CN110047508A - Voice recording method, device, computer equipment and storage medium - Google Patents
Voice recording method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110047508A CN110047508A CN201910183521.8A CN201910183521A CN110047508A CN 110047508 A CN110047508 A CN 110047508A CN 201910183521 A CN201910183521 A CN 201910183521A CN 110047508 A CN110047508 A CN 110047508A
- Authority
- CN
- China
- Prior art keywords
- voice
- voice record
- score value
- record
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 230000036651 mood Effects 0.000 claims abstract description 68
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012552 review Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 4
- 208000001491 myopia Diseases 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 206010016275 Fear Diseases 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
- H04L51/10—Multimedia information
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Psychiatry (AREA)
- Hospice & Palliative Care (AREA)
- General Health & Medical Sciences (AREA)
- Child & Adolescent Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to speech analysis field more particularly to a kind of voice recording method, device, computer equipment and storage mediums.Voice recording method includes: the voice record for obtaining user and uploading, and is identified according to the classification of voice mood in voice record to voice record, will be stored with the voice record of same mark into corresponding memory node；The comment score value for obtaining voice record judges to comment on score value for front score value or negative score value；The final scoring of voice record is calculated according to front score value and negative score value；The recommendation score of voice record is calculated according to front score value, comprehensive final scoring and recommendation score judge whether voice record is worth recommending, by recommendable voice record preferential recommendation to user.The present invention records the daily mood of user and activity by way of voice, enriches friend-making mode, meets the friend-making demand and record demand and the demand to other people story curiosities of part population.
Description
Technical field
The present invention relates to speech analysis fields, and in particular to voice recording method, device, computer equipment and storage are situated between
Matter.
Background technique
Instant messaging (Instant messaging, abbreviation IM) is a terminal service, and referring to allows two people or more people to make
The communication software exchanged with the instant transmitting message language in network, archives, voice with video.Instant messaging is divided by usage
Enterprise instant communication and website instant messaging can be divided into mobile telephone instant communication and PC instant messaging according to the object of loading again.Mesh
It is preceding in the market using more for mobile telephone instant communication, mainly include wechat, QQ and microblogging etc., the interaction of mobile telephone instant communication
Mode is mainly based upon text, phrase sound, short-sighted frequency or real-time video, user in addition to use text, phrase sound, short-sighted frequency or
Except the mode of person's real-time video is exchanged with more people, also day can be recorded by way of text, picture or short-sighted frequency
Normal mood and activity.
Currently on the market for recording user's daily life and movable main carriers include text, picture and short-sighted frequency,
Lack the recording mode of pure sound-type, thiner recording mode is not able to satisfy the friend-making demand and record of part population
Demand.
Summary of the invention
Based on this, it is necessary to for lacking the recording mode of pure sound-type currently on the market, be not able to satisfy part population
The problems such as needing the demand of richer recording mode provides a kind of voice recording method, device, computer equipment and storage and is situated between
Matter.
A kind of voice recording method, includes the following steps:
Step 1: the voice record that user uploads is obtained, according to the classification of voice mood in the voice record to described
Voice record is identified, and will be stored with the voice record of the same mark into corresponding memory node；
Step 2: obtaining the comment score value of the voice record, judges to comment on score value for front score value or negative score value；
Step 3: the final scoring of the voice record is calculated according to the front score value and the negative score value；
Step 4: calculating the recommendation score of the voice record according to the front score value, the comprehensive final scoring and
The recommendation score judges whether the voice record is worth recommending, and the recommendable voice record preferential recommendation is given
User.
In a kind of possible embodiment, the step 1 includes:
Obtain the classification of the voice mood included in the voice record that user uploads；
The voice record is identified according to the classification of the voice mood；
The voice record with the same mark is stored in memory node corresponding with the mark.
It is described to obtain the voice feelings included in the voice record that user uploads in a kind of possible embodiment
The classification of thread, comprising:
Entrance, which is uploaded, by the preset voice record obtains the voice record that user uploads；
Judge whether user passes through preset voice mood selection entrance when uploading the voice record and select institute's predicate
Sound records the classification of the corresponding voice mood, when user when uploading the voice record the non-selected voice mood
When, by identifying the word speed and intonation of the voice record, text is converted by the voice record, according to the word speed, institute
Predicate reconciles the text and determines the voice mood of the voice record；Voice is determined according to the voice mood of above-mentioned identification
The classification of mood.
In a kind of possible embodiment, the step 2 includes:
Obtain all comment score values of the voice record；
All comment score values are compared with preset scoring threshold one by one, will wherein be higher than the scoring threshold
The comment score value be defined as front score value, will wherein lower than the scoring threshold the comment score value be defined as negatively point
Value.
In a kind of possible embodiment, the step 3 includes:
The quantity of the front score value of the voice record and the quantity of the negative score value are obtained, the voice is calculated
The final scoring of record, calculation formula are as follows:
In above formula, SiIndicate the final scoring of voice record i, MiIndicate the quantity of the front score value of voice record i, NiTable
Show the quantity of the negative score value of voice record i, TiIndicate the sum of the quantity of front score value and negative score value.
In a kind of possible embodiment, the step 4 includes:
The quantity of the comment score value of the voice record and the quantity of the front score value are obtained, the voice is calculated
The front score value rate of record, calculation formula are as follows:
In above formula, PiIndicate the front score value rate of voice record i, MiIndicate the quantity of the front score value of voice record i, Ti
Indicate the quantity of the comment score value of voice record i；
The recommendation score of the voice record is calculated according to the front score value rate；
The final scoring and the recommendation score are compared with preset scoring threshold value and recommendation threshold value respectively, when
The final scoring judges the voice record higher than the scoring threshold value and when the recommendation score is higher than the recommendation threshold value
It is worth recommending, by the recommendable voice record preferential recommendation to user.
In a kind of possible embodiment, the recommendation score that the voice record is calculated according to the front score value rate,
Include:
The front score value rate for obtaining the voice record, calculates the recommendation score of the voice record, calculation formula
It is as follows:In formula, niIndicate the recommendation score of voice record i, PiIndicate the front score value of voice record i
Rate, A, B are constant.
Based on identical design, present invention also provides a kind of voice recorder, the voice recorder includes:
Mark module is set as obtaining the voice record that user uploads, according to the class of voice mood in the voice record
It is other that the voice record is identified, it will be with the voice record of same mark storage to corresponding memory node
In；
Obtain module, be set as obtaining the comment score value of the voice record, and judge to comment on score value for front score value or
Negative score value；
Computing module is set as calculating the most final review of the voice record according to the front score value and the negative score value
Point；
Recommending module is set as calculating the recommendation score of the voice record according to the front score value, and synthesis is described most
Final review point and the recommendation score judge whether the voice record is worth recommending, and the recommendable voice record is excellent
First recommend user.
Based on identical design, the embodiment of the present application also provides a kind of computer equipment, and the computer equipment includes depositing
Reservoir and processor are stored with computer-readable instruction in the memory, and the computer-readable instruction is one or more
When the processor executes, so that the step of one or more processors execute above-mentioned voice recording method.
Based on the same technical idea, the embodiment of the present application also provides a kind of storages for being stored with computer-readable instruction
Medium, when the computer-readable instruction is executed by one or more processors, so that one or more processors execute
The step of predicate voice recording method as above.
Above-mentioned voice recording method, device, computer equipment and storage medium are remembered by obtaining the voice that user uploads
Record, is identified the voice record according to the classification of voice mood in the voice record, will have the same mark
The voice record store into corresponding memory node；The comment score value for obtaining the voice record judges to comment on score value
For front score value or negative score value；The most final review of the voice record is calculated according to the front score value and the negative score value
Point；The recommendation score of the voice record, the comprehensive final scoring and the recommendation score are calculated according to the front score value
Judge whether the voice record is worth recommending, and by the recommendable voice record preferential recommendation to user.Therefore, originally
Application records the daily mood of user and activity by way of voice, enriches friend-making mode, meets the friend-making of part population
Demand and record demand and the demand to other people story curiosities.
Detailed description of the invention
Fig. 1 is the flow chart of the application voice recording method in one embodiment；
Fig. 2 is that the application calculates the flow chart finally to score in one embodiment；
Fig. 3 is the flow chart that the application recommends voice record in one embodiment；
Fig. 4 is the structural block diagram of the application voice recorder in one embodiment.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Fig. 1 is the flow chart for the voice recording method that the application provides in one embodiment, as shown in the figure, comprising:
S1, the voice record that user uploads is obtained, identifies the voice mood in the voice record, remembered according to the voice
The classification of voice mood is identified the voice record in record, will store with the voice record of the same mark
Into corresponding memory node；
The voice record obtained in this step daily, mood, narration information comprising user, while default mood class
Not, the corresponding voice mood is selected when uploading the voice record for user.
If user has selected the voice mood, root from the voice mood classification when uploading the voice record
The voice record is identified according to the classification of voice mood corresponding to selected voice mood；If user is uploading institute
Non-selected voice mood when voice record is stated, the word speed and intonation of the voice record are identified by speech recognition technology,
And text is converted by the voice record by Voice Conversion Techniques, institute is determined according to the word speed and intonation and the text
The voice mood for stating voice record is identified the voice record further according to the classification of the voice mood.It is described
After the completion of voice mood mark, it will store with the voice record of the same mark into corresponding memory node.
S2, the comment score value for obtaining the voice record judge to comment on score value for front score value or negative score value；
After the voice record uploads successfully, other users are after listening and taking the voice record, to the voice record
Provide the comment score value.The comment score value is compared with scoring threshold, when the comment score value is higher than the marking
When threshold value, defining the comment score value is the front score value, when the comment score value is lower than the scoring threshold, defines institute
Commentary opinion score value is the negative score value.
S3, the final scoring that the voice record is calculated according to the front score value and the negative score value；
By obtaining front score value described in the comment score value of the voice record and negative point described in this step
The quantity of value, calculates the final scoring of the voice record according to formula (1), formula (1) as follows,
In formula (1), SiIndicate the final scoring of voice record i, MiIndicate the quantity of the front score value of voice record i, Ni
Indicate the quantity of the negative score value of voice record i, TiIndicate the sum of the quantity of front score value and negative score value；Such as voice record
The front score value of E " participate in international conference, and shake hands in meeting with Ma Yun " has 600, and the negative score value has 200
Item, then can be calculated its described final scoring according to formula is 0.5.
S4, the recommendation score that the voice record is calculated according to the front score value, according to preset rules in conjunction with it is described most
Final review point and the recommendation score judge whether the voice record is worth recommending, and by the recommendable voice record
Preferential recommendation is to user；
The front score value of the voice record calculates the front score value rate of the voice record, according to the front point
Value rate calculates the recommendation score of the voice record, and the comprehensive final scoring and the recommendation score are from preset rules
Judge whether the voice record is worth recommending.The preset rules may be configured as: successfully uploading and selects for each first
The disclosed voice record matches an asterisk；Then the asterisk of the voice record is primarily determined according to final score
Color, preset the final scoring for [0-0.5) asterisk in stage be yellow, the final scoring is [0.5-1] stage
Asterisk is green；The recommendation score for the voice record that asterisk color is green is compared with threshold value is recommended again,
When the recommendation score is higher than the recommendation threshold value, the asterisk of the voice record is adjusted to red, when the recommendation is commented
When dividing lower than the recommendation threshold value, the color of the asterisk of the voice record is not adjusted；It is finally red institute by asterisk color
Voice record preferential recommendation is stated to user.
The diversity for enriching user's interactive mode in the present embodiment by the sharing mode of the voice record, passes through meter
The final scoring and the recommendation score for calculating the voice record, improve the accuracy for recommending the voice record.
In one embodiment, the voice record that the S1, acquisition user upload, identifies the voice in the voice record
Mood is identified the voice record according to the classification of voice mood in the voice record, will have the same mark
The voice record known is stored into corresponding memory node, comprising:
S101, the voice mood included in the voice record that user uploads is obtained；
Voice mood classification is set for user's selection by uploading the inlet of the voice record in user in this step:
The voice mood classification includes happiness, anger, sorrow, think of, compassion, fears, frightened seven major class, and it is a variety of for being finely divided again under this seven major class
Language mood, for example, " happiness " include: it is happy, happy, pleasant, joyful, happy, proud, meet, be excited, pride, it is gratified, glad,
Be satisfied with, laugh, laughing wildly, is happy, is happy etc..
If user has selected the voice mood from voice mood classification when uploading the voice record, directly
It connects and obtains corresponding classification according to the voice mood；If user is when uploading the voice record not from the voice mood
The voice mood is selected in classification, then identifies the word speed and intonation of the voice record by speech recognition technology, led to
It crosses Voice Conversion Techniques and the voice record is converted into text, further according to described in the word speed and intonation, text determination
The voice mood of voice record.
For example user A has recorded a voice record about " participate in international conference, and shake hands in meeting with Ma Yun "
The voice mood C of " excited, excitement " may be selected when upload publication for voice record E by E, user A；If user A is being uploaded
Non-selected voice mood when voice record E, convert voice record E to recognize that voice record A tells about after text be "
Met Ma Yun in certain national meeting and carried out hearty handshake with horse cloud " thing, and identify the word speed in voice record E
Comparatively fast, intonation is higher, and comprehensive word speed, intonation can determine that the corresponding voice mood of voice record E is with the word content told about
" excited, excitement ".
S102, after being identified to the voice mood of the voice record, according to the classification pair of the voice mood
The voice record is identified；
The classification of the voice mood in this step according to the voice record is identified, such as voice record E " ginseng
Adding international conference, and shake hands in meeting with Ma Yun " corresponding voice mood is " excited, excitement ", in voice mood classification
The classification belonged to is " happiness ", then voice record E is identified as " happiness ".
S103, the voice record with the same mark is stored in storage section corresponding with the class indication
Point in；The voice record is stored into corresponding memory node according to the mark of the voice record in this step, such as
Voice record E's is identified as " happiness ", and memory node F is used to store the voice record of " happiness " in database, then by voice
Record E is stored in memory node F.
The present embodiment is by being voice record described in subsequent recommendation to classification storage is carried out again after voice record mark
It provides the foundation.
Fig. 2 is the flow chart that the calculating that the application provides in one embodiment is finally scored, as shown, the S2,
The comment score value for obtaining the voice record judges to comment on score value for front score value or negative score value, comprising:
S201, all comment score values of voice record are obtained；
It obtains and successfully uploads and the comment score data of the disclosed voice record, user take institute listening in this step
Comment marking can be carried out after voice record to the voice record by stating, for example, user listened to user A publication about " participating in
After the voice record E of international conference, and shaking hands in meeting with Ma Yun ", text can be carried out to the voice record of user A and commented
By or voice remark, user B carries out marking to the voice record of user A as 7 points, and user C is to institute's predicate of user A
Sound record marking is 4 points.
S202, all comment score values are compared with preset scoring threshold one by one, will be wherein higher than described beat
The comment score value of point threshold value is defined as front score value, and the comment score value for being wherein lower than the scoring threshold is defined as
Negative score value；
After being compared the comment score value with the scoring threshold in this step, defines and wrapped in the comment score value
The front score value and the negative score value contained, such as when scoring threshold is defined as 5, if user B remembers the voice of user A
Recording E marking is 7 timesharing, then the marking of user B is front marking, and user C is 4 points to the voice record E marking of user A, then
The marking of user C is negative marking.
It is subsequent by calculating the final scoring of the voice record after the acquisition comment score value in the present embodiment
The voice record is recommended to provide the foundation.
Fig. 3 is the flow chart for the recommendation voice record that the application provides in one embodiment, as shown, the S4,
The recommendation score of the voice record, the comprehensive final scoring and recommendation score judgement are calculated according to the front score value
Whether the voice record, which is worth, is recommended, and by the recommendable voice record preferential recommendation to user, comprising:
S401, obtain the voice record the comment score value quantity and the front score value quantity, calculate institute
The front score value rate of voice record is stated, shown in calculation formula such as formula (2)；
In formula (2), PiIndicate the front score value rate of voice record i, MiIndicate the quantity of the front score value of voice record i,
TiIndicate the quantity of the comment score value of voice record i；
The quantity of the comment score value for the voice record that will acquire in this step and the quantity of the front score value,
It substitutes into formula (2) and calculates the front score value rate of the voice record.
S402, the recommendation score that the voice record is calculated according to the front score value rate；
Remembering as a result, calculating the voice further according to formula for the front score value rate being calculated is obtained in this step
The recommendation score of record.Shown in calculation formula such as formula (3)；
In formula (3), niIndicate the recommendation score of voice record i, PiIndicate the front score value rate of voice record i, A, B are
Constant；
The calculated result of the front score value rate of calculating is obtained in this step, is substituted into formula (3) described in being calculated
Recommendation score, when wherein A value 6.78, B value 14.43, such as the front score value rate are 0.6, what is be calculated described is pushed away
Recommending scoring is 4.24.
The recommendation score is calculated by the front score value rate in the present embodiment, for the subsequent judgement voice record
Whether it is worth recommending to provide the foundation.
S403, the final scoring and the recommendation score are compared with preset scoring threshold value and recommendation threshold value respectively
Compared with judging institute's predicate when the final scoring is higher than the scoring threshold value and the recommendation score higher than the recommendation threshold value
Sound record value must be recommended, by the recommendable voice record preferential recommendation to user；
The final scoring is compared with the scoring threshold value first in this step, when the final scoring is higher than institute
When commentary divides threshold value, the asterisk color of the voice record is adjusted to green, when the voice record is lower than the scoring threshold
When value, the asterisk color of the voice record is yellow, is being the recommendation of the green voice record by asterisk color
Scoring is compared with the recommendation threshold value, and when the recommendation score is higher than the recommendation threshold value, adjustment asterisk color is red
Color does not change asterisk color when the recommendation score is lower than the recommendation threshold value, is the red voice by asterisk color
Record is judged as worth recommendation, by the recommendable voice record preferential recommendation to user.
By calculating the scoring of the voice record to judge whether the voice record is worth recommending in the present embodiment,
Improve the accuracy for recommending the voice record.
Based on identical design, present invention also provides a kind of voice recorders, as shown in figure 4, shown voice record
Device includes mark module, obtains module, computing module and recommending module, in which: mark module is set as obtaining user's upload
Voice record, the voice record is identified according to the classification of voice mood in the voice record, will be had same
The voice record of the mark is stored into corresponding memory node；Module is obtained, is set as obtaining the voice record
Comment score value, judge the comment score value for front score value or negative score value；Computing module is set as according to the front point
Value and the negative score value calculate the final scoring of the voice record；Recommending module is set as according to the front score value meter
The recommendation score of the voice record is calculated, the comprehensive final scoring and the recommendation score judge whether the voice record is worth
It must recommend, and by the recommendable voice record preferential recommendation to user.
In one embodiment, the mark module includes:
Class location is obtained, is set as obtaining the voice mood included in the voice record that user uploads
Classification；
Class indication unit is set as being identified the voice record according to the classification of the voice mood；
Classification storage unit is set as being stored in the voice record with the same mark and the mark pair
In the memory node answered.
In one embodiment, the acquisition class location includes:
Pre-set categories unit is obtained, is set as uploading the institute that entrance obtains user's upload by the preset voice record
State voice record；
Intelligent recognition class location is set as judging whether user passes through preset voice when uploading the voice record
Mood selection entrance selectes the classification of the corresponding voice mood of the voice record, when user is uploading the voice record
When the non-selected voice mood when, by identifying the word speed and intonation of the voice record, convert the voice record to
Text determines the voice mood of the voice record according to the word speed, the intonation and the text；According to above-mentioned knowledge
Other voice mood determines the classification of voice mood.
In one embodiment, the acquisition module includes:
Score value unit is obtained, is set as obtaining all comment score values of the voice record；
Compare score value unit, is set as all comment score values being compared with preset scoring threshold one by one, it will
It wherein is defined as front score value higher than the comment score value of the scoring threshold, will be wherein lower than described in the scoring threshold
Comment score value is defined as negative score value；
The computing module includes that level-one calculates scoring unit, is set as according to the front score value and the negative score value
The final scoring of the voice record is calculated.
Shown in calculation formula such as formula (1)；
In formula (1), SiIndicate the final scoring of voice record i, MiIndicate the quantity of the front score value of voice record i, Ni
Indicate the quantity of the negative score value of voice record i, TiIndicate the sum of the quantity of front score value and negative score value.
In one embodiment, the recommending module includes:
Calculate front score value rate unit, be set as obtaining the quantity of the comment score value of the voice record and it is described just
The quantity of face score value calculates the front score value rate of the voice record, shown in calculation formula such as formula (2)；
In formula (2), PiIndicate the front score value rate of voice record i, MiIndicate the quantity of the front score value of voice record i,
TiIndicate the quantity of the comment score value of voice record i；
Recommendation score unit is calculated, is set as calculating the recommendation score of the voice record according to the front score value rate；
Recommendation unit, be set as by it is described it is final scoring and the recommendation score respectively with preset scoring threshold value and recommendation
Threshold value is compared, when the final scoring is higher than the scoring threshold value and the recommendation score is higher than the recommendation threshold value,
Judge that the voice record is worth recommending, by the recommendable voice record preferential recommendation to user.
In one embodiment, the calculating recommendation score unit includes:
Second level calculates scoring unit, is set as obtaining the front score value rate of the voice record, calculates the voice
The recommendation score of record, shown in calculation formula such as formula (3)；
In formula (3), niIndicate the recommendation score of voice record i, PiIndicate the front score value rate of voice record i, A, B are
Constant.
Based on the same technical idea, the embodiment of the present application also provides a kind of computer equipment, the computer equipment packet
Memory and processor are included, computer-readable instruction is stored in memory, computer-readable instruction is handled by one or more
When device executes, so that one or more processors realize the voice in the various embodiments described above when executing computer-readable instruction
The step of recording method.
Based on the same technical idea, the embodiment of the present application also provides a kind of storage Jie for being stored with computer-readable instruction
Matter, when the computer-readable instruction is executed by one or more processors, so that one or more processors execute institute
The step of realizing the voice recording method in the various embodiments described above when stating computer-readable instruction.Wherein, the storage medium can
Think non-volatile memory medium.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
Some exemplary embodiments of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but
It cannot be construed as a limitation to the scope of the present invention.It should be pointed out that for the ordinary skill people of this field
For member, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to of the invention
Protection scope.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of voice recording method characterized by comprising
Step 1: the voice record that user uploads is obtained, according to the classification of voice mood in the voice record to the voice
Record is identified, and will be stored with the voice record of the same mark into corresponding memory node；
Step 2: obtaining the comment score value of the voice record, judges to comment on score value for front score value or negative score value；
Step 3: the final scoring of the voice record is calculated according to the front score value and the negative score value；
Step 4: calculating the recommendation score of the voice record according to the front score value, the comprehensive final scoring and described
Recommendation score judges whether the voice record is worth recommending, and by the recommendable voice record preferential recommendation to use
Family.
2. a kind of voice recording method as described in claim 1, which is characterized in that the step 1 includes:
Obtain the classification of the voice mood included in the voice record that user uploads；
The voice record is identified according to the classification of the voice mood；
The voice record with the same mark is stored in memory node corresponding with the mark.
3. a kind of voice recording method as claimed in claim 2, which is characterized in that the voice for obtaining user and uploading
The classification of the voice mood included in record, comprising:
Entrance, which is uploaded, by the preset voice record obtains the voice record that user uploads；
Judge whether user passes through preset voice mood selection entrance when uploading the voice record and select the voice note
The corresponding voice mood is recorded, when user's non-selected voice mood when uploading the voice record, passes through identification
The voice record is converted text by the word speed and intonation of the voice record, according to the word speed, the intonation and described
Text determines the voice mood of the voice record；The classification of voice mood is determined according to the voice mood of above-mentioned identification.
4. a kind of voice recording method as described in claim 1, which is characterized in that the step 2 includes:
Obtain all comment score values of the voice record；
All comment score values are compared with preset scoring threshold one by one, will wherein be higher than the institute of the scoring threshold
Commentary opinion score value is defined as front score value, and the comment score value for being wherein lower than the scoring threshold is defined as negative score value.
5. a kind of voice recording method as claimed in claim 4, which is characterized in that the step 3 includes:
The quantity of the front score value of the voice record and the quantity of the negative score value are obtained, the voice record is calculated
The final scoring, calculation formula are as follows:
In above formula, SiIndicate the final scoring of voice record i, MiIndicate the quantity of the front score value of voice record i, NiIndicate language
Sound records the quantity of the negative score value of i, TiIndicate the sum of the quantity of front score value and negative score value.
6. a kind of voice recording method as described in claim 1, which is characterized in that described to include: according to the step 4
The quantity of the comment score value of the voice record and the quantity of the front score value are obtained, the voice record is calculated
Front score value rate, calculation formula is as follows:
In above formula, PiIndicate the front score value rate of voice record i, MiIndicate the quantity of the front score value of voice record i, TiIt indicates
The quantity of the comment score value of voice record i；
The recommendation score of the voice record is calculated according to the front score value rate；
The final scoring and the recommendation score are compared with preset scoring threshold value and recommendation threshold value respectively, when described
Final scoring judges that the voice record is worth higher than the scoring threshold value and when the recommendation score is higher than the recommendation threshold value
Recommend, by the recommendable voice record preferential recommendation to user.
7. a kind of voice recording method as claimed in claim 6, which is characterized in that described to be calculated according to the front score value rate
The recommendation score of the voice record, comprising:
The front score value rate of the voice record is obtained, the recommendation score calculation formula for calculating the voice record is as follows:In formula, niIndicate the recommendation score of voice record i, PiIndicate the front score value rate of voice record i,
A, B is constant.
8. a kind of voice recorder characterized by comprising
Mark module is set as obtaining the voice record that user uploads, according to the classification pair of voice mood in the voice record
The voice record is identified, and will be stored with the voice record of the same mark into corresponding memory node；
Obtain module, be set as obtaining the comment score value of the voice record, and judge comment on score value be front score value or negatively
Score value；
Computing module is set as calculating the final scoring of the voice record according to the front score value and the negative score value；
Recommending module is set as calculating the recommendation score of the voice record according to the front score value, the comprehensive most final review
Divide and the recommendation score judges whether the voice record is worth recommending, and the recommendable voice record is preferentially pushed away
It recommends to user.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by one or more processors, so that one or more processors execute such as right
It is required that the step of voice recording method described in any one of 1 to 7.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors execute the voice recording method as described in any one of claims 1 to 7
The step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910183521.8A CN110047508A (en) | 2019-03-12 | 2019-03-12 | Voice recording method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910183521.8A CN110047508A (en) | 2019-03-12 | 2019-03-12 | Voice recording method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110047508A true CN110047508A (en) | 2019-07-23 |
Family
ID=67274758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910183521.8A Pending CN110047508A (en) | 2019-03-12 | 2019-03-12 | Voice recording method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110047508A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110619868A (en) * | 2019-08-29 | 2019-12-27 | 深圳市优必选科技股份有限公司 | Voice assistant optimization method, voice assistant optimization device and intelligent equipment |
| CN112905874A (en) * | 2019-12-03 | 2021-06-04 | 贝壳技术有限公司 | House resource retrieval method, device, storage medium and equipment |
| CN114519596A (en) * | 2020-11-18 | 2022-05-20 | 中国移动通信有限公司研究院 | Data processing method, device and equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101938522A (en) * | 2010-08-31 | 2011-01-05 | 中华电信股份有限公司 | Method for voice microblog service |
| US20110040790A1 (en) * | 2009-08-12 | 2011-02-17 | Kei Tateno | Information processing apparatus, method for processing information, and program |
| CN104156390A (en) * | 2014-07-07 | 2014-11-19 | 乐视网信息技术（北京）股份有限公司 | Comment recommendation method and system |
| CN104573114A (en) * | 2015-02-04 | 2015-04-29 | 苏州大学 | Music classification method and device |
| CN108039181A (en) * | 2017-11-02 | 2018-05-15 | 北京捷通华声科技股份有限公司 | The emotion information analysis method and device of a kind of voice signal |
| CN109087670A (en) * | 2018-08-30 | 2018-12-25 | 西安闻泰电子科技有限公司 | Mood analysis method, system, server and storage medium |
| CN109241415A (en) * | 2018-08-20 | 2019-01-18 | 平安科技（深圳）有限公司 | Item recommendation method, device, computer equipment and storage medium |
| CN109271599A (en) * | 2018-08-13 | 2019-01-25 | 百度在线网络技术（北京）有限公司 | Data sharing method, equipment and storage medium |
-
2019
- 2019-03-12 CN CN201910183521.8A patent/CN110047508A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110040790A1 (en) * | 2009-08-12 | 2011-02-17 | Kei Tateno | Information processing apparatus, method for processing information, and program |
| CN101938522A (en) * | 2010-08-31 | 2011-01-05 | 中华电信股份有限公司 | Method for voice microblog service |
| CN104156390A (en) * | 2014-07-07 | 2014-11-19 | 乐视网信息技术（北京）股份有限公司 | Comment recommendation method and system |
| CN104573114A (en) * | 2015-02-04 | 2015-04-29 | 苏州大学 | Music classification method and device |
| CN108039181A (en) * | 2017-11-02 | 2018-05-15 | 北京捷通华声科技股份有限公司 | The emotion information analysis method and device of a kind of voice signal |
| CN109271599A (en) * | 2018-08-13 | 2019-01-25 | 百度在线网络技术（北京）有限公司 | Data sharing method, equipment and storage medium |
| CN109241415A (en) * | 2018-08-20 | 2019-01-18 | 平安科技（深圳）有限公司 | Item recommendation method, device, computer equipment and storage medium |
| CN109087670A (en) * | 2018-08-30 | 2018-12-25 | 西安闻泰电子科技有限公司 | Mood analysis method, system, server and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110619868A (en) * | 2019-08-29 | 2019-12-27 | 深圳市优必选科技股份有限公司 | Voice assistant optimization method, voice assistant optimization device and intelligent equipment |
| CN110619868B (en) * | 2019-08-29 | 2021-12-17 | 深圳市优必选科技股份有限公司 | Voice assistant optimization method, voice assistant optimization device and intelligent equipment |
| CN112905874A (en) * | 2019-12-03 | 2021-06-04 | 贝壳技术有限公司 | House resource retrieval method, device, storage medium and equipment |
| CN112905874B (en) * | 2019-12-03 | 2021-11-12 | 贝壳找房(北京)科技有限公司 | House resource retrieval method, device, storage medium and equipment |
| CN114519596A (en) * | 2020-11-18 | 2022-05-20 | 中国移动通信有限公司研究院 | Data processing method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210297275A1 (en) | Organizing and aggregating meetings into threaded representations | |
| US20210407520A1 (en) | Detecting user identity in shared audio source contexts | |
| US10366707B2 (en) | Performing cognitive operations based on an aggregate user model of personality traits of users | |
| US20210097502A1 (en) | Automatically determining and presenting personalized action items from an event | |
| CN112364234B (en) | Automatic grouping system for online discussion | |
| CN107211058A (en) | Dialogue-based dynamic meeting segmentation | |
| US20230282218A1 (en) | Near real-time in-meeting content item suggestions | |
| CN110047508A (en) | Voice recording method, device, computer equipment and storage medium | |
| US20130318021A1 (en) | Information processing apparatus, information processing method, and program | |
| US20240061899A1 (en) | Conference information query method and apparatus, storage medium, terminal device, and server | |
| US20230385778A1 (en) | Meeting thread builder | |
| Haaland et al. | Measuring what is top of mind | |
| CN109410934A (en) | A kind of more voice sound separation methods, system and intelligent terminal based on vocal print feature | |
| WO2024005944A1 (en) | Meeting attendance prompt | |
| CN112673641B (en) | Inline response to video or voice messages | |
| CN107423307A (en) | The distribution method and device of a kind of internet information resource | |
| Martikainen | Audio-based stylistic characteristics of Podcasts for search and recommendation: a user and computational analysis | |
| US12142260B2 (en) | Time distributions of participants across topic segments in a communication session | |
| CN112836138A (en) | User recommendation method and device | |
| US20230245646A1 (en) | Time distributions of participants across topic segments in a communication session | |
| US12112748B2 (en) | Extracting filler words and phrases from a communication session | |
| CN109726267A (en) | Story recommended method and device for Story machine | |
| US20240143936A1 (en) | Intelligent prediction of next step sentences from a communication session | |
| US11935518B2 (en) | Joint works production method and server using collective intelligence | |
| US20230326454A1 (en) | Dynamic chapter generation for a communication session |
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 |