CN110288993A - A kind of individualized intelligent voice interactive method and device based on container technique - Google Patents

A kind of individualized intelligent voice interactive method and device based on container technique Download PDF

Info

Publication number
CN110288993A
CN110288993A CN201910560474.4A CN201910560474A CN110288993A CN 110288993 A CN110288993 A CN 110288993A CN 201910560474 A CN201910560474 A CN 201910560474A CN 110288993 A CN110288993 A CN 110288993A
Authority
CN
China
Prior art keywords
container
user
address
api interface
module
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
Application number
CN201910560474.4A
Other languages
Chinese (zh)
Inventor
陈开冉
黎展
王木
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Trace Technology Co Ltd
Original Assignee
Guangzhou Trace Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Trace Technology Co Ltd filed Critical Guangzhou Trace Technology Co Ltd
Priority to CN201910560474.4A priority Critical patent/CN110288993A/en
Publication of CN110288993A publication Critical patent/CN110288993A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • G06F2009/45562Creating, deleting, cloning virtual machine instances
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/226Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
    • G10L2015/227Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of the speaker; Human-factor methodology

Abstract

The invention discloses a kind of individualized intelligent voice interactive method based on container technique, by the user information and the request of api interface IP address that obtain user, it is requested according to api interface IP address, whether there is the corresponding example of user to be currently running in detection container cluster, the api interface IP address of example is back to user if having, if the user information without if according to user, start the corresponding example of user in container cluster, and the api interface IP address of the corresponding example of user is back to user, wherein, each container instance in container cluster is at runtime, the user information of user is corresponded to according to each container instance, the corresponding participle dictionary configuration of real-time loading and algorithm model, using embodiment provided by the invention, it is that user distributes different container instances according to user information, and arrange in pairs or groups different participle dictionary configuration and Algorithm model can do personalized effect optimization processing to user, and the optimization between different users will not influence each other.

Description

A kind of individualized intelligent voice interactive method and device based on container technique
Technical field
The present invention relates to technical field of information processing more particularly to a kind of individualized intelligent voice friendships based on container technique Mutual method and device.
Background technique
Intelligent speech interactive system is then made by way of the sound of user is converted to text by ASR speech recognition Semanteme is understood with NLP natural language processing technique, obtains most suitable answer, the interaction with user is reached with this.Existing skill Some handle the dialogue of different user using the same language model to art, some use different language models, but use same One segmenter segments dialog text.
Existing technology has the disadvantage in that
1, firstly, personalized processing can not be done for different users using the same language model, language can not be optimized Say the effect of interaction.
It 2, then can not be to some special screnes secondly, if using different language models, but because segmenter is identical Word correctly segmented.Such as: it " is built inside " we are building trades, do not need the data of your offers " the words Build industry " do not need to segment, still " we are building trades, what data you can provide? " " building inside the words It is " building " and " industry " that industry ", which just needs to segment, to do different answers for different industries.
3, in addition, the language model after load can consume very big server performance (especially memory), do not have in the user This part server resource is wasted when use.
Summary of the invention
It, can be with the purpose of the embodiment of the present invention is that provide a kind of individualized intelligent voice interactive method based on container technique Personalized effect optimization processing is done to user, and the optimization between different users will not influence each other.
To achieve the above object, the embodiment of the invention provides a kind of individualized intelligent interactive voice based on container technique Method, comprising the following steps:
Obtain the user information and the request of api interface IP address of user;
It is requested according to the api interface IP address, whether there is the corresponding example of the user transporting in detection container cluster Row;
If so, the api interface IP address of the example is then back to the user;
If nothing, according to the user information of the user, start the corresponding example of the user in the container cluster, And the api interface IP address of the corresponding example of the user is back to the user;
Wherein, each container instance in the container cluster at runtime, corresponds to user's according to each container instance User information, the corresponding participle dictionary configuration of real-time loading and algorithm model.
Further, the individualized intelligent voice interactive method based on container technique, further includes:
Timing acquisition be currently running in the first container example the first heartbeat request;Wherein, first heartbeat request Load information, the first user information including the first container example;
When the load of the first container example is more than container threshold value, a phase is started according to the first container example Same second container example, for the normal use of first user;
When the first container example non-loaded time be more than preset threshold value when, or be more than the preset threshold value when Between Lungs from Non-Heart-Beating request when, the first container example is deleted, with free system resources.
The embodiment of the invention also provides a kind of individualized intelligent voice interaction device based on container technique, comprising: letter Breath obtains module, Query By Example module, first processing module and Second processing module;
The data obtaining module, for obtaining the user information and the request of api interface IP address of user;
Whether the Query By Example module has described for being requested according to the api interface IP address in detection container cluster The corresponding example of user is currently running;
The first processing module, for thering is the corresponding example of the user transporting in detecting the container cluster When row, the api interface IP address of the example is back to the user;
The Second processing module, for being transported in detecting the container cluster without the corresponding example of the user When row, according to the user information of the user, start the corresponding example of the user in the container cluster, and by the use The api interface IP address of the corresponding example in family is back to the user;
Wherein, each container instance in the container cluster at runtime, corresponds to user's according to each container instance User information, the corresponding participle dictionary configuration of real-time loading and algorithm model.
Further, the individualized intelligent voice interaction device based on container technique, further includes: heartbeat request obtains Module, addition container instance module and deletion container instance module;
The heartbeat request obtains module, for timing acquisition be currently running in the first heartbeat of the first container example ask It asks;Wherein, first heartbeat request includes the load information of the first container example, the first user information;
The addition container instance module, for when the load of the first container example be more than container threshold value when, according to The first container example starts an identical second container example, for the normal use of first user;
The deletion container instance module, for being more than preset threshold value when the first container example non-loaded time When, or be more than the preset threshold time Lungs from Non-Heart-Beating request when, the first container example is deleted, with free system resources.
As the preferred embodiment of the present invention, the present invention also provides a kind of individualized intelligent voice based on container technique Interactive device in the memory and is configured as being executed by the processor including processor, memory and storage Computer program, the processor are realized described in foregoing invention embodiment when executing the computer program based on container technique Individualized intelligent voice interactive method.
Another embodiment of the present invention provides a kind of storage medium, the computer readable storage medium includes the meter of storage Calculation machine program, wherein control equipment where the computer readable storage medium in computer program operation and execute State the individualized intelligent voice interactive method described in inventive embodiments based on container technique.
Compared with prior art, it has the following beneficial effects:
Individualized intelligent voice interactive method provided in an embodiment of the present invention based on container technique, by obtaining user's Whether user information and the request of api interface IP address, request according to api interface IP address, have user corresponding in detection container cluster Example is currently running, if so, the api interface IP address of example is then back to user, if nothing, and according to the user information of user, Start the corresponding example of user in container cluster, and the api interface IP address of the corresponding example of user be back to user, In, each container instance in container cluster corresponds to the user information of user according to each container instance at runtime, adds in real time Corresponding participle dictionary configuration and algorithm model are carried, is user's distribution according to user information using embodiment provided by the invention Different container instances, and the participle dictionary configuration for arranging in pairs or groups different and algorithm model, it is excellent can to do personalized effect to user Change processing, and the optimization between different users will not influence each other.
Detailed description of the invention
Fig. 1 is the stream of one embodiment of the individualized intelligent voice interactive method provided by the invention based on container technique Journey schematic diagram;
Fig. 2 is the work of one embodiment of the individualized intelligent voice interactive method provided by the invention based on container technique Make schematic illustration;
Fig. 3 is the knot of one embodiment of the individualized intelligent voice interaction device provided by the invention based on container technique Structure schematic diagram.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall within the protection scope of the present invention.
It is a reality of the individualized intelligent voice interactive method provided by the invention based on container technique referring to Fig. 1, Fig. 1 Apply the flow diagram of example;The embodiment of the present invention provides a kind of individualized intelligent voice interactive method based on container technique, packet Include step S1-S4;
S1 obtains the user information and the request of api interface IP address of user.
In the present embodiment, user information has all been stored in advance in the database of intelligent voice system, so in user To intelligent voice system initiate wake up when, can by database obtain user user information so that follow-up work it is normal into Row.If user uses this intelligent voice system for the first time, need first to be registered, and select one's own individual character in system Change setting, when so as to use this intelligent voice system next time, exchange method provided in an embodiment of the present invention can be used.
S2 is requested according to the api interface IP address, whether is having the corresponding example of the user in detection container cluster Operation.
S3, if so, the api interface IP address of the example is then back to the user.
S4, according to the user information of the user, starts the corresponding reality of the user if nothing in the container cluster Example, and the api interface IP address of the corresponding example of the user is back to the user.
By whether there is the corresponding example of user to be currently running in detection container cluster, the api interface of example if having Location is back to user, so that user can directly pass through api interface requests container instance, improves intelligent voice system work effect Rate.
Preferably, when detecting that the corresponding example of container cluster no user is currently running, according to the user information of user It in the database of intelligent voice system, obtains the user and corresponds to container instance information, then hold according to the user is corresponding Device example information opens cell therefor example, and returns to the api interface IP address of example, not only provides to different users exclusive Customizing mode, moreover it is possible to do not influence the normal work of other container instances, further improve the work of intelligent voice system Make efficiency.
In the present embodiment, each container instance in the container cluster at runtime, according to each container instance pair Using the user information at family, the corresponding participle dictionary configuration of real-time loading and algorithm model.
As the preferred embodiment of the present invention, the user knowledge of all users is contained in the database of intelligent voice system Library configures corresponding user knowledge base when getting user information, to realize intelligence and personalized interactive experience.
Further, there is optimal effect to make user when in use, invention also uses NLP algorithm process users Knowledge base content, then generate corresponding participle dictionary and algorithm model for different knowledge base.It, will in interactive process Text after speech recognition is passed in algorithm model, and algorithm model can return to corresponding result.Such as: there is " valence inside knowledge base The problem of lattice " correlation, user said " how much? " later, algorithm model can return to " being matched to price problem " similar knot Fruit.Wherein, participle dictionary corresponds to some special vocabulary requirements, such as: " hardware industry " needs inside certain words arts " hardware " and " industry " two words are segmented into, do not need then to separate inside certain words arts.
As the preferred embodiment of the present invention, the individualized intelligent interactive voice side provided by the invention based on container technique Method further includes step S5-S7;
S5, timing acquisition be currently running in the first container example the first heartbeat request.
In the present embodiment, first heartbeat request includes the load information of the first container example, the first user Information.
The heartbeat request that timing receipt container instance is sent is provided, it is convenient that container instance is managed, wherein administrator Member can be set by timed sending time of the backstage to the heartbeat request of container instance, and optimal is 60 seconds.
S6, when the load of the first container example is more than container threshold value, according to the first container example starting one A identical second container example, for the normal use of first user.
By the way that normally making for user can not only be made to load the identical example of example addition for being more than container threshold value With, do not return also influence user experience.
S7 when the first container example non-loaded time being more than preset threshold value, or is more than the preset threshold When being worth the request of time Lungs from Non-Heart-Beating, the first container example is deleted, with free system resources.
In the present embodiment, the preset threshold value can be configured from the background by administrative staff, and optimal is 30 points Clock.And the example by deleting the request of non-loaded and Lungs from Non-Heart-Beating, can reduce the burden of system, further improves intelligence The working efficiency of energy voice system.
Fig. 2 is referred to, Fig. 2 is one of the individualized intelligent voice interactive method provided by the invention based on container technique The operation principle schematic diagram of embodiment, the personalized intelligence based on container technique that embodiment provides in order to better illustrate the present invention Can voice interactive method principle, specific steps to realize the present invention below:
Firstly, operation system can request the container instance api interface IP address of user, control centre's meeting to container control centre It checks currently whether there is the example being currently running, interface IP address is directly returned if having, if should without the starting in container cluster The container instance of user and the interface IP address for returning to example.Operation system can pass through api interface direct request container later Example also avoids the single-point performance bottleneck of control centre without passing through control centre in this way.
In addition, each running container instance can regularly send heartbeat request to control centre, and it is attached to oneself Load information.If control centre detects that the container instance load of some user is more than threshold value, a phase can be restarted Same container instance, the request of such operation system can load between multiple containers example.If control centre detects some It is more than threshold value either for a long time without heartbeat message that the container instance of user, which does not have the loaded time, then will be deleted these and do not live The example of jump, to discharge the resource of system.
Preferably, the participle dictionary configuration of technical solution of the present invention a personalization since each container instance can load And algorithm model, it is possible to personalized effect optimization be done to different users and handled, and the optimization between different users It will not reciprocal influence.In addition, due to can intelligence dynamic control container instance load and release, this programme can be to being System resource does maximized utilization, and can be to the resource of user using fine control is done, for ease of use kimonos Business cost is all significantly improved.
Individualized intelligent voice interactive method provided in an embodiment of the present invention based on container technique, by obtaining user's Whether user information and the request of api interface IP address, request according to api interface IP address, have user corresponding in detection container cluster Example is currently running, if so, the api interface IP address of example is then back to user, if nothing, and according to the user information of user, Start the corresponding example of user in container cluster, and the api interface IP address of the corresponding example of user be back to user, In, each container instance in container cluster corresponds to the user information of user according to each container instance at runtime, adds in real time Corresponding participle dictionary configuration and algorithm model are carried, is user's distribution according to user information using embodiment provided by the invention Different container instances, and the participle dictionary configuration for arranging in pairs or groups different and algorithm model, it is excellent can to do personalized effect to user Change processing, and the optimization between different users will not influence each other;In addition, since dynamic that can be intelligent controls container instance Load and release, this programme can also do maximized utilization to system resource, and can the resource use to user do Fine control is all significantly improved for ease of use and cost of serving.
As preferred embodiment provided by the invention, Fig. 2 is referred to, Fig. 2 is provided by the invention based on container technique The structural schematic diagram of one embodiment of individualized intelligent voice interaction device, comprising: data obtaining module, Query By Example mould Block, first processing module and Second processing module;
The data obtaining module, for obtaining the user information and the request of api interface IP address of user;The Query By Example Whether module has the corresponding example of the user transporting for being requested according to the api interface IP address in detection container cluster Row;The first processing module, when for thering is the corresponding example of the user to be currently running in detecting the container cluster, The api interface IP address of the example is back to the user;The Second processing module, for detecting the sets of containers When being currently running in group without the corresponding example of the user, according to the user information of the user, opened in the container cluster The corresponding example of the user is moved, and the api interface IP address of the corresponding example of the user is back to the user;Wherein, Each container instance in the container cluster corresponds to the user information of user according to each container instance, in real time at runtime Load corresponding participle dictionary configuration and algorithm model.
In the present embodiment, the individualized intelligent voice interaction device based on container technique, further includes: heartbeat request It obtains module, addition container instance module and deletes container instance module;
The heartbeat request obtains module, for timing acquisition be currently running in the first heartbeat of the first container example ask It asks;Wherein, first heartbeat request includes the load information of the first container example, the first user information;The addition Container instance module, for when the load of the first container example be more than container threshold value when, according to the first container example Start an identical second container example, for the normal use of first user;The deletion container instance module, is used for It when the first container example non-loaded time being more than preset threshold value, or is more than the preset threshold time Lungs from Non-Heart-Beating When request, the first container example is deleted, with free system resources.
Therefore a kind of individualized intelligent voice interaction device based on container technique provided in an embodiment of the present invention, By data obtaining module obtain user user information and api interface IP address request, then by Query By Example module according to Whether the api interface IP address is requested, have the corresponding example of the user to be currently running in detection container cluster, then passes through first When processing module has the corresponding example of the user to be currently running in detecting the container cluster, by the api of the example Interface IP address is back to the user, finally by Second processing module without the user couple in detecting the container cluster When the example answered is currently running, according to the user information of the user, it is corresponding in the container cluster to start the user Example, and the api interface IP address of the corresponding example of the user is back to the user, wherein in the container cluster Each container instance at runtime, the user information of user, the corresponding participle word of real-time loading is corresponded to according to each container instance Library configuration and algorithm model can do personalized effect optimization processing to user, and the optimization between different users will not It influences each other;In addition, due to the load and release of dynamic control container instance that can be intelligent, this programme can also provide system Maximized utilization is done in source, and can to the resource of user using doing fine control, for ease of use and service at This is all significantly improved.
The individualized intelligent interactive voice equipment based on container technique that the embodiment of the invention also provides a kind of.The equipment packet Include: processor, memory and storage are in the memory and the computer program that can run on the processor.It is described Processor realizes that above-mentioned each individualized intelligent voice interactive method based on container technique is real when executing the computer program Apply the step in example, such as step S1 to S4 shown in FIG. 1.
Alleged processor can be central processing unit (Central Processing Unit, CPU), can also be it His general processor, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field- Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic, Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor Deng the processor is the control centre of the individualized intelligent interactive voice equipment based on container technique, is connect using various Mouthful and the entire individualized intelligent interactive voice equipment based on container technique of connection various pieces.
The memory can be used for storing the computer program and/or module, and the processor is by operation or executes Computer program in the memory and/or module are stored, and calls the data being stored in memory, described in realization The various functions of individualized intelligent interactive voice equipment based on container technique.The memory can mainly include storing program area The storage data area and, wherein storing program area can (such as the sound of application program needed for storage program area, at least one function Sound playing function, image player function etc.) etc.;Storage data area can store according to mobile phone use created data (such as Audio data, phone directory etc.) etc..In addition, memory may include high-speed random access memory, it can also include non-volatile Memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other Volatile solid-state part.
Wherein, if module/unit of the individualized intelligent interactive voice integration of equipments based on container technique is with soft The form of part functional unit realizes and when sold or used as an independent product, can store and computer-readable deposits at one In storage media.Based on this understanding, the present invention realizes all or part of the process in above-described embodiment method, can also pass through Computer program is completed to instruct relevant hardware, and the computer program can be stored in a computer readable storage medium In, the computer program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the calculating Machine program includes computer program code, and the computer program code can be source code form, object identification code form, can hold Style of writing part or certain intermediate forms etc..The computer-readable medium may include: that can carry the computer program code Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunications letter Number and software distribution medium etc..
It should be noted that the apparatus embodiments described above are merely exemplary, wherein described be used as separation unit The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual It needs that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.In addition, device provided by the invention In embodiment attached drawing, the connection relationship between module indicate between them have communication connection, specifically can be implemented as one or A plurality of communication bus or signal wire.Those of ordinary skill in the art are without creative efforts, it can understand And implement.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as Protection scope of the present invention.

Claims (6)

1. a kind of individualized intelligent voice interactive method based on container technique, which comprises the following steps:
Obtain the user information and the request of api interface IP address of user;
It is requested according to the api interface IP address, whether there is the corresponding example of the user to be currently running in detection container cluster;
If so, the api interface IP address of the example is then back to the user;
If nothing, according to the user information of the user, start the corresponding example of the user in the container cluster, and will The api interface IP address of the corresponding example of the user is back to the user;
Wherein, each container instance in the container cluster at runtime, the user of user is corresponded to according to each container instance Information, the corresponding participle dictionary configuration of real-time loading and algorithm model.
2. the individualized intelligent voice interactive method based on container technique as described in claim 1, which is characterized in that also wrap It includes:
Timing acquisition be currently running in the first container example the first heartbeat request;Wherein, first heartbeat request includes The load information of the first container example, the first user information;
It is identical according to the first container example starting one when the load of the first container example is more than container threshold value Second container example, for the normal use of first user;
When the first container example non-loaded time be more than preset threshold value when, or be more than the preset threshold time without When heartbeat request, the first container example is deleted, with free system resources.
3. a kind of individualized intelligent voice interaction device based on container technique characterized by comprising data obtaining module, Query By Example module, first processing module and Second processing module;
The data obtaining module, for obtaining the user information and the request of api interface IP address of user;
Whether the Query By Example module has the user in detection container cluster for requesting according to the api interface IP address Corresponding example is currently running;
The first processing module, for thering is the corresponding example of the user to be currently running in detecting the container cluster When, the api interface IP address of the example is back to the user;
The Second processing module, for being currently running in detecting the container cluster without the corresponding example of the user When, according to the user information of the user, start the corresponding example of the user in the container cluster, and by the user The api interface IP address of corresponding example is back to the user;
Wherein, each container instance in the container cluster at runtime, the user of user is corresponded to according to each container instance Information, the corresponding participle dictionary configuration of real-time loading and algorithm model.
4. the individualized intelligent voice interaction device based on container technique as claimed in claim 3, which is characterized in that further include: Heartbeat request obtains module, addition container instance module and deletes container instance module;
The heartbeat request obtains module, for timing acquisition be currently running in the first container example the first heartbeat request; Wherein, first heartbeat request includes the load information of the first container example, the first user information;
The addition container instance module, for when the load of the first container example be more than container threshold value when, according to described The first container example starts an identical second container example, for the normal use of first user;
The deletion container instance module is used for when the first container example non-loaded time being more than preset threshold value, Or when being more than preset threshold time Lungs from Non-Heart-Beating request, the first container example is deleted, with free system resources.
5. a kind of individualized intelligent interactive voice equipment based on container technique, which is characterized in that including processor, memory with And the computer program executed by the processor is stored in the memory and is configured as, described in the processor execution Realize that the individualized intelligent voice based on container technique as described in any one of claim 1 to 2 is handed over when computer program Mutual method.
6. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage Machine program, wherein equipment where controlling the computer readable storage medium in computer program operation is executed as weighed Benefit require any one of 1 to 2 described in the individualized intelligent voice interactive method based on container technique.
CN201910560474.4A 2019-06-26 2019-06-26 A kind of individualized intelligent voice interactive method and device based on container technique Pending CN110288993A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910560474.4A CN110288993A (en) 2019-06-26 2019-06-26 A kind of individualized intelligent voice interactive method and device based on container technique

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910560474.4A CN110288993A (en) 2019-06-26 2019-06-26 A kind of individualized intelligent voice interactive method and device based on container technique

Publications (1)

Publication Number Publication Date
CN110288993A true CN110288993A (en) 2019-09-27

Family

ID=68006112

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910560474.4A Pending CN110288993A (en) 2019-06-26 2019-06-26 A kind of individualized intelligent voice interactive method and device based on container technique

Country Status (1)

Country Link
CN (1) CN110288993A (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1831762A (en) * 2005-03-08 2006-09-13 微软公司 Development framework for mixing semantics-driven and state driven dialog
CN101373468A (en) * 2007-08-20 2009-02-25 北京搜狗科技发展有限公司 Method for loading word stock, method for inputting character and input method system
CN101645087A (en) * 2009-09-01 2010-02-10 腾讯科技(深圳)有限公司 Classified word bank system and updating and maintaining method thereof and client side
CN102541505A (en) * 2011-01-04 2012-07-04 中国移动通信集团公司 Voice input method and system thereof
EP2650776A1 (en) * 2012-04-10 2013-10-16 Artificial Solutions Iberia, S. L. System and methods for delivering advanced natural language interaction applications
CN103389979A (en) * 2012-05-08 2013-11-13 腾讯科技(深圳)有限公司 System, device and method for recommending classification lexicon in input method
CN103677729A (en) * 2013-12-18 2014-03-26 北京搜狗科技发展有限公司 Voice input method and system
CN105245373A (en) * 2015-10-12 2016-01-13 天津市普迅电力信息技术有限公司 Construction and operation method of container cloud platform system
CN106469554A (en) * 2015-08-21 2017-03-01 科大讯飞股份有限公司 A kind of adaptive recognition methodss and system
CN107704323A (en) * 2017-11-07 2018-02-16 广州探迹科技有限公司 A kind of web crawlers method for scheduling task and device
CN108228347A (en) * 2017-12-21 2018-06-29 上海电机学院 The Docker self-adapting dispatching systems that a kind of task perceives
CN108418862A (en) * 2018-01-31 2018-08-17 金蝶软件(中国)有限公司 Micro services management method and system based on artificial intelligence service cloud platform
CN109272995A (en) * 2018-09-26 2019-01-25 出门问问信息科技有限公司 Audio recognition method, device and electronic equipment
GB2569335A (en) * 2017-12-13 2019-06-19 Sage Global Services Ltd Chatbot system

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1831762A (en) * 2005-03-08 2006-09-13 微软公司 Development framework for mixing semantics-driven and state driven dialog
CN101373468A (en) * 2007-08-20 2009-02-25 北京搜狗科技发展有限公司 Method for loading word stock, method for inputting character and input method system
CN101645087A (en) * 2009-09-01 2010-02-10 腾讯科技(深圳)有限公司 Classified word bank system and updating and maintaining method thereof and client side
CN102541505A (en) * 2011-01-04 2012-07-04 中国移动通信集团公司 Voice input method and system thereof
EP2650776A1 (en) * 2012-04-10 2013-10-16 Artificial Solutions Iberia, S. L. System and methods for delivering advanced natural language interaction applications
CN103389979A (en) * 2012-05-08 2013-11-13 腾讯科技(深圳)有限公司 System, device and method for recommending classification lexicon in input method
CN103677729A (en) * 2013-12-18 2014-03-26 北京搜狗科技发展有限公司 Voice input method and system
CN106469554A (en) * 2015-08-21 2017-03-01 科大讯飞股份有限公司 A kind of adaptive recognition methodss and system
CN105245373A (en) * 2015-10-12 2016-01-13 天津市普迅电力信息技术有限公司 Construction and operation method of container cloud platform system
CN107704323A (en) * 2017-11-07 2018-02-16 广州探迹科技有限公司 A kind of web crawlers method for scheduling task and device
GB2569335A (en) * 2017-12-13 2019-06-19 Sage Global Services Ltd Chatbot system
CN108228347A (en) * 2017-12-21 2018-06-29 上海电机学院 The Docker self-adapting dispatching systems that a kind of task perceives
CN108418862A (en) * 2018-01-31 2018-08-17 金蝶软件(中国)有限公司 Micro services management method and system based on artificial intelligence service cloud platform
CN109272995A (en) * 2018-09-26 2019-01-25 出门问问信息科技有限公司 Audio recognition method, device and electronic equipment

Similar Documents

Publication Publication Date Title
US11030412B2 (en) System and method for chatbot conversation construction and management
CN109003605B (en) Intelligent voice interaction processing method, device, equipment and storage medium
JP7112919B2 (en) Smart device task processing method and device
CN106202505B (en) Data processing method and its system
US20220293089A1 (en) Voice dialogue processing method and apparatus
WO2018036555A1 (en) Session processing method and apparatus
CN108491147A (en) A kind of man-machine interaction method and mobile terminal based on virtual portrait
CN109637548A (en) Voice interactive method and device based on Application on Voiceprint Recognition
CN105677763B (en) A kind of image quality measure system based on Hadoop
CN107808440B (en) Queuing service processing method and processing device
CN106815254A (en) A kind of data processing method and device
CN109548691A (en) A kind of pet recognition methods, device, medium and electronic equipment
US10673789B2 (en) Bot-invocable software development kits to access legacy systems
CN107229656A (en) Full dose data export method, apparatus and system
CN111966689A (en) Application knowledge base construction method and device
CN108600564A (en) The method and apparatus of customer service
CN109410934A (en) A kind of more voice sound separation methods, system and intelligent terminal based on vocal print feature
CN107423307B (en) Internet information resource allocation method and device
CN107623620B (en) Processing method of random interaction data, network server and intelligent dialogue system
CN112069830A (en) Intelligent conversation method and device
CN110288993A (en) A kind of individualized intelligent voice interactive method and device based on container technique
CN110418181A (en) To the method for processing business of smart television, device, smart machine and storage medium
CN113055348A (en) Cross-platform data request method and device and electronic equipment
CN110442694A (en) A kind of intelligent interaction platform training method, apparatus, equipment
CN110287384A (en) Intelligent Service method, device and equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20190927

RJ01 Rejection of invention patent application after publication