CN108846098B - Information flow abstract generating and displaying method - Google Patents
Information flow abstract generating and displaying method Download PDFInfo
- Publication number
- CN108846098B CN108846098B CN201810622659.9A CN201810622659A CN108846098B CN 108846098 B CN108846098 B CN 108846098B CN 201810622659 A CN201810622659 A CN 201810622659A CN 108846098 B CN108846098 B CN 108846098B
- Authority
- CN
- China
- Prior art keywords
- information flow
- abstract
- text
- information
- stream
- 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.)
- Active
Links
Images
Landscapes
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a method for generating and displaying an information flow abstract, which comprises the steps of acquiring an information flow abstract generating instruction input by a user; acquiring an information stream according to the information stream abstract instruction; preprocessing the information flow to obtain an information flow text; generating an information flow abstract based on the information flow text according to a pre-established abstract generating model; and storing the information flow abstract and the information flow as data objects, and displaying the information flow abstract so that the user can conveniently view the information flow abstract. By the method, the key abstract is generated for the content in the information flow, so that the user is prevented from looking up all the information flows one by one, the user can conveniently retrieve the abstract and look up the corresponding information flow, the time is saved, and the efficiency is improved.
Description
[ technical field ] A
The application relates to the field of internet application, in particular to a method for generating and displaying an information flow abstract.
[ background ] A method for producing a semiconductor device
In the current society, the use of instant messaging products and/or social products in work and life has become quite popular, and the use rate and the dependence of the majority of users on the products are higher and higher.
A large number of historical information streams are generated during the use of instant messaging products and/or social products, and many of the historical information streams are of significant value or use, such as conversation information streams and media sharing (e.g., circle of friends) information streams. The user wishes to be able to review these streams at any time during use. However, the current products cannot effectively meet the requirement that users look up the information streams at any time, and the users can only browse all historical information streams in detail. Moreover, the information stream includes text content and/or non-text content, and the non-text content cannot be retrieved.
[ summary of the invention ]
Various aspects of the present application provide a method for generating and displaying an information flow summary, which is used to improve the query efficiency and accuracy of information records.
One aspect of the present application provides a method for generating and displaying an information flow summary, which is applied to a client, and includes: acquiring an information flow abstract generation instruction input by a user; acquiring an information stream according to the information stream abstract instruction; preprocessing the information flow to obtain an information flow text; generating an information flow abstract based on the information flow text according to a pre-established abstract generating model; and storing the information flow abstract and the information flow as data objects, and displaying the information flow abstract so that the user can conveniently view the information flow abstract.
Another aspect of the present application provides a method for generating and displaying an information flow summary, which is applied to a client, and includes: acquiring an information flow abstract generation instruction input by a user; acquiring an information stream according to the information stream abstract instruction; sending the information flow to a server so that the server can preprocess the information flow to obtain an information flow text, and generating an information flow abstract based on the information flow text according to a pre-established abstract generation model; and receiving and displaying the information flow abstract from the server so that the user can view the information flow abstract.
In another aspect of the present application, a method for generating and displaying an information flow summary is provided, which is applied to a server, and includes: receiving an information stream from a client; preprocessing the information flow to obtain an information flow text; generating an information flow abstract based on the information flow text according to a pre-established abstract generating model; and sending the information flow abstract to the client so that the client can receive and display the information flow abstract and a user can check the information flow abstract.
In another aspect of the present application, there is provided an apparatus, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement any of the above-described methods.
In another aspect of the application, a computer-readable storage medium is provided, on which a computer program is stored, wherein the program, when executed by a processor, performs any of the above-mentioned methods.
According to the technical scheme, the key abstract is generated for the content in the information flow through the embodiment of the application, so that the user is prevented from looking up all the information flows one by one, the user can conveniently search the abstract and look up the corresponding information flow, the time is saved, and the efficiency is improved.
[ description of the drawings ]
While the drawings needed to describe the embodiments are briefly described below, it should be apparent that the drawings in the following description are examples of the present application and that other drawings may be derived from those drawings by those of ordinary skill in the art without inventive faculty.
Fig. 1 is a schematic flowchart of a method for generating and displaying an information flow summary according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a method for generating and displaying an information flow summary according to a second embodiment of the present application;
FIG. 3 is a block diagram of an exemplary computer system/server suitable for use in implementing embodiments of the present application.
[ detailed description ] embodiments
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship.
Fig. 1 is a schematic flowchart of a method for generating and displaying an information flow summary according to an embodiment of the present application, which is applied to a client, and as shown in fig. 1, the method includes the following steps S11 to S15:
and step S11, the client acquires an information flow abstract generation instruction input by the user.
For example, the user issues a message flow summary generation instruction by clicking a message flow summary generation button or operating a menu provided on the client.
Specifically, the client may be an instant messenger client, a social messenger client, a mail messenger client, a document messenger client, or the like. According to the difference of the client, the information flow can be chat record content generated by chatting between users by utilizing an instant messaging tool client; or the content browsed by the user by utilizing the social tool client, such as blogs and friend circles; or the user can send and receive mails by using a mail tool client; but also historical documents operated by the user with the document tool client, etc.
In this embodiment, the client is an instant messenger client for example.
Illustratively, the information stream includes textual content and/or non-textual content; the non-textual content includes audio files and/or video files.
In one example, the information flow summary generation instructions include: a type of information stream summary; information flow range, etc. The summary types of the information flow can include a comprehensive summary and a condensed summary.
Wherein, the comprehensive abstract is generated by abstracting all information streams; the simplified abstract is that audio and video information in the information stream is not converted, and only the title of 'audio' and/or 'video' is reserved. Because the computing power and the battery of the user equipment to which the client belongs are limited, the client can carry out the work of generating the simplified abstract; the server performs a comprehensive digest generation job.
In this embodiment, the information flow digest type is taken as an example. The information flow abstract generating instruction is a simplified abstract instruction, and the type name of the non-text content in the information flow and the text content are used as the corresponding information flow text.
The information flow range refers to a range for generating the information flow summary. The information stream scope may be an entire information stream, such as an entire information stream generated by a user; alternatively, the information flow range may be a portion of the information flow selected by the user, such as one or more chat logs selected by the user in a chat log window of the instant messenger client.
Further, the information flow summary generation instruction may further include a frequency of generating the information flow summary, so that the summary is generated for all information flows generated by the user in the process of using the instant messenger client regularly, for example, every hour and every day.
And S12, the client acquires the information flow according to the information flow abstract instruction.
For example, the client acquires the information stream through a preset interface.
In one example, the client obtains the information flow of the range specified in the information flow summary instruction through a built-in preset interface. Generally, the chat records are stored locally at the client, and the client searches for the information stream in the specified range locally.
And S13, the client preprocesses the information flow to obtain an information flow text.
In this embodiment, the information flow summary is described as an example of a simplified summary. In the summary mode, since the information stream may contain non-text content, the non-text content needs to be processed to facilitate the subsequent summary generation operation.
For example, the audio-video information in the information stream is replaced by an "audio" and "video" title, and for example, in the form of "audio + information stream generation time" and "video + information stream generation time", the audio-video information and the text content in the information stream constitute a text file.
Specifically, each piece of information stream text may include a user ID, text content, and may further include a corresponding information stream generation time. If the information flow is chat record content, the information flow text can also comprise the user ID of the chat object.
And S14, the client generates the information flow abstract based on the information flow text according to a pre-established abstract generation model.
In one example, step S14 may include the following sub-steps a and B:
and a substep A of dividing the information stream text into one or more information stream text groups.
In one implementation of sub-step a, the subject and/or intent of the information flow text is analyzed, and the information flow text is divided into one or more information flow text groups.
Specifically, determining the theme and/or intention of each piece of information flow text in the information flow text; judging whether the subjects and/or intentions of the two adjacent information flow texts are the same, if so, combining the two adjacent information flow texts to be used as an information flow text group, otherwise, using each information flow text as an information flow text group; or judging whether the subjects and/or intentions of the two adjacent information flow text groups are the same, if so, combining the two adjacent information flow text groups into one information flow text group until the subjects and/or intentions of the two adjacent information flow text groups are different.
And a substep B, inputting the text of the information flow text group into the pre-established abstract generation model to obtain a corresponding information flow abstract generated by the pre-established abstract generation model.
In this embodiment, a summary generation model may be established in advance, the text of the information flow text group is input into the summary generation model, and the summary corresponding to the information flow text group is extracted by using the summary model.
Specifically, the method comprises two parts, namely training the abstract generation model and operating the abstract generation model.
The summary generation model may be built prior to generating the summary of the information flow based on the information flow text according to a pre-built summary generation model. Specifically, the method for establishing the abstract generation model may include: acquiring a preset number of information flow text group samples and abstract samples corresponding to each information flow text group sample in the preset number of information flow text group samples; performing vectorization processing on each information flow text group sample and the abstract sample corresponding to each information flow text group sample to obtain a vectorized information flow text group sample and a vectorized abstract sample; inputting the vectorized information flow text group samples and the vectorized abstract samples into a pre-established neural network structure for multiple iterations, calculating the probability of generating each vectorized abstract sample in the vectorized abstract samples according to the vectorized information flow text group samples in the information flow text group samples with the preset number, and maximizing the probability of generating the corresponding vectorized abstract samples according to the vectorized information flow text group samples obtained after the iterations to obtain the abstract generation model.
After the abstract generation model is obtained through training, the abstract generation model can be used for outputting a corresponding information flow abstract according to the text of the information flow text group.
Specifically, the information flow summary includes a user ID and a corresponding information flow generation time. If the information flow is the chat record content, the information flow abstract also can comprise the user ID of the chat object.
Specifically, there is no difference in the step of generating the summary of the information stream from the information stream text by using a pre-established summary generation model at the client or the server.
In one example, before generating an information flow abstract, a client or a server first determines whether the information flow abstract is locally stored, compares an information flow text corresponding to the stored information flow abstract with an information flow text of the information flow abstract to be generated, determines an incremental portion of the information flow text, and generates the information flow abstract for the incremental portion.
And S15, the client saves the information flow abstract and the corresponding information flow as data objects and displays the information flow abstract so that the user can check the information flow abstract conveniently.
Specifically, the client saves the information flow summary generated in the simplified mode and the corresponding information flow as a data object and stores the data object locally. By storing the data object at the client, the retrieval and viewing speed of the abstract can be improved. When a user needs to acquire the information stream, only the key words in the abstract corresponding to the information stream need to be input in the search box.
Specifically, the summary includes a user ID and a corresponding information flow generation time. If the information flow is chat record content, the abstract can also comprise a user ID of a chat object. Therefore, the information flow can be sorted in a default or user-selected sorting manner, for example, according to the user ID included in the information flow summary and the corresponding information flow generation time. The information flow summaries may also be ranked according to their relevance to the keywords entered by the user.
Further, a message flow summary list may be generated for the message flow summary, and the message flow summary list may be sorted according to the user ID, the corresponding message flow generation time, and the relevance of the keyword input by the user.
Specifically, a selection instruction of a user for one of the information flow summaries is received, and the corresponding information flow is jumped to and displayed to the user.
According to the method, the key abstract is generated on the text content in the information flow at the client, so that the user can conveniently search the abstract and check the corresponding information flow, the time is saved, and the efficiency is improved. In addition, the key abstract generated for the text content in the information flow saves the computing power and the electric power of the user equipment to which the client belongs.
Fig. 2 is a schematic flowchart of a method for generating and displaying an information flow summary according to a second embodiment of the present application, as shown in fig. 2, including the following steps S21 to S27:
and S21, the client acquires an information flow abstract generation instruction input by the user.
The details of step S11 may be referred to for the same or similar contents of step S21 and step S11 in fig. 1, and are not repeated herein.
In this embodiment, the information stream summary type is taken as an example of a comprehensive summary. The information flow abstract generating instruction is a comprehensive abstract instruction, and non-text content in the information flow is converted into text content which is taken as a corresponding information flow text together with original text content in the information flow.
And S22, the client acquires the information flow according to the information flow abstract instruction.
The details of step S12 may be referred to for the same or similar contents of step S22 as step S12 in fig. 1, and are not repeated herein.
And S23, the client sends the information flow to a server so that the server can preprocess the information flow to obtain an information flow text, and generates an information flow abstract based on the information flow text according to a pre-established abstract generation model.
In this embodiment, if the type of the information flow summary is a comprehensive summary, the server executes an information flow summary generation operation. The client acquires the information flow and sends the information flow to the server so that the server can preprocess the information flow to obtain an information flow text.
In one example, the client sends the information flow to the server and simultaneously sends the information flow summary generation instruction to the server, so that the server generates the information flow summary according to the information flow summary generation instruction. Or the client sends the information flow to the server and sends a comprehensive abstract generating instruction to the server at the same time, so that the server generates the information flow abstract according to the comprehensive abstract generating instruction.
In different application scenarios, the server may store and forward information streams; or forward the information stream without storing the information stream. In the case where the server merely forwards and does not store the information stream, if the server is required to perform a full summary generation operation of the information stream, the information stream needs to be uploaded by the client.
In this embodiment, taking an instant messaging application scenario as an example, the user chat record is only stored locally at the client, and due to factors such as user privacy, the server does not store the user chat record, so that the client is required to upload the user chat record that needs to generate the comprehensive summary to the server, so that the server generates the comprehensive summary.
And step S24, the server receives the information flow from the client and preprocesses the information flow to obtain an information flow text.
In one example, the server acquires the information flow sent by the client and simultaneously acquires the information flow summary generation instruction sent by the client; or, the server acquires the information stream sent by the client and simultaneously acquires the comprehensive abstract generating instruction sent by the client.
In particular, in the full summary mode, since the information stream may contain non-text content, the non-text content needs to be processed to obtain a text file, so as to facilitate the subsequent summary generation operation.
Exemplarily, if all the information streams are text contents, the text contents are taken as corresponding information stream texts; if all the information streams are non-text contents, converting the non-text contents into text contents, and taking the converted text contents as corresponding information stream texts; if the information flow contains both text content and non-text content, the text content is not converted, and only the non-text content is converted into the text content, so as to obtain the corresponding information flow text.
In specific implementation, relevant speech recognition software can be adopted to convert the sound in the audio content and the video content in the non-text content to obtain the corresponding information flow text.
In a preferred implementation manner of this embodiment, the non-text content is an audio file and/or a video file, and the audio file and/or the video file may or may not be a hyperlink.
If the audio file and/or the video file are hyperlinks, the server acquires webpage information corresponding to the hyperlinks, and acquires information stream abstracts of the audio file and the video file according to the webpage information. For example, suppose that a current user sends or receives a video in a chat window, the video is from a web page of a video website, and the web page typically includes information such as the video display window, the video name, a video content introduction, and a video uploading time. The server can directly acquire the video name on the video website as the information flow abstract of the video file; the information flow abstract of the video file can also be obtained in a mode of extracting the key words.
When the audio file and/or video file is not a hyperlink, for example, a video shot for a user device, or a recorded voice. And related voice recognition software can be adopted to convert the voice in the audio content and the video content in the non-text content to obtain the corresponding information flow text.
For example, an "audio" and/or "video" tag may be set for the converted stream text of the audio file and/or the video file.
Furthermore, different weights are set for the information stream texts obtained by converting the audio files and/or the video files and the information stream texts corresponding to the text contents, so that in the process of generating the abstract, a more detailed abstract is generated for the information stream texts corresponding to the text contents.
Specifically, each piece of information stream text may include a user ID, text content, and may further include a corresponding information stream generation time. If the information flow is chat record content, the information flow text can also comprise a user ID of a chat object.
And S25, the server generates the information flow abstract based on the information flow text according to a pre-established abstract generation model.
Step S25 is similar to the process of generating the information flow summary by the client in step S14 in fig. 1, except that the execution main body is replaced by a server, and the detailed implementation process may refer to the detailed description of step S14, which is not described herein again.
And S26, the server sends the information flow abstract to the client.
In one example, the server saves the information flow summary generated in the full summary mode and the corresponding information flow as a data object and locally.
Specifically, the server sends the data object to the client; the data object is received by the client and stored locally.
For example, the server sends the information flow summary generated in the comprehensive summary mode to the client; and receiving the information flow abstract by the client, storing the information flow abstract and the corresponding information flow as a data object and storing the data object locally.
By storing the data object at the client, the retrieval and viewing speed of the abstract can be improved.
And S27, receiving and displaying the information flow abstract by the client so that the user can check the information flow abstract conveniently.
When a user needs to acquire the information stream, only the key words in the abstract corresponding to the information stream need to be input in the search box.
Illustratively, the summary includes a user ID, a corresponding information flow generation time. If the information flow is the chat record content, the abstract can also comprise the user ID of the chat object. Therefore, the information flow can be sorted in a default or user-selected sorting manner, for example, according to the user ID included in the information flow summary and the corresponding information flow generation time. The information flow summaries may also be ranked according to their relevance to the keywords entered by the user.
Illustratively, a selection instruction of a user for one of the information flow summaries is received, and the corresponding information flow is jumped to and displayed for the user.
According to the method, the non-text content in the information flow is converted to obtain the text content, the key abstract can be generated for all the content in the information flow, a user can conveniently retrieve the abstract and check the corresponding information flow, time is saved, and efficiency is improved. In addition, the server generates the key summary of all the contents in the information flow, thereby effectively utilizing the computing resources of the server.
Fig. 3 illustrates a block diagram of an exemplary computer system/server 012 suitable for use in implementing embodiments of the present application. The computer system/server 012 shown in fig. 3 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present application.
As shown in fig. 3, computer system/server 012 is represented in the form of a general purpose computing device. The components of computer system/server 012 may include, but are not limited to: one or more processors or processing units 016, a system memory 028, and a bus 018 that couples various system components including the system memory 028 and the processing unit 016.
Computer system/server 012 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer system/server 012 and includes both volatile and nonvolatile media, removable and non-removable media.
Program/utility 040 having a set (at least one) of program modules 042 can be stored, for example, in memory 028, such program modules 042 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof might include an implementation of a network environment. Program modules 042 generally perform the functions and/or methodologies of embodiments described herein.
The computer system/server 012 may also communicate with one or more external devices 014 (e.g., keyboard, pointing device, display 024, etc.), where the computer system/server 012 communicates with external radar devices, may also communicate with one or more devices that enable a user to interact with the computer system/server 012, and/or communicates with any devices (e.g., network card, modem, etc.) that enable the computer system/server 012 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 022. Also, the computer system/server 012 can communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet) via a network adapter 020. As shown in fig. 3, the network adapter 020 communicates with the other modules of the computer system/server 012 via bus 018. It should be appreciated that although not shown in fig. 3, other hardware and/or software modules may be used in conjunction with computer system/server 012, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 016 executes programs stored in the system memory 028 to perform the functions and/or methods of the embodiments described herein.
The computer program described above may be provided in a computer storage medium encoded with a computer program that, when executed by one or more computers, causes the one or more computers to perform the method flows and/or apparatus operations illustrated in the above-described embodiments of the present application.
With the development of time and technology, the meaning of media is more and more extensive, and the propagation path of computer programs is not limited to tangible media any more, and can also be downloaded from a network directly and the like. Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (19)
1. A method for generating and displaying an information flow abstract is applied to a client and is characterized by comprising the following steps:
acquiring an information flow abstract generation instruction input by a user;
acquiring an information stream according to the information stream abstract generating instruction; the information stream comprises textual content and non-textual content;
preprocessing the information flow to obtain an information flow text; the information flow text obtained by preprocessing the non-text content has different weights with the information flow text corresponding to the text content;
generating an information flow abstract based on the information flow text according to a pre-established abstract generating model; generating a more detailed information flow abstract for the information flow text corresponding to the text content;
and storing the information flow abstract and the information flow as data objects, and displaying the information flow abstract so that the user can conveniently view the information flow abstract.
2. The method of claim 1, wherein the non-textual content comprises an audio file and/or a video file.
3. The method of claim 1, wherein the information flow summary generation instructions are condensed summary instructions, the information flow comprising non-textual content;
the preprocessing the information stream to obtain an information stream text includes:
and taking the type name of the non-text content as the information flow text.
4. The method of claim 1, wherein generating a message stream summary based on the message stream text according to a pre-established summary generation model comprises:
dividing the information stream text into one or more information stream text groups;
and inputting the text of the information flow text group into the pre-established abstract generation model to obtain the corresponding information flow abstract generated by the pre-established abstract generation model.
5. The method of claim 4, wherein dividing the stream text into one or more stream text groups comprises:
and analyzing the subject and/or intention of the information flow text, and dividing the information flow text into one or more information flow text groups.
6. The method of any of claims 1-5, wherein prior to generating a stream summary based on the stream text according to a pre-established summary generation model, the method further comprises:
acquiring a preset number of information flow text group samples and abstract samples corresponding to each information flow text group sample in the preset number of information flow text group samples;
performing vectorization processing on each information flow text group sample and the abstract sample corresponding to each information flow text group sample to obtain a vectorized information flow text group sample and a vectorized abstract sample;
inputting the vectorized information flow text group samples and the vectorized abstract samples into a pre-established neural network structure for multiple iterations, calculating the probability of generating each vectorized abstract sample in the vectorized abstract samples according to each vectorized information flow text group sample in the vectorized abstract samples, and maximizing the probability of generating corresponding vectorized abstract samples according to the vectorized information flow text group samples obtained after the iterations to obtain the abstract generation model.
7. The method of any one of claims 1 to 5, wherein said presenting the information flow summary comprises:
and generating an information flow abstract list for the information flow abstract, wherein the information flow abstract list is sorted according to at least one item of user identification, information flow generation time and correlation degree of keywords input by a user.
8. A method for generating and displaying an information flow abstract is applied to a client and is characterized by comprising the following steps:
acquiring an information flow abstract generation instruction input by a user;
acquiring an information stream according to the information stream abstract generating instruction; the information stream comprises textual content and non-textual content;
sending the information flow to a server so that the server can preprocess the information flow to obtain an information flow text, and generating an information flow abstract based on the information flow text according to a pre-established abstract generation model; the information flow text obtained by the non-text content preprocessing has different weights with the information flow text corresponding to the text content, and a more detailed information flow abstract is generated for the information flow text corresponding to the text content;
and receiving and displaying the information flow abstract from the server, and storing the information flow abstract and the information flow as data objects so that the user can view the information flow abstract conveniently.
9. The method of claim 8, wherein the non-textual content is an audio file and/or a video file.
10. The method of claim 8, wherein the information flow summary generation instructions are full summary instructions, the information flow including non-textual content;
the preprocessing the information stream to obtain an information stream text includes: converting the non-text content to text content.
11. The method according to any one of claims 8 to 10, wherein said presenting the information flow summary comprises:
and generating an information flow abstract list for the information flow abstract, wherein the information flow abstract list is ordered according to at least one item of the user identification, the information flow generation time and the correlation degree of the keywords input by the user.
12. A method for generating and displaying an information flow abstract is applied to a server and is characterized by comprising the following steps:
receiving an information stream from a client; the information stream comprises textual content and non-textual content;
preprocessing the information flow to obtain an information flow text; the information flow text obtained by preprocessing the non-text content has different weights with the information flow text corresponding to the text content;
generating an information flow abstract based on the information flow text according to a pre-established abstract generating model; generating a more detailed information flow abstract for the information flow text corresponding to the text content;
sending the information flow abstract to the client so that the client can receive and display the information flow abstract and a user can check the information flow abstract;
wherein sending the information flow summary to the client comprises:
storing the information flow abstract and the information flow as data objects, and sending the data objects to the client for storage; or the like, or a combination thereof,
sending the information flow abstract to the client; and receiving the information flow abstract by the client, and storing the information flow abstract and the corresponding information flow as a data object.
13. The method of claim 12, wherein the non-textual content comprises an audio file and/or a video file.
14. The method of claim 12, wherein the information stream includes non-text content, and wherein pre-processing the information stream to obtain information stream text comprises: converting the non-text content to text content.
15. The method of claim 12, wherein generating the summary of the information flow based on the text of the information flow according to a pre-established summary generation model comprises:
dividing the information stream text into one or more information stream text groups;
and inputting the text of the information flow text group into the pre-established abstract generation model to obtain the corresponding information flow abstract generated by the pre-established abstract generation model.
16. The method of claim 15, wherein the dividing the stream text into one or more stream text groups comprises:
and analyzing the theme and/or intention of the information flow text, and dividing the information flow text into one or more information flow text groups.
17. The method of any of claims 12 to 16, wherein prior to generating a stream summary based on the stream text according to a pre-established summary generation model, the method further comprises:
acquiring a preset number of information flow text group samples and abstract samples corresponding to each information flow text group sample in the preset number of information flow text group samples;
performing vectorization processing on each information flow text group sample and the abstract sample corresponding to each information flow text group sample to obtain a vectorized information flow text group sample and a vectorized abstract sample;
inputting the vectorized information flow text group samples and the vectorized abstract samples into a pre-established neural network structure for multiple iterations, calculating the probability of generating each vectorized abstract sample in the vectorized abstract samples according to each vectorized information flow text group sample in the vectorized abstract samples, and maximizing the probability of generating corresponding vectorized abstract samples according to the vectorized information flow text group samples obtained after the iterations to obtain the abstract generation model.
18. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-17.
19. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-17.
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 CN108846098A (en) | 2018-11-20 |
| CN108846098B true 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) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111914115B (en) * | 2019-05-08 | 2024-05-28 | 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 |
| 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 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699611A (en) * | 2013-12-16 | 2014-04-02 | 浙江大学 | Microblog flow information extracting method based on dynamic digest technology |
| 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 |
Family Cites Families (5)
| 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 |
| JP5327737B2 (en) * | 2008-03-06 | 2013-10-30 | 独立行政法人情報通信研究機構 | Dialogue device, weight information learning device, dialogue method, weight information learning method, and program |
| CN104375977B (en) * | 2013-08-14 | 2018-11-23 | 腾讯科技（深圳）有限公司 | The processing method and processing device of reply message in Ask-Answer Community |
| 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 |
| JP6604836B2 (en) * | 2015-12-14 | 2019-11-13 | 株式会社日立製作所 | Dialog text summarization apparatus and method |
-
2018
- 2018-06-15 CN CN201810622659.9A patent/CN108846098B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699611A (en) * | 2013-12-16 | 2014-04-02 | 浙江大学 | Microblog flow information extracting method based on dynamic digest technology |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108846098A (en) | 2018-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10740545B2 (en) | Information extraction from open-ended schema-less tables | |
| US9923860B2 (en) | Annotating content with contextually relevant comments | |
| US8959109B2 (en) | Business intelligent in-document suggestions | |
| US9336202B2 (en) | Method and system relating to salient content extraction for electronic content | |
| US9720904B2 (en) | Generating training data for disambiguation | |
| US20160328378A1 (en) | Anaphora resolution for semantic tagging | |
| US8903809B2 (en) | Contextual search history in collaborative archives | |
| CN107491477B (en) | Emotion symbol searching method and device | |
| CN111368043A (en) | Event question-answering method, device, equipment and storage medium based on artificial intelligence | |
| US8977620B1 (en) | Method and system for document classification | |
| CN112395420A (en) | Video content retrieval method and device, computer equipment and storage medium | |
| CN108846098B (en) | Information flow abstract generating and displaying method | |
| CN115982376B (en) | Method and device for training model based on text, multimode data and knowledge | |
| CN114328996A (en) | Method and device for publishing information | |
| US9756057B2 (en) | System and method for enhanced display-screen security and privacy | |
| CN111414471B (en) | Method and device for outputting information | |
| CN113806588A (en) | Method and device for searching video | |
| CN111078849B (en) | Method and device for outputting information | |
| US11437038B2 (en) | Recognition and restructuring of previously presented materials | |
| CN111555960A (en) | Method for generating information | |
| CN111382262A (en) | Method and apparatus for outputting information | |
| CN115640790A (en) | Information processing method and device and electronic equipment | |
| CN110276001B (en) | Checking page identification method and device, computing equipment and medium | |
| CN116303296B (en) | Data storage method, device, electronic equipment and medium | |
| US11804245B2 (en) | Video data size reduction |
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 |
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. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |