is reminded to determine, the weight for reciting accuracy information is to recite accuracy information according to determine
's.
5. the method according to claim 1, wherein also being wrapped before the prompt strategy in the determination next period
It includes:
According to the uncommon word frequency for reciting content in next period, the difficulty for reciting content in next period is determined
Spend coefficient.
6. according to the method described in claim 5, it is characterized in that, described recite the uncommon of content according to next period
Word frequency determines the degree-of-difficulty factor for reciting content in next period, comprising:
It is corresponded to according to the content of reciting in the uncommon word frequency for reciting content in next period and next period
Difficulty factor, determine the degree-of-difficulty factor for reciting content in next period;The difficulty factor includes at least one of following
Factor: the user recite textbook belonging to content, the works classification for reciting content of the user, the user recite
The length of content, the user the context for reciting content.
7. according to the method described in claim 6, it is characterized in that, being gone out according to the rarely used word for reciting content in next period
Existing frequency and next period recite the corresponding difficulty factor of content, determine the difficulty for reciting content in next period
Spend coefficient, comprising:
The uncommon word frequency for reciting content and next period to next period to recite content corresponding
Difficulty factor is weighted processing, obtains the second weighted value, and using the second weighted value reciting as next period
The degree-of-difficulty factor of content;Wherein, the corresponding weight of uncommon word frequency for reciting content in next period is according to institute
State the uncommon word frequency determination for reciting content in next period.
8. method according to claim 1-7, which is characterized in that recite state and next period according to user
The degree-of-difficulty factor for reciting content, determine the prompt strategy in next period, comprising:
According to the degree-of-difficulty factor for reciting content for reciting state and next period of the user, current time threshold is carried out
Adjustment, obtains corresponding time threshold of next period;
According to next period corresponding time threshold, the prompt strategy in next period is determined.
9. according to the method described in claim 8, it is characterized in that, the time threshold includes: first time threshold, described
In next period, the user is prompted according to the prompt strategy, comprising:
If duration that the user recited get stuck exports the first prompt information more than first time threshold, to user, described the
One prompt information is for inquiring whether the user needs to prompt;The duration that gets stuck is to detect that the user's recite language
Start recording when sound and the text information for reciting content mismatch;
If receiving the prompt response message of user, the adjacent content of text of text information at the current place of getting stuck of output, with right
The user prompts.
10. according to the method described in claim 9, it is characterized in that, the time threshold further include: second time threshold, institute
State method further include:
If receiving the instruction information without prompt of user's triggering, continue to record the duration that gets stuck;
If the duration that gets stuck is more than second time threshold, the adjacent content of text letter of the text information at the current place of getting stuck of output
Breath, to prompt the user.
11. according to the method described in claim 8, it is characterized in that, the time threshold includes third time threshold, the side
Method further include:
Record the user recites the time started;
If the difference for reciting the time started described in current time distance is more than third time threshold, the second prompt information is exported,
Second prompt information is for prompting user to recite time-out.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Claim 1-11 described in any item methods are realized when being executed by processor.
13. a kind of electronic equipment characterized by comprising
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to require 1-11 described in any item via executing the executable instruction and carry out perform claim
Method.
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 true CN110310086A (en) | 2019-10-08 |
CN110310086B 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 (16)
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 |
CN101593438A (en) * | 2009-06-05 | 2009-12-02 | 创而新(中国)科技有限公司 | Auxiliary document display method and the system of reciting |
CN101814066A (en) * | 2009-02-23 | 2010-08-25 | 富士通株式会社 | Text reading difficulty judging device and method thereof |
CN101826263A (en) * | 2009-03-04 | 2010-09-08 | 中国科学院自动化研究所 | Objective standard based automatic oral evaluation system |
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 |
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 |
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 |
CN109523194A (en) * | 2018-12-14 | 2019-03-26 | 深圳市小柠檬教育科技有限公司 | Chinese reading capability comparison method, apparatus and readable storage medium storing program for executing |
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 |
-
2019
- 2019-06-06 CN CN201910490557.0A patent/CN110310086B/en active Active
Patent Citations (16)
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 |
CN101826263A (en) * | 2009-03-04 | 2010-09-08 | 中国科学院自动化研究所 | Objective standard based automatic oral evaluation system |
CN101593438A (en) * | 2009-06-05 | 2009-12-02 | 创而新(中国)科技有限公司 | Auxiliary document display method and the system of reciting |
CN103971675B (en) * | 2013-01-29 | 2016-03-02 | 腾讯科技(深圳)有限公司 | Automatic speech recognition method and system |
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 |
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 |
CN109523194A (en) * | 2018-12-14 | 2019-03-26 | 深圳市小柠檬教育科技有限公司 | Chinese reading capability comparison method, apparatus and readable storage medium storing program for executing |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN110310086B (en) | 2022-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI321313B (en) | Apparatus and method to reduce recognization errors through context relations among dialogue turns | |
CN109271585B (en) | Information pushing method and family education equipment | |
CN110148427A (en) | Audio-frequency processing method, device, system, storage medium, terminal and server | |
CN110265040A (en) | Training method, device, storage medium and the electronic equipment of sound-groove model | |
US8234114B2 (en) | Speech interactive system and method | |
CN107316638A (en) | A kind of poem recites evaluating method and system, a kind of terminal and storage medium | |
CN108389440A (en) | A kind of speech playing method, device and voice playing equipment based on microphone | |
CN110070857B (en) | Model parameter adjusting method and device of voice awakening model and voice equipment | |
CN109256115A (en) | A kind of speech detection system and method for intelligent appliance | |
CN111833853A (en) | Voice processing method and device, electronic equipment and computer readable storage medium | |
CN108053839A (en) | A kind of methods of exhibiting and microphone apparatus of language exercise achievement | |
CN106898176A (en) | Analysis of the students method, analysis of the students server and point-of-reading system based on talking pen | |
CN110544468B (en) | Application awakening method and device, storage medium and electronic equipment | |
CN110147936A (en) | Service evaluation method, apparatus based on Emotion identification, storage medium | |
CN110459242A (en) | Change of voice detection method, terminal and computer readable storage medium | |
CN110473435A (en) | A kind of the word assistant learning system and method for the quantification with learning cycle | |
WO2020068203A1 (en) | Gathering data in a communication system | |
CN108766431A (en) | It is a kind of that method and electronic equipment are automatically waken up based on speech recognition | |
WO2019052430A1 (en) | Method and apparatus for self-service of mobile terminal | |
CN106600237B (en) | Method and device for assisting in memorizing traditional Chinese medicine books | |
CN110310086A (en) | Auxiliary recites based reminding method, equipment and storage medium | |
JP2006230548A (en) | Physical condition judging device and its program | |
CN112053205A (en) | Product recommendation method and device through robot emotion recognition | |
US20210056957A1 (en) | Ability Classification | |
JP5320152B2 (en) | Problem information output device, problem information output method, and program |
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 |
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. |
|
CP03 | Change of name, title or address |