Movatterモバイル変換


[0]ホーム

URL:


CN109543014A - Interactive method, device, terminal and server - Google Patents

Interactive method, device, terminal and server
Download PDF

Info

Publication number
CN109543014A
CN109543014ACN201811309389.2ACN201811309389ACN109543014ACN 109543014 ACN109543014 ACN 109543014ACN 201811309389 ACN201811309389 ACN 201811309389ACN 109543014 ACN109543014 ACN 109543014A
Authority
CN
China
Prior art keywords
answer
question
target
query statement
candidate
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.)
Granted
Application number
CN201811309389.2A
Other languages
Chinese (zh)
Other versions
CN109543014B (en
Inventor
钟云
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.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen 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 Tencent Technology Shenzhen Co LtdfiledCriticalTencent Technology Shenzhen Co Ltd
Priority to CN201811309389.2ApriorityCriticalpatent/CN109543014B/en
Publication of CN109543014ApublicationCriticalpatent/CN109543014A/en
Application grantedgrantedCritical
Publication of CN109543014BpublicationCriticalpatent/CN109543014B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Landscapes

Abstract

The present invention provides interactive method, device, terminal and servers, and the method includes obtaining query argument collection, the query argument collection includes query statement and the essential information of target user, and the target user is the user for issuing the query statement;The corresponding question and answer of the target user are obtained to data set according to the essential information of the target user;Data are concentrated in the question and answer and extract the corresponding candidate question and answer pair of the query statement, and obtain the first Candidate Set;Judge whether first Candidate Set is empty;If first Candidate Set is not empty, the selection target answer from first Candidate Set, and exports the target answer.The present invention configures one's own question and answer to data set with supporting user individual, to promote interactive accuracy.Under the premise of allowing to customize question and answer pair, common data sets are additionally provided, to ensure that interactive recall rate.

Description

Interactive method, device, terminal and server
Technical field
The present invention relates to computer field more particularly to interactive method, device, terminal and servers.
Background technique
Existing human-computer dialogue machine people mainly uses two kinds of technical solutions, one is each problem is directed to, using depthLearning method generates problem answers, and flow chart is as shown in Figure 1.The advantage of this method is recall rate height, i.e., for the every of userA query statement can all provide answer substantially, the disadvantage is that accuracy rate is low.Another kind is to generate problem using retrieval type method to answerCase, flow chart are as shown in Figure 2.This method needs to be pre-configured with knowledge base, for each query statement, retrieves in knowledge baseThen the problem most close with the problem out is provided using correspondence answer the problem of retrieving as answer is replied.This methodAdvantage is accuracy rate height, and the answer provided can largely suit the original idea of user, the disadvantage is that recall rate is low.
In addition, above two technical solution be for a user it is transparent, it is not configurable, therefore the answer providedSubstantially fixed, lack of diversity can not provide different answers for the same problem of different user.
Summary of the invention
In order to solve the above-mentioned technical problem, the invention proposes interactive method, device, terminal and servers.This hairBright is specifically to be realized with following technical solution:
In a first aspect, a kind of interactive method, comprising:
Query argument collection is obtained, the query argument collection includes query statement and the essential information of target user, the meshMarking user is the user for issuing the query statement;
The corresponding question and answer of the target user are obtained to data set according to the essential information of the target user;
Data are concentrated in the question and answer and extract the corresponding candidate question and answer pair of the query statement, and obtain the first candidateCollection;
The selection target answer from first Candidate Set, and export the target answer.
Second aspect, a kind of human-computer dialogue device, comprising:
Query argument collection obtains module, and for obtaining query argument collection, the query argument collection includes query statement and meshThe essential information of user is marked, the target user is the user for issuing the query statement;
Question and answer are to data set acquisition module, for obtaining the target user couple according to the essential information of the target userThe question and answer answered are to data set;
First Candidate Set obtains module, extracts the corresponding candidate of the query statement for concentrating in the question and answer to dataQuestion and answer pair, and obtain the first Candidate Set;
Target answer obtains module, is used for the selection target answer from first Candidate Set, and export the target and answerCase.
The third aspect, a kind of terminal, the terminal are used for a kind of above-mentioned human-computer dialogue device.
Fourth aspect, a kind of server, the server are used for a kind of above-mentioned human-computer dialogue device.
The present invention provides interactive method, device, terminal and servers.The present invention configures with supporting user individualOne's own question and answer are to data set, to promote interactive accuracy.Under the premise of allowing to customize question and answer pair, also mentionCommon data sets are supplied, to ensure that interactive recall rate.Further, the present invention also provides be based on FastTextThe method that term vector model chooses target answer, to further improve the accuracy of the target answer of output.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show belowThere is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only thisSome embodiments of invention for those of ordinary skill in the art without creative efforts, can be withOther attached drawings are obtained according to these attached drawings.
Fig. 1 is the interactive method flow chart based on deep learning that background of invention provides;
Fig. 2 is that background of invention provides the interactive method flow chart based on retrieval type;
Fig. 3 is a kind of interactive method flow chart provided in an embodiment of the present invention;
Fig. 4 is schematic diagram of the question and answer provided in an embodiment of the present invention to editing interface;
Fig. 5 is the pre- querying method flow chart of target answer provided in an embodiment of the present invention;
Fig. 6 is the content schematic diagram of the provided in an embodiment of the present invention first default template;
Fig. 7 is the content schematic diagram of the provided in an embodiment of the present invention second default template;
Fig. 8 is the content schematic diagram that third provided in an embodiment of the present invention presets template;
Fig. 9 is the method flow diagram provided in an embodiment of the present invention that question and answer pair are obtained according to query statement;
Figure 10 is the method flow diagram of the selection target answer provided in an embodiment of the present invention among candidate question and answer pair;
Figure 11 is the similarity based method flow chart provided in an embodiment of the present invention for obtaining candidate question and answer pair and query statement;
Figure 12 is a kind of human-computer dialogue device block diagram provided in an embodiment of the present invention;
Figure 13 is terminal schematic diagram provided in an embodiment of the present invention;
Figure 14 is a kind of server architecture schematic diagram provided in an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present inventionAttached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is onlyThe embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill peopleThe model that the present invention protects all should belong in member's every other embodiment obtained without making creative workIt encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this wayData be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein orSequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that coverCover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited toStep or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, productOr other step or units that equipment is intrinsic.
The embodiment of the invention discloses a kind of interactive methods, as shown in Figure 3, which comprises
S101. query argument collection is obtained, the query argument collection includes query statement and the essential information of target user, instituteStating target user is the user for issuing the query statement.
Specifically, user can carry out human-computer dialogue, communication circle of the Intelligent dialogue tool by Intelligent dialogue toolFace may include session window.
Specifically, the session window can be the window for interacting with user that client provides.The visitorFamily end can embed instant messaging tools (InstantMessenger, IM) client.The instant messaging tools can be appliedIn any electronic equipment, such as intelligent movable phone, Flat electronic equipment, portable computer (such as laptopDeng), personal digital assistant (PDA), desktop computer, the intelligent wearable device with information reading function etc..It is described instantMeans of communication can include but is not limited to MSN, AOL of Intelligent dialogue tool, the QQ of Tencent or wechat, MicrosoftICQ, Taobao Wang Wang, Netease POPO, Fetion, Michat of millet company etc..The Intelligent dialogue tool can be one kind can be withUser carries out the computer program of real-time interaction, can receive the input information of user, and can show in session windowThe reply message to match with the input information.The Intelligent dialogue tool may include the small ice of Microsoft, Baidu's public affairsSecret, Jingdone district company the JIMI of degree, the assistant of department come also and the Siri of Apple Inc. etc..
S102. the corresponding question and answer of the target user are obtained to data set according to the essential information of the target user.
Specifically, question and answer can be customized in the embodiment of the present invention according to user's own characteristic to data set, therefore, question and answer pairData set and target user establish one-to-one relationship.The essential information of target user includes user identifier, user identifier and useThe corresponding question and answer in family correspond data set, and question and answer corresponding to the user can be obtained to data according to user basic informationCollection.As shown in figure 4, it illustrates question and answer to the schematic diagram of editing interface.The question and answer are to editing interface for editor user'sProblem, corresponding answer and the basic data that user is set.When user uses the question and answer to editing interface editor's question and answer pairAfterwards, question and answer to will be recorded in the corresponding question and answer of the user to data set among.Question and answer further include basis to editing interfaceData entry template can automatically generate question and answer pair by inputting basic data into basic data input template.
S103. data are concentrated in the question and answer and extracts the corresponding candidate question and answer pair of the query statement, and obtain firstCandidate Set.
S104. judge whether first Candidate Set is empty.
If S105. first Candidate Set is not empty, the selection target answer from first Candidate Set, and exports instituteState target answer.
In interactive method disclosed by the embodiments of the present invention, user can permit from edlin question and answer pair, and defeatedThe link of target answer pays the utmost attention to user from edlin out and obtained question and answer are to data set.It is man-machine in compared to the prior artDialogue is merely able to the technical solution that presets, and can not freely be configured by user, it is clear that has that diversity is strong, and user experience is goodAdvantage.If target answer is aobvious in addition, target answer can successfully be exported by freely configuring to obtain the first Candidate Set by userIt is so the query demand for meeting user, therefore, also improves the accuracy of target answer.
But the content that user freely configures is limited, user is also impossible to that a large amount of problem and its corresponding answer is arranged,Therefore, in order to be not provided with to user the problem of, can also provide answer, also provide following step in the embodiment of the present invention:
If S106. first Candidate Set is sky, is concentrated in common data and extract the corresponding candidate of the query statementQuestion and answer pair, and obtain the second Candidate Set.
Specifically, the content that the common data is concentrated can not need user's customization, unrelated with specific user yet.It is publicData set can be obtained and pre-entering a large amount of corpus training altogether.
S107. judge whether second Candidate Set is empty.
If S108. second Candidate Set is not empty, the selection target answer from second Candidate Set, and exports instituteState target answer.
Further, it in order to promote the output speed of target answer, is executed in the embodiment of the present invention using double query enginesInteractive process, specifically, double query engines include full-text search engine and database engine.It is asked when user editsWhen answering questions, question and answer come into force to will be written directly into full-text search engine, while question and answer are to can be by full-text searchEngine is synchronized in database engine, thereby guarantees that the data in full-text search engine and database engine have consistency.?During human-computer dialogue, target answer (i.e. execution step S103-S105) is preferentially obtained from full-text search engine, if full text is searchedIndex, which is held up, can not provide target answer, then target answer (i.e. execution step S106-S108) is provided from database engine.ThisOutside, in design database engine, the embodiment of the present invention also fully considers disaster recovery backup, to guarantee to occur in full-text search engineWhen failure, answer can be chosen from database engine, with thereby guaranteeing that human-computer dialogue process steady implementation.
Specifically, the full-text search engine in the embodiment of the present invention uses ElasticSearch.ElasticSearch isOne search server based on Lucene.It provides the full-text search engine of a distributed multi-user ability, is based onRESTful web interface.Elasticsearch is developed with Java, and as the open source code under Apache license termsPublication is Enterprise search engine currently popular.Database engine in the embodiment of the present invention uses Mysql.MySQL is oneA Relational DBMS saves the data in different tables, rather than all data are placed on a big warehouseIt is interior, which adds speed and improve flexibility.Sql like language used in MySQL is for accessing the most normal of databaseUse standardized language.It has that small in size, speed is fast, the total cost of ownership is low, and open source code a little, and can arrange in pairs or groupsPHP and Apache forms good exploitation environment.
In order to promote the output speed of target answer, the embodiment of the present invention still further provides the mesh based on query statementMark the pre- querying method of answer, the method can be implemented between step S101 and step S102, the method as shown in figure 5,Include:
S201. judge whether the query statement is illegal query statement.
Specifically, the inquiry language can be judged by judging whether the query statement includes Chinese character or English characterWhether sentence is legal, if including, the query statement is legal, if not including, the query statement is illegal.
S202. if so, exporting target answer according to the first default template.
Further, the method also includes:
S203. if it is not, then judging whether the query statement includes sensitive word.
Specifically, sensitive word is generally referred to sensitive political orientation, violent tenet, unhealthy color in the embodiment of the present inventionColor word.In other feasible embodiments, sensitive word related with the implementation environment of interactive method can also be determinedSystem.For example, piracy of intellectual property rights can be related to by some if being applied to the scene of e-commerce, and the commodity that should not be sold, exampleSuch as " mountain vallage ", "parallel goods", " piracy ", " imprinting " are set as sensitive word, in addition, the title of rival is in some electric business websitesAnd the sensitive word that can not be issued.
Sensitive word can also be the stop word of standard literature or national publication, for example, Xinhua News Agency's publication " Xinhua News Agency is newHear the stop word (first) in report " in the stop word that refers to related generally to five aspect contents, have stable political situation society when being respectivelyStop word, the laws and regulations class stop word of life kind, stop word, Hong Kong, Macao and Taiwan and the stop word of territorial sovereignty class of ethnic and religious class,The stop word of international relations class.
S204. if so, exporting target answer according to the second default template.
Further, the method also includes:
S205. if it is not, then judging whether the query statement includes uncivil word.
Uncivil word be primarily referred to as it is some be against public morality lack or public order and good custom language.Uncivil word can also beSome " avoid as taboo and claim ", such as the word being ashamed to mention more in people's daily life.
S206. if so, presetting template output target answer according to third.
In the embodiment of the present invention, the first default template, the second default template and third are preset template and can be preset, andIt is saved among full-text search engine.Referring to FIG. 6, being non-in query statement it illustrates the content of the first default templateWhen method query statement, the content " I is also not likely to extraterrestrial language " of the first default template is exported.Referring to FIG. 7, it illustratesThe content of two default templates, when in query statement comprising sensitive word, " I less understands you to the content of the second default template of outputIt says, originally artificial intelligence is also not omnipotent ".Referring to FIG. 8, being inquired it illustrates the content that third presets templateWhen in sentence including dirty word, output third presets the content " swearing at people is not a behavior for civilization " of template.In other feasible realitiesIt applies in example, the content that the first default template, the second default template and third preset template can also be according to the actual conditions of userIt is changed, to improve the adaptivity of human-computer interaction.Such as third presets template, if user is schoolgirl," beauty, which swears at people, can become ugly " can be exported, if user is boy student, " handsome boy cannot swear at people " can be exported.
In the specific implementation process, step S203-S204 and step S205-S206 can be interchanged.It is inquiring in advanceIn the implementation procedure of method, step S102 and its subsequent step need not be executed again if outputing target answer.
In order to quickly and accurately judge whether query statement includes sensitive word or uncivil word, the present invention implements to use dictionaryTree detects sensitive word or uncivil word.Trie tree is constructed based on existing sensitive word and dirty word dictionary, is then usedTrie tree extracts sensitive word or uncivil word inside query statement.
Dictionary tree can be referred to as Trie tree again, and efficiency is higher, and can be used for counting and sorting a large amount of character string, advantageIt is to reduce meaningless character string comparison to the maximum extent, dictionary tree can use the common prefix of character string come when reducing inquiryBetween expense to achieve the purpose that improve efficiency, dictionary tree has following features: root node does not include character, except root node withOutside, each node only includes a character;From root node to some node, the Connection operator passed through on path is exactlyThe corresponding character string of the node;The character string that all child nodes of each node include is not identical.
Further, the embodiment of the invention discloses the methods for extracting question and answer pair according to query statement, as shown in figure 9, instituteThe method of stating includes:
S301. the query statement is segmented, and obtains word segmentation result collection.
S302. each participle concentrated to the word segmentation result carries out candidate question and answer to extraction, and obtains the participleCorresponding candidate's question and answer pair.
Specifically, for each question and answer pair, if in problem including the participle, the question and answer are to belonging to the participleCorresponding candidate's question and answer pair.
S303. the intersection for taking the corresponding candidate question and answer pair of each participle obtains the corresponding candidate question and answer of the query statementIt is right.
Specifically, the method for obtaining question and answer pair according to query statement can be applied to step S103 and/or step S106.
Candidate question and answer are being obtained to later, the embodiment of the present invention is further provided from selection target among candidate question and answer pairThe method of answer, the method in the embodiment of the present invention are based on FastText term vector model, and FastText is 2016Facebook releases a tool for text classification and calculating term vector, the advantage is that model is simple, training speed is fast.FastText term vector model in the embodiment of the present invention is trained in advance using 14,000,000 encyclopaedia question and answer to corpus under line, content structure is the corresponding word of every a line 100 dimensional vectors corresponding with the word.
As shown in Figure 10, the method specifically includes:
S401. similarity between each candidate question and answer pair and query statement is calculated.
S402. the highest candidate question and answer of similarity are chosen to as target question and answer pair.
S403. judge whether the similarity is greater than preset threshold.
S404. if so, using the answer of target question and answer centering as target answer.
Specifically, as shown in figure 11, candidate question and answer pair are obtained and the similarity of query statement includes:
S4011. the query statement is segmented to obtain first participle collection, to the candidate problem of candidate question and answer centering intoRow participle obtains the second participle collection.
S4012. find out first participle collection and the second participle concentrate the equivalent of each word in FastText model toAmount.
S4013. it calculates the corresponding primary vector of first participle collection and the second participle collects corresponding secondary vector.
Specifically, calculation method used in primary vector and secondary vector can be identical.With in the embodiment of the present inventionFor one vector, divided by the number of first participle concentration word after concentrating the corresponding term vector of each word to be added summation the first participlePrimary vector can be obtained, for example, the first participle collection corresponding first obtained after query statement " what is your name " participleVector be [- 0.105925, -0.137778, -0.049424, -0.049424, -0.080659,0.120057] (dimension of vector is 100 dimensions, here display portion dimension values).
S4014. the cosine similarity of primary vector and secondary vector is calculated, and as query statement and candidate question and answerPair similarity.
The calculation method of cosine similarity such as formulaIt is shown, wherein a, b be respectively primary vector andSecondary vector, | | ɑ | | indicate the mould of vector ɑ, | | b | | indicate the mould of vector b.
In another feasible embodiment of the invention, LSTM network model (Long Short-Term can also be usedMemory, shot and long term memory network) similarity that obtains candidate question and answer pair and query statement, by using LSTM network model pairThe candidate problem of query statement and candidate question and answer is encoded, and the semantic similarity between them is calculated based on coding result, andUsing the semantic similarity as query statement with the similarity of candidate question and answer pair.
User individual can be supported in method provided in an embodiment of the present invention one's own question and answer are configured to dataCollection, to promote interactive accuracy.Under the premise of allowing to customize question and answer pair, common data sets are additionally provided, thusIt ensure that interactive recall rate.Further, the present invention also provides choose target based on FastText term vector modelThe method of answer, to further improve the accuracy of the target answer of output.
The embodiment of the present invention also provides a kind of human-computer dialogue device, as shown in figure 12, comprising:
Query argument collection obtains module 501, for obtaining query argument collection, the query argument collection include query statement andThe essential information of target user, the target user are the user for issuing the query statement;
Question and answer use data set acquisition module 502 for obtaining the target according to the essential information of the target userThe corresponding question and answer in family are to data set;
First Candidate Set obtains module 503, for concentrating the extraction query statement corresponding data in the question and answerCandidate question and answer pair, and obtain the first Candidate Set;
Judgment module 504, for judging whether first Candidate Set is empty;
Target answer obtains module 505, if not being sky for first Candidate Set, selects from first Candidate SetTarget answer is selected, and exports the target answer.
A kind of the device of the invention human-computer dialogue apparatus and method embodiment as described in the examples is based on similarly inventingDesign.
The embodiments of the present invention also provide a kind of storage medium, the storage medium can be used for saving for realizing implementationA kind of program code that human-computer dialogue needs to use in example.Optionally, in the present embodiment, above-mentioned storage medium can be located atAt least one network equipment in multiple network equipments of computer network.Optionally, in the present embodiment, above-mentioned storage mediumCan include but is not limited to: USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM,Random Access Memory), mobile hard disk, the various media that can store program code such as magnetic or disk.
Figure 13 is please referred to, it illustrates the structural schematic diagrams of terminal provided by one embodiment of the present invention.The terminal operatingA kind of human-computer dialogue device provided in above-described embodiment is provided.
The terminal may include RF (Radio Frequency, radio frequency) circuit 110, include one or moreThe memory 120 of computer readable storage medium, input unit 130, display unit 140, sensor 150, voicefrequency circuit 160,WiFi (wireless fidelity, Wireless Fidelity) module 170, the processing for including one or more than one processing coreThe components such as device 180 and power supply 190.It will be understood by those skilled in the art that terminal structure shown in Figure 13 is not constituted pairThe restriction of terminal may include perhaps combining certain components or different component cloth than illustrating more or fewer componentsIt sets.Wherein:
RF circuit 110 can be used for receiving and sending messages or communication process in, signal sends and receivees, particularly, by base stationAfter downlink information receives, one or the processing of more than one processor 180 are transferred to;In addition, the data for being related to uplink are sent toBase station.In general, RF circuit 110 includes but is not limited to antenna, at least one amplifier, tuner, one or more oscillators, usesFamily identity module (SIM) card, transceiver, coupler, LNA (LowNoiseAmplifier, low-noise amplifier), duplexerDeng.In addition, RF circuit 110 can also be communicated with network and other equipment by wireless communication.The wireless communication can be usedAny communication standard or agreement, including but not limited to GSM (Global System ofMobile communication, the whole worldMobile communcations system), GPRS (General Packet Radio Service, general packet radio service), CDMA (CodeDivision MultipleAccess, CDMA), WCDMA (Wideband Code DivisionMultipleAccess, wideband code division multiple access), LTE (Long Term Evolution, long term evolution), Email, SMS(Short Messaging Service, short message service) etc..
Memory 120 can be used for storing software program and module, and processor 180 is stored in memory 120 by operationSoftware program and module, thereby executing various function application and data processing.Memory 120 can mainly include storage journeySequence area and storage data area, wherein storing program area can application program needed for storage program area, function etc.;Storing dataArea, which can be stored, uses created data etc. according to the terminal.In addition, memory 120 may include that high random access is depositedReservoir can also include nonvolatile memory, for example, at least a disk memory, flush memory device or other volatibilitySolid-state memory.Correspondingly, memory 120 can also include Memory Controller, to provide processor 180 and input unitThe access of 130 pairs of memories 120.
Input unit 130 can be used for receiving the number or character information of input, and generate and user setting and functionControl related keyboard, mouse, operating stick, optics or trackball signal input.Specifically, input unit 130 may include touchingSensitive surfaces 131 and other input equipments 132.Touch sensitive surface 131, also referred to as touch display screen or Trackpad are collected and are usedFamily on it or nearby touch operation (such as user using any suitable object or attachment such as finger, stylus in touch-sensitive tableOperation on face 131 or near touch sensitive surface 131), and corresponding attachment device is driven according to preset formula.It is optional, touch sensitive surface 131 may include both touch detecting apparatus and touch controller.Wherein, touch detecting apparatus detection is usedThe touch orientation at family, and touch operation bring signal is detected, transmit a signal to touch controller;Touch controller is from touchTouch information is received in detection device, and is converted into contact coordinate, then gives processor 180, and can receive processor 180The order sent simultaneously is executed.Furthermore, it is possible to using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic wavesRealize touch sensitive surface 131.In addition to touch sensitive surface 131, input unit 130 can also include other input equipments 132.Specifically,Other input equipments 132 can include but is not limited to physical keyboard, function key (such as volume control button, switch key etc.),One of trace ball, mouse, operating stick etc. are a variety of.
Display unit 140 can be used for showing information input by user or the information and the terminal that are supplied to userVarious graphical user interface, these graphical user interface can be made of figure, text, icon, video and any combination thereof.Display unit 140 may include display panel 141, optionally, can use LCD (Liquid Crystal Display, liquid crystalShow device), the forms such as OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) configure display panel141.Further, touch sensitive surface 131 can cover display panel 141, when touch sensitive surface 131 detects touching on it or nearbyAfter touching operation, processor 180 is sent to determine the type of touch event, is followed by subsequent processing device 180 according to the type of touch eventCorresponding visual output is provided on display panel 141.Although touch sensitive surface 131 and display panel 141 are conducts in Figure 13Two independent components realize input and input function, but in some embodiments it is possible to by touch sensitive surface 131 and displayPanel 141 is integrated and realizes and outputs and inputs function.
The terminal may also include at least one sensor 150, such as optical sensor, motion sensor and other sensingsDevice.Specifically, optical sensor may include 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 141, and proximity sensor can close display when the terminal is moved in one's earPanel 141 and/or backlight.As a kind of motion sensor, gravity accelerometer can detect in all directions (generallyThree axis) acceleration size, can detect that size and the direction of gravity when static, can be used to identify terminal posture application (ratioSuch as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap);ExtremelyIn other sensors such as gyroscope, barometer, hygrometer, thermometer, the infrared sensors that the terminal can also configure, hereinIt repeats no more.
Voicefrequency circuit 160, loudspeaker 161, microphone 162 can provide the audio interface between user and the terminal.SoundElectric signal after the audio data received conversion can be transferred to loudspeaker 161, be converted to by loudspeaker 161 by frequency circuit 160Voice signal output;On the other hand, the voice signal of collection is converted to electric signal by microphone 162, is received by voicefrequency circuit 160After be converted to audio data, then by after the processing of audio data output processor 180, be sent to through RF circuit 110 such as anotherTerminal, or audio data is exported to memory 120 to be further processed.Voicefrequency circuit 160 is also possible that earplug is insertedHole, to provide the communication of peripheral hardware earphone Yu the terminal.
WiFi belongs to short range wireless transmission technology, and the terminal can help user to receive and dispatch electricity by WiFi module 170Sub- mail, browsing webpage and access streaming video etc., it provides wireless broadband internet access for user.Although Figure 13 showsGo out WiFi module 170, but it is understood that, and it is not belonging to must be configured into for the terminal, it completely can be according to needIt to omit within the scope of not changing the essence of the invention.
Processor 180 is the control centre of the terminal, utilizes each portion of various interfaces and the entire terminal of connectionPoint, by running or execute the software program and/or module that are stored in memory 120, and calls and be stored in memory 120Interior data execute the various functions and processing data of the terminal, to carry out integral monitoring to terminal.Optionally, it handlesDevice 180 may include one or more processing cores;Preferably, processor 180 can integrate application processor and modulation /demodulation processingDevice, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is mainly locatedReason wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 180.
The terminal further includes the power supply 190 (such as battery) powered to all parts, it is preferred that power supply can pass through electricityManagement system and processor 180 are logically contiguous, to realize management charging, electric discharge and power consumption by power-supply management systemThe functions such as management.Power supply 190 can also include one or more direct current or AC power source, recharging system, power supply eventHinder the random components such as detection circuit, power adapter or inverter, power supply status indicator.
Although being not shown, the terminal can also include camera, bluetooth module etc., and details are not described herein.Specifically at thisIn embodiment, the display unit of terminal is touch-screen display, terminal further include have memory and one or more than oneProgram, one of them perhaps more than one program be stored in memory and be configured to by one or more than oneIt includes for executing the instruction in a kind of above-mentioned interactive method that one or more than one program are stated in reason device execution.
Figure 14 is please referred to, it illustrates the structural schematic diagrams of server provided by one embodiment of the present invention.The serverA kind of human-computer dialogue device provided in above-described embodiment is implemented in operation.Specifically:
The server 1200 includes 1202 He of central processing unit (CPU) 1201 including random access memory (RAM)The system storage 1204 of read-only memory (ROM) 1203, and connection system storage 1204 and central processing unit 1201System bus 1205.The server 1200 further includes that the substantially defeated of information is transmitted between each device helped in computerEnter/output system (I/O system) 1206, and is used for storage program area 1213, application program 1214 and other program modules1215 mass-memory unit 1207.
The basic input/output 1206 includes display 1208 for showing information and inputs for userThe input equipment 1209 of such as mouse, keyboard etc of information.Wherein the display 1208 and input equipment 1209 all pass throughThe input and output controller 1210 for being connected to system bus 1205 is connected to central processing unit 1201.The basic input/defeatedSystem 1206 can also include input and output controller 1210 to touch for receiving and handling from keyboard, mouse or electronics outControl the input of multiple other equipment such as pen.Similarly, input and output controller 1210 also provide output to display screen, printer orOther kinds of output equipment.
The mass-memory unit 1207 (is not shown by being connected to the bulk memory controller of system bus 1205It is connected to central processing unit 1201 out).The mass-memory unit 1207 and its associated computer-readable medium areServer 1200 provides non-volatile memories.That is, the mass-memory unit 1207 may include such as hard disk orThe computer-readable medium (not shown) of person's CD-ROM drive etc.
Without loss of generality, the computer-readable medium may include computer storage media and communication media.ComputerStorage medium includes information such as computer readable instructions, data structure, program module or other data for storageThe volatile and non-volatile of any method or technique realization, removable and irremovable medium.Computer storage medium includesRAM, ROM, EPROM, EEPROM, flash memory or other solid-state storages its technologies, CD-ROM, DVD or other optical storages, tapeBox, tape, disk storage or other magnetic storage devices.Certainly, skilled person will appreciate that the computer storage mediumIt is not limited to above-mentioned several.Above-mentioned system storage 1204 and mass-memory unit 1207 may be collectively referred to as memory.
According to various embodiments of the present invention, the server 1200 can also be arrived by network connections such as internetsRemote computer operation on network.Namely server 1200 can be connect by the network being connected on the system bus 1205Mouth unit 1211 is connected to network 1212, in other words, it is other kinds of to be connected to that Network Interface Unit 1211 also can be usedNetwork or remote computer system (not shown).
The memory further includes that one or more than one program, the one or more programs are stored inIn memory, and it is configured to be executed by one or more than one processor.Said one or more than one program includeFor executing the instruction of the method for above-mentioned server.
It should be understood that referenced herein " multiple " refer to two or more."and/or", description associationThe incidence relation of object indicates may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously AAnd B, individualism B these three situations.Character "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or".
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardwareIt completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readableIn storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention andWithin principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.

Claims (11)

CN201811309389.2A2018-11-052018-11-05Man-machine conversation method, device, terminal and serverActiveCN109543014B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN201811309389.2ACN109543014B (en)2018-11-052018-11-05Man-machine conversation method, device, terminal and server

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN201811309389.2ACN109543014B (en)2018-11-052018-11-05Man-machine conversation method, device, terminal and server

Publications (2)

Publication NumberPublication Date
CN109543014Atrue CN109543014A (en)2019-03-29
CN109543014B CN109543014B (en)2021-06-15

Family

ID=65846240

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN201811309389.2AActiveCN109543014B (en)2018-11-052018-11-05Man-machine conversation method, device, terminal and server

Country Status (1)

CountryLink
CN (1)CN109543014B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN110162611A (en)*2019-04-232019-08-23苏宁易购集团股份有限公司A kind of intelligent customer service answer method and system
CN112509690A (en)*2020-11-302021-03-16北京百度网讯科技有限公司Method, apparatus, device and storage medium for controlling quality
WO2021139243A1 (en)*2020-01-082021-07-15平安科技(深圳)有限公司Data processing method, device, and apparatus employing human-computer interaction, and storage medium
CN113918702A (en)*2021-10-252022-01-11北京航空航天大学Semantic matching-based online legal automatic question-answering method and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN103198155A (en)*2013-04-272013-07-10俞志晨Mobile terminal based smart question answering interaction system and method
US20170364806A1 (en)*2016-06-212017-12-21International Business Machines CorporationCognitive question answering pipeline blending
CN107623620A (en)*2016-07-142018-01-23腾讯科技(深圳)有限公司Processing method, the webserver and the Intelligent dialogue system of randomness interaction data
CN108182262A (en)*2018-01-042018-06-19华侨大学Intelligent Answer System construction method and system based on deep learning and knowledge mapping
CN108595619A (en)*2018-04-232018-09-28海信集团有限公司A kind of answering method and equipment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN103198155A (en)*2013-04-272013-07-10俞志晨Mobile terminal based smart question answering interaction system and method
US20170364806A1 (en)*2016-06-212017-12-21International Business Machines CorporationCognitive question answering pipeline blending
CN107623620A (en)*2016-07-142018-01-23腾讯科技(深圳)有限公司Processing method, the webserver and the Intelligent dialogue system of randomness interaction data
CN108182262A (en)*2018-01-042018-06-19华侨大学Intelligent Answer System construction method and system based on deep learning and knowledge mapping
CN108595619A (en)*2018-04-232018-09-28海信集团有限公司A kind of answering method and equipment

Cited By (6)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN110162611A (en)*2019-04-232019-08-23苏宁易购集团股份有限公司A kind of intelligent customer service answer method and system
WO2021139243A1 (en)*2020-01-082021-07-15平安科技(深圳)有限公司Data processing method, device, and apparatus employing human-computer interaction, and storage medium
CN112509690A (en)*2020-11-302021-03-16北京百度网讯科技有限公司Method, apparatus, device and storage medium for controlling quality
CN112509690B (en)*2020-11-302023-08-04北京百度网讯科技有限公司 Method, device, device and storage medium for quality control
US12032906B2 (en)2020-11-302024-07-09Beijing Baidu Netcom Science And Technology Co., Ltd.Method, apparatus and device for quality control and storage medium
CN113918702A (en)*2021-10-252022-01-11北京航空航天大学Semantic matching-based online legal automatic question-answering method and system

Also Published As

Publication numberPublication date
CN109543014B (en)2021-06-15

Similar Documents

PublicationPublication DateTitle
CN106227774B (en)Information search method and device
US9241242B2 (en)Information recommendation method and apparatus
CN108364644A (en)A kind of voice interactive method, terminal and computer-readable medium
CN104281600B (en)The method and apparatus of Intelligent Selection word
CN109543014A (en)Interactive method, device, terminal and server
CN104123937A (en)Method, device and system for reminding setting
WO2014169715A1 (en)Information recommendation method and apparatus
CN111490927B (en) A method, device and device for displaying messages
CN104951432A (en)Information processing method and device
CN110399474A (en)A kind of Intelligent dialogue method, apparatus, equipment and storage medium
CN104281394A (en)Method and device for intelligently selecting words
CN108268438B (en)Page content extraction method and device and client
CN104111927A (en)Method, equipment and system for information classification
CN109728918A (en)Virtual objects sending method, virtual objects method of reseptance, device and storage medium
CN102446205A (en)Electronic device and operating method thereof
CN104063400B (en)Data search method and data search device
CN104134043A (en)Method and device for hiding contents, method and device for unhiding contents, and terminals
CN110196833A (en)Searching method, device, terminal and the storage medium of application program
CN104281610B (en)The method and apparatus for filtering microblogging
CN104731782B (en)A kind of method and mobile terminal of information processing
US10630619B2 (en)Electronic device and method for extracting and using semantic entity in text message of electronic device
CN104424324B (en)The method and device of locating list item in list element
CN104391588B (en)A kind of method of input prompt and device
CN103871050A (en)Image partition method, device and terminal
CN104915627B (en) Method and device for character recognition

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp