CN110175806A - Item based reminding method, device and computer equipment based on semantic analysis - Google Patents
Item based reminding method, device and computer equipment based on semantic analysis Download PDFInfo
- Publication number
- CN110175806A CN110175806A CN201910302074.3A CN201910302074A CN110175806A CN 110175806 A CN110175806 A CN 110175806A CN 201910302074 A CN201910302074 A CN 201910302074A CN 110175806 A CN110175806 A CN 110175806A
- Authority
- CN
- China
- Prior art keywords
- item
- keyword
- text
- content
- trigger condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The present invention is suitable for field of artificial intelligence, provides a kind of item based reminding method based on semantic analysis, device, storage equipment and computer equipment.Wherein, method includes: the content of text for obtaining terminal device；Item keyword and trigger condition keyword associated with item keyword are extracted from content of text；Reminding triggering conditions are established according to trigger condition keyword, item reminded contents are established according to item keyword, and according to reminding triggering conditions and the corresponding prompting item of item reminded contents creation；When one or more reminding triggering conditions match preset trigger condition, prompting corresponding with item is reminded is executed according to the triggering of scheduled alerting pattern and is operated.The present invention can accurately automatically create prompting according to the text on terminal device, user is no longer needed to go to create manually, and triggering can be gone to remind according to trigger condition, the convenience of prompting is improved, solve the problems, such as cumbersome and low efficiency present in existing item based reminding method.
Description
Technical field
The invention belongs to field of artificial intelligence more particularly to a kind of item based reminding methods based on semantic analysis, dress
It sets, storage medium and computer equipment.
Background technique
Currently, item prompting is very common in daily life, terminal device usually all includes reminding module, and user can incite somebody to action
Material particular records and is arranged and reaches the predetermined time and be automatically reminded to, and to avoid omission, such as important stroke, business meetings, taking medicine is mentioned
It wakes up.
However, above-mentioned existing item based reminding method is often based on what the time was configured, and need user be directed to by
Corresponding prompting function is respectively set in a item, thus cause carry out item prompting function setting when there are it is cumbersome and effect
The low problem of rate.
Summary of the invention
The embodiment of the invention provides a kind of item based reminding method, device, storage medium and terminal based on semantic analysis
Equipment, to solve the problems, such as cumbersome and low efficiency present in existing item based reminding method.
The first aspect of the embodiment of the present invention provides a kind of item based reminding method based on semantic analysis, comprising:
Obtain the content of text of terminal device；
Item keyword is extracted from the content of text, and trigger condition associated with the item keyword is closed
Key word；
Reminding triggering conditions are established according to the trigger condition keyword, item is established according to the item keyword and is reminded
Content, and according to the reminding triggering conditions and the corresponding prompting item of item reminded contents creation；
In one or more reminding triggering conditions matching preset trigger conditions, triggered according to scheduled alerting pattern
Execute prompting operation corresponding with the prompting item.
The second aspect of the embodiment of the present invention provides a kind of item alarm set based on semantic analysis, comprising:
Module is obtained, for obtaining the content of text of terminal device；
Extraction module is used to extract item keyword from the content of text, and related to the item keyword
The trigger condition keyword of connection；
Module is established, it is crucial according to the item for establishing reminding triggering conditions according to the trigger condition keyword
Word establishes item reminded contents, and according to the reminding triggering conditions and the corresponding prompting thing of item reminded contents creation
?；
Reminding module is used in one or more reminding triggering conditions matching preset trigger conditions, according to predetermined
Alerting pattern triggering execute corresponding with prompting item prompting and operate.
The third aspect of the embodiment of the present invention provides a kind of computer equipment, comprising: memory, processor and storage
In the memory and the computer program that can run on the processor, the processor execute the computer program
When perform the steps of
Obtain the content of text of terminal device；
Item keyword is extracted from the content of text, and trigger condition associated with the item keyword is closed
Key word；
Reminding triggering conditions are established according to the trigger condition keyword, item is established according to the item keyword and is reminded
Content, and according to the reminding triggering conditions and the corresponding prompting item of item reminded contents creation；
In one or more reminding triggering conditions matching preset trigger conditions, triggered according to scheduled alerting pattern
Execute prompting operation corresponding with the prompting item.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the computer program performs the steps of when being executed by processor
Obtain the content of text of terminal device；
Item keyword is extracted from the content of text, and trigger condition associated with the item keyword is closed
Key word；
Reminding triggering conditions are established according to the trigger condition keyword, item is established according to the item keyword and is reminded
Content, and according to the reminding triggering conditions and the corresponding prompting item of item reminded contents creation；
In one or more reminding triggering conditions matching preset trigger conditions, triggered according to scheduled alerting pattern
Execute prompting operation corresponding with the prompting item.
In the embodiment of the present invention, by obtaining the content of text of terminal device, item is extracted from the content of text and is closed
Key word, and trigger condition keyword associated with the item keyword；It is mentioned according to trigger condition keyword foundation
Awake trigger condition, establishes item reminded contents according to the item keyword, and according to the reminding triggering conditions and the thing
Item reminded contents creation is corresponding to remind item；In one or more reminding triggering conditions matching preset trigger conditions,
Prompting operation corresponding with the prompting item is executed according to the triggering of scheduled alerting pattern, so as to intelligently according to terminal
Text in equipment accurately automatically creates prompting, it is no longer necessary to which user goes to create manually, and can be gone according to trigger condition
Triggering is reminded, and improves the convenience of prompting, solves cumbersome and low efficiency present in existing item based reminding method
The problem of, there is stronger usability and practicality.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is an application environment schematic diagram of the item based reminding method in the embodiment of the present invention based on semantic analysis；
Fig. 2 is the implementation process schematic diagram for the item based reminding method based on semantic analysis that the embodiment of the present invention one provides；
Fig. 3 is the schematic diagram of the item alarm set provided by Embodiment 2 of the present invention based on semantic analysis；
Fig. 4 is the signal of extraction module in the item alarm set provided by Embodiment 2 of the present invention based on semantic analysis
Figure；
Fig. 5 is that the second extraction unit shows in the item alarm set provided by Embodiment 2 of the present invention based on semantic analysis
It is intended to；
Fig. 6 is the schematic diagram for the computer equipment that the embodiment of the present invention three provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
Item based reminding method provided in an embodiment of the present invention based on semantic analysis can be applicable to the application environment such as Fig. 1
In, wherein client is communicated by network with server.Wherein, client can be, but not limited to various personal computers,
Laptop, smart phone, tablet computer and portable wearable device.Server can be with independent server either
The server cluster of multiple servers composition is realized.
In order to illustrate the item based reminding method provided by the embodiment of the present invention based on semantic analysis, below by specific reality
Example is applied to be illustrated.
Embodiment one:
Fig. 2 shows the implementation process signals for the item based reminding method based on semantic analysis that the embodiment of the present invention one provides
Figure.As shown in Fig. 2, being somebody's turn to do the item based reminding method based on semantic analysis specifically comprises the following steps 101 to step 104, it is described in detail such as
Under:
Step 101: obtaining the content of text of terminal device.
The embodiment of the present invention, which can be used for creating in terminal device, reminds, and terminal device here, which can refer to have, to be reminded
All electronic equipments of function both may include the mobile device of such as mobile phone, tablet computer etc, also may include such as
The fixed equipment of computer etc, the embodiment of the present invention are without restriction to specific terminal device.
Wherein, the item that content of text can be that user oneself creates on the terminal device is reminded, the text in terminal device
This content further includes referring to the word content newly increased in the equipment, at least may include one of following content or a variety of:
Short message, Email .txt file content .doc. file content .docx file content and .wps file content.
Step 102: item keyword, and touching associated with the item keyword are extracted from the content of text
Send out condition keyword.
In the concrete realization, it can obtained to the access authority of the above-mentioned content of text of operating system application of terminal device
After obtaining access authority, so that it may obtain corresponding content of text, and be retrieved accordingly.To have android operating system
Mobile phone for, if application obtains the access authority of short message, will receive operation when receiving new short message
The notice of system can intercept and retrieve at this time the content of new short message.For another example, obtain computer in notepad access
It, can be with the .txt content of text in notepad in scanning computer after permission.Due to .doc. file content .docx file content
Similar with the retrieving of short message and .txt content of text with the retrieving of .wps file content, therefore not to repeat here.
In the embodiment of the present invention, item keyword can be used for indicating being able to reflect the text for needing the item completed,
When creation is reminded, for establishing the item content of daily prompting；Trigger condition keyword is associated with the item keyword, can
For indicating that the item carries out under what conditions, create remind when, for establishing the trigger condition of daily prompting,
In general, the trigger condition keyword can specifically include the time-critical word with time attribute and/or have geographical location
The geographical keyword of attribute.
In one preferred embodiment of the invention, item keyword is extracted described in step 101 from content of text, and
It the step of trigger condition keyword associated with the item keyword, can specifically include:
Step 201: item keyword and trigger condition keyword are extracted from the content of text.
Step 202: the context of the item keyword and trigger condition keyword in the content of text is carried out
Semantic analysis.
Step 203: according to semantic analysis result, determination is associated with the item keyword from the content of text
Trigger condition keyword.
It, specifically can be by carrying out word cutting processing to the content of text, then from each point for step 201 and step 202
Item keyword is extracted in word.Word cutting processing, refers to a statement text being cut into individual word one by one namely each
Participle can carry out cutting to content of text according to universal electric dictionary, guaranteeing the word separated all is just in the present embodiment
Normal vocabulary separates individual character if word is not in electronic dictionary.For example, tomorrow/the morning/nine point/meeting." meeting " is then item
Keyword, " tomorrow ", " morning " and " 9 points " are trigger condition keyword.Then " tomorrow/morning/nine point/meeting " are carried out
Semantic analysis.The mode of semantic analysis includes:
For a given sentence, the corresponding semantic role ingredient of predicate in sentence, including core semantic role are found out
(such as actor, word denoting the receiver of an action person) and attached semantic role (such as place, time, mode, reason).For example, being based on syntactic analysis
As a result, obtaining its syntactic analysis first as a result, being then based on the syntactic analysis as a result, realizing again for some given sentence
Semantic analysis.
Such as sentence are as follows: 9 points of tomorrow morning has a meeting in Beijing.
Semantic formula: event (time (place (" Beijing ")))
According to above-mentioned semantic formula, sentence is changed to: 9 points of tomorrow morning of having a meeting is in Beijing.Semantic analysis usually requires
The support of knowledge base has pre-defined between the core semantic role and attached semantic role of sentence in the knowledge base
Relationship.
Step 203 can specifically include:
Step 301: carrying out matching inquiry, in time-critical character library with the time for obtaining with including in the content of text
Keyword；The time-critical character library is to establish to obtain according to temporal expressions corpus.
In practical applications, text can be expressed with acquisition time, is added to temporal expressions corpus, and according to temporal expressions
Corpus establishes the time-critical character library.For example, common temporal expressions text may include (November 11 in 2018 on date
Day, November 11 etc.), moment (11 points 11 minutes etc.), the texts such as text (tomorrow, early first-class) for expressing date or moment.
It is appreciated that specifically establishing mode and do not limit to specific temporal expressions text and time key word library of the embodiment of the present invention
System.
Step 302: carrying out matching inquiry in geographical key word library, matched with obtaining with words in the content of text
Geographical keyword；The geography key word library is to express corpus according to geographical location to establish to obtain.
In practical applications, common geographical location expression text can be collected, geographical location expression corpus is added to,
And the geographical key word library is established according to geographical location expression corpus.For example, common geographical location expression text can be with
It include: for expressing the text in geographical location (such as safety mansion), for expressing the item (hair that can be mapped to geographical location
The raw item in specific geographical location) text (pharmacy can be mapped to by such as buying medicine item, oiling item can be mapped to plus
Petrol station, item of playing ball can be mapped to arena, and shopping item can be mapped to supermarket or market etc.) etc. texts.It is appreciated that this
Inventive embodiments to specific geographical location expression text time key word library specifically to establish mode without restriction.
It should be noted that may only obtain time-critical word after executing step 201,202 and step 203, it is also possible to
Only obtain geographical keyword, it is also possible to while obtaining time-critical word and geographical keyword.
Step 303: using with item relevance the time-critical word and/or geographical keyword be used as there is item pass
The trigger condition keyword of connection property.
It reminds and completes something, the time that step 301 obtains in certain time and/or certain geographical location commonly used in prompt user
Keyword can refer to all texts with time attribute, and still, the text with time attribute might not have item
Relevance, the time-critical word without item relevance are worth without prompting.For example, the spy expressed according to language
Property, for express the text that certain time completes something not will use usually accurate date or moment (such as on August 8th, 2018,
8 points 30 seconds etc. 15 minutes) go to express, in this way, not having prompting usually using the time-critical word that accurate date or moment express
Value, it should abandon.
Similarly, the geographical keyword that step 302 obtains can refer to all texts with geographical location attribute, still,
Text with geographical location attribute might not have item relevance, and the geographical keyword without item relevance is
Without prompting value.For example, according to the characteristic that language is expressed, it is logical for expressing the text for completing something in certain geographical location
The biggish geographical location of Chang Buhui use scope (such as Beijing, Haidian District, Beijing City etc.) is gone to express, in this way, use scope is larger
Geographical location expression geographical keyword do not have usually prompting value, it should abandon.
In one preferred embodiment of the invention, described using the time-critical word with item relevance as touching
The step of sending out condition keyword, can specifically include:
Step 401: obtaining the time accuracy of the time-critical word.
Step 402: if the time accuracy meets preset accuracy condition, it is determined that the time-critical word has
Item relevance.
In the embodiment of the present invention, the time accuracy is used to indicate the accurate journey of time expressed by the time-critical word
Degree, in the concrete realization, can preset the time accuracy of certain grade, such as in a kind of application example of the invention, the time
It may include: rough, accurate level-one, accurate second level, accurate three-level that the grade of accuracy, which has, and corresponding accuracy condition is specific
If including: that the time accuracy is more than or equal to accurate three-level, the time-critical word does not have item relevance, if described
Time accuracy is the accurate rank (i.e. rough, accurate level-one and accurate second level) for being less than three-level, then the time-critical word tool
There is item relevance.Wherein, the corresponding time-critical word of coarse level, which generally comprises, is accurate to day or day, and the date is imperfect
Text, such as tomorrow, tomorrow morning, December 24；Accurate level-one generally includes the text for being accurate to hour, such as tomorrow morning
9 points etc.；The text that accurate second level generally includes to be accurate to point, such as 9 points 15 minutes；Accurate three-level generally includes to be accurate to second or year
Month day complete text, such as 8 points 58 seconds 58 minutes, on October 1st, 2018.It is appreciated that those skilled in the art can root
It is without restriction to this according to actual conditions preset time accuracy and corresponding accuracy condition, the present invention.
In one preferred embodiment of the invention, described using the time-critical word with item relevance as touching
The step of sending out condition keyword, can specifically include: the time-critical word is matched in reminder time key word library
Inquiry；If successful match, it is determined that the time-critical word has item relevance.
Wherein, the reminder time key word library is to establish to obtain according to reminder time corpus, the reminder time language
It include completing the reminder time text of something in certain time for expressing in material library.
Due to completing reminder time text (such as meeting tomorrow morning, 7 points of tomorrow morning of something in certain time for expressing
Get up) characteristic of language expression can be met, and can have item relevance, therefore, built according to reminder time corpus
Reminder time keyword in vertical obtained reminder time key word library has item relevance.
In an embodiment of the present invention, the reminder time key word library can be established as follows:
Step 501: collecting reminder time text, and be added to reminder time corpus；The reminder time text is used for
Expression completes something in certain time.
Step 502: semantic analysis being carried out to reminder time text in the reminder time corpus, and according to semantic analysis
As a result reminder time keyword is extracted from the reminder time text.
Step 503: extracted reminder time keyword is added to reminder time key word library.
By " meeting tomorrow morning ", " 8 points of tomorrow morning gets up " reminder time text for, then extract to remind and obtain
Reminder time keyword is respectively " tomorrow morning ", " 8 points of tomorrow morning ".
It should be noted that reminder time text and temporal expressions text are used equally for expressing certain in the embodiment of the present invention
Time, but one of the main distinction of the two is, and the former completes something in certain time for expressing, and the time of expression also has
Item relevance；And the latter is used to express certain time, the time of expression not necessarily has item relevance.
In addition, the present invention is using the time-critical word with item relevance as the scheme of trigger condition keyword,
Step 501 or step 502 can be individually used, step 501 and step 502 can also be used simultaneously to obtain and more accurate sentence
Disconnected result.
In one preferred embodiment of the invention, described using the geographical keyword with item relevance as tool
There is the step of trigger condition keyword of item relevance, can specifically include:
Step 601: obtaining the position fine granularity of the geographical location keyword.
Step 602: if the position fine granularity meets preset fine granularity condition, it is determined that the geographical location keyword
With item relevance.
In the embodiment of the present invention, the position fine granularity can be used for indicating geographical location expressed by the geographical keyword
Levels of precision.
Those skilled in the art can be set according to actual needs the position fine granularity, for example, for city, institute
Rheme, which sets fine granularity, can specifically include province, city, area, street, community even mansion, commercial circle title etc., and the example of mansion can
To include " 100 mansion Jing Ji ", " Tencent mansion ", " safety mansion " etc.；For rural area, the position fine granularity is specific
It may include province, city, county, small towns, village etc.；The application is without restriction to specific position fine granularity.
In a kind of application example of the invention, the corresponding fine granularity condition in city be can specifically include: if the position
Fine granularity is province, city or area, then the geographical location keyword does not have item relevance, if the position fine granularity is street
Road, community, mansion or commercial circle title, then the geographical location keyword has item relevance.Certainly, the present invention is to specific
Fine granularity condition is without restriction.
In one preferred embodiment of the invention, described using the geographical keyword with item relevance as tool
There is the step of trigger condition keyword of item relevance, can specifically include: the geographical keyword being reminded in geography and is closed
Matching inquiry is carried out in key character library；If successful match, it is determined that the geographical location keyword has item relevance.
Wherein, the geographical prompting key word library is to remind corpus to establish to obtain according to geographical, the geographical reminding language
It include completing the geographical prompting text of something in certain geographical location for expressing in material library.
Due to (having a dinner party in such as octadentate, everything city is strolled for expressing in the geographical prompting text that something is completed in certain geographical location
Street etc.) characteristic of language expression can be met, and can have item relevance, therefore, remind corpus to establish according to geographical
The obtained geographical geographical prompting keyword reminded in key word library has item relevance.
In an embodiment of the present invention, the geographical prompting key word library can be established as follows:
Step 701: collecting geographical prompting text, and be added to geographical prompting corpus；The geographical prompting text is used for
Expression completes something in certain geographical location.
Step 702: reminding text to carry out semantic analysis to geographical in the geographical prompting corpus, and according to semantic analysis
As a result geographical prompting keyword is extracted in text from geographical remind.
Step 703: extracted geographical prompting keyword is added to geographical prompting key word library.
Wherein, by taking the geography of " training of Shenzhen business school, Beijing University ", " shopping of everything city " reminds text as an example, then prompting is extracted
Obtained geographical prompting keyword is respectively " Shenzhen business school, Beijing University ", " everything city ".
It should be noted that geography reminds text and geographical location expression text to be used equally for table in the embodiment of the present invention
One of the main distinction up to certain geographical location, but the two is that the former completes something, expression in certain geographical location for expressing
Geographical location also there is item relevance；And the latter not necessarily has for expressing certain geographical location, the geographical location of expression
There is item relevance.
It is appreciated that when judging whether geographical keyword has item relevance, it can be individually using step 702 or step
Rapid 703, step 702 and step 703 can also be used to obtain more accurate judging result simultaneously.
In another preferred embodiment of the invention, the step 201 can also using reminder time key word library and
Geography reminds one or both of key word library, and the triggering item with item relevance is extracted directly from the content of text
Part keyword, correspondingly, the step 201 can specifically include:
Step 801: carrying out matching inquiry, in reminder time key word library to obtain and words phase in the content of text
The matched time-critical word with item relevance.
Wherein, the reminder time key word library is to establish to obtain according to reminder time corpus, the reminder time language
It include completing the reminder time text of something in certain time for expressing in material library；And/or
Step 802: being reminded in key word library in geography and carry out matching inquiry, to obtain and words phase in the content of text
The matched geographical location keyword with item relevance.
Wherein, the geographical prompting key word library is to remind corpus to establish to obtain according to geographical, the geographical reminding language
It include completing the geographical prompting text of something in certain geographical location for expressing in material library.
It should be noted that step 201 obtained is item keyword and trigger condition keyword, in step 202 and 203
It is then that the determining trigger condition keyword is associated with which item.In practical applications, the trigger condition keyword
Context is for indicating to be connected above and below in content of text with the trigger condition keyword.
In a kind of application example of the invention, the semantic analysis process may include: first with electronic dictionary etc.
Dictionary carries out word segmentation processing to the context of the item keyword, is then carried out according to semantic knowledge-base to word segmentation result semantic
Mark, generates corresponding semantic analysis result.Wherein, semantic knowledge-base can be used that existing and other are with identity function
Database.Assuming that receiving a new short message, corresponding content of text are as follows: " August A on the 25th, which respects, invites 28 morning of your August
Shenzhen Grand Hyatt Hong Kong is arrived before 12:00, participating in A is kind teacher's a return banquet that son holds, and is please participated at that time ", then step 201 mentions
The item keyword obtained is " kind teacher's a return banquet " or " participating in kind teacher's a return banquet " or " participating in a return banquet ", is obtained
Trigger condition keyword can specifically include: " August 25 days ", " August 28 days " " morning 12:00 " and " Shenzhen Grand Hyatt Hong Kong ", step
Rapid 202 can carry out word segmentation processing to the context for the trigger condition keyword that extraction obtains, and carry out to word segmentation result semantic
Mark, generates corresponding semantic analysis result, and final step 203 determines that trigger condition associated with the item keyword is closed
Key word can specifically include: " August morning 12:00 on the 28th " and " Shenzhen Grand Hyatt Hong Kong ".It should be noted that the embodiment of the present invention
To specific semantic analysis and extract the method for item keyword with no restriction.
For step 201, in one preferred embodiment of the invention, item keyword is extracted from the content of text
And the step of, it can specifically include:
Step 901: extracting from the context of the content of text has the words of item attribute as item keyword.
Alternatively, step 902: matching inquiry is carried out in item key word library, it is upper and lower with the content of text to obtain
The item keyword that words matches in text.
Wherein, step 901 can extract tool according to the semantic analysis result of mark from the context of the content of text
There is the words of item attribute；Usually the words with item attribute includes movement word, and such as " getting up " " reading English ", " sees
Book ", " body-building ", " swimming ", " participating in a return banquet " in above-mentioned example etc..
Step 103: reminding triggering conditions being established according to the trigger condition keyword, are established according to the item keyword
Item reminded contents, and according to the reminding triggering conditions and the corresponding prompting item of item reminded contents creation.
In the embodiment of the present invention, above-mentioned reminding triggering conditions be can specifically include: according to time-critical word determine when
Between and/or according to geographical location keyword determine position.
For example, establishing a process example of prompting when including time-critical word in the trigger condition keyword
It can be with are as follows: obtain reminder time according to time-critical word；If time-critical word is " 9 points of tomorrow morning ", then it is small can to shift to an earlier date half
When user is reminded, obtain reminder time " 8:00 tomorrow morning half "；Using the difference of current time and reminder time, establish
Notification mechanisms based on timer；The item content reminded is established according to the item keyword；For example, item keyword " is opened
Meeting " can be directly as the item content of prompting；After timer enabling, using the time clock feature of the terminal device, at the end
Corresponding remind is created in end equipment.
For another example, when including geographical location keyword in the trigger condition keyword, a process of prompting is established
Example can be with are as follows: obtains the location information that the item for needing to remind occurs according to geographical location keyword；Utilize terminal device
GPS (global positioning system, Global Positioning System), Beidou satellite navigation system (BeiDou
Navigation Satellite System, BDS) etc. positioning functions, according to the location information establish the prompting based on positioning
Mechanism；For example, " geographical location keyword " is gas station, then it can use the GPS functional localization of equipment to nearby whether having phase
The place answered.The item content reminded is established according to the item keyword；For example, item keyword " oiling " can directly be made
For the item content of prompting；After positioning function enabling, creation is corresponding in the device is reminded.
Step 104: in one or more reminding triggering conditions matching preset trigger conditions, according to scheduled prompting
Mode, which triggers, executes prompting operation corresponding with the prompting item.
Herein it should be noted that specified alerting pattern is one of all alerting patterns, i.e., user according to remind item from
The alerting pattern selected in all preset alerting pattern lists, reminding triggering conditions corresponding to each alerting pattern may
It is one or more.Above-mentioned preset trigger condition refers to for measuring whether reminding triggering conditions meet execution prompting operation
It is required that the preset condition of institute.The requirement for reminding operation is executed in order to determine whether each reminding triggering conditions meet, then is needed
Determine whether reminding triggering conditions match with preset trigger condition (it is such as threshold value, critical value etc.), if reminding triggering conditions
Preset trigger condition is matched, then executes the prompting operation for reminding item.
Optionally, setting reminding triggering conditions include: according to alerting pattern and the actual needs of item to be reminded to select one
Or multiple reminding triggering conditions, then the reminding triggering conditions of selection are carried out with the setting of preset trigger condition, e.g., user needs
It reminds and oneself dials network telephone under conditions of having net, reminding triggering conditions are as follows: network type, the mobile phone of mobile phone terminal connection
The localization region of terminal, mobile phone terminal system time, then user is respectively set after having selected three reminding triggering conditions
The corresponding preset condition of three reminding triggering conditions, as preset trigger condition is respectively set are as follows: connection network is WIFI wireless network
Network, located sites are in, the time is in 19:30:00.
Optionally, reminding triggering conditions meet connection network be WIFI wireless network, located sites be in, the time 19:
When one or more preset trigger conditions of 30:00, executes and remind operation, e.g., quarter-bell, bright screen, starting application etc..Alerting pattern
It may include executing to remind operation when any reminding triggering conditions meet, executed when all reminding triggering conditions meet and remind operation
Equal various ways.
In the embodiment of the present invention, by obtaining the content of text of terminal device, item is extracted from the content of text and is closed
Key word, and trigger condition keyword associated with the item keyword；It is mentioned according to trigger condition keyword foundation
Awake trigger condition, establishes item reminded contents according to the item keyword, and according to the reminding triggering conditions and the thing
Item reminded contents creation is corresponding to remind item；In one or more reminding triggering conditions matching preset trigger conditions,
Prompting operation corresponding with the prompting item is executed according to the triggering of scheduled alerting pattern, so as to intelligently according to terminal
Text in equipment accurately automatically creates prompting, it is no longer necessary to which user goes to create manually, and can be gone according to trigger condition
Triggering is reminded, and improves the convenience of prompting, solves cumbersome and low efficiency present in existing item based reminding method
The problem of, there is stronger usability and practicality.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment two:
Referring to FIG. 3, it illustrates the provided by Embodiment 2 of the present invention item alarm set 30 based on semantic analysis
Schematic diagram.The item alarm set 30 based on semantic analysis, comprising: obtain module 31, extraction module 32 establishes module 33
With reminding module 34.Wherein, the concrete function of each module is as follows:
Module 31 is obtained, for obtaining the content of text of terminal device；
Extraction module 32, for from the content of text extract item keyword, and with the item keyword phase
Associated trigger condition keyword；
Module 33 is established, for establishing reminding triggering conditions according to the trigger condition keyword, is closed according to the item
Key word establishes item reminded contents, and according to the reminding triggering conditions and the corresponding prompting thing of item reminded contents creation
?；
Reminding module 34 is used in one or more reminding triggering conditions matching preset trigger conditions, according to pre-
Fixed alerting pattern triggering executes prompting operation corresponding with the prompting item.
Optionally, as shown in figure 4, extraction module 32 includes:
First extraction unit 321, for extracting item keyword and trigger condition keyword from the content of text.
Semantic analysis unit 322 is used for the item keyword and trigger condition keyword in the content of text
Context carry out semantic analysis.
Second extraction unit 323, for being closed according to semantic analysis result is determining from the content of text with the item
The associated trigger condition keyword of key word.
Optionally, as shown in figure 5, the second extraction unit 323 includes:
First obtains subelement 3231, for carrying out matching inquiry in time-critical character library, to obtain in the text
The time-critical word for including in appearance.
Second obtains subelement 3232, for carrying out matching inquiry in geographical key word library, to obtain and the text
The geographical keyword that words matches in content.
Subelement 3233 is selected, for that will have the time-critical word of item relevance and/or the geographical key
Word is as the trigger condition keyword with item relevance.
Optionally, the selection subelement includes:
First obtains subelement, for obtaining the time accuracy of the time-critical word.
First determines subelement, if for determining that the time accuracy meets preset accuracy condition, it is determined that institute
Time-critical word is stated with item relevance.
Alternatively,
First inquiry subelement, for the time-critical word to be carried out matching inquiry in reminder time key word library.
Second determines subelement, if being used for successful match, it is determined that the time-critical word has item relevance.
Optionally, the selection subelement includes:
Second obtains subelement, for obtaining the position fine granularity of the geographical location keyword.
Third determines subelement, if meeting preset fine granularity condition for the position fine granularity, it is determined that describedly
Managing position keyword has item relevance.
Alternatively,
The geographical keyword is reminded in key word library in geography and carries out matching inquiry by the second inquiry subelement.
4th determines subelement, if being used for successful match, it is determined that the geographical location keyword has item relevance.
Specific restriction about the item alarm set based on semantic analysis may refer to above for based on semantic point
The restriction of the item based reminding method of analysis, details are not described herein.Each mould in the above-mentioned item alarm set based on semantic analysis
Block can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independence
In processor in computer equipment, it can also be stored in a software form in the memory in computer equipment, in order to
Processor, which calls, executes the corresponding operation of the above modules.
Embodiment three:
In the present embodiment, a kind of computer equipment is provided, which can be server, internal structure
Figure can be as shown in Figure 6.The computer equipment includes processor, the memory, network interface sum number connected by system bus
According to library.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory of the computer equipment includes
Non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data being related in the item based reminding method based on semantic analysis.The computer equipment
Network interface is used to communicate with external terminal by network connection.To realize one kind when the computer program is executed by processor
Item based reminding method based on semantic analysis.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor are realized in above-described embodiment when executing computer program based on semanteme
The step of item based reminding method of analysis, such as step 101 shown in Fig. 2 is to step 104.Alternatively, processor executes computer
The function of each module/unit of the item alarm set in above-described embodiment based on semantic analysis, such as Fig. 3 institute are realized when program
Show the function of module 31 to module 34.To avoid repeating, which is not described herein again.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step of item based reminding method in above-described embodiment based on semantic analysis, such as Fig. 2 when being executed by processor
Shown step 101 is to step 104.Alternatively, being realized when computer program is executed by processor in above-described embodiment based on semanteme
The function of each module/unit of the item alarm set of analysis, such as module 31 shown in Fig. 3 is to the function of module 34.To avoid
It repeats, which is not described herein again.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (SyNchliNk) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of item based reminding method based on semantic analysis characterized by comprising
Obtain the content of text of terminal device；
Item keyword, and trigger condition associated with item keyword key are extracted from the content of text
Word；
Reminding triggering conditions are established according to the trigger condition keyword, are established in item prompting according to the item keyword
Hold, and according to the reminding triggering conditions and the corresponding prompting item of item reminded contents creation；
In one or more reminding triggering conditions matching preset trigger conditions, is triggered and executed according to scheduled alerting pattern
Prompting operation corresponding with the prompting item.
2. the item based reminding method according to claim 1 based on semantic analysis, which is characterized in that described from the text
Item keyword is extracted in content, and trigger condition keyword associated with the item keyword includes:
Item keyword and trigger condition keyword are extracted from the content of text；
Semantic analysis is carried out to the context of the item keyword and trigger condition keyword in the content of text；
Determine that trigger condition associated with the item keyword is crucial from the content of text according to semantic analysis result
Word.
3. the item based reminding method according to claim 2 based on semantic analysis, which is characterized in that the trigger condition is closed
Key word includes time-critical word and/or geographical keyword；According to semantic analysis result from the content of text determine with it is described
The associated trigger condition keyword of item keyword includes:
Matching inquiry is carried out, in time-critical character library to obtain the time-critical word for including in the content of text；
Matching inquiry is carried out in geographical key word library, it is crucial to obtain the geography to match with words in the content of text
Word；
Using with item relevance the time-critical word and/or the geographical keyword as the touching with item relevance
Send out condition keyword.
4. the item based reminding method according to claim 3 based on semantic analysis, which is characterized in that described to have item
The time-critical word of relevance includes: as trigger condition keyword
Obtain the time accuracy of the time-critical word；
If the time accuracy meets preset accuracy condition, it is determined that the time-critical word has item relevance；
Alternatively, the time-critical word is carried out matching inquiry in reminder time key word library；
If successful match, it is determined that the time-critical word has item relevance.
5. the item based reminding method according to claim 3 based on semantic analysis, which is characterized in that described to have item
The geographical keyword of relevance includes: as the trigger condition keyword with item relevance
Obtain the position fine granularity of the geographical location keyword；
If the position fine granularity meets preset fine granularity condition, it is determined that the geographical location keyword is associated with item
Property；
Matching inquiry is carried out alternatively, the geographical keyword is reminded in key word library in geography；
If successful match, it is determined that the geographical location keyword has item relevance.
6. a kind of item alarm set based on semantic analysis characterized by comprising
Module is obtained, for obtaining the content of text of terminal device；
Extraction module is used to extract item keyword from the content of text, and associated with the item keyword
Trigger condition keyword；
Module is established, for establishing reminding triggering conditions according to the trigger condition keyword, is built according to the item keyword
Vertical item reminded contents, and according to the reminding triggering conditions and the corresponding prompting item of item reminded contents creation；
Reminding module, for being mentioned according to scheduled in one or more reminding triggering conditions matching preset trigger conditions
Awake mode, which triggers, executes prompting operation corresponding with the prompting item.
7. the item alarm set according to claim 6 based on semantic analysis, which is characterized in that the extraction module packet
It includes:
First extraction unit, for extracting item keyword and trigger condition keyword from the content of text；
Semantic analysis unit, for the context to the item keyword and trigger condition keyword in the content of text
Carry out semantic analysis；
Second extraction unit, for determination to be related to the item keyword from the content of text according to semantic analysis result
The trigger condition keyword of connection.
8. the item alarm set according to claim 7 based on semantic analysis, which is characterized in that described second extracts list
Member includes:
First obtains subelement for carrying out matching inquiry in time-critical character library includes to obtain in the content of text
Time-critical word；
Second obtains subelement, for carrying out matching inquiry in geographical key word library, to obtain and word in the content of text
The geographical keyword that word matches；
Subelement is selected, for that will have the time-critical word of item relevance and/or the geographical keyword as tool
There is the trigger condition keyword of item relevance.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The step of any one of 5 the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 5 of realization the method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910302074.3A CN110175806A (en) | 2019-04-16 | 2019-04-16 | Item based reminding method, device and computer equipment based on semantic analysis |
| PCT/CN2019/117742 WO2020211352A1 (en) | 2019-04-16 | 2019-11-13 | Item reminding method and apparatus based on semantic analysis, and computer device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910302074.3A CN110175806A (en) | 2019-04-16 | 2019-04-16 | Item based reminding method, device and computer equipment based on semantic analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110175806A true CN110175806A (en) | 2019-08-27 |
Family
ID=67689461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910302074.3A Pending CN110175806A (en) | 2019-04-16 | 2019-04-16 | Item based reminding method, device and computer equipment based on semantic analysis |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110175806A (en) |
| WO (1) | WO2020211352A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020211352A1 (en) * | 2019-04-16 | 2020-10-22 | 平安科技（深圳）有限公司 | Item reminding method and apparatus based on semantic analysis, and computer device |
| CN113434678A (en) * | 2021-06-28 | 2021-09-24 | 平安银行股份有限公司 | Item reminding method, item reminding device, item reminding equipment and storage medium based on item types |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103984687A (en) * | 2013-02-07 | 2014-08-13 | 北京搜狗科技发展有限公司 | Reminding creating method and device |
| CN104105076A (en) * | 2014-06-19 | 2014-10-15 | 北京奇虎科技有限公司 | Prompt establishment method and device, client terminal and electronic equipment |
| CN104104791A (en) * | 2014-06-19 | 2014-10-15 | 北京奇虎科技有限公司 | Prompt establishment method and device, information service method and device and client terminal |
| US20170352008A1 (en) * | 2016-06-03 | 2017-12-07 | International Business Machines Corporation | Task reminder generator |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175806A (en) * | 2019-04-16 | 2019-08-27 | 平安科技（深圳）有限公司 | Item based reminding method, device and computer equipment based on semantic analysis |
-
2019
- 2019-04-16 CN CN201910302074.3A patent/CN110175806A/en active Pending
- 2019-11-13 WO PCT/CN2019/117742 patent/WO2020211352A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103984687A (en) * | 2013-02-07 | 2014-08-13 | 北京搜狗科技发展有限公司 | Reminding creating method and device |
| CN104105076A (en) * | 2014-06-19 | 2014-10-15 | 北京奇虎科技有限公司 | Prompt establishment method and device, client terminal and electronic equipment |
| CN104104791A (en) * | 2014-06-19 | 2014-10-15 | 北京奇虎科技有限公司 | Prompt establishment method and device, information service method and device and client terminal |
| US20170352008A1 (en) * | 2016-06-03 | 2017-12-07 | International Business Machines Corporation | Task reminder generator |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020211352A1 (en) * | 2019-04-16 | 2020-10-22 | 平安科技（深圳）有限公司 | Item reminding method and apparatus based on semantic analysis, and computer device |
| CN113434678A (en) * | 2021-06-28 | 2021-09-24 | 平安银行股份有限公司 | Item reminding method, item reminding device, item reminding equipment and storage medium based on item types |
| CN113434678B (en) * | 2021-06-28 | 2024-03-19 | 平安银行股份有限公司 | Item type-based item reminding method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020211352A1 (en) | 2020-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103984687B (en) | The creation method and device of prompting | |
| Flatow et al. | On the accuracy of hyper-local geotagging of social media content | |
| US12002010B2 (en) | Event extraction systems and methods | |
| Church et al. | A large-scale study of daily information needs captured in situ | |
| Ferrari et al. | Extracting urban patterns from location-based social networks | |
| US20210149548A1 (en) | Systems, devices and methods for electronic determination and communication of location information | |
| Fast et al. | Trajectories of family care over the lifecourse: evidence from Canada | |
| CN102439957B (en) | Schedule generating method and communication terminal thereof | |
| CN110134466B (en) | Information processing method and terminal device | |
| CN109800375A (en) | Information integrates dissemination method, device, computer equipment and storage medium | |
| US20140074871A1 (en) | Device, Method and Computer-Readable Medium For Recognizing Places | |
| CN104038630A (en) | Speech processing method and device | |
| CN102413417A (en) | Calendar event remind prompting method based on cloud service, system and cloud server thereof | |
| CN107465599A (en) | Schedule method to set up and device in a kind of instant messaging | |
| CN110298039B (en) | Event place identification method, system, equipment and computer readable storage medium | |
| CN110175806A (en) | Item based reminding method, device and computer equipment based on semantic analysis | |
| CN109446284A (en) | Show method, apparatus, computer equipment and the storage medium of customer address | |
| Pandey et al. | Reach360: A comprehensive safety solution | |
| JP5482894B2 (en) | Information processing method for special day registration | |
| US20090007011A1 (en) | Semantically rich way of navigating on a user device | |
| WO2015120658A1 (en) | Transaction management method, apparatus and terminal based on communication text information | |
| US9830359B2 (en) | Marking and searching mobile content by location | |
| WO2023134521A1 (en) | Data processing system and method | |
| CN109658070A (en) | Memorandum based reminding method, terminal and the storage medium of memorandum event | |
| CN103455565B (en) | Method, client and the system of temporal information are obtained by input method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190827 |
|
| RJ01 | Rejection of invention patent application after publication |