Summary of the invention
The main purpose of the present invention is to provide a kind of intelligent assistant's management method, terminal and computer-readable storage mediumsMatter, it is intended to promote the practicability of intelligent assistant.
To achieve the above object, the present invention provides a kind of intelligent assistant's management method, which comprises
It obtains for waking up the password information of intelligent assistant, and judges whether the password information customized calls out with what is prestoredPassword information of waking up matching；
If the password information is matched with the customized wake-up password information prestored, start the intelligent assistant；
When receiving solicited message based on the intelligent assistant, language is carried out to the solicited message by the intelligent assistantJustice analysis, obtains semantic results；
The corresponding control instruction of the semantic results is generated by the intelligent assistant, and executes the control instruction.
Optionally, described to judge the step of whether password information matches with the customized wake-up password information prestored packetIt includes:
Password code, vocal print feature and speech parameter are extracted from the password information；
By the password code of extraction, vocal print feature and speech parameter, respectively and in the customized wake-up password information that prestoresPrestore customized password code, prestore vocal print feature and pre-stored voice parameter is compared；
If the password code extracted prestores that customized password code matches, the vocal print feature extracted is prestored with described with describedThe vocal print feature matching and speech parameter extracted is matched with the pre-stored voice parameter, then determine the password information and prestoreCustomized wake-up password information matching.
Optionally, described that semantic analysis is carried out to the solicited message by the intelligent assistant, obtain semantic resultsStep includes:
Word segmentation processing is successively carried out to the solicited message by the intelligent assistant and segments quantification treatment, described in acquisitionThe term vector of the participle of solicited message；
The term vector of the participle of the solicited message is analyzed by the intelligent assistant, obtains the solicited messageCorresponding semantic results.
Optionally, described that the term vector of the participle of the solicited message is analyzed by the intelligent assistant, it obtainsThe step of solicited message corresponding semantic results includes:
By the intelligent assistant calculate the term vector of the participle of the solicited message with prestore it is pre- in text databaseDeposit the Euclidean distance of term vector；
By the intelligent assistant, the Euclidean distance in prestoring text database based on calculating matches the solicited messageParticiple the corresponding content of text of term vector, the content of text that will match to is as semantic results.
Optionally, the Euclidean distance matching by the intelligent assistant, in prestoring text database based on calculatingThe step of term vector of the participle of the solicited message corresponding content of text includes:
By the intelligent assistant, from prestoring the term vector extracted in text database with the participle of the solicited messageMinimum euclidean distance it is corresponding prestore term vector, and based on prestoring in text database, prestore term vector and content of textMapping relations prestore the corresponding content of text of term vector for the minimum euclidean distance is corresponding, are determined as the solicited messageParticiple the corresponding content of text of term vector.
Optionally, described to include: by the corresponding control instruction step of intelligent assistant's generation semantic results
The corresponding request type of the semantic results is determined by the intelligent assistant, and raw according to determining request typeAt the corresponding control instruction of the semantic results.
Optionally, the vocal print feature includes tone color, amplitude and loudness, and the speech parameter includes intonation, word speed and languageGas.
Optionally, the solicited message includes text information, voice messaging and pictorial information.
In addition, to achieve the above object, the present invention also provides a kind of terminal, the terminal include: memory, processor andThe intelligent assistant's management program that is stored on the memory and can run on the processor, the intelligence assistant manage journeySequence realizes following steps when being executed by the processor:
It obtains for waking up the password information of intelligent assistant, and judges whether the password information customized calls out with what is prestoredPassword information of waking up matching；
If the password information is matched with the customized wake-up password information prestored, start the intelligent assistant；
When receiving solicited message based on the intelligent assistant, language is carried out to the solicited message by the intelligent assistantJustice analysis, obtains semantic results；
The corresponding control instruction of the semantic results is generated by the intelligent assistant, and executes the control instruction.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage mediumIntelligent assistant's management program is stored on storage medium, intelligence assistant's management program realizes following step when being executed by processorIt is rapid:
It obtains for waking up the password information of intelligent assistant, and judges whether the password information customized calls out with what is prestoredPassword information of waking up matching；
If the password information is matched with the customized wake-up password information prestored, start the intelligent assistant；
When receiving solicited message based on the intelligent assistant, language is carried out to the solicited message by the intelligent assistantJustice analysis, obtains semantic results；
The corresponding control instruction of the semantic results is generated by the intelligent assistant, and executes the control instruction.
The present invention provides a kind of intelligent assistant's management method, obtains for waking up the password information of intelligent assistant, and judgeWhether the password information matches with the customized wake-up password information prestored；If the password information customized is called out with what is prestoredPassword information of waking up matching then starts the intelligent assistant；When receiving solicited message based on the intelligent assistant, pass through the intelligenceEnergy assistant carries out semantic analysis to the solicited message, obtains semantic results；The semantic knot is generated by the intelligent assistantThe corresponding control instruction of fruit, and execute the control instruction.The present invention wakes up intelligent assistant by customized wake-up password information,Even if also intelligent assistant can be made to react rapidly in the occasion more than people, into operating mode, and to the request that intelligent assistant receivesInformation carries out semantic analysis, realizes and accurately identifies to solicited message, intelligent assistant can be made in the operational mode to userSolicited message carry out quickly and accurately feed back, to improve the sensitivity of intelligent assistant, improve the reality of intelligent assistantThe property used.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
In subsequent description, it is only using the suffix for indicating such as " module ", " component " or " unit " of elementBe conducive to explanation of the invention, itself there is no a specific meaning.Therefore, " module ", " component " or " unit " can mixGround uses.
Terminal can be implemented in a variety of manners.For example, terminal described in the present invention may include such as mobile phone, plateComputer, laptop, palm PC, personal digital assistant (Personal Digital Assistant, PDA), portableMedia player (Portable Media Player, PMP), navigation device, wearable device, Intelligent bracelet, pedometer etc. moveThe fixed terminals such as dynamic terminal, and number TV, desktop computer.
It will be illustrated by taking mobile terminal as an example in subsequent descriptions, it will be appreciated by those skilled in the art that in addition to specialExcept element for moving purpose, the construction of embodiment according to the present invention can also apply to the terminal of fixed type.
Referring to Fig. 1, a kind of hardware structural diagram of its mobile terminal of each embodiment to realize the present invention, the shiftingDynamic terminal 100 may include: RF (Radio Frequency, radio frequency) unit 101, Wi-Fi module 102, audio output unit103, A/V (audio/video) input unit 104, sensor 105, display unit 106, user input unit 107, interface unit108, the components such as memory 109, processor 110 and power supply 111.It will be understood by those skilled in the art that shown in Fig. 1Mobile terminal structure does not constitute the restriction to mobile terminal, and mobile terminal may include components more more or fewer than diagram,Perhaps certain components or different component layouts are combined.
It is specifically introduced below with reference to all parts of the Fig. 1 to mobile terminal:
Radio frequency unit 101 can be used for receiving and sending messages or communication process in, signal sends and receivees, specifically, by base stationDownlink information receive after, to processor 110 handle；In addition, the data of uplink are sent to base station.In general, radio frequency unit 101Including but not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier, duplexer etc..In addition, penetratingFrequency unit 101 can also be communicated with network and other equipment by wireless communication.Any communication can be used in above-mentioned wireless communicationStandard or agreement, including but not limited to GSM (Global System of Mobile communication, global system for mobile telecommunicationsSystem), GPRS (General Packet Radio Service, general packet radio service), CDMA2000 (CodeDivision Multiple Access 2000, CDMA 2000), WCDMA (Wideband Code DivisionMultiple Access, wideband code division multiple access), TD-SCDMA (Time Division-Synchronous CodeDivision Multiple Access, TD SDMA), FDD-LTE (Frequency DivisionDuplexing-Long Term Evolution, frequency division duplex long term evolution) and TDD-LTE (Time DivisionDuplexing-Long Term Evolution, time division duplex long term evolution) etc..
WiFi belongs to short range wireless transmission technology, and mobile terminal can help user to receive and dispatch electricity by WiFi module 102Sub- mail, browsing webpage and access streaming video etc., it provides wireless broadband internet access for user.Although Fig. 1 showsGo out WiFi module 102, but it is understood that, and it is not belonging to must be configured into for mobile terminal, it completely can be according to needIt to omit within the scope of not changing the essence of the invention.
Audio output unit 103 can be in call signal reception pattern, call mode, record mould in mobile terminal 100When under the isotypes such as formula, speech recognition mode, broadcast reception mode, by radio frequency unit 101 or WiFi module 102 it is received orThe audio data stored in memory 109 is converted into audio signal and exports to be sound.Moreover, audio output unit 103Audio output relevant to the specific function that mobile terminal 100 executes can also be provided (for example, call signal receives sound, disappearsBreath receives sound etc.).Audio output unit 103 may include loudspeaker, buzzer etc..
A/V input unit 104 is for receiving audio or video signal.A/V input unit 104 may include graphics processor(Graphics Processing Unit, GPU) 1041 and microphone 1042, graphics processor 1041 is in video acquisition modeOr the image data of the static images or video obtained in image capture mode by image capture apparatus (such as camera) carries outReason.Treated, and picture frame may be displayed on display unit 106.Through graphics processor 1041, treated that picture frame can be depositedStorage is sent in memory 109 (or other storage mediums) or via radio frequency unit 101 or WiFi module 102.MikeWind 1042 can connect in telephone calling model, logging mode, speech recognition mode etc. operational mode via microphone 1042Quiet down sound (audio data), and can be audio data by such acoustic processing.Audio that treated (voice) data canTo be converted to the format output that can be sent to mobile communication base station via radio frequency unit 101 in the case where telephone calling model.Microphone 1042 can be implemented various types of noises elimination (or inhibition) algorithms and send and receive sound to eliminate (or inhibition)The noise generated during frequency signal or interference.
Mobile terminal 100 further includes at least one sensor 105, such as optical sensor, motion sensor and other biographiesSensor.Specifically, optical sensor includes ambient light sensor and proximity sensor, wherein ambient light sensor can be according to environmentThe light and shade of light adjusts the brightness of display panel 1061, and proximity sensor can close when mobile terminal 100 is moved in one's earDisplay panel 1061 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (generalFor three axis) size of acceleration, it can detect that size and the direction of gravity when static, can be used to identify the application of mobile phone posture(such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, percussion) etc.；The fingerprint sensor that can also configure as mobile phone, pressure sensor, iris sensor, molecule sensor, gyroscope, barometer,The other sensors such as hygrometer, thermometer, infrared sensor, details are not described herein.
Display unit 106 is for showing information input by user or being supplied to the information of user.Display unit 106 can wrapDisplay panel 1061 is included, liquid crystal display (Liquid Crystal Display, LCD), Organic Light Emitting Diode can be usedForms such as (Organic Light-Emitting Diode, OLED) configure display panel 1061.
User input unit 107 can be used for receiving the number or character information of input, and generate the use with mobile terminalFamily setting and the related key signals input of function control.Specifically, user input unit 107 may include touch panel 1071 withAnd other input equipments 1072.Touch panel 1071, also referred to as touch screen collect the touch operation of user on it or nearby(for example user uses any suitable objects or attachment such as finger, stylus on touch panel 1071 or in touch panel 1071Neighbouring operation), and corresponding attachment device is driven according to preset formula.Touch panel 1071 may include touch detectionTwo parts of device and touch controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect touch operation bandThe signal come, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and by itIt is converted into contact coordinate, then gives processor 110, and order that processor 110 is sent can be received and executed.In addition, canTo realize touch panel 1071 using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic waves.In addition to touch panel1071, user input unit 107 can also include other input equipments 1072.Specifically, other input equipments 1072 can wrapIt includes but is not limited in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, operating stick etc.It is one or more, specifically herein without limitation.
Further, touch panel 1071 can cover display panel 1061, when touch panel 1071 detect on it orAfter neighbouring touch operation, processor 110 is sent to determine the type of touch event, is followed by subsequent processing device 110 according to touch thingThe type of part provides corresponding visual output on display panel 1061.Although in Fig. 1, touch panel 1071 and display panel1061 be the function that outputs and inputs of realizing mobile terminal as two independent components, but in certain embodiments, it canThe function that outputs and inputs of mobile terminal is realized so that touch panel 1071 and display panel 1061 is integrated, is not done herein specificallyIt limits.
Interface unit 108 be used as at least one external device (ED) connect with mobile terminal 100 can by interface.For example,External device (ED) may include wired or wireless headphone port, external power supply (or battery charger) port, wired or nothingLine data port, memory card port, the port for connecting the device with identification module, audio input/output (I/O) endMouth, video i/o port, ear port etc..Interface unit 108 can be used for receiving the input from external device (ED) (for example, numberIt is believed that breath, electric power etc.) and the input received is transferred to one or more elements in mobile terminal 100 or can be withFor transmitting data between mobile terminal 100 and external device (ED).
Memory 109 can be used for storing software program and various data.Memory 109 can mainly include storing program areaThe storage data area and, wherein storing program area can (such as the sound of application program needed for storage program area, at least one functionSound playing function, image player function etc.) etc.；Storage data area can store according to mobile phone use created data (such asAudio data, phone directory etc.) etc..In addition, memory 109 may include high-speed random access memory, it can also include non-easyThe property lost memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Processor 110 is the control centre of mobile terminal, utilizes each of various interfaces and the entire mobile terminal of connectionA part by running or execute the software program and/or module that are stored in memory 109, and calls and is stored in storageData in device 109 execute the various functions and processing data of mobile terminal, to carry out integral monitoring to mobile terminal.PlaceManaging device 110 may include one or more processing units；Preferably, processor 110 can integrate application processor and modulatedemodulate is mediatedManage device, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is mainProcessing wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 110.
Mobile terminal 100 can also include the power supply 111 (such as battery) powered to all parts, it is preferred that power supply 111Can be logically contiguous by power-supply management system and processor 110, to realize management charging by power-supply management system, putThe functions such as electricity and power managed.
Although Fig. 1 is not shown, mobile terminal 100 can also be including bluetooth module etc., and details are not described herein.
Based on above-mentioned terminal hardware structure, each embodiment of terminal of the present invention is proposed.
Fig. 1 is please referred to, in an embodiment of terminal of the present invention, which includes: memory 109, processor 110 and depositStore up the intelligent assistant's management program that can be run on the memory 109 and on the processor 110, the intelligence assistant pipeReason program performs the steps of when being executed by the processor 110
It obtains for waking up the password information of intelligent assistant, and judges whether the password information customized calls out with what is prestoredPassword information of waking up matching；
If the password information is matched with the customized wake-up password information prestored, start the intelligent assistant；
When receiving solicited message based on the intelligent assistant, language is carried out to the solicited message by the intelligent assistantJustice analysis, obtains semantic results；
The corresponding control instruction of the semantic results is generated by the intelligent assistant, and executes the control instruction.
Further, it is also performed the steps of when intelligent assistant's management program is executed by the processor 110
Password code, vocal print feature and speech parameter are extracted from the password information；
By the password code of extraction, vocal print feature and speech parameter, respectively and in the customized wake-up password information that prestoresPrestore customized password code, prestore vocal print feature and pre-stored voice parameter is compared；
If the password code extracted prestores that customized password code matches, the vocal print feature extracted is prestored with described with describedThe vocal print feature matching and speech parameter extracted is matched with the pre-stored voice parameter, then determine the password information and prestoreCustomized wake-up password information matching.
Further, it is also performed the steps of when intelligent assistant's management program is executed by the processor 110
Word segmentation processing is successively carried out to the solicited message by the intelligent assistant and segments quantification treatment, described in acquisitionThe term vector of the participle of solicited message；
The term vector of the participle of the solicited message is analyzed by the intelligent assistant, obtains the solicited messageCorresponding semantic results.
Further, it is also performed the steps of when intelligent assistant's management program is executed by the processor 110
By the intelligent assistant calculate the term vector of the participle of the solicited message with prestore it is pre- in text databaseDeposit the Euclidean distance of term vector；
By the intelligent assistant, the Euclidean distance in prestoring text database based on calculating matches the solicited messageParticiple the corresponding content of text of term vector, the content of text that will match to is as semantic results.
Further, it is also performed the steps of when intelligent assistant's management program is executed by the processor 110
By the intelligent assistant, from prestoring the term vector extracted in text database with the participle of the solicited messageMinimum euclidean distance it is corresponding prestore term vector, and based on prestoring in text database, prestore term vector and content of textMapping relations prestore the corresponding content of text of term vector for the minimum euclidean distance is corresponding, are determined as the solicited messageParticiple the corresponding content of text of term vector.
Further, it is also performed the steps of when intelligent assistant's management program is executed by the processor 110
The corresponding request type of the semantic results is determined by the intelligent assistant, and raw according to determining request typeAt the corresponding control instruction of the semantic results.
Embodiment to facilitate the understanding of the present invention, the communications network system that mobile terminal of the invention is based below intoRow description.
Referring to Fig. 2, Fig. 2 is a kind of communications network system architecture diagram provided in an embodiment of the present invention, the communication network systemSystem is the LTE system of universal mobile communications technology, which includes UE (User Equipment, the use of successively communication connectionFamily equipment) (the land Evolved UMTS Terrestrial Radio Access Network, evolved UMTS 201, E-UTRANGround wireless access network) 202, EPC (Evolved Packet Core, evolved packet-based core networks) 203 and operator IP operation204。
Specifically, UE201 can be above-mentioned terminal 100, and details are not described herein again.
E-UTRAN202 includes eNodeB2021 and other eNodeB2022 etc..Wherein, eNodeB2021 can be by returningJourney (backhaul) (such as X2 interface) is connect with other eNodeB2022, and eNodeB2021 is connected to EPC203,ENodeB2021 can provide the access of UE201 to EPC203.
EPC203 may include MME (Mobility Management Entity, mobility management entity) 2031, HSS(Home Subscriber Server, home subscriber server) 2032, other MME2033, SGW (Serving Gate Way,Gateway) 2034, PGW (PDN Gate Way, grouped data network gateway) 2035 and PCRF (Policy andCharging Rules Function, policy and rate functional entity) 2036 etc..Wherein, MME2031 be processing UE201 andThe control node of signaling, provides carrying and connection management between EPC203.HSS2032 is all to manage for providing some registersSuch as the function of home location register (not shown) etc, and preserves some related service features, data rates etc. and useThe dedicated information in family.All customer data can be sent by SGW2034, and PGW2035 can provide the IP of UE 201Address distribution and other functions, PCRF2036 are strategy and the charging control strategic decision-making of business data flow and IP bearing resourcePoint, it selects and provides available strategy and charging control decision with charge execution function unit (not shown) for strategy.
IP operation 204 may include internet, Intranet, IMS (IP Multimedia Subsystem, IP multimediaSystem) or other IP operations etc..
Although above-mentioned be described by taking LTE system as an example, those skilled in the art should know the present invention is not onlySuitable for LTE system, be readily applicable to other wireless communication systems, such as GSM, CDMA2000, WCDMA, TD-SCDMA withAnd the following new network system etc., herein without limitation.
Based on above-mentioned terminal hardware structure and communications network system, each reality of the intelligent assistant's management method of the present invention is proposedApply example.
The present invention provides a kind of intelligent assistant's management method.
It is the flow diagram of the intelligent assistant's management method first embodiment of the present invention referring to Fig. 3, Fig. 3.
In the present embodiment, intelligent assistant's management method is optional is applied in terminal, and the terminal is chosen as in Fig. 1The mobile terminal, terminal are equipped with intelligent assistant, and furthermore the terminal is provided with microphone, the microphone and the endThe processor communication at end connects, intelligence assistant's management method the following steps are included:
Step S10 obtains for waking up the password information of intelligent assistant, and judge the password information whether with prestoreCustomized wake-up password information matching；
In the present embodiment, in order to promote the success rate for waking up intelligent assistant, user can the intelligent assistant of customized wake-upPassword.Specifically, for user in the intelligent assistant of using terminal for the first time, the default instruction that manufacturer's setting can be used wakes up intelligenceCan assistant, then setting such as is recorded for waking up the customized password information of intelligent assistant in the setting options of intelligent assistantEnter the voice of " open sesame ", terminal receives the voice of " open sesame " of user's typing, by " open sesame " four word conductsPassword code, while extracting vocal print feature and speech parameter from the voice of " open sesame ", the vocal print feature include tone color,Amplitude and loudness, for the speech parameter for assisting in identifying, which includes intonation, word speed and the tone, and terminal is by above-mentioned mouthPassword, vocal print feature and speech parameter is enabled to save as the customized wake-up password information of user.Later, when user needsWhen waking up intelligent assistant, so that it may password information is barked out against terminal, the microphone of terminal acquires the password information that user barks out,Then judge whether the password information of acquisition matches with the customized wake-up password information prestored.In the present embodiment, described to sentenceThe step of whether password information of breaking matches with the customized wake-up password information prestored may include:
Step A1 extracts password code, vocal print feature and speech parameter from the password information；
Step A2, by the password code of extraction, vocal print feature and speech parameter, respectively with the customized wake-up password that prestoresPrestoring customized password code, prestoring vocal print feature and pre-stored voice parameter is compared in information；
Step A3, if the password code extracted with it is described prestore customized password code match, the vocal print feature extracted andThe speech parameter for prestoring vocal print feature matching and extracting is matched with the pre-stored voice parameter, then determines the password informationIt is matched with the customized wake-up password information prestored.
That is, the password information that terminal acquires microphone identifies, with therefrom extract password code, vocal print feature andSpeech parameter is believed with the customized wake-up password prestored respectively then by the password code of extraction, vocal print feature and speech parameterPrestoring customized password code, prestoring vocal print feature and pre-stored voice parameter is compared in breath, if the password extracted is closeCode with prestore customized password code match, the vocal print feature extracted with prestore vocal print feature match and the speech parameter that extracts andThe matching of pre-stored voice parameter then determines that the password information of microphone acquisition is matched with the customized wake-up password information prestored, leads toAforesaid way is crossed, the recognition accuracy to password information will be greatly promoted.
If it is determined that the password information of microphone acquisition is matched with the customized wake-up password information prestored, then follow the stepsS20 starts the intelligent assistant.Since the recognition accuracy to password information gets a promotion, the success rate of intelligent assistant is waken upAlso it will get a promotion, and provide personalized service for user, and enhance interest.
Step S30 when receiving solicited message based on the intelligent assistant, believes the request by the intelligent assistantBreath carries out semantic analysis, obtains semantic results；
Wherein, may include: referring to Fig. 4, the step S30
Step S31 successively carries out word segmentation processing and participle quantification treatment to the solicited message by the intelligent assistant,Obtain the term vector of the participle of the solicited message；
Step S32 analyzes the term vector of the participle of the solicited message by the intelligent assistant, described in acquisitionThe corresponding semantic results of solicited message.
After terminal starts intelligent assistant, user can in intelligent assistant trigger request information, for example input voice, pass throughKeyboard inputs text, uploading pictures etc., and intelligent assistant receives the solicited message of user's triggering, carries out semantic point to the solicited messageAnalysis.In the present embodiment, if solicited message is the text inputted by keyboard, directly progress semantic analysis；If requestInformation is voice, then identifies first to voice, converts speech into original text；If solicited message is picture, rightPicture formats, and is original text by the Content Transformation in picture, and then to the converted initial text for handling and obtainingThis progress semantic analysis.In the present embodiment, intelligent assistant to solicited message carry out semantic analysis, need first to solicited message according intoRow word segmentation processing obtains the participle of solicited message, then carries out quantification treatment to the participle of solicited message.Solicited message is dividedWord carries out quantification treatment can be realized by default neural network language model, that is, be input to the participle of solicited message defaultIn neural network language model, quantification treatment is carried out to the participle of solicited message by presetting neural network language model, is obtainedThe term vector of the participle of the solicited message of default neural network language model output.It in the present embodiment, can be in advance to nerveNetspeak model is trained, and specifically, is chosen relevant training sample and is input in neural network language model and instructedPractice, the parameter of the neural network language model is updated by iterative algorithm (such as Baum-we l ch algorithm), and rightThe training sample of selection is iterated training, constantly loop iteration, until reaching previously positioned the number of iterations or having receivedIt holds back, at this point, the optimal model parameters of the neural network language model can be obtained, the instruction of neural network language model can be completedPractice.And then the term vector of the participle of solicited message is analyzed, obtain semantic results.Solicited message is successively by participleAfter the participle quantification treatment of processing and neural network language model, the accurate of semantic analysis to solicited message will be greatly promotedProperty.
Step S40 generates the corresponding control instruction of the semantic results by the intelligent assistant, and executes the controlInstruction.In the present embodiment, the step of control instruction corresponding by intelligent assistant's generation semantic results, canTo include:
Step B determines the corresponding request type of the semantic results by the intelligent assistant, and according to determining requestType generates the corresponding control instruction of the semantic results.
That is, after voice assistant is to solicited message progress semantic analysis acquisition semantic results, it is first determined the semantic resultsCorresponding request type, request type include calling the services of other applications, intelligent recommendation (including service for life, newsInformation recommendation, video recommendations, music are recommended etc.), intelligent reminding (remind, the birthday by stroke reminding including flight or high-speed rail, weatherPrompting, sport health etc.), search service and translation service etc..For example, user has input " I wants to eat Guangdong dishes " in intelligent assistantVoice, after intelligent assistant carries out semantic analysis to the voice, the semantic results of " recommend Guangdong dishes shop " are obtained, so that it is determined that languageThe corresponding request type of adopted result is the service for life in intelligent recommendation.Later, intelligent assistant is raw according to determining request typeAt the corresponding control instruction of semantic results, and execute the control instruction.
The present embodiment provides a kind of intelligent assistant's management methods, obtain for waking up the password information of intelligent assistant, and sentenceWhether the password information of breaking matches with the customized wake-up password information prestored；If the password information with prestore it is customizedPassword information matching is waken up, then starts the intelligent assistant；When receiving solicited message based on the intelligent assistant, by describedIntelligent assistant carries out semantic analysis to the solicited message, obtains semantic results；The semanteme is generated by the intelligent assistantAs a result corresponding control instruction, and execute the control instruction.The present embodiment wakes up intelligence by customized wake-up password informationAssistant, even if the occasion more than the people, also can be such that intelligent assistant reacts rapidly, into operating mode, and receive to intelligent assistantSolicited message carry out semantic analysis, realize and solicited message accurately identified, intelligent assistant can be made in the operational modeThe solicited message of user quickly accurately feed back, to improve the sensitivity of intelligent assistant, intelligence is improved and helpsThe practicability of hand.
Further, the second embodiment of the intelligent assistant's management method of the present invention is proposed based on first embodiment.
The difference of the first embodiment of the 3rd embodiment of intelligent assistant's management method and intelligent assistant's management method is,May include: referring to Fig. 4, the step S32
Step S320 calculates the term vector of the participle of the solicited message by the intelligent assistant and prestores text dataThe Euclidean distance for prestoring term vector in library；
Step S321, by the intelligent assistant, the Euclidean distance in prestoring text database based on calculating matches instituteThe corresponding content of text of term vector of the participle of solicited message is stated, the content of text that will match to is as semantic results.
Wherein, the step S320 may include:
Step C is extracted and the participle of the solicited message by the intelligent assistant from prestoring in text databaseThe minimum euclidean distance of term vector is corresponding to prestore term vector, and based on prestoring in text database, prestores term vector and textThe mapping relations of content prestore the corresponding content of text of term vector for the minimum euclidean distance is corresponding, are determined as described askSeek the corresponding content of text of the term vector of the participle of information.
In the present embodiment, intelligent assistant analyzes the term vector of the participle of solicited message, is analysis request informationParticiple term vector and prestore the similarity prestored between term vector in text database, with from prestoring in text databaseIt matches and the term vector similarity of the participle of solicited message is maximum prestores term vector, thus based on text database is prestoredIn, the mapping relations of term vector and content of text are prestored, are extracted maximum with the term vector similarity of the participle of solicited messageContent of text corresponding to term vector is prestored, the corresponding content of text of the term vector of the participle as solicited message is requestedThe semantic results of information.
Specifically, similarity analysis can be realized in such a way that Euclidean distance is measured, and the smaller the two of Euclidean distance gets over phaseSeemingly.Therefore, intelligent assistant need first by the term vector of the participle of computation requests information with prestore prestoring in text databaseThe Euclidean distance of term vector, the formula for calculating Euclidean distance are as follows:
Wherein, D indicates Euclidean distance, x1kIndicate 1k coordinate of the term vector of the participle of solicited message, x2kDescribed in expression2k coordinate of the term vector in presetting database.
In the Euclidean distance of the term vector and the term vector prestored in text database of the participle that solicited message is calculatedLater, each Euclidean distance being calculated is ranked up, is then extracted in prestoring text database and solicited messageParticiple term vector minimum euclidean distance it is corresponding prestore term vector, the minimum euclidean distance is corresponding to prestore term vector justBe and the term vector similarity of the participle of solicited message is maximum prestores term vector, that is, with the word of the participle of solicited message toMeasure immediate term vector.Later, based on prestoring in text database, the mapping relations of term vector and content of text are prestored, it willMinimum euclidean distance is corresponding to prestore the corresponding content of text of term vector, is determined as the term vector pair of the participle of the solicited messageThe content of text answered obtains the semantic results of solicited message.
In the present embodiment, intelligent assistant passes through the term vector of the participle of computation requests information and prestores in text databaseThe Euclidean distance for prestoring term vector, thus Euclidean distance matching request information in prestoring text database based on calculatingThe corresponding content of text of the term vector of participle, the content of text that will match to is as semantic results.Due to the participle of solicited messageTerm vector be to obtain after processing by neural network language model, ensure that the standard of the term vector of the participle of solicited messageExactness, then by the term vector of the participle of computation requests information with prestore in text database prestore term vector it is European away fromFrom, based on Euclidean distance from prestore in text database for solicited message participle term vector matched text content, askedThe semantic results for seeking information further improve the accuracy of semantic analysis.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium.
Intelligent assistant's management program, intelligence assistant's management program are stored on computer readable storage medium of the present inventionFollowing steps are realized when being executed by processor:
It obtains for waking up the password information of intelligent assistant, and judges whether the password information customized calls out with what is prestoredPassword information of waking up matching；
If the password information is matched with the customized wake-up password information prestored, start the intelligent assistant；
When receiving solicited message based on the intelligent assistant, language is carried out to the solicited message by the intelligent assistantJustice analysis, obtains semantic results；
The corresponding control instruction of the semantic results is generated by the intelligent assistant, and executes the control instruction.
Wherein, the intelligent assistant's management program run on the processor, which is performed realized method, can refer to thisThe each embodiment of intelligent assistant's management method is invented, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-rowHis property includes, so that the process, method, article or the system that include a series of elements not only include those elements, andAnd further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsicElement.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to doThere is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment sideMethod can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many casesThe former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior artThe part contributed out can be embodied in the form of software products, which is stored in a storage mediumIn (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, computer, clothesBusiness device, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hairEquivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skillsArt field, is included within the scope of the present invention.