CN110008326A - Knowledge abstraction generating method and system in conversational system - Google Patents
Knowledge abstraction generating method and system in conversational system Download PDFInfo
- Publication number
- CN110008326A CN110008326A CN201910255435.3A CN201910255435A CN110008326A CN 110008326 A CN110008326 A CN 110008326A CN 201910255435 A CN201910255435 A CN 201910255435A CN 110008326 A CN110008326 A CN 110008326A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- knowledge point
- session
- theme
- abstract
- 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
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention discloses knowledge abstraction generating method and system in a kind of conversational system, which comprises building knowledge organization structure in advance, the knowledge organization structure includes theme map and knowledge point map；Record user's session theme involved in conversation procedure and multiple session knowledge points；The knowledge abstract is at least generated based on the theme and the multiple session knowledge point.It is used for the generation of knowledge abstract by constructing main body map and knowledge point map in advance in the present invention, so that the abstract form generated is structured text, the abstract granularity of generation to be knowledge point grade, is easy to use by users and automatically analyzes on a large scale.
Description
Technical field
The present invention relates to the knowledge abstraction generating methods in field of artificial intelligence more particularly to a kind of conversational system
And system.
Background technique
Prior art or the main abstraction generating method of product are mostly based on text snippet model at present, i.e., by user's meeting
Words are divided into several conversation groups, and each conversation group includes multiple sentences, then utilize topic model, Subject Clustering, neural network skill
Art is automatically generated text snippet or is extracted important combination of sentences from text using information extraction technique into abstract.Therefore it passes
The method that system technology utilizes text snippet, the abstract form of generation is non-structured text, lacks structural information；What is generated plucks
Wanting granularity is chapter, paragraph or Sentence-level, rather than knowledge point grade, thus is unfavorable for the use of user and automatic point extensive
Analysis.
Summary of the invention
The embodiment of the present invention provides knowledge abstraction generating method and system in a kind of conversational system, at least solving
One of above-mentioned technical problem.
In a first aspect, the embodiment of the present invention provides the knowledge abstraction generating method in a kind of conversational system, comprising:
Building knowledge organization structure in advance, the knowledge organization structure includes theme map and knowledge point map；
Record user's session theme involved in conversation procedure and multiple session knowledge points；
The knowledge abstract is at least generated based on the theme and the multiple session knowledge point.
Second aspect, the embodiment of the present invention provide the knowledge summarization generation system in a kind of conversational system, comprising:
Map construction program module, for constructing knowledge organization structure in advance, the knowledge organization structure includes thematic map
Spectrum and knowledge point map；
Logging program module, for recording user's session theme involved in conversation procedure and multiple session knowledge
Point；
Summarization generation program module is known described in the theme and the generation of the multiple session knowledge point for being at least based on
Know abstract.
The third 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, for executing the knowledge summarization generation side in any of the above-described conversational system of the present invention
Method.
Fourth 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,
Described instruction is executed by least one described processor, so that at least one described processor is able to carry out above-mentioned of the present invention
Knowledge abstraction generating method in one conversational system.
5th 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 knowledge abstraction generating method in any of the above-described conversational system.
The beneficial effect of the embodiment of the present invention is: by constructing main body map and knowledge point map in advance in the present invention
For the generation of knowledge abstract, so that the abstract form generated is structured text, the abstract granularity of generation is knowledge point grade,
It is easy to use by users and automatically analyzes on a large scale.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, making required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, for this
For the those of ordinary skill of field, without creative efforts, it can also be obtained according to these attached drawings others
Attached drawing.
Fig. 1 is the flow chart of an embodiment of the knowledge abstraction generating method in conversational system of the invention；
Fig. 2 is the flow chart of another embodiment of the knowledge abstraction generating method in conversational system of the invention；
Fig. 3 is the flow chart of the another embodiment of the knowledge abstraction generating method in conversational system of the invention；
Fig. 4 is knowledge point path schematic diagram in the conversation procedure in the embodiment of the present invention；
Fig. 5 is the schematic diagram of the knowledge abstract visualized graphs form in the embodiment of the present invention；
Fig. 6 is the institutional framework schematic diagram of the theme and knowledge point in the embodiment of the present invention；
The schematic diagram of relationship of the Fig. 7 between theme in the theme map in the embodiment of the present invention；
Fig. 8 is the relationship signal between the node of theme map and the node of knowledge point map in the embodiment of the present invention
Figure；
Fig. 9 be the embodiment of the present invention in knowledge point map in relation between knowledge points schematic diagram；
Figure 10 is the functional block diagram of an embodiment of the knowledge summarization generation system in conversational system of the invention；
Figure 11 is the functional block diagram of another embodiment of the knowledge summarization generation system in the conversational system in the present invention；
Figure 12 is the functional block diagram of an embodiment of the extender module in the present invention；
Figure 13 is the functional block diagram of another embodiment of the knowledge summarization generation system in the conversational system in the present invention；
Figure 14 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, ordinary skill people
Member's 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 journey
Sequence module.Generally, program module include routines performing specific tasks or implementing specific abstract data types, it is program, right
As, element, data structure etc..The present invention can also be practiced in a distributed computing environment, in these distributed computing environment
In, by executing task by the connected remote processing devices of communication network.In a distributed computing environment, program mould
Block can be located 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, firmly
Combination, software or software in execution of part and software etc..In detail, for example, element can with but be not limited to run on
Process, processor, object, executable element, execution thread, program and/or the computer of processor.In addition, running on service
Application program or shell script, server on device can be elements.One or more elements can execution process and/
Or in thread, and element can be localized and/or be distributed between two or multiple stage computers on one computer, and
It can be run by various computer-readable mediums.Element can also according to the signal with one or more data packets, for example,
Interacted from one with another element in local system, distributed system, and/or internet network by signal with
The signal of the data of other system interactions is 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 are used merely to
Distinguish one entity or operation from another entity or operation, without necessarily requiring or implying these entities or
There are any actual relationship or orders between operation.Moreover, the terms "include", "comprise", are not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence " including ... ", it is not excluded that wrapping
Include in the process, method, article or equipment of the element that there is also other identical elements.
This patent wishes to construct a kind of structuring, knowledge point granularity, the knowledge method of abstracting and dress of expansible extension
It sets.Topicalization tissue and fine granularity are carried out to the knowledge point in conversational system first, establish the pass between theme, knowledge point
Connection relationship and strength of association.It is then based on the institutional framework of theme and knowledge point in conversational system, in combination with user in session
The knowledge point referred in the process and correlated knowledge point, the automatic knowledge abstract for constructing user, and carrying out to knowledge abstract can
Depending on changing, summarizes and arrange to complete more efficient knowledge, improve the efficiency that user obtains knowledge, improve user satisfaction.
As shown in Figure 1, the embodiment of the present invention provides the knowledge abstraction generating method in a kind of conversational system, comprising:
S11, in advance building knowledge organization structure, the knowledge organization structure includes theme map and knowledge point map；
S12, record user's session theme involved in conversation procedure and multiple session knowledge points；
S13, the session theme and the multiple session knowledge point generation knowledge abstract are at least based on.
It is used for the generation of knowledge abstract by constructing main body map and knowledge point map in advance in the embodiment of the present invention, from
And the abstract form generated is structured text, the abstract granularity of generation is knowledge point grade, is easy to use by users and on a large scale
It automatically analyzes.
In some embodiments, the knowledge abstraction generating method in conversational system of the invention further include: known according to described
The strength of association known between knowledge point and the multiple session knowledge point in point map determines multiple extension knowledge points；
Described includes: at least base based on the session theme and the multiple session knowledge point generation knowledge abstract
The knowledge abstract is generated in the session theme, the multiple session knowledge point and the multiple extension knowledge point.
As shown in Fig. 2, in some embodiments, the knowledge point according in the knowledge point map with it is the multiple
Strength of association between session knowledge point determines that multiple extension knowledge points include:
S21, the last n session knowledge point jumped in path that the multiple session knowledge point is constituted is chosen；
S22, the neighbour knowledge point for calculating each knowledge point Ki (0 < i < n) and Ki in the last n session knowledge point
The strength of association of set, the knowledge point that it is 1 with Ki distance that neighbour's knowledge point set, which takes, calculating formula of similarity are as follows:
Sim (Ki, Kj)=e-λtS (Ki, Kj) D (Ki, Kj), i ≠ j, j ∈ Set (Ki) (1)
In formula (1), the neighbour's knowledge point set for the knowledge point Ki that Set (Ki) expression knowledge point path is i, Sim (Ki,
Kj) be Ki and Kj strength of association；e-λtFor time decay factor, t=n-i, the last one knowledge point i=n, t=on path
N-i=0；S (Ki, Kj) is the static association intensity of Ki and Kj, and D (Ki, Kj) dynamically associates intensity for Ki's and Kj；
S23, the preceding k knowledge point for taking strength of association big are as the multiple extension knowledge point.
This patent and prior art have 4 main distinctions:
First: the form of knowledge abstract is structuring；
Second: the granularity of knowledge abstract is in knowledge point grade；
Third: knowledge abstract not only includes the knowledge point in session, and does necessary extension and expansion according to knowledge point
Exhibition；
4th: knowledge, which is made a summary, can carry out the visualization of theme and knowledge point level.
As shown in figure 3, the process of another embodiment for the knowledge abstraction generating method in conversational system of the invention
Figure, comprising the following steps:
The institutional framework and dynamic of step 1. theme and knowledge point update.Knowledge organization structure includes master in conversational system
It inscribes map and knowledge point map, the node of theme map is theme, relationship includes set membership, brotherhood etc.；Knowledge point diagram
The node of spectrum include be not limited to knowledge triple or question and answer pair, also include his form knowledge point, such as<problem, operating procedure>
Deng.Knowledge organization structure includes relationship and relationship strength.
Step 2. initial knowledge summarization generation.In user and conversational system interactive process, master involved in user conversation
Topic and knowledge point can make marks in theme map and knowledge point map.After one conversation end, the knowledge point of label is as just
Beginning knowledge abstract.
Illustratively, path of the knowledge point referred in conversation procedure in theme map and knowledge point map, as just
Beginning knowledge abstract.As shown in figure 4, user starts to have chatted in conversation procedure knowledge point<S1, P1, O1>,<Q1 is then branched to,
A1>, finally jump to<S2, P2, O2>.So initial knowledge abstract for [<S1, P1, O1>,<Q1, A1>,<S2, P2, O2>].
Step 3. is made a summary based on the knowledge of theme and the knowledge point degree of correlation to be extended.It is closed according to the association of theme and knowledge point
System carries out necessary extension to initial knowledge abstract.
Illustratively, the matching of theme map and knowledge point map considers static association intensity, dynamically associates intensity simultaneously
With the path position of knowledge point knowledge point in conversation procedure.Select the last n knowledge in knowledge point path in conversation procedure
Point, n are a hyper parameters, be can be set.For example user has 10 from the knowledge point that the dialogue of rigid start and ending is related to, then n
3 can be taken.Calculate the strength of association of neighbour's knowledge point set of each knowledge point Ki (0 < i < n) and Ki, neighbour's knowledge point set
The knowledge point for being 1 with Ki distance can be taken by closing, and calculating formula of similarity is as follows:
Sim (Ki, Kj)=e-λtS (Ki, Kj) D (Ki, Kj), i ≠ j, j ∈ Set (Ki) (1)
The neighbour's knowledge point set for the knowledge point Ki that Set (Ki) expression knowledge point path is i in formula (1), Sim (Ki,
Kj) be Ki and Kj strength of association.
e-λtFor time decay factor, t=n-i, the last one knowledge point i=n, t=n-i=0 on path.
S (Ki, Kj) is the static association intensity of Ki and Kj, and D (Ki, Kj) dynamically associates intensity for Ki's and Kj.
The preceding k knowledge point for taking strength of association big is made a summary as knowledge point to be extended, and k is also hyper parameter, can be preset.
The visualization of step 4. knowledge abstract visualizes the knowledge abstract that step 3 constructs.
In some embodiments, the knowledge abstraction generating method in conversational system of the invention further include: by the knowledge
Abstract is visualized, and described visualize includes form (such as the following table 1) and/or graphic form (such as Fig. 5 institute
Show).
1 table of table visualizes example
The step 1-4 in above-described embodiment is further illustrated by respectively below:
For step 1, as shown in fig. 6, for the institutional framework schematic diagram of theme and knowledge point in the embodiment of the present invention.
Wherein, including theme map and knowledge point map, it is introduced in terms of node and relationship two below:
Node definition:
The node of theme map indicates theme, and relationship includes set membership, brotherhood；The node packet of knowledge point map
It includes but is not limited to knowledge triple (hollow node) or question and answer to the knowledge point of (solid node) or other forms.
Triple has 2 kinds of forms<entity, relationship, entities>,<entity, attribute, attribute value>；<entity, relationship, entity>
Such as<China, capital, Beijing>, wherein " China " and " Beijing " respectively indicates entity, " capital " indicates relationship.< entity, attribute,
Attribute value>and such as<China, coastline length, 1.8 ten thousand kms>wherein " China " presentation-entity, " coastline length " expression attribute,
" 1.8 ten thousand km " indicates attribute value.
Question and answer to form be<Q, A>, Q indicate problem, A indicate answer, such as<" please simply introducing China? ", " China
People's republic is located at east Asia, Pacific Ocean west bank " >.
Contextual definition:
As shown in fig. 7, the schematic diagram of the relationship between theme in the theme map in the present invention, illustratively, for
Theme " artificial intelligence " comprising sub-topics " depth learning technology ".
As shown in figure 8, the relationship signal between the node of theme map and the node of knowledge point map in the present invention
Figure.Illustratively, the node of the node of theme map and knowledge point map has inclusion relation, indicates which knowledge theme includes
Point.For example, the node " geography " in theme spectrum contains knowledge point<China in the map of knowledge point, capital, Beijing>.
As shown in figure 9, for the schematic diagram of relation between knowledge points in the knowledge point map in the present invention.Illustratively, ternary
Incidence relation between group and question and answer pair, as included entity " China " in triple, question and answer centering also includes entity " China ",
So triple and question and answer are to the incidence relation of equal value for establishing entity.It further include other kinds of other than incidence relation of equal value
Entity relationship.Construction method are as follows: question and answer are done into entity link to the entity neutralized in triple and find association of equal value, according to three
Entity relationship between tuple constructs the relationship of the entity in triple and the entity of question and answer centering.
Incidence relation between triple: the incidence relation of entity in triple.
It is also relevant between question and answer pair: the incidence relation of question and answer centering entity.
Relationship strength is divided into static relation intensity (as shown in table 2 below) and dynamic relationship intensity (as shown in table 3 below).It is dynamic
State relationship strength, which refers to, relies on conversation procedure adjustment relationship strength.The association of knowledge in the objective world that static relation intensity indicates
Intensity does not change with conversation procedure.
2 static association intensity of table
Table 3 dynamically associates intensity
Illustratively, dynamically associating intensity can be as conversation procedure dynamic updates, and when jumping to B from knowledge point A, A is arrived
B's dynamically associates intensity increase；A, the corresponding thematic relation of B also adjust accordingly simultaneously.The scene that A jumps to B includes using
The knowledge point B is asked after having asked the knowledge point A in family.After user has asked the knowledge point A, the knowledge point B has been asked in reply in conversational system recommendation, and by with
It chooses at family.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a systems
The movement of column merges, 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 also answer
This knows that the embodiments described in the specification are all preferred embodiments, and related actions and modules is not necessarily originally
Necessary to invention.In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, without detailed in some embodiment
The part stated, reference can be made to the related descriptions of other embodiments.
As shown in Figure 10, the embodiment of the present invention also provides the knowledge summarization generation system 100 in a kind of conversational system,
Include:
Map construction program module 110, for constructing knowledge organization structure in advance, the knowledge organization structure includes master
Inscribe map and knowledge point map；
Logging program module 120 is known for recording user's session theme and multiple sessions involved in conversation procedure
Know point；
Summarization generation program module 130, at least based on described in the theme and the generation of the multiple session knowledge point
Knowledge abstract.
It is used for the generation of knowledge abstract by constructing main body map and knowledge point map in advance in the present invention, to generate
Abstract form be structured text, the abstract granularity of generation is knowledge point grade, is easy to use by users and automatic point extensive
Analysis.
As shown in figure 11, in some embodiments, the knowledge summarization generation system 100 in conversational system further include: extension
Program module 140, for strong according to being associated between the knowledge point and the multiple session knowledge point in the knowledge point map
Degree determines multiple extension knowledge points；It is described to be at least based on knowing described in the session theme and the generation of the multiple session knowledge point
Know abstract include: based on the session theme, the multiple session knowledge point and the multiple extension knowledge point generation described in know
Know abstract.
As shown in figure 12, in some embodiments, the extender module 140 includes:
Knowledge point option program unit 141 jumps in path for choose that the multiple session knowledge point constituted
Last n session knowledge point；
Calculation procedure unit 142, for calculating each knowledge point Ki (0 < i < n) in the last n session knowledge point
With the strength of association of neighbour's knowledge point set of Ki, the knowledge point that it is 1 with Ki distance that neighbour's knowledge point set, which takes, similarity meter
It is as follows to calculate formula:
Sim (Ki, Kj)=e-λtS (Ki, Kj) D (Ki, Kj), i ≠ j, j ∈ Set (Ki) (1)
Wherein, Set (Ki) indicates that knowledge point path is neighbour's knowledge point set of the knowledge point Ki of i, and Sim (Ki, Kj) is
The strength of association of Ki and Kj；e-λtFor time decay factor, t=n-i, the last one knowledge point i=n, t=n-i=on path
0；S (Ki, Kj) is the static association intensity of Ki and Kj, and D (Ki, Kj) dynamically associates intensity for Ki's and Kj；
Extender unit 143, the preceding k knowledge point for taking strength of association big is as the multiple extension knowledge point.
As shown in figure 13, in some embodiments, the knowledge summarization generation system 100 in conversational system further include: visual
Change program module 150, for by the knowledge abstract visualize, it is described visualize include form and/
Or graphic form.
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 session of the present invention
Knowledge abstraction generating method in system.
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 program
Instruction makes the computer execute the knowledge in any of the above-described conversational system when described program instruction is computer-executed
Abstraction generating method.
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 execute the knowledge abstraction generating method in conversational system.
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 knowledge abstraction generating method when program is executed by processor in conversational system.
Knowledge summarization generation system in the conversational system of the embodiments of the present invention can be used for executing the embodiment of the present invention
Conversational system in knowledge abstraction generating method, and reach in the realization conversational systems of the embodiments of the present invention accordingly
Knowledge abstraction generating method technical effect achieved, which is not described herein again.At can be by hardware in the embodiment of the present invention
Manage device (hardware processor) Lai Shixian related function module.
Figure 14 is that the electronics of the knowledge abstraction generating method in the execution conversational system that another embodiment of the application provides is set
Standby hardware structural diagram, as shown in figure 14, which includes:
One or more processors 1410 and memory 1420, in Figure 14 by taking a processor 1410 as an example.
The equipment for executing the knowledge abstraction generating method in conversational system can also include: input unit 1430 and output
Device 1440.
Processor 1410, memory 1420, input unit 1430 and output device 1440 can by bus or other
Mode connects, in Figure 14 for being connected by bus.
Memory 1420 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software
Program, non-volatile computer executable program and module, such as the knowledge abstract in the conversational system in the embodiment of the present application
Corresponding program instruction/the module of generation method.Processor 1410 is stored in non-volatile soft in memory 1420 by operation
Part program, instruction and module, thereby executing the various function application and data processing of server, i.e. the realization above method
Knowledge abstraction generating method in embodiment conversational system.
Memory 1420 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 be stored according to the knowledge summarization generation in conversational system
Device uses created data etc..In addition, memory 1420 may include high-speed random access memory, can also wrap
Include nonvolatile memory, for example, at least a disk memory, flush memory device or other non-volatile solid state memories
Part.In some embodiments, it includes the memory remotely located relative to processor 1410 that memory 1420 is optional, these are remote
Journey memory can be by being connected to the network the knowledge summarization generation device into conversational system.The example of above-mentioned network include but
It is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 1430 can receive the number or character information of input, and generates and pluck with the knowledge in conversational system
Want the user setting and the related signal of function control of generating means.Output device 1440 may include that the displays such as display screen are set
It is standby.
One or more of modules are stored in the memory 1420, when by one or more of processing
When device 1410 executes, the knowledge abstraction generating method in the conversational system in above-mentioned any means embodiment is executed.
The said goods can be performed the embodiment of the present application provided by method, have the corresponding functional module of execution method and
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-end 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 includes: sound
Frequently, 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 the unit as illustrated by the separation member
It may or may not be physically separated, component shown as a unit may or may not be physics
Unit, it can it is in one place, or may be distributed over multiple network units.It can select according to the actual needs
Some or all of the modules therein is selected to 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
The mode of general hardware platform can be added to realize by software, naturally it is also possible to pass through hardware.Based on this understanding, above-mentioned
Technical solution substantially in other words can be embodied in the form of software products the part that the relevant technologies contribute, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several
Instruction is used so that computer equipment (can be personal computer, server or the network equipment an etc.) execution is each
Method described in certain parts of embodiment or embodiment.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations；To the greatest extent
Pipe is with reference to the foregoing embodiments described in detail the application, those skilled in the art should understand that: it is still
It is possible to modify the technical solutions described in the foregoing embodiments, or part of technical characteristic is equally replaced
It changes；And these are modified or replaceed, the essence of each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution
Mind and range.
Claims (10)
1. the knowledge abstraction generating method in a kind of conversational system, comprising:
Building knowledge organization structure in advance, the knowledge organization structure includes theme map and knowledge point map；
Record user's session theme involved in conversation procedure and multiple session knowledge points；
The knowledge abstract is at least generated based on the session theme and the multiple session knowledge point.
2. according to the method described in claim 1, wherein, further includes:
Multiple expansions are determined according to the strength of association between the knowledge point and the multiple session knowledge point in the knowledge point map
Open up knowledge point；
It is described at least to include: based on the session theme and the multiple session knowledge point generation knowledge abstract
The knowledge abstract is generated based on the session theme, the multiple session knowledge point and the multiple extension knowledge point.
3. according to the method described in claim 2, wherein, the knowledge point according in the knowledge point map with it is the multiple
Strength of association between session knowledge point determines that multiple extension knowledge points include:
Choose the last n session knowledge point jumped in path that the multiple session knowledge point is constituted；
Calculate the pass of neighbour's knowledge point set of each knowledge point Ki (0 < i < n) and Ki in the last n session knowledge point
Join intensity, neighbour's knowledge point set takes with Ki apart from the knowledge point for being 1, and calculating formula of similarity is as follows:
Sim(Ki, Kj)=e-λtS (Ki, Kj) D (Ki, Kj), i ≠ j, j ∈ Set (Ki) (1)
In formula (1), Set (Ki) indicates that knowledge point path is neighbour's knowledge point set of the knowledge point Ki of i, and Sim (Ki, Kj) is
The strength of association of Ki and Kj；
e-λtFor time decay factor, t=n-i, the last one knowledge point i=n, t=n-i=0 on path；
S (Ki, Kj) is the static association intensity of Ki and Kj, and D (Ki, Kj) dynamically associates intensity for Ki's and Kj；
The preceding k knowledge point for taking strength of association big is as the multiple extension knowledge point.
4. method described in any one of -3 according to claim 1, wherein further include: knowledge abstract is carried out visual
Change and show, described visualize includes form and/or graphic form.
5. the knowledge summarization generation system in a kind of conversational system, comprising:
Map construction program module, in advance construct knowledge organization structure, the knowledge organization structure include theme map and
Knowledge point map；
Logging program module, for recording user's session theme involved in conversation procedure and multiple session knowledge points；
Summarization generation program module, at least generating the knowledge based on the session theme and the multiple session knowledge point
Abstract.
6. system according to claim 5, wherein further include:
Extender module, for according to the pass between the knowledge point and the multiple session knowledge point in the knowledge point map
Connection intensity determines multiple extension knowledge points；
Described includes: at least based on described based on the session theme and the multiple session knowledge point generation knowledge abstract
Session theme, the multiple session knowledge point and the multiple extension knowledge point generate the knowledge abstract.
7. system according to claim 6, wherein the extender module includes:
Knowledge point option program unit, it is a for choosing the last n jumped in path that the multiple session knowledge point is constituted
Session knowledge point；
Calculation procedure unit, it is close with Ki for calculating each knowledge point Ki (0 < i < n) in the last n session knowledge point
The strength of association of adjacent knowledge point set, the knowledge point that it is 1 with Ki distance that neighbour's knowledge point set, which takes, calculating formula of similarity is such as
Under:
Sim (Ki, Kj)=e-λtS (Ki, Kj) D (Ki, Kj), i ≠ j, j ≠ j, j ∈ Set (Ki) (1)
Wherein, Set (Ki) indicates that knowledge point path is neighbour's knowledge point set of the knowledge point Ki of i, Sim (Ki, Kj) be Ki with
The strength of association of Kj；e-λtFor time decay factor, t=n-i, the last one knowledge point i=n, t=n-i=0 on path；S
(Ki, Kj) is the static association intensity of Ki and Kj, and D (Ki, Kj) dynamically associates intensity for Ki's and Kj；
Extender unit, the preceding k knowledge point for taking strength of association big is as the multiple extension knowledge point.
8. the system according to any one of claim 5-7, wherein further include:
Visualization procedure module, for visualizing knowledge abstract, described visualize includes table shape
Formula and/or graphic form.
9. 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 1-4 the method
Step.
10. a kind of storage medium, is stored thereon with computer program, which is characterized in that the realization when program is executed by processor
The step of any one of claim 1-4 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910255435.3A CN110008326B (en) | 2019-04-01 | 2019-04-01 | Knowledge abstract generation method and system in session system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910255435.3A CN110008326B (en) | 2019-04-01 | 2019-04-01 | Knowledge abstract generation method and system in session system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110008326A true CN110008326A (en) | 2019-07-12 |
| CN110008326B CN110008326B (en) | 2020-11-03 |
Family
ID=67169157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910255435.3A Active CN110008326B (en) | 2019-04-01 | 2019-04-01 | Knowledge abstract generation method and system in session system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110008326B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159382A (en) * | 2019-12-27 | 2020-05-15 | 苏州思必驰信息科技有限公司 | Method and device for constructing and using session system knowledge model |
| CN112597285A (en) * | 2020-12-10 | 2021-04-02 | 太极计算机股份有限公司 | Man-machine interaction method and system based on knowledge graph |
| WO2021098794A1 (en) * | 2019-11-21 | 2021-05-27 | 邝俊伟 | Text search method, device, server, and storage medium |
| CN112911073A (en) * | 2019-04-30 | 2021-06-04 | 五竹科技(北京)有限公司 | Intelligent knowledge graph construction method and device for outbound process conversation content |
| WO2021121020A1 (en) * | 2019-12-18 | 2021-06-24 | 华为技术有限公司 | Question and answer method, apparatus, and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447346A (en) * | 2016-08-29 | 2017-02-22 | 北京中电普华信息技术有限公司 | Method and system for construction of intelligent electric power customer service system |
| CN106919674A (en) * | 2017-02-20 | 2017-07-04 | 广东省中医院 | A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks |
| CN107845422A (en) * | 2017-11-23 | 2018-03-27 | 郑州大学第附属医院 | A kind of remote medical consultation with specialists session understanding and method of abstracting based on the fusion of multi-modal clue |
| CN107870994A (en) * | 2017-10-31 | 2018-04-03 | 北京光年无限科技有限公司 | Man-machine interaction method and system for intelligent robot |
| CN108763494A (en) * | 2018-05-30 | 2018-11-06 | 苏州思必驰信息科技有限公司 | Knowledge Sharing method, dialogue method and device between conversational system |
| 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 |
| CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
| CN109284363A (en) * | 2018-12-03 | 2019-01-29 | 北京羽扇智信息科技有限公司 | A kind of answering method, device, electronic equipment and storage medium |
-
2019
- 2019-04-01 CN CN201910255435.3A patent/CN110008326B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447346A (en) * | 2016-08-29 | 2017-02-22 | 北京中电普华信息技术有限公司 | Method and system for construction of intelligent electric power customer service system |
| CN106919674A (en) * | 2017-02-20 | 2017-07-04 | 广东省中医院 | A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks |
| CN107870994A (en) * | 2017-10-31 | 2018-04-03 | 北京光年无限科技有限公司 | Man-machine interaction method and system for intelligent robot |
| CN107845422A (en) * | 2017-11-23 | 2018-03-27 | 郑州大学第附属医院 | A kind of remote medical consultation with specialists session understanding and method of abstracting based on the fusion of multi-modal clue |
| CN108763494A (en) * | 2018-05-30 | 2018-11-06 | 苏州思必驰信息科技有限公司 | Knowledge Sharing method, dialogue method and device between conversational system |
| 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 |
| CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
| CN109284363A (en) * | 2018-12-03 | 2019-01-29 | 北京羽扇智信息科技有限公司 | A kind of answering method, device, electronic equipment and storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112911073A (en) * | 2019-04-30 | 2021-06-04 | 五竹科技(北京)有限公司 | Intelligent knowledge graph construction method and device for outbound process conversation content |
| CN112911073B (en) * | 2019-04-30 | 2023-04-25 | 五竹科技(北京)有限公司 | Intelligent knowledge graph construction method and device for outbound flow dialogue content |
| WO2021098794A1 (en) * | 2019-11-21 | 2021-05-27 | 邝俊伟 | Text search method, device, server, and storage medium |
| WO2021121020A1 (en) * | 2019-12-18 | 2021-06-24 | 华为技术有限公司 | Question and answer method, apparatus, and device |
| CN111159382A (en) * | 2019-12-27 | 2020-05-15 | 苏州思必驰信息科技有限公司 | Method and device for constructing and using session system knowledge model |
| CN111159382B (en) * | 2019-12-27 | 2022-07-12 | 思必驰科技股份有限公司 | Method and device for constructing and using session system knowledge model |
| CN112597285A (en) * | 2020-12-10 | 2021-04-02 | 太极计算机股份有限公司 | Man-machine interaction method and system based on knowledge graph |
| CN112597285B (en) * | 2020-12-10 | 2021-08-10 | 太极计算机股份有限公司 | Man-machine interaction method and system based on knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110008326B (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008326A (en) | Knowledge abstraction generating method and system in conversational system | |
| CN108763495B (en) | Interactive method, system, electronic equipment and storage medium | |
| JP6896690B2 (en) | Contextual exploration in multimedia content | |
| CN115082602B (en) | Method for generating digital person, training method, training device, training equipment and training medium for model | |
| US8972265B1 (en) | Multiple voices in audio content | |
| CN110349572A (en) | A kind of voice keyword recognition method, device, terminal and server | |
| CN107294837A (en) | Engaged in the dialogue interactive method and system using virtual robot | |
| CN109948151A (en) | The method for constructing voice assistant | |
| CN109389870A (en) | A kind of data adaptive method of adjustment and its device applied in electronic instruction | |
| JP7488871B2 (en) | Dialogue recommendation method, device, electronic device, storage medium, and computer program | |
| WO2018094952A1 (en) | Content recommendation method and apparatus | |
| CN111159382B (en) | Method and device for constructing and using session system knowledge model | |
| CN109416690A (en) | The strategy creation that task status for session tracks | |
| CN110427478A (en) | A kind of the question and answer searching method and system of knowledge based map | |
| CN109192212A (en) | Sound control method and device | |
| CN109902187A (en) | Method and device for constructing characteristic knowledge graph and terminal equipment | |
| Varitimiadis et al. | Towards implementing an AI chatbot platform for museums | |
| US12118319B2 (en) | Dialogue state rewriting and reply generating method and system, electronic device and storage medium | |
| US20210335357A1 (en) | Method for controlling intelligent speech apparatus, electronic device and storage medium | |
| CN108874915A (en) | Method of Knowledge Organization, system, electronic equipment and storage medium | |
| CN116431780A (en) | Man-machine conversation method, system, electronic equipment and storage medium | |
| CN107770235A (en) | One kind bucket song service implementing method and system | |
| CN108491380A (en) | Confrontation multitask training method for speech understanding | |
| CN105118345A (en) | Cloud intelligent interactive learning system | |
| Bowden et al. | Slugbot: An application of a novel and scalable open domain socialbot framework |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee after: Sipic Technology Co.,Ltd. Address before: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee before: AI SPEECH Ltd. |