CN109948151A - The method for constructing voice assistant - Google Patents
The method for constructing voice assistant Download PDFInfo
- Publication number
- CN109948151A CN109948151A CN201910162756.9A CN201910162756A CN109948151A CN 109948151 A CN109948151 A CN 109948151A CN 201910162756 A CN201910162756 A CN 201910162756A CN 109948151 A CN109948151 A CN 109948151A
- Authority
- CN
- China
- Prior art keywords
- voice assistant
- user
- information
- interface
- field
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000013507 mapping Methods 0.000 claims abstract description 21
- 230000004044 response Effects 0.000 claims abstract description 4
- 230000015654 memory Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 230000008520 organization Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005538 encapsulation Methods 0.000 description 2
- 230000001747 exhibiting effect Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000004308 accommodation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000007474 system interaction Effects 0.000 description 1
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The present invention discloses a kind of method for constructing voice assistant, comprising: creates the request of voice assistant in response to user, generates voice assistant and create interface, includes multiple information solicitation projects for user's selection in voice assistant creation interface;When detecting the selection operation of user, determine that the information solicitation project for corresponding to selection operation is destination item;It generates for guiding user to fill in the information solicitation interface of project information associated with destination item;Knowledge mapping is generated according to the project information that user is filled under information solicitation interface, to realize human-computer dialogue service for voice assistant.User only needs to fill in the relevant item information known to oneself in the present invention according to the creation interface successively showed, greatly simplify the customization work of voice assistant, not needing user has the relevant knowledges such as voice and the knowledge mapping of profession, reduces the threshold of voice assistant customization.
Description
Technical field
The present invention relates to field of artificial intelligence more particularly to a kind of methods for constructing voice assistant.
Background technique
In interactive system, the tissue of knowledge is a very complicated thing.Firstly, user does not know about nature language
Speech understanding, dialogue management and cognitive science, this quite abstruse in artificial intelligence field complicated subject and technology.But
The system of human-computer dialogue management at present, the knowledge organization provided need to carry out the tissue of knowledge according to discipline background.
Fig. 1 is that the knowledge organization management for creating voice assistant that a domestic well-known voice company provides the user with is flat
Platform has been related to " entity ", " dimension ", " main fields ", " from field ", the relevant profession name with particular technology area such as " resource "
Word, using the user of this platform, if not knowing about relevant technical background, it is very difficult to understand these vocabulary, the door used
Sill are very high.
Summary of the invention
The embodiment of the present invention provides a kind of method for constructing voice assistant, at least solving one of above-mentioned technical problem.
In a first aspect, the embodiment of the present invention provides a kind of method for constructing voice assistant, comprising:
The request of voice assistant is created in response to user, is generated voice assistant and is created interface, the voice assistant creates boundary
It include multiple information solicitation projects for user's selection in face;
When detecting the selection operation of user, determine that the information solicitation project for corresponding to the selection operation is target item
Mesh;
It generates for guiding user to fill in the information solicitation interface of project information associated with the destination item;
Knowledge mapping is generated according to the project information that user is filled under the information solicitation interface, to be used for institute's predicate
Sound assistant realizes human-computer dialogue service.
Second aspect, the embodiment of the present invention provide a kind of storage medium, are stored with one or more in the storage medium
Including the program executed instruction, it is described execute instruction can by electronic equipment (including but not limited to computer, server, or
Network equipment etc.) it reads and executes, in the method for executing any of the above-described building voice assistant of the present invention.
The third aspect provides a kind of electronic equipment comprising: at least one processor, and with described at least one
Manage the memory of device communication connection, wherein the memory is stored with the instruction that can be executed by least one described processor, institute
It states instruction to be executed by least one described processor, so that at least one described processor is able to carry out any of the above-described of the present invention
The method for constructing voice assistant.
Fourth aspect, the embodiment of the present invention also provide a kind of computer program product, and the computer program product includes
The computer program of storage on a storage medium, the computer program includes program instruction, when described program instruction is calculated
When machine executes, the computer is made to execute the method that any of the above-described constructs voice assistant.
The beneficial effect of the embodiment of the present invention is: user can carry out determining for voice assistant based on method of the invention
System, and only need to fill according to the creation interface successively showed in the present invention certainly in the customization procedure for carrying out voice assistant
Relevant item information known to oneself greatly simplifies the customization work of voice assistant, and not needing user has profession
Voice and the relevant knowledges such as knowledge mapping, reduce the threshold of voice assistant customization.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, for this field
For those of ordinary skill, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the schematic diagram for managing platform for creating the knowledge organization of voice assistant in the prior art;
Fig. 2 is the flow chart of an embodiment of the method for the semantic assistant of building of the invention;
Fig. 3 is first schematic diagram at the meeting affairs assistant creation interface in the present invention;
Fig. 4 is second schematic diagram at the meeting affairs assistant creation interface in the present invention;
Fig. 5 is the third schematic diagram at the meeting affairs assistant creation interface in the present invention;
Fig. 6 is the schematic diagram that knowledge point involved in voice assistant to be created is organized in the present invention;
Fig. 7 is the logical relation schematic diagram determined between knowledge point involved by meeting affairs assistant in the present invention;
Fig. 8 is to be related to the schematic diagram that knowledge point carries out tissue to meeting affairs assistant in the present invention;
Fig. 9 is the structural schematic diagram of an embodiment of electronic equipment of the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.
The present invention can describe in the general context of computer-executable instructions executed by a computer, such as program
Module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, programs, objects, member
Part, data structure etc..The present invention can also be practiced in a distributed computing environment, in these distributed computing environments, by
Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage equipment.
In the present invention, the fingers such as " module ", " device ", " system " are applied to the related entities of computer, such as hardware, hardware
Combination, software or software in execution with software etc..In detail, for example, element can with but be not limited to run on processing
Process, processor, object, executable element, execution thread, program and/or the computer of device.In addition, running on server
Application program or shell script, server can be element.One or more elements can be in the process and/or thread of execution
In, and element can be localized and/or be distributed between two or multiple stage computers on one computer, and can be by each
Kind computer-readable medium operation.Element can also according to the signal with one or more data packets, for example, from one with
Another element interacts in local system, distributed system, and/or the network in internet passes through signal and other system interactions
The signals of data communicated by locally and/or remotely process.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise", not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence " including ... ", it is not excluded that including described want
There is also other identical elements in the process, method, article or equipment of element.
The problems of in the prior art for solution, the present invention provides a kind of method for constructing voice assistant.It is exemplary
Ground, using voice assistant constructed by this method can for meeting affairs assistant, market assistant, customer service assistant etc., the present invention to this not
It limits.The following are of the invention convenient for clearer introductions, it is used uniformly for meeting affairs assistant and illustrates, meeting is raised
The side of doing can carry out the customization of meeting affairs assistant based on method of the invention, and only need in the customization procedure for carrying out meeting affairs assistant
The meeting relevant information known to oneself is filled according to the creation interface successively showed in the present invention, greatly simplified
The customization work of meeting affairs assistants, not needing user has the relevant knowledges such as voice and the knowledge mapping of profession, reduces language
The threshold of sound assistant customization.
As shown in Fig. 2, the embodiment of the present invention provides a kind of method for constructing voice assistant, comprising:
S10, the request that voice assistant is created in response to user generate voice assistant and create interface, the voice assistant wound
Building includes the multiple information solicitation projects selected for user in interface.
Illustratively, between the multiple information solicitation project multiple knowledge points according to involved in the voice assistant
Logical relation determines that the logical relation includes at least coordination and/or subordinate relation.
As shown in figure 3, illustratively, voice assistant is presented as meeting affairs assistant, and for user, in creation, the meeting affairs help the present invention
Creation interface is provided when hand, includes conferencing information, object of attending a meeting, ticket information, contact method, assistant under the creation interface
Multiple information solicitation projects such as image, other information, built-in technical ability.User only needs successively to click each information solicitation project,
And filling in for corresponding information is carried out according to the prompt of expansion content.
For a meeting, object of attending a meeting, ticket information, contact method, patrolling between these vivid information of assistant
The relationship of collecting is relationship arranged side by side, needs to be shown presentation to personnel participating in the meeting in parallel.Therefore, the present invention is in the form of a list
These information the displaying of flush system is subjected to, in order to which user intuitively checks and carries out the operation step of voice assistant creation
Suddenly.
S20, when detecting the selection operation of user, determine correspond to the selection operation information solicitation project be mesh
Mark project.Illustratively, for meeting affairs assistant, user can successively click selection conferencing information, object of attending a meeting, ticket information,
Multiple information solicitation projects such as contact method, assistant's image, other information, built-in technical ability carry out information solicitation, to input creation
Relevant information required for meeting affairs assistant.
S30, it generates for guiding user to fill in the information solicitation interface of project information associated with the destination item.
S40, knowledge mapping is generated according to the project information that user is filled under the information solicitation interface, to be used for institute
It states voice assistant and realizes human-computer dialogue service.
Illustratively, the project information associated with destination item includes at least one to fill message.Work as user
Selected target project and after carrying out clicking operation, destination item can also further spread out the correlation for needing user further to fill in
Content is guided, the content for needing to fill in can be contained only in the next stage of the destination item, also can wrap containing multinomial
Need the content that user fills in.
It include the prompt text and information input frame that guidance user fills in preset information on the information solicitation interface.Information
User Interface can be to be presented in the form of a list, for guiding user to fill in relevant information.
As shown in figure 4, illustratively, when the user clicks after this project of conferencing information, the boundary that is presented to the user
Face further comprises meeting title, session topic, meeting brief introduction, movable date, master under interface display conferencing information project
Multiple items such as unit and movable address are done to fill message.It is filled out as it can be seen that further comprising next stage needs under conferencing information
The content write.User only needs to fill in and submit item by item under the interface.
User can carry out the customization of voice assistant based on method of the invention, and in the customization for carrying out voice assistant
Only need to fill in the relevant item information known to oneself, pole in journey in the present invention according to the creation interface successively showed
The big customization work for simplifying voice assistant, not needing user has the relevant knowledges such as voice and the knowledge mapping of profession,
Reduce the threshold of voice assistant customization.
In some embodiments of the method for building voice assistant in the present invention, in voice assistant creation interface also
It include built-in technical ability setting label (as shown in Figure 3), for guiding user based on the behaviour to the built-in technical ability setting label
As the voice assistant, voice technical ability is set.
It can as shown in figure 5, can be presented to the user in the form of a list after user has carried out built-in technical ability setting label
Multiple built-in voice technical ability of selection, user can the function of the extension according to required for current creation voice assistant select needs
The voice technical ability of addition.
The mode that label is arranged in setting voice technical ability in voice assistant creation interface in this law inventive embodiments can be so as to
It is the voice technical ability of the additional addition perfect in shape and function of customized voice assistant in user when carrying out voice assistant customization, with
The function of customized voice assistant is extended rapidly.
In some embodiments, the method for building voice assistant of the invention further include: according to user in creation institute's predicate
The project information filled in during sound assistant generates knowledge mapping, and the knowledge mapping realizes people for the voice assistant
Machine dialogue service.
As shown in fig. 6, for the schematic diagram for organizing knowledge point involved in voice assistant to be created in the present invention.It is exemplary
Ground divides knowledge point according to topic, and according to the logical relation (for example, coordination and subordinate relation) between topic
Construct topic tree.For example, knowledge based point defines topic A, topic B, topic C, topic E, topic F, topic G.Wherein, it talks about
A rank highest is inscribed, subordinate topic is the topic B and C of coordination, and topic E, F and G are the words arranged side by side of next stage (sub-topic)
Topic, and topic E is subordinated to topic B, and topic F and G are subordinated to topic C respectively.The present invention be based on it is above it is constructed if
Logical relation in topic tree between each topic creates interface come the voice assistant constructed.
After receiving user and creating the information that interface is filled in by voice assistant, convert the information filled in
The structure of knowledge of knowledge mapping to be generated, and question and answer pair preset for each of knowledge mapping node, for man-machine right
Words.
Topic catalogue carries out different preset according to the attributes of different templates.It can be with preset knowledge card under each topic
Piece (entity of knowledge mapping), can also be with preset Rich Media's knowledge question pair.The structure of knowledge is the table structure of knowledge mapping, different
Template have the different structures of knowledge.Template further includes the list of a variety of built-in technical ability, is selected for user.The dialog strategy of template
It is configured according to the type of different templates, user is invisible.Creation content of template itself is sightless to user.User
It is seen that using the icon and operation instruction of this template.
As shown in fig. 7, to determine the logical relation schematic diagram between knowledge point involved by meeting affairs assistant in the present invention, wherein
Including meeting essential information, ticket session, conference object, conference service and other, wherein next rank of meeting essential information
Including at least conferencing information, the next stage of conferencing information include at least meeting title, meeting brief introduction, schedule, hold the time,
Host place and hold unit;The next stage of ticket session includes ticket information;Object of attending a meeting includes guest and public affairs of attending a meeting
Department;Conference service includes food and beverage sevice, accommodation service, network service and service calls.
As shown in figure 8, to be related to the schematic diagram that knowledge point carries out tissue, organizational form performance to meeting affairs assistant in the present invention
For card field table shown in Fig. 8, field name, field English name, field type, field are contained in the card field table
The projects such as label, feedback recommendation, field status and operation.
In some embodiments, knowledge graph is generated according to the project information that user is filled under the information solicitation interface
Spectrum, to realize that human-computer dialogue service includes: for the voice assistant
Corresponding field name is determined according to the filled in project information;
Determine the field type of the field name;
Determine field label belonging to the field name;
According to the field name, multiple test orders, the rhetorical question way of recommendation and field status are set;
According at least to the field name, field type, field label, rhetorical question physical examination mode, field status and test rule
Then generate card field;
The knowledge mapping is generated according to the card field.
Wherein, the title of the projects for needing user to fill in is filled in field name project, in field English name project
English name is filled in accordingly;
There are many field types, for example, Relarr, character string, image, date enumerate.What Relarr was represented is association
Entity attribute: i.e. an entity can become the relating attribute of another entity.These fields are used to define the class of an entity
Type.Citing: corresponding field name " welcome guest " is Yao Ming, then Yao Ming is a people entities, and the type of the entity is personage, people
It include many fields: height, weight, hobby, previous graduate college, career field etc. in species type.
Field label, synonym or similar set of words as field.For example, this field of personage, in field label
Content is the scale of construction.The effect of field label is that equivalent in meaning or similar field is merged into an effective field, prevents to know
Know the explosive extension of structure.
The content that rhetorical question is recommended includes various ways: having the recommendation based on other knowledge points in the same topic, also has
Recommendation based on other fields in a knowledge card.Citing:
Client: how many how many years births of the boss of XX company?
Robot: the president and CEOXXX of XX company are born in 1974;
Do robot: you want to understand his hobby?
Here rhetorical question is the inner field of knowledge based card (personage's card) (field is hobby).
The state of field mainly includes: it uses, disables, test.Wherein, using show this field work normally;Test
Non- ready state is in this field of the state surface of disabling.
Test order refers to that each field has corresponding way to put questions.Such as: the field " weight " of personage's card, its survey
Examination rule are as follows:
Does is so-and-so weight how many?
Does so-and-so have multiple?
It can be preset multiple question and answer pair in each of knowledge mapping topic node by the customization of test order.
In some embodiments, rhetorical question scheduling strategy is recommended in the dialogue for including in meeting affairs template.Meeting affairs template implies vertical
To Generalization bounds: the strategy is stronger suitable for knowledge point level, and the not strong scene of relevance between level is hit a certain topic and known
Know point, knowledge point can be chosen from hit topic itself, sub-topic and carry out recommendation rhetorical question.
Method provided by the invention, the Interface Microstructure knowledge based on template and tabular simplify user and carry out knowledge organization
Complexity, improve the experience of user.The present invention is directed to the Method of Knowledge Organization in the vertical field of conversational system, each vertical
Field is all suitable for.
1. the professional knowledge of conversational system and structure are packaged by the present invention by template.
1.1 encapsulate the concept and structure of knowledge mapping by template, the ontology (ontology) including describing knowledge mapping,
Table structure (schema), the concepts such as attribute (attribute).
1.2 encapsulate the knowledge organization of Multimedia Knowledge question and answer pair by template.
1.3 encapsulate use (Task technical ability, knowledge type technical ability, chat type technical ability, the third party of various technical ability by template
Technical ability).Different template attributes correspond to different skillset encapsulation.
1.4 encapsulate the dialog strategy of conversational system by template.
1.5 are directed to the user demand of enterprise, industry, the structure of knowledge and topic content of preset template.
Encapsulation particular content in 1.6 templates is invisible for user;User is it is seen that the function of template is described, used
Method and operating procedure.
2. the present invention shows the edit operation with the system that engages in the dialogue by table.
1.1 indicate editing interface using the list name of table, attribute, value.
1.2 convert the data exhibiting form of knowledge mapping to the attribute-value format of 1.1 descriptions, such as the meeting in figure Fig. 4
Date.
1.3 convert the data exhibiting form of Rich Media's knowledge question pair to the attribute-value format of 1.1 descriptions.
1.4 by the table name format for showing form and being converted into 1.1 descriptions of the topic of conversational system, such as the meeting in Fig. 3
Object, ticket information etc..
1.5 show the technical ability of template in the form of inventory.
1.6 users need to only pay close attention to the attribute value in filling up a form, and choose the technical ability inventory of oneself needs.Dialogue is asked
The generation of method and answer is completed by template and algorithm service.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Movement merge, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because
According to the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, and related actions and modules is not necessarily of the invention
It is necessary.In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
In some embodiments, the embodiment of the present invention provides a kind of non-volatile computer readable storage medium storing program for executing, described to deposit
Being stored in storage media one or more includes the programs executed instruction, it is described execute instruction can by electronic equipment (including but
It is not limited to computer, server or the network equipment etc.) it reads and executes, for executing any of the above-described building of the present invention
The method of voice assistant.
In some embodiments, the embodiment of the present invention also provides a kind of computer program product, and the computer program produces
Product include the computer program being stored on non-volatile computer readable storage medium storing program for executing, and the computer program includes that program refers to
It enables, when described program instruction is computer-executed, the computer is made to execute the method that any of the above-described constructs voice assistant.
In some embodiments, the embodiment of the present invention also provides a kind of electronic equipment comprising: at least one processor,
And the memory being connect at least one described processor communication, wherein the memory is stored with can be by described at least one
The instruction that a processor executes, described instruction is executed by least one described processor, so that at least one described processor energy
Enough methods for executing building voice assistant.
In some embodiments, the embodiment of the present invention also provides a kind of storage medium, is stored thereon with computer program,
It is characterized in that, the method for voice assistant is constructed when which is executed by processor.
Fig. 9 is the hardware configuration of the electronic equipment of the method for the execution building voice assistant that another embodiment of the application provides
Schematic diagram, as shown in figure 9, the equipment includes:
One or more processors 910 and memory 920, in Fig. 9 by taking a processor 910 as an example.
The equipment for executing the method for building voice assistant can also include: input unit 930 and output device 940.
Processor 910, memory 920, input unit 930 and output device 940 can pass through bus or other modes
It connects, in Fig. 9 for being connected by bus.
Memory 920 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module, the method such as the building voice assistant in the embodiment of the present application are corresponding
Program instruction/module.Processor 910 by operation be stored in memory 920 non-volatile software program, instruction and
Module, thereby executing the various function application and data processing of server, i.e. realization above method embodiment building voice helps
The method of hand.
Memory 920 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function;Storage data area can store the use of the device according to building voice assistant
The data etc. created.In addition, memory 920 may include high-speed random access memory, it can also include non-volatile deposit
Reservoir, for example, at least a disk memory, flush memory device or other non-volatile solid state memory parts.In some implementations
In example, optional memory 920 includes the memory remotely located relative to processor 910, these remote memories can pass through
Network connection extremely constructs the device of voice assistant.The example of above-mentioned network includes but is not limited to internet, intranet, local
Net, mobile radio communication and combinations thereof.
Input unit 930 can receive the number or character information of input, and generate and the device of building voice assistant
User setting and the related signal of function control.Output device 940 may include that display screen etc. shows equipment.
One or more of modules are stored in the memory 920, when by one or more of processors
910 when executing, the method that executes the building voice assistant in above-mentioned any means embodiment.
Method provided by the embodiment of the present application can be performed in the said goods, has the corresponding functional module of execution method and has
Beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to method provided by the embodiment of the present application.
The electronic equipment of the embodiment of the present application exists in a variety of forms, including but not limited to:
(1) mobile communication equipment: the characteristics of this kind of equipment is that have mobile communication function, and to provide speech, data
Communication is main target.This Terminal Type includes: smart phone (such as iPhone), multimedia handset, functional mobile phone and low
Hold mobile phone etc..
(2) super mobile personal computer equipment: this kind of equipment belongs to the scope of personal computer, there is calculating and processing function
Can, generally also have mobile Internet access characteristic.This Terminal Type includes: PDA, MID and UMPC equipment etc., such as iPad.
(3) portable entertainment device: this kind of equipment can show and play multimedia content.Such equipment include: audio,
Video player (such as iPod), handheld device, e-book and intelligent toy and portable car-mounted navigation equipment.
(4) server: providing the equipment of the service of calculating, and the composition of server includes that processor, hard disk, memory, system are total
Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, in processing energy
Power, stability, reliability, safety, scalability, manageability etc. are more demanding.
(5) other electronic devices with data interaction function.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, above-mentioned technology
Scheme substantially in other words can be embodied in the form of software products the part that the relevant technologies contribute, the computer
Software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions to
So that computer equipment (can be personal computer, server or the network equipment etc.) execute each embodiment or
Method described in certain parts of embodiment.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations;Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (8)
1. a kind of method for constructing voice assistant, comprising:
The request of voice assistant is created in response to user, is generated voice assistant and is created interface, the voice assistant creates in interface
It include multiple information solicitation projects for user's selection;
When detecting the selection operation of user, determine that the information solicitation project for corresponding to the selection operation is destination item;
It generates for guiding user to fill in the information solicitation interface of project information associated with the destination item;
Knowledge mapping is generated according to the project information that user is filled under the information solicitation interface, to help for the voice
Hand realizes human-computer dialogue service.
2. according to the method described in claim 1, wherein, being believed according to the project that user is filled under the information solicitation interface
Breath generates knowledge mapping, to realize that human-computer dialogue service includes: for the voice assistant
Corresponding field name is determined according to the filled in project information;
Determine field type, the field label of the field name;
According to the field name, multiple test orders, the rhetorical question way of recommendation and field status are set;
It is raw according at least to the field name, field type, field label, rhetorical question physical examination mode, field status and test order
At card field;
The knowledge mapping is generated according to the card field, to realize human-computer dialogue service for the voice assistant.
3. according to the method described in claim 1, wherein, the multiple information solicitation project is according to involved by the voice assistant
Multiple knowledge points between logical relation determine, the logical relation include at least coordination and/or subordinate relation.
4. according to the method described in claim 1, wherein, the project information associated with destination item includes at least one
To fill message.
5. according to the method described in claim 1, wherein, further includes: the voice assistant creation also includes voice in interface
Label is arranged in technical ability, for guiding user that language is arranged for the voice assistant based on the operation to the built-in technical ability setting label
Sound technical ability.
6. according to the method described in claim 1, wherein, on the information solicitation interface including that guidance user fills in preset information
Prompt text and information input frame.
7. a kind of electronic equipment comprising: at least one processor, and deposited with what at least one described processor communication was connect
Reservoir, wherein the memory be stored with can by least one described processor execute instruction, described instruction by it is described at least
One processor executes, so that at least one described processor is able to carry out any one of claim 1-6 the method
Step.
8. a kind of storage medium, is stored thereon with computer program, which is characterized in that realize power when the program is executed by processor
Benefit requires the step of any one of 1-6 the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910162756.9A CN109948151A (en) | 2019-03-05 | 2019-03-05 | The method for constructing voice assistant |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910162756.9A CN109948151A (en) | 2019-03-05 | 2019-03-05 | The method for constructing voice assistant |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109948151A true CN109948151A (en) | 2019-06-28 |
Family
ID=67009145
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910162756.9A Pending CN109948151A (en) | 2019-03-05 | 2019-03-05 | The method for constructing voice assistant |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109948151A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110472095A (en) * | 2019-08-16 | 2019-11-19 | 百度在线网络技术(北京)有限公司 | Voice guide method, apparatus, equipment and medium |
CN110570866A (en) * | 2019-09-11 | 2019-12-13 | 百度在线网络技术(北京)有限公司 | Voice skill creating method, device, electronic equipment and medium |
CN110990582A (en) * | 2019-11-21 | 2020-04-10 | 北京明略软件系统有限公司 | Method, device, computer storage medium and terminal for realizing transaction processing |
CN111081220A (en) * | 2019-12-10 | 2020-04-28 | 广州小鹏汽车科技有限公司 | Vehicle-mounted voice interaction method, full-duplex dialogue system, server and storage medium |
CN112328876A (en) * | 2020-11-03 | 2021-02-05 | 平安科技(深圳)有限公司 | Electronic card generation and pushing method and device based on knowledge graph |
CN114385285A (en) * | 2021-11-30 | 2022-04-22 | 重庆长安汽车股份有限公司 | Image creating method based on automobile AI intelligent assistant |
CN115202539A (en) * | 2022-06-30 | 2022-10-18 | 北京明略昭辉科技有限公司 | Recording generation method, recording generation device, storage medium, and electronic apparatus |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN108874915A (en) * | 2018-05-30 | 2018-11-23 | 苏州思必驰信息科技有限公司 | Method of Knowledge Organization, system, electronic equipment and storage medium |
CN109325097A (en) * | 2018-07-13 | 2019-02-12 | 海信集团有限公司 | A kind of voice guide method and device, electronic equipment, storage medium |
-
2019
- 2019-03-05 CN CN201910162756.9A patent/CN109948151A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN108874915A (en) * | 2018-05-30 | 2018-11-23 | 苏州思必驰信息科技有限公司 | Method of Knowledge Organization, system, electronic equipment and storage medium |
CN109325097A (en) * | 2018-07-13 | 2019-02-12 | 海信集团有限公司 | A kind of voice guide method and device, electronic equipment, storage medium |
Non-Patent Citations (1)
Title |
---|
《中国索引》编辑部编: "《快速城镇化背景下的群体性突发事件预警与阻断机制研究》", pages: 179 - 180 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110472095A (en) * | 2019-08-16 | 2019-11-19 | 百度在线网络技术(北京)有限公司 | Voice guide method, apparatus, equipment and medium |
CN110472095B (en) * | 2019-08-16 | 2023-03-10 | 百度在线网络技术(北京)有限公司 | Voice guidance method, device, equipment and medium |
CN110570866A (en) * | 2019-09-11 | 2019-12-13 | 百度在线网络技术(北京)有限公司 | Voice skill creating method, device, electronic equipment and medium |
CN110990582A (en) * | 2019-11-21 | 2020-04-10 | 北京明略软件系统有限公司 | Method, device, computer storage medium and terminal for realizing transaction processing |
CN111081220A (en) * | 2019-12-10 | 2020-04-28 | 广州小鹏汽车科技有限公司 | Vehicle-mounted voice interaction method, full-duplex dialogue system, server and storage medium |
CN111081220B (en) * | 2019-12-10 | 2022-08-16 | 广州小鹏汽车科技有限公司 | Vehicle-mounted voice interaction method, full-duplex dialogue system, server and storage medium |
CN112328876A (en) * | 2020-11-03 | 2021-02-05 | 平安科技(深圳)有限公司 | Electronic card generation and pushing method and device based on knowledge graph |
CN112328876B (en) * | 2020-11-03 | 2023-08-11 | 平安科技(深圳)有限公司 | Electronic card generation pushing method and device based on knowledge graph |
CN114385285A (en) * | 2021-11-30 | 2022-04-22 | 重庆长安汽车股份有限公司 | Image creating method based on automobile AI intelligent assistant |
CN114385285B (en) * | 2021-11-30 | 2024-02-06 | 重庆长安汽车股份有限公司 | Image creation method based on automobile AI intelligent assistant |
CN115202539A (en) * | 2022-06-30 | 2022-10-18 | 北京明略昭辉科技有限公司 | Recording generation method, recording generation device, storage medium, and electronic apparatus |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109948151A (en) | The method for constructing voice assistant | |
US11295221B2 (en) | Learning user preferences in a conversational system | |
TW202016693A (en) | Human-computer interaction processing system, method, storage medium and electronic device | |
US20170337261A1 (en) | Decision Making and Planning/Prediction System for Human Intention Resolution | |
US20180090141A1 (en) | Conversational interactions using superbots | |
CN107741976B (en) | Intelligent response method, device, medium and electronic equipment | |
US10860289B2 (en) | Flexible voice-based information retrieval system for virtual assistant | |
CN107040452B (en) | Information processing method and device and computer readable storage medium | |
Lopatovska et al. | User recommendations for intelligent personal assistants | |
CN109313668B (en) | System and method for constructing session understanding system | |
CN107480766B (en) | Method and system for content generation for multi-modal virtual robots | |
JP2021111379A (en) | Method and apparatus for recommending interactive information | |
Garrido et al. | Smart tourist information points by combining agents, semantics and AI techniques | |
CN110199274A (en) | System and method for automating query answer generation | |
CN109643540A (en) | System and method for artificial intelligent voice evolution | |
JP7488871B2 (en) | Dialogue recommendation method, device, electronic device, storage medium, and computer program | |
Wilks et al. | A prototype for a conversational companion for reminiscing about images | |
CN110008326A (en) | Knowledge abstraction generating method and system in conversational system | |
CN110427459A (en) | Visualized generation method, system and the platform of speech recognition network | |
Sabharwal et al. | Developing Cognitive Bots Using the IBM Watson Engine: Practical, Hands-on Guide to Developing Complex Cognitive Bots Using the IBM Watson Platform | |
CN111159382A (en) | Method and device for constructing and using session system knowledge model | |
CN112069830A (en) | Intelligent conversation method and device | |
CN110442698A (en) | Conversation content generation method and system | |
DE102023102142A1 (en) | CONVERSATIONAL AI PLATFORM WITH EXTRAACTIVE QUESTION ANSWER | |
Mauny et al. | A prototype of smart virtual assistant integrated with automation |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant after: Sipic Technology Co.,Ltd. Address before: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant before: AI SPEECH Ltd. |