CN109087670A - Mood analysis method, system, server and storage medium - Google Patents
Mood analysis method, system, server and storage medium Download PDFInfo
- Publication number
- CN109087670A CN109087670A CN201811005214.2A CN201811005214A CN109087670A CN 109087670 A CN109087670 A CN 109087670A CN 201811005214 A CN201811005214 A CN 201811005214A CN 109087670 A CN109087670 A CN 109087670A
- Authority
- CN
- China
- Prior art keywords
- target
- intonation
- data
- mood
- model
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
Abstract
The embodiment of the invention discloses a kind of mood analysis method, system, server and storage mediums, wherein the described method includes: language keywords and target intonation included in the voice data that identification is got；According to the language keywords and target intonation of acquisition, analyzes and determine phonetic feature point；Target emotion model, and the spotting phonetic feature point on target emotion model are generated based on the phonetic feature point；Target emotion model is matched with the standard mood model in standard mood model library, to adjust calibrated target voice characteristic point on target emotion model, and records the delta data of target voice characteristic point；By the delta data in database intonation characteristic and Psychological behavioral Characteristic data match, and user emotion or emotional change data are exported according to matching result.It can reach the emotional change of objective, accurate analysis user as a result, and help the purpose of user management mood.
Description
Technical field
The present invention relates to data analysis technique field more particularly to a kind of mood analysis method, system, server and storages
Medium.
Background technique
The emotional expression of people is for personal abnormal important, if cannot be released in due course, over time, psychology and physiology
Variation will be generated.In today of rapid economic development, treatment for specific group, people are more and more unable to do what one wishes.Therefore
Being badly in need of one kind can help the specific group there are emotional problems objectively to analyze mood by intelligent method, manage mood.
It is most common at present to understand by assigning computer system identification by affection computation machine technology, express and adapt to
The emotional ability of people, to help user objectively to analyze mood, manages mood to establish harmonious man-machine environment.Common analysis
The method of user emotion, which has, analyzes user emotion by speech recognition technology and face recognition technology.Only using speech recognition technology
It is the sensitive word by including in identification voice to analyze user emotion, accuracy is low.When using face recognition technology, by adopting
Collect the expressive features of face, and then analyzes user emotion by analysis expressive features.But people face expression typically last for when
Between it is shorter in addition one dodge and die, be not easy to acquire, and the expression of people expresses opposite mood sometimes, so that leading to sometimes
Face discriminance analysis user emotion is crossed to be inaccurate.Accordingly, it is difficult to reach the emotional change by objective and accurate analysis user,
Help the purpose of user management mood.
Summary of the invention
The embodiment of the invention provides a kind of mood analysis method, system, server and storage mediums, pass through visitor to reach
The emotional change of accurately analysis user is seen, the purpose of user management mood is helped.
In a first aspect, the embodiment of the invention provides a kind of mood analysis methods, comprising:
Identify language keywords and target intonation included in the voice data got；
According to the language keywords and target intonation of acquisition, analyzes and determine phonetic feature point, wherein the voice
Characteristic point is the keyword and intonation that user emotion is known in the language keywords and the acceptance of the bid of target intonation；
Target emotion model, and the spotting voice on the target emotion model are generated based on the phonetic feature point
Characteristic point；
The target emotion model is matched with the standard mood model in standard mood model library, described in adjustment
Calibrated target voice characteristic point on target emotion model, and record the delta data of target voice characteristic point；
By the delta data in database intonation characteristic and Psychological behavioral Characteristic data match, and root
User emotion or emotional change data are exported according to matching result.
Second aspect, the embodiment of the invention provides a kind of mood analysis systems, comprising:
Identification module, included language keywords and target intonation in the voice data got for identification；
Characteristic point analysis module is analyzed for the language keywords and target intonation according to acquisition and determines voice
Characteristic point, wherein the phonetic feature point be the language keywords and target intonation acceptance of the bid know user emotion keyword and
Intonation；
Modeling module, for generating basic target emotion model based on the phonetic feature point analyzed and determined, and
The spotting phonetic feature point on the target emotion model；
Adjust logging modle, for by the standard mood model in the target emotion model and standard mood model library into
Row matching, to adjust calibrated target voice characteristic point on the target emotion model, and records target voice characteristic point
Delta data；
Mood analysis module, for by the intonation characteristic and Psychological behavioral Characteristic in the delta data and database
Data are matched, and export user emotion or emotional change data according to matching result.
The third aspect, the embodiment of the invention also provides a kind of servers, comprising:
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the mood analysis method as described in any in the embodiment of the present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the mood method as described in any in the embodiment of the present invention when program is executed by processor.
A kind of mood analysis method, system, server and storage medium provided in an embodiment of the present invention, according to the language extracted
Sound characteristic point establishes target emotion model, and the spotting phonetic feature point on target emotion model, filters out energy to reach
The purpose of enough phonetic feature points for accurately showing user emotion, then by the mark in target emotion model and standard mood model library
Quasi- mood model is matched, adjust target emotion model on calibrated target voice characteristic point, make target emotion model with
Master pattern is closer, the subsequent intonation characteristic according in target voice characteristic point delta data and database and psychological row
It is characterized data to be matched, fast and accurately analyzes user emotion variation.
Detailed description of the invention
Fig. 1 is a kind of flow diagram for mood analysis method that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow diagram of mood analysis method provided by Embodiment 2 of the present invention；
Fig. 3 is a kind of structural schematic diagram for mood analysis system that the embodiment of the present invention three provides；
Fig. 4 is a kind of structure chart for server that the embodiment of the present invention four provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow chart for the mood analysis method that the embodiment of the present invention one provides, and the present embodiment is applicable to presence
The specific group of emotional problems objectively analyzes and manages mood, and this method can be executed by mood analysis system, the system
Such as it can be only fitted in server.The method specifically includes:
Included language keywords and target intonation in the voice data that S110, identification are got.
Wherein it is possible to acquire the voice data of user by preset rules, illustratively, according to preset time rule,
User's voice data interior for a period of time or voice data in different time periods in acquisition user one day are acquired, specifically, can
To be acquired by corresponding voice collecting software.
For the voice data acquired, can be identified by speech recognition technology semantic content included by voice data and
Intonation, wherein intonation includes volume, word speed and tone of voice data etc..Illustratively, acoustic model and language mould can be passed through
Type analysis identifies the semantic content namely content of text in voice data.
According to speech recognition as a result, extracting language keywords and target language from the semantic content and intonation identified
Adjust, wherein the target language stealthily substitute in the volume for including voice data, word speed, tone and respective variation tendency at least one
Kind.Illustratively, it using the meaningless word in participle dictionary removal semantic content, while extracting and can be shown that user emotion
Language keywords；For the intonation of identification, screening wherein meets the conduct target intonation of preset condition, illustratively, by volume
It is more than a certain more than maximum preset threshold value and screening as a kind of target intonation lower than minimum preset threshold, or by word speed
Preset threshold is also used as target intonation.
S120, the language keywords and target intonation according to acquisition are analyzed and are determined phonetic feature point, wherein institute
Predicate sound characteristic point is the keyword and intonation that user emotion is known in the language keywords and the acceptance of the bid of target intonation.
The language keywords and target language tune got are further analyzed and screened, determination can wherein clearly show that
The keyword and intonation of user emotion are as phonetic feature point, wherein phonetic feature point includes that keyword feature point and intonation are special
Sign point.Illustratively, language keywords can be screened by the mood sensitive word dictionary established in advance, and will filtered out
Keyword is determined as keyword feature point, wherein mood sensitive word dictionary includes the vocabulary often said under the various different moods of user.
It, can be using the obvious point of variation tendency as intonation spy since target intonation is usually to be shown in the form of waveform diagram
Levy point, such as the point that word speed is accelerated suddenly.
S130, target emotion model is generated based on the phonetic feature point, and demarcates mesh on the target emotion model
Poster sound characteristic point.
Target emotion model is generated according to determining phonetic feature point, so as to according to target emotion model analysis user's feelings
Thread.The spotting phonetic feature point on target emotion model, wherein target voice characteristic point can be the language determined in S120
Feature a part more outstanding in sound characteristic point, it is thus achieved that the further screening to user emotion feature, so that user
Emotional characteristics it is more obvious.
S140, the target emotion model is matched with the standard mood model in standard mood model library, to adjust
Calibrated target voice characteristic point on the whole target emotion model, and record the delta data of target voice characteristic point.
Target emotion model is matched with the standard mood model in standard mood model library, that is to say target feelings
The phonetic feature point demarcated on thread model is matched with the characteristic point in standard mood model, including keyword and intonation
Match, according to the data tendency of matching result and each target voice characteristic point to calibrated target voice on target emotion model
Characteristic point is finely adjusted, and records the delta data of target voice characteristic point.Illustratively, by target voice characteristic point from position A
It is adjusted to position B, records the situation of change of target voice characteristic point each feature between position A and B, such as Speed variation,
Intonation variation and volume change etc..
S150, by the delta data and database intonation characteristic and Psychological behavioral Characteristic data carry out
Match, and user emotion or emotional change data are exported according to matching result.
According to the intonation characteristic and Psychological behavioral Characteristic number in the delta data and database of target voice characteristic point
According to matching result, export user emotion or emotional change data.Illustratively, if word speed frequency is fast, give great volume, intonation becomes
Change big, then it is assumed that user emotion is more eager；If word speed frequency is slow, volume is moderate, intonation is gentle, then it is assumed that user emotion compares
Steadily.
In the present embodiment, target emotion model is established according to the phonetic feature point extracted, and on target emotion model
Then spotting phonetic feature point will with achieving the purpose that filter out the phonetic feature point that can accurately show user emotion
Target emotion model is matched with the mood model in standard mood model library, adjusts calibrated mesh on target emotion model
Poster sound characteristic point keeps target emotion model and master pattern closer, it is subsequent according to target voice characteristic point delta data with
Intonation characteristic and Psychological behavioral Characteristic data in database are matched, and user emotion variation is fast and accurately analyzed.
Embodiment two
Fig. 2 is a kind of flow diagram of mood analysis method provided by Embodiment 2 of the present invention, and the present embodiment is above-mentioned
It is optimized on the basis of embodiment, which comprises
Included language keywords and target intonation in the voice data that S210, identification are got.
S220, the language keywords and target intonation according to acquisition are analyzed and are determined phonetic feature point, wherein institute
Predicate sound characteristic point is the keyword and intonation that user emotion is known in the language keywords and the acceptance of the bid of target intonation.
S230, convolution algorithm is obtained as a result, based on the convolution algorithm knot to phonetic feature point progress convolution algorithm
Fruit generates target emotion model, and the extreme point in the convolution algorithm result is demarcated as target voice characteristic point.
In the present embodiment, convolution algorithm is carried out to the phonetic feature point that S220 is obtained and obtains convolution algorithm as a result, simultaneously basis
The data tendency of each characteristic point in convolution algorithm result generates target emotion model, illustratively, the target emotion mould of generation
Type can be a waveform diagram.Further, user emotion can be clearly showed that in the phonetic feature point in order to screen acquisition
The corresponding phonetic feature point of extreme point in the illustraton of model such as wave crest and wave trough position is demarcated as target voice by characteristic point
Characteristic point.
S240, the target emotion model is matched with the standard mood model in standard mood model library, to adjust
Calibrated target voice characteristic point on the whole target emotion model, and record the delta data of target voice characteristic point.
S250, by the delta data and database intonation characteristic and Psychological behavioral Characteristic data carry out
Match, and user emotion or emotional change data are exported according to matching result.
Further, in the present embodiment, it in order to improve the accuracy that user emotion is analyzed, is calculated by big data analysis
To update the intonation characteristic and Psychological behavioral Characteristic data in the database.Illustratively, periodically acquisition interconnection
Network data, and analytical calculation is carried out to collected internet data, constantly update the intonation characteristic in the database
With Psychological behavioral Characteristic data, wherein the database is local data base or internet database.
In the present embodiment, target emotion model, and root are established by carrying out convolution algorithm to the phonetic feature point of acquisition
According to the extreme value spotting phonetic feature point in calculated result, reach the mesh that screening clearly shows that user emotion phonetic feature point
, while improving the accuracy of user emotion analysis, periodically the intonation characteristic and Psychology and behavior more in new database
Characteristic is convenient for user emotion management so that mood analysis is more acurrate.
Embodiment three
Fig. 3 is a kind of structural schematic diagram for mood analysis system that the embodiment of the present invention three provides, as shown in figure 3, described
System includes:
Identification module 310, included language keywords and target intonation in the voice data got for identification；
Characteristic point analysis module 320 is analyzed for the language keywords and target intonation according to acquisition and determines language
Sound characteristic point, wherein the phonetic feature point is the keyword that user emotion is known in the language keywords and the acceptance of the bid of target intonation
And intonation；
Modeling module 330, for generating basic target emotion model based on the phonetic feature point analyzed and determined,
And the spotting phonetic feature point on the target emotion model；
Logging modle 340 is adjusted, for by the standard mood mould in the target emotion model and standard mood model library
Type is matched, and to adjust calibrated target voice characteristic point on the target emotion model, and records target voice feature
The delta data of point；
Mood analysis module 350, for by the intonation characteristic and Psychology and behavior in the delta data and database
Characteristic is matched, and exports user emotion or emotional change data according to matching result.
In the present embodiment, characteristic point analysis module determines phonetic feature point according to the recognition result of identification module, models mould
Root tuber establishes target emotion model according to phonetic feature point, and adjustment logging modle is finely adjusted target emotion model, and records mesh
The variation of poster sound characteristic point, mood analysis module analyze the mood and feelings of user according to the delta data of target voice characteristic point
Thread variation.It can reach the emotional change by objective, accurate analysis user, as a result, to help the mesh of user management mood
's.
On the basis of the above embodiments, the identification module includes:
Acquisition unit, for acquiring the voice data of user according to preset rules；
Recognition unit, for identification semantic content and intonation included by the voice data；
Extraction unit, for extracting language keyword and target intonation from the semantic content and intonation identified, wherein
The target language is stealthily substituted the volume for including voice data, word speed, tone and respective variation tendency.
On the basis of the above embodiments, the modeling module includes:
Modeling unit obtains convolution algorithm as a result, based on the volume for carrying out convolution algorithm to the phonetic feature point
Product operation result generates target emotion model.
On the basis of the above embodiments, the modeling module includes:
Unit is demarcated, for the extreme point in the convolution algorithm result to be demarcated as target voice characteristic point.
On the basis of the above embodiments, the system also includes:
Big data handles update module, for calculating the intonation characteristic updated in the database by big data analysis
According to Psychological behavioral Characteristic data, wherein the database be local data base or internet database.
Mood provided by any embodiment of the invention point can be performed in mood analysis system provided by the embodiment of the present invention
Analysis method has the corresponding functional module of execution method and beneficial effect.
Example IV
Fig. 4 is the structural schematic diagram for the server that the embodiment of the present invention four provides.Fig. 4, which is shown, to be suitable for being used to realizing this hair
The block diagram of the exemplary servers 12 of bright embodiment.The server 12 that Fig. 4 is shown is only an example, should not be to the present invention
The function and use scope of embodiment bring any restrictions.
As shown in figure 4, server 12 is showed in the form of universal computing device.The component of server 12 may include but not
Be limited to: one or more processor or processing unit 16, system storage 28 connect different system components (including system
Memory 28 and processing unit 16) bus 18.
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Server 12 typically comprises a variety of computer system readable media.These media can be and any can be serviced
The usable medium that device 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Server 12 may further include other removable/nonremovable
, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing not removable
Dynamic, non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").Although not shown in fig 4, it can provide
Disc driver for being read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to removable anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 18.Memory 28 may include at least one program product,
The program product has one group of (for example, at least one) program module, these program modules are configured to perform each implementation of the invention
The function of example.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.Program module 42 is usual
Execute the function and/or method in embodiment described in the invention.
Server 12 can also be logical with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.)
Letter, can also be enabled a user to one or more equipment interact with the server 12 communicate, and/or with make the server
The 12 any equipment (such as network interface card, modem etc.) that can be communicated with one or more of the other calculating equipment communicate.
This communication can be carried out by input/output (I/O) interface 22.Also, server 12 can also pass through network adapter 20
With one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.
As shown, network adapter 20 is communicated by bus 18 with other modules of server 12.It should be understood that although not showing in figure
Out, can in conjunction with server 12 use other hardware and/or software module, including but not limited to: microcode, device driver,
Redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize that mood provided by the embodiment of the present invention analyzes classification method, comprising:
Identify language keywords and target intonation included in the voice data got；
According to the language keywords and target intonation of acquisition, analyzes and determine phonetic feature point, wherein the voice
Characteristic point is the keyword and intonation that user emotion is known in the language keywords and the acceptance of the bid of target intonation；
Target emotion model, and the spotting phonetic feature on target emotion model are generated based on the phonetic feature point
Point；
Target emotion model is matched with the standard mood model in standard mood model library, to adjust target emotion
Calibrated target voice characteristic point on model, and record the delta data of target voice characteristic point；
By the delta data in database intonation feature and Psychological behavioral Characteristic match, and according to matching tie
Fruit exports user emotion or emotional change data.
In one embodiment, the program that processing unit 16 is stored in system storage 28 by operation, realization
Mood analysis method, further includes:
The voice data of user is acquired according to preset rules；
Identify semantic content included by the voice data and intonation；
Language keywords and target intonation are extracted from the semantic content and intonation identified, wherein the target intonation
At least one of volume, word speed, tone and respective variation tendency including voice data.
In one embodiment, the program that processing unit 16 is stored in system storage 28 by operation, realization
Mood analysis method, further includes:
Convolution algorithm is carried out to the phonetic feature point and obtains convolution algorithm as a result, generating based on the convolution algorithm result
Target emotion model.
In one embodiment, the program that processing unit 16 is stored in system storage 28 by operation, realization
Mood analysis method, further includes:
Extreme point in the convolution algorithm result is demarcated as target voice characteristic point.
In one embodiment, the program that processing unit 16 is stored in system storage 28 by operation, realization
Mood analysis method, further includes:
It is calculated by big data analysis to update the intonation characteristic and Psychological behavioral Characteristic data in the database,
Wherein, the database is local data base or internet database.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
The mood analysis method as provided by the embodiment of the present invention is realized when program is executed by processor, comprising:
Identify language keywords and target intonation included in the voice data got；
According to the language keywords and target intonation of acquisition, analyzes and determine phonetic feature point, wherein the voice
Characteristic point is the keyword and intonation that user emotion is known in the language keywords and the acceptance of the bid of target intonation；
Target emotion model, and the spotting phonetic feature on target emotion model are generated based on the phonetic feature point
Point；
Target emotion model is matched with the standard mood model in standard mood model library, to adjust target emotion
Calibrated target voice characteristic point on model, and record the delta data of target voice characteristic point；
By the delta data in database intonation feature and Psychological behavioral Characteristic match, and according to matching tie
Fruit exports user emotion or emotional change data.
In one embodiment, it can also be realized when which is executed by processor:
The voice data of user is acquired according to preset rules；
Identify semantic content included by the voice data and intonation；
Language keywords and target intonation are extracted from the semantic content and intonation identified, wherein the target intonation
At least one of volume, word speed, tone and respective variation tendency including voice data.
In one embodiment, it can also be realized when which is executed by processor:
Convolution algorithm is carried out to the phonetic feature point and obtains convolution algorithm as a result, generating based on the convolution algorithm result
Target emotion model.
In one embodiment, it can also be realized when which is executed by processor:
Extreme point in the convolution algorithm result is demarcated as target voice characteristic point.
In one embodiment, it can also be realized when which is executed by processor:
It is calculated by big data analysis to update the intonation characteristic and Psychological behavioral Characteristic data in the database,
Wherein, the database is local data base or internet database.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of mood analysis method, which is characterized in that the described method includes:
Identify language keywords and target intonation included in the voice data got；
According to the language keywords and target intonation of acquisition, analyzes and determine phonetic feature point, wherein the phonetic feature
Point is the keyword and intonation that user emotion is known in the language keywords and the acceptance of the bid of target intonation；
Target emotion model, and the spotting phonetic feature on the target emotion model are generated based on the phonetic feature point
Point；
The target emotion model is matched with the standard mood model in standard mood model library, to adjust the target
Calibrated target voice characteristic point in mood model, and record the delta data of target voice characteristic point；
By the delta data in database intonation characteristic and Psychological behavioral Characteristic data match, and according to
User emotion or emotional change data are exported with result.
2. the method according to claim 1, wherein described identify language included in the voice data got
Say keyword and target intonation, comprising:
The voice data of user is acquired according to preset rules；
Identify semantic content included by the voice data and intonation；
Language keywords and target intonation are extracted from the semantic content and intonation identified, wherein the target language, which is stealthily substituted, to be included
At least one of volume, word speed, tone and respective variation tendency of voice data.
3. the method according to claim 1, wherein based on the phonetic feature point generate target emotion model,
Include:
Convolution algorithm is carried out to the phonetic feature point and obtains convolution algorithm as a result, generating target based on the convolution algorithm result
Mood model.
4. according to the method described in claim 3, it is characterized in that, on target emotion model spotting phonetic feature point,
Include:
Extreme point in the convolution algorithm result is demarcated as target voice characteristic point.
5. the method according to claim 1, wherein the method also includes:
It is calculated by big data analysis to update the intonation characteristic and Psychological behavioral Characteristic data in the database,
In, the database is local data base or internet database.
6. a kind of mood analysis system, which is characterized in that the system comprises:
Identification module, included language keywords and target intonation in the voice data got for identification；
Characteristic point analysis module is analyzed for the language keywords and target intonation according to acquisition and determines phonetic feature
Point, wherein the phonetic feature point is the keyword and intonation that user emotion is known in the language keywords and the acceptance of the bid of target intonation；
Modeling module, for generating basic target emotion model based on the phonetic feature point analyzed and determined, and in institute
State spotting phonetic feature point on target emotion model；
Logging modle is adjusted, for carrying out the standard mood model in the target emotion model and standard mood model library
Match, to adjust calibrated target voice characteristic point on the target emotion model, and records the variation of target voice characteristic point
Data；
Mood analysis module, in the delta data and database intonation characteristic and Psychological behavioral Characteristic data into
Row matching, and user emotion or emotional change data are exported according to matching result.
7. according to right want 6 described in system, which is characterized in that the identification module includes:
Acquisition unit, for acquiring the voice data of user according to preset rules；
Recognition unit, for identification semantic content and intonation included by the voice data；
Extraction unit, for extracting language keyword and target intonation from the semantic content and intonation identified, wherein described
Target language is stealthily substituted at least one of the volume for including voice data, word speed, tone and respective variation tendency.
8. according to right want 6 described in system, which is characterized in that the system also includes:
Big data handles update module, for calculated by big data analysis update intonation characteristic in the database with
Psychological behavioral Characteristic data, wherein the database is local data base or internet database.
9. a kind of server, which is characterized in that the server includes:
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as mood analysis method as claimed in any one of claims 1 to 5.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Such as mood analysis method as claimed in any one of claims 1 to 5 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811005214.2A CN109087670B (en) | 2018-08-30 | 2018-08-30 | Emotion analysis method, system, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811005214.2A CN109087670B (en) | 2018-08-30 | 2018-08-30 | Emotion analysis method, system, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109087670A true CN109087670A (en) | 2018-12-25 |
| CN109087670B CN109087670B (en) | 2021-04-20 |
Family
ID=64840278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811005214.2A Active CN109087670B (en) | 2018-08-30 | 2018-08-30 | Emotion analysis method, system, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109087670B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110135A (en) * | 2019-04-17 | 2019-08-09 | 西安极蜂天下信息科技有限公司 | Voice characteristics data library update method and device |
| CN110399837A (en) * | 2019-07-25 | 2019-11-01 | 深圳智慧林网络科技有限公司 | User emotion recognition methods, device and computer readable storage medium |
| CN110534135A (en) * | 2019-10-18 | 2019-12-03 | 四川大学华西医院 | A method of emotional characteristics are assessed with heart rate response based on language guidance |
| CN111354377A (en) * | 2019-06-27 | 2020-06-30 | 深圳市鸿合创新信息技术有限责任公司 | Method and device for recognizing emotion through voice and electronic equipment |
| CN111447124A (en) * | 2020-04-02 | 2020-07-24 | 张瑞华 | Intelligent household control method and intelligent control equipment based on biological feature recognition |
| CN112037821A (en) * | 2019-06-03 | 2020-12-04 | 阿里巴巴集团控股有限公司 | Visual representation method and device of voice emotion and computer storage medium |
| CN112037820A (en) * | 2019-05-16 | 2020-12-04 | 杭州海康威视数字技术股份有限公司 | Security alarm method, device, system and equipment |
| CN112071304A (en) * | 2020-09-08 | 2020-12-11 | 深圳市天维大数据技术有限公司 | Semantic analysis method and device |
| CN113284494A (en) * | 2021-05-25 | 2021-08-20 | 平安普惠企业管理有限公司 | Voice assistant recognition method, device, equipment and computer readable storage medium |
| CN113468983A (en) * | 2021-06-15 | 2021-10-01 | 杭州海康威视系统技术有限公司 | Emotion analysis method, device, equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101789990A (en) * | 2009-12-23 | 2010-07-28 | 宇龙计算机通信科技(深圳)有限公司 | Method and mobile terminal for judging emotion of opposite party in conservation process |
| CN102099853A (en) * | 2009-03-16 | 2011-06-15 | 富士通株式会社 | Apparatus and method for recognizing speech emotion change |
| CN103593054A (en) * | 2013-11-25 | 2014-02-19 | 北京光年无限科技有限公司 | Question-answering system combining emotion recognition and output |
| CN104050965A (en) * | 2013-09-02 | 2014-09-17 | 广东外语外贸大学 | English phonetic pronunciation quality evaluation system with emotion recognition function and method thereof |
| CN104102627A (en) * | 2014-07-11 | 2014-10-15 | 合肥工业大学 | Multi-mode non-contact emotion analyzing and recording system |
| US20150286858A1 (en) * | 2015-03-18 | 2015-10-08 | Looksery, Inc. | Emotion recognition in video conferencing |
| CN105159979A (en) * | 2015-08-27 | 2015-12-16 | 广东小天才科技有限公司 | Good friend recommendation method and apparatus |
| CN106548788A (en) * | 2015-09-23 | 2017-03-29 | 中国移动通信集团山东有限公司 | A kind of intelligent emotion determines method and system |
| WO2018061839A1 (en) * | 2016-09-29 | 2018-04-05 | 株式会社村田製作所 | Transmission device, transmission method, and transmission program |
| CN107948417A (en) * | 2017-11-22 | 2018-04-20 | 周燕红 | A kind of method, apparatus, terminal and the storage medium of voice data monitoring |
| CN108010516A (en) * | 2017-12-04 | 2018-05-08 | 广州势必可赢网络科技有限公司 | A kind of semanteme independent voice mood characteristic recognition method and device |
| CN108010512A (en) * | 2017-12-05 | 2018-05-08 | 广东小天才科技有限公司 | The acquisition methods and recording terminal of a kind of audio |
-
2018
- 2018-08-30 CN CN201811005214.2A patent/CN109087670B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102099853A (en) * | 2009-03-16 | 2011-06-15 | 富士通株式会社 | Apparatus and method for recognizing speech emotion change |
| CN101789990A (en) * | 2009-12-23 | 2010-07-28 | 宇龙计算机通信科技(深圳)有限公司 | Method and mobile terminal for judging emotion of opposite party in conservation process |
| CN104050965A (en) * | 2013-09-02 | 2014-09-17 | 广东外语外贸大学 | English phonetic pronunciation quality evaluation system with emotion recognition function and method thereof |
| CN103593054A (en) * | 2013-11-25 | 2014-02-19 | 北京光年无限科技有限公司 | Question-answering system combining emotion recognition and output |
| CN104102627A (en) * | 2014-07-11 | 2014-10-15 | 合肥工业大学 | Multi-mode non-contact emotion analyzing and recording system |
| US20150286858A1 (en) * | 2015-03-18 | 2015-10-08 | Looksery, Inc. | Emotion recognition in video conferencing |
| CN105159979A (en) * | 2015-08-27 | 2015-12-16 | 广东小天才科技有限公司 | Good friend recommendation method and apparatus |
| CN106548788A (en) * | 2015-09-23 | 2017-03-29 | 中国移动通信集团山东有限公司 | A kind of intelligent emotion determines method and system |
| WO2018061839A1 (en) * | 2016-09-29 | 2018-04-05 | 株式会社村田製作所 | Transmission device, transmission method, and transmission program |
| CN107948417A (en) * | 2017-11-22 | 2018-04-20 | 周燕红 | A kind of method, apparatus, terminal and the storage medium of voice data monitoring |
| CN108010516A (en) * | 2017-12-04 | 2018-05-08 | 广州势必可赢网络科技有限公司 | A kind of semanteme independent voice mood characteristic recognition method and device |
| CN108010512A (en) * | 2017-12-05 | 2018-05-08 | 广东小天才科技有限公司 | The acquisition methods and recording terminal of a kind of audio |
Non-Patent Citations (1)
| Title |
|---|
| 陈鹏展 等: "基于语音信号与文本信息的双模态情感识别", 《华东交通大学学报》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110135A (en) * | 2019-04-17 | 2019-08-09 | 西安极蜂天下信息科技有限公司 | Voice characteristics data library update method and device |
| CN112037820B (en) * | 2019-05-16 | 2023-09-05 | 杭州海康威视数字技术股份有限公司 | Security alarm method, device, system and equipment |
| CN112037820A (en) * | 2019-05-16 | 2020-12-04 | 杭州海康威视数字技术股份有限公司 | Security alarm method, device, system and equipment |
| CN112037821A (en) * | 2019-06-03 | 2020-12-04 | 阿里巴巴集团控股有限公司 | Visual representation method and device of voice emotion and computer storage medium |
| CN111354377A (en) * | 2019-06-27 | 2020-06-30 | 深圳市鸿合创新信息技术有限责任公司 | Method and device for recognizing emotion through voice and electronic equipment |
| CN110399837A (en) * | 2019-07-25 | 2019-11-01 | 深圳智慧林网络科技有限公司 | User emotion recognition methods, device and computer readable storage medium |
| CN110399837B (en) * | 2019-07-25 | 2024-01-05 | 深圳智慧林网络科技有限公司 | User emotion recognition method, device and computer readable storage medium |
| CN110534135A (en) * | 2019-10-18 | 2019-12-03 | 四川大学华西医院 | A method of emotional characteristics are assessed with heart rate response based on language guidance |
| CN111447124A (en) * | 2020-04-02 | 2020-07-24 | 张瑞华 | Intelligent household control method and intelligent control equipment based on biological feature recognition |
| CN112071304A (en) * | 2020-09-08 | 2020-12-11 | 深圳市天维大数据技术有限公司 | Semantic analysis method and device |
| CN112071304B (en) * | 2020-09-08 | 2024-03-15 | 深圳市天维大数据技术有限公司 | Semantic analysis method and device |
| CN113284494A (en) * | 2021-05-25 | 2021-08-20 | 平安普惠企业管理有限公司 | Voice assistant recognition method, device, equipment and computer readable storage medium |
| CN113284494B (en) * | 2021-05-25 | 2023-12-01 | 北京基智科技有限公司 | Voice assistant recognition method, device, equipment and computer readable storage medium |
| CN113468983A (en) * | 2021-06-15 | 2021-10-01 | 杭州海康威视系统技术有限公司 | Emotion analysis method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109087670B (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109087670A (en) | Mood analysis method, system, server and storage medium | |
| Ancilin et al. | Improved speech emotion recognition with Mel frequency magnitude coefficient | |
| CN106683680B (en) | Speaker recognition method and device, computer equipment and computer readable medium | |
| CN109243491B (en) | Method, system and storage medium for emotion recognition of speech in frequency spectrum | |
| CN107767869B (en) | Method and apparatus for providing voice service | |
| US8676574B2 (en) | Method for tone/intonation recognition using auditory attention cues | |
| Pawar et al. | Convolution neural network based automatic speech emotion recognition using Mel-frequency Cepstrum coefficients | |
| WO2021000408A1 (en) | Interview scoring method and apparatus, and device and storage medium | |
| CN110880329B (en) | Audio identification method and equipment and storage medium | |
| CN112259106A (en) | Voiceprint recognition method and device, storage medium and computer equipment | |
| CN107633851B (en) | Discrete speech emotion recognition method, device and system based on emotion dimension prediction | |
| Özseven et al. | SPeech ACoustic (SPAC): A novel tool for speech feature extraction and classification | |
| CN113707173B (en) | Voice separation method, device, equipment and storage medium based on audio segmentation | |
| Chatterjee et al. | Auditory model-based design and optimization of feature vectors for automatic speech recognition | |
| KR20220044446A (en) | Method and apparatus for testing vehicle-mounted voice device, electronic device and storage medium | |
| Staudacher et al. | Fast fundamental frequency determination via adaptive autocorrelation | |
| CN115273904A (en) | Angry emotion recognition method and device based on multi-feature fusion | |
| Chi et al. | Robust emotion recognition by spectro-temporal modulation statistic features | |
| Ton-That et al. | Speech emotion recognition using a fuzzy approach | |
| CN114595692A (en) | Emotion recognition method, system and terminal equipment | |
| CN115240696B (en) | Speech recognition method and readable storage medium | |
| CN110321404B (en) | Vocabulary entry selection method and device for vocabulary learning, electronic equipment and storage medium | |
| Batzorig et al. | Speech recognition in Mongolian language using a neural network with pre-processing technique | |
| CN113761206A (en) | Intelligent information query method, device, equipment and medium based on intention recognition | |
| Hajihashemi et al. | Novel time-frequency based scheme for detecting sound events from sound background in audio segments |
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 |