CN109712618A - A kind of control method of voice service, device, storage medium and air-conditioning - Google Patents
A kind of control method of voice service, device, storage medium and air-conditioning Download PDFInfo
- Publication number
- CN109712618A CN109712618A CN201811489305.8A CN201811489305A CN109712618A CN 109712618 A CN109712618 A CN 109712618A CN 201811489305 A CN201811489305 A CN 201811489305A CN 109712618 A CN109712618 A CN 109712618A
- Authority
- CN
- China
- Prior art keywords
- user
- evaluation
- voice service
- phonetic order
- evaluation 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.)
- Pending
Links
Abstract
The invention discloses a kind of control method of voice service, device, storage medium and air-conditionings, this method comprises: obtaining the evaluation information that user is fed back during using the voice service of apparatus to be controlled;Wherein, the evaluation information, comprising: at least one of Speech Assessment information, word evaluation information, key evaluation information;The voice service is optimized according to the evaluation information, to realize that user's next time uses the voice service after optimization.The solution of the present invention, the user that can solve speech production interact very different, voice technology the agreement also variant inconvenient problem with use for leading to user, achieve the effect that promote property easy to use.
Description
Technical field
The invention belongs to voice control technology fields, and in particular to a kind of control method of voice service, device, storage are situated between
Matter and air-conditioning more particularly to a kind of voice service feedback method, device, storage medium and AI air-conditioning.
Background technique
Nowadays voice technology is more and more burning hoter, and the speech production derived is also more and more.User's interaction of speech production
Very different, the agreement of voice technology is also variant.In view of the situation, it is necessary to find out one kind and be more in line with user's use habit
Used interactive voice mode.
Such as: because different producers is each different to the processing logic of voice, same phonetic order, some equipment can
To identify, some equipment is not all right.User will not go adjustment certainly when using multiple voice equipment according to the difference of equipment
Oneself tongue, the usage experience that this problem will lead to user decrease.
Summary of the invention
It is an object of the present invention in view of the foregoing drawbacks, provide control method, the device, storage Jie of a kind of voice service
Matter and air-conditioning, very different, voice technology the agreement of user's interaction to solve speech production in the prior art is also variant to be led
It applies the inconvenient problem with use at family, achievees the effect that promote property easy to use.
The present invention provides a kind of control method of voice service, comprising: obtains user and takes using the voice of apparatus to be controlled
The evaluation information fed back during business;Wherein, the evaluation information, comprising: Speech Assessment information, is pressed at word evaluation information
At least one of key evaluation information;The voice service is optimized according to the evaluation information, to realize user's next time
Use the voice service after optimization.
Optionally, the evaluation information that user is fed back during using the voice service of apparatus to be controlled is obtained, comprising: really
The period is collected in the fixed evaluation for collecting the evaluation information that user is fed back during using the voice service of apparatus to be controlled;?
The evaluation was collected in the period, and the evaluation information fed back during using the voice service of apparatus to be controlled to user is received
Collection.
Optionally it is determined that for collecting the evaluation information that user is fed back during using the voice service of apparatus to be controlled
Evaluation collect the period, comprising: determine whether apparatus to be controlled receives having executed in the setting period after a upper phonetic order
To next phonetic order;If not receiving next phonetic order within the setting period, it is determined that the setting period
The period is collected for the evaluation;Alternatively, if receiving next phonetic order within the setting period, it is determined that described upper one
Phonetic order assigned after executing with the next phonetic order during period when evaluation collection period.
Optionally, the voice service is optimized according to the evaluation information, comprising: determine apparatus to be controlled to described
Phonetic order during voice service identifies whether success;If the identification success to the phonetic order, calls setting
The first Keywords matching model, the first evaluation keyword in the evaluation information is matched, to extract described the
One evaluation keyword;User demand is determined according to the first evaluation keyword;Optimize the voice clothes by the user demand
Business.
Optionally, the voice service is optimized according to the evaluation information, further includes: if to the phonetic order
Identification it is failed, then call the second Keywords matching model of setting, in the evaluation information second evaluation keyword
It is matched, to extract the second evaluation keyword;User's evaluation is determined according to the first evaluation keyword, and marks institute
State the corresponding phonetic order of user's evaluation;By the corresponding voice explained information and increase to the voice service of the phonetic order
In instruction database, to be identified when receiving the phonetic order next time by the explanation information.
Optionally, further includes: determine whether that receiving user allows to obtain the grant instruction of the evaluation information;If receiving
To the grant instruction, the evaluation information that user is fed back during using the voice service of apparatus to be controlled is just obtained;With/
Or, obtaining the phonetic order that user is sent during using the voice service of apparatus to be controlled;The phonetic order is carried out
Identification, obtains meaning of one's words keyword;The phonetic order is executed according to the meaning of one's words keyword, to realize user to apparatus to be controlled
The use of voice service.
Match with the above method, another aspect of the present invention provides a kind of control device of voice service, comprising: obtain single
Member, the evaluation information fed back during using the voice service of apparatus to be controlled for obtaining user;Wherein, the evaluation letter
Breath, comprising: at least one of Speech Assessment information, word evaluation information, key evaluation information;Control unit is used for basis
The evaluation information optimizes the voice service, to realize that user's next time uses the voice service after optimization.
Optionally, the acquiring unit obtains the evaluation that user is fed back during using the voice service of apparatus to be controlled
Information, comprising: determine for collecting commenting for evaluation information that user is fed back during using the voice service of apparatus to be controlled
Valence collects the period;It is collected in the period in the evaluation, user is fed back during using the voice service of apparatus to be controlled
Evaluation information is collected.
Optionally, the acquiring unit determines anti-during using the voice service of apparatus to be controlled for collecting user
The period is collected in the evaluation of the evaluation information of feedback, comprising: determines apparatus to be controlled when having executed the setting after a upper phonetic order
Next phonetic order whether is received in section;If not receiving next phonetic order within the setting period, it is determined that
It is described to set the period as the evaluation collection period;Alternatively, if receiving next phonetic order within the setting period,
The evaluation is collected when determining the period during assigning after a upper phonetic order executes with the next phonetic order
Period.
Optionally, described control unit optimizes the voice service according to the evaluation information, comprising: determine to
Control equipment identifies whether success to the phonetic order during the voice service;If being identified as to the phonetic order
Function then calls the first Keywords matching model of setting, evaluates matching for keyword to first in the evaluation information,
To extract the first evaluation keyword;User demand is determined according to the first evaluation keyword;It is excellent by the user demand
Change the voice service.
Optionally, described control unit optimizes the voice service according to the evaluation information, further includes: if right
The identification of the phonetic order is failed, then calls the second Keywords matching model of setting, in the evaluation information
Two evaluation keywords are matched, to extract the second evaluation keyword;User is determined according to the first evaluation keyword
Evaluation, and mark the corresponding phonetic order of the user's evaluation;The corresponding explanation information of the phonetic order is increased to described
In the phonetic order library of voice service, to be identified when receiving the phonetic order next time by the explanation information.
Optionally, further includes: described control unit is also used to determine whether that receiving user allows to obtain the evaluation letter
The grant instruction of breath;Described control unit just obtains user and is using apparatus to be controlled if being also used to receive the grant instruction
Voice service during the evaluation information that feeds back;And/or described control unit, it is also used to obtain user using to be controlled
The phonetic order sent during the voice service of equipment;Described control unit is also used to know the phonetic order
Not, meaning of one's words keyword is obtained;Described control unit is also used to execute the phonetic order according to the meaning of one's words keyword, with reality
Use of the current family to the voice service of apparatus to be controlled.
Match with above-mentioned apparatus, further aspect of the present invention provides a kind of air-conditioning, comprising: above-described voice service
Control device.
Match with the above method, further aspect of the present invention provides a kind of storage medium, comprising: deposited in the storage medium
Contain a plurality of instruction;The a plurality of instruction, for being loaded by processor and being executed the control method of above-described voice service.
Match with the above method, further aspect of the present invention provides a kind of air-conditioning, comprising: processor, it is a plurality of for executing
Instruction;Memory, for storing a plurality of instruction;Wherein, a plurality of instruction, for being stored by the memory, and by described
Processor loads and executes the control method of above-described voice service.
The solution of the present invention, by extracting user's evaluation in relation to interactive voice during using speech ciphering equipment,
It is analyzed by data, optimizes the interactive mode of voice system, user experience can be improved.
Further, the solution of the present invention is parsed by semanteme, and it is related during using speech ciphering equipment to extract user
The evaluation of interactive voice, is imported into user feedback system, is analyzed by data, obtains product part to be optimized, can optimize language
The interactive mode of sound technology improves user experience.
Further, the solution of the present invention, by analyzing the evaluation of user, for the unsatisfied place of user to voice system
Processing logic optimize, user experience can be promoted.
Further, the solution of the present invention, by analyzing the evaluation of user, for the unsatisfied place of user to voice system
Processing logic optimize, the efficiency of service and service effectiveness of voice service can be promoted.
Further, the solution of the present invention, by analyzing the evaluation of user, for the unsatisfied place of user to voice system
Processing logic optimize, the versatility and the scope of application of speech ciphering equipment can be promoted.
The solution of the present invention as a result, by extracting user's related interactive voice during using speech ciphering equipment
Evaluation, is analyzed by data, optimizes the interactive mode of voice system, solves user's interaction good and the bad of speech production in the prior art
Uneven, voice technology the agreement also variant inconvenient problem with use for leading to user, thus, overcome and uses in the prior art
Inconvenient, poor user experience and poor universality defect, realizes beneficial effect easy to use, user experience is good and versatility is good
Fruit.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Detailed description of the invention
Fig. 1 is the flow diagram of an embodiment of the control method of voice service of the invention;
Fig. 2 is the evaluation for obtaining user in method of the invention and feeding back during using the voice service of apparatus to be controlled
The flow diagram of one embodiment of information;
Fig. 3 is determining anti-during using the voice service of apparatus to be controlled for collecting user in method of the invention
The flow diagram of the embodiment of period is collected in the evaluation of the evaluation information of feedback;
Fig. 4 is one optimized in the case where identifying successfully to phonetic order to voice service in method of the invention
The flow diagram of embodiment;
Fig. 5 is one optimized to phonetic order recognition failures to voice service in method of the invention
The flow diagram of embodiment;
Fig. 6 is to determine whether user allows to collect the process signal of an embodiment of its evaluation information in method of the invention
Figure;
Fig. 7 is the flow diagram for realizing an embodiment of voice service in method of the invention by phonetic order;
Fig. 8 is the structural schematic diagram of an embodiment of the control device of voice service of the invention;
Fig. 9 is the flow diagram of an embodiment of air-conditioning of the invention.
In conjunction with attached drawing, appended drawing reference is as follows in the embodiment of the present invention:
102- acquiring unit;104- control unit.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the specific embodiment of the invention and
Technical solution of the present invention is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
According to an embodiment of the invention, a kind of control method of voice service is provided, method of the invention as shown in Figure 1
An embodiment flow diagram.The control method of the voice service may include: step S110 and step S120.
At step S110, the evaluation information that user is fed back during using the voice service of apparatus to be controlled is obtained.
Wherein, the evaluation information, may include: Speech Assessment information, word evaluation information, in key evaluation information at least it
One.
It is alternatively possible to which user is obtained in method of the invention as shown in connection with fig. 2 in the voice service using apparatus to be controlled
During the embodiment flow diagram of evaluation information that feeds back, further illustrate that user is obtained in step S110 to be used
The detailed process of the evaluation information fed back during the voice service of apparatus to be controlled may include: step S210 and step
S220。
Step S210, determining can be used for collecting that user fed back during using the voice service of apparatus to be controlled comments
The period is collected in the evaluation of valence information.
More it can be used for collecting user using to be controlled it is alternatively possible to determine in method of the invention as shown in connection with fig. 3
The embodiment flow diagram of period is collected in the evaluation of the evaluation information fed back during the voice service of equipment, further
Illustrate that determination can be used for collecting the evaluation that user is fed back during using the voice service of apparatus to be controlled in step S210
The detailed process of period is collected in the evaluation of information, may include: step S310 to step S330.
Whether step S310 determines apparatus to be controlled in the case where having executed and receiving in the setting period after a upper phonetic order
One phonetic order.
Step S320, if not receiving next phonetic order within the setting period, it is determined that the setting period
The period is collected for the evaluation.
Alternatively, step S330, if receiving next phonetic order within the setting period, it is determined that described upper one
Phonetic order assigned after executing with the next phonetic order during period when the evaluation collection period.
Such as: a period of time after user instruction will be executed as commenting on acquisition time, when in the solution of the present invention by this
Between span be set to 2 minutes, if user does not continue to assign next phonetic order in 2 minutes, this belong within 2 minutes comment receive
Collect the time, terminates comment later within 2 minutes and collect, if user has assigned next phonetic order, a upper language in this 2 minutes
After sound instruction execution with during next instruction issuing for comment acquisition time.The efficiency for collecting voice is both improved in this way,
The influence degree of privacy to user will be arrived minimum.
As a result, by the length according to the time interval before being assigned after a upper phonetic order with next phonetic order,
Determine that the period is collected in different evaluation, avoiding, which influences user, uses, and also ensures the convenience collect to evaluation information and reliable
Property.
Step S220 is collected in the period in the evaluation, to user during using the voice service of apparatus to be controlled
The evaluation information of feedback is collected.
As a result, by during using voice service evaluation collect in the period to the evaluation information of user feedback into
Row is collected, and can be collected evaluation information in the period is collected in evaluation, be will not influence the normal use of user, and ensure that evaluation
The reliability and comprehensive that information is collected.
At step S120, the voice service is optimized according to the evaluation information, to realize that user makes next time
With the voice service after optimization.Such as: the evaluation information is analyzed, analysis result is obtained.According to the analysis result
The voice service is optimized, to realize that user's next time uses the voice service after optimization.
Such as: in order to allow voice technology to be more in line with the habit of speaking of people, more meet the use demand of user, needs pair
The use feedback of user is collected;It can be parsed by semanteme, it is related during using speech ciphering equipment to extract user
The evaluation of interactive voice, is imported into user feedback system, is analyzed by data, obtains product part to be optimized;Optimize voice skill
The interactive mode of art improves user experience.
Such as: user in use, may make an appraisal to the service condition of speech ciphering equipment.Analysis can be passed through
The evaluation of user optimizes the processing logic of voice system for the unsatisfied place of user.
Such as: by speech analysis, user's evaluation in relation to interactive voice during using speech ciphering equipment is extracted,
It is imported into user feedback system, is analyzed by data, the interactive mode of voice system is optimized.Such as: can according to speech analysis at
Whether function, corresponding Keywords matching model is called, user comment is matched, so as to improve matching efficiency.For another example: use can be extracted
Family comment, data analysis, in such a way that this optimizes interactive voice, is allowed to more meet user demand.
As a result, by obtaining the evaluation information of user feedback during using voice service, and then according to the evaluation
Information optimizes voice service, promotes the convenience that user uses, and hommization is good.
Optionally, the voice service is optimized according to the evaluation information in step S120, may include: right
The process that phonetic order optimizes voice service in the case where identifying successfully.
Below with reference in method of the invention shown in Fig. 4 in the case where being identified successfully to phonetic order to voice service into
Row optimization an embodiment flow diagram, further illustrate in the case where being identified successfully to phonetic order to voice service into
The detailed process of row optimization, may include: step S410 to step S440.
Step S410 determines that apparatus to be controlled identifies whether success to the phonetic order during the voice service.Example
Such as: determining whether successfully to identify the phonetic order that currently can be used for controlling apparatus to be controlled, that is, whether to determine apparatus to be controlled
Success identifies the phonetic order that currently can be used for controlling apparatus to be controlled.
Step S420 is right if the identification success to the phonetic order, calls the first Keywords matching model of setting
The first evaluation keyword in the evaluation information match, to extract the first evaluation keyword.
Step S430 determines user demand according to the first evaluation keyword.
Step S440 optimizes the voice service by the user demand, to realize the optimization to the voice service.
Such as: voice system calls the first keyword models, which identifies successfully for user instruction
The case where establish keyword models, for matching user's evaluation keyword.
Such as: in 2 minutes after equipment has executed user instruction, equipment calls keyword monitoring module monitors user's language
Sound, if user mentions the word with Keywords matching, equipment, which will be called, comments on parsing module, 2 seconds before and after interception user's keyword
Voice is parsed, and is obtained user comment text and is imported into user feedback system, and user is extracted in the analysis of further progress data
Demand optimizes voice system interactive mode.
As a result, by optimizing in the case where identifying successfully to phonetic order to voice service, voice can be directed to
The successful voice service of instruction identification optimizes, and further promotes user experience.
Still optionally further, the voice service is optimized according to the evaluation information in step S120, it can be with
It include: the process optimized to phonetic order recognition failures to voice service.
Below with reference in method of the invention shown in Fig. 5 to phonetic order recognition failures to voice service into
Row optimization an embodiment flow diagram, further illustrate to phonetic order recognition failures to voice service into
The detailed process of row optimization, may include: step S510 to step S530.
Step S510 calls the second Keywords matching model of setting if failed to the identification of the phonetic order,
The second evaluation keyword in the evaluation information is matched, to extract the second evaluation keyword.
Step S520 determines user's evaluation according to the first evaluation keyword, and marks the user's evaluation corresponding
Phonetic order.
Step S530, by the corresponding phonetic order library explained information and increase to the voice service of the phonetic order
In, to be identified when receiving the phonetic order next time by the explanation information.
Such as: voice system not can recognize that user instruction, and feedback user recognition failures.Voice system calls second to close
The case where keyword model, which is directed to user instruction recognition failures, establishes keyword models, and user, which matches, to be used
Family keyword.
Such as: unlike the first keyword models, after extracting user's evaluation, user's evaluation is marked
Note, marks its corresponding user instruction.Because the user's evaluation is the explanation to the user instruction not identified, by analysis
Afterwards, it after the corresponding explanation of this unrecognized phonetic order is entered into system by voice system, is encountered similarly in next time
After phonetic order, voice system, which can recognize that, to be come, and improves user experience.
As a result, by optimizing to phonetic order recognition failures to voice service, voice can be directed to
The voice service of instruction identification failure optimizes, to facilitate greatly improve use to the use of the phonetic order user's next time
The convenience and reliability that family uses, intelligence degree are high.
It can also include following any control situation in an optional embodiment.
First control situation: determine whether user allows to collect the process of its evaluation information.
Determine whether user allows to collect an embodiment of its evaluation information below with reference in method of the invention shown in Fig. 6
Flow diagram further illustrates the detailed process for determining whether user allows to collect its evaluation information, may include: step
S610 and step S620.
Step S610, obtain the evaluation information that is fed back during using the voice service of apparatus to be controlled of user it
Before, it is determined whether receiving user allows to obtain the grant instruction of the evaluation information.
Step S620 just obtains user in the mistake of the voice service using apparatus to be controlled if receiving the grant instruction
The evaluation information fed back in journey.During specifically used, if not receiving the grant instruction, do not obtain user use to
The evaluation information fed back during the voice service for controlling equipment, to protect privacy of user.
Such as: the problem of considering privacy of user, user can choose whether to open voice service feedback according to self-demand
Function.The function is related to privacy of user problem, it is contemplated that certain customers may think that the machine of this automatic feedback user's evaluation
System has invaded its privacy, therefore user can voluntarily choose whether to open the function.Generally after phonetic order execution, user may needle
To response speed, accuracy rate etc. is executed to voice service evaluation.
As a result, by collecting evaluation information according to the grant instruction of user, it can satisfy the different demands of different user, protect
The personal secrets of user are protected, hommization is more preferable.
Second control situation: the process of voice service is realized by phonetic order.
Realize that an embodiment process of voice service is illustrated below with reference to phonetic order is pressed in method of the invention shown in Fig. 7
Figure further illustrates the detailed process for realizing voice service by phonetic order, may include: step S710 and step S720.
Step S710, obtain the evaluation information that is fed back during using the voice service of apparatus to be controlled of user it
Before, obtain the phonetic order that user is sent during using the voice service of apparatus to be controlled.Such as: obtain what user sent
It can be used for controlling the phonetic order of apparatus to be controlled.
Step S720 identifies the phonetic order, obtains meaning of one's words keyword.
Step S730 executes the phonetic order according to the meaning of one's words keyword, to realize user to the language of apparatus to be controlled
The use of sound service.
Such as: voice system can identify user instruction, and can respond instruction.
As a result, by being identified to obtain meaning of one's words keyword to phonetic order, the use to voice service, reliability are realized
High, high safety.
Through a large amount of verification experimental verification, using the technical solution of the present embodiment, speech ciphering equipment is being used by extracting user
During the evaluation in relation to interactive voice, analyzed by data, optimize the interactive mode of voice system, user's body can be improved
It tests.
According to an embodiment of the invention, additionally providing a kind of control of voice service of the control method corresponding to voice service
Device processed.The structural schematic diagram of one embodiment of the device of the invention shown in Figure 8.The control device of the voice service can be with
It include: acquiring unit 102 and control unit 104.
In an optional example, acquiring unit 102 can be used for obtaining user in the voice service using apparatus to be controlled
During the evaluation information that feeds back.Wherein, the evaluation information, may include: Speech Assessment information, word evaluation information,
At least one of key evaluation information.The concrete function of the acquiring unit 102 and processing are referring to step S110.
Optionally, the acquiring unit 102 obtains what user was fed back during using the voice service of apparatus to be controlled
Evaluation information may include:
The acquiring unit 102, specifically can be also used for determination can be used for collecting user in the language using apparatus to be controlled
The period is collected in the evaluation of the evaluation information fed back during sound service.The concrete function of the acquiring unit 102 and processing are also joined
See step S210.
More optionally, the acquiring unit 102, which determines, can be used for collecting user in the voice service using apparatus to be controlled
During the evaluation of evaluation information fed back collect the period, may include:
The acquiring unit 102 specifically can be also used for determining apparatus to be controlled after having executed a upper phonetic order
Next phonetic order whether is received in the setting period.The concrete function of the acquiring unit 102 and processing see also step
S310。
The acquiring unit 102 refers to if specifically can be also used for not receiving next voice within the setting period
It enables, it is determined that described to set the period as the evaluation collection period.The concrete function of the acquiring unit 102 and processing see also step
Rapid S320.
Such as: a period of time after user instruction will be executed as commenting on acquisition time, when in the solution of the present invention by this
Between span be set to 2 minutes, if user does not continue to assign next phonetic order in 2 minutes, this belong within 2 minutes comment receive
Collect the time, terminates comment later within 2 minutes and collect, if user has assigned next phonetic order, a upper language in this 2 minutes
After sound instruction execution with during next instruction issuing for comment acquisition time.The efficiency for collecting voice is both improved in this way,
The influence degree of privacy to user will be arrived minimum.
As a result, by the length according to the time interval before being assigned after a upper phonetic order with next phonetic order,
Determine that the period is collected in different evaluation, avoiding, which influences user, uses, and also ensures the convenience collect to evaluation information and reliable
Property.
The acquiring unit 102 specifically can be also used for collecting in the period in the evaluation, be set to user using to be controlled
The evaluation information fed back during standby voice service is collected.The concrete function of the acquiring unit 102 and processing are also joined
See step S220.
As a result, by during using voice service evaluation collect in the period to the evaluation information of user feedback into
Row is collected, and can be collected evaluation information in the period is collected in evaluation, be will not influence the normal use of user, and ensure that evaluation
The reliability and comprehensive that information is collected.
Alternatively, the acquiring unit 102, if specifically can be also used for receiving next voice within the setting period
Instruction, it is determined that a upper phonetic order assigns when period institute's commentary of period with the next phonetic order after executing
Valence collects the period.The concrete function of the acquiring unit 102 and processing see also step S330.
In an optional example, control unit 104, can be used for according to the evaluation information to the voice service into
Row optimization, to realize that user's next time uses the voice service after optimization.Such as: the evaluation information is analyzed, is divided
Analyse result.The voice service is optimized according to the analysis result, to realize that user's next time uses the voice after optimization
Service.The concrete function of the control unit 104 and processing are referring to step S120.
Such as: in order to allow voice technology to be more in line with the habit of speaking of people, more meet the use demand of user, needs pair
The use feedback of user is collected;It can be parsed by semanteme, it is related during using speech ciphering equipment to extract user
The evaluation of interactive voice, is imported into user feedback system, is analyzed by data, obtains product part to be optimized;Optimize voice skill
The interactive mode of art improves user experience.
Such as: user in use, may make an appraisal to the service condition of speech ciphering equipment.Analysis can be passed through
The evaluation of user optimizes the processing logic of voice system for the unsatisfied place of user.
Such as: by speech analysis, user's evaluation in relation to interactive voice during using speech ciphering equipment is extracted,
It is imported into user feedback system, is analyzed by data, the interactive mode of voice system is optimized.Such as: can according to speech analysis at
Whether function, corresponding Keywords matching model is called, user comment is matched, so as to improve matching efficiency.For another example: use can be extracted
Family comment, data analysis, in such a way that this optimizes interactive voice, is allowed to more meet user demand.
As a result, by obtaining the evaluation information of user feedback during using voice service, and then according to the evaluation
Information optimizes voice service, promotes the convenience that user uses, and hommization is good.
Optionally, described control unit 104 optimizes the voice service according to the evaluation information, can wrap
It includes:
Described control unit 104 specifically can be also used for determining apparatus to be controlled to the voice during the voice service
Instruction identifies whether success.Such as: determine whether successfully to identify the phonetic order that currently can be used for controlling apparatus to be controlled,
Determine whether apparatus to be controlled successfully identifies the phonetic order that currently can be used for controlling apparatus to be controlled.The control unit 104
Concrete function and processing see also step S410.
Described control unit 104 calls setting if specifically can be also used for the success of the identification to the phonetic order
First Keywords matching model, to matching for the first evaluation keyword in the evaluation information, to extract described first
Evaluate keyword.The concrete function of the control unit 104 and processing see also step S420.
Described control unit 104 specifically can be also used for determining user demand according to the first evaluation keyword.The control
The concrete function of unit 104 processed and processing see also step S430.
Described control unit 104 specifically can be also used for optimizing the voice service by the user demand, with realization pair
The optimization of the voice service.The concrete function of the control unit 104 and processing see also step S440.
Such as: voice system calls the first keyword models, which identifies successfully for user instruction
The case where establish keyword models, for matching user's evaluation keyword.
Such as: in 2 minutes after equipment has executed user instruction, equipment calls keyword monitoring module monitors user's language
Sound, if user mentions the word with Keywords matching, equipment, which will be called, comments on parsing module, 2 seconds before and after interception user's keyword
Voice is parsed, and is obtained user comment text and is imported into user feedback system, and user is extracted in the analysis of further progress data
Demand optimizes voice system interactive mode.
As a result, by optimizing in the case where identifying successfully to phonetic order to voice service, voice can be directed to
The successful voice service of instruction identification optimizes, and further promotes user experience.
Still optionally further, described control unit 104 optimizes the voice service according to the evaluation information, also
May include:
Described control unit 104 calls setting if specifically can be also used for failed to the identification of the phonetic order
The second Keywords matching model, in the evaluation information second evaluation keyword match, to extract described second
Evaluate keyword.The concrete function of the control unit 104 and processing see also step S510.
Described control unit 104 specifically can be also used for determining user's evaluation according to the first evaluation keyword, and mark
Remember the corresponding phonetic order of the user's evaluation.The concrete function of the control unit 104 and processing see also step S520.
Described control unit 104 specifically can be also used for increasing to the corresponding explanation information of the phonetic order into described
In the phonetic order library of voice service, to be identified when receiving the phonetic order next time by the explanation information.It should
The concrete function of control unit 104 and processing see also step S530.
Such as: voice system not can recognize that user instruction, and feedback user recognition failures.Voice system calls second to close
The case where keyword model, which is directed to user instruction recognition failures, establishes keyword models, and user, which matches, to be used
Family keyword.
Such as: unlike the first keyword models, after extracting user's evaluation, user's evaluation is marked
Note, marks its corresponding user instruction.Because the user's evaluation is the explanation to the user instruction not identified, by analysis
Afterwards, it after the corresponding explanation of this unrecognized phonetic order is entered into system by voice system, is encountered similarly in next time
After phonetic order, voice system, which can recognize that, to be come, and improves user experience.
As a result, by optimizing to phonetic order recognition failures to voice service, voice can be directed to
The voice service of instruction identification failure optimizes, to facilitate greatly improve use to the use of the phonetic order user's next time
The convenience and reliability that family uses, intelligence degree are high.
It can also include following any control situation in an optional embodiment.
First control situation: it determines whether user allows to collect the process of its evaluation information, specifically can be such that
Described control unit 104 can be also used in acquisition user during using the voice service of apparatus to be controlled
Before the evaluation information of feedback, it is determined whether receiving user allows to obtain the grant instruction of the evaluation information.The control list
The concrete function of member 104 and processing see also step S610.
Described control unit 104 is just obtained user and is set using to be controlled if can be also used for receiving the grant instruction
The evaluation information fed back during standby voice service.During specifically used, if not receiving the grant instruction, no
The evaluation information that user is fed back during using the voice service of apparatus to be controlled is obtained, to protect privacy of user.The control
The concrete function of unit 104 and processing see also step S620.
Such as: the problem of considering privacy of user, user can choose whether to open voice service feedback according to self-demand
Function.The function is related to privacy of user problem, it is contemplated that certain customers may think that the machine of this automatic feedback user's evaluation
System has invaded its privacy, therefore user can voluntarily choose whether to open the function.Generally after phonetic order execution, user may needle
To response speed, accuracy rate etc. is executed to voice service evaluation.
As a result, by collecting evaluation information according to the grant instruction of user, it can satisfy the different demands of different user, protect
The personal secrets of user are protected, hommization is more preferable.
Second control situation: the process of voice service is realized by phonetic order, specifically can be such that
Described control unit 104 can be also used in acquisition user during using the voice service of apparatus to be controlled
Before the evaluation information of feedback, the phonetic order that user is sent during using the voice service of apparatus to be controlled is obtained.Example
Such as: obtaining the phonetic order that can be used for controlling apparatus to be controlled that user sends.The concrete function of the control unit 104 and processing
See also step S710.
Described control unit 104 can be also used for identifying the phonetic order, obtain meaning of one's words keyword.The control
The concrete function of unit 104 processed and processing see also step S720.
Described control unit 104 can be also used for executing the phonetic order according to the meaning of one's words keyword, to realize use
Use of the family to the voice service of apparatus to be controlled.The concrete function of the control unit 104 and processing see also step S730.
Such as: voice system can identify user instruction, and can respond instruction.
As a result, by being identified to obtain meaning of one's words keyword to phonetic order, the use to voice service, reliability are realized
High, high safety.
The processing and function realized by the device of the present embodiment essentially correspond to earlier figures 1 to method shown in Fig. 7
Embodiment, principle and example, therefore not detailed place in the description of the present embodiment may refer to mutually speaking on somebody's behalf in previous embodiment
Bright, this will not be repeated here.
It is parsed using technical solution of the present invention by semanteme through a large amount of verification experimental verification, extracts user and using language
In relation to the evaluation of interactive voice during sound equipment, it is imported into user feedback system, is analyzed by data, it is excellent to show that product waits for
Change part, the interactive mode of voice technology can be optimized, improves user experience.
According to an embodiment of the invention, additionally providing a kind of air-conditioning of the control device corresponding to voice service.The air-conditioning
It may include: the control device of above-described voice service.
In an optional embodiment, in order to allow voice technology to be more in line with the habit of speaking of people, more meet user
Use demand, need use to user to feed back and be collected.The solution of the present invention proposes a kind of voice service feedback method,
This method can be parsed by semanteme, extracted user's evaluation in relation to interactive voice during using speech ciphering equipment, converged
Enter to user feedback system, analyzed by data, obtains product part to be optimized.To, optimize the interactive mode of voice technology,
Improve user experience.
Such as: user in use, may make an appraisal to the service condition of speech ciphering equipment.The solution of the present invention
It is intended to analyze the evaluation of user, the processing logic of voice system is optimized for user unsatisfied place.Such as: user
It assigns " I will listen song ", the first song of the direct shuffle of equipment one, user may evaluate " why to pay no attention to what I listen at this time
Song? ", equipment hears the user comment, and has modified processing logic according to user demand.Identical scene is encountered next time
When, equipment can ask in reply user " may I ask you will listen anything to sing, and recommend very fiery recently " desert camel " to you ".
In an optional example, this method can extract user in the mistake using speech ciphering equipment by speech analysis
In relation to the evaluation of interactive voice in journey, it is imported into user feedback system, is analyzed by data, the interaction side of voice system is optimized
Formula.
It is alternatively possible to call corresponding Keywords matching model according to speech analysis success or not, matching user is commented
By so as to improve matching efficiency.
It is alternatively possible to extract user comment, data analysis is allowed to more meet and use in such a way that this optimizes interactive voice
Family demand.
In an optional specific embodiment, example shown in Figure 9, the specific implementation to the solution of the present invention
Journey illustrates.
In an optional specific example, it is contemplated that the problem of privacy of user, in the solution of the present invention, user can according to from
Body demand chooses whether to open voice service feedback function.The function is related to privacy of user problem, it is contemplated that certain customers can
It can think that the mechanism of this automatic feedback user's evaluation has invaded its privacy, therefore user can voluntarily choose whether to open the function.
Generally after phonetic order execution, user may be evaluated voice service for response speed, execution accuracy rate etc..
Therefore a period of time after user instruction will be executed as acquisition time is commented on, by span when this in the solution of the present invention
Degree is set to 2 minutes, if user does not continue to assign next phonetic order in 2 minutes, when this belongs to comment collection for 2 minutes
Between, terminate comment later within 2 minutes and collect, if user has assigned next phonetic order in this 2 minutes, a upper voice refers to
Enable execute after with during next instruction issuing for comment acquisition time.The efficiency for collecting voice is both improved in this way, it also will be right
The influence degree of the privacy of user will arrive minimum.
In an optional specific example, for the executive mode of feedback mechanism, in the solution of the present invention, phonetic order is held
Market condition is divided into two kinds.One is user instructions to identify successfully, one is user instruction recognition failures, comments on and receives in the case of two kinds
Collecting model, there are two types of different treatment mechanisms:
Optionally, voice system can identify user instruction, and can respond instruction.
Voice system calls the first keyword models, which identifies successful situation for user instruction
Keyword models are established, for matching user's evaluation keyword.If equipment performs user instruction, user may be directed to system
Response speed, identification accuracy evaluated, such as: " response speed is good slow ", " and misplacing song to me ", " I like week
The version of outstanding human relations " ... therefore " low-response ", " misplacing ", " not to " etc. can be entered into the first key as keyword in advance
In word model.In 2 minutes after equipment has executed user instruction, equipment calls keyword monitoring module monitors user speech,
If user mentions the word with Keywords matching, equipment, which will be called, comments on parsing module, 2 seconds voices before and after interception user's keyword
It is parsed, obtains user comment text and be imported into user feedback system, the analysis of further progress data, extracting user needs
It asks, optimizes voice system interactive mode.
Optionally, voice system not can recognize that user instruction, and feedback user recognition failures.Voice system calls second
The case where keyword models, which is directed to user instruction recognition failures, establishes keyword models, user's matching
User's keyword.If equipment does not identify user instruction, user may evaluate for the instruction of oneself, such as: such as
Fruit user assigns the instruction of " who are you ", and equipment does not identify, user may then say " how I ask this product
Production man whom is ", then " how I ask that whom the production man of this product is " be to " who are you " this instruction explanation.
Therefore will " how can say ", the conduct such as " how asking " keyword is entered into the second keyword models.With the first keyword mould
Unlike in type, after extracting user's evaluation, user's evaluation is marked, mark its corresponding user instruction.Cause
For the explanation that the user's evaluation is to the user instruction not identified, after analysis, voice system is unrecognized by this
After the corresponding explanation of phonetic order is entered into system, after next time encounters same phonetic order, voice system can be identified
Out, user experience is improved.
The processing and function realized by the air-conditioning of the present embodiment essentially correspond to the implementation of aforementioned device shown in Fig. 8
Example, principle and example, therefore not detailed place in the description of the present embodiment, may refer to the related description in previous embodiment,
This is not repeated them here.
It is discontented for user by analyzing the evaluation of user using technical solution of the present invention through a large amount of verification experimental verification
The place of meaning optimizes the processing logic of voice system, can promote user experience.
According to an embodiment of the invention, additionally providing a kind of storage medium of the control method corresponding to voice service.It should
Storage medium may include: that a plurality of instruction is stored in the storage medium;The a plurality of instruction, for being loaded by processor
And execute the control method of above-described voice service.
The processing and function realized by the storage medium of the present embodiment essentially correspond to earlier figures 1 to shown in Fig. 7
Embodiment, principle and the example of method, therefore not detailed place in the description of the present embodiment, may refer to the phase in previous embodiment
It speaks on somebody's behalf bright, this will not be repeated here.
It is discontented for user by analyzing the evaluation of user using technical solution of the present invention through a large amount of verification experimental verification
The place of meaning optimizes the processing logic of voice system, can promote the efficiency of service and service effectiveness of voice service.
According to an embodiment of the invention, additionally providing a kind of air-conditioning of the control method corresponding to voice service.The air-conditioning,
It may include: processor, for executing a plurality of instruction;Memory, for storing a plurality of instruction;Wherein, a plurality of instruction is used
It is stored in by the memory, and is loaded by the processor and executed the control method of above-described voice service.
The processing and function realized by the air-conditioning of the present embodiment essentially correspond to earlier figures 1 to method shown in Fig. 7
Embodiment, principle and example, therefore not detailed place in the description of the present embodiment may refer to mutually speaking on somebody's behalf in previous embodiment
Bright, this will not be repeated here.
It is discontented for user by analyzing the evaluation of user using technical solution of the present invention through a large amount of verification experimental verification
The place of meaning optimizes the processing logic of voice system, can promote the versatility and the scope of application of speech ciphering equipment.
To sum up, it will be readily appreciated by those skilled in the art that under the premise of not conflicting, above-mentioned each advantageous manner can be certainly
It combined, be superimposed by ground.
The above description is only an embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should be included within scope of the presently claimed invention.
Claims (15)
1. a kind of control method of voice service characterized by comprising
Obtain the evaluation information that user is fed back during using the voice service of apparatus to be controlled;Wherein, the evaluation information,
It include: at least one of Speech Assessment information, word evaluation information, key evaluation information;
The voice service is optimized according to the evaluation information, to realize that user's next time is taken using the voice after optimization
Business.
2. the method according to claim 1, wherein obtaining user in the mistake of the voice service using apparatus to be controlled
The evaluation information fed back in journey, comprising:
Determine that the evaluation for collecting the evaluation information that user is fed back during using the voice service of apparatus to be controlled is collected
Period;
It is collected in the period in the evaluation, the evaluation information that user is fed back during using the voice service of apparatus to be controlled
It is collected.
3. according to the method described in claim 2, it is characterized in that, determining for collecting user in the voice using apparatus to be controlled
The period is collected in the evaluation of the evaluation information fed back during service, comprising:
Determine apparatus to be controlled is executing in the setting period after a upper phonetic order whether receive next phonetic order;
If not receiving next phonetic order within the setting period, it is determined that described to set the period and collected as the evaluation
Period;
Alternatively, if receiving next phonetic order within the setting period, it is determined that a upper phonetic order executes
The evaluation when period of period is assigned with the next phonetic order afterwards and collects the period.
4. method described in one of -3 according to claim 1, which is characterized in that according to the evaluation information to the voice service
It optimizes, comprising:
Determine that apparatus to be controlled identifies whether success to the phonetic order during the voice service;
If the identification success to the phonetic order, calls the first Keywords matching model of setting, to the evaluation information
In the first evaluation keyword match, to extract the first evaluation keyword;
User demand is determined according to the first evaluation keyword;
Optimize the voice service by the user demand.
5. according to the method described in claim 4, it is characterized in that, being carried out according to the evaluation information to the voice service excellent
Change, further includes:
If failed to the identification of the phonetic order, the second Keywords matching model of setting is called, the evaluation is believed
The second evaluation keyword in breath is matched, to extract the second evaluation keyword;
User's evaluation is determined according to the first evaluation keyword, and marks the corresponding phonetic order of the user's evaluation;
The corresponding explanation information of the phonetic order is increased in the phonetic order library of the voice service, to be received in next time
It is identified when to the phonetic order by the explanation information.
6. method described in one of -5 according to claim 1, which is characterized in that further include:
Determine whether that receiving user allows to obtain the grant instruction of the evaluation information;
If receiving the grant instruction, the evaluation that user is fed back during using the voice service of apparatus to be controlled is just obtained
Information;
And/or
Obtain the phonetic order that user is sent during using the voice service of apparatus to be controlled;
The phonetic order is identified, meaning of one's words keyword is obtained;
The phonetic order is executed according to the meaning of one's words keyword, to realize the use of voice service of the user to apparatus to be controlled.
7. a kind of control device of voice service characterized by comprising
Acquiring unit, the evaluation information fed back during using the voice service of apparatus to be controlled for obtaining user;Wherein,
The evaluation information, comprising: at least one of Speech Assessment information, word evaluation information, key evaluation information;
Control unit, for being optimized according to the evaluation information to the voice service, to realize that it is excellent that user's next time uses
Voice service after change.
8. device according to claim 7, which is characterized in that the acquiring unit obtains user using apparatus to be controlled
The evaluation information fed back during voice service, comprising:
Determine that the evaluation for collecting the evaluation information that user is fed back during using the voice service of apparatus to be controlled is collected
Period;
It is collected in the period in the evaluation, the evaluation information that user is fed back during using the voice service of apparatus to be controlled
It is collected.
9. device according to claim 8, which is characterized in that the acquiring unit determine for collect user use to
The period is collected in the evaluation of the evaluation information fed back during the voice service for controlling equipment, comprising:
Determine apparatus to be controlled is executing in the setting period after a upper phonetic order whether receive next phonetic order;
If not receiving next phonetic order within the setting period, it is determined that described to set the period and collected as the evaluation
Period;
Alternatively, if receiving next phonetic order within the setting period, it is determined that a upper phonetic order executes
The evaluation when period of period is assigned with the next phonetic order afterwards and collects the period.
10. the device according to one of claim 7-9, which is characterized in that described control unit is according to the evaluation information
The voice service is optimized, comprising:
Determine that apparatus to be controlled identifies whether success to the phonetic order during the voice service;
If the identification success to the phonetic order, calls the first Keywords matching model of setting, to the evaluation information
In the first evaluation keyword match, to extract the first evaluation keyword;
User demand is determined according to the first evaluation keyword;
Optimize the voice service by the user demand.
11. device according to claim 10, which is characterized in that described control unit is according to the evaluation information to described
Voice service optimizes, further includes:
If failed to the identification of the phonetic order, the second Keywords matching model of setting is called, the evaluation is believed
The second evaluation keyword in breath is matched, to extract the second evaluation keyword;
User's evaluation is determined according to the first evaluation keyword, and marks the corresponding phonetic order of the user's evaluation;
The corresponding explanation information of the phonetic order is increased in the phonetic order library of the voice service, to be received in next time
It is identified when to the phonetic order by the explanation information.
12. the device according to one of claim 7-11, which is characterized in that further include:
Described control unit is also used to determine whether that receiving user allows to obtain the grant instruction of the evaluation information;
Described control unit is just obtained user and is taken using the voice of apparatus to be controlled if being also used to receive the grant instruction
The evaluation information fed back during business;
And/or
Described control unit is also used to obtain the voice that user is sent during using the voice service of apparatus to be controlled and refers to
It enables;
Described control unit is also used to identify the phonetic order, obtains meaning of one's words keyword;
Described control unit is also used to execute the phonetic order according to the meaning of one's words keyword, to realize that user sets to be controlled
The use of standby voice service.
13. a kind of air-conditioning characterized by comprising the control device of the voice service as described in claim 7-12 is any.
14. a kind of storage medium, which is characterized in that be stored with a plurality of instruction in the storage medium;The a plurality of instruction, is used for
It is loaded by processor and executes the control method of the voice service as described in claim 1-6 is any.
15. a kind of air-conditioning characterized by comprising
Processor, for executing a plurality of instruction;
Memory, for storing a plurality of instruction;
Wherein, a plurality of instruction for being stored by the memory, and is loaded by the processor and is executed such as claim
The control method of any voice service of 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811489305.8A CN109712618A (en) | 2018-12-06 | 2018-12-06 | A kind of control method of voice service, device, storage medium and air-conditioning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811489305.8A CN109712618A (en) | 2018-12-06 | 2018-12-06 | A kind of control method of voice service, device, storage medium and air-conditioning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109712618A true CN109712618A (en) | 2019-05-03 |
Family
ID=66254689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811489305.8A Pending CN109712618A (en) | 2018-12-06 | 2018-12-06 | A kind of control method of voice service, device, storage medium and air-conditioning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109712618A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110163528A (en) * | 2019-05-31 | 2019-08-23 | 重庆先特服务外包产业有限公司 | Quality of proxy service management system and method for call center |
CN110288990A (en) * | 2019-06-12 | 2019-09-27 | 深圳康佳电子科技有限公司 | A kind of voice control optimization method, storage medium and intelligent terminal |
CN110378704A (en) * | 2019-07-23 | 2019-10-25 | 珠海格力电器股份有限公司 | Method, storage medium and the terminal device of suggestion feedback based on fuzzy diagnosis |
CN110417589A (en) * | 2019-07-23 | 2019-11-05 | 徐州工程学院 | A kind of vehicle-mounted voice cloud user experience quality road measuring method |
CN110619868A (en) * | 2019-08-29 | 2019-12-27 | 深圳市优必选科技股份有限公司 | Voice assistant optimization method, voice assistant optimization device and intelligent equipment |
CN110675188A (en) * | 2019-09-19 | 2020-01-10 | 百度在线网络技术(北京)有限公司 | Method and device for acquiring feedback information |
CN111090305A (en) * | 2019-11-27 | 2020-05-01 | 新华蓝海(北京)人工智能技术有限公司 | 3D intelligent tax service equipment |
CN111240478A (en) * | 2020-01-07 | 2020-06-05 | 百度在线网络技术(北京)有限公司 | Method, device, equipment and storage medium for evaluating equipment response |
CN112270926A (en) * | 2020-09-27 | 2021-01-26 | 青岛海尔空调器有限总公司 | After-sale service method of environment adjusting equipment and after-sale service equipment |
CN112463108A (en) * | 2020-12-14 | 2021-03-09 | 美的集团股份有限公司 | Voice interaction processing method and device, electronic equipment and storage medium |
CN114678012A (en) * | 2022-02-18 | 2022-06-28 | 青岛海尔科技有限公司 | Voice interaction data processing method and device, storage medium and electronic device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105027197A (en) * | 2013-03-15 | 2015-11-04 | 苹果公司 | Training an at least partial voice command system |
CN106233375A (en) * | 2014-04-25 | 2016-12-14 | 纽昂斯通信有限公司 | User version based on mass-rent input starts anew to learn language model |
CN106227779A (en) * | 2016-07-18 | 2016-12-14 | 深圳追科技有限公司 | A kind of man-machine interaction method of customer service system |
CN108416041A (en) * | 2018-03-14 | 2018-08-17 | 苏州思必驰信息科技有限公司 | Voice log analysis method and system |
US20180329998A1 (en) * | 2017-05-15 | 2018-11-15 | Apple Inc. | Optimizing dialogue policy decisions for digital assistants using implicit feedback |
CN108881377A (en) * | 2018-04-28 | 2018-11-23 | 上海车音智能科技有限公司 | A kind of application service invocation method, terminal device and server |
-
2018
- 2018-12-06 CN CN201811489305.8A patent/CN109712618A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105027197A (en) * | 2013-03-15 | 2015-11-04 | 苹果公司 | Training an at least partial voice command system |
CN106233375A (en) * | 2014-04-25 | 2016-12-14 | 纽昂斯通信有限公司 | User version based on mass-rent input starts anew to learn language model |
CN106227779A (en) * | 2016-07-18 | 2016-12-14 | 深圳追科技有限公司 | A kind of man-machine interaction method of customer service system |
US20180329998A1 (en) * | 2017-05-15 | 2018-11-15 | Apple Inc. | Optimizing dialogue policy decisions for digital assistants using implicit feedback |
CN108416041A (en) * | 2018-03-14 | 2018-08-17 | 苏州思必驰信息科技有限公司 | Voice log analysis method and system |
CN108881377A (en) * | 2018-04-28 | 2018-11-23 | 上海车音智能科技有限公司 | A kind of application service invocation method, terminal device and server |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110163528A (en) * | 2019-05-31 | 2019-08-23 | 重庆先特服务外包产业有限公司 | Quality of proxy service management system and method for call center |
CN110163528B (en) * | 2019-05-31 | 2021-12-07 | 重庆先特服务外包产业有限公司 | Proxy service quality management system and method for call center |
CN110288990A (en) * | 2019-06-12 | 2019-09-27 | 深圳康佳电子科技有限公司 | A kind of voice control optimization method, storage medium and intelligent terminal |
CN110378704B (en) * | 2019-07-23 | 2021-10-22 | 珠海格力电器股份有限公司 | Opinion feedback method based on fuzzy recognition, storage medium and terminal equipment |
CN110378704A (en) * | 2019-07-23 | 2019-10-25 | 珠海格力电器股份有限公司 | Method, storage medium and the terminal device of suggestion feedback based on fuzzy diagnosis |
CN110417589A (en) * | 2019-07-23 | 2019-11-05 | 徐州工程学院 | A kind of vehicle-mounted voice cloud user experience quality road measuring method |
CN110417589B (en) * | 2019-07-23 | 2022-11-29 | 徐州工程学院 | Vehicle-mounted voice cloud user experience quality drive test method |
CN110619868B (en) * | 2019-08-29 | 2021-12-17 | 深圳市优必选科技股份有限公司 | Voice assistant optimization method, voice assistant optimization device and intelligent equipment |
CN110619868A (en) * | 2019-08-29 | 2019-12-27 | 深圳市优必选科技股份有限公司 | Voice assistant optimization method, voice assistant optimization device and intelligent equipment |
CN110675188A (en) * | 2019-09-19 | 2020-01-10 | 百度在线网络技术(北京)有限公司 | Method and device for acquiring feedback information |
CN111090305A (en) * | 2019-11-27 | 2020-05-01 | 新华蓝海(北京)人工智能技术有限公司 | 3D intelligent tax service equipment |
CN111240478A (en) * | 2020-01-07 | 2020-06-05 | 百度在线网络技术(北京)有限公司 | Method, device, equipment and storage medium for evaluating equipment response |
CN111240478B (en) * | 2020-01-07 | 2023-10-13 | 百度在线网络技术(北京)有限公司 | Evaluation method, device, equipment and storage medium for equipment response |
CN112270926A (en) * | 2020-09-27 | 2021-01-26 | 青岛海尔空调器有限总公司 | After-sale service method of environment adjusting equipment and after-sale service equipment |
CN112270926B (en) * | 2020-09-27 | 2023-05-23 | 青岛海尔空调器有限总公司 | After-sales service method of environment adjusting equipment and after-sales service equipment |
CN112463108A (en) * | 2020-12-14 | 2021-03-09 | 美的集团股份有限公司 | Voice interaction processing method and device, electronic equipment and storage medium |
WO2022126734A1 (en) * | 2020-12-14 | 2022-06-23 | 美的集团股份有限公司 | Voice interaction processing method and apparatus, electronic device, and storage medium |
CN114678012A (en) * | 2022-02-18 | 2022-06-28 | 青岛海尔科技有限公司 | Voice interaction data processing method and device, storage medium and electronic device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109712618A (en) | A kind of control method of voice service, device, storage medium and air-conditioning | |
US11030412B2 (en) | System and method for chatbot conversation construction and management | |
CN107818798B (en) | Customer service quality evaluation method, device, equipment and storage medium | |
KR102119468B1 (en) | System and method for learning counseling chatter robot based on counceling contents of counselor | |
US11120342B2 (en) | Electronic meeting intelligence | |
CN107665708B (en) | Intelligent voice interaction method and system | |
CN108347646B (en) | Multimedia content playing method and device | |
US7912714B2 (en) | Method for segmenting communication transcripts using unsupervised and semi-supervised techniques | |
US10891436B2 (en) | Device and method for voice-driven ideation session management | |
US20050010411A1 (en) | Speech data mining for call center management | |
CN105979376A (en) | Recommendation method and device | |
JP2017215931A (en) | Conference support system, conference support device, conference support method, and program | |
CN106294774A (en) | User individual data processing method based on dialogue service and device | |
US11315569B1 (en) | Transcription and analysis of meeting recordings | |
US11232261B2 (en) | Open domain real-time question answering | |
CN104834691A (en) | Voice robot | |
US8781880B2 (en) | System, method and apparatus for voice analytics of recorded audio | |
US11783829B2 (en) | Detecting and assigning action items to conversation participants in real-time and detecting completion thereof | |
CN109766474A (en) | Inquest signal auditing method, device, computer equipment and storage medium | |
CN107547942A (en) | A kind of binary system television system and method | |
CN106407287A (en) | Multimedia resource pushing method and system | |
Valbonesi et al. | Multimodal signal analysis of prosody and hand motion: Temporal correlation of speech and gestures | |
CN112233690A (en) | Double recording method, device, terminal and storage medium | |
JP2020160425A (en) | Evaluation system, evaluation method, and computer program | |
CN106843461A (en) | A kind of interactive output intent and robot for robot |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190503 |
|
RJ01 | Rejection of invention patent application after publication |