CN109635086A - A kind of knowledge recommendation method and device applied to knowledge platform - Google Patents
A kind of knowledge recommendation method and device applied to knowledge platform Download PDFInfo
- Publication number
- CN109635086A CN109635086A CN201811498206.6A CN201811498206A CN109635086A CN 109635086 A CN109635086 A CN 109635086A CN 201811498206 A CN201811498206 A CN 201811498206A CN 109635086 A CN109635086 A CN 109635086A
- Authority
- CN
- China
- Prior art keywords
- information
- knowledge
- described problem
- problem information
- business scenario
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present application discloses a kind of knowledge recommendation method and device applied to knowledge platform.In this method, the problem of obtaining user's input after information, the problem information is analyzed, extracts the characteristic information for including in problem information；Then determine that the corresponding business scenario of problem information determines whether problem information meets the trigger condition under the business scenario according to the characteristic information for including in described problem information；If the problem information meets trigger condition, the target requirement of the user is determined according to described problem information, by searching for the corresponding knowledge base of the business scenario, is obtained the corresponding recommendation knowledge of the target requirement and is shown.Pass through scheme disclosed in the embodiment of the present application, problem information under the different business scene that can be proposed to user carries out knowledge recommendation, so as to cope with multiple business scene, it solves the problems, such as that knowledge platform in the prior art can only propose the problem of replying to user under single scene, meets the various demands of user.
Description
This application claims in submission on June 5th, 2018 Patent Office of the People's Republic of China, application No. is 201810568453.2, invention names
A kind of referred to as priority of the Chinese patent application of " knowledge recommendation method and device applied to intelligent robot interaction " is complete
Portion's content is hereby incorporated by reference in the application.
Technical field
This application involves field of human-computer interaction more particularly to a kind of knowledge recommendation methods and dress applied to knowledge platform
It sets.
Background technique
In order to meet the needs of user's quick obtaining information, it is now provided with a variety of knowledge platforms, such as intelligent online visitor
Take robot, mobile phone assistant etc..To after knowledge platform input problem, knowledge platform can be answered accordingly user to user feedback
Case, to meet the needs of user obtains information.For example, passing through the intelligence of shopping website offer when user accesses shopping website
Energy online customer service robot, can obtain the relevant information of commodity, meet the shopping need of user.
But inventor has found in the research process of the application, existing various knowledge platforms can only be to user in list
The problem of proposing under one scene is replied accordingly, is not able to satisfy the various demands of user.
Summary of the invention
The embodiment of the present application provides a kind of knowledge recommendation method and device applied to knowledge platform, to solve existing skill
The problem of can only proposing under single scene to user in art, is replied accordingly, is not able to satisfy the various demands of user
Problem.
In the embodiment of the present application in a first aspect, providing a kind of knowledge recommendation method applied to knowledge platform, comprising:
After the problem of obtaining user's input information, by analyzing described problem information, described problem information is extracted
In include characteristic information；
Determine the corresponding business scenario of described problem information, wherein each business scenario is corresponding comprising the business scenario
Knowledge base, the knowledge base is stored in knowledge platform；
According to the characteristic information for including in described problem information, determine whether described problem information meets the business scenario
Under trigger condition；
If described problem information meets the trigger condition under the business scenario, the use is determined according to described problem information
The target requirement at family；
By searching for the corresponding knowledge base of the business scenario, obtains the corresponding recommendation knowledge of the target requirement and show
Show.
Optionally, described according to the characteristic information for including in described problem information, determine whether described problem information meets
Trigger condition under the business scenario, comprising:
Whether judge in the characteristic information comprising the corresponding trigger parameter of the business scenario；
If including the corresponding trigger parameter of the business scenario in the characteristic information, obtains the trigger parameter and continuously go out
Existing number, the number that the trigger parameter is continuously occurred is as triggering times；
If the triggering times are not less than preset threshold, determine that described problem information meets the triggering under the business scenario
Condition.
Optionally, the corresponding business scenario of the determining described problem information, comprising:
The interaction parameter of described problem information is obtained, and the corresponding industry of described problem information is determined by the interaction parameter
Business scene；
And/or
According to the characteristic information for including in described problem information, the business demand of described problem information is determined；
According to the business demand of described problem information, the corresponding business scenario of described problem information is determined.
Optionally, after determining whether described problem information meets the trigger condition under the business scenario, further includes:
If it is determined that described problem information does not meet the trigger condition under the business scenario, according to preparatory in the knowledge base
The corresponding relationship of each problem information being arranged and answer information determines the corresponding answer information of described problem information；
Show the corresponding answer information of described problem information.
Optionally, after obtaining the corresponding recommendation knowledge of the target requirement and showing, further includes:
According to pre-set active question and answer information, Xiang Suoshu user issues active question and answer；
After receiving return information of the user for the active question and answer information input, show preset time
Answer sentence.
Optionally, after showing preset return exp, further includes:
Search whether there is association knowledge associated with the return information；
Association knowledge associated with the return information if it exists generates the corresponding menu choosing of the association knowledge
, Xiang Suoshu user show the menu option, and receive the user be directed to the menu option selection operation it
Afterwards, the corresponding association knowledge of the menu option is shown；
The association knowledge if it does not exist shows preset END, or exits this recommended flowsheet.
In the second aspect of the embodiment of the present application, a kind of knowledge recommendation device applied to knowledge platform is provided, comprising:
Characteristic information extracting module, after obtaining the problem of user inputs information, by being carried out to described problem information
The characteristic information for including in described problem information is extracted in analysis；
Business scenario determining module, for determining the corresponding business scenario of described problem information, wherein each business scenario
Comprising the corresponding knowledge base of the business scenario, the knowledge base is stored in knowledge platform；
Trigger condition determining module, for determining that described problem is believed according to the characteristic information for including in described problem information
Whether breath meets the trigger condition under the business scenario；
Target requirement determining module, if meeting the trigger condition under the business scenario for described problem information, according to
Described problem information determines the target requirement of the user；
Recommend knowledge display module, for by searching for the corresponding knowledge base of the business scenario, obtaining the target to be needed
It seeks corresponding recommendation knowledge and shows.
Optionally, the trigger condition determining module includes:
Trigger parameter judging unit, for whether judging in the characteristic information comprising the corresponding triggering of the business scenario
Parameter；
Triggering times acquiring unit, if for including the corresponding trigger parameter of the business scenario in the characteristic information,
The number that the trigger parameter continuously occurs is obtained, the number that the trigger parameter is continuously occurred is as triggering times；
Trigger condition determination unit determines that described problem information accords with if being not less than preset threshold for the triggering times
Close the trigger condition under the business scenario.
Optionally, the business scenario determining module includes:
First scene determination unit, for obtaining the interaction parameter of described problem information, and it is true by the interaction parameter
Determine the corresponding business scenario of described problem information；
And/or
Business demand determination unit, for determining that described problem is believed according to the characteristic information for including in described problem information
The business demand of breath；
Second scene determination unit determines that described problem information is corresponding for the business demand according to described problem information
Business scenario.
Optionally, further includes:
Answer information determining module, for determining whether described problem information meets the triggering item under the business scenario
After part, however, it is determined that described problem information does not meet the trigger condition under the business scenario, according to preparatory in the knowledge base
The corresponding relationship of each problem information being arranged and answer information determines the corresponding answer information of described problem information；
Answer information display module, for showing the corresponding answer information of described problem information.
The embodiment of the present application discloses a kind of knowledge recommendation method and device applied to knowledge platform.In this method, obtaining
After the problem of taking family input information, the problem information is analyzed, the characteristic information for including in problem information is extracted；Then determination is asked
The corresponding business scenario of topic information determines whether problem information meets this according to the characteristic information for including in described problem information
Trigger condition under business scenario；If the problem information meets trigger condition, determine the user's according to described problem information
Target requirement obtains the corresponding recommendation knowledge of the target requirement and shows by searching for the corresponding knowledge base of the business scenario
Show.
Therefore, the problem by scheme disclosed in the embodiment of the present application, under the different business scene that can be proposed to user
Information carries out knowledge recommendation, and so as to cope with multiple business scene, solving knowledge platform in the prior art can only be to user
The problem of the problem of proposing under single scene is replied, so as to meet the various demands of user.
Detailed description of the invention
In order to illustrate more clearly of the technical solution of the application, letter will be made to attached drawing needed in the embodiment below
Singly introduce, it should be apparent that, for those of ordinary skills, without any creative labor,
It is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of workflow signal of the knowledge recommendation method applied to knowledge platform disclosed in the embodiment of the present application
Figure；
Fig. 2 is to determine that problem is believed in a kind of knowledge recommendation method applied to knowledge platform disclosed in the embodiment of the present application
Whether breath meets the workflow schematic diagram of the trigger condition under business scenario；
Fig. 3 shows for the business scenario in a kind of knowledge recommendation method applied to knowledge platform disclosed in the embodiment of the present application
It is intended to；
Fig. 4 is that another disclosed workflow for being applied to the knowledge recommendation method of knowledge platform of the embodiment of the present application is shown
It is intended to；
Fig. 5 is that another disclosed workflow for being applied to the knowledge recommendation method of knowledge platform of the embodiment of the present application is shown
It is intended to；
Fig. 6 is that another disclosed workflow for being applied to the knowledge recommendation method of knowledge platform of the embodiment of the present application is shown
It is intended to；
Fig. 7 is a kind of structural schematic diagram of the knowledge recommendation device applied to knowledge platform disclosed in the embodiment of the present application.
Specific embodiment
It, cannot in order to solve the problems, such as can only to propose to be replied accordingly under single scene to user in the prior art
The problem of meeting user's various demands, the embodiment of the present application provide a kind of knowledge recommendation method applied to knowledge platform and
Device.
The application first embodiment discloses a kind of knowledge recommendation method applied to knowledge platform, in this way, knowledge
Platform can carry out knowledge recommendation to user.Workflow schematic diagram shown in Figure 1, method includes the following steps:
Step S11, after the problem of obtaining user's input information, by analyzing described problem information, described in extraction
The characteristic information for including in problem information.
In the embodiment of the present application, the characteristic information is a conceptual information in problem information, for characterizing
The intention of the knowledge point or user that include in problem information is stated, will pass through the demand that characteristic information understands user.Wherein, should
Characteristic information is usually a nominal and/or verb character conceptual information.For example, if the problem information is that " gasoline can take winged
Machine ", then " gasoline " and " aircraft " can be used as characteristic information, if the problem information be " rentability of fund ", " fund " and
" rentability " can be used as characteristic information.
When the characteristic information for including in extracting problem information, semantic analysis can be carried out to the problem information, pass through semanteme
Analysis, splits the problem information, obtains each word, and obtain the part of speech of each word, further according to each word
The part of speech of language determines the characteristic information for including in problem information.
Step S12, the corresponding business scenario of described problem information is determined, wherein each business scenario includes the business
The corresponding knowledge base of scene, the knowledge base are stored in knowledge platform.
In the knowledge platform of the scheme disclosed in application the embodiment of the present application, it is configured with multiple business scene, to meet
Demand of the user under different business scene.Wherein, in the embodiment of the present application, business scenario may include customer service scene, battalion
Sale place scape, intelligent recommendation scene and outgoing call scene etc..It is, of course, also possible to support other business scenarios, the embodiment of the present application is to this
It is not construed as limiting.
Wherein, customer service scene is for solving the problems, such as client pre-sales and after sale；In marketing scene, it can be pushed to user
Pre-stored Marketing Savvy；In intelligent recommendation scene, user may propose the fuzzy problem of some comparisons, knowledge platform root
According to these problems guidance confirmation step by step, answer required for user is finally obtained；Outgoing call scene refers to knowledge platform master
It is dynamic to be contacted with user, with the scene asked questions.
In addition, knowledge base corresponding to each business scenario also includes multiple types, for example, knowledge base generally includes FAQ
(Frequently Asked Questions, frequently asked questions and corresponding answer) class knowledge base, rich text knowledge base, concept type knowledge base,
Plain edition knowledge base, element type knowledge base and list type knowledge base etc..
Step S13, according to the characteristic information for including in described problem information, it is described to determine whether described problem information meets
Trigger condition under business scenario.
In the embodiment of the present application, corresponding trigger condition is set for each business scenario in advance.For example, in capital investment
In this business scenario, when settable user repeatedly seeks advice from the relevant information of a certain fund, it is believed that meet under the business scenario
Trigger condition, thereby executing subsequent operation.
It is true according to described problem information if step S14, described problem information meets the trigger condition under the business scenario
The target requirement of the fixed user；
Step S15, it by searching for the corresponding knowledge base of the business scenario, obtains the corresponding recommendation of the target requirement and knows
Know and shows.
If problem information meets the trigger condition under the business scenario, then it is assumed that user, which exists, understands associated recommendation knowledge
Be intended to, i.e., the target requirement of user in order to decorrelation recommendation knowledge.In this case, then the corresponding recommendation of target requirement is obtained
Knowledge, and the recommendation knowledge is shown by knowledge platform, to meet the needs of users.
Wherein, the corresponding relationship between target requirement and recommendation knowledge, is set in advance according to business scenario.Work as problem
When information meets the trigger condition under the business scenario, by searching for the corresponding relationship, it is corresponding target requirement can be got
Recommend knowledge.
For example, if user repeatedly seeks advice from the relevant information of a certain fund, can recognize in this business scenario of capital investment
To meet the trigger condition under the business scenario, the target requirement of user is to understand the fund, then corresponding with the target requirement
Recommending knowledge is the related introduction of the fund, so as to recommend the related introduction of the fund to user by step S15.
It, should according to foregoing description it is found that the embodiment of the present application discloses a kind of knowledge recommendation method applied to knowledge platform
In method, the problem of obtaining user's input after information, the problem information is analyzed, extracts the feature letter for including in problem information
Breath；Then it determines the corresponding business scenario of problem information, according to the characteristic information for including in described problem information, determines that problem is believed
Whether breath meets the trigger condition under the business scenario；It is true according to described problem information if the problem information meets trigger condition
It is corresponding to obtain the target requirement by searching for the corresponding knowledge base of the business scenario for the target requirement of the fixed user
Recommend knowledge and shows.
Therefore, the problem by scheme disclosed in the embodiment of the present application, under the different business scene that can be proposed to user
Information carries out knowledge recommendation and solves knowledge platform intelligent robot in the prior art so as to cope with multiple business scene
The problem of the problem of can only proposing under single scene to user, replys, so as to meet the various demands of user.
It is applied to the knowledge recommendation method that knowledge platform is applied to intelligent robot interaction disclosed in the embodiment of the present application
In, comprising determining whether described problem information meets the business scenario according to the characteristic information for including in described problem information
Under trigger condition operation.Wherein, when whether test problems information meets the trigger condition, usually consider trigger parameter
With the two factors of triggering times.
In this case, workflow schematic diagram shown in Figure 2, it is described according to the spy for including in described problem information
Reference breath, determines whether described problem information meets the trigger condition under the business scenario, comprising the following steps:
Step S21, judge whether comprising the corresponding trigger parameter of the business scenario in the characteristic information, if so, holding
The operation of row step S22, if it is not, executing the operation of step S25.
In the embodiment of the present application, corresponding trigger parameter is provided with for each business scenario in advance.For example, being thrown in fund
It provides in this business scenario, settable " rentability ", " annual earnings " and " falling amount of increase " etc. is trigger parameter.
If in step S22, the described characteristic information including the corresponding trigger parameter of the business scenario, the triggering ginseng is obtained
The number that number continuously occurs, the number that the trigger parameter is continuously occurred is as triggering times.
Step S23, judge whether the triggering times are less than preset threshold.
Wherein, if the triggering times are not less than preset threshold, the operation of S24 is thened follow the steps, if the trigger parameter
The number continuously occurred is less than preset threshold, thens follow the steps the operation of S25.
If the number that step S24, the described trigger parameter continuously occurs is not less than preset threshold, determine that described problem information accords with
Close the trigger condition under the business scenario.
Wherein, the size of preset threshold can be preset by the manager of knowledge platform intelligent robot.For example, settable
The preset threshold is 3 etc..
Step S25, determine that described problem information does not meet the trigger condition under the business scenario.
By step S21 to the operation of step S25, it is able to detect that whether problem information meets the triggering under business scenario
Condition.For this clear process, a specific example explanation can be passed through below.
The business scenario of the example is capital investment, in the business scenario, preset " rentability ", " annual earnings " and
" falling amount of increase " etc. is trigger parameter, and it is 3 that the preset threshold, which is arranged,.In this case, if user continuously proposes " A fund
Fall amount of increase ", " annual earnings of A fund " and information the problems such as " rentability of A fund ", then show what trigger parameter continuously occurred
Number is not less than preset threshold, can determine that " rentability of A fund " this problem information meets the triggering under the business scenario
Condition.Further, the target requirement of user is determined to understand A fund, so as to recommend relevant content to A fund.
Specifically, business scenario schematic diagram shown in Figure 3, setting user proposes " rentability of Capricorn " this problem
When information, which meets the trigger condition under the business scenario, and in this case, knowledge platform can recommend to rub to user
The relevant knowledge of castrated ram's fund.
Further, in the embodiment of the present application, it is thus necessary to determine that the corresponding business scenario of problem information, described in the determination
The corresponding business scenario of problem information, comprising:
The interaction parameter of described problem information is obtained, and the corresponding industry of described problem information is determined by the interaction parameter
Business scene；
And/or
According to the characteristic information for including in described problem information, the business demand of described problem information is determined；
According to the business demand of described problem information, the corresponding business scenario of described problem information is determined.
Wherein, the interaction parameter generally includes the source parameter of the problem of user is uploaded to knowledge platform information.For example,
The problem of if user proposes problem information when accessing a certain shopping website, to knowledge platform, then user is uploaded to knowledge platform
The source parameter of information is the shopping website.In this case, it may be determined that the corresponding business scenario of the problem information is customer service field
The corresponding application of scape.
Furthermore it is also possible to determine the corresponding business scenario of the problem information according to business demand.For example, if characteristic information packet
" credit card " and " payment " etc. are included, can determine that current business demand is pressed for payment of for credit card, in this case, it may be determined that this is asked
Inscribe the business scenario that the corresponding business scenario of information is outgoing call.
Further, in some cases, problem information does not meet the trigger condition under business scenario.In this case, join
Workflow schematic diagram as shown in Figure 4, the disclosed knowledge recommendation method applied to knowledge platform of the embodiment of the present application include
Following steps:
Step S41, after the problem of obtaining user's input information, by analyzing described problem information, described in extraction
The characteristic information for including in problem information.
Step S42, the corresponding business scenario of described problem information is determined, wherein each business scenario includes the business
The corresponding knowledge base of scene, the knowledge base are stored in knowledge platform.
Step S43, according to the characteristic information for including in described problem information, it is described to determine whether described problem information meets
Trigger condition under business scenario.
Wherein, if meeting, the operation of step S44 is executed, if not meeting, executes the operation of step S46.
It is true according to described problem information if step S44, described problem information meets the trigger condition under the business scenario
The target requirement of the fixed user.
Step S45, it by searching for the corresponding knowledge base of the business scenario, obtains the corresponding recommendation of the target requirement and knows
Know and shows.
Wherein, the specific operation process phase of the specific operation process of step S41 to step S45 and step S11 to step S15
Together, can be cross-referenced, details are not described herein again.
Step S46, if it is determined that described problem information does not meet the trigger condition under the business scenario, according to the knowledge
The corresponding relationship of pre-set each problem information and answer information in library determines the corresponding answer letter of described problem information
Breath.
Step S47, the corresponding answer information of display described problem information.
In step S46 and step S47, however, it is determined that problem information does not meet the trigger condition under business scenario, then directly
Reply the corresponding answer information of the problem information.Wherein, various answer informations and problem information pass corresponding with answer information
System, is pre-stored in knowledge base.
For example, if the problem of user proposes information " rentability of A fund ", does not meet the trigger condition under business scenario,
Then by search knowledge base, determine the corresponding answer information of the problem information, and show the answer information to user, and no longer into
Row is recommended.
Further, workflow schematic diagram shown in Figure 5 is obtaining the mesh after executing step S15
It is further comprising the steps of after the corresponding recommendation knowledge of mark demand and display:
Step S16, according to pre-set active question and answer information, Xiang Suoshu user issues active question and answer；
Step S17, after receiving return information of the user for the active question and answer information input, display is preparatory
The return exp of setting.
The problem of being proposed according to user information to the corresponding answer information of user feedback or recommends knowledge, is passive question and answer
Form.Further, the embodiment of the present application can also execute active question and answer by step S16 to the operation of step S17.According to
Preparatory setting, the active question and answer can execute a wheel or more wheels.
For example, in business scenario schematic diagram shown in Fig. 3, " you are good, may I ask and whether bought Capricorn intelligence and throw and related
Product ", as active question and answer information, accordingly, user can choose "Yes" or "No", using as return information.It is receiving
After this return information of "Yes", " it is good, thank you participation (you whether purchase: yes) " be preset response language
Sentence.
In addition, in business scenario schematic diagram shown in Fig. 3, " you are good, may I ask how you feel income " is as actively asked
Information is answered, accordingly, user can choose " fine " or " general " or " sustaining losses in business ", using as return information.Receiving " fine "
After this return information, " thanks to your evaluation, congratulate your income and become better and better.(your earning rate: being to set in advance very well) "
Fixed return exp.
It is directed to the return information of the active question and answer information input according to user, can further determine that the target of user needs
It asks.
Further, it is applied in the knowledge recommendation method of knowledge platform disclosed in the embodiment of the present application, referring to Fig. 6 institute
The workflow schematic diagram shown, after showing preset return exp, further includes:
Step S18, search whether there is association knowledge associated with the return information.If so, executing step S19's
Operation, if it is not, executing the operation of step S20.
Step S19, association knowledge associated with the return information if it exists, it is corresponding to generate the association knowledge
Menu option, Xiang Suoshu user shows the menu option, and is receiving the user for the selection of the menu option
After operation, the corresponding association knowledge of the menu option is shown.
Step S20, the association knowledge if it does not exist, shows preset END, or exit this recommendation
Process.
The return information inputted by user, can further determine that the target requirement of user.It in this case, can be into one
Step searches whether there is association knowledge associated with the return information.For example, if according to the return information that user inputs, really
The Capricorn intelligence throwing for determining user is interested, then can be further shown that " Capricorn brief introduction ", " consulting process of purchase " and " Capricorn feature "
Equal menu options, for selection by the user, and operation shows corresponding association knowledge according to the user's choice, so as to further satisfaction
The demand of user.
Correspondingly, a kind of knowledge recommendation device applied to knowledge platform is also disclosed in the embodiment of the present application, by the device,
Knowledge platform can carry out knowledge recommendation to user.Structural schematic diagram shown in Figure 7, the knowing applied to knowledge platform
Knowing recommendation apparatus includes: characteristic information extracting module 100, business scenario determining module 200, trigger condition determining module 300, mesh
Mark demand determining module 400 and recommendation knowledge display module 500.
Wherein, the characteristic information extracting module 100, after obtaining the problem of user inputs information, by described
Problem information is analyzed, and the characteristic information for including in described problem information is extracted.
In the embodiment of the present application, the characteristic information is a conceptual information in problem information, for characterizing
The intention of the knowledge point and user that include in problem information is stated, will pass through the demand that characteristic information understands user.The spy
When the characteristic information that sign information extraction modules 100 include in extracting problem information, semantic analysis can be carried out to the problem information,
By semantic analysis, which is split, obtains each word, and obtains the part of speech of each word, then basis
The part of speech of each word determines the characteristic information for including in problem information.
The business scenario determining module 200, for determining the corresponding business scenario of described problem information, wherein each
Business scenario includes the corresponding knowledge base of the business scenario, and the knowledge base is stored in knowledge platform.
In the knowledge platform of the scheme disclosed in application the embodiment of the present application, it is configured with multiple business scene, to meet
Demand of the user under different business scene.Wherein, in the embodiment of the present application, business scenario may include customer service scene, battalion
Sale place scape, intelligent recommendation scene and outgoing call scene etc..It is, of course, also possible to support other business scenarios, the embodiment of the present application is to this
It is not construed as limiting.
In addition, knowledge base corresponding to each business scenario also includes multiple types, for example, knowledge base generally includes FAQ
(Frequently Asked Questions, frequently asked questions and corresponding answer) class knowledge base, rich text knowledge base, concept type knowledge base,
Plain edition knowledge base, element type knowledge base and list type knowledge base etc..
The trigger condition determining module 300, described in determining according to the characteristic information for including in described problem information
Whether problem information meets the trigger condition under the business scenario.
In the embodiment of the present application, corresponding trigger condition is set for each business scenario in advance.For example, in capital investment
In this business scenario, when settable user repeatedly seeks advice from the relevant information of a certain fund, it is believed that meet under the business scenario
Trigger condition, thereby executing subsequent operation.
The target requirement determining module 400, if meeting the triggering item under the business scenario for described problem information
Part determines the target requirement of the user according to described problem information.
The recommendation knowledge display module 500, for by searching for the corresponding knowledge base of the business scenario, described in acquisition
The corresponding recommendation knowledge of target requirement is simultaneously shown.
If problem information meets the trigger condition under the business scenario, then it is assumed that user, which exists, understands associated recommendation knowledge
Be intended to, i.e., the target requirement of user in order to decorrelation recommendation knowledge.In this case, recommend knowledge display module 500 can
The corresponding recommendation knowledge of target requirement is obtained, and the recommendation knowledge is shown by knowledge platform, to meet the needs of users.
Wherein, the corresponding relationship between target requirement and recommendation knowledge, is set in advance according to business scenario.Work as problem
When information meets the trigger condition under the business scenario, by searching for the corresponding relationship, it is corresponding target requirement can be got
Recommend knowledge.
By scheme disclosed in the embodiment of the present application, problem information under the different business scene that can be proposed to user into
Row knowledge recommendation, so as to cope with multiple business scene, solving knowledge platform in the prior art can only be to user single
The problem of the problem of proposing under scene is replied, so as to meet the various demands of user.
It is applied in the knowledge recommendation device of knowledge platform disclosed in the embodiment of the present application, whether is determining problem information
When meeting the trigger condition, trigger parameter and triggering times the two factors are usually considered.In this case, the triggering item
Part determining module includes:
Trigger parameter judging unit, for whether judging in the characteristic information comprising the corresponding triggering of the business scenario
Parameter；
Triggering times acquiring unit, if for including the corresponding trigger parameter of the business scenario in the characteristic information,
The number that the trigger parameter continuously occurs is obtained, the number that the trigger parameter is continuously occurred is as triggering times；
Trigger condition determination unit determines that described problem information accords with if being not less than preset threshold for the triggering times
Close the trigger condition under the business scenario.
In addition, if not including the corresponding trigger parameter of the business scenario in characteristic information, although alternatively, in characteristic information
Comprising the corresponding trigger parameter of the business scenario, but triggering times are less than preset threshold, then trigger condition determination unit is also
It can determine that described problem information does not meet the trigger condition under the business scenario.
Further, it is applied in the knowledge recommendation device of knowledge platform disclosed in the embodiment of the present application, the business
Scene determining module includes:
First scene determination unit, for obtaining the interaction parameter of described problem information, and it is true by the interaction parameter
Determine the corresponding business scenario of described problem information；
And/or
Business demand determination unit, for determining that described problem is believed according to the characteristic information for including in described problem information
The business demand of breath；
Second scene determination unit determines that described problem information is corresponding for the business demand according to described problem information
Business scenario.
Wherein, the interaction parameter generally includes the source parameter of the problem of user is uploaded to knowledge platform information.For example,
The problem of if user proposes problem information when accessing a certain shopping website, to knowledge platform, then user is uploaded to knowledge platform
The source parameter of information is the shopping website.In this case, it may be determined that the corresponding business scenario of the problem information is customer service field
The corresponding application of scape.
Further, it is applied in the knowledge recommendation device of knowledge platform disclosed in the embodiment of the present application, further includes:
Answer information determining module, for determining whether described problem information meets the triggering item under the business scenario
After part, however, it is determined that described problem information does not meet the trigger condition under the business scenario, according to preparatory in the knowledge base
The corresponding relationship of each problem information being arranged and answer information determines the corresponding answer information of described problem information；
Answer information display module, for showing the corresponding answer information of described problem information.
Pass through answer information determining module and answer information display module, however, it is determined that problem information is not met under business scenario
Trigger condition, then directly reply the corresponding answer information of the problem information.Wherein, various answer informations and problem information
With the corresponding relationship of answer information, it is pre-stored in knowledge base.
In the specific implementation, the embodiment of the present application also provides a kind of computer readable storage medium, wherein this is computer-readable
Storage medium can be stored with program, which may include the intelligence machine provided by the present application suitable for multi-service scene when executing
Step some or all of in each embodiment of the implementation method of people.The storage medium can be magnetic disk, CD, read-only storage
Memory body (read-only memory, ROM) or random access memory (random access memory, RAM) etc..
It is required that those skilled in the art can be understood that the technology in the embodiment of the present application can add by software
The mode of general hardware platform realize.Based on this understanding, the technical solution in the embodiment of the present application substantially or
Say that the part that contributes to existing technology can be embodied in the form of software products, which can deposit
Storage is in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that computer equipment (can be with
It is personal computer, server or the network equipment etc.) execute certain part institutes of each embodiment of the application or embodiment
The method stated.
Same and similar part may refer to each other between each embodiment in this specification.Especially for device and end
For the embodiment of end equipment, since it is substantially similar to the method embodiment, so be described relatively simple, related place referring to
Explanation in embodiment of the method.
Above-described the application embodiment does not constitute the restriction to the application protection scope.
Claims (10)
1. a kind of knowledge recommendation method applied to knowledge platform characterized by comprising
After the problem of obtaining user's input information, by analyzing described problem information, extracts and wrapped in described problem information
The characteristic information contained；
Determine the corresponding business scenario of described problem information, wherein each business scenario, which includes that the business scenario is corresponding, to be known
Know library, the knowledge base is stored in knowledge platform；
According to the characteristic information for including in described problem information, determine whether described problem information meets under the business scenario
Trigger condition；
If described problem information meets the trigger condition under the business scenario, determine the user's according to described problem information
Target requirement；
By searching for the corresponding knowledge base of the business scenario, obtains the corresponding recommendation knowledge of the target requirement and show.
2. the knowledge recommendation method according to claim 1 applied to knowledge platform, which is characterized in that described according to
The characteristic information for including in problem information, determines whether described problem information meets the trigger condition under the business scenario, packet
It includes:
Whether judge in the characteristic information comprising the corresponding trigger parameter of the business scenario；
If including the corresponding trigger parameter of the business scenario in the characteristic information, obtain what the trigger parameter continuously occurred
Number, the number that the trigger parameter is continuously occurred is as triggering times；
If the triggering times are not less than preset threshold, determine that described problem information meets the triggering item under the business scenario
Part.
3. the knowledge recommendation method according to claim 1 applied to knowledge platform, which is characterized in that described in the determination
The corresponding business scenario of problem information, comprising:
The interaction parameter of described problem information is obtained, and the corresponding business field of described problem information is determined by the interaction parameter
Scape；
And/or
According to the characteristic information for including in described problem information, the business demand of described problem information is determined；
According to the business demand of described problem information, the corresponding business scenario of described problem information is determined.
4. the knowledge recommendation method according to claim 1 applied to knowledge platform, which is characterized in that ask described in the determination
Whether topic information meets after the trigger condition under the business scenario, further includes:
If it is determined that described problem information does not meet the trigger condition under the business scenario, preset according in the knowledge base
Each problem information and answer information corresponding relationship, determine the corresponding answer information of described problem information；
Show the corresponding answer information of described problem information.
5. the knowledge recommendation method according to claim 1 applied to knowledge platform, which is characterized in that obtaining the mesh
After the corresponding recommendation knowledge of mark demand and display, further includes:
According to pre-set active question and answer information, Xiang Suoshu user issues active question and answer；
After receiving return information of the user for the active question and answer information input, preset response language is shown
Sentence.
6. the knowledge recommendation method according to claim 5 applied to knowledge platform, which is characterized in that set in advance in display
After fixed return exp, further includes:
Search whether there is association knowledge associated with the return information；
Association knowledge associated with the return information if it exists generates the corresponding menu option of the association knowledge, to
The user shows the menu option, and after receiving selection operation of the user for the menu option, shows
Show the corresponding association knowledge of the menu option；
The association knowledge if it does not exist shows preset END, or exits this recommended flowsheet.
7. a kind of knowledge recommendation device applied to knowledge platform characterized by comprising
Characteristic information extracting module, after obtaining the problem of user inputs information, by analyzing described problem information,
Extract the characteristic information for including in described problem information；
Business scenario determining module, for determining the corresponding business scenario of described problem information, wherein each business scenario includes
The corresponding knowledge base of the business scenario, the knowledge base are stored in knowledge platform；
Trigger condition determining module, for determining that described problem information is according to the characteristic information for including in described problem information
The no trigger condition met under the business scenario；
Target requirement determining module, if meeting the trigger condition under the business scenario for described problem information, according to described
Problem information determines the target requirement of the user；
Recommend knowledge display module, for obtaining the target requirement pair by searching for the corresponding knowledge base of the business scenario
The recommendation knowledge answered simultaneously is shown.
8. the knowledge recommendation device according to claim 7 applied to knowledge platform, which is characterized in that the trigger condition
Determining module includes:
Trigger parameter judging unit, for whether judging in the characteristic information comprising the corresponding triggering ginseng of the business scenario
Number；
Triggering times acquiring unit, if being obtained for including the corresponding trigger parameter of the business scenario in the characteristic information
The number that the trigger parameter continuously occurs, the number that the trigger parameter is continuously occurred is as triggering times；
Trigger condition determination unit determines that described problem information meets institute if being not less than preset threshold for the triggering times
State the trigger condition under business scenario.
9. the knowledge recommendation device according to claim 7 applied to knowledge platform, which is characterized in that the business scenario
Determining module includes:
First scene determination unit determines institute for obtaining the interaction parameter of described problem information, and by the interaction parameter
State the corresponding business scenario of problem information；
And/or
Business demand determination unit, for determining described problem information according to the characteristic information for including in described problem information
Business demand；
Second scene determination unit determines the corresponding industry of described problem information for the business demand according to described problem information
Business scene.
10. the knowledge recommendation device according to claim 7 applied to knowledge platform, which is characterized in that further include:
Answer information determining module, for determine described problem information whether meet the trigger condition under the business scenario it
Afterwards, however, it is determined that described problem information does not meet the trigger condition under the business scenario, presets according in the knowledge base
Each problem information and answer information corresponding relationship, determine the corresponding answer information of described problem information；
Answer information display module, for showing the corresponding answer information of described problem information.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810568453.2A CN108776689A (en) | 2018-06-05 | 2018-06-05 | A kind of knowledge recommendation method and device applied to intelligent robot interaction |
| CN2018105684532 | 2018-06-05 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109635086A true CN109635086A (en) | 2019-04-16 |
Family
ID=64024694
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810568453.2A Pending CN108776689A (en) | 2018-06-05 | 2018-06-05 | A kind of knowledge recommendation method and device applied to intelligent robot interaction |
| CN201811498206.6A Pending CN109635086A (en) | 2018-06-05 | 2018-12-07 | A kind of knowledge recommendation method and device applied to knowledge platform |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810568453.2A Pending CN108776689A (en) | 2018-06-05 | 2018-06-05 | A kind of knowledge recommendation method and device applied to intelligent robot interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN108776689A (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109887483A (en) * | 2019-01-04 | 2019-06-14 | 平安科技（深圳）有限公司 | Self-Service processing method, device, computer equipment and storage medium |
| CN110046235B (en) * | 2019-03-18 | 2023-06-02 | 创新先进技术有限公司 | Knowledge base assessment method, device and equipment |
| CN110032625B (en) * | 2019-03-28 | 2023-01-13 | 腾讯科技（上海）有限公司 | Man-machine conversation method and device |
| CN110674268B (en) * | 2019-08-23 | 2021-03-19 | 深圳追一科技有限公司 | Man-machine conversation method and related equipment |
| CN112506963B (en) * | 2020-11-23 | 2022-09-09 | 上海方立数码科技有限公司 | Multi-service-scene-oriented service robot problem matching method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105630456A (en) * | 2014-11-05 | 2016-06-01 | 中兴通讯股份有限公司 | Instruction processing method and device |
| CN106777135A (en) * | 2016-05-27 | 2017-05-31 | 中科鼎富（北京）科技发展有限公司 | Service scheduling method, device and robot service system |
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| CN107256224A (en) * | 2017-04-28 | 2017-10-17 | 北京神州泰岳软件股份有限公司 | A kind of generation method of the key element structure of knowledge, searching method, apparatus and system |
-
2018
- 2018-06-05 CN CN201810568453.2A patent/CN108776689A/en active Pending
- 2018-12-07 CN CN201811498206.6A patent/CN109635086A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105630456A (en) * | 2014-11-05 | 2016-06-01 | 中兴通讯股份有限公司 | Instruction processing method and device |
| CN106777135A (en) * | 2016-05-27 | 2017-05-31 | 中科鼎富（北京）科技发展有限公司 | Service scheduling method, device and robot service system |
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| CN107256224A (en) * | 2017-04-28 | 2017-10-17 | 北京神州泰岳软件股份有限公司 | A kind of generation method of the key element structure of knowledge, searching method, apparatus and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108776689A (en) | 2018-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635086A (en) | A kind of knowledge recommendation method and device applied to knowledge platform | |
| Ikumoro et al. | Intention to use intelligent conversational agents in e-commerce among Malaysian SMEs: an integrated conceptual framework based on tri-theories including unified theory of acceptance, use of technology (UTAUT), and TOE | |
| Duijst | Can we improve the user experience of chatbots with personalisation | |
| CN110378749B (en) | Client similarity evaluation method and device, terminal equipment and storage medium | |
| US10678516B2 (en) | Chatbot builder user interface | |
| US10108998B2 (en) | Method and system of directed, two-way consultative communications between a webpage user and a remote representative | |
| CN110580282B (en) | Method and device for interacting with customer service through simulation user | |
| CN108920530B (en) | Information processing method and device, storage medium and electronic equipment | |
| AU2017415315A1 (en) | Integrating virtual and human agents in a multi-channel support system for complex software applications | |
| CN112183098B (en) | Session processing method and device, storage medium and electronic device | |
| CA3147634A1 (en) | Method and apparatus for analyzing sales conversation based on voice recognition | |
| PW Ellway | The voice-to-technology (V2T) encounter and the call centre servicescape: Navigation, spatiality and movement | |
| JP6442807B1 (en) | Dialog server, dialog method and dialog program | |
| CN114817507A (en) | Reply recommendation method, device, equipment and storage medium based on intention recognition | |
| CN115146047A (en) | Information processing method, apparatus, storage medium, and program product | |
| CN111259124A (en) | Dialogue management method, device, system and storage medium | |
| CN111159379B (en) | Automatic question setting method, device and system | |
| CN109542528A (en) | Customer information processing method, device, computer equipment and storage medium | |
| CN107832342A (en) | Robot chat method and system | |
| CN107871254A (en) | The method and device of data object information is provided | |
| CN111787042A (en) | Method and device for pushing information | |
| CN109189881A (en) | Man-machine interaction method and intelligent robot | |
| CN113112326A (en) | User identification method, method for displaying data to user and related device | |
| CN113723974A (en) | Information processing method, device, equipment and storage medium | |
| CN110232115A (en) | Question processing method, unit and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |
|
| RJ01 | Rejection of invention patent application after publication |