CN106095742A - Text content generation method and server - Google Patents
Text content generation method and server Download PDFInfo
- Publication number
- CN106095742A CN106095742A CN201610443679.0A CN201610443679A CN106095742A CN 106095742 A CN106095742 A CN 106095742A CN 201610443679 A CN201610443679 A CN 201610443679A CN 106095742 A CN106095742 A CN 106095742A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- content
- described user
- server
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention discloses a text content generation method and a server, and relates to the field of computer internet. The method comprises the following steps: the server receives a text content request sent by the terminal, wherein the text content request comprises user identification information and text content currently browsed by a user; the server acquires a language model library corresponding to the user according to the user identification information, wherein the language model library of the user comprises language attribute information of the user; the server converts the text content currently browsed by the user according to the language attribute information of the user to generate text content matched with the language attribute information; the server transmits the generated text content to the terminal to cause the terminal to display. The invention realizes that the server can convert the text content currently browsed by the user according to the language model library of the user to generate the text content suitable for the user to read, so that the user can quickly acquire the required information, the time of the user is saved, and the user experience is improved.
Description
Technical field
The present invention relates to computer internet field, particularly relate to a kind of content of text and generate method and server.
Background technology
At present, issuing article or during news in internet web page, author is according to self experience and to a certain thing
The objective understanding of part, down or writes on line, and the content write is issued.
Certainly, owing to different authors have different experience and the faculty of understanding different to event, author is to same
The word of part thing describes or language convention is diverse.Such as, part author is accustomed to active Writing model；Portion
Author is divided to be accustomed to the Writing model of passive type.
In prior art, author writes the mode of article or news and there is problems in that word and the language of reader
Custom varies, and author may not meet all of reader to the describing mode of event；Furthermore, reader is reading in a large number
The article not meeting self reading habit or during news, it is impossible to quick obtaining to the information needed, reduce the reading of reader
Experience, waste reader's time.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of content of text to generate method and server, to solve prior art
The describing mode of middle author does not meets the reading habit of reader so that reader cannot quick obtaining to need information,
The problem of waste reader's time.
First aspect, the embodiment of the present invention provides a kind of content of text to generate method, including:
Server receive terminal send content of text request, described content of text request include user totem information and
The content of text that described user currently browses；
Described server, according to described user totem information, obtains the language model corresponding with described user totem information
Storehouse, described user language model library includes the linguistic property information of described user；
Described server is carried out according to the linguistic property information of described user, the content of text currently browsed described user
Conversion processing, generates the content of text with described linguistic property information matches；
Described server sends the described content of text generated to described terminal, so that described terminal shows.
In conjunction with first aspect, in the first embodiment of first aspect, described server receives the literary composition that terminal sends
Before this content requests, described method includes:
Server receives described user totem information and the user's word content that described terminal sends, in described user's word
Hold is that described user inputs in described terminal or described user browses；
Described server carries out syntactic analysis process to described user's word content, sets up the language corresponding with described user
Model library；
Described server sets up the corresponding relation between described user totem information and described language model storehouse.
In conjunction with the first embodiment of first aspect, in the second embodiment of first aspect, described server
Described user's word content is carried out syntactic analysis process, sets up the language model storehouse corresponding with described user, specifically include:
Described server carries out word segmentation processing to described user's word content, obtains constituting described user's word content many
Individual user's participle information, and obtain user's part-of-speech information of each described participle information；
Described server obtains user's word frequency information of described each user's participle information；
User's part-of-speech information described in described server record and the grammatical relation between described user's word frequency information；
Described server, according to the described grammatical relation of record, sets up the language model storehouse corresponding with described user.
In conjunction with the second embodiment of first aspect, in the third embodiment of first aspect, described user's
Linguistic property information includes described user's part-of-speech information, described user's word frequency information and described user's part-of-speech information and described use
Grammatical relation between the word frequency information of family；
Described server is carried out according to the linguistic property information of described user, the content of text currently browsed described user
Conversion processing, generates the content of text with described linguistic property information matches, specifically includes:
The content of text that described user is currently browsed by described server carries out word segmentation processing, obtains multiple participle information,
And obtain the part-of-speech information of each described participle information；
Described server according to described user's part-of-speech information, described user's word frequency information and described user's part-of-speech information with
Grammatical relation between described user's word frequency information, reorders participle information corresponding for described part-of-speech information, generation
The content of text joined.
Second aspect, the embodiment of the present invention provides a kind of server, including:
Receiving unit, for receiving the content of text request that terminal sends, the request of described content of text includes ID
The content of text that information and described user currently browse；
Acquiring unit, for according to described user totem information, obtains the language mould corresponding with described user totem information
Type storehouse, described user language model library includes the linguistic property information of described user；
It is converted into unit, for the linguistic property information according to described user, the text that described user is currently browsed
Content carries out conversion processing, generates the content of text with described linguistic property information matches；
Transmitting element, for sending the described content of text generated, so that described terminal shows to described terminal.
In conjunction with second aspect, in the first embodiment of second aspect, described reception unit is additionally operable to, and receives described
The described user totem information of terminal transmission and user's word content, described user's word content is that described user is in described terminal
Middle input or described user browse；
Described server also includes: set up unit, for described user's word content is carried out syntactic analysis process, sets up
The language model storehouse corresponding with described user；
Described set up unit, be additionally operable to the corresponding pass setting up between described user totem information with described language model storehouse
System.
In conjunction with the first embodiment of second aspect, in the second embodiment of second aspect, described foundation is single
Unit specifically for, described user's word content is carried out word segmentation processing, obtains constituting multiple users of described user's word content
Participle information, and obtain user's part-of-speech information of each described participle information；
Obtain user's word frequency information of described each user's participle information；
Record the grammatical relation between described user's part-of-speech information and described user's word frequency information；
According to the described grammatical relation of record, set up the language model storehouse corresponding with described user.
In conjunction with the second embodiment of second aspect, in the third embodiment of second aspect, described acquisition is single
The linguistic property information of the described user that unit obtains includes described user's part-of-speech information, described user's word frequency information and described use
Grammatical relation between family part-of-speech information and described user's word frequency information；
Described be converted into unit specifically for, the content of text currently browsed described user carries out word segmentation processing,
To multiple participle information, and obtain the part-of-speech information of each described participle information；
According to described user's part-of-speech information, described user's word frequency information and described user's part-of-speech information and described user's word
Frequently the grammatical relation between information, reorders participle information corresponding for described part-of-speech information, generates in the text of coupling
Hold.
The third aspect, the embodiment of the present invention provides a kind of server, and described server includes: housing, processor, storage
Device, circuit board and power circuit, wherein, circuit board is placed in the interior volume that housing surrounds, processor and memorizer and is arranged on
On circuit board；Power circuit, powers for each circuit or the device for above-mentioned electronic equipment；Memorizer is used for storing and can perform
Program code；Processor runs corresponding with executable program code by reading the executable program code of storage in memorizer
Program, aforementioned arbitrary described for performing.
A kind of content of text that the embodiment of the present invention provides generates method and server, and server receives the literary composition that terminal sends
This content requests, asks the user totem information carried, obtains the language mould corresponding with user totem information according to content of text
Type storehouse, according to the linguistic property information of the user that language model storehouse includes, carries out conversion processing, generates and language content of text
The content of text of speech attribute information coupling, sends the content of text generated, so that content of text is shown by terminal to terminal
Show.Can solve the problem that in prior art, the describing mode of author does not meets the reading habit of reader so that reader cannot be fast
Speed gets the information of needs, wastes reader's time, reduces the problem that reader experiences.Achieving server can be according to user
Language model storehouse, the content of text currently browsed user changes, and generates and is suitable for the content of text that user reads so that
User can quick obtaining information needed, save user time.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to
Other accompanying drawing is obtained according to these accompanying drawings.
Fig. 1 generates the flow chart of method for a kind of content of text that the embodiment of the present invention provides；
Fig. 2 generates the flow chart of method for the another kind of content of text that the embodiment of the present invention provides；
A kind of server architecture schematic diagram that Fig. 3 provides for the embodiment of the present invention；
The another kind of server architecture schematic diagram that Fig. 4 provides for the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings the embodiment of the present invention is described in detail.
It will be appreciated that described embodiment be only the present invention a part of embodiment rather than whole embodiments.Base
Embodiment in the present invention, those of ordinary skill in the art obtained under not making creative work premise all its
Its embodiment, broadly falls into the scope of protection of the invention.
Below in conjunction with the accompanying drawings 1, the scheme that describing the embodiment of the present invention in detail provides illustrates, and Fig. 1 is that the present invention implements
A kind of content of text that example provides generates the flow chart of method, and subject of implementation is server in embodiments of the present invention.Such as Fig. 1 institute
Showing, the method that the embodiment of the present invention provides specifically includes following steps:
Step 110, server receive the content of text request that terminal sends, and the request of described content of text includes ID
The content of text that information and described user currently browse.
In the embodiment of the present invention, user browses webpage by terminal, selects the article on webpage or headline
Selecting property is read.When user selects article or the headline that expectation is read, this title is clicked on by user, and entering should
The content of text that title is corresponding.Terminal receives the clicking operation of user's input, and obtains content of text.
It is understood that terminal can also obtain the link information of content of text, obtain correspondence by this link information
Content of text.This link information is specially the link address information of content of text.
Terminal generates content of text request, includes what user totem information and user currently browsed in text request
The link information of content of text.Wherein, terminal can be to have to browse webpage, the smart mobile phone of read function, panel computer, individual
The electronic equipment such as computer, desktop computer.
In embodiments of the present invention, the identification information of available terminal is as user totem information, and the identification information of terminal can
The most uniquely characterizing the information of terminal, such as, when terminal is smart mobile phone, the identification information of terminal can be specially IMEI.
Terminal to server sends text content requests.
Step 120, described server, according to described user totem information, obtain the language corresponding with described user totem information
Speech model library, described user language model library includes the linguistic property information of described user.
In the embodiment of the present invention, after server obtains content of text request, from content of text is asked, obtain ID
Information and the link information of content of text currently browsed.
According to user totem information, server obtains the language model storehouse corresponding with this user totem information, this user's language
Speech model library includes the linguistic property information of this user.
Further, the linguistic property information of user includes user's part-of-speech information, user's word frequency information and user's part of speech
Grammatical relation between information and user's word frequency information.
Step 130, described server are according to the linguistic property information of described user, the text currently browsed described user
Content carries out conversion processing, generates the content of text with described linguistic property information matches.
In the embodiment of the present invention, first server obtains the content of text that user currently browses from content of text is asked；
Or, after first server obtains the link information of the content of text that user currently browses from content of text is asked, according to this
Link information, obtains the content of text that the user corresponding with link information currently browses；Server is further according to from user language mould
The linguistic property information obtained in type storehouse, the content of text currently browsed user carries out conversion process, generates and linguistic property
The content of text of information matches.
Further, the content of text that user is currently browsed by server carries out word segmentation processing, obtains multiple participle information
Part-of-speech information, and obtain the part-of-speech information of each participle information；Server according to user's part-of-speech information, user's word frequency information with
And the grammatical relation between user's part-of-speech information and user's word frequency information, participle information corresponding for part-of-speech information is reset
Sequence, generates the content of text of coupling.
Step 140, described server send the described content of text generated to described terminal, so that described terminal is carried out
Display.
In the embodiment of the present invention, after server generates the content of text with linguistic property information matches, sending to terminal should
Content of text, text content is shown by terminal, to facilitate user to read.
In the embodiment of the present invention, server receives the content of text request that terminal sends, and carries according to content of text request
User totem information, obtain the language model storehouse corresponding with user totem information, the user included according to language model storehouse
Linguistic property information, content of text is carried out conversion processing, generates the content of text with linguistic property information matches, to terminal
Send the content of text generated, so that content of text is shown by terminal.Can solve the problem that retouching of author in prior art
The mode of stating does not meets the reading habit of reader so that reader cannot quick obtaining to need information, waste reader time
Between, reduce the problem that reader experiences.Achieving server can be according to the language model storehouse of user, the literary composition currently browsed user
This content is changed, generate be suitable for user read content of text so that user can quick obtaining information needed, save user
Time, improve Consumer's Experience.
Below in conjunction with the accompanying drawings 2, the scheme that describing the embodiment of the present invention in detail provides illustrates, and Fig. 2 is that the present invention implements
The another kind of content of text that example provides generates the flow chart of method, and subject of implementation is server in embodiments of the present invention.Such as Fig. 2
Shown in, the method that the embodiment of the present invention provides specifically includes following steps:
Step 210, server receive described user totem information and user's word content, the described use that described terminal sends
Family word content is that described user inputs in described terminal or described user browses.
In the embodiment of the present invention, user A inputs word content by terminal, and the word content of input is that user A is daily
The language mode of custom in life；Or, user A browses word content by terminal.
In one example, user A have input " you are liked by me " word content by terminal.
Terminal collects the word content of user A input, and sends user's word content and user totem information to server,
Server receives above two information, and stores.
It is understood that terminal can be using the identification information of self as user totem information.This user totem information is used
It is marked in the user's word content making server that terminal to be sent, to determine user.
Step 220, described server carry out syntactic analysis process to described user's word content, set up and described user couple
The language model storehouse answered.
In the embodiment of the present invention, server carries out word segmentation processing to user's word content, obtains constituting user's word content
Multiple user's participle information, and obtain user's part-of-speech information of each participle information；Server obtains each user's participle letter
User's word frequency information of breath；Grammatical relation between server record user's part-of-speech information and user's word frequency information；Server root
According to the grammatical relation of record, set up the language model storehouse corresponding with user.
Wherein, non-limiting as example, server can use Stanford Parser software tool in user's word
Hold and carry out syntactic analysis process.In actual applications, it is possible to use Ikanalyzer, ICTCLAS, MMSEG, CRF, THULAC etc.
Software tool carries out the process of syntactic analysis, does not limit at this.
In the embodiment of the present invention, illustrate as a example by Stanford Parser software tool.
According to the example in step 210, server passes through Stanford Parser software tool to user's word content
" you are liked by me " carries out word segmentation processing, obtains 4 participle information, is " you ", " quilt ", " I ", " liking " respectively, obtains meanwhile
Take user's part-of-speech information of each participle information, such as: " you " be pronoun (PN), " quilt " be pronoun by verb (LB), " I "
(PN), " liking " is predicate adjective (VA).
Wherein, the part-of-speech information of this participle of letter representation such as PN, LB, set voluntarily for Stanford Parser software tool
Fixed.
Server obtains user's word frequency information of each user's participle information.In the above example, each user's participle letter
Breath all occurs once, and therefore, user's word frequency information of each user's participle information is 1.
Grammatical relation between server record user's part-of-speech information and user's word frequency information, i.e. records each user's part of speech
The number of times that information occurs；Server, according to the grammatical relation of record, sets up the language model storehouse corresponding with user.
Running that Stanford Parser software tool concrete is given below.
Step 230, described server set up the corresponding relation between described user totem information and described language model storehouse.
In the embodiment of the present invention, after server sets up language model storehouse, by step 210 obtain user totem information with
Corresponding relation is set up in language model storehouse, to determine the language model storehouse that this language model storehouse is this user A.
In like manner, server be user B, user C set up corresponding language model storehouse.
Step 240, server receive the content of text request that terminal sends, and the request of described content of text includes ID
The content of text that information and described user currently browse.
In the embodiment of the present invention, server receives process and the said method embodiment of the content of text request that terminal sends
Step 110 be similar to, here is omitted.
According to previous example, the content of text request that server receives includes user totem information and the user A of user A
The content of text currently browsed.
Step 250, described server, according to described user totem information, obtain the language corresponding with described user totem information
Speech model library, described user language model library includes the linguistic property information of described user.
In the embodiment of the present invention, server, according to described user totem information, obtains corresponding with described user totem information
The process in language model storehouse similar with the step 120 of said method embodiment, here is omitted.
According to previous example, server, according to the user totem information of user A, obtains the language model corresponding with user A
Storehouse, that is to say the language model storehouse set up in abovementioned steps 220.
Step 260, described server are according to the linguistic property information of described user, the text currently browsed described user
Content carries out conversion processing, generates the content of text with described linguistic property information matches.
In the embodiment of the present invention, server is according to the linguistic property information of user, the content of text currently browsed user
Carry out conversion processing, the process of the content of text of generation and linguistic property information matches and the step 130 of said method embodiment
Similar, here is omitted.
In this step, the content of text that user currently browses specially " made known in the news conference of today and newly set by XX
Standby ".
According to previous example, server passes through in the text that user is currently browsed by Stanford Parser software tool
Hold " XX made known in the news conference of today new equipment " and carry out word segmentation processing, obtain 10 participle information, be respectively " XX ",
" ", " today ", " ", " issue ", " can go up ", " making known ", " ", " newly ", " equipment ", meanwhile, obtain each participle information
User's part-of-speech information, as: " XX " be pronoun (PN), " " be prepositional phrase (P), " today " be time noun (NT), " "
It is to constitute to represent that the phrase (DEG) of belonging relation, " issue " are that major terms (NN), " can go up " are major terms (NN), " take off
Dawn " be verb (VV), " " be content-label (AS), " newly " be adjective or ordinal number (JJ), " equipment " be major terms
(NN)。
Server is according to the user's part-of-speech information obtained in the language model storehouse set up in step 220, user's word frequency information
And the grammatical relation between user's part-of-speech information and user's word frequency information, by 10 corresponding for above-mentioned 10 part-of-speech information participles
Information reorders, and generates the content of text of coupling.
If the content of text of: generation is particularly as follows: " new equipment is announced by XX in the news conference of today ".
Running that Stanford Parser software tool concrete is given below.
Step 270, described server send the described content of text generated to described terminal, so that described terminal is carried out
Display.
In the embodiment of the present invention, server sends the content of text generated to terminal, and terminal carries out the process that shows and upper
The step 140 stating embodiment of the method is similar to, and here is omitted.
According to previous example, the content of text " new equipment is announced by XX in the news conference of today " generated is sent out by server
Delivering to terminal, terminal shows, to facilitate user to read.
It is understood that previous embodiment only illustrates with simple sentence, in actual applications, can be by above-mentioned step
Suddenly article or news are changed accordingly, to facilitate user that article or news are read so that user can quickly obtain
Take information needed, save user time, improve Consumer's Experience.
In one example, the news that user is read by server is changed accordingly.
The content of news is that " some areas high temperature, rainstorm weather alternately, have impact on production and the transport of fresh vegetable, fresh vegetable valency
Lattice ring, than rise 6.8%, affects CPI and goes up 0.21 percentage point ".The content of this news can be automatically generated by the equipment of writing.
According to the description of step 240-step 260, server carries out word segmentation processing to the content of text of above-mentioned news, obtains
The part-of-speech information of multiple participle information, and obtain the part-of-speech information of each participle information；Server is according to user's part-of-speech information, use
Grammatical relation between family word frequency information and user's part-of-speech information and user's word frequency information, by participle letter corresponding for part-of-speech information
Breath reorders, and generates the content of text of coupling.
The content of text generated is that " production of fresh vegetable and transport are by some areas high temperature, rainstorm weather alternately impact, fresh vegetable
Price chain rate rise 6.8%, CPI, by fresh vegetable price chain rate rise 6.8% impact, goes up 0.21 percentage point.”
Due to this, to be converted into process similar with the process that previous embodiment describes, and no longer repeats at this.
A kind of content of text that the embodiment of the present invention provides generates method and server, and server receives the literary composition that terminal sends
This content requests, asks the user totem information carried, obtains the language mould corresponding with user totem information according to content of text
Type storehouse, according to the linguistic property information of the user that language model storehouse includes, carries out conversion processing, generates and language content of text
The content of text of speech attribute information coupling, sends the content of text generated, so that content of text is shown by terminal to terminal
Show.Can solve the problem that in prior art, the describing mode of author does not meets the reading habit of reader so that reader cannot be fast
Speed gets the information of needs, wastes reader's time, reduces the problem that reader experiences.Achieving server can be according to user
Language model storehouse, the content of text currently browsed user changes, and generates and is suitable for the content of text that user reads so that
User can quick obtaining information needed, save user time, improve Consumer's Experience.
A kind of server architecture schematic diagram that Fig. 3 provides for the embodiment of the present invention, as it is shown on figure 3, the embodiment of the present invention carries
The server of confession may include that reception unit 310, acquiring unit 320, is converted into unit 330 and transmitting element 340.
Wherein, described reception unit 310, for receiving the content of text request that terminal sends, described content of text is asked
The content of text currently browsed including user totem information and described user；
Acquiring unit 320, for according to described user totem information, obtains the language corresponding with described user totem information
Model library, described user language model library includes the linguistic property information of described user；
It is converted into unit 330, for the linguistic property information according to described user, the literary composition that described user is currently browsed
This content carries out conversion processing, generates the content of text with described linguistic property information matches；
Transmitting element 340, for sending the described content of text generated, so that described terminal shows to described terminal
Show.
Further, described reception unit 310 is additionally operable to, and receives described user totem information and use that described terminal sends
Family word content, described user's word content is that described user inputs in described terminal or described user browses；
Described server also includes: set up unit 350, for described user's word content is carried out syntactic analysis process,
Set up the language model storehouse corresponding with described user；
Described setting up unit 350, be additionally operable to set up between described user totem information with described language model storehouse is corresponding
Relation.
Further, described set up unit 350 specifically for, described user's word content is carried out word segmentation processing, obtains
Constitute multiple user's participle information of described user's word content, and obtain user's part-of-speech information of each described participle information；
Obtain user's word frequency information of described each user's participle information；
Record the grammatical relation between described user's part-of-speech information and described user's word frequency information；
According to the described grammatical relation of record, set up the language model storehouse corresponding with described user.
Further, the linguistic property information of the described user that described acquiring unit 320 obtains includes described user's part of speech
Grammatical relation between information, described user's word frequency information and described user's part-of-speech information and described user's word frequency information；
Described be converted into unit 330 specifically for, the content of text currently browsed described user carries out word segmentation processing,
Obtain multiple participle information, and obtain the part-of-speech information of each described participle information；
According to described user's part-of-speech information, described user's word frequency information and described user's part-of-speech information and described user's word
Frequently the grammatical relation between information, reorders participle information corresponding for described part-of-speech information, generates in the text of coupling
Hold.
The device that the embodiment of the present invention provides, may be used for performing the technical scheme of embodiment of the method shown in Fig. 1, Fig. 2, its
Realizing principle similar with technique effect, here is omitted.
Correspondingly, a kind of server that the embodiment of the present invention provides can also be used with another kind of structure and realizes.Fig. 4 is that the present invention takes
The structural representation of business another embodiment of device, it is possible to achieve the flow process of Fig. 1-2 illustrated embodiment of the present invention, as shown in Figure 4, on
State server and may include that housing 41, processor 42, memorizer 43, circuit board 44 and power circuit 45, wherein, circuit board 44
It is placed in the interior volume that housing 41 surrounds, processor 42 and memorizer 43 to be arranged on circuit board 44；Power circuit 45, is used for
Each circuit or device for above-mentioned server are powered；Memorizer 43 is used for storing executable program code；Processor 42 passes through
Read the executable program code of storage in memorizer 43 and run the program corresponding with executable program code, before performing
State the method described in embodiment.
Processor 42 to concrete process and the processor 42 of performing of above-mentioned steps by running executable program code
The step performed further, may refer to the description of Fig. 1-2 illustrated embodiment of the present invention, does not repeats them here.
This server: providing the equipment of the service of calculating, the composition of server includes processor, hard disk, internal memory, system bus
Deng, server is similar with general computer architecture, but owing to needing to provide highly reliable service, therefore disposal ability,
The aspects such as stability, reliability, safety, extensibility, manageability require higher.
It should be noted that in this article, such as term " includes ", " comprising " or its any other variant are intended to
Comprising of nonexcludability, so that include that the process of a series of key element, method, article or equipment not only include that those are wanted
Element, but also include other key elements being not expressly set out, or also include for this process, method, article or equipment
Intrinsic key element.In the case of there is no more restriction, statement " including ... " key element limited, it is not excluded that
Including process, method, article or the equipment of described key element there is also other identical element.
Each embodiment in this specification all uses relevant mode to describe, identical similar portion between each embodiment
Dividing and see mutually, what each embodiment stressed is the difference with other embodiments.
For device embodiment, owing to it is substantially similar to embodiment of the method, so the comparison described is simple
Single, relevant part sees the part of embodiment of the method and illustrates.
Represent in flow charts or the logic described otherwise above at this and/or step, for example, it is possible to be considered as to use
In the sequencing list of the executable instruction realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (system such as computer based system, including processor or other can hold from instruction
Row system, device or equipment instruction fetch also perform the system instructed) use, or combine these instruction execution systems, device or set
Standby and use.For the purpose of this specification, " computer-readable medium " can be any can to comprise, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or combines these instruction execution systems, device or equipment and the dress that uses
Put.
The more specifically example (non-exhaustive list) of computer-readable medium includes following: have one or more wiring
Electrical connection section (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read only memory
(ROM), erasable read only memory (EPROM or flash memory), the fiber device edited, and portable optic disk is read-only deposits
Reservoir (CDROM).It addition, computer-readable medium can even is that and can print the paper of described program thereon or other are suitable
Medium, because then can carry out editing, interpreting or if desired with it such as by paper or other media are carried out optical scanning
His suitable method is processed to electronically obtain described program, is then stored in computer storage.
Should be appreciated that each several part of the present invention can realize by hardware, software, firmware or combinations thereof.
In the above-described embodiment, multiple steps or method can be with storing in memory and by suitably instructing execution
Software or firmware that system performs realize.Such as, if realized with hardware, with the most the same, available
Any one or their combination in following technology well known in the art realize: have for data signal realizes logic merit
The discrete logic of the logic gates of energy, has the special IC of suitable combination logic gate circuit, programmable gate
Array (PGA), field programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that and realize all or part of step that above-described embodiment method is carried
Suddenly the program that can be by completes to instruct relevant hardware, and described program can be stored in a kind of computer-readable storage medium
In matter, this program upon execution, including one or a combination set of the step of embodiment of the method.
For convenience of description, describing apparatus above is to be divided into various units/modules to be respectively described with function.Certainly, exist
Implement the function of each unit/module to be realized in same or multiple softwares and/or hardware during the present invention.
As seen through the above description of the embodiments, those skilled in the art it can be understood that to the present invention can
The mode adding required general hardware platform by software realizes.Based on such understanding, technical scheme essence
On the part that in other words prior art contributed can embody with the form of software product, this computer software product
Can be stored in storage medium, such as ROM/RAM, magnetic disc, CD etc., including some instructions with so that a computer equipment
(can be personal computer, server, or the network equipment etc.) performs some of each embodiment of the present invention or embodiment
Method described in part.
Claims (9)
1. a content of text generates method, it is characterised in that including:
Server receives the content of text request that terminal sends, and the request of described content of text includes user totem information and described
The content of text that user currently browses；
Described server, according to described user totem information, obtains the language model storehouse corresponding with described user totem information, institute
State user language model library and include the linguistic property information of described user；
Described server converts according to the linguistic property information of described user, the content of text currently browsed described user
Process, generate the content of text with described linguistic property information matches；
Described server sends the described content of text generated to described terminal, so that described terminal shows.
Method the most according to claim 1, it is characterised in that described server receives the content of text request that terminal sends
Before, described method includes:
Server receives described user totem information and the user's word content that described terminal sends, and described user's word content is
Described user inputs in described terminal or described user browses；
Described server carries out syntactic analysis process to described user's word content, sets up the language model corresponding with described user
Storehouse；
Described server sets up the corresponding relation between described user totem information and described language model storehouse.
Method the most according to claim 2, it is characterised in that described server carries out grammer to described user's word content
Analyzing and processing, sets up the language model storehouse corresponding with described user, specifically includes:
Described server carries out word segmentation processing to described user's word content, obtains constituting multiple use of described user's word content
Family participle information, and obtain user's part-of-speech information of each described participle information；
Described server obtains user's word frequency information of described each user's participle information；
User's part-of-speech information described in described server record and the grammatical relation between described user's word frequency information；
Described server, according to the described grammatical relation of record, sets up the language model storehouse corresponding with described user.
Method the most according to claim 3, it is characterised in that the linguistic property information of described user includes described user's word
Property information, grammatical relation between described user's word frequency information and described user's part-of-speech information and described user's word frequency information；
Described server converts according to the linguistic property information of described user, the content of text currently browsed described user
Process, generate the content of text with described linguistic property information matches, specifically include:
The content of text that described user is currently browsed by described server carries out word segmentation processing, obtains multiple participle information, and obtains
Take the part-of-speech information of each described participle information；
Described server according to described user's part-of-speech information, described user's word frequency information and described user's part-of-speech information with described
Grammatical relation between user's word frequency information, reorders participle information corresponding for described part-of-speech information, generates coupling
Content of text.
5. a server, it is characterised in that including:
Receiving unit, for receiving the content of text request that terminal sends, the request of described content of text includes user totem information
And the content of text that described user currently browses；
Acquiring unit, for according to described user totem information, obtains the language model storehouse corresponding with described user totem information,
Described user language model library includes the linguistic property information of described user；
It is converted into unit, for the linguistic property information according to described user, the content of text that described user is currently browsed
Carry out conversion processing, generate the content of text with described linguistic property information matches；
Transmitting element, for sending the described content of text generated, so that described terminal shows to described terminal.
Server the most according to claim 5, it is characterised in that described reception unit is additionally operable to, receives described terminal and sends out
The described user totem information sent and user's word content, described user's word content is that described user inputs in described terminal
Or described user browses；
Described server also includes: set up unit, for described user's word content carries out syntactic analysis process, sets up and institute
State the language model storehouse that user is corresponding；
Described set up unit, be additionally operable to set up the corresponding relation between described user totem information and described language model storehouse.
Server the most according to claim 6, it is characterised in that described set up unit specifically for, to described user literary composition
Word content carries out word segmentation processing, obtains constituting multiple user's participle information of described user's word content, and obtains each described
User's part-of-speech information of participle information；
Obtain user's word frequency information of described each user's participle information；
Record the grammatical relation between described user's part-of-speech information and described user's word frequency information；
According to the described grammatical relation of record, set up the language model storehouse corresponding with described user.
Server the most according to claim 7, it is characterised in that the language of the described user that described acquiring unit obtains belongs to
Property information include described user's part-of-speech information, described user's word frequency information and described user's part-of-speech information and described user's word frequency
Grammatical relation between information；
Described be converted into unit specifically for, the content of text currently browsed described user carries out word segmentation processing, obtains many
Individual participle information, and obtain the part-of-speech information of each described participle information；
Believe with described user's word frequency according to described user's part-of-speech information, described user's word frequency information and described user's part-of-speech information
Grammatical relation between breath, reorders participle information corresponding for described part-of-speech information, generates the content of text of coupling.
9. a server, it is characterised in that described server includes: housing, processor, memorizer, circuit board and power supply electricity
Road, wherein, circuit board is placed in the interior volume that housing surrounds, processor and memorizer and arranges on circuit boards；Power circuit,
For powering for each circuit of above-mentioned electronic equipment or device；Memorizer is used for storing executable program code；Processor leads to
Cross the executable program code of storage in reading memorizer and run the program corresponding with executable program code, before performing
State described in any claim 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610443679.0A CN106095742A (en) | 2016-06-20 | 2016-06-20 | Text content generation method and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610443679.0A CN106095742A (en) | 2016-06-20 | 2016-06-20 | Text content generation method and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106095742A true CN106095742A (en) | 2016-11-09 |
Family
ID=57238801
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610443679.0A Pending CN106095742A (en) | 2016-06-20 | 2016-06-20 | Text content generation method and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106095742A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108052494A (en) * | 2017-12-28 | 2018-05-18 | 掌阅科技股份有限公司 | Comic books generation method, electronic equipment and computer storage media |
| CN108122555A (en) * | 2017-12-18 | 2018-06-05 | 北京百度网讯科技有限公司 | The means of communication, speech recognition apparatus and terminal device |
| 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 |
| WO2020088464A1 (en) * | 2018-10-31 | 2020-05-07 | 中兴通讯股份有限公司 | Rcs public message processing method, mobile terminal, and readable storage medium |
| CN111767712A (en) * | 2019-04-02 | 2020-10-13 | 北京地平线机器人技术研发有限公司 | Business data screening method and device based on language model, medium and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030187829A1 (en) * | 2002-03-28 | 2003-10-02 | Matsushita Electric Industrial Co., Ltd. | Content retrieval apparatus and method |
| CN101470700A (en) * | 2007-12-28 | 2009-07-01 | 日电（中国）有限公司 | Text template generator, text generation equipment, text checking equipment and method thereof |
| CN101499056A (en) * | 2008-01-28 | 2009-08-05 | 徐文新 | Backward reference sentence pattern language analysis method |
| CN102455998A (en) * | 2010-10-27 | 2012-05-16 | 王博 | Method and apparatus for filtering text information |
| CN103955454A (en) * | 2014-03-19 | 2014-07-30 | 北京百度网讯科技有限公司 | Method and equipment for carrying out literary form conversion between vernacular Chinese and classical Chinese |
-
2016
- 2016-06-20 CN CN201610443679.0A patent/CN106095742A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030187829A1 (en) * | 2002-03-28 | 2003-10-02 | Matsushita Electric Industrial Co., Ltd. | Content retrieval apparatus and method |
| CN101470700A (en) * | 2007-12-28 | 2009-07-01 | 日电（中国）有限公司 | Text template generator, text generation equipment, text checking equipment and method thereof |
| CN101499056A (en) * | 2008-01-28 | 2009-08-05 | 徐文新 | Backward reference sentence pattern language analysis method |
| CN102455998A (en) * | 2010-10-27 | 2012-05-16 | 王博 | Method and apparatus for filtering text information |
| CN103955454A (en) * | 2014-03-19 | 2014-07-30 | 北京百度网讯科技有限公司 | Method and equipment for carrying out literary form conversion between vernacular Chinese and classical Chinese |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122555A (en) * | 2017-12-18 | 2018-06-05 | 北京百度网讯科技有限公司 | The means of communication, speech recognition apparatus and terminal device |
| 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 |
| 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 |
| CN108052494A (en) * | 2017-12-28 | 2018-05-18 | 掌阅科技股份有限公司 | Comic books generation method, electronic equipment and computer storage media |
| CN108052494B (en) * | 2017-12-28 | 2021-09-14 | 掌阅科技股份有限公司 | Cartoon book generation method, electronic device and computer storage medium |
| WO2020088464A1 (en) * | 2018-10-31 | 2020-05-07 | 中兴通讯股份有限公司 | Rcs public message processing method, mobile terminal, and readable storage medium |
| CN111767712A (en) * | 2019-04-02 | 2020-10-13 | 北京地平线机器人技术研发有限公司 | Business data screening method and device based on language model, medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106095742A (en) | Text content generation method and server | |
| McArthur et al. | The roles of artificial intelligence in education: current progress and future prospects | |
| CN100371927C (en) | System for identifying paraphrases using machine translation techniques | |
| Farrelly | Rethinking intertextuality in CDA | |
| Mankoff et al. | Some Computer Science Issues in Creating a Sustainable World. | |
| Tian et al. | The blue stragglers formed via mass transfer in old open clusters | |
| Nikitin | Large deviations of U-empirical Kolmogorov–Smirnov tests and their efficiency | |
| WO2011066456A2 (en) | Methods and systems for content recommendation based on electronic document annotation | |
| US9514113B1 (en) | Methods for automatic footnote generation | |
| CN103020295A (en) | Problem label marking method and device | |
| CN104268192A (en) | Webpage information extracting method, device and terminal | |
| JP2019149161A (en) | Method for generating word expression, device, and computer-readable storage medium | |
| CN105550354A (en) | Configuration file management method and system | |
| Wang et al. | The evolution of digital humanities in China | |
| Kaur et al. | Semantic-based integrated plagiarism detection approach for english documents | |
| CN106126485A (en) | Text format generation method, server and terminal | |
| Mak | System dynamics and discrete event simulation modelling. | |
| Trilling | Doing computational social science with python: An introduction | |
| CN103164462A (en) | Method and system for downloading patent literature | |
| Choi | Knowledge is power: Symbolic knowledge distillation, commonsense morality, & multimodal script knowledge | |
| CN112307530B (en) | Method and device for framing book of child books based on big data | |
| KR102531310B1 (en) | Web based spreadsheets service providing apparatus and method | |
| CN110580332A (en) | method, system, electronic device and storage medium for automatically writing product information | |
| Rajagopal et al. | Online news popularity prediction before publication: effect of readability, emotion, psycholinguistics features | |
| Baek et al. | Towards Recovering Fault Traceability Links by Using Information Retrieval Technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190117 Address after: 519031 Room 105-53811, No. 6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province Applicant after: Zhuhai Leopard Technology Co.,Ltd. Address before: 100085 East District, No. 33 Xiaoying West Road, Haidian District, Beijing Applicant before: BEIJING KINGSOFT INTERNET SECURITY SOFTWARE Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |