CN108446296A - A kind of information processing method and device - Google Patents
A kind of information processing method and device Download PDFInfo
- Publication number
- CN108446296A CN108446296A CN201810068768.0A CN201810068768A CN108446296A CN 108446296 A CN108446296 A CN 108446296A CN 201810068768 A CN201810068768 A CN 201810068768A CN 108446296 A CN108446296 A CN 108446296A
- Authority
- CN
- China
- Prior art keywords
- report
- event
- event report
- text
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An embodiment of the present invention provides a kind of information processing method and device, the method includes：Obtain focus incident label and multiple events report；The first text similarity of the focus incident label and the multiple event report is calculated, and, the second text similarity between the multiple event report is calculated, and, obtain the Aging Characteristic value of the multiple event report；According to first text similarity, second text similarity and the Aging Characteristic value, the maximal margin correlation of the multiple event report is calculated；It polymerize the multiple event report according to the maximal margin correlation of the multiple event report, obtains report polymerization result.According to embodiments of the present invention, it saves user and obtains the time and efforts reported with diversity, the event of timeliness.
Description
Technical field
The present invention relates to field of information processing, more particularly to a kind of information processing method, and, a kind of information processing apparatus
It sets, and, a kind of mobile terminal, and, a kind of computer readable storage medium.
Background technology
Currently, more and more users register capital to news, the especially concern to current hotspot event by Interworking GateWay.
In general, the event report that user can be directed to focus incident scans for obtaining relevant event report, alternatively, by
The event report of focus incident is recommended user by website operator.When search events are reported or recommend event report, need
A large amount of event report is polymerize, user is sent to using polymerization result as search result or recommendation results.
However, in current event report polymerization methods, the relevance of event report and focus incident is only accounted for, is caused
Duplicate contents are excessive in the multiple events report being polymerize, moreover, the event report being polymerize may be expired.And by upper
A large amount of repetitions, expired event report may be supplied to user, when user also needs to spend by the event report polymerization methods stated
Between and energy therefrom screen, to meet the demand of diversity, timeliness that it reports event etc..
Therefore, there is expend user time and energy to the event report polymerization methods of the prior art.
Invention content
The embodiment of the present invention provides a kind of information processing method for technical problem to be solved, and, Yi Zhongxin
Cease processing unit.
To solve the above-mentioned problems, the present invention provides a kind of information processing method, the method includes：
Obtain focus incident label and multiple events report；
The first text similarity of the focus incident label and the multiple event report is calculated, and, described in calculating
The second text similarity between multiple event reports, and, obtain the Aging Characteristic value of the multiple event report；
According to first text similarity, second text similarity and the Aging Characteristic value, calculate described more
The maximal margin correlation of a event report；
It polymerize the multiple event report according to the maximal margin correlation of the multiple event report, obtains report polymerization
As a result.
Optionally, the focus incident label has corresponding first text vector, described to calculate the focus incident mark
The step of first text similarity of label and the multiple event report, including：
Event report to be evaluated is chosen from the multiple event report；
Word segmentation processing is carried out to the event report to be evaluated, obtains multiple report participle texts；
Calculate the second text vector of the multiple report participle text；
The cosine value for calculating first text vector and second text vector, it is similar as first text
Degree.
Optionally, the event report has N number of, and N number of event report includes M and evaluated event report, 0 ＜ M ＜
N, the event report of having evaluated have corresponding third text vector, second calculated between the multiple event report
The step of text similarity, including：
Calculate the third text that the second text vector of the event report to be evaluated has evaluated event report with the M
M cosine value of vector；
Maximum cosine value is extracted in the M cosine value, as second text similarity.
Optionally, there is the focus incident label event time, the event report to have report time, the acquisition
The step of Aging Characteristic value of the multiple event report, including：
It calculates between the report time of the event report to be evaluated and the time of the event time of the focus incident label
Every value；
Using the time interval value and preset timeliness pad value, the Aging Characteristic of the event report to be evaluated is calculated
Value.
Optionally, the Aging Characteristic value includes the first Aging Characteristic value and the second Aging Characteristic value, described in the basis
First text similarity, second text similarity and the Aging Characteristic value calculate the maximum of the multiple event report
The step of edge correlation, including：
Calculate the first product of first text similarity and the first Aging Characteristic value；
Calculate the second product of second text similarity and the second Aging Characteristic value；
The difference for calculating first product and second product, as the maximal margin correlation.
Optionally, the maximal margin correlation according to the multiple event report polymerize the multiple event and reports,
The step of obtaining report polymerization result, including：
According to the size of the maximal margin correlation, the multiple event report is ranked up；
It regard multiple events report after sequence as the report polymerization result.
Optionally, the maximal margin correlation according to the multiple event report polymerize the multiple event and reports,
The step of obtaining report polymerization result, including：
In the multiple event report, the event for extracting the maximal margin correlation more than predetermined threshold value is reported；
The event extracted is reported and is used as the report polymerization result.
Optionally, the method further includes：
When receiving report searching request of the user for the focus incident label, the report polymerization result is sent extremely
The user；Or
Recommend the report polymerization result to user.
To solve the above-mentioned problems, the present invention also provides a kind of information processing unit, described device includes：
Label, report acquisition module, for obtaining focus incident label and multiple events report；
Text similarity, Aging Characteristic value computing module, for calculating the focus incident label and the multiple event
First text similarity of report, and, the second text similarity between the multiple event report is calculated, and, it obtains
The Aging Characteristic value of the multiple event report；
Maximal margin correlation value calculation module, for according to first text similarity, second text similarity
With the Aging Characteristic value, the maximal margin correlation of the multiple event report is calculated；
Report aggregation module, the maximal margin correlation for being reported according to the multiple event polymerize the multiple event
Report obtains report polymerization result.
Optionally, the focus incident label has corresponding first text vector, the text similarity, Aging Characteristic
It is worth computing module, including：
Event report to be evaluated chooses submodule, for choosing event report to be evaluated from the multiple event report；
Word segmentation processing submodule obtains multiple report participles for carrying out word segmentation processing to the event report to be evaluated
Text；
Second text vector computational submodule, the second text vector for calculating the multiple report participle text；
First Text similarity computing submodule, for calculating first text vector and second text vector
Cosine value, as first text similarity.
Optionally, the event report has N number of, and N number of event report includes M and evaluated event report, 0 ＜ M ＜
N, the event of having evaluated report there is corresponding third text vector, the text similarity, Aging Characteristic value computing module,
Including：
M cosine value computational submodule, the second text vector and the M for calculating the event report to be evaluated are a
M cosine value of the third text vector of event report is evaluated；
Second text similarity extracting sub-module, for extracting maximum cosine value in the M cosine value, as described
Second text similarity.
Optionally, there is the focus incident label event time, the event report to have report time, the text
Similarity, Aging Characteristic value computing module, including：
Time interval value computational submodule, the report time for calculating the event report to be evaluated and the hot spot thing
The time interval value of the event time of part label；
Aging Characteristic value computational submodule calculates institute for using the time interval value and preset timeliness pad value
State the Aging Characteristic value of event report to be evaluated.
Optionally, the Aging Characteristic value includes the first Aging Characteristic value and the second Aging Characteristic value, the maximal margin
Correlation value calculation module, including：
First product computational submodule, for calculating first text similarity and the first Aging Characteristic value
One product；
Second product computational submodule, for calculating second text similarity and the second Aging Characteristic value
Two products；
Product mathematic interpolation submodule, the difference for calculating first product and second product, as described
Maximal margin correlation.
Optionally, the report aggregation module, including：
Report sorting sub-module, for according to the maximal margin correlation size, to the multiple event report into
Row sequence；
First report polymerization result generates submodule, polymerize as the report for multiple events report after sorting
As a result.
Optionally, the report aggregation module, including：
Event reports extracting sub-module, in the multiple event report, extracting the maximal margin correlation
Event more than predetermined threshold value is reported；
Second report polymerization result generates submodule, for reporting the event extracted as report polymerization knot
Fruit.
Optionally, described device further includes：
It reports polymerization result sending module, is asked for the report search of the focus incident label for user ought to be received
It asks, sends the report polymerization result to the user；Or recommend the report polymerization result to user.
To solve the above-mentioned problems, it the present invention also provides a kind of mobile terminal, including processor, memory and is stored in
On the memory and the computer program that can run on the processor, the computer program are executed by the processor
When, realize any of the above-described information processing method.
To solve the above-mentioned problems, the present invention also provides a kind of computer readable storage mediums, which is characterized in that described
Computer program is stored on computer readable storage medium, when the computer program is executed by processor, is realized any of the above-described
The information processing method.
The embodiment of the present invention can reach advantageous effect below：
According to embodiments of the present invention, the first text similarity for being reported with multiple events in conjunction with focus incident label, multiple
The Aging Characteristic value of the second text similarity and multiple events report between event report, calculates multiple event reports
Maximal margin correlation, and multiple events report is polymerize according to maximal margin correlation, obtain report polymerization result.To
User provides this report polymerization result, without the screening of user effort time and efforts meet diversity that it reports event, when
The event report of effect property etc. demand saves user and obtains the time reported with diversity, the event of timeliness and essence
Power.
Description of the drawings
Fig. 1 is the step flow chart for the information processing method that the embodiment of the present invention one provides；
Fig. 2 is the step flow chart of information processing method provided by Embodiment 2 of the present invention；
Fig. 3 is the structure diagram for the information processing unit that the embodiment of the present invention three provides；
Fig. 4 is the structure diagram for the information processing unit that the embodiment of the present invention four provides.
Specific implementation mode
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is described in further detail.
Embodiment one
Fig. 1 is the step flow chart for the information processing method that the embodiment of the present invention one provides, and the method can be wrapped specifically
Include following steps：
Step 110, focus incident label and multiple events report are obtained.
Above-mentioned focus incident label can be one or more keywords of mark focus incident.
In the specific implementation, can be searched to multiple according to the temperature of search key by collecting the search key of user
Rope keyword is filtered and arranges, and obtains focus incident label.
For example, being directed to focus incident " the partner performer Li great Mei of Zhao Benshan dies of illness ", for search key, can obtain
Corresponding focus incident label is " performer Li great Mei dies of illness ", " Zhao Benshan partner dies of illness ", " Li great Mei dies of illness " etc..
Above-mentioned event report can be the report of news release, microblogging, blog articles on network for focus incident etc.
Road.
In the specific implementation, can be scanned for based on focus incident label, multiple event reports are extracted from search result.
It on the basis of previous example, searches for " performer Li great Mei dies of illness ", can obtain entitled " grieved！Zhao Benshan takes
The big U.S.A of shelves Lee dies of illness！The red child of son sends out microblogging and allows people's tear mesh！", " Zhao Benshan work together the big dead son of U.S. of Lee be small Shenyang fellow disciple teacher
Younger brother ", " the big U.S. of Song little Bao partner Lee is dead, dies at the age of 55 years old！Online friend:Zhao Jiaban is really eventful period！", " this mountain medium loses again
A member senior general, beloved pupil Lee is big, and U.S. is dead, and I had never expected son unexpectedly is him" etc. multiple events report.
Focus incident label is got as a result, and is reported for multiple events of focus incident label.
Step 120, the first text similarity of the focus incident label and the multiple event report is calculated, and,
The second text similarity between the multiple event report is calculated, and, obtain the Aging Characteristic of the multiple event report
Value.
In the specific implementation, the text vector of each keyword in focus incident label can be calculated, and, calculate event report
The text vector of each keyword in road calculates the cosine value between two text vectors, as above-mentioned text similarity.For
Explanation is distinguished, by the text similarity between focus incident label and event report, is named as the first text similarity.This
One text similarity can be used for the degree of association of evaluation event report and focus incident.
It is reported in the specific implementation, two events can be directed to, calculates the text vector of its each keyword, calculate two texts
Cosine value between this vector, as above-mentioned text similarity.In order to distinguish explanation, the text between two events are reported
Similarity is named as the second text similarity.First text similarity can be used for evaluating the pass between two event reports
Connection degree.
In the specific implementation, the event time of focus incident can be determined first, and, when determining the report of event report
Between, the Aging Characteristic value of event report is calculated according to event time and report time.The Aging Characteristic value, can be used for evaluating
The timeliness of event report.
In practical applications, can include to have evaluated event report and event to be evaluated report in multiple event reports.
Evaluated event report can be be evaluated as meeting user demand and event report labeled as final polymerization result
Road, and event to be evaluated report can be then currently carry out evaluating whether to meet user demand, it is unmarked be final polymerization knot
The event of fruit is reported.When executing step 120, more specifically, an event report to be evaluated can be chosen first, hot spot is calculated
The first text similarity between event tag and event to be evaluated report, and, calculate event report to be evaluated and at least one
A the second text similarity evaluated between event report, and, the report reported according to event time and event to be evaluated
Time calculates the Aging Characteristic value of the event report to be evaluated.
Certainly, in actual application scenarios, whole event reports can also be directed to and calculate the first text similarity, second
Text similarity and Aging Characteristic value, those skilled in the art can according to the first text similarity of actual demand setup algorithm,
The concrete mode and particular order of second text similarity and Aging Characteristic value, the embodiment of the present invention are not restricted this.
Step 130, according to first text similarity, second text similarity and the Aging Characteristic value, meter
Calculate the maximal margin correlation of the multiple event report.
In the specific implementation, MMR models (Maximal Marginal Relevance, maximal margin are related) meter may be used
Calculate maximal margin correlation.MMR models can report it based on similarity, the event between focus incident label and event report
Between similarity, event time and the dimensions such as interval between the report time, overall merit and the associated multiple things of focus incident
Relevance, diversity and the timeliness of part report.
Step 140, it polymerize the multiple event according to the maximal margin correlation of the multiple event report to report, obtains
Report polymerization result.
In the specific implementation, the size for the maximal margin correlation that can be reported according to multiple events, reports multiple events
It is ranked up, by the event report after sequence as report polymerization result；It can also be according to maximal margin correlation, to multiple things
Part report is screened, and filters out several events report of the maximal margin correlation more than predetermined threshold value as report polymerization knot
Fruit.Multiple events report in polymerization result, sorting forward is and focus incident close association, repetitive rate is relatively low and has
The event of timeliness reports, alternatively, being in polymerization result and focus incident close association, repetitive rate is relatively low and has timeliness
Event report, user need not in addition spend time and efforts, from polymerization result screening meet its event is reported it is various
Property, timeliness etc. demand event report.
According to embodiments of the present invention, the first text similarity for being reported with multiple events in conjunction with focus incident label, multiple
The Aging Characteristic value of the second text similarity and multiple events report between event report, calculates multiple event reports
Maximal margin correlation, and multiple events report is polymerize according to maximal margin correlation, obtain report polymerization result.To
User provides this report polymerization result, without the screening of user effort time and efforts meet diversity that it reports event, when
The event report of effect property etc. demand saves user and obtains the time reported with diversity, the event of timeliness and essence
Power.
Embodiment two
Fig. 2 is the step flow chart of information processing method provided by Embodiment 2 of the present invention, and the method can be wrapped specifically
Include following steps：
Step 210, focus incident label and multiple events report are obtained.
Step 220, the first text similarity of the focus incident label and the multiple event report is calculated, and,
The second text similarity between the multiple event report is calculated, and, obtain the Aging Characteristic of the multiple event report
Value.
Optionally, the focus incident label has corresponding first text vector, described to calculate the focus incident mark
The step of first text similarity of label and the multiple event report, including：
Step 221, event report to be evaluated is chosen from the multiple event report；
Step 222, word segmentation processing is carried out to the event report to be evaluated, obtains multiple report participle texts；
Step 223, the second text vector of the multiple report participle text is calculated；
Step 224, the cosine value for calculating first text vector and second text vector, as first text
This similarity.
In the specific implementation, the text vector of each keyword in focus incident label can be calculated, as focus incident mark
First text vector of label.It is reported for multiple events, can therefrom choose a thing for not being evaluated maximal margin correlation
Part is reported, is reported as event to be evaluated.Then, word segmentation processing is carried out to the event report to be evaluated, obtains multiple reports point
Word text.In practical application, the title that can be reported only for event to be evaluated carries out word segmentation processing.For example, for be evaluated
The title " this mountain medium loses a member senior general again, and beloved pupil Lee is big, and U.S. is dead, and I had never expected son unexpectedly is him " of event report, is segmented
Processing obtains multiple participle texts such as " this mountain ", " beloved pupil ", " Li great Mei ", " dead ", " son ", calculates multiple participle text
Text vector, as event to be evaluated report the second text vector.
After the second text vector for obtaining event report to be evaluated, the first text vector of focus incident label is calculated
Cosine value between the second text vector of event to be evaluated report, as the first above-mentioned text similarity.
For example, the first text vector of focus incident label E vent is eevent, currently there is N number of event to report, choose i-th
A event reports Feedi, reported as event to be evaluated, the second text vector is efeed_i, calculate the first text vector eevent
With the second text vector efeed_iBetween cosine value sim1Formula it is as follows：
Optionally, the event report has N number of, and N number of event report includes M and evaluated event report, 0 ＜ M ＜
N, the event report of having evaluated have corresponding third text vector, second calculated between the multiple event report
The step of text similarity, including：
Step 225, the second text vector for calculating the event report to be evaluated has evaluated event report with the M
M cosine value of third text vector；
Step 226, maximum cosine value is extracted in the M cosine value, as second text similarity.
In the specific implementation, assuming currently there is N number of event report, M event report therein has been evaluated, i.e., N number of
There are M to have been evaluated event report in event report.For event report has been evaluated, the text of its each keyword can be calculated
Vector, as the third text vector for having evaluated event report.
After the second text vector for obtaining event report to be evaluated, the second text of event report to be evaluated can be calculated
Cosine value between this vector and the M third text vectors for having evaluated event report, obtains M cosine value.It is remaining for the M
String value searches the maximum cosine value of numerical value, as the second above-mentioned text similarity.
On the basis of above-mentioned example, there are M to evaluate event report in N number of event report, take wherein j-th and evaluated
Event reports Feedj, third text vector is efeed_j, calculate the second text vector efeed_iWith third text vector efeed_j
Between cosine value sim2Formula it is as follows：
Optionally, there is the focus incident label event time, the event report to have report time, the acquisition
The step of Aging Characteristic value of the multiple event report, including：
Step 227, the event time of the report time and the focus incident label of the event report to be evaluated is calculated
Time interval value；
Step 228, using the time interval value and preset timeliness pad value, the event report to be evaluated is calculated
Aging Characteristic value.
In the specific implementation, the time of origin of focus incident can be determined in such a way that Manual definition or network crawl, make
The event time having for focus incident label.Furthermore, it is possible to which the publication event that event is reported, event is reported as it.By
This, has obtained the report time of the event and event report of focus incident label.
For the event time of the report time and focus incident label of event to be evaluated report, between the time between calculating
Every value.For example, the event time of focus incident label E vent is Tevent, event report Feed to be evaluatediThe report time be
Tfeed_i, time interval value Δ t=Tevent-Tfeed_i。
Above-mentioned timeliness pad value t can be preset based on experience valueo, the event for adjusting certain type focus incident
The ratio degree that temperature decays at any time.For time interval value Δ t and timeliness pad value to, can by exponential function formula
The Aging Characteristic value of event report to be evaluated is calculated.For example, following formula computational valid time eigenvalue λ may be used：
By above-mentioned formula, the event that can quantify reports the timeliness relative to focus incident.
Step 230, according to first text similarity, second text similarity and the Aging Characteristic value, meter
Calculate the maximal margin correlation of the multiple event report.
Optionally, the Aging Characteristic value include the first Aging Characteristic value and the second Aging Characteristic value, the step 230,
Including：
Step 231, the first product of first text similarity and the first Aging Characteristic value is calculated；
Step 232, the second product of second text similarity and the second Aging Characteristic value is calculated；
Step 233, the difference for calculating first product and second product, as the maximal margin correlation.
In practical application, MMR models may be used and calculate maximal margin correlation.MMR formula are as follows：
From above-mentioned formula as it can be seen that calculating the first text similarity sim1(Feedi, Event) and with the first Aging Characteristic value λ's
First product calculates the second text similarityWith the second Aging Characteristic value
The maximal margin correlation of event report to be evaluated can be calculated according to the difference of two products in second product of (1- λ)
MMRfeed_i。
It is reported for each event, the mode to repeat the above steps, you can obtain the maximal margin phase of multiple event reports
Pass value.
After the maximal margin correlation for obtaining event report, it can be correspondingly marked to have evaluated event report.
Step 240, it polymerize the multiple event according to the maximal margin correlation of the multiple event report to report, obtains
Report polymerization result.
Optionally, the step 240, including：
Step 241, according to the size of the maximal margin correlation, the multiple event report is ranked up；
Step 242, it regard multiple events report after sequence as the report polymerization result.
In the specific implementation, the maximal margin correlation that can be directed to multiple events report is ranked up, by the thing after sequence
Part report polymerization is as above-mentioned report polymerization result.This report polymerization result makes several events for sorting forward report,
Report that user can easily browse as a result, for the event relatively low and with timeliness with focus incident close association, repetitive rate
It is reported to required event.
Optionally, the step 240, including：
Step 243, in the multiple event report, the thing that the maximal margin correlation is more than predetermined threshold value is extracted
Part is reported；
Step 244, the event extracted is reported and is used as the report polymerization result.
In the specific implementation, the maximal margin correlation that event is reported can be compared with predetermined threshold value, if maximum side
Edge correlation is more than predetermined threshold value, then is retained, if maximal margin correlation is less than predetermined threshold value, is abandoned.Finally,
The event remained is reported that polymerization is used as above-mentioned report polymerization result.The event report that this report polymerization result is included,
It is that the event relatively low and with timeliness with focus incident close association, repetitive rate reports that user can be easily clear as a result,
It lookes to required event report.
Step 250, when receiving report searching request of the user for the focus incident label, it is poly- to send the report
Result is closed to the user；Alternatively, recommending the report polymerization result to user.
In the specific implementation, when user's search events are reported, user would generally submit some search key, if search is closed
Keyword and some focus incident tag match, then can be sent to user by the corresponding report polymerization result of focus incident label.
In addition it is also possible to the report polymerization result of some focus incident label periodically be sent to user, by multiple events
Report recommends user's browsing.
It should be noted that information processing method provided in an embodiment of the present invention can be applied on server, server
It can be reported according to the focus incident label of acquisition and multiple events by the above method, obtain report polymerization result, will report
Polymerization result is sent to the user terminal, and is shown to user.Certainly, in practical applications, can also be applied on user terminal, by
User terminal is reported by the above method according to the focus incident label of acquisition and multiple events, and report polymerization result is obtained, to
User shows.
Embodiment three
Fig. 3 be the embodiment of the present invention three provide information processing unit structure diagram, described information processing unit 300,
It can specifically include with lower module：
Label, report acquisition module 310, for obtaining focus incident label and multiple events report；
Text similarity, Aging Characteristic value computing module 320, for calculating the focus incident label and the multiple thing
First text similarity of part report, and, the second text similarity between the multiple event report is calculated, and, it obtains
Take the Aging Characteristic value of the multiple event report；
Maximal margin correlation value calculation module 330, for similar according to first text similarity, second text
Degree and the Aging Characteristic value calculate the maximal margin correlation of the multiple event report；
Report aggregation module 340, the maximal margin correlation polymerization for being reported according to the multiple event is the multiple
Event is reported, report polymerization result is obtained.
According to embodiments of the present invention, focus incident label and multiple event reports are obtained by label, report acquisition module 310
Road, by text similarity, Aging Characteristic value computing module 320 obtain the first text similarity, the second text similarity and when
Characteristic value is imitated, the first text of focus incident label and multiple events report is combined by maximal margin correlation value calculation module 330
The Aging Characteristic value of the second text similarity and multiple events report between similarity, multiple events report, calculates multiple
The maximal margin correlation of event report, and by reporting aggregation module 340 according to maximal margin correlation to multiple event reports
Road is polymerize, and report polymerization result is obtained.This report polymerization result is provided a user, is sieved without user effort time and efforts
The event report for selecting the diversity for meeting it and reporting event, timeliness etc. demand, saves user and obtains with more
Sample, timeliness event report time and efforts.
Example IV
Fig. 4 be the embodiment of the present invention four provide information processing unit structure diagram, described information processing unit 400,
It can specifically include with lower module：
Label, report acquisition module 410, for obtaining focus incident label and multiple events report；
Text similarity, Aging Characteristic value computing module 420, for calculating the focus incident label and the multiple thing
First text similarity of part report, and, the second text similarity between the multiple event report is calculated, and, it obtains
Take the Aging Characteristic value of the multiple event report；
Maximal margin correlation value calculation module 430, for similar according to first text similarity, second text
Degree and the Aging Characteristic value calculate the maximal margin correlation of the multiple event report；
Report aggregation module 440, the maximal margin correlation polymerization for being reported according to the multiple event is the multiple
Event is reported, report polymerization result is obtained；
It reports polymerization result sending module 450, is searched for the report of the focus incident label for user ought to be received
Rope is asked, and sends the report polymerization result to the user；Or recommend the report polymerization result to user.
Optionally, the focus incident label has corresponding first text vector, the text similarity, Aging Characteristic
It is worth computing module 420, following submodule can be specifically included：
Event report to be evaluated chooses submodule 421, for choosing event report to be evaluated from the multiple event report
Road；
Word segmentation processing submodule 422 obtains multiple reports point for carrying out word segmentation processing to the event report to be evaluated
Word text；
Second text vector computational submodule 423, the second text vector for calculating the multiple report participle text；
First Text similarity computing submodule 424, for calculate first text vector and second text to
The cosine value of amount, as first text similarity.
Optionally, the event report has N number of, and N number of event report includes M and evaluated event report, 0 ＜ M ＜
N, the event report of having evaluated have corresponding third text vector, the text similarity, Aging Characteristic value computing module
420, following submodule can be specifically included：
M cosine value computational submodule 425, for calculate the second text vector of the event to be evaluated report with it is described
M cosine value of the M third text vectors for having evaluated event report；
Second text similarity extracting sub-module 426, for extracting maximum cosine value in the M cosine value, as
Second text similarity.
Optionally, there is the focus incident label event time, the event report to have report time, the text
Similarity, Aging Characteristic value computing module 420, can specifically include following submodule：
Time interval value computational submodule 427, the report time for calculating the event report to be evaluated and the heat
The time interval value of the event time of point event tag；
Aging Characteristic value computational submodule 428 is calculated for using the time interval value and preset timeliness pad value
The Aging Characteristic value of the event report to be evaluated.
Optionally, the Aging Characteristic value includes the first Aging Characteristic value and the second Aging Characteristic value, the maximal margin
Correlation value calculation module 430, including：
First product computational submodule 431, for calculating first text similarity and the first Aging Characteristic value
The first product；
Second product computational submodule 432, for calculating second text similarity and the second Aging Characteristic value
The second product；
Product mathematic interpolation submodule 433, the difference for calculating first product and second product, as institute
State maximal margin correlation.
Optionally, the report aggregation module 440, can specifically include following submodule：
It reports sorting sub-module 441, for the size according to the maximal margin correlation, the multiple event is reported
It is ranked up；
First report polymerization result generates submodule 442, and the report is used as multiple events report after sorting
Polymerization result.
Optionally, the report aggregation module 440, can specifically include following submodule：
Event reports extracting sub-module 443, in the multiple event report, it is related to extract the maximal margin
Value is reported more than the event of predetermined threshold value；
Second report polymerization result generates submodule 444, polymerize as the report for reporting the event extracted
As a result.
Embodiment five
The embodiment of the present invention five provides a kind of mobile terminal, the mobile terminal, may include processor, memory and
It is stored in the computer program that can be run on the memory and on the processor；
When the computer program is executed by the processor, any described information in above method embodiment may be implemented
The step of processing method, and identical technique effect can be reached, to avoid repeating, which is not described herein again.
Wherein, processor is the control centre of mobile terminal, utilizes each of various interfaces and the entire terminal of connection
Part by running or execute the software program and/or module that are stored in memory, and is called and is stored in memory
Data execute the various functions and processing data of terminal.In addition, memory may include high-speed random access memory, may be used also
To include nonvolatile memory, for example, at least a disk memory, flush memory device or other volatile solid-states
Part.
Embodiment six
The embodiment of the present invention six provides a kind of computer readable storage medium, is deposited on the computer readable storage medium
Computer program is stored up, when the computer program is executed by processor, any letter in above method embodiment may be implemented
The step of ceasing processing method, and identical technique effect can be reached, to avoid repeating, which is not described herein again.
Wherein, the computer readable storage medium, as read-only memory (Read-Only Memory, abbreviation ROM),
Random access memory (Random Access Memory, abbreviation RAM), magnetic disc or CD etc..
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiment, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can be provided as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
In a typical configuration, the computer system includes one or more processors (CPU), input/output
Interface, network interface and memory.Memory may include the volatile memory in computer-readable medium, random access memory
The forms such as device (RAM) and/or Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is to calculate
The example of machine readable medium.Computer-readable medium includes that permanent and non-permanent, removable and non-removable media can be with
Information storage is realized by any method or technique.Information can be computer-readable instruction, data structure, the module of program or
Other data.The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM
(SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), fast flash memory bank or other memory techniques, CD-ROM are read-only
Memory (CD-ROM), digital versatile disc (DVD) or other optical storages, magnetic tape cassette, tape magnetic disk storage or
Other magnetic storage systems or any other non-transmission medium, can be used for storing can be by the information of computing system accesses.According to
Herein defines, and computer-readable medium does not include non-persistent computer readable media (transitory media), such as
The data-signal and carrier wave of modulation.
The embodiment of the present invention be with reference to according to the method for the embodiment of the present invention, terminal system (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in flow and/or box combination.These can be provided
Computer program instructions are to all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminal systems
The processor of system is to generate a machine so that is held by the processor of computer or other programmable data processing terminal systems
Capable instruction generates for realizing in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes
The device of specified function.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing terminal systems
In computer-readable memory operate in a specific manner so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one flow of flow chart or multiple flows and/or one side of block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing terminal systems so that
Series of operation steps are executed on computer or other programmable terminal systems to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal systems is provided for realizing in one flow of flow chart or multiple flows
And/or in one box of block diagram or multiple boxes specify function the step of.
Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal system including a series of elements are not only wrapped
Those elements are included, but also include other elements that are not explicitly listed, or further include for this process, method, article
Or the element that terminal system is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal system including the element.
Technical solution provided by the present invention is described in detail above, specific case used herein is to this hair
Bright principle and embodiment is expounded, the explanation of above example is only intended to help understand the present invention method and its
Core concept；Meanwhile for those of ordinary skill in the art, according to the thought of the present invention, in specific implementation mode and application
There will be changes in range, in conclusion the content of the present specification should not be construed as limiting the invention.
Claims (18)
1. a kind of information processing method, which is characterized in that the method includes：
Obtain focus incident label and multiple events report；
The first text similarity of the focus incident label and the multiple event report is calculated, and, it calculates the multiple
The second text similarity between event report, and, obtain the Aging Characteristic value of the multiple event report；
According to first text similarity, second text similarity and the Aging Characteristic value, the multiple thing is calculated
The maximal margin correlation of part report；
It polymerize the multiple event report according to the maximal margin correlation of the multiple event report, obtains report polymerization knot
Fruit.
2. according to the method described in claim 1, it is characterized in that, the focus incident label have corresponding first text to
The step of amount, first text similarity for calculating the focus incident label and the multiple event report, including：
Event report to be evaluated is chosen from the multiple event report；
Word segmentation processing is carried out to the event report to be evaluated, obtains multiple report participle texts；
Calculate the second text vector of the multiple report participle text；
The cosine value for calculating first text vector and second text vector, as first text similarity.
3. according to the method described in claim 2, it is characterized in that, event report has N number of, wrapped in N number of event report
It includes M and has evaluated event report, 0 ＜ M ＜ N, the event report of having evaluated has corresponding third text vector, the calculating
The step of the second text similarity between the multiple event report, including：
Calculate the third text vector that the second text vector of the event report to be evaluated has evaluated event report with the M
M cosine value；
Maximum cosine value is extracted in the M cosine value, as second text similarity.
4. according to the method described in claim 2, it is characterized in that, the focus incident label has event time, the thing
Part report has the step of report time, the Aging Characteristic value for obtaining the multiple event report, including：
Calculate the time interval value of the report time and the event time of the focus incident label of the event report to be evaluated；
Using the time interval value and preset timeliness pad value, the Aging Characteristic value of the event report to be evaluated is calculated.
5. according to the method described in claim 1, it is characterized in that, the Aging Characteristic value includes the first Aging Characteristic value and the
Two Aging Characteristic values, it is described according to first text similarity, second text similarity and the Aging Characteristic value, meter
The step of calculating the maximal margin correlation of the multiple event report, including：
Calculate the first product of first text similarity and the first Aging Characteristic value；
Calculate the second product of second text similarity and the second Aging Characteristic value；
The difference for calculating first product and second product, as the maximal margin correlation.
6. according to the method described in claim 1, it is characterized in that, the maximal margin phase reported according to the multiple event
Pass value polymerize the multiple event report, the step of obtaining reporting polymerization result, including：
According to the size of the maximal margin correlation, the multiple event report is ranked up；
It regard multiple events report after sequence as the report polymerization result.
7. according to the method described in claim 1, it is characterized in that, the maximal margin phase reported according to the multiple event
Pass value polymerize the multiple event report, the step of obtaining reporting polymerization result, including：
In the multiple event report, the event for extracting the maximal margin correlation more than predetermined threshold value is reported；
The event extracted is reported and is used as the report polymerization result.
8. according to the method described in claim 1, it is characterized in that, the method further includes：
When the report searching request for receiving user and being directed to the focus incident label, the report polymerization result is sent to described
User；Or
Recommend the report polymerization result to user.
9. a kind of information processing unit, which is characterized in that described device includes：
Label, report acquisition module, for obtaining focus incident label and multiple events report；
Text similarity, Aging Characteristic value computing module are reported for calculating the focus incident label with the multiple event
The first text similarity, and, calculate the second text similarity between the multiple event report, and, described in acquisition
The Aging Characteristic value of multiple event reports；
Maximal margin correlation value calculation module, for according to first text similarity, second text similarity and institute
Aging Characteristic value is stated, the maximal margin correlation of the multiple event report is calculated；
Report aggregation module, the maximal margin correlation for being reported according to the multiple event polymerize the multiple event report
Road obtains report polymerization result.
10. device according to claim 9, which is characterized in that the focus incident label has corresponding first text
Vector, the text similarity, Aging Characteristic value computing module, including：
Event report to be evaluated chooses submodule, for choosing event report to be evaluated from the multiple event report；
Word segmentation processing submodule obtains multiple report participle texts for carrying out word segmentation processing to the event report to be evaluated；
Second text vector computational submodule, the second text vector for calculating the multiple report participle text；
First Text similarity computing submodule, the cosine for calculating first text vector and second text vector
Value, as first text similarity.
11. device according to claim 10, which is characterized in that event report have it is N number of, in N number of event report
Event report, 0 ＜ M ＜ N are evaluated including M, the event report of having evaluated has corresponding third text vector, the text
This similarity, Aging Characteristic value computing module, including：
M cosine value computational submodule, the second text vector for calculating the event report to be evaluated have been commented with the M
M cosine value of the third text vector of valence event report；
Second text similarity extracting sub-module, for extracting maximum cosine value in the M cosine value, as described second
Text similarity.
12. device according to claim 10, which is characterized in that the focus incident label has event time, described
Event report, which has, reports the time, the text similarity, Aging Characteristic value computing module, including：
Time interval value computational submodule, the report time for calculating the event report to be evaluated and the focus incident mark
The time interval value of the event time of label；
Aging Characteristic value computational submodule is waited for for using the time interval value and preset timeliness pad value described in calculating
The Aging Characteristic value of evaluation event report.
13. device according to claim 9, which is characterized in that the Aging Characteristic value include the first Aging Characteristic value and
Second Aging Characteristic value, the maximal margin correlation value calculation module, including：
First product computational submodule multiplies for calculating first text similarity with the first of the first Aging Characteristic value
Product；
Second product computational submodule multiplies for calculating second text similarity with the second of the second Aging Characteristic value
Product；
Product mathematic interpolation submodule, the difference for calculating first product and second product, as the maximum
Edge correlation.
14. device according to claim 9, which is characterized in that the report aggregation module, including：
It reports sorting sub-module, for the size according to the maximal margin correlation, the multiple event report is arranged
Sequence；
First report polymerization result generates submodule, for multiple events report after sorting as report polymerization knot
Fruit.
15. device according to claim 9, which is characterized in that the report aggregation module, including：
Event reports extracting sub-module, in the multiple event report, extracting the maximal margin correlation and being more than
The event of predetermined threshold value is reported；
Second report polymerization result generates submodule, and the report polymerization result is used as reporting the event extracted.
16. device according to claim 9, which is characterized in that described device further includes：
Report polymerization result sending module, for working as the report searching request for receiving user and being directed to the focus incident label,
The report polymerization result is sent to the user；Or recommend the report polymerization result to user.
17. a kind of mobile terminal, which is characterized in that including processor, memory and be stored on the memory and can be in institute
The computer program run on processor is stated, when the computer program is executed by the processor, realizes the claims
Any information processing methods of 1-8.
18. a kind of computer readable storage medium, which is characterized in that store computer journey on the computer readable storage medium
Sequence when the computer program is executed by processor, realizes any information processing methods of the claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810068768.0A CN108446296B (en) | 2018-01-24 | 2018-01-24 | Information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810068768.0A CN108446296B (en) | 2018-01-24 | 2018-01-24 | Information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108446296A true CN108446296A (en) | 2018-08-24 |
| CN108446296B CN108446296B (en) | 2021-10-15 |
Family
ID=63191142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810068768.0A Active CN108446296B (en) | 2018-01-24 | 2018-01-24 | Information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108446296B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918627A (en) * | 2019-01-08 | 2019-06-21 | 平安科技（深圳）有限公司 | Document creation method, device, electronic equipment and storage medium |
| CN110543914A (en) * | 2019-09-04 | 2019-12-06 | 软通动力信息技术有限公司 | Event data processing method and device, computing equipment and medium |
| CN110929018A (en) * | 2019-12-04 | 2020-03-27 | Oppo（重庆）智能科技有限公司 | Text processing method and device, storage medium and electronic equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101174273A (en) * | 2007-12-04 | 2008-05-07 | 清华大学 | News event detecting method based on metadata analysis |
| JP4231298B2 (en) * | 2003-01-14 | 2009-02-25 | 日本電信電話株式会社 | Information extraction rule creation system, information extraction rule creation program, information extraction system, and information extraction program |
| US20120089599A1 (en) * | 2006-12-07 | 2012-04-12 | Google Inc. | Interleaving Search Results |
| CN102929977A (en) * | 2012-10-16 | 2013-02-13 | 浙江大学 | Event tracing method aiming at news website |
| CN102937960A (en) * | 2012-09-06 | 2013-02-20 | 北京邮电大学 | Device and method for identifying and evaluating emergency hot topic |
| CN103020159A (en) * | 2012-11-26 | 2013-04-03 | 百度在线网络技术（北京）有限公司 | Method and device for news presentation facing events |
| CN103984757A (en) * | 2014-05-29 | 2014-08-13 | 北京奇虎科技有限公司 | Method and system for inserting news information articles in search result page |
| CN104217033A (en) * | 2014-09-29 | 2014-12-17 | 北京奇虎科技有限公司 | Search method and device based on timeliness |
| CN104915447A (en) * | 2015-06-30 | 2015-09-16 | 北京奇艺世纪科技有限公司 | Method and device for tracing hot topics and confirming keywords |
| CN106776933A (en) * | 2016-12-01 | 2017-05-31 | 厦门市美亚柏科信息股份有限公司 | A kind of processing method and system that polymerization is analyzed to similar case information |
| CN106874419A (en) * | 2017-01-22 | 2017-06-20 | 北京航空航天大学 | A kind of real-time focus polymerization of many granularities |
| CN107038193A (en) * | 2016-11-17 | 2017-08-11 | 阿里巴巴集团控股有限公司 | A kind for the treatment of method and apparatus of text message |
-
2018
- 2018-01-24 CN CN201810068768.0A patent/CN108446296B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4231298B2 (en) * | 2003-01-14 | 2009-02-25 | 日本電信電話株式会社 | Information extraction rule creation system, information extraction rule creation program, information extraction system, and information extraction program |
| US20120089599A1 (en) * | 2006-12-07 | 2012-04-12 | Google Inc. | Interleaving Search Results |
| CN101174273A (en) * | 2007-12-04 | 2008-05-07 | 清华大学 | News event detecting method based on metadata analysis |
| CN102937960A (en) * | 2012-09-06 | 2013-02-20 | 北京邮电大学 | Device and method for identifying and evaluating emergency hot topic |
| CN102929977A (en) * | 2012-10-16 | 2013-02-13 | 浙江大学 | Event tracing method aiming at news website |
| CN103020159A (en) * | 2012-11-26 | 2013-04-03 | 百度在线网络技术（北京）有限公司 | Method and device for news presentation facing events |
| CN103984757A (en) * | 2014-05-29 | 2014-08-13 | 北京奇虎科技有限公司 | Method and system for inserting news information articles in search result page |
| CN104217033A (en) * | 2014-09-29 | 2014-12-17 | 北京奇虎科技有限公司 | Search method and device based on timeliness |
| CN104915447A (en) * | 2015-06-30 | 2015-09-16 | 北京奇艺世纪科技有限公司 | Method and device for tracing hot topics and confirming keywords |
| CN107038193A (en) * | 2016-11-17 | 2017-08-11 | 阿里巴巴集团控股有限公司 | A kind for the treatment of method and apparatus of text message |
| CN106776933A (en) * | 2016-12-01 | 2017-05-31 | 厦门市美亚柏科信息股份有限公司 | A kind of processing method and system that polymerization is analyzed to similar case information |
| CN106874419A (en) * | 2017-01-22 | 2017-06-20 | 北京航空航天大学 | A kind of real-time focus polymerization of many granularities |
Non-Patent Citations (1)
| Title |
|---|
| 白庆祥: "《新闻论语》", 31 October 2002, 北京：北京广播学院出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918627A (en) * | 2019-01-08 | 2019-06-21 | 平安科技（深圳）有限公司 | Document creation method, device, electronic equipment and storage medium |
| CN109918627B (en) * | 2019-01-08 | 2024-03-19 | 平安科技（深圳）有限公司 | Text generation method, device, electronic equipment and storage medium |
| CN110543914A (en) * | 2019-09-04 | 2019-12-06 | 软通动力信息技术有限公司 | Event data processing method and device, computing equipment and medium |
| CN110543914B (en) * | 2019-09-04 | 2022-06-24 | 软通智慧信息技术有限公司 | Event data processing method and device, computing equipment and medium |
| CN110929018A (en) * | 2019-12-04 | 2020-03-27 | Oppo（重庆）智能科技有限公司 | Text processing method and device, storage medium and electronic equipment |
| CN110929018B (en) * | 2019-12-04 | 2023-03-21 | Oppo（重庆）智能科技有限公司 | Text processing method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108446296B (en) | 2021-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Reddy et al. | Content-based movie recommendation system using genre correlation | |
| US9449271B2 (en) | Classifying resources using a deep network | |
| CA2655196C (en) | System and method for generating a display of tags | |
| Yu et al. | TIIREC: A tensor approach for tag-driven item recommendation with sparse user generated content | |
| KR20140091530A (en) | Relevance of name and other search queries with social network features | |
| Ricci | Recommender Systems: Models and Techniques. | |
| CN102955810B (en) | A kind of Web page classification method and equipment | |
| Bouadjenek et al. | Persador: personalized social document representation for improving web search | |
| Oliveira et al. | A recommendation approach for consuming linked open data | |
| Hamouda et al. | Put-tag: personalized user-centric tag recommendation for social bookmarking systems | |
| CN104123285B (en) | The air navigation aid and device of search result | |
| CN108446296A (en) | A kind of information processing method and device | |
| Rawat et al. | A comprehensive study on recommendation systems their issues and future research direction in e-learning domain | |
| Cena et al. | Anisotropic propagation of user interests in ontology-based user models | |
| Jay et al. | Review on web search personalization through semantic data | |
| Lotfi et al. | A tool for study on impact of Big Data technologies on firm performance | |
| Loizou | How to recommend music to film buffs: enabling the provision of recommendations from multiple domains | |
| Han | [Retracted] Recommendation Algorithm of Web‐Based Learning Resources considering Timeliness and Popularity | |
| Liang et al. | Personalized recommender system based on item taxonomy and folksonomy | |
| Movahedian et al. | A tag-based recommender system using rule-based collaborative profile enrichment | |
| Sharma et al. | A trust-based architectural framework for collaborative filtering recommender system | |
| Mirizzi et al. | Linked Open Data for content-based recommender systems | |
| Alinaghi et al. | A multi-agent question-answering system for e-learning and collaborative learning environment | |
| Sammulal et al. | A personalized recommender system using conceptual dynamics | |
| Srifi et al. | A concise survey on content recommendations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |