CN105096938A - Method and device for obtaining user characteristic information of user - Google Patents
Method and device for obtaining user characteristic information of user Download PDFInfo
- Publication number
- CN105096938A CN105096938A CN201510376948.1A CN201510376948A CN105096938A CN 105096938 A CN105096938 A CN 105096938A CN 201510376948 A CN201510376948 A CN 201510376948A CN 105096938 A CN105096938 A CN 105096938A
- Authority
- CN
- China
- Prior art keywords
- user
- predetermined characteristic
- information
- user characteristics
- characteristics object
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for obtaining user characteristic information of a user. The method comprises the following steps: for each user characteristic object in one or more user characteristic objects, obtaining predetermined characteristics matched with voice information from a plurality of predetermined characteristics of the user characteristic object according to the voice information of the user; according to the predetermined characteristics matched with voice information, determining the user characteristic information of the user. According to the scheme, matched predetermined characteristics of the voice information for multiple user characteristic objects can be obtained according to the voice information of the user, so that relatively comprehensive user characteristic information can be obtained, and identity recognition of the user is facilitated, for example, in the national security field, the method can be used for obtaining user characteristic information of suspects according to recording of suspects, and thus the scope of the suspects is reduced.
Description
Technical field
The present invention relates to field of computer technology, particularly relating to a kind of method and apparatus of the user's characteristic information for obtaining user.
Background technology
At present, along with the development of machine learning field degree of depth Learning Studies, the application of speech recognition technology is also more and more wider.But in prior art, speech recognition technology is generally used for identifying voice content exactly, as realized paying dues or function of search etc. of speech trigger by speech recognition technology.
Summary of the invention
The object of this invention is to provide a kind of method and apparatus of the user's characteristic information for obtaining user.
According to an aspect of the present invention, provide a kind of method of the user's characteristic information for obtaining user, wherein, the method comprises the following steps:
For each user characteristics object at least one user characteristics object, according to the voice messaging of described user, from multiple predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice messaging;
According to the predetermined characteristic matched with described voice messaging, determine the user's characteristic information of described user.
According to another aspect of the present invention, additionally provide a kind of device of the user's characteristic information for obtaining user, wherein, this device comprises with lower device:
Coalignment, for for each user characteristics object at least one user characteristics object, according to the voice messaging of described user, obtains the predetermined characteristic matched with described voice messaging from multiple predetermined characteristic of this user characteristics object;
Determining device, for the predetermined characteristic that basis and described voice messaging match, determines the user's characteristic information of described user.
Compared with prior art, the present invention has the following advantages: can according to the voice messaging of user, obtain this voice messaging for multiple user characteristics object, the predetermined characteristic that matches, thus more comprehensive user's characteristic information can be obtained, the identification carrying out user can be convenient to, as in national security field, can be used for the user's characteristic information obtaining suspect according to the recording from suspect, thus reduce suspect's scope; Can according to the voice characteristics information corresponding with voice messaging and/or text message, the predetermined characteristic matched with voice messaging is determined from multiple predetermined characteristic of each user characteristics object, and can based on the speech samples set of large data and the incompatible raising accuracy of word sample set; For each user characteristics object at least one user characteristics object, can in conjunction with current acquired, with the predetermined characteristic of other user characteristics match objects, from multiple predetermined characteristic of this user characteristics object, determine the predetermined characteristic of mating with voice messaging; By gathering a large amount of speech samples or word sample sets up the speech samples set corresponding with each predetermined characteristic or word sample set, can mate for voice messaging, obtaining more accurately comprehensively user's characteristic information.
Accompanying drawing explanation
By reading the detailed description done non-limiting example done with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:
Fig. 1 is the schematic flow sheet of the method for the user's characteristic information for obtaining user of one embodiment of the invention;
Fig. 2 is the structural representation of the device of the user's characteristic information for obtaining user of one embodiment of the invention;
Fig. 3 is the schematic diagram of the corresponding relation between the user characteristics object of the present invention's example and predetermined characteristic.
In accompanying drawing, same or analogous Reference numeral represents same or analogous parts.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
Fig. 1 is the schematic flow sheet of the method for the user's characteristic information for obtaining user of one embodiment of the invention.
Wherein, the method for the present embodiment realizes mainly through computer equipment; Described computer equipment comprises subscriber equipment and the network equipment.The described network equipment includes but not limited to the server group that single network server, multiple webserver form or the cloud be made up of a large amount of computing machine or the webserver based on cloud computing (CloudComputing), wherein, cloud computing is the one of Distributed Calculation, the super virtual machine be made up of a group loosely-coupled computing machine collection; Network residing for the described network equipment includes but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN etc.Described subscriber equipment includes but not limited to PC, panel computer, smart mobile phone, PDA, IPTV etc.
It should be noted that, described subscriber equipment, the network equipment and network are only citing, and other computer equipments that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this with way of reference.
Step S1 and step S2 is comprised according to the method for the present embodiment.
In step sl, for each user characteristics object at least one user characteristics object, computer equipment, according to the voice messaging of user, obtains the predetermined characteristic matched with this voice messaging from multiple predetermined characteristic of this user characteristics object.
Wherein, described user characteristics object comprise any describe user characteristics time can as the object of target; Preferably, described user characteristics object includes but not limited to: the sex, age, region, personality, occupation etc. of user.
Wherein, a user characteristics object comprises multiple predetermined characteristic, and the plurality of predetermined characteristic carries out to this user characteristics object the feature that predetermined division obtains for representing.Such as, Fig. 3 is the schematic diagram of the corresponding relation between the user characteristics object of the present invention's example and predetermined characteristic, wherein, the predetermined characteristic of user characteristics object " sex " comprising: the male sex, women, the predetermined characteristic of user characteristics object " age " comprising: 0 years old-15 years old, 15 years old-30 years old, 30 years old-50 years old, more than 50 years old, the predetermined characteristic of user characteristics object " region " comprising: North China, the Northeast, East China, Central China, South China, southwest, the Northwest, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type, the predetermined characteristic of user characteristics object " occupation " comprising: Skill and method, affairs type, research, artistic type, through cast, koinotropic type.
Wherein, computer equipment can adopt various ways to obtain the voice messaging of user.Such as, computer equipment directly obtains and is stored in voice messaging in this computer equipment, user.Again such as, computer equipment is the network equipment, and this network equipment receives user is uploaded to this network equipment voice messaging by subscriber equipment.
Particularly, for each user characteristics object at least one user characteristics object, computer equipment is according to the voice messaging of user, and the implementation obtaining the predetermined characteristic matched with this voice messaging from multiple predetermined characteristic of this user characteristics object includes but not limited to:
1) described step S1 comprises step S11-1 and step S11-2 further.
In step S11-1, computer equipment, according to described voice messaging, obtains the voice characteristics information corresponding with described voice messaging.
Wherein, described voice characteristics information comprises any information relevant to the feature of voice; Preferably, described voice characteristics information includes but not limited to:
A) information that corresponding to voice frequency of sound wave is relevant, as the tone, pitch etc. of voice.
B) information that corresponding to sound sonic wave amplitude is relevant, as the loudness, loudness of a sound etc. of voice.
C) information that corresponding to the voice sound wave cycle is relevant, as the duration of a sound etc. of voice.
D) information that corresponding to voice waveform characteristic is relevant, as the tone color etc. of voice.
It should be noted that, above-mentioned voice characteristics information is only citing, but not limitation of the present invention, those skilled in the art will be understood that any information relevant to the feature of voice, all should be included in the scope of voice characteristics information of the present invention.
Particularly, computer equipment can adopt various ways according to described voice messaging, obtains the voice characteristics information corresponding with described voice messaging.
Such as, computer equipment directly carries out speech analysis process (as Fast Fourier Transform (FFT) etc.) to the voice messaging of user, extracts the voice characteristics information in voice messaging.
Again such as, computer equipment, using the input of voice messaging as speech model (this speech model is the model for extracting voice characteristics information obtained by sample training), obtains the voice characteristics information that this voice messaging is corresponding.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any according to described voice messaging, obtain the implementation of the voice characteristics information corresponding with described voice messaging, all should be within the scope of the present invention.
In step S11-2, for each user characteristics object at least one user characteristics object described, computer equipment is according to described voice characteristics information, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice characteristics information.
Wherein, described speech samples set is for gathering multiple speech samples, and described speech samples set can show various ways, as document form, database form, vector set form etc.
Wherein, for each predetermined characteristic of user characteristics object, the speech samples set corresponding with this predetermined characteristic comprises at least one speech samples corresponding with this predetermined characteristic.Such as, user characteristics object " sex " comprises following predetermined characteristic: the male sex, women; The speech samples set of predetermined characteristic " male sex " correspondence comprises the multiple speech samples from male user, and the speech samples set of predetermined characteristic " women " correspondence comprises the multiple speech samples from female user.Again such as, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type, (it is higher that the plurality of speech samples has tone to multiple speech samples that speech samples set corresponding to predetermined characteristic " export-oriented " comprises from the user with extrovert personality, word speed is feature faster), (it is lower that the plurality of speech samples has tone to multiple speech samples that speech samples set corresponding to predetermined characteristic " internally-oriented " comprises from the user with introversion, the feature that word speed is slower), (it is more stable that the plurality of speech samples has tone to multiple speech samples that speech samples set corresponding to predetermined characteristic " balanced type " comprises from the user with balanced personality, the feature that word speed is milder).
It should be noted that, the speech samples set corresponding with each predetermined characteristic of user characteristics object is merged, be the total speech samples set corresponding with this user characteristics object, each speech samples in this total speech samples set is this speech samples corresponding to user characteristics object.
Particularly, for each user characteristics object at least one user characteristics object, computer equipment is according to described voice characteristics information, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object, the implementation obtaining the predetermined characteristic matched with described voice characteristics information includes but not limited to:
A) for each user characteristics object at least one user characteristics object, sample training is carried out in the computer equipment pair speech samples set corresponding with each predetermined characteristic of this user characteristics object, obtains the speech samples model corresponding with described each predetermined characteristic; In step S11-2, speech samples model corresponding to each predetermined characteristic mates with voice characteristics information by computer equipment, and using predetermined characteristic corresponding for speech samples model the highest for matching degree as the predetermined characteristic matched with voice characteristics information.
Such as, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type; Wherein, the speech samples set corresponding with predetermined characteristic " export-oriented " is Set1, carrying out to Set1 the speech samples model that sample training obtains is model1, the speech samples set corresponding with predetermined characteristic " internally-oriented " is Set2, carrying out to Set2 the speech samples model that sample training obtains is model2, the speech samples set corresponding with predetermined characteristic " balanced type " is Set3, and carrying out to Set3 the speech samples model that sample training obtains is model3; In step S11-1, computer equipment obtains voice characteristics information Info1, in step S11-2, Info1 mates with model1, model2, model3 by computer equipment respectively, and using the predetermined characteristic " internally-oriented " corresponding to model2 the highest for matching degree as the predetermined characteristic matched with voice characteristics information.
B) for each user characteristics object at least one user characteristics object, the voice characteristics information obtained in step S11-1 mates with each speech samples corresponding to this user characteristics object by computer equipment, and using the predetermined characteristic corresponding to speech samples the highest for matching degree as the predetermined characteristic matched with this voice characteristics information.
Such as, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type, wherein, the speech samples set corresponding with predetermined characteristic " export-oriented " is Set1, the speech samples set corresponding with predetermined characteristic " internally-oriented " is Set2, and the speech samples set corresponding with predetermined characteristic " balanced type " is Set3; In step S11-1, computer equipment obtains voice characteristics information Info1, in step S11-2, Info1 mates with each speech samples in Set1, Set2, Set3 by computer equipment respectively, and using the predetermined characteristic " internally-oriented " (predetermined characteristic also namely corresponding to Set2) corresponding to speech samples Sample100 (this Sample100 belongs to Set2) the highest for matching degree as the predetermined characteristic matched with voice characteristics information.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any for each user characteristics object at least one user characteristics object described, according to described voice characteristics information, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object, obtain the implementation of the predetermined characteristic matched with described voice characteristics information, all should be within the scope of the present invention.
2) described step S1 comprises step S12-1 and step S12-2 further.
In step S12-1, computer equipment carries out speech recognition to described voice messaging, obtains the text message corresponding with described voice messaging.
Wherein, computer equipment can adopt multiple voice recognition method, carries out speech recognition to obtain described text message to voice messaging.Such as, computer equipment can adopt dynamic time warping (DTW, DynamicTimeWarping), or analog matching technique, carries out speech recognition to voice messaging, obtains the text message etc. corresponding with this voice messaging.
In step S12-2, for each user characteristics object at least one user characteristics object described, computer equipment is according to described text message, and with each predetermined characteristic parallel expression sample set of this user characteristics object, obtain the predetermined characteristic matched with described text message.
Wherein, described word sample set is for gathering multiple word, and described word sample set can show various ways, as document form, database form etc.
Wherein, for each predetermined characteristic of user characteristics object, comprise at least one word sample corresponding with this predetermined characteristic with this predetermined characteristic parallel expression sample set.Wherein, described word sample includes but not limited to the conventional modal particle corresponding with predetermined characteristic or feature vocabulary, as comprised the technical term of medical industry with predetermined characteristic " doctor " the parallel expression sample of user characteristics object " occupation ", comprise the dialectism of the Northeast with predetermined characteristic " the Northeast " the parallel expression sample of user characteristics object " region ", comprise with predetermined characteristic " women " the parallel expression sample of user characteristics object " sex " modal particle that women commonly uses.
It should be noted that, each predetermined characteristic parallel expression sample set with user characteristics object is merged, be the total word sample set corresponding with this user characteristics object, each word sample in this total word sample set is this word sample corresponding to user characteristics object.
Particularly, for each user characteristics object at least one user characteristics object, the text message obtained in step S12-1 mates with each word sample corresponding to this user characteristics object by computer equipment, and using the predetermined characteristic corresponding to word sample the highest for matching degree as the predetermined characteristic with text information match.
Such as, the predetermined characteristic of user characteristics object " region " comprises North China, the Northeast, East China, Central China, South China, southwest, the Northwest; In step S11-1, it is " the Chinese boxing thief that I has just learned is severe " that computer equipment obtains the text message corresponding with voice messaging; In step S11-2, for user characteristics object " region ", text information is mated with the word sample set corresponding to above-mentioned predetermined characteristic by computer equipment respectively, and using the predetermined characteristic " the Northeast " corresponding to word sample set the highest for matching degree as the predetermined characteristic with text information match.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any for each user characteristics object at least one user characteristics object described, according to described text message, and with each predetermined characteristic parallel expression sample set of this user characteristics object, obtain the implementation of the predetermined characteristic matched with described text message, all should be within the scope of the present invention.
As a kind of preferred version of step S1, described step S1 comprises step S13 further.In step s 13, for each user characteristics object at least one user characteristics object, computer equipment is according to the voice messaging of user, and in conjunction with current acquired, with the predetermined characteristic of other user characteristics match objects, from multiple predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice messaging.
As an example, the predetermined characteristic of user characteristics object " sex " comprising: the male sex, women; The predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type; Before step S13, computer equipment is determined according to the instruction operation of operating personnel: the predetermined characteristic matched with voice messaging in the predetermined characteristic of user characteristics object " sex " is " women "; In step s 13, computer equipment is according to this voice messaging and predetermined characteristic " women ", the predetermined characteristic " export-oriented " that acquisition and this voice messaging match from multiple predetermined characteristic of user characteristics object " personality " is (for different sexes, criterion between voice messaging from personality is different, and the tone as the male sex of pitch ratio " export-oriented " personality of the women of " export-oriented " personality is high).
As another example, the predetermined characteristic of user characteristics object " sex " comprising: the male sex, women; The predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type; In step s 13, computer equipment is first from the predetermined characteristic of user characteristics " sex ", determine that the predetermined characteristic matched with voice messaging is " women ", afterwards, computer equipment, according to fixed predetermined characteristic " women " and this voice messaging, obtains the predetermined characteristic " export-oriented " matched with this voice messaging from multiple predetermined characteristic of user characteristics object " personality ".
It should be noted that, above-mentioned implementation 1), 2) and above-mentioned preferred version between can be combined with each other.Such as, computer equipment obtains the voice characteristics information corresponding with voice messaging and text message, for each user characteristics object at least one user characteristics object, computer equipment according to described by described voice characteristics information, described text message, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object and word sample set, determine the predetermined characteristic matched with voice messaging.Again such as, for each user characteristics object at least one user characteristics object, computer equipment, according to the voice characteristics information corresponding with voice messaging, the speech samples set corresponding with each predetermined characteristic of this user characteristics object and the current acquired predetermined characteristic with other user characteristics match objects, is determined and the predetermined characteristic that described voice characteristics information matches.Again such as, for each user characteristics object at least one user characteristics object, computer equipment according to the text message corresponding with voice messaging, with each predetermined characteristic parallel expression sample set of this user characteristics object and the current acquired predetermined characteristic with other user characteristics match objects, determine and the predetermined characteristic that described text message matches.
It should be noted that, for each user characteristics object, computer equipment may obtain the multiple predetermined characteristic matched with voice messaging; Such as, the predetermined characteristic of user characteristics object " occupation " comprising: Skill and method, affairs type, research, artistic type, through cast, koinotropic type, computer equipment obtains the predetermined characteristic matched with the voice messaging of user and is from above-mentioned predetermined characteristic: Skill and method, research.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any for each user characteristics object at least one user characteristics object, according to the voice messaging of user, from multiple predetermined characteristic of this user characteristics object, obtain the implementation of the predetermined characteristic matched with this voice messaging, all should be within the scope of the present invention.
In step s 2, computer equipment, according to the predetermined characteristic matched with described voice messaging, determines the user's characteristic information of described user.
Wherein, described user's characteristic information comprises any information being used to indicate the feature of user; Preferably, described user's characteristic information includes but not limited to:
1) the sex character information of user.
Wherein, described sex character information is used to indicate the sex of the user corresponding with voice messaging, as the male sex, women.
2) the age characteristics information of user.
Wherein, described age characteristics information comprises any information being used to indicate the age characteristics of the user corresponding with voice messaging, preferably, described age characteristics information includes but not limited to: be used to indicate the information of the age range (as 30 years old-50 years old etc.) of user, be used to indicate the age level (as children, teenager, youth, middle age, old age etc.) of user.
3) the regional feature information of user.
Wherein, described regional feature information comprises any information being used to indicate the regional feature of user, preferably, described regional feature information includes but not limited to: the nationality belonging to user, the region belonging to user (as region, North China), the province (as Hebei province) belonging to user, the city (as Chengde) etc. belonging to user.
4) the character trait information of user.
Wherein, described character trait information comprises any information being used to indicate the character trait of user; Wherein, described character trait comprises and divides based on any standard the character trait obtained, character trait as divided based on mental function comprises: intellectual type, emotion type, will type, and the character trait divided based on psychological activity tendentiousness comprises: export-oriented, internally-oriented, balanced type etc.
5) the job characteristics information of user.
Wherein, described job characteristics information comprises any information being used to indicate the job characteristics of user; Wherein, described job characteristics includes but not limited to concrete occupation (as doctor, teacher etc.), occupation type (as Skill and method, affairs type, research, artistic type etc.).
It should be noted that, above-mentioned user's characteristic information is only citing, but not limitation of the present invention, those skilled in the art will be understood that any information being used to indicate the feature of user, all should be included in the scope of user's characteristic information of the present invention.
Particularly, all predetermined characteristic that the voice messaging with user matches by computer equipment merge, and determine the user's characteristic information of user.
Such as, based on the user characteristics object shown in Fig. 3, in step sl, it is " male sex " that computer equipment obtains the predetermined characteristic matched with voice messaging from multiple predetermined characteristic of " sex ", from multiple predetermined characteristic at " age ", obtain the predetermined characteristic matched with voice messaging is " 30 years old-50 years old ", from multiple predetermined characteristic of " region ", obtain the predetermined characteristic matched with voice messaging is " the Northeast ", from multiple predetermined characteristic of " personality ", obtain the predetermined characteristic matched with voice messaging is " internally-oriented ", from multiple predetermined characteristic of " occupation ", obtain the predetermined characteristic matched with voice messaging is " Skill and method ", then in step s 2, all predetermined characteristic that are obtained, that match with voice messaging in step sl merge by computer equipment, and obtaining user's characteristic information is: the male sex, 30 years old-50 years old, northeast area, internally-oriented personality, be engaged in Skill and method occupation.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, the predetermined characteristic that any basis matches with described voice messaging, determine the implementation of the user's characteristic information of described user, all should be within the scope of the present invention.
As a preferred version of the present embodiment, the method for the present embodiment also comprises step S3.
In step s3, computer equipment performs following operation to each user characteristics object at least one user characteristics object described:
For each predetermined characteristic in multiple predetermined characteristic of this user characteristics object, according to the voice document corresponding with this predetermined characteristic, set up the speech samples set of this predetermined characteristic.
Such as, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type; In step s3, computer equipment collection has the voice document of multiple users of " export-oriented " personality, sets up the speech samples set corresponding with " export-oriented "; Computer equipment collection has the voice document of multiple users of " internally-oriented " personality, sets up the speech samples set corresponding with " internally-oriented "; Computer equipment collection has the voice document of multiple users of " balanced type " personality, sets up the speech samples set corresponding with " balanced type ".
As another preferred version of the present embodiment, the method for the present embodiment also comprises step S4.
In step s 4 which, computer equipment performs following operation to each user characteristics object at least one user characteristics object:
For each predetermined characteristic in multiple predetermined characteristic of this user characteristics object, according to the multiple words corresponding with this predetermined characteristic, set up the word sample set of this predetermined characteristic.
Such as, the predetermined characteristic of user characteristics object " region " comprising: North China, the Northeast, East China, Central China, South China, southwest, the Northwest; In step s3, for above-mentioned each predetermined characteristic, computer equipment gathers the dialectism that the user in region corresponding to this predetermined characteristic commonly uses, and sets up the word sample set of this predetermined characteristic.
According to the scheme of the present embodiment, can according to the voice messaging of user, obtain this voice messaging for multiple user characteristics object, the predetermined characteristic that matches, thus more comprehensive user's characteristic information can be obtained, the feature identification carrying out user can be convenient to, as in national security field, can be used for the user's characteristic information obtaining suspect according to the recording from suspect, thus reduce suspect's scope; Can according to the voice characteristics information corresponding with voice messaging and/or text message, the predetermined characteristic matched with voice messaging is determined from multiple predetermined characteristic of each user characteristics object, and can based on the speech samples set of large data and the incompatible raising accuracy of word sample set; For each user characteristics object at least one user characteristics object, can in conjunction with current acquired, with the predetermined characteristic of other user characteristics match objects, from multiple predetermined characteristic of this user characteristics object, determine the predetermined characteristic of mating with voice messaging; By gathering a large amount of speech samples or word sample sets up the speech samples set corresponding with each predetermined characteristic or word sample set, can mate for voice messaging, obtaining more accurately comprehensively user's characteristic information.
Fig. 2 is the structural representation of the device of the user's characteristic information for obtaining user of one embodiment of the invention.This device (hereinafter referred to as " feature acquisition device ") being used for the user's characteristic information obtaining user comprises coalignment 1 and determining device 2.For each user characteristics object at least one user characteristics object, coalignment 1, according to the voice messaging of user, obtains the predetermined characteristic matched with this voice messaging from multiple predetermined characteristic of this user characteristics object.
Wherein, described user characteristics object comprise any describe user characteristics time can as the object of target; Preferably, described user characteristics object includes but not limited to: the sex, age, region, personality, occupation etc. of user.
Wherein, a user characteristics object comprises multiple predetermined characteristic, and the plurality of predetermined characteristic carries out to this user characteristics object the feature that predetermined division obtains for representing.Such as, Fig. 3 is the schematic diagram of the corresponding relation between the user characteristics object of the present invention's example and predetermined characteristic, wherein, the predetermined characteristic of user characteristics object " sex " comprising: the male sex, women, the predetermined characteristic of user characteristics object " age " comprising: 0 years old-15 years old, 15 years old-30 years old, 30 years old-50 years old, more than 50 years old, the predetermined characteristic of user characteristics object " region " comprising: North China, the Northeast, East China, Central China, South China, southwest, the Northwest, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type, the predetermined characteristic of user characteristics object " occupation " comprising: Skill and method, affairs type, research, artistic type, through cast, koinotropic type.
Wherein, coalignment 1 can adopt various ways to obtain the voice messaging of user.Such as, the coalignment 1 of computer equipment directly obtains and is stored in voice messaging in this computer equipment, user.Again such as, computer equipment is the network equipment, and the coalignment 1 of this network equipment receives user is uploaded to this network equipment voice messaging by subscriber equipment.
Particularly, for each user characteristics object at least one user characteristics object, coalignment 1 is according to the voice messaging of user, and the implementation obtaining the predetermined characteristic matched with this voice messaging from multiple predetermined characteristic of this user characteristics object includes but not limited to:
1) coalignment 1 comprises the first obtaining means (not shown) and the first sub-coalignment (not shown) further.
First obtaining means, according to described voice messaging, obtains the voice characteristics information corresponding with described voice messaging.
Wherein, described voice characteristics information comprises any information relevant to the feature of voice; Preferably, described voice characteristics information includes but not limited to:
A) information that corresponding to voice frequency of sound wave is relevant, as the tone, pitch etc. of voice.
B) information that corresponding to sound sonic wave amplitude is relevant, as the loudness, loudness of a sound etc. of voice.
C) information that corresponding to the voice sound wave cycle is relevant, as the duration of a sound etc. of voice.
D) information that corresponding to voice waveform characteristic is relevant, as the tone color etc. of voice.
It should be noted that, above-mentioned voice characteristics information is only citing, but not limitation of the present invention, those skilled in the art will be understood that any information relevant to the feature of voice, all should be included in the scope of voice characteristics information of the present invention.
Particularly, the first obtaining means can adopt various ways according to described voice messaging, obtains the voice characteristics information corresponding with described voice messaging.
Such as, the first obtaining means directly carries out speech analysis process (as Fast Fourier Transform (FFT) etc.) to the voice messaging of user, extracts the voice characteristics information in voice messaging.
Again such as, the first obtaining means, using the input of voice messaging as speech model (this speech model is the model for extracting voice characteristics information obtained by sample training), obtains the voice characteristics information that this voice messaging is corresponding.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any according to described voice messaging, obtain the implementation of the voice characteristics information corresponding with described voice messaging, all should be within the scope of the present invention.
For each user characteristics object at least one user characteristics object described, first sub-coalignment is according to described voice characteristics information, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice characteristics information.
Wherein, described speech samples set is for gathering multiple speech samples, and described speech samples set can show various ways, as document form, database form, vector set form etc.
Wherein, for each predetermined characteristic of user characteristics object, the speech samples set corresponding with this predetermined characteristic comprises at least one speech samples corresponding with this predetermined characteristic.Such as, user characteristics object " sex " comprises following predetermined characteristic: the male sex, women; The speech samples set of predetermined characteristic " male sex " correspondence comprises the multiple speech samples from male user, and the speech samples set of predetermined characteristic " women " correspondence comprises the multiple speech samples from female user.Again such as, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type, (it is higher that the plurality of speech samples has tone to multiple speech samples that speech samples set corresponding to predetermined characteristic " export-oriented " comprises from the user with extrovert personality, word speed is feature faster), (it is lower that the plurality of speech samples has tone to multiple speech samples that speech samples set corresponding to predetermined characteristic " internally-oriented " comprises from the user with introversion, the feature that word speed is slower), (it is more stable that the plurality of speech samples has tone to multiple speech samples that speech samples set corresponding to predetermined characteristic " balanced type " comprises from the user with balanced personality, the feature that word speed is milder).
It should be noted that, the speech samples set corresponding with each predetermined characteristic of user characteristics object is merged, be the total speech samples set corresponding with this user characteristics object, each speech samples in this total speech samples set is this speech samples corresponding to user characteristics object.
Particularly, for each user characteristics object at least one user characteristics object, first sub-coalignment is according to described voice characteristics information, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object, the implementation obtaining the predetermined characteristic matched with described voice characteristics information includes but not limited to:
A) for each user characteristics object at least one user characteristics object, sample training is carried out in the computer equipment pair speech samples set corresponding with each predetermined characteristic of this user characteristics object, obtains the speech samples model corresponding with described each predetermined characteristic; Speech samples model corresponding to each predetermined characteristic mates with voice characteristics information by the first sub-coalignment, and using predetermined characteristic corresponding for speech samples model the highest for matching degree as the predetermined characteristic matched with voice characteristics information.
Such as, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type; Wherein, the speech samples set corresponding with predetermined characteristic " export-oriented " is Set1, carrying out to Set1 the speech samples model that sample training obtains is model1, the speech samples set corresponding with predetermined characteristic " internally-oriented " is Set2, carrying out to Set2 the speech samples model that sample training obtains is model2, the speech samples set corresponding with predetermined characteristic " balanced type " is Set3, and carrying out to Set3 the speech samples model that sample training obtains is model3; First obtaining means obtains voice characteristics information Info1, Info1 mates with model1, model2, model3 by the first sub-coalignment respectively, and using the predetermined characteristic " internally-oriented " corresponding to model2 the highest for matching degree as the predetermined characteristic matched with voice characteristics information.
B) for each user characteristics object at least one user characteristics object, the voice characteristics information that first obtaining means obtains by the first sub-coalignment mates with each speech samples corresponding to this user characteristics object, and using the predetermined characteristic corresponding to speech samples the highest for matching degree as the predetermined characteristic matched with this voice characteristics information.
Such as, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type, wherein, the speech samples set corresponding with predetermined characteristic " export-oriented " is Set1, the speech samples set corresponding with predetermined characteristic " internally-oriented " is Set2, and the speech samples set corresponding with predetermined characteristic " balanced type " is Set3; First obtaining means obtains voice characteristics information Info1; Info1 mates with each speech samples in Set1, Set2, Set3 by the first sub-coalignment respectively, and using the predetermined characteristic " internally-oriented " (predetermined characteristic also namely corresponding to Set2) corresponding to speech samples Sample100 (this Sample100 belongs to Set2) the highest for matching degree as the predetermined characteristic matched with voice characteristics information.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any for each user characteristics object at least one user characteristics object described, according to described voice characteristics information, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object, obtain the implementation of the predetermined characteristic matched with described voice characteristics information, all should be within the scope of the present invention.
2) coalignment 1 comprises the second obtaining means (not shown) and the second sub-coalignment (not shown) further.
Second obtaining means carries out speech recognition to described voice messaging, obtains the text message corresponding with described voice messaging.
Wherein, the second obtaining means can adopt multiple voice recognition method, carries out speech recognition to obtain described text message to voice messaging.Such as, the second obtaining means can adopt dynamic time warping (DTW, DynamicTimeWarping), or analog matching technique, carries out speech recognition to voice messaging, obtains the text message etc. corresponding with this voice messaging.
For each user characteristics object at least one user characteristics object described, second sub-coalignment is according to described text message, and with each predetermined characteristic parallel expression sample set of this user characteristics object, obtain the predetermined characteristic matched with described text message.
Wherein, described word sample set is for gathering multiple word, and described word sample set can show various ways, as document form, database form etc.
Wherein, for each predetermined characteristic of user characteristics object, comprise at least one word sample corresponding with this predetermined characteristic with this predetermined characteristic parallel expression sample set.Wherein, described word sample includes but not limited to the conventional modal particle corresponding with predetermined characteristic or feature vocabulary, as comprised the technical term of medical industry with predetermined characteristic " doctor " the parallel expression sample of user characteristics object " occupation ", comprise the dialectism of the Northeast with predetermined characteristic " the Northeast " the parallel expression sample of user characteristics object " region ", comprise with predetermined characteristic " women " the parallel expression sample of user characteristics object " sex " modal particle that women commonly uses.
It should be noted that, each predetermined characteristic parallel expression sample set with user characteristics object is merged, be the total word sample set corresponding with this user characteristics object, each word sample in this total word sample set is this word sample corresponding to user characteristics object.
Particularly, for each user characteristics object at least one user characteristics object, the text message that second obtaining means obtains by the second sub-coalignment mates with each word sample corresponding to this user characteristics object, and using the predetermined characteristic corresponding to word sample the highest for matching degree as the predetermined characteristic with text information match.
Such as, the predetermined characteristic of user characteristics object " region " comprises North China, the Northeast, East China, Central China, South China, southwest, the Northwest; It is " the Chinese boxing thief that I has just learned is severe " that second obtaining means obtains the text message corresponding with voice messaging; For user characteristics object " region ", text information is mated with the word sample set corresponding to above-mentioned predetermined characteristic by the second sub-coalignment respectively, and using the predetermined characteristic " the Northeast " corresponding to word sample set the highest for matching degree as the predetermined characteristic with text information match.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any for each user characteristics object at least one user characteristics object described, according to described text message, and with each predetermined characteristic parallel expression sample set of this user characteristics object, obtain the implementation of the predetermined characteristic matched with described text message, all should be within the scope of the present invention.
As a kind of preferred version of coalignment 1, described coalignment 1 comprises the 3rd sub-coalignment (not shown) further.For each user characteristics object at least one user characteristics object, 3rd sub-coalignment is according to the voice messaging of user, and in conjunction with current acquired, with the predetermined characteristic of other user characteristics match objects, from multiple predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice messaging.
As an example, the predetermined characteristic of user characteristics object " sex " comprising: the male sex, women; The predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type; Before the 3rd sub-coalignment executable operations, computer equipment is determined according to the instruction operation of operating personnel: the predetermined characteristic matched with voice messaging in the predetermined characteristic of user characteristics object " sex " is " women "; 3rd sub-coalignment is according to this voice messaging and predetermined characteristic " women ", the predetermined characteristic " export-oriented " that acquisition and this voice messaging match from multiple predetermined characteristic of user characteristics object " personality " is (for different sexes, criterion between voice messaging from personality is different, and the tone as the male sex of pitch ratio " export-oriented " personality of the women of " export-oriented " personality is high).
As another example, the predetermined characteristic of user characteristics object " sex " comprising: the male sex, women; The predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type; 3rd sub-coalignment is first from the predetermined characteristic of user characteristics " sex ", determine that the predetermined characteristic matched with voice messaging is " women ", afterwards, 3rd sub-coalignment, according to fixed predetermined characteristic " women " and this voice messaging, obtains the predetermined characteristic " export-oriented " matched with this voice messaging from multiple predetermined characteristic of user characteristics object " personality ".
It should be noted that, above-mentioned implementation 1), 2) and above-mentioned preferred version between can be combined with each other.Such as, coalignment 1 obtains the voice characteristics information corresponding with voice messaging and text message, for each user characteristics object at least one user characteristics object, coalignment 1 according to described by described voice characteristics information, described text message, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object and word sample set, determine the predetermined characteristic matched with voice messaging.Again such as, for each user characteristics object at least one user characteristics object, coalignment 1, according to the voice characteristics information corresponding with voice messaging, the speech samples set corresponding with each predetermined characteristic of this user characteristics object and the current acquired predetermined characteristic with other user characteristics match objects, is determined and the predetermined characteristic that described voice characteristics information matches.Again such as, for each user characteristics object at least one user characteristics object, coalignment 1 according to the text message corresponding with voice messaging, with each predetermined characteristic parallel expression sample set of this user characteristics object and the current acquired predetermined characteristic with other user characteristics match objects, determine and the predetermined characteristic that described text message matches.
It should be noted that, for each user characteristics object, coalignment 1 may obtain the multiple predetermined characteristic matched with voice messaging; Such as, the predetermined characteristic of user characteristics object " occupation " comprising: Skill and method, affairs type, research, artistic type, through cast, koinotropic type, coalignment 1 obtains the predetermined characteristic matched with the voice messaging of user and is from above-mentioned predetermined characteristic: Skill and method, research.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any for each user characteristics object at least one user characteristics object, according to the voice messaging of user, from multiple predetermined characteristic of this user characteristics object, obtain the implementation of the predetermined characteristic matched with this voice messaging, all should be within the scope of the present invention.
Determining device 2, according to the predetermined characteristic matched with described voice messaging, determines the user's characteristic information of described user.
Wherein, described user's characteristic information comprises any information being used to indicate the feature of user; Preferably, described user's characteristic information includes but not limited to:
1) the sex character information of user.
Wherein, described sex character information is used to indicate the sex of the user corresponding with voice messaging, as the male sex, women.
2) the age characteristics information of user.
Wherein, described age characteristics information comprises any information being used to indicate the age characteristics of the user corresponding with voice messaging, preferably, described age characteristics information includes but not limited to: be used to indicate the information of the age range (as 30 years old-50 years old etc.) of user, be used to indicate the age level (as children, teenager, youth, middle age, old age etc.) of user.
3) the regional feature information of user.
Wherein, described regional feature information comprises any information being used to indicate the regional feature of user, preferably, described regional feature information includes but not limited to: the nationality belonging to user, the region belonging to user (as region, North China), the province (as Hebei province) belonging to user, the city (as Chengde) etc. belonging to user.
4) the character trait information of user.
Wherein, described character trait information comprises any information being used to indicate the character trait of user; Wherein, described character trait comprises and divides based on any standard the character trait obtained, character trait as divided based on mental function comprises: intellectual type, emotion type, will type, and the character trait divided based on psychological activity tendentiousness comprises: export-oriented, internally-oriented, balanced type etc.
5) the job characteristics information of user.
Wherein, described job characteristics information comprises any information being used to indicate the job characteristics of user; Wherein, described job characteristics includes but not limited to concrete occupation (as doctor, teacher etc.), occupation type (as Skill and method, affairs type, research, artistic type etc.).
It should be noted that, above-mentioned user's characteristic information is only citing, but not limitation of the present invention, those skilled in the art will be understood that any information being used to indicate the feature of user, all should be included in the scope of user's characteristic information of the present invention.
Particularly, all predetermined characteristic that the voice messaging with user matches by determining device 2 merge, and determine the user's characteristic information of user.
Such as, based on the user characteristics object shown in Fig. 3, it is " male sex " that coalignment 1 obtains the predetermined characteristic matched with voice messaging from multiple predetermined characteristic of " sex ", from multiple predetermined characteristic at " age ", obtain the predetermined characteristic matched with voice messaging is " 30 years old-50 years old ", from multiple predetermined characteristic of " region ", obtain the predetermined characteristic matched with voice messaging is " the Northeast ", from multiple predetermined characteristic of " personality ", obtain the predetermined characteristic matched with voice messaging is " internally-oriented ", from multiple predetermined characteristic of " occupation ", obtain the predetermined characteristic matched with voice messaging is " Skill and method ", then determining device 2 coalignment 1 is obtained, all predetermined characteristic of matching with voice messaging merge, obtaining user's characteristic information is: the male sex, 30 years old-50 years old, northeast area, internally-oriented personality, be engaged in Skill and method occupation.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, the predetermined characteristic that any basis matches with described voice messaging, determine the implementation of the user's characteristic information of described user, all should be within the scope of the present invention.
As a preferred version of the present embodiment, the feature acquisition device of the present embodiment also comprises the first apparatus for establishing (not shown).
First apparatus for establishing performs following operation to each user characteristics object at least one user characteristics object described:
For each predetermined characteristic in multiple predetermined characteristic of this user characteristics object, according to the voice document corresponding with this predetermined characteristic, set up the speech samples set of this predetermined characteristic.
Such as, the predetermined characteristic of user characteristics object " personality " comprising: export-oriented, internally-oriented, balanced type; First apparatus for establishing collection has the voice document of multiple users of " export-oriented " personality, sets up the speech samples set corresponding with " export-oriented "; First apparatus for establishing collection has the voice document of multiple users of " internally-oriented " personality, sets up the speech samples set corresponding with " internally-oriented "; First apparatus for establishing collection has the voice document of multiple users of " balanced type " personality, sets up the speech samples set corresponding with " balanced type ".
As another preferred version of the present embodiment, the feature acquisition device of the present embodiment also comprises the second apparatus for establishing (not shown).
Second apparatus for establishing performs following operation to each user characteristics object at least one user characteristics object:
For each predetermined characteristic in multiple predetermined characteristic of this user characteristics object, according to the multiple words corresponding with this predetermined characteristic, set up the word sample set of this predetermined characteristic.
Such as, the predetermined characteristic of user characteristics object " region " comprising: North China, the Northeast, East China, Central China, South China, southwest, the Northwest; For above-mentioned each predetermined characteristic, the second apparatus for establishing gathers the dialectism that the user in region corresponding to this predetermined characteristic commonly uses, and sets up the word sample set of this predetermined characteristic.
According to the scheme of the present embodiment, can according to the voice messaging of user, obtain this voice messaging for multiple user characteristics object, the predetermined characteristic that matches, thus more comprehensive user's characteristic information can be obtained, the feature identification carrying out user can be convenient to, as in national security field, can be used for the user's characteristic information obtaining suspect according to the recording from suspect, thus reduce suspect's scope; Can according to the voice characteristics information corresponding with voice messaging and/or text message, the predetermined characteristic matched with voice messaging is determined from multiple predetermined characteristic of each user characteristics object, and can based on the speech samples set of large data and the incompatible raising accuracy of word sample set; For each user characteristics object at least one user characteristics object, can in conjunction with current acquired, with the predetermined characteristic of other user characteristics match objects, from multiple predetermined characteristic of this user characteristics object, determine the predetermined characteristic of mating with voice messaging; By gathering a large amount of speech samples or word sample sets up the speech samples set corresponding with each predetermined characteristic or word sample set, can mate for voice messaging, obtaining more accurately comprehensively user's characteristic information.
It should be noted that the present invention can be implemented in the assembly of software and/or software restraint, such as, each device of the present invention can adopt special IC (ASIC) or any other similar hardware device to realize.In one embodiment, software program of the present invention can perform to realize step mentioned above or function by processor.Similarly, software program of the present invention (comprising relevant data structure) can be stored in computer readable recording medium storing program for performing, such as, and RAM storer, magnetic or CD-ROM driver or flexible plastic disc and similar devices.In addition, steps more of the present invention or function can adopt hardware to realize, such as, as coordinating with processor thus performing the circuit of each step or function.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when not deviating from spirit of the present invention or essential characteristic, the present invention can be realized in other specific forms.Therefore, no matter from which point, all should embodiment be regarded as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, and all changes be therefore intended in the implication of the equivalency by dropping on claim and scope are included in the present invention.Any Reference numeral in claim should be considered as the claim involved by limiting.In addition, obviously " comprising " one word do not get rid of other unit or step, odd number does not get rid of plural number.Multiple unit of stating in system claims or device also can be realized by software or hardware by a unit or device.First, second word such as grade is used for representing title, and does not represent any specific order.
Claims (16)
1., for obtaining a method for the user's characteristic information of user, wherein, the method comprises the following steps:
For each user characteristics object at least one user characteristics object, according to the voice messaging of described user, from multiple predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice messaging;
According to the predetermined characteristic matched with described voice messaging, determine the user's characteristic information of described user.
2. method according to claim 1, wherein, the user's characteristic information of described user comprises following at least one item:
The sex character information of-user;
The age characteristics information of-user;
The regional feature information of-user;
The character trait information of-user;
The job characteristics information of-user.
3. method according to claim 1 and 2, wherein, described for each user characteristics object at least one user characteristics object, according to the voice messaging of user, the step obtaining the predetermined characteristic matched with described voice messaging from multiple predetermined characteristic of this user characteristics object comprises:
According to described voice messaging, obtain the voice characteristics information corresponding with described voice messaging;
For each user characteristics object at least one user characteristics object described, according to described voice characteristics information, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice characteristics information.
4. method according to claim 1 and 2, wherein, described for each user characteristics object at least one user characteristics object, according to the voice messaging of user, the step obtaining the predetermined characteristic matched with described voice messaging from multiple predetermined characteristic of this user characteristics object comprises:
Speech recognition is carried out to described voice messaging, obtains and believe corresponding text message with described voice;
For each user characteristics object at least one user characteristics object described, according to described text message, and with each predetermined characteristic parallel expression sample set of this user characteristics object, obtain the predetermined characteristic matched with described text message.
5. method according to claim 1 and 2, wherein, described for each user characteristics object at least one user characteristics object, according to the voice messaging of user, the step obtaining the predetermined characteristic matched with described voice messaging from multiple predetermined characteristic of this user characteristics object comprises:
For each user characteristics object at least one user characteristics object, according to the voice messaging of user, and in conjunction with current acquired, with the predetermined characteristic of other user characteristics match objects, from multiple predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice messaging.
6. method according to any one of claim 1 to 5, wherein, the method also comprises:
Following operation is performed to each user characteristics object at least one user characteristics object described:
For each predetermined characteristic in multiple predetermined characteristic of this user characteristics object, according to the voice document corresponding with this predetermined characteristic, set up the speech samples set of this predetermined characteristic.
7. method according to any one of claim 1 to 6, wherein, the method also comprises:
Following operation is performed to each user characteristics object at least one user characteristics object described:
For each predetermined characteristic in multiple predetermined characteristic of this user characteristics object, according to the multiple words corresponding with this predetermined characteristic, set up the word sample set of this predetermined characteristic.
8. method according to claim 3, wherein, described voice characteristics information comprises:
The information that-the frequency of sound wave corresponding to voice is relevant;
The information that-the sonic wave amplitude corresponding to sound is relevant;
The information that-sound wave cycle corresponding to voice is relevant;
The information that-the waveform characteristic corresponding to voice is relevant.
9. for obtaining a device for the user's characteristic information of user, wherein, this device comprises with lower device:
Coalignment, for for each user characteristics object at least one user characteristics object, according to the voice messaging of described user, obtains the predetermined characteristic matched with described voice messaging from multiple predetermined characteristic of this user characteristics object;
Determining device, for the predetermined characteristic that basis and described voice messaging match, determines the user's characteristic information of described user.
10. device according to claim 9, wherein, the user's characteristic information of described user comprises following at least one item:
The sex character information of-user;
The age characteristics information of-user;
The regional feature information of-user;
The character trait information of-user;
The job characteristics information of-user.
11. devices according to claim 9 or 10, wherein, described coalignment comprises:
First obtaining means, for according to described voice messaging, obtains the voice characteristics information corresponding with described voice messaging;
First sub-coalignment, for for each user characteristics object at least one user characteristics object described, according to described voice characteristics information, and the speech samples set corresponding with each predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice characteristics information.
12. devices according to claim 9 or 10, wherein, described coalignment comprises:
Second obtaining means, for carrying out speech recognition to described voice messaging, obtaining and believing corresponding text message with described voice;
Second sub-coalignment, for for each user characteristics object at least one user characteristics object described, according to described text message, and with each predetermined characteristic parallel expression sample set of this user characteristics object, obtain the predetermined characteristic matched with described text message.
13. devices according to claim 9 or 10, wherein, described coalignment comprises:
3rd sub-coalignment, for each user characteristics object at least one user characteristics object, according to the voice messaging of user, and in conjunction with current acquired, with the predetermined characteristic of other user characteristics match objects, from multiple predetermined characteristic of this user characteristics object, obtain the predetermined characteristic matched with described voice messaging.
14. devices according to any one of claim 9 to 13, wherein, this device also comprises:
First apparatus for establishing, for performing following operation to each user characteristics object at least one user characteristics object described:
For each predetermined characteristic in multiple predetermined characteristic of this user characteristics object, according to the voice document corresponding with this predetermined characteristic, set up the speech samples set of this predetermined characteristic.
15. devices according to any one of claim 9 to 14, wherein, this device also comprises:
Second apparatus for establishing, for performing following operation to each user characteristics object at least one user characteristics object described:
For each predetermined characteristic in multiple predetermined characteristic of this user characteristics object, according to the multiple words corresponding with this predetermined characteristic, set up the word sample set of this predetermined characteristic.
16. devices according to claim 11, wherein, described voice characteristics information comprises:
The information that-the frequency of sound wave corresponding to voice is relevant;
The information that-the sonic wave amplitude corresponding to sound is relevant;
The information that-sound wave cycle corresponding to voice is relevant;
The information that-the waveform characteristic corresponding to voice is relevant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510376948.1A CN105096938A (en) | 2015-06-30 | 2015-06-30 | Method and device for obtaining user characteristic information of user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510376948.1A CN105096938A (en) | 2015-06-30 | 2015-06-30 | Method and device for obtaining user characteristic information of user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105096938A true CN105096938A (en) | 2015-11-25 |
Family
ID=54577224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510376948.1A Pending CN105096938A (en) | 2015-06-30 | 2015-06-30 | Method and device for obtaining user characteristic information of user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105096938A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228978A (en) * | 2016-08-04 | 2016-12-14 | 成都佳荣科技有限公司 | A kind of audio recognition method |
| CN106303955A (en) * | 2016-08-05 | 2017-01-04 | 百度在线网络技术（北京）有限公司 | For the method and apparatus that hotspot and POI are mated |
| CN106653057A (en) * | 2016-09-30 | 2017-05-10 | 北京智能管家科技有限公司 | Data processing method and apparatus |
| CN107632992A (en) * | 2016-07-18 | 2018-01-26 | 深圳市珍爱网信息技术有限公司 | A kind of blind date matching process and device based on speech recognition |
| CN107886955A (en) * | 2016-09-29 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | A kind of personal identification method, device and the equipment of voice conversation sample |
| CN108735222A (en) * | 2018-05-03 | 2018-11-02 | 广州国音科技有限公司 | A kind of vocal print identification method and system based on Application on Voiceprint Recognition |
| CN109448737A (en) * | 2018-08-30 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | Creation method, device, electronic equipment and the storage medium of virtual image |
| CN110379427A (en) * | 2019-06-19 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Resource information recommended method, device, terminal and medium based on speech recognition |
| CN113808575A (en) * | 2020-06-15 | 2021-12-17 | 珠海格力电器股份有限公司 | Voice interaction method, system, storage medium and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101668085A (en) * | 2009-09-16 | 2010-03-10 | 宇龙计算机通信科技(深圳)有限公司 | Method for regulating voice output of mobile terminal and mobile terminal |
| CN101741858A (en) * | 2009-12-22 | 2010-06-16 | 中兴通讯股份有限公司 | Method and system for accurately positioning media information audience |
| CN103353973A (en) * | 2013-06-17 | 2013-10-16 | 上海方付通商务服务有限公司 | Banking transaction authentication method based on video verification, and banking transaction authentication system based on video verification |
| CN104038788A (en) * | 2014-06-19 | 2014-09-10 | 中山大学深圳研究院 | Community social network system and content recommendation method |
| CN104239456A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | User characteristic data extraction method and user characteristic data extraction device |
| US20150039318A1 (en) * | 2013-08-02 | 2015-02-05 | Diotek Co., Ltd. | Apparatus and method for selecting control object through voice recognition |
| CN104700831A (en) * | 2013-12-05 | 2015-06-10 | 国际商业机器公司 | Analyzing method and device of voice features of audio files |
-
2015
- 2015-06-30 CN CN201510376948.1A patent/CN105096938A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101668085A (en) * | 2009-09-16 | 2010-03-10 | 宇龙计算机通信科技(深圳)有限公司 | Method for regulating voice output of mobile terminal and mobile terminal |
| CN101741858A (en) * | 2009-12-22 | 2010-06-16 | 中兴通讯股份有限公司 | Method and system for accurately positioning media information audience |
| CN103353973A (en) * | 2013-06-17 | 2013-10-16 | 上海方付通商务服务有限公司 | Banking transaction authentication method based on video verification, and banking transaction authentication system based on video verification |
| US20150039318A1 (en) * | 2013-08-02 | 2015-02-05 | Diotek Co., Ltd. | Apparatus and method for selecting control object through voice recognition |
| CN104700831A (en) * | 2013-12-05 | 2015-06-10 | 国际商业机器公司 | Analyzing method and device of voice features of audio files |
| CN104038788A (en) * | 2014-06-19 | 2014-09-10 | 中山大学深圳研究院 | Community social network system and content recommendation method |
| CN104239456A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | User characteristic data extraction method and user characteristic data extraction device |
Non-Patent Citations (2)
| Title |
|---|
| CHIH-CHANG CHEN ET AL.: "Gender-to-Age Hierarchical Recognition for Speech", 《2011 IEEE 54TH INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS)》 * |
| 南开大学文学院等: "《南开语言学刊 2011年 第2期 总第18期》", 31 December 2011, 商务印书馆 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107632992A (en) * | 2016-07-18 | 2018-01-26 | 深圳市珍爱网信息技术有限公司 | A kind of blind date matching process and device based on speech recognition |
| CN107632992B (en) * | 2016-07-18 | 2021-04-20 | 深圳市珍爱网信息技术有限公司 | Method and device for matching relatives based on voice recognition |
| CN106228978A (en) * | 2016-08-04 | 2016-12-14 | 成都佳荣科技有限公司 | A kind of audio recognition method |
| CN106303955A (en) * | 2016-08-05 | 2017-01-04 | 百度在线网络技术（北京）有限公司 | For the method and apparatus that hotspot and POI are mated |
| CN107886955A (en) * | 2016-09-29 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | A kind of personal identification method, device and the equipment of voice conversation sample |
| CN106653057A (en) * | 2016-09-30 | 2017-05-10 | 北京智能管家科技有限公司 | Data processing method and apparatus |
| CN108735222A (en) * | 2018-05-03 | 2018-11-02 | 广州国音科技有限公司 | A kind of vocal print identification method and system based on Application on Voiceprint Recognition |
| CN109448737A (en) * | 2018-08-30 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | Creation method, device, electronic equipment and the storage medium of virtual image |
| CN109448737B (en) * | 2018-08-30 | 2020-09-01 | 百度在线网络技术（北京）有限公司 | Method and device for creating virtual image, electronic equipment and storage medium |
| CN110379427A (en) * | 2019-06-19 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Resource information recommended method, device, terminal and medium based on speech recognition |
| WO2020253109A1 (en) * | 2019-06-19 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Resource information recommendation method and apparatus based on speech recognition, and terminal and medium |
| CN113808575A (en) * | 2020-06-15 | 2021-12-17 | 珠海格力电器股份有限公司 | Voice interaction method, system, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105096938A (en) | Method and device for obtaining user characteristic information of user | |
| US10403282B2 (en) | Method and apparatus for providing voice service | |
| US11238306B2 (en) | Generating vector representations of code capturing semantic similarity | |
| CN105023573B (en) | It is detected using speech syllable/vowel/phone boundary of auditory attention clue | |
| CN110459205B (en) | Speech recognition method and device, computer storage medium | |
| CN112380377B (en) | Audio recommendation method and device, electronic equipment and computer storage medium | |
| CN111444967A (en) | Training method, generation method, device, equipment and medium for generating confrontation network | |
| US20120221656A1 (en) | Tracking message topics in an interactive messaging environment | |
| CN109710931A (en) | A kind of class teaching content evaluation system and its method based on Intellectual Analysis Technology | |
| Rammo et al. | Detecting the speaker language using CNN deep learning algorithm | |
| CN105095415A (en) | Method and apparatus for confirming network emotion | |
| JP2005241997A (en) | Device, method, and program for speech analysis | |
| CN114333881B (en) | Audio transmission noise reduction method, device and medium based on environment self-adaptation | |
| Gumelar et al. | Forward feature selection for toxic speech classification using support vector machine and random forest | |
| Sultana et al. | A non-hierarchical approach of speech emotion recognition based on enhanced wavelet coefficients and K-means clustering | |
| CN104866091A (en) | Method and device for outputting audio-effect information in computer equipment | |
| CN114533084B (en) | Electroencephalogram feature extraction method and device, electronic equipment and storage medium | |
| CN110708619A (en) | Word vector training method and device for intelligent equipment | |
| CN115457436A (en) | Video heat prediction method and device | |
| CN111324710B (en) | Online investigation method and device based on virtual person and terminal equipment | |
| CN111950591B (en) | Model training method, interaction relation recognition device and electronic equipment | |
| Geroulanos et al. | Emotion Recognition in Music Using Deep Neural Networks | |
| Sridhar et al. | Performance Analysis of Two-Stage Iterative Ensemble Method over Random Oversampling Methods on Multiclass Imbalanced Datasets | |
| CN109344289B (en) | Method and apparatus for generating information | |
| CN114446316B (en) | Audio separation method, training method, device and equipment of audio separation model |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151125 |