CN109766422A - Information processing method, apparatus and system, storage medium, terminal - Google Patents
Information processing method, apparatus and system, storage medium, terminal Download PDFInfo
- Publication number
- CN109766422A CN109766422A CN201811637981.5A CN201811637981A CN109766422A CN 109766422 A CN109766422 A CN 109766422A CN 201811637981 A CN201811637981 A CN 201811637981A CN 109766422 A CN109766422 A CN 109766422A
- Authority
- CN
- China
- Prior art keywords
- expert
- label
- described problem
- user
- information processing
- 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
A kind of information processing method, apparatus and system, storage medium, terminal, the information processing method include: the problem of receiving user's input, and described problem is matched with the knowledge point in knowledge base;In response to it fails to match, the label of described problem, the classification of the label instruction described problem of described problem are determined;The corresponding relationship of label and each label and expert user according at least to described problem determines target expert;Described problem is pushed to the user terminal of the target expert.Technical solution of the present invention is able to ascend question and answer efficiency.
Description
Technical field
The present invention relates to natural language processing technique field more particularly to a kind of information processing method, apparatus and system, deposit
Storage media, terminal.
Background technique
In intelligent answer field, it is normally based on knowledge base and answers customer problem.The quality of knowledge base will will affect feedback
To the accuracy of the answer of user.
Typically, knowledge in knowledge base point is the form of question-response, is independent from each other between multiple knowledge points.It is right
In the user the problem of, if searching matched knowledge point in knowledge base, by the answer feedback in knowledge point to user.
But for searching for the customer problem less than answer, answer, treatment effeciency can just be provided by needing to improve knowledge base
It is low.
Summary of the invention
Present invention solves the technical problem that being how to promote question and answer efficiency.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of information processing method, information processing method includes:
The problem of receiving user's input, and described problem is matched with the knowledge point in knowledge base;In response to it fails to match, determine
The label of described problem, the classification of the label instruction described problem of described problem;Label according at least to described problem and each
The corresponding relationship of a label and expert user determines target expert;Described problem is pushed to the user terminal of the target expert.
Optionally, the label of the determining described problem includes: to carry out semantics recognition to described problem, to obtain described ask
The semantics recognition result of topic;The semantics recognition result of described problem is matched with each default label, and will be matched pre-
Bidding label are determined as the label of described problem.
Optionally, described to be determined according at least to the corresponding relationship of the label of described problem and each label and expert user
Target expert includes: to carry out semantic matches to the label of described problem and each label, determines matched label;According to described
The corresponding relationship of matched label and each label and expert user determines at least one matched expert user;In response to
The quantity of at least one matched expert user be it is multiple, according to the history performance information of multiple expert users determine described in
Target expert.
Optionally, the history performance information is selected from: problem replys total amount, response time and answer and adopts rate;Described
Determine that the target expert includes: to reply total amount in response to the problem of expert user according to the history performance information of multiple expert users
Reach first threshold, determines that the expert user is the target expert;And/or it is small in response to the response time of expert user
In second threshold, determine that the expert user is the target expert;And/or adopts rate in response to the answer of expert user and reach
To third threshold value, determine that the expert user is the target expert.
Optionally, the information processing method further include: receive the described problem that the user terminal of the target expert provides
Answer;The answer of described problem is pushed to the user terminal of the user.
Optionally, the information processing method further include: receive the user terminal of the target expert for described problem
Label after change;New target is determined according to the corresponding relationship of label and each label and expert user after the change
Expert;Described problem is pushed to the user terminal of the new target expert;The user terminal for receiving the new target expert mentions
The answer of the described problem of confession, and the answer of described problem is pushed to the user terminal of the user.
Optionally, the information processing method further include: using the answer of described problem and described problem as knowledge point
It stores into the knowledge base.
Optionally, the knowledge point in the knowledge base is determining in the following manner: acquisition initial data, described original
Data are selected from the data that the user uploads and/or the data crawled;The initial data is split as problem and answer, and is made
It stores for knowledge point into the knowledge base.
Optionally, the format of described problem is selected from voice, picture, video and document;The format of the answer be selected from voice,
Picture, video and document.
In order to solve the above technical problems, the embodiment of the invention also discloses a kind of information processing unit, information processing unit
Include: problem matching module, the problem of to receive user's input, and the knowledge point in described problem and knowledge base is carried out
Match;Label determining module, in response to it fails to match, to determine the label of described problem, described in the label instruction of described problem
The classification of problem;Target expert's determining module, to according to the label of described problem and pair of each label and expert user
It should be related to the determining and matched target expert of described problem;Problem pushing module, described problem is pushed to the target
The user terminal of expert.
In order to solve the above technical problems, the embodiment of the invention also discloses a kind of information processing system, information processing system
It include: the information processing unit;At least one problem user terminal to receive the problem of user inputs, and is sent to described
Information processing unit;At least one expert user end, to receive the problem of information processing unit pushes.
Optionally, at least one described expert user end also receives the answer for described problem, and the answer is sent out
Give the information processing unit.
The embodiment of the invention also discloses a kind of storage mediums, are stored thereon with computer instruction, the computer instruction
The step of information processing method is executed when operation.
The embodiment of the invention also discloses a kind of terminal, including memory and processor, being stored on the memory can
The computer instruction run on the processor, the processor execute the information processing when running the computer instruction
The step of method.
Compared with prior art, the technical solution of the embodiment of the present invention has the advantages that
Technical solution of the present invention receives the problem of user's input, and the knowledge point in described problem and knowledge base is carried out
Match;In response to it fails to match, the label of described problem, the classification of the label instruction described problem of described problem are determined;According to institute
State the label of problem and corresponding relationship determination and the matched target expert of described problem of each label and expert user;By institute
The problem of stating is pushed to the user terminal of the target expert.Knowledge point in technical solution of the present invention, in problem and knowledge base
In the case where with failure, determine that target expert, target expert have identical with the label of described problem by the label of problem
Label;By the way that problem to be pushed to the user terminal of target expert, the answer that target expert is directed to described problem can be obtained, thus
The problem of being enable to respond quickly user promotes question and answer efficiency.
Further, the user terminal of the target expert is received for the label after the change of described problem;According to described
The corresponding relationship of label and each label and expert user after change determines new target expert;Described problem is pushed to
The user terminal of the new target expert;The answer of the described problem of the user terminal offer of the new target expert is provided, and
The answer of described problem is pushed to the user terminal of the user.In technical solution of the present invention, by the use for receiving target expert
Family end redefines new target expert for the label after the change of described problem, can be wrong to avoid the label of problem
Answer mistake caused by accidentally, to guarantee the accuracy for being pushed to the answer of user terminal.
Detailed description of the invention
Fig. 1 is a kind of flow chart of information processing method of the embodiment of the present invention;
Fig. 2 is a kind of flow chart of specific embodiment of step S103 shown in Fig. 1;
Fig. 3 is the flow chart of another kind information processing method of the embodiment of the present invention;
Fig. 4 is a kind of structural schematic diagram of information processing unit of the embodiment of the present invention;
Fig. 5 is a kind of structural schematic diagram of information processing system of the embodiment of the present invention.
Specific embodiment
As described in the background art, it for searching for the customer problem less than answer, needs to improve knowledge base and can just provide and answer
Case, treatment effeciency are low.
In the embodiment of the present invention, in the case that it fails to match the knowledge point in problem and knowledge base, pass through the mark of problem
It signs and determines that target expert, target expert have label identical with the label of described problem;It is special by the way that problem is pushed to target
The user terminal of family can obtain target expert for the problem that the answer of described problem, so as to quick response user, promotion
Question and answer efficiency.
To make the above purposes, features and advantages of the invention more obvious and understandable, with reference to the accompanying drawing to the present invention
Specific embodiment be described in detail.
Fig. 1 is a kind of flow chart of information processing method of the embodiment of the present invention.
Information processing method shown in Fig. 1 may comprise steps of:
Step S101: the problem of receiving user's input, and described problem is matched with the knowledge point in knowledge base;
Step S102: in response to it fails to match, determine that the label of described problem, the label of described problem indicate described problem
Classification;
Step S103: the corresponding relationship of label and each label and expert user according at least to described problem determines mesh
Mark expert;
Step S104: described problem is pushed to the user terminal of the target expert.
It should be pointed out that the serial number of each step does not represent the limit to the execution sequence of each step in the present embodiment
It is fixed.
In the specific implementation of step S101, the problem of input, can be text formatting.The problem of input, specifically can be
The text of user's input, or can be text of the voice of user after conversion.By described problem and knowing in knowledge base
Knowing the matched process of point progress can be the process that knowledge point each in described problem and knowledge base is carried out to semantic matches, such as
It can be the semantic similarity of computational problem Yu each knowledge point, when the semantic similarity of problem and knowledge point is greater than preset value,
Expression problem matches with the knowledge point.Matched result can be successful match or it fails to match.Successful match refers to, knowledge
There is the knowledge point to match with described problem in library;It fails to match refers to, does not exist in knowledge base and matches with described problem
Knowledge point.
In a non-limiting embodiment, the format of described problem is selected from voice, picture, video and document.
In a non-limiting embodiment, step S101 can specifically include following steps: obtain the voice of user;
The voice of the user is converted into text, the problem of to obtain the input.
In the specific implementation of step S102, in the case where it fails to match, the label of problem can be determined.It specifically can be with
The label of described problem is determined according to the semanteme of described problem.The label of described problem can indicate the classification of described problem.
In a non-limiting embodiment, step S102 be may comprise steps of: be carried out to described problem semantic
Identification, to obtain the semantics recognition result of described problem;The semantics recognition result of described problem and each default label are carried out
It matches, and matched default label is determined as to the label of described problem.
In the present embodiment, each default label can be pre-set.By by the semantics recognition result of described problem
Semantic matches are carried out with default label, can determine the label of described problem.
It, can be according to institute in the specific implementation of step S103 and step S104 since expert user has label
State label determination and the matched target expert of described problem of problem.For example, the label of problem 1 is " debt-credit ", expert user 1 has
Standby label " financing ", expert user 2 have label " debt-credit ", then expert user 2 can be determined as to the target expert of problem 1.
And then described problem can be pushed to the user terminal of target expert.Target expert can be via the use of target expert
Family end provides the answer for being directed to described problem.In specific implementation, the quantity of target expert can be one, be also possible to multiple.
It, can also be to after the user terminal that described problem is pushed to the target expert in a specific example
The user terminal of the target expert sends instant alerts message, such as can be and send voice prompt or pop-up instant message window
Mouthful etc., to remind target expert to reply described problem in time.
In a non-limiting embodiment of the invention, the described problem of the user terminal offer of the target expert is received
Answer;The answer of described problem is pushed to the user terminal of the user.
In a unrestricted example of the invention, the format of the answer is selected from voice, picture, video and document.
Specifically, the format of the answer stored in knowledge base can be selected from voice, picture, video and document.Alternatively, knowledge
The format of answer in library is document format, before the user terminal that answer is pushed to user, answer can be carried out format
Conversion, to obtain format as the answer of voice, picture or video.
In the embodiment of the present invention, in the case that it fails to match the knowledge point in problem and knowledge base, pass through the mark of problem
It signs and determines that target expert, target expert have label identical with the label of described problem;It is special by the way that problem is pushed to target
The user terminal of family can obtain target expert for the problem that the answer of described problem, so as to quick response user, promotion
Question and answer efficiency.
In a non-limiting embodiment of the invention, referring to figure 2., step S103 shown in Fig. 1 may include following step
It is rapid:
Step S201: label and each label to described problem carry out semantic matches, determine matched label;
Step S202: it according to the matched label and the corresponding relationship of each label and expert user, determines at least
One matched expert user;
Step S203: in response at least one matched expert user quantity be it is multiple, according to multiple experts use
The history performance information at family determines the target expert.
In the present embodiment, the label with problem can be determined by the way that the label of problem and each label are carried out semantic matches
The label to match, the corresponding expert user of matched label are the matched expert user.The matched expert user
Quantity can be one or more.
If the quantity of matched expert user is one, directly determining the matched expert user is target expert.
If the quantity of matched expert user be it is multiple, can be sieved according to the history performance information of multiple expert users
It selects and determines target expert.
In a specific embodiment of the invention, the history performance information is selected from: problem is replied total amount, response time and is answered
Case adopts rate.
In the present embodiment, step S203 shown in Fig. 2 be may comprise steps of: be replied the problem of in response to expert user total
Amount reaches first threshold, determines that the expert user is the target expert;And/or the response time in response to expert user
Less than second threshold, determine that the expert user is the target expert;And/or rate is adopted in response to the answer of expert user
Reach third threshold value, determines that the expert user is the target expert.
Target expert is determined through the embodiment of the present invention, it is ensured that the reliability that target expert determines, so as to protect
Card promotes user experience for the quality and response speed of the answer of described problem.
It should be noted that the specific value of first threshold, second threshold and third threshold value can be answered according to actual
Carry out the setting of adaptability with scene, the embodiment of the present invention to this with no restriction.
In an alternative embodiment of the invention, step S203 shown in Fig. 2 could alternatively be following steps: described in determining at least
The current state of one expert user, and determine that the expert user being online is the target expert.
Target expert is determined through the embodiment of the present invention, it is ensured that target expert is currently at presence, so as to
To obtain answer from the user terminal of target expert in time, the response speed for being directed to the user is improved.
In a non-limiting embodiment of the invention, referring to figure 3., method shown in Fig. 1 can with the following steps are included:
Step S301: the user terminal of the target expert is received for the label after the change of described problem;
Step S302: it is determined newly according to the corresponding relationship of label and each label and expert user after the change
Target expert;
Step S303: described problem is pushed to the user terminal of the new target expert;
Step S304: the answer of the described problem of the user terminal offer of the new target expert is provided, and is asked described
The answer of topic is pushed to the user terminal of the user.
In the present embodiment, target expert can be modified the label of problem, to guarantee the accuracy of the label of problem,
Namely enable problem label more accurately indication problem classification.
Since the label of problem is changed, it is therefore desirable to redefine target expert.It specifically can be according to the label after change
And the corresponding relationship of each label and expert user determines new target expert.By the way that problem to be pushed to new target expert
User terminal, new target expert can be made to furnish an answer, and the answer is pushed to the user terminal of user, to guarantee answer
Accuracy.
About more specific embodiments of the embodiment of the present invention, previous embodiment is please referred to, details are not described herein.
In a non-limiting embodiment of the invention, method shown in Fig. 1 can be the following steps are included: by described problem
And the answer of described problem is stored as knowledge point into the knowledge base.
In the present embodiment, it fails to match for the knowledge point in described problem and knowledge base, indicates to be not present and institute in knowledge base
The knowledge point that the problem of stating matches.Knowledge base is added by the answer for providing described problem and target expert, so that knowledge
The knowledge point to match with the problem is stored in library, next time and when being successfully received identical problem, can directly from
The answer of the problem is got in knowledge base and feeds back to user, promotes question and answer efficiency.
In a non-limiting embodiment of the invention, the knowledge point in the knowledge base is determining in the following manner
: acquisition initial data, the initial data are selected from the data that the user uploads and/or the data crawled;It will be described original
Data are split as problem and answer, and store as knowledge point into the knowledge base.
In the present embodiment, to the problem of user matched used in knowledge base be data structure using the user
It builds.It specifically can be the data uploaded using user and/or the related data crawled.By the way that the initial data is split as
Problem and answer form knowledge point, and store to knowledge base.In other words, the corresponding knowledge base of each user, can be to not
Same user constructs knowledge base respectively.
When initial data is split as problem and answer, the keyword of initial data can be extracted, which can be with
As problem, initial data is as answer.For example, for format be video initial data, can extract video title and
Content, for the title of video as problem, the content of video, can also be using video as answer as answer.
In a specific application scenarios, initial data can be stored in the data of user terminal local, can be use
The data of family end caching, are also possible to data of the user record in user terminal, such as can be the voice of user.
The embodiment of the invention also discloses a kind of information processing units.Referring to figure 4., information processing unit 40 can wrap
It includes: problem matching module 401, label determining module 402, target expert determining module 403 and problem pushing module 404.
Wherein, the problem of problem matching module 401 is to receive user's input, and by described problem and knowing in knowledge base
Know point to be matched;Label determining module 402 to determine the label of described problem in response to it fails to match, described problem
The classification of label instruction described problem;Target expert determining module 403 is to the label and each label according to described problem
Corresponding relationship determination and the matched target expert of described problem with expert user;Problem pushing module 404 by described to ask
Topic is pushed to the user terminal of the target expert.
The information processing unit 40 of the embodiment of the present invention can be built in or outside is coupled to terminal device.The terminal is set
It is standby to can be computer equipment, mobile terminal, it is also possible to server apparatus.
In a non-limiting embodiment of the invention, label determining module shown in Fig. 4 402 may include: problem semanteme
Recognition unit, to carry out semantics recognition to described problem, to obtain the semantics recognition result of described problem;Problem matching is single
Member is determined to match the semantics recognition result of described problem with each default label, and by matched default label
For the label of described problem.
In the present embodiment, each default label can be pre-set.By by the semantics recognition result of described problem
Semantic matches are carried out with default label, can determine the label of described problem.It, can root since expert user has label
Label determination and the matched target expert of described problem according to described problem.
In a non-limiting embodiment of the invention, the determining module of target expert shown in Fig. 4 403 may include: label
Matching unit determines matched label to the label and each label progress semantic matches to described problem;Expert user
Determination unit determines at least one to the corresponding relationship according to the matched label and each label and expert user
Matched expert user;Target expert's determination unit, to be in response to the quantity of at least one matched expert user
It is multiple, the target expert is determined according to the history performance information of multiple expert users.
In the present embodiment, the label with problem can be determined by the way that the label of problem and each label are carried out semantic matches
The label to match, the corresponding expert user of matched label are the matched expert user.The matched expert user
Quantity can be one or more.
If the quantity of matched expert user is one, directly determining the matched expert user is target expert.
If the quantity of matched expert user be it is multiple, can according to the history of multiple expert users show information sifting determine mesh
Mark expert.
In a specific embodiment of the invention, the history performance information can be selected from: problem replys total amount, response time
Rate is adopted with answer.
In a non-limiting embodiment of the invention, information processing unit 40 shown in Fig. 4 can also include: that answer receives
Module, the answer for the described problem that the user terminal to receive the target expert provides;Pushing module, to by described problem
Answer be pushed to the user terminal of the user.
In a non-limiting embodiment of the invention, information processing unit 40 shown in Fig. 4 can also include: that label receives
Module, to receive the user terminal of the target expert for the label after the change of described problem;Target expert redefines
Module, to determine that new target is special according to the corresponding relationship of label and each label and expert user after the change
Family;Again pushing module, described problem to be pushed to the user terminal of the new target expert;Answer receives mould again
Block, the answer for the described problem that the user terminal to receive the new target expert provides, and the answer of described problem is pushed away
Give the user terminal of the user.
In the present embodiment, target expert can be modified the label of problem, to guarantee the accuracy of the label of problem,
Namely enable problem label more accurately indication problem classification.
Since the label of problem is changed, it is therefore desirable to redefine target expert.It specifically can be according to the label after change
And the corresponding relationship of each label and expert user determines new target expert.By the way that problem to be pushed to new target expert
User terminal, new target expert can be made to furnish an answer, and the answer is pushed to the user terminal of user, to guarantee answer
Accuracy.
Further, information processing unit 40 shown in Fig. 4 can also include: knowledge point memory module, suitable for asking described
The answer of topic and described problem is stored as knowledge point into the knowledge base.
In the present embodiment, it fails to match for the knowledge point in described problem and knowledge base, indicates to be not present and institute in knowledge base
The knowledge point that the problem of stating matches.Knowledge base is added by the answer for providing described problem and target expert, so that knowledge
The knowledge point to match with the problem is stored in library, next time and when being successfully received identical problem, can directly from
The answer of the problem is got in knowledge base and feeds back to user, promotes question and answer efficiency.
In the embodiment of the present invention, in the case that it fails to match the knowledge point in problem and knowledge base, pass through the mark of problem
It signs and determines that target expert, target expert have label identical with the label of described problem;It is special by the way that problem is pushed to target
The user terminal of family can obtain target expert for the problem that the answer of described problem, so as to quick response user, promotion
Question and answer efficiency.
Working principle, more contents of working method about the information processing unit 40, are referred to Fig. 1 to Fig. 3
In associated description, which is not described herein again.
The embodiment of the invention also discloses a kind of information processing systems.Referring to figure 5., information processing system 50 may include
At least one problem user terminal 501, information processing unit 502 and at least one expert user end 503.
Wherein, the problem of problem user terminal 501 is to receive user's input, and it is sent to the information processing unit 502;
The problem of expert user end 503 is to receive information processing unit push.
In the present embodiment, problem user terminal 501 can receive the problem of user uploads, and problem is forwarded to information processing
Device 502, information processing unit can execute each step shown in FIG. 1, determine that target is special in multiple expert user ends 503
The expert user end 503 of family, and described problem is pushed to the expert user end 503 of target expert.
In a non-limiting embodiment of the invention, at least one described expert user end 503 is also received for described
The answer of problem, and the answer is sent to the information processing unit 502.
Specifically, expert user can upload the answer for described problem to information processing via expert user end 503
Device 502.Information processing unit 502 can use the answer building or maintenance that at least one described expert user end 503 is sent
Knowledge base.
Working principle, more contents of working method about information processing unit 502, are referred to Fig. 1 into Fig. 3
Associated description, which is not described herein again.
The embodiment of the invention also discloses a kind of storage mediums, are stored thereon with computer instruction, the computer instruction
The step of method shown in Fig. 1, Fig. 2 or Fig. 3 can be executed when operation.The storage medium may include ROM, RAM, disk or
CD etc..The storage medium can also include non-volatility memorizer (non-volatile) or non-transient (non-
Transitory) memory etc..
The embodiment of the invention also discloses a kind of terminal, the terminal may include memory and processor, the storage
The computer instruction that can be run on the processor is stored on device.The processor can be with when running the computer instruction
The step of executing method shown in Fig. 1, Fig. 2 or Fig. 3.The terminal includes but is not limited to that mobile phone, computer, tablet computer etc. are whole
End equipment.
Although present disclosure is as above, present invention is not limited to this.Anyone skilled in the art are not departing from this
It in the spirit and scope of invention, can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
Subject to the range of restriction.
Claims (14)
1. a kind of information processing method characterized by comprising
The problem of receiving user's input, and described problem is matched with the knowledge point in knowledge base;
In response to it fails to match, the label of described problem, the classification of the label instruction described problem of described problem are determined;
The corresponding relationship of label and each label and expert user according at least to described problem determines target expert;
Described problem is pushed to the user terminal of the target expert.
2. information processing method according to claim 1, which is characterized in that the label of the determining described problem includes:
Semantics recognition is carried out to described problem, to obtain the semantics recognition result of described problem;
The semantics recognition result of described problem is matched with each default label, and matched default label is determined as institute
State the label of problem.
3. information processing method according to claim 1, which is characterized in that the label according at least to described problem with
And the corresponding relationship of each label and expert user determines that target expert includes:
Label and each label to described problem carry out semantic matches, determine matched label;
According to the matched label and the corresponding relationship of each label and expert user, at least one matched expert is determined
User;
In response at least one matched expert user quantity be it is multiple, according to the history of multiple expert users show believe
Breath determines the target expert.
4. information processing method according to claim 3, which is characterized in that the history performance information is selected from: problem is returned
Rate is adopted in multiple total amount, response time and answer;The history performance information according to multiple expert users determines that the target is special
Family include:
The problem of in response to expert user, replys total amount and reaches first threshold, determines that the expert user is the target expert;
And/or it is less than second threshold in response to the response time of expert user, determine that the expert user is that the target is special
Family;
And/or adopt rate in response to the answer of expert user and reach third threshold value, determine that the expert user is that the target is special
Family.
5. information processing method according to claim 1, which is characterized in that further include:
The answer of the described problem of the user terminal offer of the target expert is provided;
The answer of described problem is pushed to the user terminal of the user.
6. information processing method according to claim 1, which is characterized in that further include:
The user terminal of the target expert is received for the label after the change of described problem;
New target expert is determined according to the corresponding relationship of label and each label and expert user after the change;
Described problem is pushed to the user terminal of the new target expert;
The answer of the described problem of the user terminal offer of the new target expert is provided, and the answer of described problem is pushed to
The user terminal of the user.
7. information processing method according to claim 5 or 6, which is characterized in that further include:
It stores the answer of described problem and described problem as knowledge point into the knowledge base.
8. information processing method according to claim 1, which is characterized in that the knowledge point in the knowledge base be by with
What under type determined:
Initial data is acquired, the initial data is selected from the data that the user uploads and/or the data crawled;
The initial data is split as problem and answer, and is stored as knowledge point into the knowledge base.
9. information processing method according to claim 5 or 6, which is characterized in that the format of described problem is selected from voice, figure
Piece, video and document;The format of the answer is selected from voice, picture, video and document.
10. a kind of information processing unit characterized by comprising
Problem matching module the problem of to receive user's input, and the knowledge point in described problem and knowledge base is carried out
Match;
Label determining module, in response to it fails to match, to determine the label of described problem, described in the label instruction of described problem
The classification of problem;
Target expert's determining module, it is true to the corresponding relationship according to the label of described problem and each label and expert user
The fixed and matched target expert of described problem;
Problem pushing module, described problem to be pushed to the user terminal of the target expert.
11. a kind of information processing system characterized by comprising
Information processing unit as claimed in claim 10;
At least one problem user terminal to receive the problem of user inputs, and is sent to the information processing unit;
At least one expert user end, to receive the problem of information processing unit pushes.
12. information processing system according to claim 11, which is characterized in that at least one described expert user end also connects
The answer narrowed to described problem, and the answer is sent to the information processing unit.
13. a kind of storage medium, is stored thereon with computer instruction, which is characterized in that the computer instruction executes when running
Described in any one of claims 1 to 9 the step of information processing method.
14. a kind of terminal, including memory and processor, the meter that can be run on the processor is stored on the memory
Calculation machine instruction, which is characterized in that perform claim requires any one of 1 to 9 institute when the processor runs the computer instruction
The step of stating information processing method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811637981.5A CN109766422A (en) | 2018-12-29 | 2018-12-29 | Information processing method, apparatus and system, storage medium, terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811637981.5A CN109766422A (en) | 2018-12-29 | 2018-12-29 | Information processing method, apparatus and system, storage medium, terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109766422A true CN109766422A (en) | 2019-05-17 |
Family
ID=66453198
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811637981.5A Pending CN109766422A (en) | 2018-12-29 | 2018-12-29 | Information processing method, apparatus and system, storage medium, terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109766422A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110188248A (en) * | 2019-05-28 | 2019-08-30 | 新华网股份有限公司 | Data processing method, device and electronic equipment based on news question and answer interactive system |
CN110532265A (en) * | 2019-08-20 | 2019-12-03 | 北京齐尔布莱特科技有限公司 | Method, apparatus and calculating equipment based on product service manual building question answering system |
CN110597989A (en) * | 2019-08-30 | 2019-12-20 | 腾讯科技(深圳)有限公司 | Data processing method and device and computer storage medium |
CN110674395A (en) * | 2019-08-23 | 2020-01-10 | 深圳市新系区块链技术有限公司 | Information pushing method, device and equipment |
CN110674261A (en) * | 2019-10-14 | 2020-01-10 | 出门问问信息科技有限公司 | Information processing method and device and computer readable storage medium |
CN112527831A (en) * | 2021-02-05 | 2021-03-19 | 武汉听讼信息技术有限公司 | Resource processing method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103177108A (en) * | 2013-03-26 | 2013-06-26 | 中山大学 | Medical treatment automatic question answering method based on internet and system thereof |
CN107220389A (en) * | 2017-07-12 | 2017-09-29 | 广州市昊链信息科技股份有限公司 | A kind of Logistics Knowledge intelligent Answer System and method |
CN107783970A (en) * | 2016-08-25 | 2018-03-09 | 武汉聚蜗网络科技有限公司 | A kind of expert's question answering system and its operating method |
CN108153738A (en) * | 2018-02-10 | 2018-06-12 | 灯塔财经信息有限公司 | A kind of chat record analysis method and device based on hierarchical clustering |
KR20180101949A (en) * | 2017-03-06 | 2018-09-14 | 네이버 주식회사 | Item recommendation method, apparatus and computer program for excuting the method |
-
2018
- 2018-12-29 CN CN201811637981.5A patent/CN109766422A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103177108A (en) * | 2013-03-26 | 2013-06-26 | 中山大学 | Medical treatment automatic question answering method based on internet and system thereof |
CN107783970A (en) * | 2016-08-25 | 2018-03-09 | 武汉聚蜗网络科技有限公司 | A kind of expert's question answering system and its operating method |
KR20180101949A (en) * | 2017-03-06 | 2018-09-14 | 네이버 주식회사 | Item recommendation method, apparatus and computer program for excuting the method |
CN107220389A (en) * | 2017-07-12 | 2017-09-29 | 广州市昊链信息科技股份有限公司 | A kind of Logistics Knowledge intelligent Answer System and method |
CN108153738A (en) * | 2018-02-10 | 2018-06-12 | 灯塔财经信息有限公司 | A kind of chat record analysis method and device based on hierarchical clustering |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110188248A (en) * | 2019-05-28 | 2019-08-30 | 新华网股份有限公司 | Data processing method, device and electronic equipment based on news question and answer interactive system |
CN110532265A (en) * | 2019-08-20 | 2019-12-03 | 北京齐尔布莱特科技有限公司 | Method, apparatus and calculating equipment based on product service manual building question answering system |
CN110532265B (en) * | 2019-08-20 | 2022-03-18 | 北京齐尔布莱特科技有限公司 | Method and device for constructing question-answering system based on product instruction manual and computing equipment |
CN110674395A (en) * | 2019-08-23 | 2020-01-10 | 深圳市新系区块链技术有限公司 | Information pushing method, device and equipment |
CN110597989A (en) * | 2019-08-30 | 2019-12-20 | 腾讯科技(深圳)有限公司 | Data processing method and device and computer storage medium |
CN110674261A (en) * | 2019-10-14 | 2020-01-10 | 出门问问信息科技有限公司 | Information processing method and device and computer readable storage medium |
CN112527831A (en) * | 2021-02-05 | 2021-03-19 | 武汉听讼信息技术有限公司 | Resource processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109766422A (en) | Information processing method, apparatus and system, storage medium, terminal | |
US10777207B2 (en) | Method and apparatus for verifying information | |
US10230668B2 (en) | Information replying method and apparatus | |
CN112685565A (en) | Text classification method based on multi-mode information fusion and related equipment thereof | |
CN107807960B (en) | Intelligent customer service method, electronic device and computer readable storage medium | |
CN110515951B (en) | BOM standardization method and system, electronic device and storage medium | |
CN109858045B (en) | Machine translation method and device | |
CN106485261B (en) | Image recognition method and device | |
JP2022088304A (en) | Method for processing video, device, electronic device, medium, and computer program | |
CN109829164B (en) | Method and device for generating text | |
CN110399306B (en) | Automatic testing method and device for software module | |
CN113505272B (en) | Control method and device based on behavior habit, electronic equipment and storage medium | |
CN103530313A (en) | Searching method and device of application information | |
CN111737443B (en) | Answer text processing method and device and key text determining method | |
CN113407851A (en) | Method, device, equipment and medium for determining recommendation information based on double-tower model | |
CN114358023A (en) | Intelligent question-answer recall method and device, computer equipment and storage medium | |
CN112417874A (en) | Named entity recognition method and device, storage medium and electronic device | |
CN107623620B (en) | Processing method of random interaction data, network server and intelligent dialogue system | |
CN112182255A (en) | Method and apparatus for storing media files and for retrieving media files | |
CN116049370A (en) | Information query method and training method and device of information generation model | |
CN113779934B (en) | Multi-mode information extraction method, device, equipment and computer readable storage medium | |
CN116071590A (en) | Model training method, system, computer device and storage medium | |
CN114490990B (en) | Method, device, equipment and storage medium for determining text to be annotated | |
CN115394295A (en) | Segmentation processing method, device, equipment and storage medium | |
CN110990528A (en) | Question answering method and device and electronic equipment |
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: 20190517 |
|
RJ01 | Rejection of invention patent application after publication |