CN107220389A - A kind of Logistics Knowledge intelligent Answer System and method - Google Patents
A kind of Logistics Knowledge intelligent Answer System and method Download PDFInfo
- Publication number
- CN107220389A CN107220389A CN201710567587.8A CN201710567587A CN107220389A CN 107220389 A CN107220389 A CN 107220389A CN 201710567587 A CN201710567587 A CN 201710567587A CN 107220389 A CN107220389 A CN 107220389A
- Authority
- CN
- China
- Prior art keywords
- information
- module
- answer
- expert
- question
- 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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Logistics Knowledge intelligent Answer System, it is related to the technical field of big data processing, including question and answer interactive module and expert assistant's subsystem, question and answer interactive module is used to receive the enquirement from user terminal；Expert assistant's subsystem includes technocracy module and expert info pushing module, technocracy module is based on expert data and carries out expert's portrait, expert info pushing module is drawn a portrait to push to expert according to expert and putd question to, and expert is sent into user terminal according to original route to the answer of enquirement.The invention also discloses a kind of Logistics Knowledge intelligent answer method.The present invention is by big data analysis and data mining, and to question and answer knowledge induction and conclusion, developing intellectual resource question answering system realizes domain knowledge intelligent answer, solve existing question answering system can not high-quality answer the problem of client questions including the practitioner of this area.
Description
Technical field
The present invention relates to the technical field of big data processing, and in particular to a kind of Logistics Knowledge intelligent Answer System and side
Method.
Background technology
As net purchase culture is increasingly flourishing, logistic industry flourishes.And in logistics, customs broker in the industry, policy, focus
The influence changed to business is very big, and industrial hot spot trend is grasped in time and Policy Toward is understood ten for enterprise, business personnel
Divide important.But because industry practitioner's know-how differs, there is business personnel's writing ability of abundant business experience unqualified, and
The strong possibility domain knowledge of writing ability not enough, causes pass business and logistic industry knowledge not to precipitate effectively.
In existing logistic industry, user puts question to and typically answered by contact staff, but contact staff is to domain knowledge
Amount of storage be difficult to meet be used for demand, this defect embodies particularly on practical business operative knowledge and focus policy knowledge
It is prominent.Logistics and pass business industry are influenceed very big by policy and focus trend, and network information is very different, it is difficult to effectively screened
Real focus trend, these all cause certain to the enquirement demand for meeting the client including the practitioner of this area
It is difficult.In view of logistics and close business industry influenceed very big by policy and focus trend, hot information it is ageing extremely important, but
Close business and logistic industry knowledge and specification is all issued from top to down by government department, therefore policy relevant information is difficult to land in reality
Border question and answer operation, causes the q＆r that answer is putd question to all to be greatly lowered.
Chinese patent application CN105956809A discloses a kind of cloud real time propelling movement logistics information monitoring based on big data
Management system, including goods station Warehouse IMS, with car monitoring management system, big data analysis system, big data communicate
Network system, big data server and cross-domain access server, wherein goods station Warehouse IMS are distributed in material route
On the way in each goods station, and it is connected by big data communication network system with big data analysis system, with car monitoring management system point
Cloth is connected in each logistics transportation instrument, and by big data communication network system with big data analysis system, big data analysis
System is connected with big data server and cross-domain access server respectively by big data communication network system.One aspect of the present invention
Track of the whole process monitoring can be carried out to means of transport running situation, on the other hand can each stream line goods and materials source distribution situation of getting in stocks enter
Row monitoring, so as to be that means of transport traffic control and goods allotment provide reliable foundation.Nowadays the technology of logistic industry is ground
Study carefully direction and concentrate on acquisition, output and tracking of information and goods in actual mechanical process etc., in logistic industry knowledge accumulation, face
Knowledge question to specialty and amateur user etc. still suffers from more blank.
Chinese patent application CN105630938 discloses a kind of intelligent Answer System, including：More than one problem inputs mould
Block, problem input module includes for inputting the problem of needing to answer, and problem being set in source identification, the source identification
Large user's information it is at least two or more, large user includes small user further below, be between large user it is independent of each other, it is different
Large user between small user be independent；One problem base；One problem matching module；One general answer storehouse；One
Above specialty answer storehouse；One question response module, exists according to the source identification of the matching result of problem matching module and problem
Found in professional answer storehouse or general answer storehouse the answer of corresponding problem and according to source identification by corresponding answer feedback to answer
The side of needs.Research on question answering system at present tends to be ripe, but can not all be advantageously applied in logistic industry, based on logistics
And the characteristic of business industry is closed, it can not realize that high-quality user's question and answer are interactive from expected data storehouse or manual service.
The content of the invention
In view of the shortcomings of the prior art, the purpose of the present invention aims to provide a kind of Logistics Knowledge intelligent Answer System and side
Method, is mainly used in logistic industry, with solve existing question answering system can not high-quality answer include this area practitioner and exist
The problem of interior client questions, and ensure that question answering system exports the ageing of answer.
To achieve the above object, the present invention is adopted the following technical scheme that：
A kind of Logistics Knowledge intelligent Answer System, including：
Question and answer interactive module, for receiving the enquirement from user terminal；
Expert assistant's subsystem, including technocracy module and expert info pushing module, technocracy module are based on special
Family's data carry out expert's portrait, and expert info pushing module is drawn a portrait to push to expert according to expert and putd question to, and by expert to puing question to
Answer be sent to user terminal according to original route.
Further, Logistics Knowledge intelligent Answer System disclosed by the invention also includes classifying module and data storage mould
Block, expert info pushing module will be putd question to and answer content is sent to classifying module, and classifying module is used in puing question to and answering
Hold and carry out homogeneous classification processing, data memory module is used for the homogeneous classification result according to classifying module according to classification data storage.
Further, in order to ensure the ageing of data, data memory module is additionally operable to be stored according to preset rules
Information be respectively set to effective information and outdated information, preset rules include：A, the information corresponding to particular category follow in
Corresponding effective time, the information of the particular category switchs to outdated information after effective time；B, data memory module are from returning
The fresh information received in generic module is contrasted with original effective information, when fresh information and the key of original effective information
When Word similarity reaches setting value, then original effective information switchs to outdated information, and fresh information replaces original information as effective
Information.
Further, question and answer interactive module is additionally operable to the effective information stored according to subject of question in data memory module
The middle matching degree extracted answer and calculate extracted answer and enquirement, question and answer interactive module is additionally operable to after being selected according to the matching degree
Continuous data transfer mode：When matching degree reaches first threshold, the answer is sent to user terminal and completes automation answer；Separately
There is the Second Threshold less than first threshold, when matching degree is less than first threshold and is not less than Second Threshold, the answer is transmitted
To user terminal, in order to improve the answer while subject of question is sent into artificial end through expert assistant's subsystem, manually hold to carrying
The answer asked is sent to user terminal according to original route；When matching degree is less than Second Threshold, directly by subject of question through expert assistant
Subsystem is sent to artificial end, and artificial end is sent to user terminal to the answer of enquirement according to original route.
Further, Logistics Knowledge intelligent Answer System disclosed by the invention also includes data obtaining module, acquisition of information
Module is used to obtain hot information from high in the clouds and is sent to classifying module, and the categorized module of hot information carries out homogeneous classification processing
After be sent in data memory module and stored.
Further, Logistics Knowledge intelligent Answer System disclosed by the invention also includes message processing module, information processing
Module and expert assistant's subsystem are handled it during hot information is from data obtaining module to classifying module, tool
Body, message processing module is used to receive the hot information from data obtaining module and former data classification is carried out to it, completes
The hot information of former data classification is sent to expert info pushing module, and expert info pushing module is drawn a portrait to expert according to expert
Hot information is pushed, and expert is sent to classification to the hot information of the interpretive analysis of hot information and the former data classification of completion
Module；Classifying module carries out homogeneous classification to the hot information and expert that complete former data classification to the interpretive analysis of hot information
Processing, data memory module is according to the homogeneous classification result of classifying module according to classification data storage.
Further, attributive character of the message processing module based on multiple dimensions carries out former data classification to hot information.
Further, message processing module is before former data classification is carried out to hot information, to hot information multiple
The attributive character of dimension distributes corresponding weighted value.
Further, multiple dimensions include source web, come source directory, location information and frequency of reading.
A kind of Logistics Knowledge intelligent answer method, comprises the following steps：
S0, technocracy module are based on expert data and carry out expert's portrait；
S1, question and answer interactive module answer is extracted in data memory module according to subject of question and calculate extracted answer with
The matching degree of enquirement；
S1 ', question and answer interactive module select follow-up data transfer mode according to matching degree：When matching degree reaches first threshold
When, the answer is sent to user terminal and completes automation answer；The another Second Threshold having less than first threshold, when matching degree is less than
First threshold and when being not less than Second Threshold, is sent to user terminal, in order to improve the answer simultaneously by subject of question by the answer
It is sent to expert info pushing module；When matching degree is less than Second Threshold, subject of question is directly sent to expert info and pushed away
Send module；
S2, expert info pushing module are pushed according to expert portrait selection expert and putd question to；
S3, expert pushed into user terminal to the answer of enquirement according to original route.
Further, the information stored is divided into effective information and outdated information by data memory module according to preset rules
Two states, setting rule includes：A, the information corresponding to particular category were followed in corresponding effective time, the particular category
Information switchs to outdated information after effective time；The fresh information that b, data memory module are received from classifying module and original
There is effective information to be contrasted, it is when the crucial Word similarity of fresh information and original effective information reaches setting value, then original
Effective information switchs to outdated information, and fresh information replaces original information and is used as effective information；
And in S1, question and answer interactive module is carried according to subject of question in the effective information that data memory module is stored
Take answer.
The beneficial effects of the present invention are：(1) user is putd question to by expert assistant's subsystem and pushes to expert, by theory
Expert or practical operation expert are answered, and are solved and are overcome personnel not possess practical operation experience generally, can not understand heat in the prior art
The problem of point information；(2) include technocracy module in expert assistant's subsystem, expert is carried out by technocracy module
Portrait, user is putd question to and accurately pushes to the expert for being good at correspondence field, is made enquirement flow direction really " expert ", is ensured significantly
Answer quality；(3) hot information is obtained by high in the clouds, hot information is classified, interpretive analysis, store again after homogeneous classification to
The question and answer content of data memory module, artificial end and user terminal is also stored after processing to data memory module, is formed industry and is known
Know storehouse, realize to the precipitation of logistic industry knowledge, for deeper into big data excavate and provide condition；(4) combine on high in the clouds
Real-time hot information, data memory module (i.e. database or answer storehouse) is updated the data according to preset rules automation, makes storage
Content " is grown with each passing hour ", and script is uphang to the focus information such as policy, regulation in room beam and landed in actual question and answer, has ensured and has asked
The ageing of system output answer is answered, the reliability of system is substantially increased；(5) question and answer interaction systems can according to subject of question from
Answer is extracted in database and carries out automation answer, it is to avoid repeats to push the problem of same, AI is progressively transitioned into from manual answering
Intelligent Answering, saves expert's human cost.
Brief description of the drawings
Fig. 1 is a kind of structured flowchart of Logistics Knowledge intelligent Answer System in the present invention.
Embodiment
Below, with reference to accompanying drawing and embodiment, the present invention is described further：
Embodiment 1
As shown in figure 1, a kind of Logistics Knowledge intelligent Answer System, including data obtaining module, message processing module, expert
Assistant's subsystem, classifying module, data memory module and question and answer interactive module：
Connecting the data obtaining module in high in the clouds is used for the predefined setting according to logistic industry keyword and information source, leads to
Cross crawler technology and obtain hot information from high in the clouds, hot information includes the policy information and its derivative letter related to logistic industry
Breath；Data obtaining module is additionally operable to the hot information for completing pretreatment being sent to message processing module；
Message processing module is used to carry out hot information screening and former data are classified, the heat for meeting particular keywords
Point news is set up according to time shaft and follows the trail of index, and its Central Plains data classification uses Decision Tree Algorithm, is specially：Extract focus
Information is in source web, the attributive character carried out source directory, be related to the dimensions such as industry, location information, frequency of reading, to multiple dimensions
Attributive character distribute corresponding weighted value, and hot information conclude and former data point by analysis tools such as Orange
Class；The hot information for completing former data classification is sent to expert assistant's subsystem by message processing module；
Expert assistant's subsystem is used to connect system and artificial end, including technocracy module and expert info push mould
Block, artificial end face carries out expert's picture to the industry specialists such as theoretical expert and practical operation expert, technocracy module according to expert data
Picture, expert data include essential information, essential information include education background, the affiliated segmented industry, the entire period of actual operation, industry experience and
Label etc. is paid close attention to, former data classification results and expert of the expert info pushing module based on hot information are drawn a portrait and push heat to expert
Point information, expert info pushing module also is drawn a portrait to push to expert and putd question to based on user's subject of question combination user data and expert
Content, the user data includes user's concern label, user (includes the association of the affiliated segmented industry to the degree of association of each expert
Degree) and attention rate etc., hot information and user is putd question to flow direction really " expert ", expert understands information and answer is carried to improve
The efficiency asked, answer that expert is putd question to user the interpretive analysis of hot information, expert, the answer are remembered in the repercussion of user terminal
Record will also carry out the foundation of expert's portrait as technocracy module；Expert assistant's subsystem passes through at artificial end to the answer of enquirement
Question and answer interactive module is sent to user terminal, and expert assistant's subsystem is also by the hot information of the former data classification of completion, expert to warm
The interpretive analysis and question and answer content of point information are sent to classifying module；In the process of running, expert assistant's subsystem can also pass through
Logic verify is carried out to each item data and realizes upgrading of self evolving；
Classifying module is for the hot information to completing former data classification, expert to the interpretive analysis of hot information and by people
The question and answer content that work end completes answer carries out unitized classification processing, and the information content for completing unitized classification processing is transmitted
To data memory module, the classification selection of homogeneous classification processing includes practical operation class, corresponding to related to practical business operation
Content；
Data memory module is used for according to classification storage information, and the classification of storage information also includes practical operation class；Data are deposited
Storage module is additionally operable to that the information stored is respectively set into effective information and outdated information two states according to preset rules, in advance
If rule includes：A, the information corresponding to particular category were followed in corresponding effective time, and the information of the particular category is by having
Effect switchs to outdated information after the time；The fresh information that b, data memory module are received from classifying module and original effective information
Contrasted, when the crucial Word similarity of fresh information and original effective information reaches setting value, then original effective information turns
For outdated information, fresh information replaces original information and is used as effective information；
Question and answer interactive module user oriented end, for receiving the enquirement from user terminal, is deposited according to subject of question from data
Answer is extracted in the effective information that storage module is precipitated and extracted answer and the matching degree putd question to is calculated, and question and answer interactive module is also
Follow-up data transfer mode is selected according to matching degree：When matching degree is not less than first threshold, the answer is sent to user
End completes automation answer；The another Second Threshold having less than first threshold, when matching degree less than first threshold is not less than second
During threshold value, the answer is sent to user terminal, in order to improve the answer while subject of question and user data are sent to together
Expert assistant's subsystem, and subject of question is pushed into artificial end by expert assistant's subsystem, artificial end to the answer of enquirement according to
Original route is sent to user terminal；When matching degree is less than Second Threshold, directly subject of question and user data are sent to together
Expert assistant's subsystem, and subject of question is pushed into artificial end by expert assistant's subsystem, artificial end to the answer of enquirement according to
Original route is sent to user terminal；Wherein first threshold is set to 90%, and Second Threshold is set to 60%.
Embodiment 2
A kind of Logistics Knowledge intelligent answer method, comprises the following steps：
S0, manually hold Expert-oriented, expert assistant's subsystem includes technocracy module and expert info pushing module, specially
Family's management module carries out expert's portrait according to expert data using iteration decision making algorithm (GBDT), and expert data includes basic letter
Breath, essential information includes education background, the affiliated segmented industry, the entire period of actual operation, industry experience and concern label etc.；
S1, question and answer interactive module extract answer simultaneously according to subject of question in the effective information that data memory module is stored
Calculate the matching degree extracted answer and putd question to；
S1 ', question and answer interactive module select follow-up data transfer mode according to the matching degree of extracted answer and enquirement：When
When matching degree is not less than first threshold, the answer is sent to user terminal and completes automation answer；When matching degree is less than the first threshold
When value is not less than Second Threshold, the answer is sent to user terminal, in order to improve the answer simultaneously by subject of question and user
Data are sent to expert info pushing module together；When matching degree is less than Second Threshold, directly by subject of question and number of users
According to being sent to expert info pushing module together；
S2, the enquirement for being sent to expert info pushing module carry user data, and user data includes user and pays close attention to mark
Label, user are to degree of association (degree of association for including the affiliated segmented industry) and attention rate of each expert etc., expert info pushing module
Push and put question to reference to expert's portrait and user data selection expert；
S3, expert pushed into user terminal to the answer of enquirement according to original route；
S4, homogeneous classification processing will be carried out by the enquirement and the categorized module of answer content of expert assistant's subsystem, will
The data storage of homogeneous classification is completed in data memory module, data memory module is according to preset rules by the information stored
Effective information and outdated information two states are respectively set to, preset rules include：A, the information corresponding to particular category are followed
In corresponding effective time, the information of the particular category switchs to outdated information after effective time；B, data memory module from
The fresh information received in classifying module is contrasted with original effective information, when fresh information and the pass of original effective information
When keyword similarity reaches setting value, then original effective information switchs to outdated information, and fresh information replaces original information as having
Imitate information.
While S0~S4 is carried out, obtain hot spot data from high in the clouds and be refined into useful data and store to data storage mould
In block, following steps are specifically included：
T1, data obtaining module obtain focus according to the predefined setting of logistic industry keyword and information source from high in the clouds
Information, and pretreated hot information will be carried out be sent to message processing module, the content of pretreatment include it is unified format,
Simple classification (such as policy class, news category) and simple filtration (such as whetheing there is illegal keyword)；
T2, message processing module carry out former data to hot information using Decision Tree Algorithm and classified, and are specially：Extract
Hot information is in source web, the attributive character carried out source directory, be related to the dimensions such as industry, location information, frequency of reading, to multiple
The attributive character of dimension distributes corresponding weighted value, and hot information conclude and former number by analysis tools such as Orange
According to classification；Former data classification results and expert of the expert info pushing module based on hot information are drawn a portrait and push focus letter to expert
Breath, obtains interpretive analysis of the artificial end to hot information, and by the hot information of the former data classification of completion, expert to hot information
Interpretive analysis be sent to classifying module；
T3, classifying module are united to completing the hot information of former data classification, expert to the interpretive analysis of hot information
One changes classification processing, and the information for completing unitized classification processing is stored to data memory module according to classification.
It will be apparent to those skilled in the art that technical scheme that can be as described above and design, make other various
It is corresponding to change and deformation, and all these change and deformation should all belong to the protection domain of the claims in the present invention
Within.
Claims (10)
1. a kind of Logistics Knowledge intelligent Answer System, it is characterised in that including：
Question and answer interactive module, for receiving the enquirement from user terminal；
Expert assistant's subsystem, including technocracy module and expert info pushing module, the technocracy module are based on special
Family's data carry out expert's portrait, and expert info pushing module is drawn a portrait to push to expert according to expert and putd question to, and by expert to puing question to
Answer be sent to user terminal according to original route.
2. Logistics Knowledge intelligent Answer System as claimed in claim 1, it is characterised in that the Logistics Knowledge intelligent answer system
System also includes classifying module and data memory module, and the expert info pushing module will be putd question to and answer content is sent to classification
Module, classifying module to puing question to and answering content for carrying out homogeneous classification processing, and data memory module is used for according to classification mould
The homogeneous classification result of block is according to classification data storage.
3. Logistics Knowledge intelligent Answer System as claimed in claim 2, it is characterised in that the data memory module is additionally operable to
The information stored is respectively set to effective information and outdated information according to preset rules, preset rules include：A, correspond to
The information of particular category was followed in corresponding effective time, and the information of the particular category switchs to expired letter after effective time
Breath；The fresh information that b, data memory module are received from classifying module is contrasted with original effective information, is believed when updating
When the crucial Word similarity of breath and original effective information reaches setting value, then original effective information switchs to outdated information, updates letter
Breath replaces original information and is used as effective information.
4. Logistics Knowledge intelligent Answer System as claimed in claim 3, it is characterised in that the question and answer interactive module is additionally operable to
Answer is extracted in the effective information that data memory module is stored according to subject of question and calculates extracted answer and puts question to
Matching degree, question and answer interactive module is additionally operable to select follow-up data transfer mode according to the matching degree：When matching degree reaches
During one threshold value, the answer is sent to user terminal and completes automation answer；The another Second Threshold having less than first threshold, works as matching
When degree is less than first threshold and is not less than Second Threshold, the answer is sent to user terminal, while subject of question is helped through expert
Hand subsystem is sent to artificial end, and artificial end is sent to user terminal to the answer of enquirement according to original route；When matching degree is less than second
During threshold value, subject of question is directly sent to artificial end through expert assistant's subsystem, artificial end is to the answer of enquirement according to original route
It is sent to user terminal.
5. Logistics Knowledge intelligent Answer System as claimed in claim 4, it is characterised in that the Logistics Knowledge intelligent answer system
System also includes data obtaining module, and data obtaining module is used to obtain hot information from high in the clouds and is sent to classifying module, focus
Information categorized module be sent to after homogeneous classification processing in data memory module and stored.
6. Logistics Knowledge intelligent Answer System as claimed in claim 5, it is characterised in that the Logistics Knowledge intelligent answer system
System also includes message processing module, and message processing module and expert assistant's subsystem are in hot information from data obtaining module to returning
It is handled during generic module, specifically, message processing module is used to receive the focus from data obtaining module
Information simultaneously carries out former data classification to it, and the hot information for completing former data classification is sent to expert info pushing module, expert
Info push module is drawn a portrait according to expert and pushes hot information, and the interpretive analysis to hot information and completion by expert to expert
The hot information of former data classification is sent to classifying module；The classifying module is to completing the hot information and specially of former data classification
Family carries out homogeneous classification processing to the interpretive analysis of hot information, and data memory module is according to the homogeneous classification result of classifying module
According to classification data storage.
7. Logistics Knowledge intelligent Answer System as claimed in claim 6, it is characterised in that described information processing module is based on many
The attributive character of individual dimension carries out former data to hot information and classified.
8. Logistics Knowledge intelligent Answer System as claimed in claim 7, it is characterised in that described information processing module is to heat
Point information is carried out before former data classification, and the attributive character to hot information in multiple dimensions distributes corresponding weighted value.
9. a kind of Logistics Knowledge intelligent answer method, it is characterised in that comprise the following steps：
S0, technocracy module are based on expert data and carry out expert's portrait；
S1, question and answer interactive module extract answer in data memory module according to subject of question and calculate extracted answer with puing question to
Matching degree；
S1 ', question and answer interactive module select follow-up data transfer mode according to the matching degree：When matching degree reaches first threshold
When, the answer is sent to user terminal and completes automation answer；The another Second Threshold having less than first threshold, when matching degree is less than
First threshold and when being not less than Second Threshold, is sent to user terminal, while subject of question is sent into expert info by the answer
Pushing module；When matching degree is less than Second Threshold, subject of question is directly sent to expert info pushing module；
S2, expert info pushing module are pushed according to expert portrait selection expert and putd question to；
S3, expert pushed into user terminal to the answer of enquirement according to original route.
10. Logistics Knowledge intelligent answer method as claimed in claim 9, it is characterised in that the data memory module according to
The information stored is divided into effective information and outdated information two states by preset rules, and setting rule includes：A, corresponding to spy
The information for determining classification was followed in corresponding effective time, and the information of the particular category switchs to outdated information after effective time；
The fresh information that b, data memory module are received from classifying module is contrasted with original effective information, when fresh information with
When the crucial Word similarity of original effective information reaches setting value, then original effective information switchs to outdated information, and fresh information is replaced
Original information is changed as effective information；
In the S1, question and answer interactive module is extracted in the effective information that data memory module is stored according to subject of question and answered
Case.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710567587.8A CN107220389A (en) | 2017-07-12 | 2017-07-12 | A kind of Logistics Knowledge intelligent Answer System and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710567587.8A CN107220389A (en) | 2017-07-12 | 2017-07-12 | A kind of Logistics Knowledge intelligent Answer System and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107220389A true CN107220389A (en) | 2017-09-29 |
Family
ID=59953329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710567587.8A Pending CN107220389A (en) | 2017-07-12 | 2017-07-12 | A kind of Logistics Knowledge intelligent Answer System and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220389A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766422A (en) * | 2018-12-29 | 2019-05-17 | 上海智臻智能网络科技股份有限公司 | Information processing method, apparatus and system, storage medium, terminal |
| CN110413748A (en) * | 2019-07-03 | 2019-11-05 | 北京智齿博创科技有限公司 | Based on big data robot service knowledge base entry recommender system |
| 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 |
| CN110717105A (en) * | 2019-10-12 | 2020-01-21 | 浙江大学 | Personalized active pushing method for scientific and technological resources |
| CN111143530A (en) * | 2019-12-24 | 2020-05-12 | 平安健康保险股份有限公司 | Intelligent answering method and device |
| CN113591953A (en) * | 2021-07-20 | 2021-11-02 | 深圳市德邦物流有限公司 | SVM (support vector machine) -based dynamic logistics big data effective information extraction algorithm |
| CN116109120A (en) * | 2023-04-17 | 2023-05-12 | 厦门微亚智能科技有限公司 | Industrial equipment management sharing system and management sharing method thereof |
Citations (2)
| 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 |
| CN105069177A (en) * | 2015-09-25 | 2015-11-18 | 苏州天梯卓越传媒有限公司 | Selected topic optimization system and selected topic optimization method for publishing industry |
-
2017
- 2017-07-12 CN CN201710567587.8A patent/CN107220389A/en active Pending
Patent Citations (2)
| 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 |
| CN105069177A (en) * | 2015-09-25 | 2015-11-18 | 苏州天梯卓越传媒有限公司 | Selected topic optimization system and selected topic optimization method for publishing industry |
Non-Patent Citations (1)
| Title |
|---|
| 赵金海: "《中国优秀硕士学位论文全文数据库》", 30 June 2007 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766422A (en) * | 2018-12-29 | 2019-05-17 | 上海智臻智能网络科技股份有限公司 | Information processing method, apparatus and system, storage medium, terminal |
| CN110413748A (en) * | 2019-07-03 | 2019-11-05 | 北京智齿博创科技有限公司 | Based on big data robot service knowledge base entry recommender system |
| 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 |
| CN110717105A (en) * | 2019-10-12 | 2020-01-21 | 浙江大学 | Personalized active pushing method for scientific and technological resources |
| CN111143530A (en) * | 2019-12-24 | 2020-05-12 | 平安健康保险股份有限公司 | Intelligent answering method and device |
| CN111143530B (en) * | 2019-12-24 | 2024-04-05 | 平安健康保险股份有限公司 | Intelligent reply method and device |
| CN113591953A (en) * | 2021-07-20 | 2021-11-02 | 深圳市德邦物流有限公司 | SVM (support vector machine) -based dynamic logistics big data effective information extraction algorithm |
| CN113591953B (en) * | 2021-07-20 | 2022-06-28 | 深圳市德邦物流有限公司 | Dynamic logistics big data effective information extraction algorithm |
| CN116109120A (en) * | 2023-04-17 | 2023-05-12 | 厦门微亚智能科技有限公司 | Industrial equipment management sharing system and management sharing method thereof |
| CN116109120B (en) * | 2023-04-17 | 2023-06-13 | 厦门微亚智能科技有限公司 | Industrial equipment management sharing system and management sharing method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220389A (en) | A kind of Logistics Knowledge intelligent Answer System and method | |
| CN109767255B (en) | Method for realizing intelligent operation and accurate marketing through big data modeling | |
| Yang et al. | Social media data analytics for business decision making system to competitive analysis | |
| Banker et al. | The use of categorical variables in data envelopment analysis | |
| Revathi et al. | A review on impact of information communication & computation technology (ICCT) on selected primary, secondary, and tertiary industrial sectors | |
| CN106709017B (en) | A kind of aid decision-making method based on big data | |
| CN107908606A (en) | Method and system based on different aforementioned sources automatic report generation | |
| CN106326413A (en) | Personalized video recommending system and method | |
| CN108830466A (en) | A kind of image content semanteme marking system and method based on cloud platform | |
| CN110516901A (en) | Customer value hierarchical mode building system and client's layered approach based on big data | |
| Boche et al. | Unraveling" land grabbing"-Different models of large-scale land acquisition in Southern Africa: LDPI Working Paper 46 | |
| CN103605738A (en) | Webpage access data statistical method and webpage access data statistical device | |
| CN105046435A (en) | School information system | |
| CN108897778A (en) | A kind of image labeling method based on multi-source big data analysis | |
| CN104346698A (en) | Catering member big data analysis and checking system based on cloud computing and data mining | |
| Joshi et al. | Critical challenges of integrating OPEX strategies with I4. 0 technologies in manufacturing SMEs: A few pieces of evidence from developing economies | |
| CN107992937A (en) | Unstructured data decision method and device based on deep learning | |
| Corbett et al. | Using community information systems to communicate traditional knowledge embedded in the landscape | |
| CN109359106A (en) | Campus big data cleaning-based service system | |
| CN107679702A (en) | A kind of enterprise's big data intellectual analysis manages method | |
| Guitart et al. | Adoption of business strategies to provide analytical systems for teachers in the context of universities | |
| CN104915388A (en) | Book tag recommendation method based on spectral clustering and crowdsourcing technology | |
| CN109874032A (en) | The program special topic personalized recommendation system and method for smart television | |
| CN108197194A (en) | A kind of processing method and system of information of reporting a case to the security authorities | |
| Dragičević et al. | Digital transformation in the mining enterprise: The empirical study |
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: 20170929 |
|
| RJ01 | Rejection of invention patent application after publication |