CN106469214A - Information demonstrating method based on artificial intelligence and device - Google Patents
Information demonstrating method based on artificial intelligence and device Download PDFInfo
- Publication number
- CN106469214A CN106469214A CN201610805851.2A CN201610805851A CN106469214A CN 106469214 A CN106469214 A CN 106469214A CN 201610805851 A CN201610805851 A CN 201610805851A CN 106469214 A CN106469214 A CN 106469214A
- Authority
- CN
- China
- Prior art keywords
- information
- search
- text fragments
- search information
- mentioned
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
Abstract
This application discloses the information demonstrating method based on artificial intelligence and device.One specific embodiment of methods described includes：Obtain the search information of user and click information set in preset time period, wherein, described click information set includes clicked information in the Search Results presenting in response to searching for described search information；According to described search information, generate association search information；Contrast described search information and described association search information, extract described search information and total text fragments in described association search information；Confirm that described text fragments whether there is in described click information set；In response to confirming that described text fragments are present in described click information set, then further determine that whether described text fragments meet default condition；If so, then store described text fragments, and assume described text fragments.This embodiment improves the ageing of word excavation.
Description
Technical field
The application is related to field of computer technology and in particular to technical field of information processing, is more particularly, to based on artificial intelligence
The information demonstrating method of energy and device.
Background technology
Artificial intelligence (Artificial Intelligence, AI) is research, is developed for simulation, extends and extension people
The theory of intelligence, new science of technology of method, technology and application system.Artificial intelligence is of computer science
Branch, it attempts to understand the essence of intelligence, and produces a kind of new intelligence that can make a response in the way of human intelligence is similar
Energy machine, the research in this field includes robot, language identification, image recognition, natural language processing and specialist system etc..
In artificial intelligence field, neologisms digging technology has and is increasingly widely applied.Neologisms, are also called unregistered word
(Out Of Vocabulary, OOV), refers to word or the phrase do not included in dictionary, common unregistered word include name,
Name and enterprise's name etc..By the neologisms method for digging of artificial intelligence technology for natural language processing field multiple shallow-layer morphology
Analysis task has vital impact.Existing neologisms method for digging is normally based on the grammatical ruless of natural language, from
The vocabulary of hit particular search mode is extracted in target text, or, based on large-scale corpus statisticses, from the statistics of vocabulary
The support information that character string becomes word is found, however, these modes need manually the data of rule or statistics to be carried out in feature
Process, exist that word digging efficiency is low and word excavates ageing low problem.
Content of the invention
The purpose of the application is to propose a kind of improved information demonstrating method based on artificial intelligence and device, to solve
The technical problem that background section above is mentioned.
In a first aspect, this application provides a kind of information demonstrating method based on artificial intelligence, methods described includes：Obtain
The search information of user and click information set in preset time period, wherein, described click information set is included in response to searching
Clicked information in the Search Results that Suo Suoshu searches for information and presents；According to described search information, generate association search letter
Breath；Contrast described search information and described association search information, extract described search information common with described association search information
Some text fragments；Confirm that described text fragments whether there is in described click information set；In response to confirming described literary composition
This fragment is present in described click information set, then further determine that whether described text fragments meet default condition；If
It is then to store described text fragments, and assume described text fragments.
In certain embodiments, described association search information is generated according to described search information, including：Search with described
The related relevant search information of search information, wherein, described relevant search information include following at least one：With described search letter
Breath have same clip search information and with described search information synon search information each other；Obtain in response to search
Described relevant search information and clicked related click information in the Search Results that present, and generate related click information collection
Close；Determine that the described related related click information clicked in information aggregate is had with the click information in described click information set
The quantity of identical information, and confirm whether described quantity is more than default amount threshold；If so, then by described relevant search information
As association search information.
In certain embodiments, whether the described text fragments of described determination meet default condition, including：Determine described literary composition
Whether the number of words of this fragment is less than default number of words threshold value；Number of words in response to determining described text fragments is less than default word
Number threshold value is it is determined that described text fragments meet default condition.
In certain embodiments, whether the described text fragments of described determination meet default condition, including：Determine described literary composition
Whether this fragment is more than default retrieval frequency threshold value as the number of times that search information is retrieved；In response to determining described text
The number of times that fragment is retrieved as search information be more than default retrieval frequency threshold value it is determined that described text fragments meet default
Condition.
In certain embodiments, described assume described text fragments, including：Obtain in preset time period in default application
The middle frequency using described text fragments；Determine whether the described frequency using described text fragments is more than default usage frequency
Threshold value；If so, then described text fragments are processed, and assume the described text fragments after process, wherein, described to described
Text fragments carry out processing include following at least one：Font processing, amplification is processed, color treatments.
In certain embodiments, the described search information of described contrast and described association search information, extracts described search letter
Breath and total text fragments in described association search information, including：Described search information is divided at least one searching piece
Section, to generate search snippet set；Described association search information is divided at least one association search fragment, to generate association
Search snippet set；Detect search snippet in described search snippet set whether there is with described association search set of segments in
Association search fragment identical text fragments；If so, described identical text fragments are then extracted.
Second aspect, this application provides a kind of information presentation device based on artificial intelligence, described device includes：Obtain
Unit, is configured to obtain the search information of user and click information set in preset time period, wherein, described click information collection
Close and include clicked information in the Search Results presenting in response to searching for described search information；Signal generating unit, configuration is used
According to described search information, generate association search information；Extraction unit, is configured to contrast described search information and described pass
Connection search information, extracts described search information and total text fragments in described association search information；Confirmation unit, configuration is used
Whether there is in described click information set in the described text fragments of confirmation；Determining unit, is configured in response to confirming
Described text fragments are present in described click information set, then further determine that whether described text fragments meet default bar
Part；Display unit, if being configured to described text fragments to meet default condition, stores described text fragments, and assumes institute
State text fragments.
In certain embodiments, described signal generating unit includes：Searching modul, is configured to search and described search information phase
Close relevant search information, wherein, described relevant search information include following at least one：With described search information have identical
The search information of fragment and with described search information synon search information each other；Generation module, is configured to obtain and is ringing
In searching for described relevant search information and clicked related click information in the Search Results that present, and related click should be generated
Information aggregate；Confirm module, be configured to determine the described related related click information clicked in information aggregate and described click
Click information in information aggregate has the quantity of identical information, and confirms whether described quantity is more than default amount threshold；
Processing module, if being configured to confirm, described quantity is more than default amount threshold, using described relevant search information as
Association search information.
In certain embodiments, described determining unit includes：First determining module, is configured to determine described text fragments
Number of words whether be less than default number of words threshold value；Second determining module, is configured in response to determining described text fragments
Number of words is less than default number of words threshold value it is determined that described text fragments meet default condition.
In certain embodiments, described determining unit includes：3rd determining module, is configured to determine described text fragments
Whether it is more than default retrieval frequency threshold value as the number of times that search information is retrieved；4th determining module, is configured to respond
In determining that the number of times that described text fragments are retrieved as search information is more than default retrieval frequency threshold value it is determined that described
Text fragments meet default condition.
In certain embodiments, described display unit includes：Acquisition module, is configured to obtain in preset time period pre-
If application in using described text fragments frequency；Determining module, be configured to determine described using described text fragments
Whether frequency is more than default usage frequency threshold value；Assume module, be configured to if it is determined that described using described text fragments
Frequency be more than default usage frequency threshold value, then described text fragments are processed, and assume the described text after process
Fragment, wherein, described described text fragments are carried out process include following at least one：Font processing, amplification is processed, face
Color is processed.
In certain embodiments, described extraction unit includes：First division module, is configured to draw described search information
It is divided at least one search snippet, to generate search snippet set；Second division module, is configured to believe described association search
Breath is divided at least one association search fragment, to generate association search set of segments；Detection module, is configured to detection described
Search snippet in search snippet set whether there is and the association search fragment identical in described association search set of segments
Text fragments；Extraction module, if be configured to detect that the search snippet in described search snippet set exists and described association
Association search fragment identical text fragments in search snippet set, then extract described identical text fragments.
The information demonstrating method based on artificial intelligence and device that the application provides, by carrying out to the search information of user
Analysis, generates association search information, and extracts search information and identical text fragments in association search information, then in determination
State text fragments to whether there is in click information, if so, further determine whether above-mentioned text fragments meet default bar
Part, if above-mentioned text fragments meet default condition, stores and presents above-mentioned text fragments, thus effectively make use of user
Search information with corresponding click information so that the word excavated is more accurate, improve simultaneously word excavation efficiency and
It is ageing that word excavates.
Brief description
By reading the detailed description that non-limiting example is made made with reference to the following drawings, other of the application
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that the application can apply to exemplary system architecture figure therein；
Fig. 2 is the flow chart of an embodiment according to the application based on the information demonstrating method of artificial intelligence；
Fig. 3 is the schematic diagram of application scenarios according to the application based on the information demonstrating method of artificial intelligence；
Fig. 4 is the flow chart of another embodiment according to the application based on the information demonstrating method of artificial intelligence；
Fig. 5 is the structural representation of an embodiment according to the application based on the information presentation device of artificial intelligence；
Fig. 6 is adapted for the structural representation of the computer system of the server for realizing the embodiment of the present application.
Specific embodiment
With reference to the accompanying drawings and examples the application is described in further detail.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to this invention.It also should be noted that, in order to
It is easy to describe, in accompanying drawing, illustrate only the part related to about invention.
It should be noted that in the case of not conflicting, the embodiment in the application and the feature in embodiment can phases
Mutually combine.To describe the application below with reference to the accompanying drawings and in conjunction with the embodiments in detail.
Fig. 1 shows the information demonstrating method based on artificial intelligence or the letter based on artificial intelligence that can apply the application
Breath assumes the exemplary system architecture 100 of the embodiment of device.
As shown in figure 1, system architecture 100 can include terminal unit 101,102,103, network 104 server 105.
Network 104 is in order to provide the medium of communication link between terminal unit 101,102,103 server 105.Network 104 is permissible
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted with server 105 by network 104 with using terminal equipment 101,102,103, to receive or to send out
Send message etc..Various telecommunication customer end applications can be provided with terminal unit 101,102,103, for example, web browser should
With the application of, searching class, input method application etc..
Terminal unit 101,102,103 can be to have the various electronic equipments that display screen and supported web page browse, bag
Include but be not limited to smart mobile phone, panel computer, E-book reader, pocket computer on knee and desk computer etc..
Server 105 can be the server providing various services, such as to acquisition on terminal unit 101,102,103
The search information of user and click information set provide the backstage word server supported.Backstage word server can be to acquisition
To user search information and click information set in the data such as click information be analyzed etc. processing, and by result
(text fragments for example excavated) feed back to terminal unit.
It should be noted that the information demonstrating method based on artificial intelligence that provided of the embodiment of the present application is typically by servicing
Device 105 executes, and correspondingly, is generally positioned in server 105 based on the information presentation device of artificial intelligence.
It should be understood that the terminal unit in Fig. 1, the number of network server are only schematically.According to realizing need
Will, can have any number of terminal unit, network server.
With continued reference to Fig. 2, show an embodiment based on the information demonstrating method of artificial intelligence according to the application
Flow process 200.The described information demonstrating method based on artificial intelligence, comprises the following steps：
Step 201, obtains the search information of user and click information set in preset time period.
In the present embodiment, the information demonstrating method based on artificial intelligence runs electronic equipment (such as Fig. 1 institute thereon
The server showing) terminal of information search can be carried out from user using it by wired connection mode or radio connection
Obtain the click information set of user the search information of (for example, one month, one week etc.) and user within the default time period, its
In, above-mentioned click information set can be when above-mentioned user search for above-mentioned search information after at the Search Results midpoint presenting
The set of the information hit, for example, after above-mentioned user search " tea is doted on for what implied meaning ", the retrieval result that presents has that " tea is doted on
Be particular about, tea dotes on picture appreciation ", " on Tea Service, putting that what tea is doted on " etc., user clicks in Search Results " it is exquisite that tea is doted on,
Tea dotes on picture appreciation " after, the click information in above-mentioned click information set can be for " it is exquisite that tea is doted on, and tea dotes on picture reward
Analysis ".It is pointed out that above-mentioned radio connection can include but is not limited to 3G/4G connection, WiFi connection, bluetooth connection,
WiMAX connects, Zigbee connects, UWB (ultra wideband) connects and other are currently known or exploitation in the future wireless
Connected mode.
Step 202, according to search information, generates association search information.
In the present embodiment, after step 201 gets the search information of user, above-mentioned electronic equipment can be according to upper
State search information, generate association search information.Above-mentioned search information can be divided at least one search by above-mentioned electronic equipment
Then search word is substituted for synonym or the near synonym of search word by word, and the search information after replacing it is as association search
Information, for example, when the information of search is " effect of coldrex ", " effect of coldrex " is divided into " coldrex " and " makees
With ", then " coldrex " is substituted for " fever medicine ", " acting on " is substituted for " effect ", then association search information can be for " sending out
Burn effect of medicine "；Above-mentioned electronic equipment can also obtain to be occurred in the click information in search information and click information set
Frequency highest search word, obtains the search letter comprising above-mentioned search word in preset time period in predetermined application afterwards
Breath, then selects the search information that searched number of times highest comprises above-mentioned search word in search information, and above-mentioned search is believed
Breath is as association search information.Above-mentioned association search information can be the pass that user clicks in the region assuming association search information
Join the association search information of other operations that search information or user are carried out in the region assuming association search information.
Step 203, contrast search information and association search information, have in extraction search information and association search information
Text fragments.
In the present embodiment, above-mentioned electronic equipment can pass through to contrast above-mentioned search information and above-mentioned association search information,
Extract above-mentioned search information and total text fragments in above-mentioned association search information, wherein, above-mentioned text fragments can be word
Language, short sentence etc..For example, when search information is " which coldrex effect is good ", above-mentioned association search information is " which coldrex
Small side effects ", then the total text fragments extracting can be " which ", " flu ", " medicine " and " coldrex ".
In some optional implementations of the present embodiment, above-mentioned search information can be drawn by above-mentioned electronic equipment first
It is divided at least one search snippet, and generate search snippet set；Afterwards, above-mentioned association search information can be divided at least
One association search fragment, and generate association search set of segments；Then, above-mentioned electronic equipment can detect above-mentioned search snippet
Whether there is in search snippet in set and the association search fragment identical text piece in above-mentioned association search set of segments
Section, is searched with associating in above-mentioned association search set of segments if detecting and existing in the search snippet in above-mentioned search snippet set
Rope fragment identical text fragments, then can extract above-mentioned identical text fragments.As an example, when getting above-mentioned search letter
Cease for " what tea ointment is ", above-mentioned association search information is " what color tea ointment is ", " effect of tea ointment ", " Pu'er tea paste valency
Lattice " etc., search information " what tea ointment is " can be divided into " tea ointment ", "Yes", " what " by above-mentioned electronic equipment first, and
Put it in search snippet set, then by association search information " what color tea ointment is ", " effect of tea ointment " and " Folium camelliae assamicae
Cream price " is divided into " tea ointment ", "Yes", " what ", " color ", " effect ", " Pu'er ", " price ", and puts it into association and search
In rope set of segments；Afterwards, above-mentioned electronic equipment can detect search snippet " tea ointment " in above-mentioned search snippet set,
In "Yes", " what " whether there is with above-mentioned association search set of segments in relevant search set of segments " tea ointment ", "Yes",
" what ", " color ", " effect ", " Pu'er ", " price " identical text fragments, detect above-mentioned search snippet " tea ointment ", " assorted
" identical with above-mentioned association search fragment " tea ointment ", " what ", then extract above-mentioned identical text fragments " tea ointment " and " assorted
".
Step 204, confirms that text fragments whether there is in click information set.
In the present embodiment, above-mentioned electronic equipment can confirm that the text fragments extracting in step 203 whether there is in upper
State in click information set, for example, the text fragments of said extracted are " tea ointment " and " what ", in above-mentioned click information set
Click information is " how tea ointment is drunk " and " benefit of cream of having tea ", and above-mentioned electronic equipment can be first by above-mentioned click information
How about " how tea ointment is drunk " and " benefit of cream of having tea " is divided into " tea ointment ", " ", " drinking ", " benefit ", then, judges " tea
How about cream " and " what " are with the presence or absence of in " tea ointment ", " ", " drinking ", " benefit ".
Step 205, in response to confirming that text fragments are present in click information set, then further determines that text fragments
Whether meet default condition.
In the present embodiment, confirm that above-mentioned text fragments are present in above-mentioned click information set, above-mentioned electronic equipment
Can determine whether above-mentioned text fragments meet default condition, wherein, above-mentioned default condition can be according to history text
That the rule that fragment is excavated is configured or being configured according to user-defined condition.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can count above-mentioned text fragments first
Number of words；Afterwards it may be determined that whether above-mentioned number of words is less than default number of words threshold value, if so, then can determine above-mentioned text piece
The default condition of Duan Fuhe.For example, when above-mentioned default number of words threshold value is five, when the number of words determining above-mentioned text fragments is less than
It is determined that above-mentioned text fragments meet default condition when five.
Step 206 meets default condition however, it is determined that going out text fragments, then store text fragments, and assume text fragments.
In the present embodiment, meet default condition in response to determining above-mentioned text fragments, above-mentioned electronic equipment is permissible
Store above-mentioned text fragments, and assume above-mentioned text fragments.Above-mentioned electronic equipment can assume what excavation was arrived in the form of word cloud
Text fragments, wherein, visual prominent, shape that above-mentioned word cloud is that higher to the frequency of occurrences in network text " key word " gives
Become " key word cloud layer " or " key word renders ", thus filtering out substantial amounts of text message, as long as making to browse webpage, person sweeps at a glance
Cross the purport that text just can have a taste of text；Above-mentioned electronic equipment can also provide the query interface of above-mentioned text fragments, convenient
The text fragments that user excavated in the query history time period；Above-mentioned electronic equipment can also be in natural language processing field
The morphological analysis systems such as civilian Words partition system, name Entity recognition provide basic resource to assist the performance improving these systems.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can obtain above-mentioned text fragments first
The usage frequency in default application (for example, A search engine, B input method etc.) within the default time period；Then, above-mentioned
Electronic equipment can determine whether the usage frequency of above-mentioned text fragments is more than default usage frequency threshold value, if so, then to upper
State text fragments to be processed, and assume the text fragments after process, wherein, carrying out process to above-mentioned text fragments can include
Font to above-mentioned text fragments is processed (for example, to be carried out overstriking, inclination, adds lower stroke to the font of above-mentioned text fragments
Line etc.) process (for example, with 1.5 times of above-mentioned texts of amplification of original font it is also possible to above-mentioned text fragments are amplified with multiple
The font of fragment), the color of above-mentioned text fragments can also be processed and (for example, the font of above-mentioned text fragments be arranged
The eye-catching color such as yellowly, redness).
With continued reference to Fig. 3, Fig. 3 is the application scenarios according to the present embodiment based on the information demonstrating method of artificial intelligence
One schematic diagram.In the application scenarios of Fig. 3, after the search information of user input is " tea is doted on for what implied meaning " 301, on
State backstage word server and association search information 303 is drawn according to " tea is doted on for what implied meaning " 301 analysis, user is in response afterwards
" it is exquisite that tea is doted on, and tea dotes on picture appreciation " 302 is clicked in the Search Results of search " tea is doted on for what implied meaning " 301, above-mentioned
Backstage word server can show that neologisms are " tea is doted on " by analysis.
The method that above-described embodiment of the application provides is passed through to analyze the search behavior of user with the behavior of click so that excavating
The word going out is more accurate, and improves the efficiency of word excavation and the ageing of word excavation.
With further reference to Fig. 4, it illustrates the flow process of another embodiment of information demonstrating method based on artificial intelligence
400.It is somebody's turn to do the flow process 400 of the information demonstrating method based on artificial intelligence, comprise the following steps：
Step 401, obtains the search information of user and click information set in preset time period.
In the present embodiment, the information demonstrating method based on artificial intelligence runs electronic equipment (such as Fig. 1 institute thereon
The server showing) terminal of information search can be carried out from user using it by wired connection mode or radio connection
Obtain the click information set of user the search information of (for example, one day) and user within the default time period, wherein, above-mentioned point
Hitting information aggregate can be the information clicked in the Search Results presenting after searching for above-mentioned search information as above-mentioned user
Set, for example, after above-mentioned user search " tea is doted on for what implied meaning ", the retrieval result that presents has " being particular about of doting on of tea, tea
Dote on picture appreciation ", " on Tea Service, putting that what tea is doted on " etc., user clicks in Search Results that " being particular about of doting on of tea, tea dotes on picture reward
After analysis ", the click information in above-mentioned click information set can be " it is exquisite that tea is doted on, and tea dotes on picture appreciation ".
Step 402, searches the relevant search information related to search information.
In the present embodiment, above-mentioned electronic equipment can search the correlation related to the search information obtaining in step 401
Search information, wherein, above-mentioned relevant search information can be the search information with above-mentioned search information with same clip, example
As when above-mentioned search information is " effect of coldrex ", then relevant search information can be " side effect of coldrex ", " flu
Action principle of medicine " etc.；Above-mentioned relevant search information can also be and above-mentioned search information synon search information each other, example
As when above-mentioned search information is " week rears people ", then relevant search information can be " Lu xun ".
Step 403, obtains clicked phase in the Search Results presenting in response to searching for described relevant search information
Close click information, and generate related click information aggregate.
In the present embodiment, above-mentioned electronic equipment can obtain in the search knot searched for above-mentioned relevant search information and present
The information that in fruit, user clicks on, using above- mentioned information as related click information, and generates related click information aggregate, for example, when
During user's search " action principle of coldrex ", the Search Results presenting have " what principle that coldrex is cured the disease is ", " coldrex
Species and pharmacological action ", " teaching you to understand the taboo in coldrex name " etc., user clicks " species of coldrex and medicine
Reason acts on " and " what the principle that coldrex is cured the disease is ", then " species of coldrex and pharmacological action " and " it is former that coldrex is cured the disease
What reason is " may reside in related click in information aggregate.
Step 404, determines that the related related click information clicked in information aggregate is believed with the click in click information set
Breath has the quantity of identical information, and confirms whether quantity is more than default amount threshold.
In the present embodiment, above-mentioned electronic equipment can determine in the related click information aggregate generating in step 403
Click information in the click information set obtaining in related click information and step 401 has the quantity of identical information, and really
Recognize whether above-mentioned quantity is more than default amount threshold, for example, when the above-mentioned related related click information clicked in information aggregate
For " species of coldrex and pharmacological action ", " what principle that coldrex is cured the disease is ", " effect of several conventional coldrexs with become
Point " and " side effect minimum coldrex ", the click information in above-mentioned click information set is " dissect coldrex and treat principle ",
" species of coldrex and pharmacological action ", " effect of several conventional coldrexs and composition " and " the minimum coldrex of side effect ",
Then can determine that the quantity with identical information is 3, when above-mentioned amount threshold is 2, then can confirm that out that above-mentioned quantity is big
In default amount threshold.
Step 405, if confirming, quantity is more than default amount threshold, and relevant search information is believed as association search
Breath.
In the present embodiment, it is more than default amount threshold, above-mentioned electricity when confirming the above-mentioned quantity with identical information
Sub- equipment can be using above-mentioned relevant search information as association search information.
In the present embodiment, above-mentioned user can be clicked on by above-mentioned electronic equipment in the region assuming association search information
Relevant search information as association search information it is also possible to above-mentioned user is carried out in the region assuming association search information its
The relevant search information that it operates is as association search information.
Step 406, contrast search information and association search information, have in extraction search information and association search information
Text fragments.
In the present embodiment, above-mentioned electronic equipment can pass through to contrast above-mentioned search information and above-mentioned association search information,
Extract above-mentioned search information and total text fragments in above-mentioned association search information.For example, when search information is " which flu
Drug effect fruit is good ", above-mentioned association search information is " which coldrex Small side effects ", then the total text fragments extracting can be
" which ", " flu ", " medicine " and " coldrex ".
Step 407, confirms that text fragments whether there is in click information set.
In the present embodiment, above-mentioned electronic equipment can confirm that the text fragments extracting in step 406 whether there is in upper
State in click information set, for example, the text fragments of said extracted are " tea ointment " and " what ", in above-mentioned click information set
Click information is " how tea ointment is drunk " and " benefit of cream of having tea ", and above-mentioned electronic equipment can be first by above-mentioned click information
How about " how tea ointment is drunk " and " benefit of cream of having tea " is divided into " tea ointment ", " ", " drinking ", " benefit ", then, judges " tea
How about cream " and " what " are with the presence or absence of in " tea ointment ", " ", " drinking ", " benefit ".
Step 408, in response to confirming that text fragments are present in click information set, then further determines that text fragments
Whether meet default condition.
In the present embodiment, confirm that above-mentioned text fragments are present in above-mentioned click information set, above-mentioned electronic equipment
Can determine whether above-mentioned text fragments meet default condition, wherein, above-mentioned default condition can be according to history text
That the rule that fragment is excavated is configured or being configured according to user-defined condition.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can obtain above-mentioned text fragments first
The number of times being retrieved as search information；Afterwards it may be determined that whether above-mentioned number of times is more than default retrieval frequency threshold value, if
It is then to can determine that above-mentioned text fragments meet default condition.For example, when above-mentioned default retrieval frequency threshold value is 200,
Getting " tea ointment " as the number of times that search information is retrieved is 378 times, and the number of times that " what " is retrieved as search information is
53 times, then can determine that " tea ointment " meets default condition, and " what " does not meet default condition.
Step 409 meets default condition however, it is determined that going out text fragments, then store text fragments, and assume text fragments.
In the present embodiment, meet default condition in response to determining above-mentioned text fragments, above-mentioned electronic equipment is permissible
Store above-mentioned text fragments, and assume above-mentioned text fragments.Above-mentioned electronic equipment can assume what excavation was arrived in the form of word cloud
Text fragments, wherein, visual prominent, shape that above-mentioned word cloud is that higher to the frequency of occurrences in network text " key word " gives
Become " key word cloud layer " or " key word renders ", thus filtering out substantial amounts of text message, as long as making to browse webpage, person sweeps at a glance
Cross the purport that text just can have a taste of text；Above-mentioned electronic equipment can also provide the query interface of above-mentioned text fragments, convenient
The text fragments that user excavated in the query history time period；Above-mentioned electronic equipment can also be in natural language processing field
The morphological analysis systems such as civilian Words partition system, name Entity recognition provide basic resource to assist the performance improving these systems.
Figure 4, it is seen that the information based on artificial intelligence compared with embodiment corresponding with Fig. 2, in the present embodiment
The flow process 400 of rendering method highlights the step generating association search information according to search information.Thus, the present embodiment describes
Scheme can generate more accurately association search information, so that the word excavated is more accurate.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides a kind of be based on artificial intelligence
One embodiment of the information presentation device of energy, this device embodiment is corresponding with the embodiment of the method shown in Fig. 2, and this device has
Body can apply in various electronic equipments.
As shown in figure 5, being included based on the information presentation device 500 of artificial intelligence described in the present embodiment：Acquiring unit
501st, signal generating unit 502, extraction unit 503, confirmation unit 504, determining unit 505 and display unit 506.Wherein, obtain list
Unit 501 is configured to obtain the search information of user and click information set in preset time period, wherein, described click information collection
Close and include clicked information in the Search Results presenting in response to searching for described search information；Signal generating unit 502 configures
For according to described search information, generating association search information；Extraction unit 503 is configured to contrast described search information and institute
State association search information, extract described search information and total text fragments in described association search information；Confirmation unit 504
It is configured to confirm that described text fragments whether there is in described click information set；Determining unit 505 is configured to respond
In confirming that described text fragments are present in described click information set, then further determine that whether described text fragments meet
Default condition；And if display unit 506 is configured to described text fragments and meets default condition, store described text piece
Section, and assume described text fragments.
In the present embodiment, the acquiring unit 501 of the information presentation device 500 based on artificial intelligence can pass through wired company
Connect mode or radio connection and carry out the terminal acquisition user of information search from user within the default time period using it
Search information and user click information set, wherein, above-mentioned click information set can be when above-mentioned user search on
After stating search information in the Search Results presenting click on information set, for example, when above-mentioned user search " tea dote on have assorted
After implied meaning ", the retrieval result presenting has " it is exquisite that tea is doted on, and tea dotes on picture appreciation ", " putting on Tea Service that what tea is doted on " etc.,
Click letter after user clicks on " it is exquisite that tea is doted on, and tea dotes on picture appreciation " in Search Results, in above-mentioned click information set
Breath can be " it is exquisite that tea is doted on, and tea dotes on picture appreciation ".
In the present embodiment, get the search information of user based on above-mentioned acquiring unit 501 after, above-mentioned signal generating unit
502 can generate association search information according to above-mentioned search information.Above-mentioned search information can be drawn by above-mentioned signal generating unit 502
It is divided at least one search word, then search word is substituted for synonym or the near synonym of search word, by the search after replacing it
Information is as association search information；Above-mentioned signal generating unit 502 can also obtain the point in search information and click information set
Hit frequency of occurrences highest search word in information, obtain afterwards and comprise above-mentioned search in preset time period in predetermined application
The search information of word, then selects the search information that searched number of times highest comprises above-mentioned search word in search information, will
Above-mentioned search information is as association search information.Above-mentioned association search information can be user in the area assuming association search information
Association search information that domain is clicked on or the associations of other operations that user is carried out in the region assuming association search information
Search information.
In the present embodiment, said extracted unit 503 can be by contrasting above-mentioned search information and above-mentioned association search letter
Breath, extracts above-mentioned search information and total text fragments in above-mentioned association search information, wherein, above-mentioned text fragments can be
Word, short sentence etc..For example, when search information is " which coldrex effect is good ", above-mentioned association search information is " which flu
Medicine Small side effects ", then the total text fragments extracting can be " which ", " flu ", " medicine " and " coldrex ".In this enforcement
In example, above-mentioned confirmation unit 504 can confirm that the text fragments extracting in said extracted unit 503 whether there is in above-mentioned click
In information aggregate, for example, the text fragments of said extracted are " tea ointment " and " what ", the click letter in above-mentioned click information set
Cease for " how tea ointment is drunk " and " benefit of cream of having tea ", above-mentioned confirmation unit 504 can be first by above-mentioned click information " tea ointment
How to drink " and " benefit of cream of having tea " how be divided into " tea ointment ", " ", " drinking ", " benefit ", then, judge " tea ointment " and
How about " what " is with the presence or absence of in " tea ointment ", " ", " drinking ", " benefit ".
In the present embodiment, when above-mentioned confirmation unit 504 confirms that above-mentioned text fragments are present in above-mentioned click information collection
In conjunction, above-mentioned determining unit 505 can determine whether above-mentioned text fragments meet default condition, wherein, above-mentioned default bar
Part is configured according to the rule that history text fragment is excavated or is carried out according to user-defined condition
Setting.
In the present embodiment, meet default condition in response to determining above-mentioned text fragments, above-mentioned display unit 506 can
To store above-mentioned text fragments, and assume above-mentioned text fragments.Above-mentioned display unit 506 can assume excavation in the form of word cloud
The text fragments arriving, wherein, above-mentioned word cloud is that higher to the frequency of occurrences in network text " key word " gives visual dashing forward
Go out, formed " key word cloud layer " or " key word renders ", thus filtering out substantial amounts of text message, as long as making to browse webpage person one
Eye is inswept, and text just can have a taste of the purport of text；Above-mentioned display unit 506 can also provide the inquiry of above-mentioned text fragments to connect
Mouthful, facilitate the text fragments excavated in user's query history time period；Above-mentioned display unit 506 can also be at natural language
The morphological analysis systems such as the Chinese automatic word-cut in reason field, name Entity recognition provide basic resource to improve these systems to assist
Performance.
In some optional implementations of the present embodiment, above-mentioned signal generating unit 502 can include searching modul 5021,
Generation module 5022, confirmation module 5023 and processing module 5024.Wherein, above-mentioned searching modul 5021 can be searched and be obtained list
The relevant search information of the search information correlation obtaining in unit 501, wherein, above-mentioned relevant search information can be and above-mentioned search
Information has the search information of same clip；Above-mentioned relevant search information can also be synon each other with above-mentioned search information
Search information.Above-mentioned generation module 5022 can obtain user in the Search Results searched for above-mentioned relevant search information and present
The information clicked on, using above- mentioned information as related click information, and generates related click information aggregate.Above-mentioned confirmation module 5023
Can determine the related related click information clicked in information aggregate and above-mentioned acquisition list generating in above-mentioned generation module 5022
Click information in the click information set obtaining in unit 501 has the quantity of identical information, and confirms whether above-mentioned quantity is big
In default amount threshold.When confirming that the above-mentioned quantity with identical information is more than default amount threshold, above-mentioned process mould
Block 5025 can be using above-mentioned relevant search information as association search information.
In some optional implementations of the present embodiment, above-mentioned determining unit 505 can include：First determining module
5051 and second determining module 5052.Wherein, above-mentioned first determining module 5051 can count the word of above-mentioned text fragments first
Number；Afterwards, above-mentioned first determining module 5051 can determine whether above-mentioned number of words is less than default number of words threshold value, if so, then goes up
State the second determining module 5052 and can determine that above-mentioned text fragments meet default condition.
In some optional implementations of the present embodiment, above-mentioned determining unit 505 can include：3rd determining module
5053 and the 4th determining module 5054.Wherein, above-mentioned 3rd determining module 5053 can obtain above-mentioned text fragments conduct first
The number of times that search information is retrieved；Afterwards it may be determined that whether above-mentioned number of times is more than default retrieval frequency threshold value, if so, then
Above-mentioned 4th determining module 5054 can determine that above-mentioned text fragments meet default condition.
In some optional implementations of the present embodiment, above-mentioned display unit 506 can include：Acquisition module
5061st, determining module 5062 and assume module 5063.Wherein, above-mentioned acquisition module 5061 can obtain above-mentioned text fragments first
The usage frequency in default application within the default time period；Then, above-mentioned determining module 5062 can determine above-mentioned literary composition
Whether the usage frequency of this fragment is more than default usage frequency threshold value, if so, then the above-mentioned module 5063 that presents to above-mentioned text
Fragment is processed, and assumes the text fragments after process, wherein, carries out process to above-mentioned text fragments and can include to above-mentioned
The font of text fragments is processed to be processed it is also possible to above-mentioned text fragments are amplified with multiple, can also be to above-mentioned text
The color of fragment is processed.
In some optional implementations of the present embodiment, said extracted unit 503 can include：First division module
5031st, the second division module 5032, detection module 5033 and extraction module 5034.Wherein, above-mentioned first division module 5031 can
First above-mentioned search information to be divided at least one search snippet, and generates search snippet set；Afterwards, above-mentioned second stroke
Above-mentioned association search information can be divided at least one association search fragment by sub-module 5032, and generates association search fragment
Set；Then, above-mentioned detection module 5033 can detect in the search snippet in above-mentioned search snippet set whether there is with upper
State the association search fragment identical text fragments in association search set of segments, if detecting in above-mentioned search snippet set
Search snippet exists and the association search fragment identical text fragments in above-mentioned association search set of segments, then said extracted mould
Block 5034 can extract above-mentioned identical text fragments.
Below with reference to Fig. 6, it illustrates the computer system 600 being suitable to the server for realizing the embodiment of the present invention
Structural representation.
As shown in fig. 6, computer system 600 includes CPU (CPU) 601, it can be read-only according to being stored in
Program in memorizer (ROM) 602 or be loaded into program random access storage device (RAM) 603 from storage part 608 and
Execute various suitable actions and process.In RAM603, the system that is also stored with 600 operates required various program datas.
CPU601, ROM602 and RAM603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to bus
604.
Connected to I/O interface 605 with lower component：Importation 606 including keyboard, mouse etc.；Penetrate including such as negative electrode
Spool (CRT), liquid crystal display (LCD) etc. and the output par, c 607 of speaker etc.；Storage part 608 including hard disk etc.；
And include the communications portion 609 of the NIC of LAN card, modem etc..Communications portion 609 via such as because
The network execution communication process of special net.Driver 610 connects to I/O interface 605 also according to needs.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc., are arranged in driver 610, as needed in order to read from it
Computer program as needed be mounted into storage part 608.
Especially, in accordance with an embodiment of the present disclosure, the process above with reference to flow chart description may be implemented as computer
Software program.For example, embodiment of the disclosure includes a kind of computer program, and it includes being tangibly embodied in machine readable
Computer program on medium, above computer program bag contains the program code for the method shown in execution flow chart.At this
In the embodiment of sample, this computer program can be downloaded and installed from network by communications portion 609, and/or from removable
Unload medium 611 to be mounted.
Flow chart in accompanying drawing and block diagram are it is illustrated that according to the system of various embodiments of the invention, method and computer journey
The architectural framework in the cards of sequence product, function and operation.At this point, each square frame in flow chart or block diagram can generation
A part for one module of table, program segment or code, the part of above-mentioned module, program segment or code comprises one or more
For realizing the executable instruction of the logic function of regulation.It should also be noted that in some realizations as replacement, institute in square frame
The function of mark can also be to occur different from the order being marked in accompanying drawing.For example, the square frame that two succeedingly represent is actual
On can execute substantially in parallel, they can also execute sometimes in the opposite order, and this is depending on involved function.Also to
It is noted that the combination of each square frame in block diagram and/or flow chart and the square frame in block diagram and/or flow chart, Ke Yiyong
Execute the function of regulation or the special hardware based system of operation to realize, or can be referred to computer with specialized hardware
The combination of order is realizing.
It is described in involved unit in the embodiment of the present invention to realize by way of software it is also possible to pass through hard
The mode of part is realizing.Described unit can also be arranged within a processor, for example, it is possible to be described as：A kind of processor bag
Include acquiring unit, signal generating unit, extraction unit, confirmation unit, determining unit and display unit.Wherein, the title of these units
Do not constitute under certain conditions to the restriction of of this unit itself.For example, acquiring unit is also described as " obtaining user's
Search information and the unit of click information set ".
As another aspect, present invention also offers a kind of nonvolatile computer storage media, this non-volatile calculating
Machine storage medium can be the nonvolatile computer storage media included in said apparatus in above-described embodiment；Can also be
Individualism, without the nonvolatile computer storage media allocated in terminal.Above-mentioned nonvolatile computer storage media is deposited
Contain one or more program, when said one or multiple program are executed by an equipment so that the said equipment：Obtain
The search information of user and click information set in preset time period, wherein, described click information set is included in response to searching
Clicked information in the Search Results that Suo Suoshu searches for information and presents；According to described search information, generate association search letter
Breath；Contrast described search information and described association search information, extract described search information common with described association search information
Some text fragments；Confirm that described text fragments whether there is in described click information set；In response to confirming described literary composition
This fragment is present in described click information set, then further determine that whether described text fragments meet default condition；If
It is then to store described text fragments, and assume described text fragments.
Above description is only presently preferred embodiments of the present invention and the explanation to institute's application technology principle.People in the art
Member is it should be appreciated that involved invention scope is however it is not limited to the technology of the particular combination of above-mentioned technical characteristic in the present invention
Scheme, also should cover simultaneously in the case of without departing from described inventive concept, be carried out by above-mentioned technical characteristic or its equivalent feature
Combination in any and other technical schemes of being formed.Such as features described above has similar work(with the (but not limited to) disclosed in the present invention
The technical scheme that the technical characteristic of energy is replaced mutually and formed.
Claims (12)
1. a kind of information demonstrating method based on artificial intelligence is it is characterised in that methods described includes：
Obtain the search information of user and click information set in preset time period, wherein, described click information set includes
Clicked information in the Search Results presenting in response to searching for described search information；
According to described search information, generate association search information；
Contrast described search information and described association search information, extract described search information common with described association search information
Some text fragments；
Confirm that described text fragments whether there is in described click information set；
In response to confirming that described text fragments are present in described click information set, then further determine that described text fragments
Whether meet default condition；
If so, then store described text fragments, and assume described text fragments.
2. method according to claim 1 it is characterised in that described according to described search information, generate association search letter
Breath, including：
Search the relevant search information related to described search information, wherein, described relevant search information includes following at least one
?：With described search information have same clip search information and with described search information synon search information each other；
Obtain clicked related click information in the Search Results presenting in response to searching for described relevant search information, and
Generate related click information aggregate；
Determine that the described related related click information clicked in information aggregate and the click information in described click information set have
There is the quantity of identical information, and confirm whether described quantity is more than default amount threshold；
If so, then using described relevant search information as association search information.
3. method according to claim 1 is it is characterised in that whether the described text fragments of described determination meet default bar
Part, including：
Determine whether the number of words of described text fragments is less than default number of words threshold value；
In response to determine described text fragments number of words be less than default number of words threshold value it is determined that described text fragments meet pre-
If condition.
4. method according to claim 1 is it is characterised in that whether the described text fragments of described determination meet default bar
Part, including：
Determine whether described text fragments are more than default retrieval frequency threshold value as the number of times that search information is retrieved；
In response to determining that the number of times that described text fragments are retrieved as search information is more than default retrieval frequency threshold value, then
Determine that described text fragments meet default condition.
5. the method according to one of claim 1-4 is it is characterised in that described assume described text fragments, including：
Obtain preset time period in default application in using described text fragments frequency；
Determine whether the described frequency using described text fragments is more than default usage frequency threshold value；
If so, then described text fragments are processed, and assume the described text fragments after process, wherein, described to described
Text fragments carry out processing include following at least one：Font processing, amplification is processed, color treatments.
6. method according to claim 1 is it is characterised in that described contrast described search information is believed with described association search
Breath, extracts described search information and total text fragments in described association search information, including：
Described search information is divided at least one search snippet, to generate search snippet set；
Described association search information is divided at least one association search fragment, to generate association search set of segments；
Detect that the search snippet in described search snippet set whether there is to search with associating in described association search set of segments
Rope fragment identical text fragments；
If so, described identical text fragments are then extracted.
7. a kind of information presentation device based on artificial intelligence is it is characterised in that described device includes：
Acquiring unit, is configured to obtain the search information of user and click information set in preset time period, wherein, described point
Hit information aggregate and include clicked information in the Search Results presenting in response to searching for described search information；
Signal generating unit, is configured to, according to described search information, generate association search information；
Extraction unit, is configured to contrast described search information and described association search information, extracts described search information and institute
State total text fragments in association search information；
Confirmation unit, is configured to confirm that described text fragments whether there is in described click information set；
Determining unit, is configured in response to confirming that described text fragments are present in described click information set, then enter one
Step determines whether described text fragments meet default condition；
Display unit, if being configured to described text fragments to meet default condition, stores described text fragments, and assumes institute
State text fragments.
8. device according to claim 7 is it is characterised in that described signal generating unit includes：
Searching modul, is configured to search the relevant search information related to described search information, wherein, described relevant search letter
Cease at least one below including：With described search information have same clip search information and with described search information each other with
The search information of adopted word；
Generation module, is configured to acquisition clicked in the Search Results presenting in response to searching for described relevant search information
Related click information, and generate and related click on information aggregate；
Confirm module, be configured to determine the described related related click information clicked in information aggregate and described click information collection
Click information in conjunction has the quantity of identical information, and confirms whether described quantity is more than default amount threshold；
Processing module, if be configured to confirm that described quantity is more than default amount threshold, by described relevant search information
As association search information.
9. device according to claim 7 is it is characterised in that described determining unit includes：
First determining module, is configured to determine whether the number of words of described text fragments is less than default number of words threshold value；
Second determining module, is configured to be less than default number of words threshold value in response to the number of words determining described text fragments, then
Determine that described text fragments meet default condition.
10. device according to claim 7 is it is characterised in that described determining unit includes：
3rd determining module, is configured to determine described text fragments are preset as whether the number of times that search information is retrieved is more than
Retrieval frequency threshold value；
4th determining module, is configured in response to determining that the number of times that described text fragments are retrieved as search information is more than
Default retrieval frequency threshold value is it is determined that described text fragments meet default condition.
11. devices according to one of claim 7-10 are it is characterised in that described display unit includes：
Acquisition module, be configured to obtain preset time period in default application in using described text fragments frequency；
Determining module, is configured to determine whether the described frequency using described text fragments is more than default usage frequency threshold
Value；
Assume module, be configured to if it is determined that the described frequency using described text fragments is more than default usage frequency threshold
Value, then described text fragments are processed, and assume the described text fragments after process, wherein, described to described text piece
Duan Jinhang process include following at least one：Font processing, amplification is processed, color treatments.
12. devices according to claim 7 are it is characterised in that described extraction unit includes：
First division module, is configured to described search information is divided at least one search snippet, to generate search snippet
Set；
Second division module, is configured to for described association search information to be divided at least one association search fragment, to generate
Association search set of segments；
Detection module, is configured to detect that the search snippet in described search snippet set whether there is and described association search piece
Association search fragment identical text fragments in Duan Jihe；
Extraction module, if be configured to detect that the search snippet in described search snippet set exists and described association search piece
Association search fragment identical text fragments in Duan Jihe, then extract described identical text fragments.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610805851.2A CN106469214B (en) | 2016-09-06 | 2016-09-06 | Information demonstrating method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610805851.2A CN106469214B (en) | 2016-09-06 | 2016-09-06 | Information demonstrating method and device based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106469214A true CN106469214A (en) | 2017-03-01 |
| CN106469214B CN106469214B (en) | 2019-10-15 |
Family
ID=58230450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610805851.2A Active CN106469214B (en) | 2016-09-06 | 2016-09-06 | Information demonstrating method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106469214B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1628298A (en) * | 2002-05-28 | 2005-06-15 | 弗拉迪米尔·叶夫根尼耶维奇·涅博利辛 | Method for synthesising self-learning system for knowledge acquistition for retrieval systems |
| CN103914487A (en) * | 2013-01-08 | 2014-07-09 | 邓寅生 | Document collection, identification and association system |
| CN104102654A (en) * | 2013-04-08 | 2014-10-15 | 阿里巴巴集团控股有限公司 | Vocabulary clustering method and device |
| CN104750873A (en) * | 2015-04-22 | 2015-07-01 | 百度在线网络技术（北京）有限公司 | Popular search term push method and device |
| CN105095229A (en) * | 2014-04-29 | 2015-11-25 | 国际商业机器公司 | Method for training topic model, method for comparing document content and corresponding device |
| US20160196351A1 (en) * | 2015-01-07 | 2016-07-07 | International Business Machines Corporation | Estimating article publication dates and authors based on social media context |
| CN105760521A (en) * | 2016-02-29 | 2016-07-13 | 百度在线网络技术（北京）有限公司 | Information input method and device |
-
2016
- 2016-09-06 CN CN201610805851.2A patent/CN106469214B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1628298A (en) * | 2002-05-28 | 2005-06-15 | 弗拉迪米尔·叶夫根尼耶维奇·涅博利辛 | Method for synthesising self-learning system for knowledge acquistition for retrieval systems |
| CN103914487A (en) * | 2013-01-08 | 2014-07-09 | 邓寅生 | Document collection, identification and association system |
| CN104102654A (en) * | 2013-04-08 | 2014-10-15 | 阿里巴巴集团控股有限公司 | Vocabulary clustering method and device |
| CN105095229A (en) * | 2014-04-29 | 2015-11-25 | 国际商业机器公司 | Method for training topic model, method for comparing document content and corresponding device |
| US20160196351A1 (en) * | 2015-01-07 | 2016-07-07 | International Business Machines Corporation | Estimating article publication dates and authors based on social media context |
| CN104750873A (en) * | 2015-04-22 | 2015-07-01 | 百度在线网络技术（北京）有限公司 | Popular search term push method and device |
| CN105760521A (en) * | 2016-02-29 | 2016-07-13 | 百度在线网络技术（北京）有限公司 | Information input method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106469214B (en) | 2019-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105574092B (en) | Information mining method and device | |
| CN107105031A (en) | Information-pushing method and device | |
| CN109635120A (en) | Construction method, device and the storage medium of knowledge mapping | |
| JP2015532753A (en) | Character input method, system and apparatus | |
| CN107391675A (en) | Method and apparatus for generating structure information | |
| US20150339298A1 (en) | Document management system, document management method, and document management program | |
| CN104243273A (en) | Method and device for displaying information on instant messaging client and information display system | |
| CN107516235A (en) | Commodity preference predictor method and device | |
| US20160078115A1 (en) | Interactive System and Method for Processing On-Screen Items of Textual Interest | |
| CN101751459A (en) | Method and device for processing data in electronic equipment | |
| CN106407377A (en) | Search method and device based on artificial intelligence | |
| CN103970800B (en) | The extraction processing method and system of webpage associative key | |
| CN108021598A (en) | Page extraction template matching process, device and server | |
| CN107729453A (en) | A kind of method and apparatus for extracting hub products word | |
| CN107944032A (en) | Method and apparatus for generating information | |
| CN106294885A (en) | A kind of data collection towards isomery webpage and mask method | |
| WO2020253368A1 (en) | Electronic reading display method, storage method, electronic device, computer device, and medium | |
| CN103020277B (en) | A kind of search terms suggestions method and apparatus | |
| CN106372232B (en) | Information mining method and device based on artificial intelligence | |
| CN107168635A (en) | Information demonstrating method and device | |
| CN114092948A (en) | Bill identification method, device, equipment and storage medium | |
| CN104965894A (en) | Data analysis system for IDC hazardous information monitoring platform | |
| US11074306B2 (en) | Web content extraction method, device, storage medium | |
| CN105279191A (en) | Potential user mining method based on network data analysis | |
| CN108268488A (en) | The recognition methods of webpage master map and device |
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 |