CN105206269A - Voice processing method and device - Google Patents
Voice processing method and device Download PDFInfo
- Publication number
- CN105206269A CN105206269A CN201510502763.0A CN201510502763A CN105206269A CN 105206269 A CN105206269 A CN 105206269A CN 201510502763 A CN201510502763 A CN 201510502763A CN 105206269 A CN105206269 A CN 105206269A
- Authority
- CN
- China
- Prior art keywords
- text data
- attributive character
- user
- voice messaging
- listener
- 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 voice processing method and a device. The method comprises steps that, voice information of a user is acquired, and the user is a talker and/or a listener; text data corresponding to the voice information and attribute characteristics of the user are parsed according to the acquired voice information; voice response information or a feedback information table is generated according to the text data and the attribute characteristics. The device comprises a voice information acquisition module used for acquiring the voice information of the user, a parsing module is used for parsing the text data corresponding to the voice information and the attribute characteristics of the user, a processing module used for generating the voice response information or generating the feedback information table according to the text data and the attribute characteristics, wherein the user is the talker and/or the listener. Through the method and the device, a problem that voice information processing requires a lot of manual operation in the prior art is solved, manpower operation cost is greatly saved, and the satisfaction degree of the user is improved.
Description
Technical field
The embodiment of the present invention relates to technical field of internet application, particularly relates to a kind of method of speech processing and device.
Background technology
Along with the explosive increase of internet data, client's consulting that client service center of businessman receives is also more and more frequent, the call center of some businessman has calling record function, the voice messaging of words person can be sent by Real-time Obtaining, or recording is carried out in this call store, for follow-up Data Analysis Services.
But no matter be real-time voice answer-back, or follow-uply carry out data processing to recording call, all need manually to carry out identifying processing, therefore businessman needs to increase increasing artificial customer service and could tackle, so need artificial O&M cost in a large number.
Summary of the invention
The embodiment of the present invention provides a kind of method of speech processing and device, with automatic processed voice information, reduces O&M cost.
First aspect, embodiments provides a kind of method of speech processing, comprising:
Obtain the voice messaging of user, described user is for sending words person and/or listener;
According to obtained voice messaging, parse the attributive character of text data corresponding to described voice messaging and user;
According to described text data and attributive character, produce audio response message, or produce feedback information table.
Second aspect, the embodiment of the present invention additionally provides a kind of voice processing apparatus, comprising:
Voice messaging acquisition module, for obtaining the voice messaging of user, described user is for sending words person and/or listener;
Parsing module, for according to obtained voice messaging, parses the attributive character of text data corresponding to described voice messaging and user;
Processing module, for according to described text data and attributive character, produces audio response message, or produces feedback information table.
Technical scheme provided by the invention, the voice messaging of the user obtaining which kind of type can be selected according to practical application scene, both be applicable to carry out voice answer-back according to voice messaging real-time on line, also be applicable to carry out data analysis to the voice messaging under line, solve in prior art and need by the problem of a large amount of manual operations realization to the process of voice messaging, therefore can save a large amount of artificial O&M costs, and improve user satisfaction.
Accompanying drawing explanation
The process flow diagram of a kind of method of speech processing that Fig. 1 provides for the embodiment of the present invention one;
The schematic flow sheet of a kind of method of speech processing that Fig. 2 provides for the embodiment of the present invention two;
The schematic flow sheet of a kind of method of speech processing that Fig. 3 provides for the embodiment of the present invention three;
The schematic flow sheet of a kind of method of speech processing that Fig. 4 provides for the embodiment of the present invention four;
The structural representation of a kind of voice processing apparatus that Fig. 5 provides for the embodiment of the present invention five.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, illustrate only part related to the present invention in accompanying drawing but not entire infrastructure.
Before in further detail exemplary embodiment being discussed, it should be mentioned that some exemplary embodiments are described as the process or method described as process flow diagram.Although operations (or step) is described as the process of order by process flow diagram, many operations wherein can be implemented concurrently, concomitantly or simultaneously.In addition, the order of operations can be rearranged.Described process can be terminated when its operations are completed, but can also have the additional step do not comprised in the accompanying drawings.Described process can correspond to method, function, code, subroutine, subroutine etc.
Embodiment one
The process flow diagram of a kind of method of speech processing that Fig. 1 provides for the embodiment of the present invention one, the method of the present embodiment can be performed by voice processing apparatus, this device realizes by the mode of hardware and/or software, and the terminal device of general accessible site in website tool of communications class or incoming call analysis tool-class service end place (such as, desktop computer, notebook or mobile terminal etc.) in, or as the subroutine of website tool of communications class or incoming call analysis tool-class service end.The method of the present embodiment comprises following operation:
The voice messaging of S11, acquisition user, described user is for sending words person and/or listener;
Which kind of user the wherein voice messaging of above-mentioned acquisition user, can select according to embody rule scene.Such as, when being applied in customer service call platform on some lines, after sending words person's incoming call customer service call platform, if prosthetic response, then obtain the voice messaging sending words person; If there is manual answering, then can obtain the voice messaging of listener, or obtain the voice messaging sending words person and listener simultaneously.When applying online, the present embodiment also directly can receive the calling record information that businessman sends, and therefrom obtains the voice messaging sending words person and/or listener.
S12, according to obtained voice messaging, parse the attributive character of text data corresponding to described voice messaging and user;
The object of this operation is resolved by the voice messaging of the user of aforesaid operations S11 acquisition, parses the attributive character of text data corresponding to described voice messaging and user.Voice messaging generally comprises voice content and voice attributes, and the voice content in voice messaging is resolved to text data by this operation respectively, and voice attributes is resolved to attributive character.The various biological aspects of described attributive character reaction user.
S13, according to described text data and attributive character, produce audio response message, or produce feedback information table.
This operation can be divided into two kinds, online and offline applicable cases.For situation on line, because the voice messaging obtained is real-time, therefore the present embodiment can be resolved according to the voice messaging of Real-time Obtaining, and according to the text data parsed and attributive character, produce audio response message, carry out voice feedback timely.For the situation under line, obtain and can obtain a large amount of voice messagings, analyzing and processing is carried out to it, parses text data and attributive character, thus create feedback information table.
It should be noted that, the method that the present embodiment provides can be applicable in no scene, such as apply in customer service call platform on line, user is for sending words person, can in real time according to the audio response message sending the voice messaging of words person to provide corresponding, solve the prompting of existing self-assisted voice can not initiatively put question to, or the content stored in database can only be selected to carry out the problem of puing question to, point out compared to self-assisted voice of the prior art, initiatively identification can send the demand of words person, and reply, improve the satisfaction of user.
The method that the present embodiment provides can also use in the data processing scene online, such as can receive the recorded speech that businessman sends, obtain the voice messaging sending words person and/or listener in described recorded speech, the feedback information table produced can carry out Treatment Analysis to a large amount of voice messagings automatically, obtain structural data, for businessman provides structural data, adjust follow-up marketing planning for businessman and carry out the adjustment of market direction.Therefore without the need to manually carrying out follow-up data processing operation, a large amount of artificial O&M costs can be saved, and improve user satisfaction.
Such as, on line with in the scene under line, in the method that the present embodiment provides, when described user is listener, the feedback information table of generation, can reflect the response situation of listener, assesses etc. for the response satisfaction of listener.
Technical scheme provided by the invention, the voice messaging of the user obtaining which kind of type can be selected according to practical application scene, both be applicable to carry out voice answer-back according to voice messaging real-time on line, also be applicable to carry out data analysis to the voice messaging under line, produce feedback information table, solve in prior art and need, by the process problem of a large amount of manual operations realization to voice messaging, therefore can save a large amount of artificial O&M costs, and improve user satisfaction.
On the basis of above-described embodiment, optionally, described method also comprises: according to described text data and attributive character, when cannot generate audio response message, set up and send words person to be connected with the call of attend a banquet contact staff or third party's terminal.
This operation is applicable to the scene of response in real time on line, and when producing audio response message, then foundation send words person to be connected with the call of attend a banquet contact staff or third party's terminal.Described third party's terminal generally refers to the communicating terminal of the artificial customer service of businessman.The present embodiment is when automatically producing the situation of voice answer-back, automatically the call sending the voice incoming call of words person with attend a banquet contact staff or third party's terminal is connected, improve Consumer's Experience further, avoid user to abandon this voice incoming call due to the response of expectation cannot be obtained.
On the basis of above-described embodiment, optionally, described method also comprises:
Judge whether to there is idle seating contact staff;
When there is not idle seating contact staff, perform the operation of the voice messaging obtaining user.
The present embodiment is before the voice messaging obtaining user, first judge whether to there is idle seating contact staff, when there is idle seating contact staff, words person is sent in direct foundation the communication connection with idle seating contact staff place terminal, when there is not idle seating contact staff, performing the operation of the voice messaging of follow-up acquisition user, can customer service of attending a banquet be made full use of like this, and can prevent because customer service of attending a banquet is busy, and miss the phone of user.
Embodiment two
The schematic flow sheet of a kind of method of speech processing that Fig. 2 provides for the embodiment of the present invention two, the present embodiment is the optimization on above-described embodiment basis, accordingly, according to described text data and attributive character, produce audio response message, comprise: the site identity obtaining listener, determine default training pattern according to the site identity of described listener; According to described text data, attributive character and described default training pattern, produce audio response message.As shown in Figure 2, the method that the present embodiment provides comprises following operation:
The voice messaging of S21, acquisition user, described user is for sending words person and/or listener;
S22, according to obtained voice messaging, parse the attributive character of text data corresponding to described voice messaging and user;
By the voice messaging obtained in aforesaid operations, carry out semantic analysis, parse corresponding text data, and by sound groove recognition technology in e, parse the attributive character of user.Optionally, described attributive character comprises: at least one in sex character, age characteristics and emotional characteristics.The sex of people, age and emotional state can be embodied by voice messaging, such as, people is when being in different emotional states, the word speed of speaking can be different, the tone of speaking is also different, therefore, the mood of user can be judged by obtaining the voice messaging of user, such as the emotional characteristics such as sad, glad, surprised and angry.The people of all ages and classes, different sexes, its voice messaging is also different, can also judge the age characteristics of user and sex character etc. by obtaining the voice messaging of user.
The site identity of S23, acquisition listener, determines default training pattern according to the site identity of described listener;
After obtaining the site identity of listener, default training pattern corresponding to the site identity of described listener can be inquired about according to described site identity.Described default training pattern is through training study and is pre-created.Such as, when sending words person's voice incoming call businessman A, businessman A is listener, obtains the site identity of businessman A, thus determines the default training pattern of businessman A according to described site identity.
S24, according to described text data, attributive character and described default training pattern, produce audio response message.
By the text data of described acquisition and the described default training pattern of attributive character input.Obtain the demand of user from text, the demand that such as identifies is business consultation, complains suggestion and after sale service etc.Dependency feature judges the various biological aspects of user, as sex, age and mood etc., then produce the audio response message corresponding with the voice messaging of described acquisition.The audio response message that the present embodiment provides produces according to described text data, attributive character and described default training pattern, therefore, can the demand of initiatively discriminating user, and it is high with the demand compatible degree of user, different voice answer-backs can be made for the attributive character that user is different, meet the expectation of user.
On the basis of above-described embodiment, optionally, the present embodiment additionally provides a kind of method example obtaining default training pattern, and the sequential of the method is generally according to described text data and attributive character, before producing audio response message, comprising:
Obtain history voice messaging;
Identify the text data that described history voice messaging is corresponding and send the attributive character of words person and listener;
According to described text data and the attributive character sending words person and listener, obtain and preset training pattern.
Wherein, above-mentioned history voice messaging can be the history calling record that businessman sends, and can also be the history voice messaging that line stores after response.The history voice messaging of acquisition is parsed corresponding text data and send the attributive character of words person and listener, and according to text data and the attributive character giving words person and listener, such as extract speech characteristic parameter, make sound template, carry out training study, the training pattern that final acquisition is preset.
On the basis of above-described embodiment, optionally, according to described text data and attributive character, produce audio response message, comprising:
According to described text data and attributive character, produce text message;
Described text message is converted to audio response message.
The present embodiment, after obtaining text data corresponding to voice messaging and attributive character, first produces the text message of response, and then described text message is converted to audio response message, reply.
Further, optionally, after text message is converted to audio response message, directly can send the terminal that feeding words person is corresponding, can also be converted in the process of audio response message carrying out text message, for described audio response message adds the attributive character of listener, namely described audio response message comprises listener's attributive character.Such as, when sending the attributive character of words person for indignation, the text message of generation for expressing apology, and provides the content of solution, and is directly converted to audio response message.Can also be converted in the process of audio response message by text message, add the attributive character of listener, such as sorry tone of pacifying, produces soft audio response message, pacifies the mood sending words person, improves service satisfaction.
Embodiment three
The schematic flow sheet of a kind of method of speech processing that Fig. 3 provides for the embodiment of the present invention three, as shown in Figure 3, the method specifically comprises:
The voice messaging of S31, acquisition user, described user is for sending words person;
S32, according to obtained voice messaging, parse the attributive character of text data corresponding to described voice messaging and user;
By optional in aforesaid operations, described attributive character comprises: at least one in sex character, age characteristics and emotional characteristics.The mood of user can be judged, such as the emotional characteristics such as sad, glad, surprised and angry by obtaining the voice messaging of user; Judge the age and sex etc. of user.
S33, according to described text data, determine the communication intent features of described user, and according to described communication intent features filtering harassing call.
According to the text data of above-mentioned acquisition, such as can by semanteme, grammer and Concordance, obtain and send the communication intent features of words person, certainly can also by the text data obtained described in keyword technical Analysis, to send the communication intent features of words person described in parsing.Described communication intent features such as comprises consulting, complaint, malice harassing and wrecking etc., and this operation, by obtaining the communication intent features sending words person in text orientation analysis, can have filtering harassing call.Such as when being determined that by described text data the communication intent features of user is harassed for malice, then directly terminate the voice incoming call that this send words person, reach the object of filtering harassing call.
S34, according to described text data and attributive character, produce audio response message.
This operation can according to the text data of above-mentioned acquisition and attributive character, the audio response message that the generation of real-time high-efficiency is corresponding with it, then terminal corresponding to words person send by the audio response message of generation.For example, when sending words person to carry out business consultation, the demand for counseling sending words person can be determined according to text data and attributive character, and send the sex of words person, age and mood etc., for the demand for counseling sending words person different, send the sex of words person, age produces different audio response messages, be women when sending the sex of words person, age is 20-30 year, when mood is glad, applicable women can be provided for it, meet the trendy product information audio response message the most of young woman, optionally, the emotional characteristics of the audio response message produced also is glad, sex character can be chosen as the male sex or women according to practical application scene, and corresponding age bracket.
The present embodiment send the speech data of words person by Real-time Obtaining, and makes corresponding audio response message in time, points out compared to self-assisted voice of the prior art, initiatively identification can send the demand of words person, and carry out effective voice answer-back.Therefore artificial customer service can be replaced to carry out voice answer-back, and without the need to manual intervention, the real demand of accurate analysis user is also replied accordingly, improves the satisfaction of user, has saved artificial O&M cost.
Embodiment four
The schematic flow sheet of a kind of method of speech processing that Fig. 4 provides for the embodiment of the present invention four, as shown in Figure 4, the method specifically comprises:
The voice messaging of S41, acquisition user, described user is for sending words person and listener;
The method that the present embodiment provides is applicable to the speech processes under line, and the voice messaging of acquisition is generally a large amount of calling records of businessman's transmission, has both comprised the voice messaging sending the voice messaging of words person also to comprise listener in described calling record.
S42, according to obtained voice messaging, parse the attributive character of text data corresponding to described voice messaging and user;
According to the voice messaging sending words person and listener of above-mentioned acquisition, parse the attributive character sent text data corresponding to the voice messaging of words person, send words person respectively, and text data corresponding to the voice messaging of listener, listener attributive character.Described attributive character comprises at least one in sex character, age characteristics and emotional characteristics.
S43, according to described text data and attributive character, produce feedback information table.
To text data corresponding to the voice messaging of words person be sent, send the attributive character of words person, and text data corresponding to the voice messaging of listener, listener attributive character, carry out data processing, set up corresponding feedback information table.The feedback information table that this operation is produced by the method such as such as cluster, pattern analysis, correlation analysis can send the age bracket of words person, emotional change, gender groups, issuer to data such as, client regions by programming count, can also the emotional change etc. of programming count listener.By to sending the voice messaging of words person to carry out analyzing and processing, the service observation after automatically realizing words can be avoided, improve work efficiency, reduce cost of labor.By carrying out analyzing and processing to the voice messaging of listener, the service quality of listener conveniently can be understood.
Embodiment five
The structural representation of a kind of voice processing apparatus that Fig. 5 provides for the embodiment of the present invention five, as shown in Figure 5, described device comprises:
Voice messaging acquisition module 51, for obtaining the voice messaging of user, described user is for sending words person and/or listener;
Parsing module 52, for according to obtained voice messaging, parses the attributive character of text data corresponding to described voice messaging and user;
Processing module 53, for according to described text data and attributive character, produces audio response message, or produces feedback information table.
Technical scheme provided by the invention, the voice messaging of the user obtaining which kind of type can be selected according to practical application scene, both be applicable to carry out voice answer-back according to voice messaging real-time on line, also be applicable to carry out data analysis to the voice messaging under line, produce feedback information table, solve in prior art and need, by the problem of a large amount of manual operations realization to the process of voice messaging, therefore can save a large amount of artificial O&M costs, and improve user satisfaction.
On the basis of above-described embodiment, optionally, described device also comprises:
Call link block, for according to described text data and attributive character, when cannot generate audio response message, sets up and send words person to be connected with the call of attend a banquet contact staff or third party's terminal.
On the basis of above-described embodiment, optionally, described device also comprises:
, there is idle seating contact staff for judging whether in judge module; When there is not idle seating contact staff, perform the operation of the voice messaging obtaining user.
On the basis of above-described embodiment, optionally, described processing module comprises:
Text message generation unit, for according to described text data, attributive character and described default training pattern, produces text message;
Speech conversion unit, for being converted to audio response message by described text message.
On the basis of above-described embodiment, optionally, described processing module comprises:
Presetting training pattern determining unit, for obtaining the site identity of listener, determining default training pattern according to the site identity of described listener;
Audio response message generation unit, for according to described text data, attributive character and described default training pattern, produces audio response message.
On the basis of above-described embodiment, optionally, described device also comprises:
Model training module, for obtaining history voice messaging; Identify the text data that described history voice messaging is corresponding and send the attributive character of words person and listener; According to described text data and the attributive character sending words person and listener, obtain and preset training pattern.
On the basis of above-described embodiment, optionally, when described user is for sending words person, described device also comprises:
Filtering module, for according to described text data, determines the communication intent features of described user, and according to described communication intent features filtering harassing call.
On the basis of above-described embodiment, optionally, described audio response message comprises listener's attributive character.
On the basis of above-described embodiment, optionally, described attributive character comprises: at least one in sex character, age characteristics and emotional characteristics.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, various obvious change can be carried out for a person skilled in the art, readjust and substitute and can not protection scope of the present invention be departed from.Therefore, although be described in further detail invention has been by above embodiment, the present invention is not limited only to above embodiment, when not departing from the present invention's design, can also comprise other Equivalent embodiments more, and scope of the present invention is determined by appended right.
Claims (15)
1. a method of speech processing, is characterized in that, comprising:
Obtain the voice messaging of user, described user is for sending words person and/or listener;
According to obtained voice messaging, parse the attributive character of text data corresponding to described voice messaging and user;
According to described text data and attributive character, produce audio response message, or produce feedback information table.
2. method according to claim 1, is characterized in that, according to described text data and attributive character, when cannot generate audio response message, sets up and send words person to be connected with the call of attend a banquet contact staff or third party's terminal.
3. method according to claim 1, is characterized in that, according to described text data and attributive character, produces audio response message, comprising:
According to described text data and attributive character, produce text message;
Described text message is converted to audio response message.
4. method according to claim 1, is characterized in that, according to described text data and attributive character, produces audio response message, comprising:
Obtain the site identity of listener, determine default training pattern according to the site identity of described listener;
According to described text data, attributive character and described default training pattern, produce audio response message.
5. method according to claim 4, is characterized in that, according to described text data and attributive character, before producing audio response message, also comprises:
Obtain history voice messaging;
Identify the text data that described history voice messaging is corresponding and send the attributive character of words person and listener;
According to described text data and the attributive character sending words person and listener, obtain and preset training pattern.
6. method according to claim 1, is characterized in that, when described user is for sending words person, according to obtained voice messaging, after the text data corresponding to parsing and the attributive character of user, also comprises:
According to described text data, determine the communication intent features of described user, and according to described communication intent features filtering harassing call.
7. method according to claim 1, is characterized in that, described audio response message comprises listener's attributive character.
8. method according to claim 1, is characterized in that, described attributive character comprises: at least one in sex character, age characteristics and emotional characteristics.
9. a voice processing apparatus, is characterized in that, comprising:
Voice messaging acquisition module, for obtaining the voice messaging of user, described user is for sending words person and/or listener;
Parsing module, for according to obtained voice messaging, parses the attributive character of text data corresponding to described voice messaging and user;
Processing module, for according to described text data and attributive character, produces audio response message, or produces feedback information table.
10. device according to claim 9, is characterized in that, also comprises:
Call link block, for according to described text data and attributive character, when cannot generate audio response message, sets up and send words person to be connected with the call of attend a banquet contact staff or third party's terminal.
11. devices according to claim 9, is characterized in that, described processing module comprises:
Text message generation unit, for according to described text data, attributive character and described default training pattern, produces text message;
Speech conversion unit, for being converted to audio response message by described text message.
12. devices according to claim 9, is characterized in that, described processing module comprises:
Presetting training pattern determining unit, for obtaining the site identity of listener, determining default training pattern according to the site identity of described listener;
Audio response message generation unit, for according to described text data, attributive character and described default training pattern, produces audio response message.
13. devices according to claim 12, is characterized in that, also comprise:
Model training module, for obtaining history voice messaging; Identify the text data that described history voice messaging is corresponding and send the attributive character of words person and listener; According to described text data and the attributive character sending words person and listener, obtain and preset training pattern.
14. devices according to claim 9, is characterized in that, when described user is for sending words person, also comprise:
Filtering module, for according to described text data, determines the communication intent features of described user, and according to described communication intent features filtering harassing call.
15. devices according to claim 9, is characterized in that, described audio response message comprises listener's attributive character;
Described attributive character comprises: at least one in sex character, age characteristics and emotional characteristics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510502763.0A CN105206269A (en) | 2015-08-14 | 2015-08-14 | Voice processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510502763.0A CN105206269A (en) | 2015-08-14 | 2015-08-14 | Voice processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105206269A true CN105206269A (en) | 2015-12-30 |
Family
ID=54953898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510502763.0A Pending CN105206269A (en) | 2015-08-14 | 2015-08-14 | Voice processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105206269A (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654950A (en) * | 2016-01-28 | 2016-06-08 | 百度在线网络技术（北京）有限公司 | Self-adaptive voice feedback method and device |
| CN105701211A (en) * | 2016-01-13 | 2016-06-22 | 北京光年无限科技有限公司 | Question-answering system-oriented active interaction data processing method and system |
| CN105810200A (en) * | 2016-02-04 | 2016-07-27 | 深圳前海勇艺达机器人有限公司 | Man-machine dialogue apparatus and method based on voiceprint identification |
| CN105895083A (en) * | 2016-05-30 | 2016-08-24 | 珠海市魅族科技有限公司 | Information processing method and device |
| CN106548358A (en) * | 2016-11-22 | 2017-03-29 | 美的集团股份有限公司 | Conversation processing method and device |
| CN106683672A (en) * | 2016-12-21 | 2017-05-17 | 竹间智能科技（上海）有限公司 | Intelligent dialogue method and system based on emotion and semantics |
| CN106710591A (en) * | 2016-12-13 | 2017-05-24 | 云南电网有限责任公司电力科学研究院 | Voice customer service system for power terminal |
| CN106773923A (en) * | 2016-11-30 | 2017-05-31 | 北京光年无限科技有限公司 | The multi-modal affection data exchange method and device of object manipulator |
| CN106782521A (en) * | 2017-03-22 | 2017-05-31 | 海南职业技术学院 | A kind of speech recognition system |
| CN106910514A (en) * | 2017-04-30 | 2017-06-30 | 上海爱优威软件开发有限公司 | Method of speech processing and system |
| CN107146622A (en) * | 2017-06-16 | 2017-09-08 | 合肥美的智能科技有限公司 | Refrigerator, voice interactive system, method, computer equipment, readable storage medium storing program for executing |
| CN107246714A (en) * | 2017-06-28 | 2017-10-13 | 广东美的制冷设备有限公司 | Air conditioning control method and its equipment |
| CN107292327A (en) * | 2016-04-01 | 2017-10-24 | 北京易车互联信息技术有限公司 | Gather around car state identification method and device |
| CN107403619A (en) * | 2017-06-30 | 2017-11-28 | 武汉泰迪智慧科技有限公司 | A kind of sound control method and system applied to bicycle environment |
| CN107516511A (en) * | 2016-06-13 | 2017-12-26 | 微软技术许可有限责任公司 | The Text To Speech learning system of intention assessment and mood |
| WO2018006470A1 (en) * | 2016-07-07 | 2018-01-11 | 深圳狗尾草智能科技有限公司 | Artificial intelligence processing method and device |
| WO2018023516A1 (en) * | 2016-08-04 | 2018-02-08 | 易晓阳 | Voice interaction recognition and control method |
| CN107705166A (en) * | 2016-08-11 | 2018-02-16 | 杭州朗和科技有限公司 | Information processing method and device |
| CN107818787A (en) * | 2017-10-31 | 2018-03-20 | 努比亚技术有限公司 | A kind of processing method of voice messaging, terminal and computer-readable recording medium |
| CN107894972A (en) * | 2017-11-15 | 2018-04-10 | 北京百度网讯科技有限公司 | A kind of session tokens method, apparatus, aggregate server and storage medium |
| CN109087671A (en) * | 2018-09-20 | 2018-12-25 | 重庆先特服务外包产业有限公司 | Government integrates hot line service platform |
| CN109101612A (en) * | 2018-08-06 | 2018-12-28 | 优信数享（北京）信息技术有限公司 | It is a kind of that the methods, devices and systems of solution are provided |
| CN109242529A (en) * | 2018-07-31 | 2019-01-18 | 上海博泰悦臻电子设备制造有限公司 | Vehicle, vehicle device equipment and the online method of investigation and study of user experience based on scene analysis |
| CN109361824A (en) * | 2018-10-26 | 2019-02-19 | 温州博盈科技有限公司 | A kind of digitization customer service system |
| CN110010124A (en) * | 2019-04-09 | 2019-07-12 | 深圳平安综合金融服务有限公司上海分公司 | Equipment and the call method of inspection are examined in call |
| CN110138982A (en) * | 2018-02-09 | 2019-08-16 | 埃森哲环球解决方案有限公司 | Service based on artificial intelligence is realized |
| CN110164455A (en) * | 2018-02-14 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Device, method and the storage medium of user identity identification |
| CN110677540A (en) * | 2019-09-28 | 2020-01-10 | 宏脉信息技术（广州）股份有限公司 | Intelligent voice recognition management system for consultation telephone of medical institution |
| CN110730274A (en) * | 2019-10-17 | 2020-01-24 | 厦门快商通科技股份有限公司 | Voice packet capture analysis method, system, mobile terminal and storage medium |
| JP2020016875A (en) * | 2018-07-24 | 2020-01-30 | バイドゥ オンライン ネットワーク テクノロジー （ベイジン） カンパニー リミテッド | Voice interaction method, device, equipment, computer storage medium, and computer program |
| CN110765242A (en) * | 2018-07-27 | 2020-02-07 | 优信拍（北京）信息科技有限公司 | Method, device and system for providing customer service information |
| CN111048075A (en) * | 2018-10-11 | 2020-04-21 | 上海智臻智能网络科技股份有限公司 | Intelligent customer service system and intelligent customer service robot |
| CN111665732A (en) * | 2020-06-11 | 2020-09-15 | 安吉县广播电视网络有限公司 | Smart home voice device and voice system |
| TWI779237B (en) * | 2019-10-09 | 2022-10-01 | 兆豐國際商業銀行股份有限公司 | Automatic call distribution system and automatic call distribution method |
| CN117198338A (en) * | 2023-11-07 | 2023-12-08 | 中瑞科技术有限公司 | Interphone voiceprint recognition method and system based on artificial intelligence |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1283843A (en) * | 1999-08-10 | 2001-02-14 | 国际商业机器公司 | Speech datas extraction |
| CN1449518A (en) * | 2000-03-21 | 2003-10-15 | 美国联机股份有限公司 | System and method for voice access to internet-based information |
| CN1592427A (en) * | 2003-06-30 | 2005-03-09 | 微软公司 | Ideal transfer of call handling from automated systems to human operators |
| CN1694162A (en) * | 2005-03-31 | 2005-11-09 | 金庆镐 | Phonetic recognition analysing system and service method |
| CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
| CN103516854A (en) * | 2012-06-15 | 2014-01-15 | 三星电子株式会社 | Terminal apparatus and control method thereof |
| US20140079195A1 (en) * | 2012-09-19 | 2014-03-20 | 24/7 Customer, Inc. | Method and apparatus for predicting intent in ivr using natural language queries |
| CN104243729A (en) * | 2013-06-18 | 2014-12-24 | 殷程 | Telephone traffic butler |
-
2015
- 2015-08-14 CN CN201510502763.0A patent/CN105206269A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1283843A (en) * | 1999-08-10 | 2001-02-14 | 国际商业机器公司 | Speech datas extraction |
| CN1449518A (en) * | 2000-03-21 | 2003-10-15 | 美国联机股份有限公司 | System and method for voice access to internet-based information |
| CN1592427A (en) * | 2003-06-30 | 2005-03-09 | 微软公司 | Ideal transfer of call handling from automated systems to human operators |
| CN1694162A (en) * | 2005-03-31 | 2005-11-09 | 金庆镐 | Phonetic recognition analysing system and service method |
| CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
| CN103516854A (en) * | 2012-06-15 | 2014-01-15 | 三星电子株式会社 | Terminal apparatus and control method thereof |
| US20140079195A1 (en) * | 2012-09-19 | 2014-03-20 | 24/7 Customer, Inc. | Method and apparatus for predicting intent in ivr using natural language queries |
| CN104243729A (en) * | 2013-06-18 | 2014-12-24 | 殷程 | Telephone traffic butler |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701211A (en) * | 2016-01-13 | 2016-06-22 | 北京光年无限科技有限公司 | Question-answering system-oriented active interaction data processing method and system |
| CN105654950B (en) * | 2016-01-28 | 2019-07-16 | 百度在线网络技术（北京）有限公司 | Adaptive voice feedback method and device |
| CN105654950A (en) * | 2016-01-28 | 2016-06-08 | 百度在线网络技术（北京）有限公司 | Self-adaptive voice feedback method and device |
| CN105810200A (en) * | 2016-02-04 | 2016-07-27 | 深圳前海勇艺达机器人有限公司 | Man-machine dialogue apparatus and method based on voiceprint identification |
| CN107292327A (en) * | 2016-04-01 | 2017-10-24 | 北京易车互联信息技术有限公司 | Gather around car state identification method and device |
| CN105895083A (en) * | 2016-05-30 | 2016-08-24 | 珠海市魅族科技有限公司 | Information processing method and device |
| US11238842B2 (en) | 2016-06-13 | 2022-02-01 | Microsoft Technology Licensing, Llc | Intent recognition and emotional text-to-speech learning |
| CN107516511A (en) * | 2016-06-13 | 2017-12-26 | 微软技术许可有限责任公司 | The Text To Speech learning system of intention assessment and mood |
| CN107590120A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | Artificial intelligence process method and device |
| WO2018006470A1 (en) * | 2016-07-07 | 2018-01-11 | 深圳狗尾草智能科技有限公司 | Artificial intelligence processing method and device |
| WO2018023516A1 (en) * | 2016-08-04 | 2018-02-08 | 易晓阳 | Voice interaction recognition and control method |
| CN107705166A (en) * | 2016-08-11 | 2018-02-16 | 杭州朗和科技有限公司 | Information processing method and device |
| CN106548358A (en) * | 2016-11-22 | 2017-03-29 | 美的集团股份有限公司 | Conversation processing method and device |
| CN106773923A (en) * | 2016-11-30 | 2017-05-31 | 北京光年无限科技有限公司 | The multi-modal affection data exchange method and device of object manipulator |
| CN106773923B (en) * | 2016-11-30 | 2020-04-21 | 北京光年无限科技有限公司 | Multi-mode emotion data interaction method and device for robot |
| CN106710591A (en) * | 2016-12-13 | 2017-05-24 | 云南电网有限责任公司电力科学研究院 | Voice customer service system for power terminal |
| CN106683672A (en) * | 2016-12-21 | 2017-05-17 | 竹间智能科技（上海）有限公司 | Intelligent dialogue method and system based on emotion and semantics |
| CN106683672B (en) * | 2016-12-21 | 2020-04-03 | 竹间智能科技（上海）有限公司 | Intelligent dialogue method and system based on emotion and semantics |
| CN106782521A (en) * | 2017-03-22 | 2017-05-31 | 海南职业技术学院 | A kind of speech recognition system |
| CN106910514A (en) * | 2017-04-30 | 2017-06-30 | 上海爱优威软件开发有限公司 | Method of speech processing and system |
| CN107146622B (en) * | 2017-06-16 | 2021-02-19 | 合肥美的智能科技有限公司 | Refrigerator, voice interaction system, method, computer device and readable storage medium |
| CN107146622A (en) * | 2017-06-16 | 2017-09-08 | 合肥美的智能科技有限公司 | Refrigerator, voice interactive system, method, computer equipment, readable storage medium storing program for executing |
| CN107246714B (en) * | 2017-06-28 | 2020-03-27 | 广东美的制冷设备有限公司 | Air conditioner control method and device |
| CN107246714A (en) * | 2017-06-28 | 2017-10-13 | 广东美的制冷设备有限公司 | Air conditioning control method and its equipment |
| CN107403619A (en) * | 2017-06-30 | 2017-11-28 | 武汉泰迪智慧科技有限公司 | A kind of sound control method and system applied to bicycle environment |
| CN107818787A (en) * | 2017-10-31 | 2018-03-20 | 努比亚技术有限公司 | A kind of processing method of voice messaging, terminal and computer-readable recording medium |
| CN107894972A (en) * | 2017-11-15 | 2018-04-10 | 北京百度网讯科技有限公司 | A kind of session tokens method, apparatus, aggregate server and storage medium |
| CN110138982B (en) * | 2018-02-09 | 2021-08-10 | 埃森哲环球解决方案有限公司 | Service implementation based on artificial intelligence |
| CN110138982A (en) * | 2018-02-09 | 2019-08-16 | 埃森哲环球解决方案有限公司 | Service based on artificial intelligence is realized |
| CN110164455A (en) * | 2018-02-14 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Device, method and the storage medium of user identity identification |
| JP2020016875A (en) * | 2018-07-24 | 2020-01-30 | バイドゥ オンライン ネットワーク テクノロジー （ベイジン） カンパニー リミテッド | Voice interaction method, device, equipment, computer storage medium, and computer program |
| CN110765242A (en) * | 2018-07-27 | 2020-02-07 | 优信拍（北京）信息科技有限公司 | Method, device and system for providing customer service information |
| CN109242529A (en) * | 2018-07-31 | 2019-01-18 | 上海博泰悦臻电子设备制造有限公司 | Vehicle, vehicle device equipment and the online method of investigation and study of user experience based on scene analysis |
| CN109101612B (en) * | 2018-08-06 | 2022-06-17 | 优信数享（北京）信息技术有限公司 | Method, device and system for providing solution |
| CN109101612A (en) * | 2018-08-06 | 2018-12-28 | 优信数享（北京）信息技术有限公司 | It is a kind of that the methods, devices and systems of solution are provided |
| CN109087671A (en) * | 2018-09-20 | 2018-12-25 | 重庆先特服务外包产业有限公司 | Government integrates hot line service platform |
| CN111048075A (en) * | 2018-10-11 | 2020-04-21 | 上海智臻智能网络科技股份有限公司 | Intelligent customer service system and intelligent customer service robot |
| CN109361824A (en) * | 2018-10-26 | 2019-02-19 | 温州博盈科技有限公司 | A kind of digitization customer service system |
| CN110010124A (en) * | 2019-04-09 | 2019-07-12 | 深圳平安综合金融服务有限公司上海分公司 | Equipment and the call method of inspection are examined in call |
| CN110677540A (en) * | 2019-09-28 | 2020-01-10 | 宏脉信息技术（广州）股份有限公司 | Intelligent voice recognition management system for consultation telephone of medical institution |
| TWI779237B (en) * | 2019-10-09 | 2022-10-01 | 兆豐國際商業銀行股份有限公司 | Automatic call distribution system and automatic call distribution method |
| CN110730274B (en) * | 2019-10-17 | 2021-11-19 | 厦门快商通科技股份有限公司 | Voice packet capture analysis method, system, mobile terminal and storage medium |
| CN110730274A (en) * | 2019-10-17 | 2020-01-24 | 厦门快商通科技股份有限公司 | Voice packet capture analysis method, system, mobile terminal and storage medium |
| CN111665732A (en) * | 2020-06-11 | 2020-09-15 | 安吉县广播电视网络有限公司 | Smart home voice device and voice system |
| CN117198338A (en) * | 2023-11-07 | 2023-12-08 | 中瑞科技术有限公司 | Interphone voiceprint recognition method and system based on artificial intelligence |
| CN117198338B (en) * | 2023-11-07 | 2024-01-26 | 中瑞科技术有限公司 | Interphone voiceprint recognition method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105206269A (en) | Voice processing method and device | |
| CN109672786B (en) | Incoming call answering method and device | |
| CN106790004B (en) | Customer service auxiliary real-time prompt system based on artificial intelligence | |
| US10057419B2 (en) | Intelligent call screening | |
| CN109064315A (en) | Overdue bill intelligence collection method, apparatus, computer equipment and storage medium | |
| US20160117624A1 (en) | Intelligent meeting enhancement system | |
| CN107818798A (en) | Customer service quality evaluating method, device, equipment and storage medium | |
| CN104185868A (en) | Voice authentication and speech recognition system and method | |
| CN109979457A (en) | A method of thousand people, thousand face applied to Intelligent dialogue robot | |
| CN108052605A (en) | A kind of intelligent Answer System based on client feature library | |
| US11948577B1 (en) | Analysis of digital voice data in a data-communication server system | |
| CN110895940A (en) | Intelligent voice interaction method and device | |
| JP6073649B2 (en) | Automatic voice recognition / conversion system | |
| CN110809095A (en) | Method and device for voice call-out | |
| CN111128241A (en) | Intelligent quality inspection method and system for voice call | |
| CN112131358A (en) | Scene flow structure and intelligent customer service system applied by same | |
| TW202036323A (en) | Intelligent online customer service convergence core system which can provide a reply or query to an intention generated through voice recognition and natural language processing procedures | |
| CN111405236A (en) | Video conference big data analysis method and system | |
| CN115858744A (en) | Outbound method, device and storage medium based on AI | |
| CN113962735A (en) | Intelligent marketing system | |
| CN113779217A (en) | Intelligent voice outbound service method and system based on human-computer interaction | |
| CN104715045A (en) | Information transmitting method and terminal | |
| CN112182185A (en) | Intelligent client auxiliary processing method and system for power supply field | |
| CN104243729A (en) | Telephone traffic butler | |
| WO2023090380A1 (en) | Program, information processing system, and information processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151230 |
|
| RJ01 | Rejection of invention patent application after publication |