CN108846098A - A kind of information flow summarization generation and methods of exhibiting - Google Patents
A kind of information flow summarization generation and methods of exhibiting Download PDFInfo
- Publication number
- CN108846098A CN108846098A CN201810622659.9A CN201810622659A CN108846098A CN 108846098 A CN108846098 A CN 108846098A CN 201810622659 A CN201810622659 A CN 201810622659A CN 108846098 A CN108846098 A CN 108846098A
- Authority
- CN
- China
- Prior art keywords
- information flow
- text
- abstract
- sample
- vectorization
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
This application provides a kind of information flow summarization generation and methods of exhibiting, and the method includes obtaining the information flow summarization generation instruction of user's input;Information flow is obtained according to the information flow digest instructions;The information flow is pre-processed, information flow text is obtained;It is made a summary according to the summarization generation model pre-established based on the information flow text generation information flow;Information flow abstract is saved as into data object with the information flow, and shows the information flow abstract, so that the user checks the information flow abstract.By herein described method, emphasis abstract is generated to the content in information flow, user is avoided to the access one by one of all information stream, facilitates user to retrieve the abstract and check corresponding information flow, saved the time, improved efficiency.
Description
【Technical field】
This application involves internet application field more particularly to a kind of information flow summarization generations and methods of exhibiting.
【Background technique】
In today's society, the use of instant messaging product and/or social category product in work and life is quite general
And change, users are higher and higher to the utilization rate and dependence of these products.
A large amount of historical information stream is produced in the use process of instant messaging product and/or social category product, and it is very much
Historical information stream all has important value or purposes, such as dialog information stream and media sharing (such as circle of friends) information
Stream.User wants to consult these information flows at any time in use.But current product cannot effectively meet user with
When consult the demands of these information flows, user can only browse in detail whole historical information streams.Also, the information flow packet
Content of text and/or non-textual content are included, non-textual content can not be retrieved.
【Summary of the invention】
The many aspects of the application provide a kind of information flow summarization generation and methods of exhibiting, for improving looking into for information record
Ask efficiency and accuracy rate.
The one side of the application provides a kind of information flow summarization generation and methods of exhibiting, is applied to client, including:It obtains
Take the information flow summarization generation instruction of family input;Information flow is obtained according to the information flow digest instructions;To the information flow
It is pre-processed, obtains information flow text;Believed according to the summarization generation model pre-established based on the information flow text generation
Breath stream abstract;Information flow abstract is saved as into data object with the information flow, and shows the information flow abstract, so as to
The user checks the information flow abstract.
The another aspect of the application provides a kind of information flow summarization generation and methods of exhibiting, is applied to client, including:
Obtain the information flow summarization generation instruction of user's input;Information flow is obtained according to the information flow digest instructions;It is sent out to server
The information flow is sent, so that the server pre-processes the information flow, obtains information flow text, and according to building in advance
Vertical summarization generation model is made a summary based on the information flow text generation information flow;It is received from the server and shows the letter
Breath stream abstract, so that the user checks the information flow abstract.
The another aspect of the application provides a kind of information flow summarization generation and methods of exhibiting, is applied to server, including:
Information flow is received from client;The information flow is pre-processed, information flow text is obtained;It is raw according to the abstract pre-established
It is made a summary at model based on the information flow text generation information flow;The information flow abstract is sent to the client, with toilet
It states client to receive and show the information flow abstract, checks that the information flow is made a summary by user.
The another aspect of the application provides a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes any above-mentioned method.
The another aspect of the application provides a kind of computer readable storage medium, is stored thereon with computer program, special
Sign is that the program realizes any above-mentioned method when being executed by processor.
By the technical solution it is found that by the embodiment of the present application, emphasis abstract is generated to the content in information flow, is avoided
One by one access of the user to all information stream, facilitates user to retrieve the abstract and checks corresponding information flow, saves
About the time, improve efficiency.
【Detailed description of the invention】
Attached drawing needed in describing below to embodiment is briefly described, it should be apparent that, it retouches below
Attached drawing in stating is some embodiments of the present application, for those of ordinary skill in the art, is not being made the creative labor
Under the premise of property, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram of a kind of information flow summarization generation that the embodiment of the present application one provides and methods of exhibiting;
Fig. 2 is the flow diagram of a kind of information flow summarization generation that the embodiment of the present application two provides and methods of exhibiting;
Fig. 3 is the block diagram suitable for being used to realize the exemplary computer system/server of the embodiment of the present application.
【Specific embodiment】
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on this Shen
Please in embodiment, whole obtained by those of ordinary skill in the art without making creative efforts other implementation
Example, shall fall in the protection scope of this application.
In addition, the terms "and/or", only a kind of incidence relation for describing affiliated partner, indicates may exist
Three kinds of relationships, for example, A and/or B, can indicate:Individualism A exists simultaneously A and B, these three situations of individualism B.Separately
Outside, character "/" herein typicallys represent the relationship that forward-backward correlation object is a kind of "or".
Fig. 1 is the flow diagram of a kind of information flow summarization generation that the embodiment of the present application one provides and methods of exhibiting, is answered
For client, as shown in Figure 1, including the following steps S11-S15:
Step S11, client obtains the information flow summarization generation instruction of user's input.
For example, user issues information by clicking the information flow summarization generation button or actions menu that are arranged in client
Flow summarization generation instruction.
Specifically, the client can be immediate communication tool client, social tool client, e-mail tool client
End, document tool client etc..According to the difference of the client, the information flow, which can be, utilizes instant messaging between user
Instrument client terminal carries out the chat record content of chat generation;It is also possible to user using the interior of social tool Client browse
Hold, such as blog, circle of friends;It is also possible to the mail that user utilizes the transmitting-receiving of e-mail tool client;It can also be user using text
The history archive etc. of shelves instrument client terminal operation.
In the present embodiment, it is described so that the client is immediate communication tool client as an example.
Illustratively, the information flow includes content of text and/or non-textual content;The non-textual content includes audio
File and/or video file.
In one example, the information flow summarization generation, which instructs, includes:Information flow writing abstract;Information flow range etc..
Wherein, information flow writing abstract may include pandect, simplify abstract.
Wherein, the pandect, which refers to, carries out summarization generation to all information stream;The abstract of simplifying refers to information
Audio/video information in stream only retains " audio " and/or " video " title without conversion.The user as belonging to client sets
Therefore standby computing capability and battery limited can be carried out simplifying summarization generation work by client;It is carried out by server comprehensive
Summarization generation work.
In the present embodiment, by taking the information flow writing abstract is to simplify writing abstract as an example.The information flow summarization generation
Instruction is simplifies digest instructions, by the typonym of the non-textual content in information flow together with content of text, as corresponding
Information flow text.
The information flow range refers to the range for generating information flow abstract.The information flow range can be all information
Stream, such as all information stream that user generates;Alternatively, the information flow range can be the selected partial information stream of user,
Such as one or more chat record that user selects in the chat record window of immediate communication tool client.
Further, the information flow summarization generation instruction can also include the frequency for generating information flow abstract, so as to fixed
Phase, for example, per hour, daily, being generated to all information stream that user is generated in using immediate communication tool client process
Abstract.
Step S12, client obtains information flow according to the information flow digest instructions.
For example, client obtains information flow by preset interface.
In one example, client obtains the range specified in information flow digest instructions by built-in preset interface
Information flow.In general, chat record is stored in client local, client is in the information flow for locally searching specified range
It can.
Step S13, client pre-processes the information flow, obtains information flow text.
In the present embodiment, it is described so that information flow abstract is to simplify abstract as an example.In the mode for simplifying abstract, due to
It may include non-textual content in information flow, it is therefore desirable to handle non-textual content, in order to subsequent summarization generation behaviour
Make.
For example, the audio/video information in information flow is replaced with " audio ", " video " title, for example, with " audio+information
Stream generates the time ", the form of " video+information flow generate time ", collectively constitute text file with the content of text in information flow.
Specifically, each information flow text may include User ID, content of text, can also include corresponding information flow
Generate the time.If the information flow is chat record content, the information flow text can also include the user of chatting object
ID。
Step S14, client is based on the information flow text generation information flow according to the summarization generation model pre-established
Abstract.
In one example, step S14 may include following sub-step A and B:
Sub-step A, the information flow text is divided into one or more information flow group of text.
In a kind of implementation of sub-step A, the theme and/or intention of the information flow text are analyzed, by the letter
Breath stream text is divided into one or more information flow group of text.
Specifically, it is determined that in the information flow text each information flow text theme and/or intention;Judge adjacent two
The theme of bar information flow text and/or be intended to it is whether identical, if so, merging adjacent two information flow texts as one
A information flow group of text, otherwise, using every information flow text as an information flow group of text;Alternatively, judging two neighboring letter
Whether the theme and/or intention of breath stream group of text are identical, if so, two neighboring information flow group of text is merged into an information
Group of text is flowed, until the theme of two neighboring information flow group of text and/or intention are different.
Sub-step B, by the text input of the information flow group of text into the summarization generation model pre-established, obtain
Obtain the corresponding information flow abstract that the summarization generation model pre-established generates.
The abstract of information flow group of text is obtained about the text for using natural language processing algorithm to analyze information flow group of text,
Summarization generation model can be pre-established in the present embodiment there are many implementation, by the text of information flow group of text
It is input in summarization generation model, utilizes abstract model extraction abstract corresponding with the information flow group of text.
Specifically, including following two parts content, first is that training summarization generation model, second is that running the summarization generation mould
Type.
It, can be with before being based on information flow text generation information flow abstract according to the summarization generation model that pre-establishes
First establish summarization generation model.Specifically, the method for building up of summarization generation model may include:Obtain the information flow of preset number
Group of text sample and with each information flow group of text sample is corresponding in the information flow group of text sample of the preset number plucks
Want sample;Each information flow group of text sample and abstract sample corresponding with each information flow group of text sample are held
Row vectorization processing obtains vectorization information flow group of text sample and vectorization abstract sample;By the vectorization information flow text
This group of sample and vectorization abstract sample are input in the neural network structure pre-established and carry out successive ignition, calculate root
The vectorization abstract sample is generated according to vectorization information flow group of text sample in the information flow group of text sample of the preset number
The probability of each vectorization abstract sample in this, obtains iteration later raw according to the vectorization information flow group of text sample
At the maximum probability of corresponding vectorization abstract sample, the summarization generation model is obtained.
After training obtains summarization generation model, so that it may corresponding for the text output according to information flow group of text
Information flow abstract.
Specifically, the information flow abstract includes User ID, corresponding information flow generation time.If the information flow is
Chat record content, the information flow abstract can also include the User ID of chatting object.
Specifically, using the summarization generation model pre-established that the information flow text is raw in client server
The step of making a summary at information flow has no difference.
In one example, local whether store are first determined whether before generating information flow abstract for client or server
There is an information flow abstract, and the information flow stored is made a summary the information flow of corresponding information flow text and information flow to be generated abstract
Text compares, and determines the incremental portion of information flow text, generates information flow abstract to the incremental portion.
Step S15, the information flow is made a summary and saves as data object with corresponding information flow by client, and described in displaying
Information flow abstract, so that the user checks the information flow abstract.
Specifically, the information flow generated under simplifying mode is made a summary and saves as data object with corresponding information flow by client
And it is stored in local.By storing the data object in client, the retrieval of abstract can be improved and check speed.Work as user
When needing to obtain information flow, it is only necessary to the keyword in the corresponding abstract of input stream in the search box.
Specifically, the abstract includes User ID, corresponding information flow generation time.If the information flow is chat note
Content is recorded, the abstract can also include the User ID of chatting object.Therefore, the sortord of can defaulting or user choosing into
Row sequence, such as according to the information flow abstract in include User ID, corresponding information flow generate the time be ranked up.It can also
The degree of correlation of the keyword inputted according to information flow abstract with user is ranked up.
It is possible to further be the information flow summarization generation information flow summary lists, the information flow summary lists are pressed
The time is generated according to User ID, corresponding information flow, the degree of correlation of the keyword inputted with user is ranked up.
Specifically, the selection instruction that user makes a summary to a wherein information flow is received, is jumped in corresponding information flow simultaneously
It is presented to user.
According to the present embodiment the method, emphasis abstract is generated to the content of text in information flow in client, facilitates use
Corresponding information flow is retrieved to the abstract and is checked at family, has been saved the time, has been improved efficiency.In addition, in information flow
Content of text generate emphasis abstract and saved the computing capability and electric power of user equipment belonging to client.
Fig. 2 is the flow diagram of a kind of information flow summarization generation that the embodiment of the present application two provides and methods of exhibiting, such as
Shown in Fig. 2, include the following steps S21-S27:
Step S21, client obtains the information flow summarization generation instruction of user's input.
The same or similar content of step S11 in step S21 and Fig. 1 can refer to the detailed description of step S11, herein
It does not repeat them here.
In the present embodiment, by taking the information flow writing abstract is pandect as an example.The information flow summarization generation instruction
It is original content of text in content of text, with information flow by the non-textual Content Transformation in information flow for pandect instruction
Together, as corresponding information flow text.
Step S22, client obtains information flow according to the information flow digest instructions.
The same or similar content of step S12 in step S22 and Fig. 1 can refer to the detailed description of step S12, herein
It does not repeat them here.
Step S23, user end to server sends the information flow, so that the server carries out in advance the information flow
Processing obtains information flow text, and is based on the information flow text generation information flow according to the summarization generation model pre-established
Abstract.
In the present embodiment, if the information flow writing abstract is pandect, is made a summary and given birth to by server execution information stream
At operation.Client obtains information flow, by the information stream to server, so that server locates information flow in advance
Reason, obtains information flow text.
In one example, client by the information stream to server while, by the information flow make a summary give birth to
It is sent to server at instruction, generates information flow abstract so that server is instructed according to the information flow summarization generation.Alternatively, objective
Family end by the information stream to server while, to server send pandect generate instruction, so as to server root
Instruction, which is generated, according to the pandect generates information flow abstract.
In different application scenarios, server can store and forwarding information stream;Or forwarding information stream is believed without storing
Breath stream.It is raw if necessary to server execution information stream pandect in the case where server is only forwarded without storing information flow
At operation, then need by client upload information stream.
In the present embodiment, by taking instant messaging application scenarios as an example, user's chat record is merely stored in client local, by
User's chat record is not stored in the factors such as privacy of user, server, will need to generate to pluck comprehensively therefore, it is necessary to client
The user's chat record wanted is uploaded onto the server, so that server generates pandect.
Step S24, server receives the information flow from client, pre-processes to the information flow, obtains information
Flow text.
In one example, while server obtains the information flow that client is sent, obtain what client was sent simultaneously
The information flow summarization generation instruction;Alternatively, obtaining client simultaneously while server obtains the information flow that client is sent
The pandect sent generates instruction.
Specifically, in pandect mode, since information flow may include non-textual content, it is therefore desirable to described non-
Content of text is handled to obtain text file, in order to the operation of subsequent summarization generation.
Illustratively, if all content of text of information flow, it is using content of text as corresponding information flow text
It can;It is content of text by non-textual Content Transformation if all non-textual contents of information flow, it will be in the text that be converted to
Hold and is used as corresponding information flow text;If information flow had not only included content of text but also include non-textual content, content of text is not
Conversion process is done, is only content of text by non-textual Content Transformation, obtains corresponding information flow text.
When it is implemented, can be using related voice identification software to audio content, the video content in non-textual content
In sound converted, obtain corresponding information flow text.
In a kind of preferred implementation of the present embodiment, non-textual content be audio file and/or video file, it is described
Audio file and/or video file can be hyperlink, may not be.
If the audio file and/or video file are hyperlink, server obtains the corresponding webpage information of the hyperlink,
And the information flow abstract of the audio, video file is obtained according to the webpage information.For example, it is assumed that active user is in chat window
In send or receive one section of video, webpage of the video from Mr. Yu's video website generally will include the video exhibition on the webpage
Show the information such as window, video name, video content brief introduction, video uplink time.Server can directly acquire the video website
On video name as the video file information flow make a summary;The video can also be obtained by way of extracting keywords
The information flow of file is made a summary.
When the audio file and/or video file are not hyperlink, for example, for the video of user equipment shooting, or
The voice of recording.It can be using related voice identification software to the audio content in non-textual content, the sound in video content
It is converted, obtains corresponding information flow text.
Illustratively, the information flow text that can be converted to for audio file and/or video file be arranged " audio " and/
Or " video " label.
Further, information flow text audio file and/or video file being converted to, it is corresponding with content of text
Different weights is arranged in information flow text, is the corresponding information flow text of content of text during carrying out summarization generation
Generate more detailed abstract.
Specifically, each information flow text may include User ID, content of text, can also include corresponding information flow
Generate the time.If the information flow is chat record content, the information flow text can also include the user of chatting object
ID。
Step S25, server is based on the information flow text generation information flow according to the summarization generation model pre-established
Abstract.
Step S25 is similar to the process that client generation information flow is made a summary in step S14 in Fig. 1, and difference is to execute master
Body replaces with server, and specific implementation process can refer to the detailed description of step S14, be not repeated herein.
Step S26, information flow abstract is sent to client by server.
In one example, server makes a summary the information flow generated under pandect mode and corresponding information flow
It saves as data object and is stored in local.
Specifically, the data object is sent to client by server;The data object is received by client and is deposited
Storage is in local.
For example, the information flow generated under pandect mode abstract is sent to client by server;By client
The information flow abstract is received, and saves as data object with corresponding information flow and is stored in local.
By storing the data object in client, the retrieval of abstract can be improved and check speed.
Step S27, client receives and shows the information flow abstract, so that the user checks that the information flow is plucked
It wants.
When user needs to obtain information flow, it is only necessary to the keyword in the corresponding abstract of input stream in the search box
?.
Illustratively, the abstract includes User ID, corresponding information flow generation time.If the information flow is chat
Content is recorded, the abstract can also include the User ID of chatting object.Therefore, the sortord of can default or user choosing
Be ranked up, for example, according to the information flow abstract in include User ID, corresponding information flow generate the time be ranked up.?
It can be ranked up according to the degree of correlation for the keyword that information flow abstract is inputted with user.
Illustratively, the selection instruction that user makes a summary to a wherein information flow is received, is jumped in corresponding information flow
And it is presented to user.
According to the present embodiment the method, the non-textual content in information flow is converted to obtain content of text, it can
To generate emphasis abstract to the full content in information flow, facilitates user to retrieve the abstract and check corresponding information
Stream, has saved the time, has improved efficiency.In addition, it is effective to generate emphasis abstract to the full content in information flow in server end
The computing resource of server is utilized.
Fig. 3 shows the frame for being suitable for the exemplary computer system/server 012 for being used to realize the application embodiment
Figure.The computer system/server 012 that Fig. 3 is shown is only an example, should not function and use to the embodiment of the present application
Range band carrys out any restrictions.
As shown in figure 3, computer system/server 012 is showed in the form of universal computing device.Computer system/clothes
The component of business device 012 can include but is not limited to:One or more processor or processing unit 016, system storage
028, connect the bus 018 of different system components (including system storage 028 and processing unit 016).
Bus 018 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer system/server 012 typically comprises a variety of computer system readable media.These media, which can be, appoints
The usable medium what can be accessed by computer system/server 012, including volatile and non-volatile media, movably
With immovable medium.
System storage 028 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 030 and/or cache memory 032.Computer system/server 012 may further include other
Removable/nonremovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 034 can
For reading and writing immovable, non-volatile magnetic media (Fig. 3 do not show, commonly referred to as " hard disk drive ").Although in Fig. 3
It is not shown, the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and to can
The CD drive of mobile anonvolatile optical disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these situations
Under, each driver can be connected by one or more data media interfaces with bus 018.Memory 028 may include
At least one program product, the program product have one group of (for example, at least one) program module, these program modules are configured
To execute the function of each embodiment of the application.
Program/utility 040 with one group of (at least one) program module 042, can store in such as memory
In 028, such program module 042 includes --- but being not limited to --- operating system, one or more application program, other
It may include the realization of network environment in program module and program data, each of these examples or certain combination.Journey
Sequence module 042 usually executes function and/or method in embodiments described herein.
Computer system/server 012 can also with one or more external equipments 014 (such as keyboard, sensing equipment,
Display 024 etc.) communication, in this application, computer system/server 012 is communicated with outside radar equipment, can also be with
One or more enable a user to the equipment interacted with the computer system/server 012 communication, and/or with make the meter
Any equipment (such as network interface card, the modulation that calculation machine systems/servers 012 can be communicated with one or more of the other calculating equipment
Demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 022.Also, computer system/clothes
Being engaged in device 012 can also be by network adapter 020 and one or more network (such as local area network (LAN), wide area network (WAN)
And/or public network, such as internet) communication.As shown in figure 3, network adapter 020 by bus 018 and computer system/
Other modules of server 012 communicate.It should be understood that computer system/server 012 can be combined although being not shown in Fig. 3
Using other hardware and/or software module, including but not limited to:Microcode, device driver, redundant processing unit, external magnetic
Dish driving array, RAID system, tape drive and data backup storage system etc..
The program that processing unit 016 is stored in system storage 028 by operation, thereby executing described herein
Function and/or method in embodiment.
Above-mentioned computer program can be set in computer storage medium, i.e., the computer storage medium is encoded with
Computer program, the program by one or more computers when being executed, so that one or more computers execute in the application
State method flow shown in embodiment and/or device operation.
With time, the development of technology, medium meaning is more and more extensive, and the route of transmission of computer program is no longer limited by
Tangible medium, can also be directly from network downloading etc..It can be using any combination of one or more computer-readable media.
Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer-readable storage medium
Matter for example may be-but not limited to-system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or
Any above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes:With one
Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM),
Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can
With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
Person is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with one or more programming languages or combinations thereof come write for execute the application operation computer
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN) is connected to subscriber computer, or, it may be connected to outer computer (such as provided using Internet service
Quotient is connected by internet).
Finally it should be noted that:Above embodiments are only to illustrate the technical solution of the application, rather than its limitations;Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that:It still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (20)
1. a kind of information flow summarization generation and methods of exhibiting are applied to client, which is characterized in that including:
Obtain the information flow summarization generation instruction of user's input;
Information flow is obtained according to the information flow digest instructions;
The information flow is pre-processed, information flow text is obtained;
It is made a summary according to the summarization generation model pre-established based on the information flow text generation information flow;
Information flow abstract is saved as into data object with the information flow, and shows the information flow abstract, so as to described
User checks the information flow abstract.
2. the method according to claim 1, wherein the information flow include content of text and/or it is non-textual in
Hold;Wherein, the non-textual content includes audio file and/or video file.
3. the method according to claim 1, wherein the information flow digest instructions be simplify digest instructions, institute
Stating information flow includes non-textual content;
It is described that the information flow is pre-processed, information flow text is obtained, including:
Using the typonym of the non-textual content as the information flow text.
4. the method according to claim 1, wherein the summarization generation model that the basis pre-establishes is based on institute
Information flow text generation information flow abstract is stated, including:
The information flow text is divided into one or more information flow group of text;
By the text input of the information flow group of text into the summarization generation model pre-established, acquisition is described to build in advance
The corresponding information flow abstract that vertical summarization generation model generates.
5. according to the method described in claim 4, it is characterized in that, the information flow text is divided into one or more information
Group of text is flowed, including:
The information flow text is divided into one or more letters by the theme and/or intention for analyzing the information flow text
Breath stream group of text.
6. the method according to any one of claims 1 to 5, which is characterized in that the abstract that the basis pre-establishes is raw
Before being based on information flow text generation information flow abstract at model, the method also includes:
Obtain preset number information flow group of text sample and with it is each in the information flow group of text sample of the preset number
The corresponding abstract sample of information flow group of text sample;
Each information flow group of text sample and abstract sample corresponding with each information flow group of text sample are executed
Vectorization processing obtains vectorization information flow group of text sample and vectorization abstract sample;
The vectorization information flow group of text sample and vectorization abstract sample are input to the neural network pre-established
Successive ignition is carried out in structure, is calculated and is generated according to each vectorization information flow group of text sample in vectorization abstract sample
The probability of each vectorization abstract sample in vectorization abstract sample makes what is obtained after iteration to be believed according to the vectorization
Breath stream group of text sample generates the maximum probability of corresponding vectorization abstract sample, obtains the summarization generation model.
7. method according to any one of claim 1 to 6, which is characterized in that described to show the information flow abstract, packet
It includes:
For the information flow summarization generation information flow summary lists, the information flow summary lists are according to user identifier, information flow
It generates the time and is ranked up at least one in the degree of correlation of the keyword of user's input.
8. a kind of information flow summarization generation and methods of exhibiting are applied to client, which is characterized in that including:
Obtain the information flow summarization generation instruction of user's input;
Information flow is obtained according to the information flow digest instructions;
The information flow is sent to server, so that the server pre-processes the information flow, obtains information flow text
This, and made a summary according to the summarization generation model pre-established based on the information flow text generation information flow;
Receive and show the information flow abstract, from the server so that the user checks the information flow abstract.
9. according to the method described in claim 8, it is characterized in that, the information flow include content of text and/or it is non-textual in
Hold;Wherein, the non-textual content is audio file and/or video file.
10. according to the method described in claim 8, it is characterized in that, the information flow digest instructions are pandect instruction, institute
Stating information flow includes non-textual content;
It is described that the information flow is pre-processed, information flow text is obtained, including:It is text by the non-textual Content Transformation
Content.
11. the method according to any one of claim 8 to 10, which is characterized in that it is described to show the information flow abstract,
Including:
For the information flow summarization generation information flow summary lists, the information flow summary lists are according to user identifier, information flow
It generates the time and is ranked up at least one in the degree of correlation of the keyword of user's input.
12. a kind of information flow summarization generation and methods of exhibiting are applied to server, which is characterized in that including:
Information flow is received from client;
The information flow is pre-processed, information flow text is obtained;
It is made a summary according to the summarization generation model pre-established based on the information flow text generation information flow;
The information flow abstract is sent to the client, so that the client receives and shows the information flow abstract, by
User checks the information flow abstract.
13. according to the method for claim 12, which is characterized in that the information flow includes content of text and/or non-textual
Content;Wherein, the non-textual content includes audio file and/or video file.
14. according to the method for claim 12, which is characterized in that the information flow includes non-textual content, described to institute
It states information flow to be pre-processed, obtains information flow text, including:It is content of text by the non-textual Content Transformation.
15. according to the method for claim 12, which is characterized in that the summarization generation model that the basis pre-establishes is based on
The information flow text generation information flow abstract, including:
The information flow text is divided into one or more information flow group of text;
By the text input of the information flow group of text into the summarization generation model pre-established, acquisition is described to build in advance
The corresponding information flow abstract that vertical summarization generation model generates.
16. according to the method for claim 15, which is characterized in that described that the information flow text is divided into one or more
A information flow group of text, including:
The information flow text is divided into one or more information flows by the theme and/or intention for analyzing the information flow text
Group of text.
17. method described in any one of 2 to 16 according to claim 1, which is characterized in that the abstract that the basis pre-establishes
Model is generated to be based on before information flow text generation information flow abstract, the method also includes:
Obtain preset number information flow group of text sample and with it is each in the information flow group of text sample of the preset number
The corresponding abstract sample of information flow group of text sample;
Each information flow group of text sample and abstract sample corresponding with each information flow group of text sample are executed
Vectorization processing obtains vectorization information flow group of text sample and vectorization abstract sample;
The vectorization information flow group of text sample and vectorization abstract sample are input to the neural network pre-established
Successive ignition is carried out in structure, is calculated and is generated according to each vectorization information flow group of text sample in vectorization abstract sample
The probability of each vectorization abstract sample in vectorization abstract sample makes what is obtained after iteration to be believed according to the vectorization
Breath stream group of text sample generates the maximum probability of corresponding vectorization abstract sample, obtains the summarization generation model.
18. method described in any one of 2-17 according to claim 1, which is characterized in that send the letter to the client
Breath abstract, including:
Information flow abstract is saved as into data object with the information flow, and is sent to the client and is stored;Or,
Information flow abstract is sent to the client;Information flow abstract is received by the client, and with it is corresponding
Information flow save as data object and store.
19. a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-18.
20. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The method as described in any in claim 1-18 is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810622659.9A CN108846098B (en) | 2018-06-15 | 2018-06-15 | Information flow abstract generating and displaying method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810622659.9A CN108846098B (en) | 2018-06-15 | 2018-06-15 | Information flow abstract generating and displaying method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108846098A true CN108846098A (en) | 2018-11-20 |
CN108846098B CN108846098B (en) | 2023-03-10 |
Family
ID=64202113
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810622659.9A Active CN108846098B (en) | 2018-06-15 | 2018-06-15 | Information flow abstract generating and displaying method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108846098B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111460218A (en) * | 2020-03-31 | 2020-07-28 | 联想(北京)有限公司 | Information processing method and device |
CN111914115A (en) * | 2019-05-08 | 2020-11-10 | 阿里巴巴集团控股有限公司 | Sound information processing method and device and electronic equipment |
CN115334367A (en) * | 2022-07-11 | 2022-11-11 | 北京达佳互联信息技术有限公司 | Video summary information generation method, device, server and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040230951A1 (en) * | 2003-04-02 | 2004-11-18 | Scandura Joseph M. | Method for Building Highly Adaptive Instruction Based on the Structure as Opposed to the Semantics of Knowledge Representations |
JP2009211629A (en) * | 2008-03-06 | 2009-09-17 | National Institute Of Information & Communication Technology | Interaction device, weight information learning device, interaction method, weight information learning method, and program |
CN103699611A (en) * | 2013-12-16 | 2014-04-02 | 浙江大学 | Microblog flow information extracting method based on dynamic digest technology |
CN104375977A (en) * | 2013-08-14 | 2015-02-25 | 腾讯科技(深圳)有限公司 | Answer message processing method and device for question-answer communities |
CN105991398A (en) * | 2015-02-04 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Instant message IM chatting records storage method and apparatus |
CN106407178A (en) * | 2016-08-25 | 2017-02-15 | 中国科学院计算技术研究所 | Session abstract generation method and device |
US20170169822A1 (en) * | 2015-12-14 | 2017-06-15 | Hitachi, Ltd. | Dialog text summarization device and method |
-
2018
- 2018-06-15 CN CN201810622659.9A patent/CN108846098B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040230951A1 (en) * | 2003-04-02 | 2004-11-18 | Scandura Joseph M. | Method for Building Highly Adaptive Instruction Based on the Structure as Opposed to the Semantics of Knowledge Representations |
JP2009211629A (en) * | 2008-03-06 | 2009-09-17 | National Institute Of Information & Communication Technology | Interaction device, weight information learning device, interaction method, weight information learning method, and program |
CN104375977A (en) * | 2013-08-14 | 2015-02-25 | 腾讯科技(深圳)有限公司 | Answer message processing method and device for question-answer communities |
CN103699611A (en) * | 2013-12-16 | 2014-04-02 | 浙江大学 | Microblog flow information extracting method based on dynamic digest technology |
CN105991398A (en) * | 2015-02-04 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Instant message IM chatting records storage method and apparatus |
US20170169822A1 (en) * | 2015-12-14 | 2017-06-15 | Hitachi, Ltd. | Dialog text summarization device and method |
CN106407178A (en) * | 2016-08-25 | 2017-02-15 | 中国科学院计算技术研究所 | Session abstract generation method and device |
Non-Patent Citations (2)
Title |
---|
FONG-CHING YUAN等: "Practical voice session selection with FAHP in next generation wireless network", 《2015 SEVENTH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS》 * |
杨凯翔: "聊天机器人知识挖掘方法研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111914115A (en) * | 2019-05-08 | 2020-11-10 | 阿里巴巴集团控股有限公司 | Sound information processing method and device and electronic equipment |
CN111460218A (en) * | 2020-03-31 | 2020-07-28 | 联想(北京)有限公司 | Information processing method and device |
CN115334367A (en) * | 2022-07-11 | 2022-11-11 | 北京达佳互联信息技术有限公司 | Video summary information generation method, device, server and storage medium |
CN115334367B (en) * | 2022-07-11 | 2023-10-17 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for generating abstract information of video |
Also Published As
Publication number | Publication date |
---|---|
CN108846098B (en) | 2023-03-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11106877B2 (en) | Dynamic text generation for social media posts | |
CN108509569A (en) | Generation method, device, electronic equipment and the storage medium of enterprise's portrait | |
US20100223335A1 (en) | Dynamically Managing Online Communication Groups | |
CN109408826A (en) | A kind of text information extracting method, device, server and storage medium | |
US10614422B2 (en) | Method and system for communication content management | |
CN110417575A (en) | Alarm method, device and the computer equipment of O&M monitor supervision platform | |
CN103369477B (en) | Display media method, device, client, graphical control display packing and device | |
US11436446B2 (en) | Image analysis enhanced related item decision | |
CN109302461A (en) | Information displaying, processing method, medium, system and calculating equipment | |
CN108846098A (en) | A kind of information flow summarization generation and methods of exhibiting | |
CN109271358A (en) | Data summarization method, querying method, device, equipment and storage medium | |
US20190146636A1 (en) | Generating predicted reactions of a user | |
US20220103503A1 (en) | Conversation slipstream propagation | |
CN105378717A (en) | Method for user categorization in social media, computer program, and computer | |
CN107733894A (en) | Comparison method, system, equipment and the storage medium of logic interfacing message | |
US11366641B2 (en) | Generating microservices for monolithic system using a design diagram | |
CN110325987A (en) | Context voice driven depth bookmark | |
CN103999082B (en) | Method, computer program and computer for detecting the community in social media | |
CN109960554A (en) | Show method, equipment and the computer storage medium of reading content | |
WO2021068493A1 (en) | Method and apparatus for processing information | |
CN109145164A (en) | Data processing method, device, equipment and medium | |
CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
JP2022093317A (en) | Computer-implemented method, system and computer program product (recognition and restructuring of previously presented information) | |
CN110083677A (en) | Searching method, device, equipment and the storage medium of contact person | |
CN109933254A (en) | Show method, equipment and the computer storage medium of reading content |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200714 Address after: Room 909, No. 12, Huangshan Road, Jianye District, Nanjing City, Jiangsu Province Applicant after: Nanjing Shangwang Network Technology Co.,Ltd. Address before: 201806, room 5358, 140 Shanghai Yi Road, Shanghai, Jiading District Applicant before: SHANGHAI ZHANGMEN SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |