CN107291680A - A kind of system and implementation method that automatically generate composition based on template - Google Patents
A kind of system and implementation method that automatically generate composition based on template Download PDFInfo
- Publication number
- CN107291680A CN107291680A CN201710322347.1A CN201710322347A CN107291680A CN 107291680 A CN107291680 A CN 107291680A CN 201710322347 A CN201710322347 A CN 201710322347A CN 107291680 A CN107291680 A CN 107291680A
- Authority
- CN
- China
- Prior art keywords
- composition
- template
- topic
- keyword
- unit
- 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
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
Abstract
The present invention relates to a kind of system and implementation method that automatically generate composition based on template, system includes：Modular unit, rules unit, selection unit, topic unit, the modular unit, to provide composition template interface, the rules unit, to provide create-rule interface, the selection unit, to the selected center topic and keyword intended in generation composition, the topic unit, topic parameter can be called to be provided according to center topic topic, based on above-mentioned composition template and create-rule, and according to the center topic and keyword, generation composition.The present invention is based on template and keyword, and user only needs input center topic and keyword, it becomes possible to automatically generates and meets the desired composition of user, while meeting writing rule, the center topic for the user that links closely.In addition, it can also be other Languages that the mode that the system is automatically generated, which can be English,.
Description
Technical field
The present invention relates to natural language processing field, more particularly to a kind of system for automatically generating composition based on template and
Implementation method.
Background technology
Early in 2009, Britain's examining body Edexcel was just announced to read and make comments English Writing paper using computer.Britain《Thailand meets
Scholar's report education supplementary issue》Reporting at that time, by the computer of special programming by " scanning " paper, assesses the grammer and word of student
Converge, distinguish fixed possible correct answer, and provide total score.
, Britain in 2014《Guardian》Paper media's test plan is carried out." robot " is arranged on social networks
Share focus and concern temperature carries out statistical analysis, Content Selection, editing and composing and printing are carried out immediately, portion is ultimately produced
Newspaper.
In 2015, Japanese future University of Hakodate R＆D team using artificial intelligence create this piece composition, be by
The mankind have been previously set after " parts " such as character in a play, content outlines, and artificial intelligence is automatically raw further according to these " parts "
Into.
Recently, venture company of Israel Articoolo develops a kind of algorithm, and any theme that can be selected according to user is gone
Generation composition, so long as theme can be gone with 2 to 5 words description.User needs accurately to summarize the theme of oneself, tells meter
Calculation machine user wishes how many word of writing a composition, and selects preference, then clicks on generation button, you can wait artificial intelligence to complete to make
The creation of text.
It can be seen that, the process based on machine autonomous learning in artificial intelligence field that the method for composition has is automatically generated at present,
The mode based on sorting algorithm and machine autonomous learning having.Also there are some solutions, such as, Chinese patent in the prior art
Apply for CN201611003822.0, the method and system of composition are automatically generated based on description text, method includes：Receive to be generated
The description text of composition；Determine it is described description text theme, and using the theme as composition to be generated theme；According to institute
State the corresponding corpus of text of theme and build descriptor figure；The composition of the correspondence theme is generated according to the descriptor figure of structure.This
Invention can improve the efficiency and accuracy of generation composition.Shortcoming is：In order to ensure the uniformity for generating result, text is expected
Corresponding relation mode with theme is single.Again such as, a kind of Chinese patent application CN201610803388.8, practical writing is given birth to automatically
Into method, step 1) set up corpus；Step 2) select multiple applicable entities and input its corresponding particular content；Step 3) build
Shuttering storehouse simultaneously therefrom selects a template；Step 4) selected template is polished.Although setting up sufficiently large expectation
Storehouse, but has the disadvantage that：It can not ensure that composition can meet multi-field different requirements.
The content of the invention
The technical problem to be solved in the present invention is to provide can be accurately positioned for special module and keyword one
The system for automatically generating composition based on template of kind.
Above-mentioned technical problem is solved, the invention provides a kind of system for automatically generating composition based on template, including：Mould
Slab element, rules unit, selection unit, topic unit,
The modular unit, to provide composition template interface,
The rules unit, to provide create-rule interface,
The selection unit, to the selected center topic and keyword intended in generation composition,
The topic unit, topic parameter can be called to be provided according to center topic topic,
Based on above-mentioned composition template and create-rule, and according to the center topic and keyword, generation composition.
Further, system also includes：One client, the client includes：The input condition page and composition generation knot
The fruit page,
User intends { parameter, the condition } of generation composition by being inputted in the input condition page；
It is described composition generation results page receive above-mentioned { parameter, condition }, and to background server send composition content please
Ask,
The server generates results page to the composition and returns to composition template content, and passes through the composition generation knot
Fruit page conversion rear line display composition content.
Further, the modular unit includes：First template, the second template, the 3rd template and the 4th template,
First template, the related content of template content in webpage is obtained to set up a web crawler,
Second template, to set up Chinese composition template,
3rd template, to set up English composition template,
4th template, to set up intertranslatable composition corpus.
Further, the rules unit includes：
Tense unit, the tense that Chinese/English is met to set up uses rule
Voice unit, the voice of Chinese/English is met to set up using rule,
Lexical unit, the morphological processing rule of Chinese/English is met to set up.
Further, the selection unit includes：Query interface, associated interface and matched interfaces,
The query interface, the query interface to provide the keyword/center topic,
The associated interface, to be associated according to the keyword and/or center topic,
The matched interfaces, to be matched according to inquiry and relational structure.
Further, the keyword includes：Chinese key, English keyword and amendment keyword,
The Chinese key or English keyword, to as the label data in composition,
The amendment keyword, is modified to the semanteme to above-mentioned Chinese key or English keyword.
Further, the center topic includes：The label of { necessary topic, much-talked-about topic, academic topic }.
Further, user sends access request, the backstage clothes by the web browser in terminal to background server
WEB server on business device searches corresponding page and hands to the apps server of the background server, the application
Program servers position and complete the instruction in the page, and by the Page retrieval of completion to WEB server, by described
WEB server completes the response of accessing page request,
The access request at least includes：Intend generation composition.
Based on above-mentioned, present invention also offers a kind of method for automatically generating composition, comprise the following steps：
S1 initialization provides composition template, create-rule,
The selected center topics and keyword intended in generation composition of S2,
S3 is provided according to center topic topic can call topic parameter,
S4 is based on above-mentioned composition template and create-rule, and according to the center topic and keyword, generation composition.
Further, the S1 also includes：Initializing composition template is：Expository writing, describe text, narrative, argumentative writing or
One or more in person's practical writing.
Beneficial effects of the present invention：
In the present invention, can be based on language specialist storehouse, examination due to providing composition template interface in the modular unit
Master storehouse and network update ATL, maximized can meet the composition writing type of user.Due to single in the rule
Member provides create-rule interface, the rule based on including but not limited to grammer, the semantic and meaning of a word, enables to the composition of generation
Meet thinking and narrative logic so that it is lower press close to people expression.Due in the selected plan generation composition of the selection unit
Center topic and keyword, on the premise of with template and rule, in being intended by or transmit by keying in user
Heart topic, using the teaching of the invention it is possible to provide the selection form of user's different dimensions, while coordinating keyword, forms the purport text of similar composition summary
Part is used to follow-up expansion.Because in the topic unit, topic parameter can be called by being provided according to center topic topic, topic ginseng
Count the confidence level between the center topic for determining the trend of composition and being intended by with user.By being in the present invention
System, based on template and keyword, can accurately generate and meet the desired composition of user, while composition meets writing rule, tightly
Detain the center topic of user.
Brief description of the drawings
Fig. 1 is the system structure diagram in one embodiment of the invention；
Fig. 2 is the interactive mode schematic flow sheet in one embodiment of the invention；
Fig. 3 is the modular unit structural representation in Fig. 1；
Fig. 4 is the rules unit structural representation in Fig. 1；
Fig. 5 is the selection cellular construction schematic diagram in Fig. 1；
Fig. 6 is the method flow schematic diagram in one embodiment of the invention.
Embodiment
The principle of the disclosure is described referring now to some example embodiments.It is appreciated that these embodiments are merely for saying
It is bright and help it will be understood by those skilled in the art that with the purpose of the embodiment disclosure and describe, rather than advise model of this disclosure
Any limitation enclosed.Content of this disclosure described here can be implemented in the various modes outside mode described below.
As described herein, term " comprising " and its various variants are construed as open-ended term, it means that " bag
Include but be not limited to ".Term "based" is construed as " being based at least partially on ".Term " one embodiment " it is understood that
For " at least one embodiment ".Term " another embodiment " is construed as " at least one other embodiment ".
Refer to Fig. 1 is that one kind in the system structure diagram in one embodiment of the invention, the present embodiment is based on template
The system for automatically generating composition, including：Modular unit 1, rules unit 3, selection unit 2, topic unit 4, the template list
Member 1, to provide composition template interface, the rules unit 2, to provide create-rule interface, the selection unit 2, use
With the selected center topic and keyword intended in generation composition, the topic unit 4 can be provided according to center topic topic
Topic parameter is called, based on above-mentioned composition template and create-rule, and according to the center topic and keyword, generation composition.
The modular unit 1, the mode for obtaining template includes but is not limited to, based on existing composition template, the composition mould based on expert
Block, based on device for examining warp, based on template in internet etc..The rules unit 3, includes but is not limited to, Chinese grammer, Chinese word
Method and Chinese are semantic, English grammar, English morphology and English semanteme etc..The selection unit 2 can be based on user
Demand is gathered, and receives the center topic that user submits in the selection unit 2, the center topic includes but is not limited to, must
Topic, much-talked-about topic, academic topic etc. are wanted, than topic if necessary according to that can be determined according to different type test subject, is compared again
As much-talked-about topic can be according to the higher topic of concerned degree in setting range (such as, college entrance examination, prepare for the postgraduate qualifying examination), academic topic root for another example
According to according to different field divisions (academic problem such as based on Great Britain's encyclopedia definition).
Using the system in the present embodiment, the composition writing type of user maximized can be met.And rule-based make
The composition that must be generated meet thinking and narrative logic so that it is lower press close to people expression.It can be carried when user is selected
For the selection form of user's different dimensions, while coordinating keyword, the purport file for forming similar composition summary is used to follow-up
Expand.As preferred in the present embodiment, refer to Fig. 2 is the interactive mode schematic flow sheet in one embodiment of the invention, is
A client is based in system, the client includes：The input condition page and composition generation results page, user pass through described
{ parameter, the condition } of generation composition is intended in the input of the input condition page；The composition generation results page receives above-mentioned { parameter, bar
Part }, and composition content requests are sent to background server, the server generates results page to the composition and returns to composition mould
Plate content, and results page conversion rear line display composition content is generated by the composition.
In certain embodiments, above-mentioned client includes but is not limited to, mobile phone, tablet personal computer, desktop computer.
In certain embodiments, above-mentioned client includes but is not limited to, PC ends, Android end, iPhone ends, WP ends, iPad
The six big customer ends such as end, Mac ends.
In certain embodiments, above-mentioned { parameter, condition } includes but is not limited to, { center topic, keyword }.
In certain embodiments, above-mentioned { parameter, condition } includes but is not limited to, { number of words/form, Chinese/English }.
In certain embodiments, above-mentioned { parameter, condition } includes but is not limited to, { paper, academic }.
In certain embodiments, above-mentioned { parameter, condition } includes but is not limited to, { work letter, daily }.
In certain embodiments, above-mentioned { parameter, condition } includes but is not limited to, { composition, the TOEFL }.
In certain embodiments, above-mentioned { parameter, condition } includes but is not limited to, { composition, IELTS }.
As preferred in the present embodiment, refer to Fig. 3 is the modular unit structural representation in Fig. 1, the template list
Member 1 includes：First template 11, the second template 12, the 3rd template 13 and the 4th template 14, first template 11, to build
A vertical web crawler obtains the related content of template content, second template 12, to set up Chinese composition in webpage
Template, the 3rd template 13, to set up English composition template, the 4th template 14, to set up intertranslatable composition
Corpus.The related content of template content in webpage is obtained using web crawler in first template 11.This area
Technical staff can understand that (be otherwise known as web crawlers webpage spider, and network robot is more frequent in the middle of FOAF communities
Referred to as webpage follower), it is a kind of according to certain rule, automatically captures the program or script of web message.Second
Chinese composition template during template 12 is set up according to the information obtained in web crawlers, or the second template 12 can use language specialist
Template, machine are through template, examination high score template etc..
In certain embodiments, Chinese composition template during the second template 12 is set up according to the information obtained in web crawlers,
Including but not limited to following processing mode：From content of text extract numerical characteristics in mark (tokenizing) text and
For an integer ID of each possible mark (token) distribution, such as the dividing as mark with white space and punctuation mark
Cut symbol (if the problem of Chinese is then related to participle).
In some embodiments, the second template 12 can be integrated through system with machine or can be included in and for example be wrapped
Include being different among computing device or system of the machine through system for server.Including but not limited to Baidupedia, Wikipedia
Deng.
In some embodiments, 12 pairs of keywords generated using keyword generation engine of the second template are summarized
Various news agregators conduct interviews, receive comment about it, share, approve of.
In certain embodiments, Chinese composition template during the second template 12 is set up according to the information obtained in web crawlers,
Including but not limited to following processing mode：Count the frequency of occurrences i.e. feature that (counting) is marked in each text.Feature
It is defined as：The frequency (regardless of whether normal state) that each mark occurs.
In certain embodiments, Chinese composition template during the second template 12 is set up according to the information obtained in web crawlers,
Including but not limited to following processing mode：Normal state (nomalizating) reduction all occurs in most numerical example/document
The weight of mark, multivariate sample is defined as：In given file the vectorial conduct that is constituted of the markd frequency of occurrences.
Preferably, web crawlers uses Scrapy.
In certain embodiments, the 3rd template 13, which is directly only used, quantifies template, and the keyword of definition is screened.
In certain embodiments, including but not limited to such a way is preferably used in the 4th template 14：
The alignment techniques (Alignment) of bilingual corpora, domestic and foreign scholars have gone out with regard to a variety of strategies of this proposition and method
The program or instrument [Gale 1993] of many bilingual or multi-lingual language materials that align are showed；
The various applications of bilingual corpora, as in the machine translation mothod [Brown 1990] based on statistics, Case-based Reasoning
It is double in machine translation mothod [Nagao 1984], bilingual dictionary compilation [Klavans and Tzoukermann 1990] technology
Language corpus all plays highly important effect；
Design, collection, coding and the problem of management of bilingualism corpora.Comparing famous corpus encoding scheme has TEI texts
This coding standard and CES standards, both of which are studied based on SGML markup languages.
In certain embodiments, the corpus of extensive real text is preferably based in the 4th template 14, to language
The use of word carries out the corpus of dynamic tracing, and the corpus being monitored to the development and change of language.
In certain embodiments, the composition corpus priority in the 4th template 14 is：TOEFL, refined thinking
Examination, GRE.
As preferred in the present embodiment, refer to Fig. 4 is the rules unit structural representation in Fig. 1, and the rule is single
Member 3 includes：Tense unit 31, the tense of Chinese/English is met to set up using regular voice unit 33, is met to set up
The voice of Chinese/English meets the morphological processing rule of Chinese/English to set up using rule, lexical unit 32.
In certain embodiments, tense unit 31 includes but is not limited to, tense { present indefinite simple present, past idenfinite, one
As future tense, past future indefinite；Present progressive tense, past progressive tense, future progressive tense, past future continuous tense；Now
During completion, past perfect tense, future perfect tense, past future perfect tense；When completing to carry out now, past perfect continuous tense will
During completing to carry out, when the past completes to carry out in the future }.
In certain embodiments, the tense unit 31 includes but is not limited to, and { completion status, progress state, completion are carried out
State or general state }.
In certain embodiments, the tense unit 31 includes but is not limited to, { past, now, in the future }.
In certain embodiments, the voice unit 33 includes but is not limited to, { active voice, passive voice }.
In certain embodiments, the voice unit 33 includes but is not limited to, and present indefinite simple present, be+V. V.s, am
Is are+ (p.p) future simple tense, will be going to, will be+ (p.p)
Present progressive tense, am is are+V.ing, am is are+being+ (p.p), past idenfinite, 1. was
Were 2. V.ed, was were+ (p.p).
In certain embodiments, the voice unit 33 includes but is not limited to, and present perfect tense, have has+V.p.p,
Have has+been+ (p.p), past perfect tense, had+V.p.p, had+been+ (p.p), past progressive tense, was were+
V.ing, was were+being+ (p.p).
In certain embodiments, the voice unit 33 includes but is not limited to, { modal verb, modal verb+V., mood
Verb+be+ (p.p) }.
In certain embodiments, a series of word symbols are resolved into according to word-building rule in lexical unit 32.Word is language
Call the turn the least unit with independent meaning, including keyword, identifier, operator, boundary's symbol and constant etc..Wherein, keyword
It is the identifier with fixed meaning defined by english language.For example, begin, end, if, while are reserved words, and incite somebody to action
Name, building, place name etc. are removed.These words are generally not used as general identifier.Identifier, for representing various names, such as
Variable name, array name, procedure name etc..Constant, the type of constant typically has integer, full mold, Boolean type, character type etc..Computing
Symbol such as+,-, * ,/.Boundary accord with, such as comma, branch, bracket,.
As preferred in the present embodiment, refer to Fig. 5 is the selection cellular construction schematic diagram in Fig. 1, the selection list
Member 3 includes：Query interface 31, associated interface 32 and matched interfaces 33, the query interface 31, to provide the key
The query interface of word/center topic, the associated interface 32, to be associated according to the keyword and/or center topic,
The matched interfaces 33, to be matched according to inquiry and relational structure.The rule of query interface is, word, word or
Attachable sentence.The rule of associated interface is the active correlation that conjunction is associated, temperature word association and user input.Association
Mode includes but is not limited to, and, or, not etc..
As preferred in the present embodiment, refer to Fig. 6 is the method flow schematic diagram in one embodiment of the invention, this reality
A kind of method for automatically generating composition in example is applied, is comprised the following steps：
Step S1 initialization provides composition template, create-rule,
The selected center topics and keyword intended in generation composition of step S2,
Step S3 is provided according to center topic topic can call topic parameter,
Step S4 is based on above-mentioned composition template and create-rule, and according to the center topic and keyword, generation composition.
Specifically included in above-mentioned steps S3：User sends access by the web browser in terminal to background server please
Ask, the WEB server on the background server searches corresponding page and hands to the application program clothes of the background server
It is engaged in device, the apps server positions and complete the instruction in the page, and by the Page retrieval of completion to WEB service
Device, the response of accessing page request is completed by the WEB server, and the access request at least includes：Intend generation composition.This
Art personnel can understand that web application is one group of static and dynamic Web page set.Static Web page refers to work as
The page is directly sent to request Web by the page that content will not be changed when Web server is connected to user's request, Web server
Browser, without doing any processing to it.On the contrary, before dynamic Web page to be sent to request browser, server will be to this
Page processing, performs the code run in server end being embedded in webpage, so as to be dynamically generated a html webpage, is sent to
Client browser.
Specifically included in above-mentioned steps S4：Template/rule language material is extracted by the Gensim Text Pretreatment scripts provided,
Every article a line text storage, is then based on Gensim Word2Vec modules training term vector model.Gensim is a
The third party's Python kits increased income, for from original non-structured text, learning to text hidden layer unsupervisedly
Theme vector expression.
Above-mentioned steps S4 further comprises：A kind of language model is set up based on Markov model, in this model,
It can predict that what next word is according to current one or several words.It is one if simply predicted according to a upper word
Individual first-order Markov model.It is a second order Markov model if using two word predictions.Based on NLTK
(the NLP storehouses in Python), an array is converted into using split () function by character string (being obtained from text).
The function of top two is the basic function of code." conditional frequency dictionary " in the NLTK finally to be used must be with
Paired array as input, so phrase " hello her name is A " need to be changed into [(" hello ", " her "), (" her,
“name”),(“name”,“is”),(“is”,“A”)].Function makePairs (is obtained) with an array with word separating character string
As input, output meets the array of top form.
Client is based on when the above method is realized, the client includes：The input condition page and composition generation result page
Face,
User intends { parameter, the condition } of generation composition by being inputted in the input condition page；
It is described composition generation results page receive above-mentioned { parameter, condition }, and to background server send composition content please
Ask,
The server generates results page to the composition and returns to composition template content, and passes through the composition generation knot
Fruit page conversion rear line display composition content.
Template of being write a composition in above-mentioned steps S1 includes but is not limited to, and template in webpage is obtained to set up a web crawler
First template of the related content of content, the second template to set up Chinese composition template, to set up English composition template
The template of volume the 3rd, the 4th template to set up intertranslatable composition corpus.
Rules unit includes described in above-mentioned steps S1：
The tense that foundation meets Chinese/English uses rule
The voice for meeting Chinese/English is set up using rule,
Set up the morphological processing rule for meeting Chinese/English.
Choose mode in above-mentioned steps S3 to include but is not limited to, the inquiry to provide the keyword/center topic connects
Mouthful, to be associated according to the keyword and/or center topic, and to according to inquiry and relational structure progress
Match somebody with somebody.
Keyword includes described in above-mentioned steps S2：To be closed as the label data Chinese key in composition or English
Keyword and the amendment keyword being modified to the semanteme to above-mentioned Chinese key or English keyword.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, the software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, the application specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or the spy that the embodiment or example are described
Point is contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not
Necessarily refer to identical embodiment or example.Moreover, specific features, structure, material or the feature of description can be any
One or more embodiments or example in combine in an appropriate manner.
In general, the various embodiments of the disclosure can be with hardware or special circuit, software, logic or its any combination
Implement.Some aspects can be implemented with hardware, and some other aspect can be with firmware or software implementation, and the firmware or software can
With by controller, microprocessor or other computing devices.Although the various aspects of the disclosure be shown and described as block diagram,
Flow chart is represented using some other drawing, but it is understood that frame described herein, equipment, system, techniques or methods can
With in a non limiting manner with hardware, software, firmware, special circuit or logic, common hardware or controller or other calculating
Equipment or some of combination are implemented.
In addition, although operation is described with particular order, but this is understood not to require this generic operation with shown suitable
Sequence is performed or performed with generic sequence, or requires that all shown operations are performed to realize expected result.In some feelings
Under shape, multitask or parallel processing can be favourable.Similarly, although the details of some specific implementations is superincumbent to beg for
By comprising but these are not necessarily to be construed as any limitation of scope of this disclosure, but the description of feature is only pin in
To specific embodiment.Some features described in some embodiments of separation can also in combination be held in single embodiment
OK.Mutually oppose, the various features described in single embodiment can also be implemented separately or to appoint in various embodiments
The mode of what suitable sub-portfolio is implemented.
Claims (10)
1. a kind of system for automatically generating composition based on template, it is characterised in that including：Modular unit, rules unit, selection
Unit, topic unit,
The modular unit, to provide composition template interface,
The rules unit, to provide create-rule interface,
The selection unit, to the selected center topic and keyword intended in generation composition,
The topic unit, topic parameter can be called to be provided according to center topic topic,
Based on above-mentioned composition template and create-rule, and according to the center topic and keyword, generation composition.
2. the system according to claim 1 for automatically generating composition, it is characterised in that also include：One client, the visitor
Family end includes：The input condition page and composition generation results page,
User intends { parameter, the condition } of generation composition by being inputted in the input condition page；
The composition generation results page receives above-mentioned { parameter, condition }, and sends composition content requests to background server,
The server generates results page to the composition and returns to composition template content, and generates result page by the composition
Face conversion rear line display composition content.
3. the system according to claim 1 for automatically generating composition, it is characterised in that the modular unit includes：First
Template, the second template, the 3rd template and the 4th template,
First template, the related content of template content in webpage is obtained to set up a web crawler,
Second template, to set up Chinese composition template,
3rd template, to set up English composition template,
4th template, to set up intertranslatable composition corpus.
4. the system according to claim 1 for automatically generating composition, it is characterised in that the rules unit includes：
Tense unit, the tense that Chinese/English is met to set up uses rule
Voice unit, the voice of Chinese/English is met to set up using rule,
Lexical unit, the morphological processing rule of Chinese/English is met to set up.
5. the system according to claim 1 for automatically generating composition, it is characterised in that the selection unit includes：Inquiry
Interface, associated interface and matched interfaces,
The query interface, the query interface to provide the keyword/center topic,
The associated interface, to be associated according to the keyword and/or center topic,
The matched interfaces, to be matched according to inquiry and relational structure.
6. the system according to claim 1 for automatically generating composition, it is characterised in that the keyword includes：Chinese is closed
Keyword, English keyword and amendment keyword,
The Chinese key or English keyword, to as the label data in composition,
The amendment keyword, is modified to the semanteme to above-mentioned Chinese key or English keyword.
7. the system according to claim 1 for automatically generating composition, it is characterised in that the center topic includes：It is { necessary
Topic, much-talked-about topic, academic topic } label.
8. the system according to claim 1 for automatically generating composition, it is characterised in that user is clear by the WEB in terminal
The WEB server that device of looking at is sent to background server on access request, the background server is searched corresponding page and handed to
The apps server of the background server, the apps server positions and completes the instruction in the page,
And by the Page retrieval of completion to WEB server, the response of accessing page request is completed by the WEB server,
The access request at least includes：Intend generation composition.
9. a kind of method for automatically generating composition, it is characterised in that comprise the following steps：
S1 initialization provides composition template, create-rule,
The selected center topics and keyword intended in generation composition of S2,
S3 is provided according to center topic topic can call topic parameter,
S4 is based on above-mentioned composition template and create-rule, and according to the center topic and keyword, generation composition.
10. method according to claim 9, it is characterised in that the S1 also includes：Initializing composition template is：Explanation
Text, the one or more described in text, narrative, argumentative writing or practical writing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710322347.1A CN107291680A (en) | 2017-05-09 | 2017-05-09 | A kind of system and implementation method that automatically generate composition based on template |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710322347.1A CN107291680A (en) | 2017-05-09 | 2017-05-09 | A kind of system and implementation method that automatically generate composition based on template |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107291680A true CN107291680A (en) | 2017-10-24 |
Family
ID=60094998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710322347.1A Pending CN107291680A (en) | 2017-05-09 | 2017-05-09 | A kind of system and implementation method that automatically generate composition based on template |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107291680A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108052490A (en) * | 2017-12-29 | 2018-05-18 | 北京仁和汇智信息技术有限公司 | A kind of online methodology of composition of XML papers and device |
| CN108763516A (en) * | 2018-05-31 | 2018-11-06 | 悦未来科技（深圳）有限公司 | Write exchange method, device and computer readable storage medium |
| CN109284298A (en) * | 2018-11-09 | 2019-01-29 | 上海晏鼠计算机技术股份有限公司 | A kind of contents production system handled based on machine learning and big data |
| CN109657857A (en) * | 2018-12-17 | 2019-04-19 | 广东小天才科技有限公司 | A kind of essay examination proposition prediction technique and device |
| CN109801527A (en) * | 2019-01-31 | 2019-05-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| CN109977390A (en) * | 2017-12-27 | 2019-07-05 | 北京搜狗科技发展有限公司 | A kind of method and device generating text |
| WO2019169992A1 (en) * | 2018-03-08 | 2019-09-12 | 腾讯科技（深圳）有限公司 | Method and device for generating text information, storage medium, and apparatus |
| CN111783468A (en) * | 2020-06-28 | 2020-10-16 | 百度在线网络技术（北京）有限公司 | Text processing method, device, equipment and medium |
| CN112052649A (en) * | 2020-10-12 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Text generation method and device, electronic equipment and storage medium |
| CN112307176A (en) * | 2020-03-09 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and device for guiding user to write |
| CN113312911A (en) * | 2021-05-26 | 2021-08-27 | 上海晏鼠计算机技术股份有限公司 | Automatic authorization and intelligent text segment creation method based on outline |
-
2017
- 2017-05-09 CN CN201710322347.1A patent/CN107291680A/en active Pending
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977390B (en) * | 2017-12-27 | 2023-11-03 | 北京搜狗科技发展有限公司 | Method and device for generating text |
| CN109977390A (en) * | 2017-12-27 | 2019-07-05 | 北京搜狗科技发展有限公司 | A kind of method and device generating text |
| CN108052490A (en) * | 2017-12-29 | 2018-05-18 | 北京仁和汇智信息技术有限公司 | A kind of online methodology of composition of XML papers and device |
| CN108052490B (en) * | 2017-12-29 | 2019-04-30 | 北京仁和汇智信息技术有限公司 | A kind of online methodology of composition of XML paper and device |
| WO2019169992A1 (en) * | 2018-03-08 | 2019-09-12 | 腾讯科技（深圳）有限公司 | Method and device for generating text information, storage medium, and apparatus |
| CN108763516A (en) * | 2018-05-31 | 2018-11-06 | 悦未来科技（深圳）有限公司 | Write exchange method, device and computer readable storage medium |
| CN109284298A (en) * | 2018-11-09 | 2019-01-29 | 上海晏鼠计算机技术股份有限公司 | A kind of contents production system handled based on machine learning and big data |
| CN109657857A (en) * | 2018-12-17 | 2019-04-19 | 广东小天才科技有限公司 | A kind of essay examination proposition prediction technique and device |
| CN109801527A (en) * | 2019-01-31 | 2019-05-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| CN112307176A (en) * | 2020-03-09 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and device for guiding user to write |
| CN111783468A (en) * | 2020-06-28 | 2020-10-16 | 百度在线网络技术（北京）有限公司 | Text processing method, device, equipment and medium |
| CN111783468B (en) * | 2020-06-28 | 2023-08-15 | 百度在线网络技术（北京）有限公司 | Text processing method, device, equipment and medium |
| CN112052649A (en) * | 2020-10-12 | 2020-12-08 | 腾讯科技（深圳）有限公司 | Text generation method and device, electronic equipment and storage medium |
| CN113312911A (en) * | 2021-05-26 | 2021-08-27 | 上海晏鼠计算机技术股份有限公司 | Automatic authorization and intelligent text segment creation method based on outline |
| CN113312911B (en) * | 2021-05-26 | 2022-07-12 | 上海晏鼠计算机技术股份有限公司 | Automatic authorization and intelligent text segment creation method based on outline |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107291680A (en) | A kind of system and implementation method that automatically generate composition based on template | |
| Poongodi et al. | Chat-bot-based natural language interface for blogs and information networks | |
| CN109325112B (en) | A kind of across language sentiment analysis method and apparatus based on emoji | |
| CN112131366A (en) | Method, device and storage medium for training text classification model and text classification | |
| Davydov et al. | Mathematical method of translation into Ukrainian sign language based on ontologies | |
| Haug et al. | Neural multi-step reasoning for question answering on semi-structured tables | |
| CN106503101A (en) | Electric business customer service automatically request-answering system sentence keyword extracting method | |
| Priyadarshi et al. | Towards the first Maithili part of speech tagger: Resource creation and system development | |
| Liu et al. | Large-scale simple question generation by template-based seq2seq learning | |
| CN115858758A (en) | Intelligent customer service knowledge graph system with multiple unstructured data identification | |
| Yan et al. | Response selection from unstructured documents for human-computer conversation systems | |
| Chen et al. | ADOL: a novel framework for automatic domain ontology learning | |
| Kang | Spoken language to sign language translation system based on HamNoSys | |
| Mo | Design and implementation of an interactive english translation system based on the information-assisted processing function of the internet of things | |
| Zhang | Application of intelligent grammar error correction system following deep learning algorithm in English teaching | |
| Bai et al. | Gated character-aware convolutional neural network for effective automated essay scoring | |
| Pavlic et al. | Adjective representation with the method Nodes of Knowledge | |
| Kumar et al. | Learning enhancement using question-answer generation for e-book using contrastive fine-tuned T5 | |
| Khandait et al. | Automatic question generation through word vector synchronization using lamma | |
| Cao et al. | Improving efficiency and accuracy in English translation learning: Investigating a semantic analysis correction algorithm | |
| Praveena et al. | Chunking based malayalam paraphrase identification using unfolding recursive autoencoders | |
| Kong et al. | Construction of microblog-specific chinese sentiment lexicon based on representation learning | |
| CN112529743A (en) | Contract element extraction method, contract element extraction device, electronic equipment and medium | |
| Hou et al. | Design and Implementation of Interactive English Translation System in Internet of Things Auxiliary Information Processing | |
| Vukomanović et al. | An example of chatbot in the field of education in the Republic of Serbia |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171024 |