CN109451188A - Method, apparatus, computer equipment and the storage medium of the self-service response of otherness - Google Patents
Method, apparatus, computer equipment and the storage medium of the self-service response of otherness Download PDFInfo
- Publication number
- CN109451188A CN109451188A CN201811446908.XA CN201811446908A CN109451188A CN 109451188 A CN109451188 A CN 109451188A CN 201811446908 A CN201811446908 A CN 201811446908A CN 109451188 A CN109451188 A CN 109451188A
- Authority
- CN
- China
- Prior art keywords
- current
- client
- casting
- content
- information
- 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
- 230000004044 response Effects 0.000 title claims abstract description 206
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005266 casting Methods 0.000 claims abstract description 206
- 230000036651 mood Effects 0.000 claims abstract description 126
- 238000012512 characterization method Methods 0.000 claims abstract description 100
- 238000012216 screening Methods 0.000 claims abstract description 93
- 230000001755 vocal effect Effects 0.000 claims description 42
- 230000002996 emotional effect Effects 0.000 claims description 30
- 230000008859 change Effects 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 13
- 239000000203 mixture Substances 0.000 claims description 13
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 230000006854 communication Effects 0.000 abstract description 17
- 230000003993 interaction Effects 0.000 abstract description 7
- 230000002452 interceptive effect Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 13
- 238000012360 testing method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 206010022998 Irritability Diseases 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000009223 counseling Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
-
- 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
- G10L17/00—Speaker identification or verification techniques
-
- 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
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Multimedia (AREA)
- Child & Adolescent Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Computational Linguistics (AREA)
- Telephonic Communication Services (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Provided herein method, apparatus, computer equipment and the storage medium of a kind of self-service response of otherness, is related to interactive voice field, and wherein method includes: the current talking information of real-time acquisition client;Current talking information is parsed, current talking content and current voiceprint are obtained;Current voiceprint is inputted in mood data library, screening obtains corresponding existing customer mood characterization parameter;Obtain the corresponding current casting content of sensitive word and the corresponding current response voice of customer anger characterization parameter in current talking content;Current casting content and current response voice are sent to client terminal, so that client currently broadcasts content using current response voice broadcast.The application acquires the voiceprint and dialog context of client in real time in communication process, identify customer anger information and call wish, and according to customer anger dynamic adjustment casting voice, while corresponding casting content is met according to current talking content matching, improves the interaction integrality with client.
Description
Technical field
This application involves technical field of voice interaction, in particular to the method, apparatus of a kind of self-service response of otherness calculates
Machine equipment and storage medium.
Background technique
Self-service answering system can answer most of consultation information of client according to default scene and presupposed information automatically,
To mitigate the operating pressure of contact staff significantly, it is widely used in the work of consultation of various industries, such as telephone expenses inquiry.But
It is that existing self-service answering system can only use single casting voice, volume, word speed in the interactive process with client
It cannot be adjusted in real time according to the practical interaction scenario with client with mood etc., experience of client when using self-service answering system
Feel very poor, is easy to cause terminal call in advance, cannot achieve advisory role.
Summary of the invention
The main purpose of the application is to provide method, apparatus, computer equipment and the storage of a kind of self-service response of otherness
Medium, it is intended to solve existing self-service answering system and set inflexible, the drawback of interaction integrality difference in interactive process.
To achieve the above object, this application provides a kind of methods of the self-service response of otherness, are applied to response terminal, side
Method includes:
The current talking information of acquisition client in real time;
The current talking information is parsed, current talking content and current voiceprint are obtained;
In the mood data library that the current voiceprint input is constructed in advance, screening obtains the current voiceprint
Corresponding existing customer mood characterization parameter, the mood data library are corresponding with customer anger characterization parameter by multiple groups voiceprint
Composition;
The corresponding current casting content of sensitive word and the customer anger table in the current talking content are obtained respectively
Levy the corresponding current response voice of parameter;
The current casting content and the current response voice are sent to the client terminal, so that the client
Content is currently broadcasted using described in the current response voice broadcast.
Further, in the mood data library that the current voiceprint input is constructed in advance, screening obtains described
The step of current voiceprint corresponding existing customer mood characterization parameter, comprising:
The current voiceprint is parsed, the current vocal print parameter of the client is obtained, the current vocal print parameter includes
Word speed, tone and the volume of the client;
The current vocal print parameter is inputted in the mood data library, according to the word speed, the tone and the sound
The numerical intervals respectively fallen in are measured, the corresponding existing customer mood characterization parameter of the current vocal print parameter, the feelings are filtered out
Thread database is made of numerical intervals and customer anger the characterization parameter correspondence of multiple groups vocal print parameter.
Further, described to obtain the corresponding current casting content of the current talking content and the customer anger respectively
The step of characterization parameter corresponding current response voice, comprising:
In the casting database that current talking content input is constructed in advance, screening is obtained in the current casting
Hold;
In the response sound bank that existing customer mood characterization parameter input is constructed in advance, screening obtains described current
Response voice, content is corresponding forms with casting by multiple groups dialog context for the casting database, and the response sound bank has multiple groups
Customer anger characterization parameter composition corresponding with response voice.
Further, in the casting database that current talking content input is constructed in advance, screening obtains institute
The step of stating current casting content, comprising:
Identify the sensitive word for including in the current talking content;
The sensitive word is inputted in the casting database, screening obtains casting content corresponding with the sensitive word;
It is the current casting content by the corresponding casting curriculum offering of the sensitive word.
Further, before the step of current talking information of the real-time acquisition client, including
Call-information for the first time is obtained, and parses the call-information for the first time and obtains tonality feature, the call-information for the first time
Carry scene selection;
The tonality feature is inputted to the gender data library constructed in advance, screening obtains the corresponding client of the tonality feature
Gender, the gender data library are made of multiple groups tonality feature and client gender correspondence;
By in the casting sound bank that constructs in advance of client gender input, screening obtains that the client gender is corresponding to be broadcast
Voice is reported, while in the scene database that scene selection input is constructed in advance, screening obtains the scene and selects corresponding field
Scape content, voice is corresponding forms with casting by two groups of client genders for the casting sound bank, and the scene database has multiple groups field
Scape selection composition corresponding with scene content;
The scene content and the casting voice are sent to the client terminal, so that described in the client use
Broadcast scene content described in voice broadcast.
Further, described to generate using the information of casting for the first time for broadcasting scene content described in voice broadcast and export
After the step of to the client terminal, comprising:
The client gender and the client personal information of preparatory typing are bound.
Further, described to generate using the information of casting for the first time for broadcasting scene content described in voice broadcast and export
After the step of to the client terminal, comprising:
According to variation of the existing customer mood characterization parameter within the unit air time, the mood of the client is obtained
Change information;
In the personality database that the emotional change information input is constructed in advance, screening obtains the emotional change information
Corresponding existing customer personality;
The existing customer personality is bound with the client personal information.
Present invention also provides a kind of devices of the self-service response of otherness, comprising:
Acquisition module, for acquiring the current talking information of client in real time;
First parsing module obtains current talking content and current voiceprint for parsing the current talking information;
First screening module is screened for inputting the current voiceprint in the mood data library constructed in advance
To the corresponding existing customer mood characterization parameter of the current voiceprint;
Module is obtained, for obtaining the corresponding current casting content of the sensitive word in the current talking content and institute respectively
State the corresponding current response voice of customer anger characterization parameter;
First sending module, for sending the current casting content and the current response language to the client terminal
Sound, so that the client currently broadcasts content using described in the current response voice broadcast.
Further, first screening module includes:
Resolution unit obtains the current vocal print parameter of the client for parsing the current voiceprint;
First screening unit, for will in the current vocal print parameter input mood data library, according to the word speed,
The numerical intervals that the tone and the volume are respectively fallen in filter out the corresponding existing customer mood of the current vocal print parameter
Characterization parameter.
Further, the acquisition module includes:
Second screening unit is screened for inputting the current talking content in the casting database constructed in advance
To the current casting content;
Third filtering unit, for the existing customer mood characterization parameter to be inputted the response sound bank constructed in advance
In, screening obtains the current response voice, the casting database by multiple groups dialog context with broadcast that content is corresponding to be formed.
Further, second screening unit includes:
Identify subelement, the sensitive word for including in the current talking content for identification;
Subelement is screened, for inputting the sensitive word in the casting database, screening is obtained and the sensitive word
Corresponding casting content;
Subelement is set, for being the current casting content by the corresponding casting curriculum offering of the sensitive word.
Further, described device further include:
Second parsing module for obtaining call-information for the first time, and parses the call-information for the first time and obtains tonality feature;
Second screening module, for the tonality feature to be inputted the gender data library constructed in advance, screening obtains described
The corresponding client gender of tonality feature;
Third screening module, for inputting the client gender in the casting sound bank constructed in advance, screening obtains institute
The corresponding casting voice of client gender is stated, while in the scene database that scene selection input is constructed in advance, screening obtains institute
It states scene and selects corresponding scene content;
Second sending module, for sending the scene content and the casting voice to the client terminal, so that
The client uses scene content described in the casting voice broadcast.
Further, described device further include:
Binding module, for binding the client gender and the client personal information of preparatory typing.
Further, described device further include:
Third parsing module, for the variation according to the existing customer mood characterization parameter within the unit air time,
Obtain the emotional change information of the client;
4th screening module in the personality database for constructing the emotional change information input in advance, is screened
To the corresponding existing customer personality of the emotional change information;
Second binding module, for binding the existing customer personality with the client personal information.
The application also provides a kind of computer equipment, including memory and processor, is stored with calculating in the memory
The step of machine program, the processor realizes method described above when executing the computer program.
The application also provides a kind of computer readable storage medium, is stored thereon with computer program, the computer journey
The step of method described above is realized when sequence is executed by processor.
Method, apparatus, computer equipment and the storage medium of the self-service response of a kind of otherness provided herein, pass through
The current voiceprint and current talking content for acquiring client in real time in communication process, identify the current emotional information of client
With call wish, and according to word speed, tone and the volume of customer anger dynamic adjustment casting voice, while according in current talking
Hold the casting content that matching meets client's call wish, improves the interaction integrality with client.
Detailed description of the invention
Fig. 1 is the step schematic diagram of the method for the self-service response of otherness in one embodiment of the application;
Fig. 2 is the structural block diagram of the device of the self-service response of otherness in one embodiment of the application;
Fig. 3 is the structural schematic block diagram of the computer equipment of one embodiment of the application.
The embodiments will be further described with reference to the accompanying drawings for realization, functional characteristics and the advantage of the application purpose.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Referring to Fig.1, a kind of mode of self-service response of otherness is provided in one embodiment of the application, comprising:
S1: the current talking information of acquisition client in real time;
S2: the current talking information is parsed, current talking content and current voiceprint are obtained;
S3: in the mood data library that the current voiceprint input is constructed in advance, screening obtains the current vocal print
The corresponding existing customer mood characterization parameter of information, the mood data library is by multiple groups voiceprint and customer anger characterization parameter
Corresponding composition;
S4: the corresponding current casting content of sensitive word and the customer anger in the current talking content are obtained respectively
The corresponding current response voice of characterization parameter;
S5: Xiang Suoshu client terminal sends the current casting content and the current response voice, so that the visitor
Content is currently broadcasted using described in the current response voice broadcast in family end.
In the present embodiment, response terminal is built based on selected scene process with client after the selected information of casting for the first time
Vertical communication channel, the current talking information of whole acquisition client, carries out by taking the specific a certain moment as an example here in communication process
Explanation.Response terminal acquires the current talking information of client in real time, and is parsed according to the difference of information type, will currently lead to
The current talking content and the separation of current voiceprint in information are talked about, so as to the analysis and matching of next step.Wherein, info class
Type refers to the data type in current talking information, i.e. text data and voiceprint.Current voiceprint will be by will currently lead to
The voice signal of words information is converted into electric signal, directly extracts and obtains;Current talking content is the text in current talking information
Data, for example " inquiry " the two words are text data, and the voice data for saying " inquiry " the two words is vocal print letter
Breath.The current voiceprint of response terminal acquisition includes the current word speed of client, tone and volume.Response terminal is obtained in parsing
After current voiceprint, current voiceprint is inputted in the mood data library constructed in advance, screening obtains current voiceprint
Corresponding existing customer mood characterization parameter.Wherein, mood data library is by multiple groups voiceprint and customer anger characterization parameter pair
It should form.Developer passes through the numerical value of the word speed, tone and volume that detect people under different moods, and will test numerical classification
Statistics, forms corresponding numerical intervals, so that training forms mood data library.Response terminal passes through this current talking information pair
Word speed, tone and the volume of client is calculated, and generates corresponding specific value.For example, word speed, tone and volume pair
The specific value answered is 120,60,70.Wherein, response terminal can be according to the syllable of the complete current talking information received
Word speed is calculated divided by the time used of the current call-information in number;And tone and volume can directly measure current talking
The frequency and frequency width of the voice signal of information obtain, and the frequency of voice signal corresponds to tone, and frequency width corresponds to volume.Mood data library
In use, the specific value of the current voiceprint of client is compared response terminal with mood data library, pass through matching
Corresponding value type and section can recognize the current emotional characterization parameter of client.For example, the mood table in mood data library
The numerical intervals of the corresponding word speed of parameter " calmness " state of sign, tone and volume are 100-120,50-70 and 40-60;" intolerant to
It is tired " numerical intervals of the corresponding word speed of state, tone and volume are 120-150,70-80 and 60-80;" anger " state pair
The numerical intervals of word speed, tone and the volume answered are 150-180,80-90 and 80-100.The current word speed of client, tone and
The specific value of volume is 120,60 and 50, after comparing can determine that existing customer mood characterization parameter is " calmness ".It answers
After answering the current emotional characterization parameter that terminal obtains client, current talking content is inputted in the casting database constructed in advance,
And it is screened to obtain current casting content according to the sensitive word in call-information.Existing customer mood characterization parameter is inputted simultaneously pre-
In the response sound bank first constructed, screening obtains current response voice.Wherein, casting database has multiple groups dialog context and casting
The corresponding composition of the sensitive word of content, response sound bank are formed by multiple groups customer anger characterization parameter is corresponding with response voice.For example,
When terminal recognition is impatient of to client, by screen the obtained word speed of response voice be it is very fast, the tone be it is soft, volume is
It is larger.Meanwhile the sensitive word in terminal recognition current talking content, it is matched with response sound bank, exports the sensitive word pair
The current broadcast content answered.For example, terminal recognition includes " personal insurance " into the dialog context of client, then according to the " person
This sensitive word of insurance " exports the corresponding casting content of preparatory typing, such as the type of personal insurance, protection amount etc.
Text information.Response terminal sends current casting content and current response voice to client terminal, so that client use is worked as
Preceding response voice broadcast currently broadcasts content.
Further, according in the mood data library that constructs the current voiceprint input in advance, screening obtains
The step of current voiceprint corresponding existing customer mood characterization parameter, comprising:
S301: the parsing current voiceprint obtains the current vocal print parameter of the client, the current vocal print parameter
Word speed, tone and volume including the client;
S302: the current vocal print parameter is inputted in the mood data library, according to the word speed, the tone and institute
The numerical intervals that volume is respectively fallen in are stated, the corresponding existing customer mood characterization parameter of the current vocal print parameter, institute are filtered out
Mood data library is stated to be made of numerical intervals and customer anger the characterization parameter correspondence of multiple groups vocal print parameter.
In the present embodiment, response terminal parses the current voiceprint of collected client, is translated into tool
The vocal print parameter of body obtains the word speed of existing customer, the specific value of tone and volume.Wherein, when word speed can be according to unit
Between be collected client current talking information in syllable number calculate obtain.For example, response terminal is collected in 5S
Syllable number in the current talking information of client is 100, then the word speed of active user is 120 words/s.Tone and volume then may be used
To be obtained by the acoustic signals in detection current talking information, acoustic signals have certain frequency and frequency width, wherein frequency
Corresponding tone, frequency width correspond to volume.Word speed, tone and volume in current voiceprint after parsing is corresponded to table by response terminal
It is now specific current vocal print parameter, for example, the word speed of active user is 120, tone 60, volume 70.In response terminal
Portion is built with mood data library, by developer according to preparatory test, by various moods word speed corresponding with its, tone and volume
Numerical intervals are grouped typing generation.Response terminal passes through word speed, the design parameter value of tone and volume after parsing, defeated
Enter mood data library to be screened, obtains corresponding existing customer mood table according to the numerical intervals that parameters value is respectively fallen in
Levy parameter.For example, the numerical intervals of the corresponding word speed of " impatient " state, tone and volume in mood data library are 150-
200, the specific value of 50-80 and 100-150, the current word speed of client, tone and volume pass through comparison for 160,60 and 120
It can determine that existing customer mood characterization parameter is " impatient " afterwards.
Further, foundation obtains the corresponding current casting content of the current talking content and the customer anger respectively
The step of characterization parameter corresponding current response voice, comprising:
S401: by the casting database that constructs in advance of current talking content input, screening obtains described currently broadcasting
Report content;
S402: in the response sound bank that existing customer mood characterization parameter input is constructed in advance, screening obtains institute
State current response voice, content is corresponding forms by multiple groups dialog context and casting for the casting database, the response sound bank
It is formed by multiple groups customer anger characterization parameter is corresponding with response voice.
In the present embodiment, in the casting database that response terminal constructs the input of current talking content in advance.Wherein, it broadcasts
Database by developer's preparatory typing setting multiple groups dialog context and broadcast that content is corresponding to be formed.Response terminal passes through ASR
(speech recognition technology) identifies the current talking content of client, is converted into text information, and identify in text information
Sensitive word, the sensitive word that response terminal is obtained according to identification screen corresponding current casting content from casting database.For example,
Response terminal recognition includes " personal insurance " into the current talking content of client, then according to " personal insurance " this sensitive word
Screening obtains the corresponding current casting content of preparatory typing, such as type, the guarantor of personal insurance from casting database
Content of volume etc..Meanwhile response terminal inputs existing customer mood characterization parameter in the response sound bank constructed in advance, sieve
Choosing obtains current response voice.It wherein, include that the multiple groups of preparatory typing and different clients mood characterization are joined in response sound bank
The corresponding response voice of number, response voice includes different word speeds, the tone and volume.For example, current customer anger characterizes ginseng
When number is " calmness ", the word speed in corresponding response voice be it is moderate, the tone be it is soft, volume is moderate.Response terminal passes through
It is screened after customer anger characterization parameter is inputted response sound bank, obtains the corresponding response of existing customer mood characterization parameter
Voice.
Further, in the casting database that current talking content input is constructed in advance, screening obtains institute
The step of stating current casting content, comprising:
S4011: the sensitive word for including in the current talking content is identified;
S4012: the sensitive word is inputted in the casting database, and screening obtains casting corresponding with the sensitive word
Content;
S4013: being the current casting content by the corresponding casting curriculum offering of the sensitive word.
In the present embodiment, response terminal identifies the current talking content of client by ASR (speech recognition technology), by its turn
It is changed to text information.Typing has at least one pre-set sensitive word of developer in response terminal, is stored in sensitive dictionary
In.Also, there is different sensitive dictionaries in response terminal according to different response scenes.Such as the sensitive word in inquiry scene
Different from paying a return visit the sensitive word in scene, there are two different sensitive dictionaries for the two tool.Response terminal when identifying sensitive word,
It needs according to the current corresponding sensitive dictionary of response process selecting response process.Response terminal successively traverses in sensitive dictionary
Each sensitive word, judges whether the sensitive word is included in text information, so that identification obtains the record for including in text information
The sensitive word entered.After the sensitive word that response terminal recognition includes into current talking content, which is inputted into casting number
According in library, to filter out the corresponding casting content of sensitive word, and screening is obtained into the corresponding casting curriculum offering of sensitive word and is
Current casting content, to carry out next movement.For example, response terminal, which is sent in the previous casting information of client, inquires visitor
Whether family has purchase endowment insurance, is " having " in the dialog context that response terminal recognition to client feedback is returned, then according to " having "
This sensitive word transfers the corresponding casting content of preparatory typing from casting database, for example, endowment insurance type,
Insured amount content etc..
Further, before the step of current talking information of the real-time acquisition client, including
S6: obtaining call-information for the first time, and parses the call-information for the first time and obtain tonality feature, the call letter for the first time
Breath carries scene selection;
S7: the tonality feature is inputted to the gender data library constructed in advance, it is corresponding that screening obtains the tonality feature
Client gender, the gender data library are made of multiple groups tonality feature and client gender correspondence;
S8: in the casting sound bank that client gender input is constructed in advance, it is corresponding that screening obtains the client gender
Casting voice, while by the scene database that constructs in advance of scene selection input, screening obtains the scene selection and corresponds to
Scene content, voice is corresponding forms with casting by two groups of client genders for the casting sound bank, and the scene database has more
Group scene selection composition corresponding with scene content;
S9: Xiang Suoshu client terminal sends the scene content and the casting voice, so that the client uses
Scene content described in the casting voice broadcast.
In the present embodiment, response terminal needs to judge the gender of client when connecting phone with client for the first time, is closed with being adapted to
The other casting voice of adaptive improves the call experience of client.When response terminal is initially conversed by acquiring existing customer for the first time
The voice signal of call-information for the first time is converted electric signal by call-information, directly extracts and obtains voiceprint, and parses acquisition
The corresponding frequency of voice signal, the i.e. corresponding tonality feature of client.The tone of men and women's sound is different, and the tone of male is more low
Heavy, the tone of women is more high thin, i.e. the frequency of male voice is lower, and the frequency of female voice is higher.Response terminal is previously according to gender
Difference is built with corresponding tone section, therefore the tonality feature can be inputted the gender data library constructed in advance, passes through
Tonality feature is compared with tone section, so that screening obtains the corresponding client gender of existing customer.Call-information for the first time
Middle carrying scene selection, such as user's corresponding scene of selection key 1 in communication process are selected as counseling services scene.Response
Terminal has different casting information according to different scene settings.For example, the scene content word of collection scene is more sharp, language
Gas is more severe;The scene content word for paying a return visit scene more mitigates, and the tone is more soft.The instruction of scene selection can be by answering
Terminal sending is answered, can also be issued by client.As response terminal active call client, then the instruction of scene selection is by response
Terminal issues.When customer call response terminal, then the instruction of scene selection needs client to issue, and scene selection information includes
In call-information for the first time.In the casting sound bank that response terminal constructs client gender input in advance, screening obtains client's property
Not corresponding casting voice.Wherein, casting sound bank by two groups of client genders and broadcasts that voice is corresponding forms.For example, client's property
Not Wei women when, second casting information be also female voice.In the scene database that scene selection input is constructed in advance simultaneously, screening
It obtains scene and selects corresponding scene content.Response terminal sends scene content and casting voice to client terminal, so that objective
Family end uses casting voice broadcast scene content.
Further, it generates the information of casting for the first time using scene content described in the casting voice broadcast and is output to institute
After the step of stating client terminal, comprising:
S10: the client gender and the personal information of the client of preparatory typing are bound.
It, can be by the client gender recognized before and visitor after the current casting information of response terminal output in the present embodiment
The personal information at family is bound, such as the phone number or name of client.Wherein, the personal information of client is pre- by developer
It first collects and is entered into response terminal afterwards, while the personal information of collected client is imperfect, in this classification of client gender
In there is no Given information.Response terminal is after by client gender and personal information binding, when conversing again with the client, Ke Yitong
Personal information, such as phone number Direct Recognition client gender are crossed, so that corresponding casting voice is directly matched, without again
It is secondary to be identified, the time is effectively saved, working efficiency is improved.
Further, it generates the information of casting for the first time using scene content described in the casting voice broadcast and is output to institute
After the step of stating client terminal, comprising:
S11: according to variation of the existing customer mood characterization parameter within the unit air time, obtain the client's
Emotional change information;
S12: in the personality database that the emotional change information input is constructed in advance, screening obtains the emotional change
The corresponding existing customer personality of information;
S13: the existing customer personality is bound with the client personal information.
In the present embodiment, for response terminal in the communication process with client, the moment records feelings of the client in communication process
Thread change information, and the variation according to existing customer mood characterization parameter within the unit air time, the mood for obtaining client become
Change information.Wherein, emotional change information includes that mood characterization parameter changed air time and mood characterization parameter become
Change the specific mood characterization parameter of front and back.Response terminal inner is built with personality information bank in advance, will be various by testing in advance
Corresponding air time section is corresponding when personality information changes with mood characterization parameter, changes is grouped.For example, the personality of client is believed
Breath is " irritability ", and corresponding mood characterization parameter is initially " calmness ", and subsequent variation is " impatient ", generates the call of variation
Time is 1-3 minutes.Response terminal is after terminating primary call, according to the mood characterization parameter of client in entire communication process
Variation and while changing corresponding air time, input personality information bank screened, obtain the client's of this call
Corresponding personality information, i.e. existing customer personality, and the personal information of existing customer personality and client, such as phone number are carried out
Binding when conversing again so as to next time with the client, directly selects initial casting voice appropriate according to existing customer personality, than
If irritable client selects word speed initially to broadcast voice faster, customer experience is effectively improved.
The method of the self-service response of a kind of otherness provided in the present embodiment, by acquiring client in real time in communication process
Current voiceprint and current talking content, the current emotional information of client and call wish are identified, and according to client's feelings
Word speed, tone and the volume of thread dynamic adjustment casting voice, while client's call wish is met according to current talking content matching
Casting content, improve and the interaction integrality of client.
Referring to Fig. 2, a kind of device of self-service response of otherness is additionally provided in one embodiment of the application, comprising:
Acquisition module 1, for acquiring the current talking information of client in real time;
First parsing module 2 obtains current talking content and current vocal print letter for parsing the current talking information
Breath;
First screening module 3 is screened for inputting the current voiceprint in the mood data library constructed in advance
To the corresponding existing customer mood characterization parameter of the current voiceprint;
Obtain module 4, for obtain respectively the corresponding current casting content of the sensitive word in the current talking content with
The corresponding current response voice of the customer anger characterization parameter;
First sending module 5, for sending the current casting content and the current response language to the client terminal
Sound, so that the client currently broadcasts content using described in the current response voice broadcast.
In the present embodiment, response terminal is built based on selected scene process with client after the selected information of casting for the first time
Vertical communication channel, the current talking information of whole acquisition client, carries out by taking the specific a certain moment as an example here in communication process
Explanation.Response terminal acquires the current talking information of client in real time, and is parsed according to the difference of information type, will currently lead to
The current talking content and the separation of current voiceprint in information are talked about, so as to the analysis and matching of next step.Wherein, info class
Type refers to the data type in current talking information, i.e. text data and voiceprint.Current voiceprint will be by will currently lead to
The voice signal of words information is converted into electric signal, directly extracts and obtains;Current talking content is the text in current talking information
Data, for example " inquiry " the two words are text data, and the voice data for saying " inquiry " the two words is vocal print letter
Breath.The current voiceprint of response terminal acquisition includes the current word speed of client, tone and volume.Response terminal is obtained in parsing
After current voiceprint, current voiceprint is inputted in the mood data library constructed in advance, screening obtains current voiceprint
Corresponding existing customer mood characterization parameter.Wherein, mood data library is by multiple groups voiceprint and customer anger characterization parameter pair
It should form.Developer passes through the numerical value of the word speed, tone and volume that detect people under different moods, and will test numerical classification
Statistics, forms corresponding numerical intervals, so that training forms mood data library.Response terminal passes through this current talking information pair
Word speed, tone and the volume of client is calculated, and generates corresponding specific value.For example, word speed, tone and volume pair
The specific value answered is 120,60,70.Wherein, response terminal can be according to the syllable of the complete current talking information received
Word speed is calculated divided by the time used of the current call-information in number;And tone and volume can directly measure current talking
The frequency and frequency width of the voice signal of information obtain, and the frequency of voice signal corresponds to tone, and frequency width corresponds to volume.Mood data library
In use, the specific value of the current voiceprint of client is compared response terminal with mood data library, pass through matching
Corresponding value type and section can recognize the current emotional characterization parameter of client.For example, the mood table in mood data library
The numerical intervals of the corresponding word speed of parameter " calmness " state of sign, tone and volume are 100-120,50-70 and 40-60;" intolerant to
It is tired " numerical intervals of the corresponding word speed of state, tone and volume are 120-150,70-80 and 60-80;" anger " state pair
The numerical intervals of word speed, tone and the volume answered are 150-180,80-90 and 80-100.The current word speed of client, tone and
The specific value of volume is 120,60 and 50, and after comparing can determine that existing customer mood characterization parameter is " calmness ".It answers
After answering the current emotional characterization parameter that terminal obtains client, current talking content is inputted in the casting database constructed in advance,
And it is screened to obtain current casting content according to the sensitive word in call-information.Existing customer mood characterization parameter is inputted simultaneously pre-
In the response sound bank first constructed, screening obtains current response voice.Wherein, casting database has multiple groups dialog context and casting
The corresponding composition of the sensitive word of content, response sound bank are formed by multiple groups customer anger characterization parameter is corresponding with response voice.For example,
When terminal recognition is impatient of to client, by screen the obtained word speed of response voice be it is very fast, the tone be it is soft, volume is
It is larger.Meanwhile the sensitive word in terminal recognition current talking content, it is matched with response sound bank, exports the sensitive word pair
The current broadcast content answered.For example, terminal recognition includes " personal insurance " into the dialog context of client, then according to the " person
This sensitive word of insurance " exports the corresponding casting content of preparatory typing, such as the type of personal insurance, protection amount etc.
Text information.Response terminal sends current casting content and current response voice to client terminal, so that client use is worked as
Preceding response voice broadcast currently broadcasts content.
Further, first screening module 3 includes:
Resolution unit obtains the current vocal print parameter of the client for parsing the current voiceprint;
First screening unit, for will in the current vocal print parameter input mood data library, according to the word speed,
The numerical intervals that the tone and the volume are respectively fallen in filter out the corresponding existing customer mood of the current vocal print parameter
Characterization parameter.
In the present embodiment, response terminal parses the current voiceprint of collected client, is translated into tool
The vocal print parameter of body obtains the word speed of existing customer, the specific value of tone and volume.Wherein, when word speed can be according to unit
Between be collected client current talking information in syllable number calculate obtain.For example, response terminal is collected in 5S
Syllable number in the current talking information of client is 100, then the word speed of active user is 120 words/s.Tone and volume then may be used
To be obtained by the acoustic signals in detection current talking information, acoustic signals have certain frequency and frequency width, wherein frequency
Corresponding tone, frequency width correspond to volume.Word speed, tone and volume in current voiceprint after parsing is corresponded to table by response terminal
It is now specific current vocal print parameter, for example, the word speed of active user is 120, tone 60, volume 70.In response terminal
Portion is built with mood data library, by developer according to preparatory test, by various moods word speed corresponding with its, tone and volume
Numerical intervals are grouped typing generation.Response terminal passes through word speed, the design parameter value of tone and volume after parsing, defeated
Enter mood data library to be screened, obtains corresponding existing customer mood table according to the numerical intervals that parameters value is respectively fallen in
Levy parameter.For example, the numerical intervals of the corresponding word speed of " impatient " state, tone and volume in mood data library are 150-
200, the specific value of 50-80 and 100-150, the current word speed of client, tone and volume pass through comparison for 160,60 and 120
It can determine that existing customer mood characterization parameter is " impatient " afterwards.
Further, the acquisition module 4 includes:
Second screening unit is screened for inputting the current talking content in the casting database constructed in advance
To the current casting content;
Third filtering unit, for the existing customer mood characterization parameter to be inputted the response sound bank constructed in advance
In, screening obtains the current response voice, the casting database by multiple groups dialog context with broadcast that content is corresponding to be formed.
In the present embodiment, in the casting database that response terminal constructs the input of current talking content in advance.Wherein, it broadcasts
Database by developer's preparatory typing setting multiple groups dialog context and broadcast that content is corresponding to be formed.Response terminal passes through ASR
(speech recognition technology) identifies the current talking content of client, is converted into text information, and identify in text information
Sensitive word, the sensitive word that response terminal is obtained according to identification screen corresponding current casting content from casting database.1 ratio
Such as, response terminal recognition includes " personal insurance " into the current talking content of client, then according to " personal insurance ", this is quick
The screening from casting database of sense word obtains the corresponding current casting content of preparatory typing, such as the kind of personal insurance
Class, insured amount content etc..Meanwhile existing customer mood characterization parameter is inputted the response sound bank constructed in advance by response terminal
In, screening obtains current response voice.It wherein, include multiple groups and the different emotional informations pair of preparatory typing in response sound bank
The response voice answered, response voice include different word speeds, the tone and volume.For example, current customer anger characterization parameter is
When " calmness ", word speed in corresponding response voice be it is moderate, the tone be it is soft, volume is moderate.Response terminal is by will be objective
It is screened after family mood characterization parameter input response sound bank, obtains the corresponding response language of existing customer mood characterization parameter
Sound.
Further, second screening unit includes:
Identify subelement, the sensitive word for including in the current talking content for identification;
Subelement is screened, for inputting the sensitive word in the casting database, screening is obtained and the sensitive word
Corresponding casting content;
Subelement is set, for being the current casting content by the corresponding casting curriculum offering of the sensitive word.
In the present embodiment, response terminal identifies the current talking content of client by ASR (speech recognition technology), by its turn
It is changed to text information.Typing has at least one pre-set sensitive word of developer in response terminal, is stored in sensitive dictionary
In.Also, there is different sensitive dictionaries in response terminal according to different response scenes.Such as the sensitive word in inquiry scene
Different from paying a return visit the sensitive word in scene, there are two different sensitive dictionaries for the two tool.Response terminal when identifying sensitive word,
It needs according to the current corresponding sensitive dictionary of response process selecting response process.Response terminal successively traverses in sensitive dictionary
Each sensitive word, judges whether the sensitive word is included in text information, so that identification obtains the record for including in text information
The sensitive word entered.After the sensitive word that response terminal recognition includes into current talking content, which is inputted into casting number
According in library, to filter out the corresponding casting content of sensitive word, and screening is obtained into the corresponding casting curriculum offering of sensitive word and is
Current casting content, to carry out next movement.For example, response terminal, which is sent in the previous casting information of client, inquires visitor
Whether family has purchase endowment insurance, is " having " in the dialog context that response terminal recognition to client feedback is returned, then according to " having "
This sensitive word transfers the corresponding casting content of preparatory typing from casting database, for example, endowment insurance type,
Insured amount content etc..
Further, the processing unit further include:
Second parsing module for obtaining call-information for the first time, and parses the call-information for the first time and obtains tonality feature;
Second screening module, for the tonality feature to be inputted the gender data library constructed in advance, screening obtains described
The corresponding client gender of tonality feature;
Third screening module, for inputting the client gender in the casting sound bank constructed in advance, screening obtains institute
The corresponding casting voice of client gender is stated, while in the scene database that scene selection input is constructed in advance, screening obtains institute
It states scene and selects corresponding scene content;
Second sending module, for sending the scene content and the casting voice to the client terminal, so that
The client uses scene content described in the casting voice broadcast.
In the present embodiment, response terminal needs to judge the gender of client when connecting phone with client for the first time, is closed with being adapted to
The other casting voice of adaptive improves the call experience of client.When response terminal is initially conversed by acquiring existing customer for the first time
The voice signal of call-information for the first time is converted electric signal by call-information, directly extracts and obtains voiceprint, and parses acquisition
The corresponding frequency of voice signal, the i.e. corresponding tonality feature of client.The tone of men and women's sound is different, and the tone of male is more low
Heavy, the tone of women is more high thin, i.e. the frequency of male voice is lower, and the frequency of female voice is higher.Response terminal is previously according to gender
Difference is built with corresponding tone section, therefore the tonality feature can be inputted the gender data library constructed in advance, passes through
Tonality feature is compared with tone section, so that screening obtains the corresponding client gender of existing customer.Call-information for the first time
Middle carrying scene selection, such as user's corresponding scene of selection key 1 in communication process are selected as counseling services scene.Response
Terminal has different casting information according to different scene settings.For example, the scene content word of collection scene is more sharp, language
Gas is more severe;The scene content word for paying a return visit scene more mitigates, and the tone is more soft.The instruction of scene selection can be by answering
Terminal sending is answered, can also be issued by client.As response terminal active call client, then the instruction of scene selection is by response
Terminal issues.When customer call response terminal, then the instruction of scene selection needs client to issue, and scene selection information includes
In call-information for the first time.In the casting sound bank that response terminal constructs client gender input in advance, screening obtains client's property
Not corresponding casting voice.Wherein, casting sound bank by two groups of client genders and broadcasts that voice is corresponding forms.For example, client's property
Not Wei women when, second casting information be also female voice.In the scene database that scene selection input is constructed in advance simultaneously, screening
It obtains scene and selects corresponding scene content.Response terminal sends scene content and casting voice to client terminal, so that objective
Family end uses casting voice broadcast scene content.
Further, the processing unit further include:
Binding module, for binding the client gender and the client personal information of preparatory typing.
It, can be by the client gender recognized before and visitor after the current casting information of response terminal output in the present embodiment
The personal information at family is bound, such as the phone number or name of client.Wherein, the personal information of client is pre- by developer
It first collects and is entered into response terminal afterwards, while the personal information of collected client is imperfect, in this classification of client gender
In there is no Given information.Response terminal is after by client gender and personal information binding, when conversing again with the client, Ke Yitong
Personal information, such as phone number Direct Recognition client gender are crossed, so that corresponding casting voice is directly matched, without again
It is secondary to be identified, the time is effectively saved, working efficiency is improved.
Further, the processing unit further include:
Third parsing module, for the variation according to the existing customer mood characterization parameter within the unit air time,
Obtain the emotional change information of the client;
4th screening module in the personality database for constructing the emotional change information input in advance, is screened
To the corresponding existing customer personality of the emotional change information;
Second binding module, for binding the existing customer personality with the client personal information.
In the present embodiment, for response terminal in the communication process with client, the moment records feelings of the client in communication process
Thread change information, and the variation according to existing customer mood characterization parameter within the unit air time, the mood for obtaining client become
Change information.Wherein, emotional change information includes that mood characterization parameter changed air time and mood characterization parameter become
Change the specific mood characterization parameter of front and back.Response terminal inner is built with personality information bank in advance, will be various by testing in advance
Corresponding air time section is corresponding when personality information changes with mood characterization parameter, changes is grouped.For example, the personality of client is believed
Breath is " irritability ", and corresponding mood characterization parameter is initially " calmness ", and subsequent variation is " impatient ", generates the call of variation
Time is 1-3 minutes.Response terminal is after terminating primary call, according to the mood characterization parameter of client in entire communication process
Variation and while changing corresponding air time, input personality information bank screened, obtain the client's of this call
Corresponding personality information, i.e. existing customer personality, and the personal information of existing customer personality and client, such as phone number are carried out
Binding when conversing again so as to next time with the client, directly selects initial casting voice appropriate according to existing customer personality, than
If irritable client selects word speed initially to broadcast voice faster, customer experience is effectively improved.
The device of the self-service response of a kind of otherness provided in the present embodiment, by acquiring client in real time in communication process
Current voiceprint and current talking content, the current emotional information of client and call wish are identified, and according to client's feelings
Word speed, tone and the volume of thread dynamic adjustment casting voice, while client's call wish is met according to current talking content matching
Casting content, improve and the interaction integrality of client.
Referring to Fig. 3, a kind of computer equipment is also provided in the embodiment of the present application, which can be server,
Its internal structure can be as shown in Figure 3.The computer equipment includes processor, the memory, network connected by system bus
Interface and database.Wherein, the processor of the Computer Design is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program
And database.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.
The database of the computer equipment is for storing the data such as mood data library.The network interface of the computer equipment is used for and outside
Terminal by network connection communication.A kind of side of self-service response of otherness is realized when the computer program is executed by processor
Method.
Above-mentioned processor executes the step of method of the self-service response of above-mentioned otherness:
S1: the current talking information of acquisition client in real time;
S2: the current talking information is parsed, current talking content and current voiceprint are obtained;
S3: in the mood data library that the current voiceprint input is constructed in advance, screening obtains the current vocal print
The corresponding existing customer mood characterization parameter of information, the mood data library is by multiple groups voiceprint and customer anger characterization parameter
Corresponding composition;
S4: the corresponding current casting content of sensitive word and the customer anger in the current talking content are obtained respectively
The corresponding current response voice of characterization parameter;
S5: Xiang Suoshu client terminal sends the current casting content and the current response voice, so that the visitor
Content is currently broadcasted using described in the current response voice broadcast in family end.
Further, according in the mood data library that constructs the current voiceprint input in advance, screening obtains
The step of current voiceprint corresponding existing customer mood characterization parameter, comprising:
S301: the parsing current voiceprint obtains the current vocal print parameter of the client, the current vocal print parameter
Word speed, tone and volume including the client;
S302: the current vocal print parameter is inputted in the mood data library, according to the word speed, the tone and institute
The numerical intervals that volume is respectively fallen in are stated, the corresponding existing customer mood characterization parameter of the current vocal print parameter, institute are filtered out
Mood data library is stated to be made of numerical intervals and customer anger the characterization parameter correspondence of multiple groups vocal print parameter.
Further, foundation obtains the corresponding current casting content of the current talking content and the customer anger respectively
The step of characterization parameter corresponding current response voice, comprising:
S401: by the casting database that constructs in advance of current talking content input, screening obtains described currently broadcasting
Report content;
S402: in the response sound bank that existing customer mood characterization parameter input is constructed in advance, screening obtains institute
State current response voice, content is corresponding forms by multiple groups dialog context and casting for the casting database, the response sound bank
It is formed by multiple groups customer anger characterization parameter is corresponding with response voice.
Further, in the casting database that current talking content input is constructed in advance, screening obtains institute
The step of stating current casting content, comprising:
S4011: the sensitive word for including in the current talking content is identified;
S4012: the sensitive word is inputted in the casting database, and screening obtains casting corresponding with the sensitive word
Content;
S4013: being the current casting content by the corresponding casting curriculum offering of the sensitive word.
Further, before the step of current talking information of the real-time acquisition client, including
S6: obtaining call-information for the first time, and parses the call-information for the first time and obtain tonality feature, the call letter for the first time
Breath carries scene selection;
S7: the tonality feature is inputted to the gender data library constructed in advance, it is corresponding that screening obtains the tonality feature
Client gender, the gender data library are made of multiple groups tonality feature and client gender correspondence;
S8: in the casting sound bank that client gender input is constructed in advance, it is corresponding that screening obtains the client gender
Casting voice, while by the scene database that constructs in advance of scene selection input, screening obtains the scene selection and corresponds to
Scene content, voice is corresponding forms with casting by two groups of client genders for the casting sound bank, and the scene database has more
Group scene selection composition corresponding with scene content;
S9: Xiang Suoshu client terminal sends the scene content and the casting voice, so that the client uses
Scene content described in the casting voice broadcast.
Further, it generates the information of casting for the first time using scene content described in the casting voice broadcast and is output to institute
After the step of stating client terminal, comprising:
S10: the client gender and the personal information of the client of preparatory typing are bound.
Further, it generates the information of casting for the first time using scene content described in the casting voice broadcast and is output to institute
After the step of stating client terminal, comprising:
S11: according to variation of the existing customer mood characterization parameter within the unit air time, obtain the client's
Emotional change information;
S12: in the personality database that the emotional change information input is constructed in advance, screening obtains the emotional change
The corresponding existing customer personality of information;
S13: the existing customer personality is bound with the client personal information.
It will be understood by those skilled in the art that structure shown in Fig. 3, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme.
One embodiment of the application also provides a kind of computer readable storage medium, is stored thereon with computer program, calculates
A kind of machine program realizes otherness self-service response method when being executed by processor, specifically:
S1: the current talking information of acquisition client in real time;
S2: the current talking information is parsed, current talking content and current voiceprint are obtained;
S3: in the mood data library that the current voiceprint input is constructed in advance, screening obtains the current vocal print
The corresponding existing customer mood characterization parameter of information, the mood data library is by multiple groups voiceprint and customer anger characterization parameter
Corresponding composition;
S4: the corresponding current casting content of sensitive word and the customer anger in the current talking content are obtained respectively
The corresponding current response voice of characterization parameter;
S5: Xiang Suoshu client terminal sends the current casting content and the current response voice, so that the visitor
Content is currently broadcasted using described in the current response voice broadcast in family end.
Further, according in the mood data library that constructs the current voiceprint input in advance, screening obtains
The step of current voiceprint corresponding existing customer mood characterization parameter, comprising:
S301: the parsing current voiceprint obtains the current vocal print parameter of the client, the current vocal print parameter
Word speed, tone and volume including the client;
S302: the current vocal print parameter is inputted in the mood data library, according to the word speed, the tone and institute
The numerical intervals that volume is respectively fallen in are stated, the corresponding existing customer mood characterization parameter of the current vocal print parameter, institute are filtered out
Mood data library is stated to be made of numerical intervals and customer anger the characterization parameter correspondence of multiple groups vocal print parameter.
Further, foundation obtains the corresponding current casting content of the current talking content and the customer anger respectively
The step of characterization parameter corresponding current response voice, comprising:
S401: by the casting database that constructs in advance of current talking content input, screening obtains described currently broadcasting
Report content;
S402: in the response sound bank that existing customer mood characterization parameter input is constructed in advance, screening obtains institute
State current response voice, content is corresponding forms by multiple groups dialog context and casting for the casting database, the response sound bank
It is formed by multiple groups customer anger characterization parameter is corresponding with response voice.
Further, in the casting database that current talking content input is constructed in advance, screening obtains institute
The step of stating current casting content, comprising:
S4011: the sensitive word for including in the current talking content is identified;
S4012: the sensitive word is inputted in the casting database, and screening obtains casting corresponding with the sensitive word
Content;
S4013: being the current casting content by the corresponding casting curriculum offering of the sensitive word.
Further, before the step of current talking information of the real-time acquisition client, including
S6: obtaining call-information for the first time, and parses the call-information for the first time and obtain tonality feature, the call letter for the first time
Breath carries scene selection;
S7: the tonality feature is inputted to the gender data library constructed in advance, it is corresponding that screening obtains the tonality feature
Client gender, the gender data library are made of multiple groups tonality feature and client gender correspondence;
S8: in the casting sound bank that client gender input is constructed in advance, it is corresponding that screening obtains the client gender
Casting voice, while by the scene database that constructs in advance of scene selection input, screening obtains the scene selection and corresponds to
Scene content, voice is corresponding forms with casting by two groups of client genders for the casting sound bank, and the scene database has more
Group scene selection composition corresponding with scene content;
S9: Xiang Suoshu client terminal sends the scene content and the casting voice, so that the client uses
Scene content described in the casting voice broadcast.
Further, it generates the information of casting for the first time using scene content described in the casting voice broadcast and is output to institute
After the step of stating client terminal, comprising:
S10: the client gender and the personal information of the client of preparatory typing are bound.
Further, it generates the information of casting for the first time using scene content described in the casting voice broadcast and is output to institute
After the step of stating client terminal, comprising:
S11: according to variation of the existing customer mood characterization parameter within the unit air time, obtain the client's
Emotional change information;
S12: in the personality database that the emotional change information input is constructed in advance, screening obtains the emotional change
The corresponding existing customer personality of information;
S13: the existing customer personality is bound with the client personal information.
In conclusion being set for a kind of method, apparatus of the self-service response of otherness provided in the embodiment of the present application, computer
Standby and storage medium.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can store and a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
Any reference used in provided herein and embodiment to memory, storage, database or other media,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM can by diversified forms
, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double speed according to rate SDRAM (SSRSDRAM),
Enhanced SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) are direct
RAM (RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, device, article or the method that include a series of elements not only include those elements, and
And further include the other elements being not explicitly listed, or further include for this process, device, article or method institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, device of element, article or method.
The foregoing is merely preferred embodiment of the present application, are not intended to limit the scope of the patents of the application, all utilizations
Equivalent structure or equivalent flow shift made by present specification and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, similarly include in the scope of patent protection of the application.
Claims (10)
1. a kind of method of the self-service response of otherness, which is characterized in that be applied to response terminal, method includes:
The current talking information of acquisition client in real time;
The current talking information is parsed, current talking content and current voiceprint are obtained;
In the mood data library that the current voiceprint input is constructed in advance, it is corresponding that screening obtains the current voiceprint
Existing customer mood characterization parameter, the mood data library is by corresponding with customer anger characterization parameter group of multiple groups voiceprint
At;
The corresponding current casting content of sensitive word and customer anger characterization ginseng in the current talking content are obtained respectively
The corresponding current response voice of number;
The current casting content and the current response voice are sent to the client terminal, so that the client uses
Content is currently broadcasted described in the current response voice broadcast.
2. the method for the self-service response of otherness according to claim 1, which is characterized in that described to believe the current vocal print
In the mood data library that breath input constructs in advance, screening obtains the corresponding existing customer mood characterization ginseng of the current voiceprint
Several steps, comprising:
The current voiceprint is parsed, the current vocal print parameter of the client is obtained, the current vocal print parameter includes described
Word speed, tone and the volume of client;
The current vocal print parameter is inputted in the mood data library, according to the word speed, the tone and the volume point
The numerical intervals not fallen into filter out the corresponding existing customer mood characterization parameter of the current vocal print parameter, the mood number
It is made of according to library numerical intervals and the customer anger correspondence of multiple groups vocal print parameter.
3. the method for the self-service response of otherness according to claim 1, which is characterized in that it is described obtain respectively it is described current
The step of corresponding current casting content of dialog context and the customer anger characterization parameter corresponding current response voice, packet
It includes:
In the casting database that current talking content input is constructed in advance, screening obtains the current casting content;
In the response sound bank that existing customer mood characterization parameter input is constructed in advance, screening obtains the current response
Voice, content is corresponding forms with casting by multiple groups dialog context for the casting database, and the response sound bank has multiple groups client
Mood characterization parameter composition corresponding with response voice.
4. the method for the self-service response of otherness according to claim 3, which is characterized in that it is described will be in the current talking
Hold in the casting database that input constructs in advance, screen the step of obtaining the current casting content, comprising:
Identify the sensitive word for including in the current talking content;
The sensitive word is inputted in the casting database, screening obtains casting content corresponding with the sensitive word;
It is the current casting content by the corresponding casting curriculum offering of the sensitive word.
5. the method for the self-service response of otherness according to claim 1, which is characterized in that the real-time acquisition client's works as
Before the step of preceding call-information, including
Call-information for the first time is obtained, and parses the call-information for the first time and obtains tonality feature, the call-information for the first time carries
Scene selection;
The tonality feature is inputted to the gender data library constructed in advance, screening obtains the corresponding client's property of the tonality feature
Not, the gender data library is made of multiple groups tonality feature and client gender correspondence;
In the casting sound bank that client gender input is constructed in advance, screening obtains the corresponding casting language of the client gender
Sound, while in the scene database that scene selection input is constructed in advance, screening obtains the scene and selects in corresponding scene
Hold, the casting sound bank is by two groups of client genders and broadcasts that voice is corresponding forms, and the scene database has multiple groups scene to select
Select composition corresponding with scene content;
The scene content and the casting voice are sent to the client terminal, so that the client uses the casting
Scene content described in voice broadcast.
6. the method for the self-service response of otherness according to claim 5, which is characterized in that the generation uses the casting
The information of casting for the first time of scene content described in voice broadcast and the step of be output to the client terminal after, comprising:
The client gender and the client personal information of preparatory typing are bound.
7. the method for the self-service response of otherness according to claim 6, which is characterized in that the generation uses the casting
The information of casting for the first time of scene content described in voice broadcast and the step of be output to the client terminal after, comprising:
According to variation of the existing customer mood characterization parameter within the unit air time, the emotional change of the client is obtained
Information;
In the personality database that the emotional change information input is constructed in advance, it is corresponding that screening obtains the emotional change information
Existing customer personality;
The existing customer personality is bound with the client personal information.
8. a kind of device of the self-service response of otherness characterized by comprising
Acquisition module, for acquiring the current talking information of client in real time;
First parsing module obtains current talking content and current voiceprint for parsing the current talking information;
First screening module, for inputting the current voiceprint in the mood data library constructed in advance, screening obtains institute
State the corresponding existing customer mood characterization parameter of current voiceprint;
Module is obtained, for obtaining the corresponding current casting content of sensitive word and the visitor in the current talking content respectively
The corresponding current response voice of family mood characterization parameter;
First sending module, for sending the current casting content and the current response voice to the client terminal, with
So that the client currently broadcasts content using described in the current response voice broadcast.
9. a kind of computer equipment, including memory and processor, it is stored with computer program in the memory, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811446908.XA CN109451188B (en) | 2018-11-29 | 2018-11-29 | Method and device for differential self-help response, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811446908.XA CN109451188B (en) | 2018-11-29 | 2018-11-29 | Method and device for differential self-help response, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109451188A true CN109451188A (en) | 2019-03-08 |
CN109451188B CN109451188B (en) | 2022-03-18 |
Family
ID=65555181
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811446908.XA Active CN109451188B (en) | 2018-11-29 | 2018-11-29 | Method and device for differential self-help response, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109451188B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110062117A (en) * | 2019-04-08 | 2019-07-26 | 商客通尚景科技(上海)股份有限公司 | A kind of sonic detection and method for early warning |
CN110265062A (en) * | 2019-06-13 | 2019-09-20 | 上海指旺信息科技有限公司 | Collection method and device after intelligence based on mood detection is borrowed |
CN110719362A (en) * | 2019-09-10 | 2020-01-21 | 北京百度网讯科技有限公司 | Call processing method and device, electronic equipment and storage medium |
CN111193834A (en) * | 2019-12-16 | 2020-05-22 | 北京淇瑀信息科技有限公司 | Man-machine interaction method and device based on user sound characteristic analysis and electronic equipment |
CN111614845A (en) * | 2020-04-21 | 2020-09-01 | 深圳追一科技有限公司 | Human-computer dialogue human-set matching method and device, computer equipment and storage medium |
CN111933138A (en) * | 2020-08-20 | 2020-11-13 | Oppo(重庆)智能科技有限公司 | Voice control method, device, terminal and storage medium |
CN112233699A (en) * | 2020-10-13 | 2021-01-15 | 中移(杭州)信息技术有限公司 | Voice broadcasting method, intelligent voice device and computer readable storage medium |
CN113208592A (en) * | 2021-03-29 | 2021-08-06 | 济南大学 | Psychological test system with multiple answering modes |
TWI738610B (en) * | 2021-01-20 | 2021-09-01 | 橋良股份有限公司 | Recommended financial product and risk control system and implementation method thereof |
TWI741937B (en) * | 2021-01-20 | 2021-10-01 | 橋良股份有限公司 | Judgment system for suitability of talents and implementation method thereof |
CN113643684A (en) * | 2021-07-21 | 2021-11-12 | 广东电力信息科技有限公司 | Speech synthesis method, speech synthesis device, electronic equipment and storage medium |
CN113676527A (en) * | 2021-08-10 | 2021-11-19 | 未鲲(上海)科技服务有限公司 | Information pushing method, device, equipment and storage medium |
WO2021232594A1 (en) * | 2020-05-22 | 2021-11-25 | 深圳壹账通智能科技有限公司 | Speech emotion recognition method and apparatus, electronic device, and storage medium |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103634472A (en) * | 2013-12-06 | 2014-03-12 | 惠州Tcl移动通信有限公司 | Method, system and mobile phone for judging mood and character of user according to call voice |
EP2887627A1 (en) * | 2013-12-18 | 2015-06-24 | Telefonica Digital España, S.L.U. | Method and system for extracting out characteristics of a communication between at least one client and at least one support agent and computer program product thereof |
CN106294774A (en) * | 2016-08-11 | 2017-01-04 | 北京光年无限科技有限公司 | User individual data processing method based on dialogue service and device |
CN106649404A (en) * | 2015-11-04 | 2017-05-10 | 陈包容 | Session scene database creation method and apparatus |
CN106776936A (en) * | 2016-12-01 | 2017-05-31 | 上海智臻智能网络科技股份有限公司 | intelligent interactive method and system |
CN106874265A (en) * | 2015-12-10 | 2017-06-20 | 深圳新创客电子科技有限公司 | A kind of content outputting method matched with user emotion, electronic equipment and server |
CN107293310A (en) * | 2017-06-28 | 2017-10-24 | 上海航动科技有限公司 | A kind of user emotion analysis method and system |
CN107301213A (en) * | 2017-06-09 | 2017-10-27 | 腾讯科技(深圳)有限公司 | Intelligent answer method and device |
CN107329996A (en) * | 2017-06-08 | 2017-11-07 | 三峡大学 | A kind of chat robots system and chat method based on fuzzy neural network |
CN107645523A (en) * | 2016-07-21 | 2018-01-30 | 北京快乐智慧科技有限责任公司 | A kind of method and system of mood interaction |
CN108197115A (en) * | 2018-01-26 | 2018-06-22 | 上海智臻智能网络科技股份有限公司 | Intelligent interactive method, device, computer equipment and computer readable storage medium |
CN108363706A (en) * | 2017-01-25 | 2018-08-03 | 北京搜狗科技发展有限公司 | The method and apparatus of human-computer dialogue interaction, the device interacted for human-computer dialogue |
CN108648768A (en) * | 2018-04-16 | 2018-10-12 | 广州市菲玛尔咨询服务有限公司 | A kind of consulting recommendation method and its management system |
CN108735232A (en) * | 2017-04-24 | 2018-11-02 | 北京理工大学 | A kind of personality recognition methods and device |
-
2018
- 2018-11-29 CN CN201811446908.XA patent/CN109451188B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103634472A (en) * | 2013-12-06 | 2014-03-12 | 惠州Tcl移动通信有限公司 | Method, system and mobile phone for judging mood and character of user according to call voice |
EP2887627A1 (en) * | 2013-12-18 | 2015-06-24 | Telefonica Digital España, S.L.U. | Method and system for extracting out characteristics of a communication between at least one client and at least one support agent and computer program product thereof |
CN106649404A (en) * | 2015-11-04 | 2017-05-10 | 陈包容 | Session scene database creation method and apparatus |
CN106874265A (en) * | 2015-12-10 | 2017-06-20 | 深圳新创客电子科技有限公司 | A kind of content outputting method matched with user emotion, electronic equipment and server |
CN107645523A (en) * | 2016-07-21 | 2018-01-30 | 北京快乐智慧科技有限责任公司 | A kind of method and system of mood interaction |
CN106294774A (en) * | 2016-08-11 | 2017-01-04 | 北京光年无限科技有限公司 | User individual data processing method based on dialogue service and device |
CN106776936A (en) * | 2016-12-01 | 2017-05-31 | 上海智臻智能网络科技股份有限公司 | intelligent interactive method and system |
CN108363706A (en) * | 2017-01-25 | 2018-08-03 | 北京搜狗科技发展有限公司 | The method and apparatus of human-computer dialogue interaction, the device interacted for human-computer dialogue |
CN108735232A (en) * | 2017-04-24 | 2018-11-02 | 北京理工大学 | A kind of personality recognition methods and device |
CN107329996A (en) * | 2017-06-08 | 2017-11-07 | 三峡大学 | A kind of chat robots system and chat method based on fuzzy neural network |
CN107301213A (en) * | 2017-06-09 | 2017-10-27 | 腾讯科技(深圳)有限公司 | Intelligent answer method and device |
CN107293310A (en) * | 2017-06-28 | 2017-10-24 | 上海航动科技有限公司 | A kind of user emotion analysis method and system |
CN108197115A (en) * | 2018-01-26 | 2018-06-22 | 上海智臻智能网络科技股份有限公司 | Intelligent interactive method, device, computer equipment and computer readable storage medium |
CN108648768A (en) * | 2018-04-16 | 2018-10-12 | 广州市菲玛尔咨询服务有限公司 | A kind of consulting recommendation method and its management system |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110062117A (en) * | 2019-04-08 | 2019-07-26 | 商客通尚景科技(上海)股份有限公司 | A kind of sonic detection and method for early warning |
CN110265062A (en) * | 2019-06-13 | 2019-09-20 | 上海指旺信息科技有限公司 | Collection method and device after intelligence based on mood detection is borrowed |
CN110719362A (en) * | 2019-09-10 | 2020-01-21 | 北京百度网讯科技有限公司 | Call processing method and device, electronic equipment and storage medium |
CN111193834A (en) * | 2019-12-16 | 2020-05-22 | 北京淇瑀信息科技有限公司 | Man-machine interaction method and device based on user sound characteristic analysis and electronic equipment |
CN111193834B (en) * | 2019-12-16 | 2022-04-15 | 北京淇瑀信息科技有限公司 | Man-machine interaction method and device based on user sound characteristic analysis and electronic equipment |
CN111614845A (en) * | 2020-04-21 | 2020-09-01 | 深圳追一科技有限公司 | Human-computer dialogue human-set matching method and device, computer equipment and storage medium |
WO2021232594A1 (en) * | 2020-05-22 | 2021-11-25 | 深圳壹账通智能科技有限公司 | Speech emotion recognition method and apparatus, electronic device, and storage medium |
CN111933138A (en) * | 2020-08-20 | 2020-11-13 | Oppo(重庆)智能科技有限公司 | Voice control method, device, terminal and storage medium |
CN111933138B (en) * | 2020-08-20 | 2022-10-21 | Oppo(重庆)智能科技有限公司 | Voice control method, device, terminal and storage medium |
CN112233699A (en) * | 2020-10-13 | 2021-01-15 | 中移(杭州)信息技术有限公司 | Voice broadcasting method, intelligent voice device and computer readable storage medium |
CN112233699B (en) * | 2020-10-13 | 2023-04-28 | 中移(杭州)信息技术有限公司 | Voice broadcasting method, intelligent voice equipment and computer readable storage medium |
TWI738610B (en) * | 2021-01-20 | 2021-09-01 | 橋良股份有限公司 | Recommended financial product and risk control system and implementation method thereof |
TWI741937B (en) * | 2021-01-20 | 2021-10-01 | 橋良股份有限公司 | Judgment system for suitability of talents and implementation method thereof |
CN113208592A (en) * | 2021-03-29 | 2021-08-06 | 济南大学 | Psychological test system with multiple answering modes |
CN113208592B (en) * | 2021-03-29 | 2022-08-16 | 济南大学 | Psychological test system with multiple answering modes |
CN113643684A (en) * | 2021-07-21 | 2021-11-12 | 广东电力信息科技有限公司 | Speech synthesis method, speech synthesis device, electronic equipment and storage medium |
CN113643684B (en) * | 2021-07-21 | 2024-02-27 | 广东电力信息科技有限公司 | Speech synthesis method, device, electronic equipment and storage medium |
CN113676527A (en) * | 2021-08-10 | 2021-11-19 | 未鲲(上海)科技服务有限公司 | Information pushing method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109451188B (en) | 2022-03-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109451188A (en) | Method, apparatus, computer equipment and the storage medium of the self-service response of otherness | |
US9813551B2 (en) | Multi-party conversation analyzer and logger | |
US10083686B2 (en) | Analysis object determination device, analysis object determination method and computer-readable medium | |
CN112804400A (en) | Customer service call voice quality inspection method and device, electronic equipment and storage medium | |
CN107818798A (en) | Customer service quality evaluating method, device, equipment and storage medium | |
CN110177182B (en) | Sensitive data processing method and device, computer equipment and storage medium | |
CN110047490A (en) | Method for recognizing sound-groove, device, equipment and computer readable storage medium | |
WO2014069076A1 (en) | Conversation analysis device and conversation analysis method | |
DE10054583C2 (en) | Method and apparatus for recording, searching and playing back notes | |
CN109272993A (en) | Recognition methods, device, computer equipment and the storage medium of voice class | |
Enzinger et al. | Empirical test of the performance of an acoustic-phonetic approach to forensic voice comparison under conditions similar to those of a real case | |
US20180308501A1 (en) | Multi speaker attribution using personal grammar detection | |
CN109560941A (en) | Minutes method, apparatus, intelligent terminal and storage medium | |
CN109473101A (en) | A kind of speech chip structures and methods of the random question and answer of differentiation | |
CN109460891A (en) | Data processing method, device and computer equipment based on satisfaction evaluation | |
CN110246503A (en) | Blacklist vocal print base construction method, device, computer equipment and storage medium | |
CN113191787A (en) | Telecommunication data processing method, device electronic equipment and storage medium | |
CN113870892A (en) | Conference recording method, device, equipment and storage medium based on voice recognition | |
CN110602334A (en) | Intelligent outbound method and system based on man-machine cooperation | |
CN111062221A (en) | Data processing method, data processing device, electronic equipment and storage medium | |
CN105845143A (en) | Speaker confirmation method and speaker confirmation system based on support vector machine | |
KR20210109914A (en) | Apparatus and method for filling electronic document using dialogue comprehension based on format of electronic document | |
CN110310127A (en) | Recording acquisition methods, device, computer equipment and storage medium | |
CN113194210B (en) | Voice call access method and device | |
DE60014583T2 (en) | METHOD AND DEVICE FOR INTEGRITY TESTING OF USER INTERFACES OF VOICE CONTROLLED EQUIPMENT |
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 |