CN106484916A - A kind of enrollment answering method and device - Google Patents
A kind of enrollment answering method and device Download PDFInfo
- Publication number
- CN106484916A CN106484916A CN201610964054.9A CN201610964054A CN106484916A CN 106484916 A CN106484916 A CN 106484916A CN 201610964054 A CN201610964054 A CN 201610964054A CN 106484916 A CN106484916 A CN 106484916A
- Authority
- CN
- China
- Prior art keywords
- enrollment
- knowledge base
- key element
- current request
- information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of enrollment answering method and device, and methods described includes：The current request information of user is obtained, to nature semantic understanding being carried out based on the request text of the current request information, to obtain current request key element；Enrollment knowledge base is mated according to the current request key element, if the match is successful, the request answer is sent to the user according to the request answer that matching result obtains the current request information.Methods described and device can lift the intelligent level of enrollment question and answer.
Description
Technical field
The present invention relates to technical field of intelligent interaction, more particularly to a kind of enrollment answering method and device.
Background technology
Enrollment process faces more object, and the main body of enrollment is also more, generally occurs substantial amounts of during enrollment
Consulting.Consulting with reply generally by being accomplished manually, often there is more repetition in these, traditional artificial answer in seeking advice from
More manpower and materials can be wasted.
In a kind of prior art, by detecting that whether counseling problem is the counseling problem that occurred, if occurring
The counseling problem that crosses then is automatically replied.
But, the existing intelligent level for automatically replying has to be hoisted.
Content of the invention
Present invention solves the technical problem that being the intelligent level of lifting enrollment question and answer.
For solving above-mentioned technical problem, the embodiment of the present invention provides a kind of enrollment answering method, including：Obtain working as user
Front solicited message, to carrying out nature semantic understanding based on the request text of the current request information, will to obtain current request
Element；Enrollment knowledge base is mated according to the current request key element, if the match is successful, obtains described currently please according to matching result
The request answer of information is asked to send the request answer to the user.
Optionally, mating enrollment knowledge base according to the current request key element includes：Determine historical requests key element, described go through
History request key element is the request key element that the historical requests information to the user carries out that nature semantic understanding is obtained；Work as in conjunction with described
Front request key element and historical requests key element coupling enrollment knowledge base.
Optionally, the enrollment knowledge base includes one or more of following knowledge base：General enrollment knowledge base, be directed to one
School's enrollment knowledge base of individual or multiple school sides and the source of students ground knowledge base of recruiting student for one or more sources of students ground.
Optionally, the enrollment knowledge base includes general enrollment knowledge base, also includes the school of one or more school sides
Enrollment knowledge base and/or the source of students ground knowledge base of recruiting student for one or more sources of students ground, current request described in the combination will
Plain and described historical requests key element coupling enrollment knowledge base includes：Judge the current request key element and the historical requests key element
In whether include school information or source of students ground information；If so, then with corresponding school enrollment knowledge base or source of students ground knowledge of recruiting student
Storehouse matches；If it is not, then matching with the general enrollment knowledge base.
Optionally, current request key element described in the combination and historical requests key element coupling enrollment knowledge base include：
If all comprising school information or source of students ground information in the current request key element and the historical requests key element, judging described working as
Whether front request key element is consistent with the school information included in the historical requests key element and/or source of students ground information；If consistent,
Knowledge base of recruiting student matches with recruiting student knowledge base or source of students with corresponding school；If having inconsistent, user is pointed out to select described
In current request key element and the historical requests key element inconsistent school information and/or source of students ground information, with corresponding
School enrollment knowledge base or source of students ground enrollment knowledge base match；If or have inconsistent, according in the current request key element
Knowledge base of recruiting student matches with recruiting student knowledge base or source of students with corresponding school for school information and/or source of students ground information.
Optionally, the current request information for obtaining user includes to obtain current request by way of following at least one
Information：Wechat, webpage, application software, phone, note, tangible machine people and independently seek advice from terminal.
Optionally, the enrollment knowledge base includes：Local enrollment knowledge base and at least one outside enrollment knowledge base, described
Local enrollment knowledge base is connected with the outside knowledge base of recruiting student by external interface.
Optionally, mating enrollment knowledge base according to the current request key element includes：Described local enrollment knowledge base and
The enrollment knowledge base associated with least a portion of the current request key element is selected at least one outside enrollment knowledge base；Root
Enrollment knowledge base according to the current request key element match selection.
Optionally, the outside enrollment knowledge base include following any one：The database of different school sides, is wherein stored with
School admission imformation and/or enrollment policy；Third-party database, be wherein stored with enrollment network question and answer and/or evaluation.
Optionally, the enrollment answering method also includes：Provide a user with multiple recommend ask, user therefrom select one or
Multiple recommendations are asked as the current request information.
Optionally, the enrollment answering method also includes：If it fails to match, rhetorical question message is sent to the user, with
So that user is supplemented to the current request information.
Optionally, the rhetorical question message includes the side information related to the current request information and/or recommendation information.
Optionally, after the current request answer is sent to user, also include：Recommend to the user current with described
The related other information of request answer and/or current request information.
Optionally, the current request information of the user is voice messaging；Obtained based on described current by speech recognition
The request text of solicited message.
Optionally, include to the request to carrying out nature semantic understanding based on the request text of the current request information
Text carries out following at least one fault-tolerant revision：Illegal word is filtered, sews filtration in front and back, stops word filtration and phonetic filtration.
The embodiment of the present invention also provides a kind of enrollment question and answer system, including：Current request key element acquiring unit, for obtaining
The current request information of user, to carrying out nature semantic understanding based on the request text of the current request information, to be worked as
Front request key element；Enrollment knowledge base matching unit, for mating enrollment knowledge base according to the current request key element；Request answer
Unit, if for the match is successful, sends out to the user according to the request answer that matching result obtains the current request information
Send the request answer.
Optionally, the enrollment knowledge base matching unit includes：Historical requests key element determining unit, for determining that history please
Seek key element, the historical requests key element be the historical requests information to the user carry out request that nature semantic understanding obtains will
Element；In conjunction with matching unit, for combining the current request key element and historical requests key element coupling enrollment knowledge base.
Optionally, the enrollment knowledge base includes one or more of following knowledge base：General enrollment knowledge base, be directed to one
School's enrollment knowledge base of individual or multiple school sides and the source of students ground knowledge base of recruiting student for one or more sources of students ground.
Optionally, the enrollment knowledge base includes general enrollment knowledge base, also includes the school of one or more school sides
Enrollment knowledge base and/or the source of students ground knowledge base of recruiting student for one or more sources of students ground, the combination matching unit include：The
One judging unit, for judging whether include school information or source of students in the current request key element and the historical requests key element
Ground information；First matching unit, for when the judged result of the judging unit is for being, with corresponding school enrollment knowledge base
Or source of students ground enrollment knowledge base matches；Second matching unit, for the judged result in first judging unit for no when,
Match with the general enrollment knowledge base.
Optionally, the combination matching unit includes：Second judging unit, in the current request key element and described
When all including school information or source of students ground information in historical requests key element, the current request key element and the historical requests are judged
The school information included in key element and/or source of students ground information whether consistent；3rd matching unit, single for judging described second
The judged result of unit is for, when being, knowledge base of recruiting student matches with recruiting student knowledge base or source of students with corresponding school；Tip element or
4th matching unit, wherein：Tip element, for the judged result in second judging unit for no when, point out user choosing
Select in the current request key element and the historical requests key element inconsistent school information and/or source of students ground information, with right
Knowledge base of recruiting student matches with recruiting student knowledge base or source of students for the school that answers；4th matching unit, single for judging described second
When the judged result of unit is no, according to the school information in the current request key element and/or source of students ground information and corresponding
School enrollment knowledge base or source of students ground enrollment knowledge base match.
Optionally, the current request key element acquiring unit is used for obtaining current request letter by way of following at least one
Breath：Wechat, webpage, application software, phone, note, tangible machine people and independently seek advice from terminal.
Optionally, the enrollment knowledge base includes：Local enrollment knowledge base and at least one outside enrollment knowledge base, described
Local enrollment knowledge base is connected with the outside knowledge base of recruiting student by external interface.
Optionally, the enrollment knowledge base matching unit includes：Knowledge base select unit, for knowing in the local enrollment
Knowing in the knowledge base of recruiting student outside with least one of storehouse selects the enrollment associated with least a portion of the current request key element to know
Know storehouse；5th matching unit, for the enrollment knowledge base according to the current request key element match selection.
Optionally, the outside enrollment knowledge base include following any one：The database of different school sides, is wherein stored with
School admission imformation and/or enrollment policy；Third-party database, be wherein stored with enrollment network question and answer and/or evaluation.
Optionally, the enrollment question and answer system also includes：Recommend unit is asked, ask for providing a user with multiple recommendations, use
Family therefrom selects one or more recommendations to ask as the current request information.
Optionally, the enrollment question and answer system also includes：Rhetorical question unit, for when it fails to match, sending out to the user
Rhetorical question message is sent, so that user is supplemented to the current request information.
Optionally, the rhetorical question message includes the side information related to the current request information and/or recommendation information.
Optionally, the enrollment question and answer system also includes：Recommendation unit, for answering to user's transmission current request
After case, recommend the other information related to the current request answer and/or current request information to the user.
Optionally, the current request information of the user is voice messaging；The current request key element acquiring unit is used for
Request text based on the current request information is obtained by speech recognition.
Optionally, the current request key element acquiring unit is fault-tolerant for carrying out following at least one to the request text
Revision：Illegal word is filtered, sews filtration in front and back, stops word filtration and phonetic filtration.
Compared with prior art, the technical scheme of the embodiment of the present invention has the advantages that：
In embodiments of the present invention, the request text to current request information carries out natural language understanding, current to obtain
Request key element, and enrollment knowledge base is mated according to the current request key element, if the match is successful, institute is obtained according to matching result
The request answer for stating current request information sends the request answer to the user.By semantic to asking text to carry out nature
Understand obtain current request key element, obtained from current request key element identifiability higher, therefore according to the current request will
Element coupling enrollment knowledge base, the probability that the match is successful is far longer than directly carries out text matches using counseling problem, so that
Enrollment answering method in the embodiment of the present invention can give reply to more current request information, and then can be more
The efficiency of upper lifting enrolment consultation process, and cost-effective, also improve the intelligent level of enrollment answering method further.
Description of the drawings
Fig. 1 is a kind of flow chart of enrollment answering method in the embodiment of the present invention；
Fig. 2 is a kind of flow chart for implementing of step S12 in Fig. 1；
Fig. 3 is a kind of flow chart for implementing of step S22 in Fig. 2；
Fig. 4 is the flow chart that the another kind of step S22 in Fig. 2 is implemented；
Fig. 5 is another flow chart for implementing of step S22 in Fig. 2
A kind of structural representation of enrollment question and answer system in Fig. 6 embodiment of the present invention；
Fig. 7 is a kind of structural representation for implementing of enrollment knowledge base matching unit 62 in Fig. 6；
Fig. 8 is a kind of structural representation for implementing in Fig. 7 with reference to matching unit 72；
Fig. 9 a is the structural representation implemented with reference to the another kind of matching unit 72 in Fig. 7；
Fig. 9 b is another structural representation for implementing in Fig. 7 with reference to matching unit 72；
Figure 10 is the structural representation that the another kind of enrollment knowledge base matching unit 62 in Fig. 6 is implemented.
Specific embodiment
As it was previously stated, existing automatic reply method, by detecting that whether counseling problem is the counseling problem that occurred,
If the counseling problem for having occurred is then automatically replied.
But, due to the diversity of natural language, only by detecting the whether literal repetition of counseling problem, can automatically reply
Problem less, coverage rate is less, and the improved efficiency to whole consultation process is less, and intelligent level has to be hoisted.
In embodiments of the present invention, the request text to current request information carries out natural language understanding, current to obtain
Request key element, and enrollment knowledge base is mated according to the current request key element, if the match is successful, institute is obtained according to matching result
The request answer for stating current request information sends the request answer to the user.
As the current request key element for obtaining is to asking text to carry out obtaining after nature semantic understanding, machine can recognize that
Property higher, therefore enrollment knowledge base is mated according to the current request key element, the probability that the match is successful is far longer than directly using consulting
Inquiry topic carries out text matches, more current request information can be given so as to the enrollment answering method in the embodiment of the present invention
With reply, and then the efficiency of enrolment consultation process can be lifted to a greater extent, and cost-effective, also improve enrollment further
The intelligent level of answering method.
Above-mentioned purpose, feature and beneficial effect for enabling the present invention become apparent from understandable, below in conjunction with the accompanying drawings to this
The specific embodiment of invention is described in detail.
Fig. 1 is a kind of flow chart of enrollment answering method in the embodiment of the present invention, specifically may include steps of：
Step S11, obtains the current request information of user, to being carried out certainly based on the request text of the current request information
Right semantic understanding, to obtain current request key element；
Step S12, mates enrollment knowledge base according to the current request key element, if the match is successful, according to matching result
The request answer for obtaining the current request information sends the request answer to the user.
Wherein, the current request information of user can be from the information of multiple channel, can be for example by with down to
A kind of few mode gets：Wechat, webpage, application software, phone, note, tangible machine people and independently seek advice from terminal.User
Current request information can include one or more type information, can for example include voice messaging, Word message, picture
One or more in information.
Can be that specific aim is carried out based on different types of current request information based on the request text of current request information
Process obtain, such as when in solicited message comprising non-legible information, type can be carried out to these non-legible information and turn
Change, be converted into Word message.
In a non-limiting example, the current request information of user is voice messaging, can pass through speech recognition,
Obtain the request text based on the current request information.
To asking text to carry out nature semantic understanding, can include to asking text to carry out fault-tolerant revision, with to a greater extent
Obtain ask the key message of text, and determine request key element.Can specifically include to asking the word in text to carry out
Filter, for example, can carry out any one or more filtration following：Illegal word is filtered, sews filtration in front and back, stops word filtration and phonetic filtration.
Illegal word filters, sews filtrations in front and back, stop that word is filtered and phonetic filters and can be based on corresponding illegal dictionary, sew in front and back
Storehouse, stop dictionary, phonetic storehouse and carry out.Illegal word is filtered and can filter out the illegal word such as dirty word；Stop word filtration and can filter out deactivation
Word；Phonetic is filtered and can directly filter out phonetic, or word is changed in front and back by phonetic combination, to obtain corresponding word.
Current request key element can include the index entry needed for coupling enrollment knowledge base, for example school, province, fraction, specially
Industry, arts and science etc..Enrollment knowledge base is mated according to current request key element, can be included using the rope included in current request key element
Draw item coupling enrollment knowledge base.Enrollment knowledge base is mated according to current request key element, when the match is successful, is sent to user described
Request answer, it is also ensured that the accuracy of request answer.The complete of corresponding current request can be included in the request answer
Describing mode, to reduce the possibility that user error understands answer.
Step S11 and step S12 are illustrated with a non-limiting example below：The text of current request information
For " hello, and I has examined 490 points, and I is that SS saves examinee, can enter oneself for the examination what specialty of XX school "；By natural semantic understanding, obtain
Current request key element can be：" 490 points ", " SS province ", " XX school " " specialty "；Now according to current request key element to enrollment
After knowledge base is mated, following answer can be made：" XX school yyyy saves plan in SS and recruits zzzz, mmmm specialty, yyyy
Year acceptance cut-off point are ... ".
Fig. 2 is a kind of flow chart for implementing of step S12 in Fig. 1, specifically may comprise steps of：
Step S21, determines historical requests key element, and the historical requests key element is that the historical requests information to the user is entered
The request key element that row nature semantic understanding is obtained；
Step S22, in conjunction with the current request key element and historical requests key element coupling enrollment knowledge base.
Historical requests information is the solicited message of same user corresponding with current request information, can by ID or
Dialog procedure determines corresponding relation.
The reception mode of historical requests information and type can be believed the same as or similar to current request information to historical requests
Breath carries out processing the mode for obtaining historical requests key element can also or class identical with the mode processed by current request information
Seemingly, here is not all repeated.
The current request information and historical requests information of user may each be the solicited message based on counseling problem, or
The information of own situation is described.
It is further described below by way of a non-limiting example：The request text of current request information is " many
Few point can above XX university ", and to should be in the historical requests information of user comprising " I is that SS is saved ".Now, if merely with
The current request key element that current request information is obtained, it is more difficult to which the match is successful with enrollment knowledge base, if but combining and being believed by historical requests
The historical requests key element that breath is obtained, then successfully can be mated.
In being embodied as, knowledge base of recruiting student can include one or more of following knowledge base：General enrollment knowledge base,
School's enrollment knowledge base for one or more school sides and the source of students ground knowledge base of recruiting student for one or more sources of students ground.
Referring to Fig. 3, in an embodiment of the present invention, the enrollment knowledge base includes general enrollment knowledge base, also includes one
School's enrollment knowledge base of individual or multiple school sides and/or the source of students ground knowledge base of recruiting student for one or more sources of students ground, step
Rapid S22 may include steps of：
Step S221, judges whether include school information or life in the current request key element and the historical requests key element
Source ground information；If so, then execution step S222, if it is not, then execution step S223.
Step S222, knowledge base of recruiting student matches with recruiting student knowledge base or source of students with corresponding school；
Step S223, is matched with the general enrollment knowledge base.
Due to being directed to different schools, or for different sources of students ground, user's concern might have different features, therefore
Knowledge base is made a distinction, is divided into general-purpose knowledge bases and targetedly knowledge base, certain can be pointed in current request information
School, or when current request information points to certain source of students ground, mate what current request information was pointed to according to current request key element
Knowledge base in school or source of students ground, it is hereby achieved that more accurately ask answer.
By arranging general enrollment knowledge base so that the enrollment answering method in the embodiment of the present invention goes for more
Scene, when being not directed to certain school or source of students ground in the current request information of user, it is also possible to mated, go forward side by side one
Step provides request answer.
In intelligent answer field, typically, if user can be solved the problems, such as by intelligent answer, without the need for being manually situated between
Enter；If conversely, user cannot be solved the problems, such as by intelligent answer, needing manpower intervention.If therefore the answer of intelligent answer is accurate
Really property is higher, and specific aim is stronger, then can save manual resource, lifts the efficiency of enrollment process further.
Fig. 4 is the flow chart that the another kind of step S22 in Fig. 2 is implemented, and specifically may include steps of：
Step S41, determines all comprising school information or source of students in the current request key element and the historical requests key element
Ground information；
Step S42, judges school information and/or the life included in the current request key element and the historical requests key element
Whether ground information in source is consistent；If consistent, execution step S43, otherwise, execution step S44.
Step S43, knowledge base of recruiting student matches with recruiting student knowledge base or source of students with corresponding school；
Step S44, points out user to select inconsistent school in the current request key element and the historical requests key element
Information and/or source of students ground information, so that knowledge base of recruiting student matches with recruiting student knowledge base or source of students with corresponding school；Or according to institute
State the school information in current request key element and/or source of students ground information is recruited student with corresponding school and known with recruiting student knowledge base or source of students
Know storehouse to match.
In being embodied as, enrollment knowledge base can include：Local enrollment knowledge base and at least one outside enrollment knowledge
Storehouse, the local enrollment knowledge base are connected with the outside knowledge base of recruiting student by external interface.
Local enrollment knowledge base may be located at the server for providing enrollment question and answer service, and outside enrollment knowledge base can be logical
The knowledge base that network is connected with local enrollment knowledge base is crossed with external interface.By arranging external knowledge storehouse, can cause to recruit
Raw knowledge base is more complete, such that it is able to respond to more user's current request information.
Fig. 5 is another flow chart for implementing of step S22 in Fig. 2, specifically may include steps of：
Step S51, selects in knowledge base of recruiting student current with described outside the local enrollment knowledge base and at least one
The enrollment knowledge base of at least a portion association of request key element；
Step S52, according to the enrollment knowledge base of the current request key element match selection.
Wherein, the outside enrollment knowledge base can include following any one：The database of different school sides, wherein stores
There are school admission imformation and/or enrollment policy；Third-party database, be wherein stored with enrollment network question and answer and/or evaluation.
For example, include that XX school and source of students ground SS save time in current request key element, if the local enrollment knowledge base is
For the knowledge base of XX school, external knowledge storehouse include to store the enrollment knowledge base of SS province enrollment policy be stored with to XX
The network question and answer of school and/or the enrollment knowledge base of evaluation, then can according to the local enrollment knowledge base of current request key element coupling,
The enrollment knowledge base of storage SS province enrollment policy, and the enrollment of be stored with the network question and answer to XX school and/or evaluation knows
Know storehouse.
With continued reference to Fig. 1, the enrollment answering method of the embodiment of the present invention can also include：Provide a user with multiple recommendations
Ask, user therefrom selects one or more recommendations to ask as current request information in step S11.
Can be during user input, the keyword according to user input provides a user with recommendation and asks, for example, works as user
During input " XX school ", the recommendation for providing is asked can be " XX school recruits how many people ", " XX school score line ", or " XX school
There is which school district ".
In being embodied as, if it fails to match in step S12, rhetorical question message can be sent to the user, so that
Obtain user to supplement the current request information.
Wherein, rhetorical question message includes the side information related to the current request information and/or recommendation information.
For example, when the current request information of user is " your school PP specialty ", according to being obtained based on current request information
Current request key element it fails to match is carried out to knowledge base of recruiting student, now can send rhetorical question message to user, for example, can send out
Send：" you may want to ask be：1st, PP specialty how many people is recruited this year？Or 2, pp undergraduate course is in which school district "；Or can also send out
" may I ask you to take an examination " is sent in what province.
In the enrollment answering method of the embodiment of the present invention, after step s 12, step S13 can also be included：To described
User recommends the other information related to the current request answer and/or current request information.The recommendation of other information is permissible
Be based on the data statistics to question and answer.
For example, when the request text of user's current request information is for " hello, and I has examined 490 points, and I is that SS saves examinee, energy
What specialty of XX school entered oneself for the examination ", after mating to knowledge base of recruiting student according to current request key element, make following answer：" XX
School yyyy saves plan in SS and recruits zzzz, mmmm specialty, and yyyy acceptance cut-off point are ... ".
After this, " perhaps you also wonder can also to recommend other information to user：1st, the school district distribution of XX school；
2nd, XX school saves in SS and recruits that how many people 3, XX school have which key discipline and Characteristic Speciality ".
In embodiments of the present invention, the request text to current request information carries out natural language understanding, current to obtain
Request key element, and enrollment knowledge base is mated according to the current request key element, if the match is successful, institute is obtained according to matching result
The request answer for stating current request information sends the request answer to the user.By semantic to asking text to carry out nature
Understand obtain current request key element, obtained from current request key element identifiability higher, therefore according to the current request will
Element coupling enrollment knowledge base, the probability that the match is successful is far longer than directly carries out text matches using counseling problem, so as to this
Enrollment answering method in bright embodiment can give reply to more current request information, and then can carry to a greater extent
The efficiency of enrolment consultation process is risen, and cost-effective, also improve the intelligent level of enrollment answering method further.
The embodiment of the present invention also provides a kind of enrollment question and answer system, and its structural representation is referring to Fig. 6.Enrollment question and answer system tool
Body can include：
Current request key element acquiring unit 61, for obtaining the current request information of user, to being based on the current request
The request text of information carries out nature semantic understanding, to obtain current request key element；
Enrollment knowledge base matching unit 62, for mating enrollment knowledge base according to the current request key element；
Request answer unit 63, if for the match is successful, obtains asking for the current request information according to matching result
Answer is asked to send the request answer to the user.
Enrollment question and answer system can be integrated in the server for providing enrollment question and answer service, and the server can be distributed clothes
Business device, enrollment question and answer system can also be distributed in enrollment question and answer robot server, and wherein, question and answer robot can also be regarded as
Server.For example, realization part and the request answer list of user request information are obtained in current request key element acquiring unit 61
The realization part for the request answer being sent to the user in unit 63 may be located at enrollment question and answer robot.
Current request key element acquiring unit 61 can obtain current request information by way of following at least one：Wechat,
Webpage, application software, phone, note, tangible machine people and independently seek advice from terminal.
When the current request information of user is voice messaging, current request key element acquiring unit 61 can also be adopted including voice
Acquisition means collected sound signal, the current request key element acquiring unit 61 can be entered to voice signal by speech recognition equipment
Row identification, to obtain the request text based on the current request information.In being embodied as, current request key element acquiring unit
61 can be to asking text to carry out following at least one fault-tolerant revision：Illegal word filters, sews filtration in front and back, stops word filtration and phonetic
Filter.
Carry out filtering illegal word filter, sew in front and back filtrations, stop process that word filters can based on the coupling carried out by dictionary,
Carry out phonetic filtration and can be based on phonetic identifying device.
Enrollment knowledge base is mated according to current request key element, when the match is successful, the request answer is sent to user,
Can ensure that the accuracy of request answer.The complete describing mode of corresponding current request can be included in the request answer, with
Reduce the possibility that user error understands answer.
Referring to Fig. 7, in being embodied as, enrollment knowledge base matching unit 62 can include：
Historical requests key element determining unit 71, for determining historical requests key element, the historical requests key element be to described
The historical requests information of user carries out the request key element that nature semantic understanding is obtained；
In conjunction with matching unit 72, for combining the current request key element and historical requests key element coupling enrollment knowledge
Storehouse.
Wherein, historical requests key element determining unit 71 by the interface of detection user input or ID judgement can be
The no solicited message for belonging to same user input, using the solicited message for belonging to same user input as historical requests information.
In being embodied as, the enrollment knowledge base includes one or more of following knowledge base：General enrollment knowledge base,
School's enrollment knowledge base for one or more school sides and the source of students ground knowledge base of recruiting student for one or more sources of students ground.
Referring to Fig. 8, in an embodiment of the present invention, the enrollment knowledge base includes general enrollment knowledge base, also includes one
School's enrollment knowledge base of individual or multiple school sides and/or the source of students ground knowledge base of recruiting student for one or more sources of students ground, knot
Closing matching unit 72 can include：
First judging unit 81, for judging whether include to learn in the current request key element and the historical requests key element
School information or source of students ground information；
First matching unit 82, for when the judged result of the judging unit is for being, recruiting student with corresponding school and knowing
Know storehouse or source of students ground enrollment knowledge base matches；
Second matching unit 83, for the judged result in first judging unit for no when, with the general enrollment
Knowledge base matches.
Wherein, the first judging unit 81 can be by recognizing current request key element and the key in the historical requests key element
Word, judges whether include school information or source of students ground information in the current request key element and the historical requests key element.
Due to being directed to different schools, or for different sources of students ground, user's concern might have different features, therefore
Knowledge base is made a distinction, is divided into general-purpose knowledge bases and targetedly knowledge base, certain can be pointed in current request information
School, or when current request information points to certain source of students ground, mate what current request information was pointed to according to current request key element
Knowledge base in school or source of students ground, it is hereby achieved that more accurately ask answer.
By arranging general enrollment knowledge base so that the enrollment answering method in the embodiment of the present invention goes for more
Scene, when being not directed to certain school or source of students ground in the current request information of user, it is also possible to mated, go forward side by side one
Step provides request answer.
Fig. 9 a is the structural representation implemented with reference to the another kind of matching unit 72 in Fig. 7, can specifically include：
Second judging unit 91, for all believing comprising school in the current request key element and the historical requests key element
When breath or source of students ground information, judge the school information that includes in the current request key element and the historical requests key element and/or
Whether source of students ground information is consistent；
3rd matching unit 92, for when the judged result of second judging unit is for being, recruiting with corresponding school
Raw knowledge base or source of students ground enrollment knowledge base match；
Tip element 93, for the judged result in second judging unit for no when, point out user to select described working as
Front request key element and the historical requests key element in inconsistent school information and/or source of students ground information, with corresponding school
Enrollment knowledge base or source of students ground enrollment knowledge base match.
In being embodied as, enrollment knowledge base can include：Local enrollment knowledge base and at least one outside enrollment knowledge
Storehouse, the local enrollment knowledge base are connected with the outside knowledge base of recruiting student by external interface.
Local enrollment knowledge base may be located at the server for providing enrollment question and answer service, and outside enrollment knowledge base can be logical
The knowledge base that network is connected with local enrollment knowledge base is crossed with external interface.By arranging external knowledge storehouse, can cause to recruit
Raw knowledge base is more complete, such that it is able to respond to more user's current request information.
Fig. 9 b is another structural representation for implementing in Fig. 7 with reference to matching unit 72, can equally include：The
Two judging units 91, the 3rd matching unit 92, in addition can include the 4th matching unit 94, in second judging unit
Judged result for no when, according to the school information in the current request key element and/or source of students ground information and corresponding school
Enrollment knowledge base or source of students ground enrollment knowledge base match.
In being embodied as, the enrollment knowledge base can include：Local enrollment knowledge base and at least one outside enrollment
Knowledge base, the local enrollment knowledge base are connected with the outside knowledge base of recruiting student by external interface.
Wherein, the outside enrollment knowledge base include following any one：The database of different school sides, be wherein stored with trick
Raw information and/or enrollment policy；Third-party database, be wherein stored with enrollment network question and answer and/or evaluation.
Referring to Figure 10, knowledge base of recruiting student matching unit 62 can include：
Knowledge base select unit 101, for recruiting student in knowledge base outside the local enrollment knowledge base and at least one
Select the enrollment knowledge base associated with least a portion of the current request key element；
5th matching unit 102, for the enrollment knowledge base according to the current request key element match selection.
Wherein, knowledge base select unit 101 can be by mating the keyword in current request key element, with enrollment knowledge base
In keyword, select the enrollment knowledge base associated with least a portion of the current request key element.
With continued reference to Fig. 6, question and answer system of recruiting student can also be including recommending to ask unit 64, for providing a user with multiple recommendations
Ask, user therefrom selects one or more recommendations to ask as the current request information.
Enrollment question and answer system can also include rhetorical question unit 65, for when it fails to match, sending rhetorical question to the user
Message, so that user is supplemented to the current request information.
Wherein, the rhetorical question message can include the side information related to the current request information and/or recommendation
Breath.
Enrollment question and answer system can also include recommendation unit 66, for sending the current request answer to user
Afterwards, recommend the other information related to the current request answer and/or current request information to the user.
Recommend to ask that unit 64, rhetorical question unit 65 and recommendation unit 66 all can coordinate work with user oriented suggestion device
Make, such as display screen, voice playing device etc., recommendation is provided a user with using suggestion device and ask, ask in reply message and/or other letters
Breath.
In embodiments of the present invention, the request text to current request information carries out natural language understanding, current to obtain
Request key element, and enrollment knowledge base is mated according to the current request key element, if the match is successful, institute is obtained according to matching result
The request answer for stating current request information sends the request answer to the user.By semantic to asking text to carry out nature
Understand obtain current request key element, obtained from current request key element identifiability higher, therefore according to the current request will
Element coupling enrollment knowledge base, the probability that the match is successful is far longer than directly carries out text matches using counseling problem, so as to this
Enrollment answering method in bright embodiment can give reply to more current request information, and then can carry to a greater extent
The efficiency of enrolment consultation process is risen, and cost-effective, also improve the intelligent level of enrollment answering method further.
The explanation of each noun that the enrollment question and answer system in the embodiment of the present invention is related to, concrete application scene etc. may refer to
Enrollment answering method, will not be described here.
The each unit in enrollment question and answer system in the embodiment of the present invention can be using one or more general processor knots
Close interactive device to realize.General processor can be microprocessor, but in alternative, the processor can be any routine
Processor, controller, microcontroller or state machine.Processor is also implemented as the combination of computing device, such as DSP
With the combining of microprocessor, one or more microprocessors that multi-microprocessor is cooperated with DSP core or any other this
Class is configured.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
Completed with instructing the hardware of correlation by program, the program can be stored in a computer-readable recording medium, storage
Medium can include：ROM, RAM, disk or CD etc..
Although present disclosure is as above, the present invention is not limited to this.Any those skilled in the art, without departing from this
In the spirit and scope of invention, can all make various changes or modifications, therefore protection scope of the present invention should be with claim institute
The scope of restriction is defined.
Claims (30)
1. a kind of enrollment answering method, it is characterised in that include：
The current request information of user is obtained, to carrying out nature semantic understanding based on the request text of the current request information,
To obtain current request key element；
Enrollment knowledge base is mated according to the current request key element, if the match is successful, is obtained according to matching result described current
The request answer of solicited message sends the request answer to the user.
2. enrollment answering method according to claim 1, it is characterised in that according to current request key element coupling enrollment
Knowledge base includes：
Determine historical requests key element, the historical requests key element is that the historical requests information to the user carries out the semantic reason of nature
The request key element that solution is obtained；
In conjunction with the current request key element and historical requests key element coupling enrollment knowledge base.
3. enrollment answering method according to claim 2, it is characterised in that the enrollment knowledge base includes following knowledge base
One or more：General enrollment knowledge base, the school's enrollment knowledge base for one or more school sides and for one or
The source of students ground enrollment knowledge base on multiple source of students ground.
4. enrollment answering method according to claim 3, it is characterised in that the enrollment knowledge base includes that general enrollment is known
Know storehouse, also include school's enrollment knowledge base and/or the source of students ground for one or more sources of students ground of one or more school sides
Enrollment knowledge base, current request key element described in the combination and historical requests key element coupling enrollment knowledge base include：
Judge in the current request key element and the historical requests key element, whether to include school information or source of students ground information；
If so, then with corresponding school enrollment knowledge base or source of students knowledge base of recruiting student match；
If it is not, then matching with the general enrollment knowledge base.
5. enrollment answering method according to claim 3, it is characterised in that current request key element described in the combination and institute
Stating historical requests key element coupling enrollment knowledge base includes：
If all comprising school information or source of students ground information in the current request key element and the historical requests key element, judging institute
State current request key element whether consistent with the school information included in the historical requests key element and/or source of students ground information；
If consistent, knowledge base of recruiting student matches with recruiting student knowledge base or source of students with corresponding school；
If there is inconsistent, inconsistent school in the prompting user selection current request key element and the historical requests key element
Information and/or source of students ground information, so that knowledge base of recruiting student matches with recruiting student knowledge base or source of students with corresponding school；
If or have inconsistent, according to the school information in the current request key element and/or source of students ground information and corresponding
School enrollment knowledge base or source of students ground enrollment knowledge base match.
6. enrollment answering method according to claim 1, it is characterised in that the current request packet of the acquisition user
Including, current request information is obtained by way of following at least one：Wechat, webpage, application software, phone, note, tangible machine
People and autonomous consulting terminal.
7. enrollment answering method according to claim 1, it is characterised in that the enrollment knowledge base includes：Local enrollment
Knowledge base and at least one outside enrollment knowledge base, the local enrollment knowledge base are known by external interface and the outside enrollment
Know storehouse to be connected.
8. enrollment answering method according to claim 7, it is characterised in that according to current request key element coupling enrollment
Knowledge base includes：
Select with the current request key element extremely in knowledge base of recruiting student outside the local enrollment knowledge base and at least one
The enrollment knowledge base of few part association；
Enrollment knowledge base according to the current request key element match selection.
9. enrollment answering method according to claim 7, it is characterised in that the outside enrollment knowledge base includes following
A kind of：The database of different school sides, the school admission imformation that is wherein stored with and/or enrollment policy；Third-party database, wherein deposits
Contain enrollment network question and answer and/or evaluation.
10. enrollment answering method according to claim 1, it is characterised in that also include：Provide a user with multiple recommendations
Ask, user therefrom selects one or more recommendations to ask as the current request information.
11. enrollment answering methods according to claim 1, it is characterised in that also include：If it fails to match, to described
User sends rhetorical question message, so that user is supplemented to the current request information.
12. enrollment answering methods according to claim 11, it is characterised in that the rhetorical question message includes current with described
The related side information of solicited message and/or recommendation information.
13. enrollment answering methods according to claim 1, it is characterised in that answer the current request is sent to user
After case, also include：Recommend the other information related to the current request answer and/or current request information to the user.
14. enrollment answering methods according to claim 1, it is characterised in that the current request information of the user is language
Message ceases；Request text based on the current request information is obtained by speech recognition.
The 15. enrollment answering methods according to any one of claim 1 to 14, it is characterised in that to currently please based on described
Ask information request text carry out nature semantic understanding include to described request text carry out following at least one fault-tolerant revision：Non-
Method word is filtered, sews filtration in front and back, stops word filtration and phonetic filtration.
16. a kind of enrollment question and answer systems, it is characterised in that include：
Current request key element acquiring unit, for obtaining the current request information of user, to based on the current request information
Request text carries out nature semantic understanding, to obtain current request key element；
Enrollment knowledge base matching unit, for mating enrollment knowledge base according to the current request key element；
Request answer unit, if for the match is successful, obtains the request answer of the current request information according to matching result
The request answer is sent to the user.
17. enrollment question and answer systems according to claim 16, it is characterised in that the enrollment knowledge base matching unit bag
Include：
Historical requests key element determining unit, for determining historical requests key element, the historical requests key element be to the user
Historical requests information carries out the request key element that nature semantic understanding is obtained；
In conjunction with matching unit, for combining the current request key element and historical requests key element coupling enrollment knowledge base.
18. enrollment question and answer systems according to claim 17, it is characterised in that the enrollment knowledge base includes following knowledge
One or more of storehouse：General enrollment knowledge base, for one or more school sides school enrollment knowledge base and be directed to one
Or the source of students ground enrollment knowledge base on multiple source of students ground.
19. enrollment question and answer systems according to claim 18, it is characterised in that the enrollment knowledge base includes general enrollment
Knowledge base, also includes school's enrollment knowledge base and/or the source of students for one or more sources of students ground of one or more school sides
Ground enrollment knowledge base, the combination matching unit include：
First judging unit, for judging whether include school information in the current request key element and the historical requests key element
Or source of students ground information；
First matching unit, for the judged result of the judging unit for be when, with corresponding school enrollment knowledge base or
Source of students ground enrollment knowledge base matches；
Second matching unit, for the judged result in first judging unit for no when, with the general enrollment knowledge base
Match.
20. enrollment question and answer systems according to claim 18, it is characterised in that the combination matching unit includes：
Second judging unit, for all comprising school information or life in the current request key element and the historical requests key element
During source ground information, school information and/or the source of students ground included in the current request key element and the historical requests key element is judged
Whether information is consistent；
3rd matching unit, for when the judged result of second judging unit is for being, with corresponding school enrollment knowledge
Storehouse or source of students ground enrollment knowledge base match；
Tip element or the 4th matching unit, wherein：
Tip element, for the judged result in second judging unit for no when, point out user to select the current request
In key element and the historical requests key element, inconsistent school information and/or source of students ground information, are known with being recruited student with corresponding school
Know storehouse or source of students ground enrollment knowledge base matches；
4th matching unit, for the judged result in second judging unit for no when, according to the current request key element
In school information and/or source of students ground information and corresponding school enrollment knowledge base or source of students knowledge base of recruiting student match.
21. enrollment question and answer systems according to claim 16, it is characterised in that the current request key element acquiring unit is used
In obtaining current request information by way of following at least one：Wechat, webpage, application software, phone, note, tangible machine
People and autonomous consulting terminal.
22. enrollment question and answer systems according to claim 16, it is characterised in that the enrollment knowledge base includes：Local trick
Raw knowledge base and at least one outside enrollment knowledge base, the local enrollment knowledge base is by external interface and the outside enrollment
Knowledge base is connected.
23. enrollment question and answer systems according to claim 22, it is characterised in that the enrollment knowledge base matching unit bag
Include：
Knowledge base select unit, for selecting and institute in knowledge base of recruiting student outside the local enrollment knowledge base and at least one
State the enrollment knowledge base of at least a portion association of current request key element；
5th matching unit, for the enrollment knowledge base according to the current request key element match selection.
24. enrollment question and answer systems according to claim 22, it is characterised in that the outside enrollment knowledge base includes following
Any one：The database of different school sides, the school admission imformation that is wherein stored with and/or enrollment policy；Third-party database, wherein
Be stored with enrollment network question and answer and/or evaluation.
25. enrollment question and answer systems according to claim 16, it is characterised in that also include：Recommend ask unit, for
Family provides multiple recommendations and asks, user therefrom selects one or more recommendations to ask as the current request information.
26. enrollment question and answer systems according to claim 16, it is characterised in that also include：Rhetorical question unit, in coupling
During failure, rhetorical question message is sent to the user, so that user is supplemented to the current request information.
27. enrollment question and answer systems according to claim 26, it is characterised in that the rhetorical question message includes current with described
The related side information of solicited message and/or recommendation information.
28. enrollment question and answer systems according to claim 16, it is characterised in that also include：Recommendation unit, for
After family sends the current request answer, recommend and the current request answer and/or current request information phase to the user
The other information of pass.
29. enrollment question and answer systems according to claim 16, it is characterised in that the current request information of the user is language
Message ceases；The current request key element acquiring unit is used for obtaining the request based on the current request information by speech recognition
Text.
The 30. enrollment question and answer systems according to any one of claim 16 to 29, it is characterised in that the current request key element
Acquiring unit, for carrying out following at least one fault-tolerant revision to the request text：Illegal word filters, sews filtration in front and back, stops
Word is filtered and phonetic is filtered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610964054.9A CN106484916A (en) | 2016-11-04 | 2016-11-04 | A kind of enrollment answering method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610964054.9A CN106484916A (en) | 2016-11-04 | 2016-11-04 | A kind of enrollment answering method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106484916A true CN106484916A (en) | 2017-03-08 |
Family
ID=58271941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610964054.9A Pending CN106484916A (en) | 2016-11-04 | 2016-11-04 | A kind of enrollment answering method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106484916A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107225579A (en) * | 2017-05-27 | 2017-10-03 | 众德云格机器人（苏州）有限公司 | The machine question answering system of rhetorical question formula |
| CN107256226A (en) * | 2017-04-28 | 2017-10-17 | 北京神州泰岳软件股份有限公司 | The construction method and device of a kind of knowledge base |
| 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 |
| CN108090170A (en) * | 2017-12-14 | 2018-05-29 | 南京美桥信息科技有限公司 | A kind of intelligence inquiry method for recognizing semantics and visible intelligent interrogation system |
| CN108427722A (en) * | 2018-02-09 | 2018-08-21 | 卫盈联信息技术（深圳）有限公司 | intelligent interactive method, electronic device and storage medium |
| CN108984800A (en) * | 2018-08-22 | 2018-12-11 | 广东小天才科技有限公司 | Voice question searching method and terminal equipment |
| CN109829047A (en) * | 2019-01-21 | 2019-05-31 | 青牛智胜(深圳)科技有限公司 | A kind of intelligence assistant system and implementation method |
| CN110008324A (en) * | 2019-03-29 | 2019-07-12 | 上海大易云计算股份有限公司 | A kind of recruitment chat method and system based on natural semantic analysis |
| CN111026855A (en) * | 2019-12-06 | 2020-04-17 | 易小博(武汉)科技有限公司 | Intelligent customer service response method, system, controller and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101118554A (en) * | 2007-09-14 | 2008-02-06 | 中兴通讯股份有限公司 | Intelligent interactive request-answering system and processing method thereof |
| CN101193071A (en) * | 2007-03-28 | 2008-06-04 | 腾讯科技（深圳）有限公司 | A client service method, system and device based on instant communication |
| CN104090907A (en) * | 2014-05-28 | 2014-10-08 | 北京百度网讯科技有限公司 | Method and device for providing information for user in specific application field |
| CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
| CN105677822A (en) * | 2016-01-05 | 2016-06-15 | 首都师范大学 | Enrollment automatic question-answering method and system based on conversation robot |
-
2016
- 2016-11-04 CN CN201610964054.9A patent/CN106484916A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101193071A (en) * | 2007-03-28 | 2008-06-04 | 腾讯科技（深圳）有限公司 | A client service method, system and device based on instant communication |
| CN101118554A (en) * | 2007-09-14 | 2008-02-06 | 中兴通讯股份有限公司 | Intelligent interactive request-answering system and processing method thereof |
| CN104090907A (en) * | 2014-05-28 | 2014-10-08 | 北京百度网讯科技有限公司 | Method and device for providing information for user in specific application field |
| CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
| CN105677822A (en) * | 2016-01-05 | 2016-06-15 | 首都师范大学 | Enrollment automatic question-answering method and system based on conversation robot |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256226A (en) * | 2017-04-28 | 2017-10-17 | 北京神州泰岳软件股份有限公司 | The construction method and device of a kind of knowledge base |
| 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 |
| CN107256226B (en) * | 2017-04-28 | 2018-10-30 | 北京神州泰岳软件股份有限公司 | A kind of construction method and device of knowledge base |
| CN107225579A (en) * | 2017-05-27 | 2017-10-03 | 众德云格机器人（苏州）有限公司 | The machine question answering system of rhetorical question formula |
| CN108090170A (en) * | 2017-12-14 | 2018-05-29 | 南京美桥信息科技有限公司 | A kind of intelligence inquiry method for recognizing semantics and visible intelligent interrogation system |
| CN108427722A (en) * | 2018-02-09 | 2018-08-21 | 卫盈联信息技术（深圳）有限公司 | intelligent interactive method, electronic device and storage medium |
| CN108984800A (en) * | 2018-08-22 | 2018-12-11 | 广东小天才科技有限公司 | Voice question searching method and terminal equipment |
| CN108984800B (en) * | 2018-08-22 | 2020-10-16 | 广东小天才科技有限公司 | Voice question searching method and terminal equipment |
| CN109829047A (en) * | 2019-01-21 | 2019-05-31 | 青牛智胜(深圳)科技有限公司 | A kind of intelligence assistant system and implementation method |
| CN110008324A (en) * | 2019-03-29 | 2019-07-12 | 上海大易云计算股份有限公司 | A kind of recruitment chat method and system based on natural semantic analysis |
| CN111026855A (en) * | 2019-12-06 | 2020-04-17 | 易小博(武汉)科技有限公司 | Intelligent customer service response method, system, controller and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106484916A (en) | A kind of enrollment answering method and device | |
| CN107329967B (en) | Question answering system and method based on deep learning | |
| US10031983B2 (en) | Query tree navigation | |
| AU2020200909A1 (en) | Evaluation control | |
| US20230161801A1 (en) | Machine learning query session enhancement | |
| CN105488142B (en) | Performance information input method and system | |
| CN105989084B (en) | A kind of method and apparatus of reply problem | |
| CN109670023A (en) | Man-machine automatic top method for testing, device, equipment and storage medium | |
| Cardno et al. | Documentary analysis hui: An emergent bricolage method for culturally responsive qualitative research | |
| CN104809920A (en) | Personalized learning method and device | |
| CN103699955B (en) | Business model analysis method and device based on self-defined classifying rules | |
| CN111178940B (en) | Method and system for automatically generating sales call operation map | |
| CN106780223A (en) | A kind of method and system of intelligent recommendation college entrance will table | |
| CN108763548A (en) | Collect method, apparatus, equipment and the computer readable storage medium of training data | |
| WO2020042584A1 (en) | Method and system for training underperforming personnel, computer device, and storage medium | |
| CN106202288A (en) | The optimization method of a kind of man-machine interactive system knowledge base and system | |
| Piers William Ellway | Is the quantity-quality trade-off in call centres a false dichotomy? | |
| KR102276442B1 (en) | Method and device for providing information through screen recognition | |
| CN116383027B (en) | Man-machine interaction data processing method and server | |
| CN117236758A (en) | Method, device, equipment and storage medium for evaluating capability of data governance personnel | |
| CN117522185A (en) | Flexibly configurable evaluation method, system and terminal | |
| US11055329B2 (en) | Query and information meter for query session | |
| CN110532374A (en) | The processing method and processing device of insurance information | |
| US8051026B2 (en) | Rules collector system and method with user interaction | |
| Hedley et al. | Talking about results |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170308 |