CN112600750A - Method and device for processing multiple pieces of dialogue information in instant messaging - Google Patents
Method and device for processing multiple pieces of dialogue information in instant messaging Download PDFInfo
- Publication number
- CN112600750A CN112600750A CN202011561850.0A CN202011561850A CN112600750A CN 112600750 A CN112600750 A CN 112600750A CN 202011561850 A CN202011561850 A CN 202011561850A CN 112600750 A CN112600750 A CN 112600750A
- Authority
- CN
- China
- Prior art keywords
- information
- pieces
- dialogue
- text
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012545 processing Methods 0.000 title claims abstract description 26
- 238000005516 engineering process Methods 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 4
- 238000003058 natural language processing Methods 0.000 abstract description 8
- 101150054987 ChAT gene Proteins 0.000 description 40
- 101100203187 Mus musculus Sh2d3c gene Proteins 0.000 description 40
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/02—Details
- H04L12/16—Arrangements for providing special services to substations
- H04L12/18—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast
- H04L12/1813—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast for computer conferences, e.g. chat rooms
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the specification provides a method and a device for processing a plurality of pieces of dialogue information in instant messaging, wherein the method comprises the following steps: when a preset trigger condition is met, acquiring a plurality of pieces of dialogue information in instant messaging, wherein the plurality of pieces of dialogue information comprise text information and/or voice information; combining the plurality of pieces of dialogue information to obtain a combined dialogue text; carrying out abstract extraction on the combined conversation text to obtain abstract information comprising keywords; determining target dialogue information corresponding to the keyword from the plurality of pieces of dialogue information; and displaying the abstract information, and linking the keyword to the target conversation information. The efficiency of obtaining information by a user in instant messaging can be improved, and especially when a plurality of pieces of dialogue information comprise voice information, the method is realized by combining a voice recognition technology and a natural language processing technology, so that the efficiency is improved more remarkably.
Description
Technical Field
One or more embodiments of the present specification relate to the field of computers, and in particular, to a method and an apparatus for processing multiple pieces of dialog information in instant messaging.
Background
Instant Messaging (IM) is the most popular communication method on the internet at present, and can send and receive messages instantly, for example, instant messaging can be performed between users through chat software, chat rooms, and the like.
The scheme of each IM product at present needs a user to check interactive messages individually, and when the information backlog is large and new messages are generated continuously, the user needs to check chat records completely, so that the efficiency of obtaining information by the user is low, and the user is difficult to enter the chat situation quickly.
Accordingly, improved solutions are desired that can improve the efficiency of obtaining information by a user in instant messaging.
Disclosure of Invention
One or more embodiments of the present specification describe a method and an apparatus for processing multiple pieces of session information in instant messaging, which can improve the efficiency of obtaining information by a user in instant messaging.
In a first aspect, a method for processing multiple pieces of dialog information in instant messaging is provided, and the method includes:
when a preset trigger condition is met, acquiring a plurality of pieces of dialogue information in instant messaging, wherein the plurality of pieces of dialogue information comprise text information and/or voice information;
combining the plurality of pieces of dialogue information to obtain a combined dialogue text;
carrying out abstract extraction on the combined conversation text to obtain abstract information comprising keywords;
determining target dialogue information corresponding to the keyword from the plurality of pieces of dialogue information;
and displaying the abstract information, and linking the keyword to the target conversation information.
In a possible implementation, the summary information further includes auxiliary words; the displaying the summary information comprises:
and displaying auxiliary words included in the summary information in a first mode, and displaying keywords included in the summary information in a second mode.
In a possible implementation, after the presenting the summary information, the method further includes:
and skipping to the target dialogue information when the preset operation of the keyword is received.
In a possible implementation, the triggering condition includes:
receiving a first instruction, wherein the first instruction is used for indicating to enter a first type of chat interface; and/or the presence of a gas in the gas,
the number of pieces of unread dialog information is greater than a first threshold value; and/or the presence of a gas in the gas,
and receiving a second instruction, wherein the second instruction is used for instructing to execute the acquisition of the plurality of pieces of session information in the instant messaging.
Further, the first type is a group chat type of a multi-person chat or a single chat type of a two-person chat.
In a possible implementation manner, the obtaining multiple pieces of dialog information in the instant messaging includes:
acquiring all unread conversation information in instant messaging; or,
and acquiring a preset number of pieces of unread dialog information in instant messaging.
In a possible implementation manner, the merging the plurality of pieces of dialog information to obtain a merged dialog text includes:
judging whether the plurality of pieces of dialogue information comprise voice information or not;
and if the judgment result is that the plurality of pieces of dialogue information do not include the voice information, combining the text information in the plurality of pieces of dialogue information to obtain the combined dialogue text.
In a possible implementation manner, the merging the plurality of pieces of dialog information to obtain a merged dialog text includes:
judging whether the plurality of pieces of dialogue information comprise voice information or not;
if the judgment result is that the plurality of pieces of dialogue information comprise voice information, acquiring a character result after the voice information is converted into characters;
and combining the text information and the character result in the plurality of pieces of dialogue information to obtain the combined dialogue text.
Further, the obtaining of the text result after the voice information is converted into the text includes:
inquiring whether a character result obtained after the asynchronously generated voice information is converted into characters exists or not;
and if so, reading the text result.
Further, after querying whether a text result after the voice information is converted into text already exists, the method further includes:
if not, identifying the voice information through an automatic voice identification technology to obtain a character result after the voice information is converted into characters.
Further, the literal result is asynchronously generated by:
monitoring conversation information in instant messaging;
when the dialogue information is voice information, recognizing the voice information through an automatic voice recognition technology to obtain a character result after the voice information is converted into characters;
and storing the text result.
In a second aspect, an apparatus for processing multiple pieces of dialog information in instant messaging is provided, the apparatus comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a plurality of pieces of dialogue information in instant messaging when a preset trigger condition is met, and the plurality of pieces of dialogue information comprise text information and/or voice information;
the merging unit is used for merging the plurality of pieces of dialogue information acquired by the acquisition unit to obtain a merged dialogue text;
the extraction unit is used for carrying out abstract extraction on the combined conversation text obtained by the combination unit to obtain abstract information comprising key words;
a determining unit configured to determine target dialogue information corresponding to the keyword obtained by the extracting unit from the plurality of pieces of dialogue information obtained by the obtaining unit;
and the display unit is used for displaying the abstract information obtained by the extraction unit and linking the keyword to the target conversation information determined by the determination unit.
In a third aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of the first aspect.
In a fourth aspect, there is provided a computing device comprising a memory having stored therein executable code and a processor that, when executing the executable code, implements the method of the first aspect.
According to the method and the device provided by the embodiment of the specification, firstly, when a preset trigger condition is met, a plurality of pieces of dialogue information in instant messaging are acquired, wherein the plurality of pieces of dialogue information comprise text information and/or voice information; then combining the plurality of pieces of dialogue information to obtain a combined dialogue text; then, abstract extraction is carried out on the combined dialog text to obtain abstract information comprising keywords; determining target dialogue information corresponding to the keywords from the plurality of dialogue information; and finally, displaying the abstract information and linking the keyword to the target conversation information. As can be seen from the above, in the embodiment of the present specification, by processing a plurality of pieces of session information in instant messaging, obtaining summary information including a keyword and target session information corresponding to the keyword, displaying the summary information, and linking the keyword to the target session information, a user can obtain the keyword in the plurality of pieces of session information by browsing the summary information without browsing the plurality of pieces of session information one by one, and skip to the target session information by operating the keyword by the user, so as to further understand session content, and improve efficiency of obtaining information by the user in instant messaging, especially when the plurality of pieces of session information include voice information, the efficiency is improved more significantly by combining a voice recognition technology and a natural language processing technology.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram illustrating an implementation scenario of an embodiment disclosed herein;
FIG. 2 illustrates a flow diagram of a method for processing multiple pieces of dialog information in instant messaging, according to one embodiment;
FIG. 3 illustrates a user interface diagram according to one embodiment;
FIG. 4 shows a user interface diagram according to another embodiment;
FIG. 5 illustrates a foreground flow diagram according to one embodiment;
FIG. 6 illustrates a background flow diagram according to one embodiment;
fig. 7 shows a schematic block diagram of a processing device for a plurality of pieces of dialog information in instant messaging according to an embodiment.
Detailed Description
The scheme provided by the specification is described below with reference to the accompanying drawings.
Fig. 1 is a schematic view of an implementation scenario of an embodiment disclosed in this specification. The implementation scenario involves the processing of multiple pieces of dialog information in instant messaging. Referring to fig. 1, taking a group chat scenario in instant messaging as an example, the chat group shown in fig. 1 has 100 people in all, and these 100 people are respectively denoted as user 1, user 2, and … … user 100, where when a user 10 enters a chat interface of the chat group, 13 pieces of unread dialog information are displayed on the chat interface, the dialog information is dialog information of user 1, user 2, and user 3, and the dialog information may be text information, voice information, picture information, video information, and the like, and if reading each piece of information one by one, it takes a long time.
In the embodiment of the description, not only are each piece of dialog information displayed in the chat interface, but also summary information corresponding to a plurality of pieces of dialog information is displayed, the summary information includes one or more keywords, for example, the summary information shown in the figure includes three keywords, and each keyword is respectively linked to the corresponding target dialog information, so that a user can acquire the keywords in the plurality of pieces of dialog information by browsing the summary information without browsing the plurality of pieces of dialog information one by one, and can jump to the target dialog information by operating the keywords by the user, further know the dialog content, and improve the efficiency of acquiring information by the user in instant messaging.
Group chat: the chat tool is a chat mode of the chat tool, and three or more users can simultaneously transmit texts, voice or videos. In this chat mode, it is easy to accumulate a large amount of unread dialog information, and thus, this may be used as a typical application scenario of the embodiments of the present specification.
It should be noted that the present embodiment is not limited to the application scenario of the group chat, but is also applicable to an application scenario of a single chat that only enables two-person chat, for example, when the user 1 opens the chat interface with the user 2, there may be a plurality of pieces of dialog information that the user 1 has already input, and the plurality of pieces of dialog information belong to unread dialog information for the user 2, and by applying the method provided by the present embodiment, the efficiency of the user obtaining information in instant messaging can also be improved. In addition, in the embodiment of the present specification, it is not limited that a plurality of pieces of session information are definitely unread session information, and the read session information may also be processed in a similar manner, so that a user can review the previous session content quickly, and the efficiency of obtaining information by the user in instant messaging can also be improved.
Fig. 2 is a flowchart illustrating a method for processing multiple pieces of dialog information in instant messaging according to an embodiment, where the method may be based on the implementation scenario illustrated in fig. 1, and the execution subject may be a terminal used by a user, where the terminal may be, but is not limited to, a mobile phone, a tablet, a computer, and the like. As shown in fig. 2, the method for processing multiple pieces of session information in instant messaging in this embodiment includes the following steps: step 21, when a preset trigger condition is met, acquiring a plurality of pieces of dialogue information in instant messaging, wherein the plurality of pieces of dialogue information comprise text information and/or voice information; step 22, combining the plurality of pieces of dialogue information to obtain a combined dialogue text; step 23, abstract extraction is carried out on the merged dialog text to obtain abstract information comprising keywords; step 24, determining target dialogue information corresponding to the keyword from the plurality of dialogue information; and step 25, displaying the summary information and linking the keywords to the target conversation information. Specific execution modes of the above steps are described below.
Firstly, in step 21, when a preset trigger condition is met, a plurality of pieces of dialogue information in instant messaging are acquired, wherein the plurality of pieces of dialogue information comprise text information and/or voice information. It can be understood that the trigger condition may be associated with an operation of a user, and the user may issue a predetermined instruction through an operation such as a mouse click or a touch on a touch screen.
In one example, the trigger condition includes:
receiving a first instruction, wherein the first instruction is used for indicating to enter a first type of chat interface; and/or the presence of a gas in the gas,
the number of pieces of unread dialog information is greater than a first threshold value; and/or the presence of a gas in the gas,
and receiving a second instruction, wherein the second instruction is used for instructing to execute the acquisition of the plurality of pieces of session information in the instant messaging.
Further, the first type is a group chat type of a multi-person chat or a single chat type of a two-person chat.
For example, fig. 3 is a schematic diagram of a user interface according to an embodiment, referring to fig. 3, a user enters a chat interface, if the unread information is too much, for example, the unread information exceeds 10 pieces of unread information, prompt information "whether to view summary information" is displayed, and a button "yes" and a button "no" are displayed, and after the user clicks the button "yes", the system acquires a plurality of pieces of conversation information in instant messaging. The user enters a chat interface and correspondingly receives a first instruction; the aforementioned user clicking on the button "yes" corresponds to receiving the second instruction.
In one example, the obtaining of the pieces of dialogue information in the instant messaging includes:
acquiring all unread conversation information in instant messaging; or,
and acquiring a preset number of pieces of unread dialog information in instant messaging.
It can be understood that all the unread dialog messages in the instant messaging can be obtained no matter how many unread dialog messages exist; or, a number threshold may be preset, and if the number of unread dialog messages is greater than the number threshold, a preset number of unread dialog messages in the instant messaging is obtained, where the preset number may be less than or equal to the number threshold; and if the number of the unread dialog messages is less than or equal to the number threshold, acquiring all the unread dialog messages in the instant messaging. For example, the preset number threshold is 20, and if the number of pieces of unread dialog information is 100, the 100 pieces of unread dialog information may be divided into 5 groups, each group of 20 pieces of unread dialog information is obtained, the unread dialog information of one group is obtained first, and the unread dialog information of each group is processed respectively.
In this embodiment of the present description, a plurality of pieces of dialog information that need to be acquired may also be selected from each piece of dialog information displayed in the user interface according to an operation of the user. For example, fig. 4 shows a schematic diagram of a user interface according to another embodiment, referring to fig. 4, a user defines an area by a frame selection operation, where the area includes session information 4 to session information 13, and step 21 is specifically to acquire a plurality of pieces of session information in the area selected by the user.
The plurality of pieces of dialog information are then merged, resulting in a merged dialog text, at step 22. It is understood that the plurality of pieces of dialog information acquired in step 21 may include one or more of text information, voice information, picture information and video information, and the various pieces of dialog information need to be processed separately in the merging process.
In one example, the merging the plurality of pieces of dialog information to obtain a merged dialog text includes:
judging whether the plurality of pieces of dialogue information comprise voice information or not;
and if the judgment result is that the plurality of pieces of dialogue information do not include the voice information, combining the text information in the plurality of pieces of dialogue information to obtain the combined dialogue text.
In one example, the merging the plurality of pieces of dialog information to obtain a merged dialog text includes:
judging whether the plurality of pieces of dialogue information comprise voice information or not;
if the judgment result is that the plurality of pieces of dialogue information comprise voice information, acquiring a character result after the voice information is converted into characters;
and combining the text information and the character result in the plurality of pieces of dialogue information to obtain the combined dialogue text.
It can be understood that, when the plurality of pieces of session information further include picture information or video information, no processing may be performed on the picture information and the video information, that is, the picture information and the video information are ignored; or converting the picture information into a text result, and merging the text result in the same way as the text information; or, the voice result contained in the video information is extracted, and when the video information is included in the plurality of pieces of dialogue information, the plurality of pieces of dialogue information are considered to include the voice information.
Further, the obtaining of the text result after the voice information is converted into the text includes:
inquiring whether a character result obtained after the asynchronously generated voice information is converted into characters exists or not;
and if so, reading the text result.
It can be understood that the time consumption for converting the voice information into the characters is long, the character results after the voice information is converted into the characters through asynchronous generation are obtained in advance, the character results are directly read when needed, the waiting time of a user can be reduced, and the user experience is improved.
Further, after querying whether a text result after the voice information is converted into text already exists, the method further includes:
if not, identifying the voice information through an automatic voice identification technology to obtain a character result after the voice information is converted into characters.
It will be appreciated that for the speech information just received, there may not yet be an asynchronously generated textual result, and the speech information may be recognized in real time by automatic speech recognition techniques.
Among them, the Automatic Speech Recognition (ASR) technology is a technology for converting human speech into text, and various solutions can be adopted.
Further, the literal result is asynchronously generated by:
monitoring conversation information in instant messaging;
when the dialogue information is voice information, recognizing the voice information through an automatic voice recognition technology to obtain a character result after the voice information is converted into characters;
and storing the text result.
It will be appreciated that the above-described asynchronous generation process may occur before step 21, thereby effectively saving the user waiting time.
Then, in step 23, abstract extraction is performed on the merged dialog text to obtain abstract information including keywords. It is understood that the summary information may include only a number of keywords, or the summary information may include a number of auxiliary words in addition to a number of keywords to constitute a sentence, thereby expressing complete semantic information.
The abstract extraction refers to automatically summarizing the main content of a document by using a computer program under the condition of not changing the original meaning of the document. The abstract extraction can be realized through keyword extraction.
Keyword extraction refers to an application technology for automatically extracting key information of entities, relations, events and the like of specified types from natural language texts. Keyword extraction may be performed by a Natural Language Processing (NLP) model.
In step 24, the target dialogue information corresponding to the keyword is determined from the plurality of pieces of dialogue information. It is understood that when the summary information including a plurality of keywords is obtained in step 23, the target dialog information corresponding to each keyword needs to be determined in step 24.
For example, the plurality of pieces of session information include session information 1, session information 2, and … …, the digest information includes a keyword 1, a keyword 2, and a keyword 3, the target session information corresponding to the keyword 1 is the session information 2, the target session information corresponding to the keyword 2 is the session information 4, and the target session information corresponding to the keyword 3 is the session information 5.
In the embodiments of the present specification, how to identify the target dialog information corresponding to the keyword may be implemented in various ways, for example, when the keyword, the synonym of the keyword, or the synonym of the keyword exists in the dialog information, the dialog information is considered as the target dialog information corresponding to the keyword.
Finally, in step 25, the summary information is presented and the keywords are linked to the target dialog information. It is understood that the relation between the keyword and the target dialog information may be established by means of a link, wherein the specific manner of the link may be the manner of an anchor link.
In one example, the summary information further includes auxiliary words; the displaying the summary information comprises:
and displaying auxiliary words included in the summary information in a first mode, and displaying keywords included in the summary information in a second mode.
It can be understood that the first manner is different from the second manner, and specifically, the font may be different, or the color of the character may be different, the size of the character may be different, whether underlining exists or not, and the like, so as to visually represent the difference in importance between the auxiliary word and the keyword.
In one example, after the presenting the summary information, the method further comprises:
and skipping to the target dialogue information when the preset operation of the keyword is received.
For example, when the user clicks the keyword, the target dialog information is displayed at a more prominent position on the screen, for example, the initial display position of the target dialog information is not easily noticed visually at the lower part of the screen, and the display position of the target dialog information can be adjusted at the upper part of the screen, so that the user can notice more easily; or, the target dialogue information is not displayed on the current screen, and the target dialogue information is displayed on the current screen through page jump. Furthermore, underlining or other annotations can be added below the target dialog information, so that the user can more easily notice the target dialog information. In this way, the user can know the important content of the conversation only by browsing the target conversation information corresponding to the keyword without browsing all unread conversation information.
According to the method provided by the embodiment of the specification, firstly, when a preset trigger condition is met, a plurality of pieces of dialogue information in instant messaging are acquired, wherein the plurality of pieces of dialogue information comprise text information and/or voice information; then combining the plurality of pieces of dialogue information to obtain a combined dialogue text; then, abstract extraction is carried out on the combined dialog text to obtain abstract information comprising keywords; determining target dialogue information corresponding to the keywords from the plurality of dialogue information; and finally, displaying the abstract information and linking the keyword to the target conversation information. As can be seen from the above, in the embodiment of the present specification, by processing a plurality of pieces of session information in instant messaging, obtaining summary information including a keyword and target session information corresponding to the keyword, displaying the summary information, and linking the keyword to the target session information, a user can obtain the keyword in the plurality of pieces of session information by browsing the summary information without browsing the plurality of pieces of session information one by one, and skip to the target session information by operating the keyword by the user, so as to further understand session content, and improve efficiency of obtaining information by the user in instant messaging, especially when the plurality of pieces of session information include voice information, the efficiency is improved more significantly by combining a voice recognition technology and a natural language processing technology.
Generally, the most important dialog messages are text messages and voice messages, wherein most of the chat software and chat rooms support voice input, and it is difficult to quickly acquire core contents especially in group chat scenarios where a large amount of voice messages are accumulated. The voice information needs to be completely listened to before the information content can be obtained; and the speech often has a large amount of useless information such as tone words, stop words and the like; most voice message playback cannot be accelerated. The above characteristics of the voice information result in very inefficient acquisition of the voice information. The method provided by the embodiment of the specification can help the user to quickly acquire the key information in the chat. The scheme comprises a foreground flow and a background flow, wherein the foreground flow refers to a process executed in real time after the operation of a user, the background flow refers to a process executed asynchronously after a system acquires a monitoring result, and the background flow has no perception on the user.
FIG. 5 illustrates a foreground flow diagram according to one embodiment. Referring to fig. 5, by a user operation, the foreground flow starts:
if the judgment result is no, executing step 59; if the judgment result is yes, the steps are executed in sequence.
if yes, go to step 55; if the determination result is negative, step 56 is executed.
wherein, the key words included in the abstract information are linked to the original words or voices by anchor points.
wherein, the method comprises displaying keywords included in the summary information.
And step 59, ending.
FIG. 6 illustrates a background flow diagram according to one embodiment. Referring to fig. 6, the background flow begins:
step 61, monitoring a received message;
if the judgment result is no, executing step 63; if yes, go to step 64.
Step 63, skipping;
and step 66, ending the background process.
It is understood that the aforementioned NLP model and ASR model can be deployed locally at the terminal, or at the server.
In the embodiment of the present description, division of the foreground process and the background process may be appropriately adjusted, for example, both the speech and text processing processes may be asynchronous in the background, so as to further shorten the waiting time of the user, and for example, the speech and text processing processes may also be completely executed synchronously after the user operates under the condition that the privacy of the user is not allowed.
According to another embodiment, a device for processing multiple pieces of dialogue information in instant messaging is also provided, and the device is used for executing the processing method for multiple pieces of dialogue information in instant messaging provided by the embodiment of the specification. Fig. 7 shows a schematic block diagram of a processing device for a plurality of pieces of dialog information in instant messaging according to an embodiment. As shown in fig. 7, the apparatus 700 includes:
the acquiring unit 71 is configured to acquire a plurality of pieces of session information in instant messaging when a preset trigger condition is met, where the plurality of pieces of session information include text information and/or voice information;
a merging unit 72, configured to merge the pieces of dialog information acquired by the acquiring unit 71 to obtain a merged dialog text;
an extracting unit 73, configured to perform abstract extraction on the merged dialog text obtained by the merging unit 72 to obtain abstract information including keywords;
a determining unit 74 configured to determine target dialogue information corresponding to the keyword obtained by the extracting unit from the plurality of pieces of dialogue information obtained by the obtaining unit 71;
a presentation unit 75, configured to present the summary information obtained by the extraction unit 73, and link the keyword to the target session information determined by the determination unit 74.
Optionally, as an embodiment, the summary information further includes auxiliary words; the display unit 75 is specifically configured to display auxiliary words included in the summary information in a first manner, and display keywords included in the summary information in a second manner.
Optionally, as an embodiment, the apparatus further includes:
a skipping unit, configured to skip to the target dialog information when a preset operation on the keyword is received after the display unit 75 displays the summary information.
Optionally, as an embodiment, the trigger condition includes:
receiving a first instruction, wherein the first instruction is used for indicating to enter a first type of chat interface; and/or the presence of a gas in the gas,
the number of pieces of unread dialog information is greater than a first threshold value; and/or the presence of a gas in the gas,
and receiving a second instruction, wherein the second instruction is used for instructing to execute the acquisition of the plurality of pieces of session information in the instant messaging.
Further, the first type is a group chat type of a multi-person chat or a single chat type of a two-person chat.
Optionally, as an embodiment, the obtaining unit 71 is specifically configured to obtain all unread dialog information in the instant messaging; or, obtaining a preset number of pieces of unread dialog information in the instant messaging.
Optionally, as an embodiment, the merging unit 72 includes:
a judging subunit, configured to judge whether the plurality of pieces of dialog information include voice information;
and the first merging subunit is configured to merge text information in the plurality of pieces of dialog information to obtain the merged dialog text, if the judgment result of the judging subunit is that the plurality of pieces of dialog information do not include the voice information.
Optionally, as an embodiment, the merging unit 72 includes:
a judging subunit, configured to judge whether the plurality of pieces of dialog information include voice information;
the obtaining subunit is configured to obtain a text result after the voice information is converted into text if the judgment result of the judging subunit is that the plurality of pieces of dialog information include the voice information;
and the second merging subunit is used for merging the text information in the plurality of pieces of dialogue information and the character result acquired by the acquiring subunit to obtain the merged dialogue text.
Further, the acquiring subunit includes:
the query module is used for querying whether a character result obtained after the asynchronously generated voice information is converted into characters exists or not;
and the reading module is used for reading the character result if the query result of the query module exists.
Further, the acquiring subunit further includes:
and the recognition module is used for recognizing the voice information through an automatic voice recognition technology to obtain a character result of the voice information converted into the characters if the query module queries whether the character result of the voice information converted into the characters exists or not and the query module does not query whether the character result of the voice information converted into the characters exists or not.
Further, the literal result is asynchronously generated by:
monitoring conversation information in instant messaging;
when the dialogue information is voice information, recognizing the voice information through an automatic voice recognition technology to obtain a character result after the voice information is converted into characters;
and storing the text result.
With the apparatus provided in this specification, first, when a preset trigger condition is met, the obtaining unit 71 obtains a plurality of pieces of dialog information in instant messaging, where the plurality of pieces of dialog information include text information and/or voice information; then the merging unit 72 merges the plurality of pieces of dialog information to obtain a merged dialog text; then, the extracting unit 73 extracts the summary of the merged dialog text to obtain summary information including keywords; the determining unit 74 determines target dialogue information corresponding to the keyword from the plurality of pieces of dialogue information; finally, the presentation unit 75 presents the summary information and links the keyword to the target dialog information. As can be seen from the above, in the embodiment of the present specification, by processing a plurality of pieces of session information in instant messaging, obtaining summary information including a keyword and target session information corresponding to the keyword, displaying the summary information, and linking the keyword to the target session information, a user can obtain the keyword in the plurality of pieces of session information by browsing the summary information without browsing the plurality of pieces of session information one by one, and skip to the target session information by operating the keyword by the user, so as to further understand session content, and improve efficiency of obtaining information by the user in instant messaging, especially when the plurality of pieces of session information include voice information, the efficiency is improved more significantly by combining a voice recognition technology and a natural language processing technology.
According to an embodiment of another aspect, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method described in connection with fig. 2.
According to an embodiment of yet another aspect, there is also provided a computing device comprising a memory and a processor, the memory having stored therein executable code, the processor, when executing the executable code, implementing the method described in connection with fig. 2.
Those skilled in the art will recognize that, in one or more of the examples described above, the functions described in this invention may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present invention should be included in the scope of the present invention.
Claims (24)
1. A method for processing a plurality of pieces of dialogue information in instant messaging, the method comprising:
when a preset trigger condition is met, acquiring a plurality of pieces of dialogue information in instant messaging, wherein the plurality of pieces of dialogue information comprise text information and/or voice information;
combining the plurality of pieces of dialogue information to obtain a combined dialogue text;
carrying out abstract extraction on the combined conversation text to obtain abstract information comprising keywords;
determining target dialogue information corresponding to the keyword from the plurality of pieces of dialogue information;
and displaying the abstract information, and linking the keyword to the target conversation information.
2. The method of claim 1, wherein the summary information further includes auxiliary words; the displaying the summary information comprises:
and displaying auxiliary words included in the summary information in a first mode, and displaying keywords included in the summary information in a second mode.
3. The method of claim 1, wherein after said presenting said summary information, said method further comprises:
and skipping to the target dialogue information when the preset operation of the keyword is received.
4. The method of claim 1, wherein the trigger condition comprises:
receiving a first instruction, wherein the first instruction is used for indicating to enter a first type of chat interface; and/or the presence of a gas in the gas,
the number of pieces of unread dialog information is greater than a first threshold value; and/or the presence of a gas in the gas,
and receiving a second instruction, wherein the second instruction is used for instructing to execute the acquisition of the plurality of pieces of session information in the instant messaging.
5. The method of claim 4, wherein the first type is a group chat type of a multi-person chat or a single chat type of a two-person chat.
6. The method of claim 1, wherein the obtaining of the plurality of pieces of dialog information in the instant messaging comprises:
acquiring all unread conversation information in instant messaging; or,
and acquiring a preset number of pieces of unread dialog information in instant messaging.
7. The method of claim 1, wherein said merging the plurality of pieces of dialog information to obtain a merged dialog text comprises:
judging whether the plurality of pieces of dialogue information comprise voice information or not;
and if the judgment result is that the plurality of pieces of dialogue information do not include the voice information, combining the text information in the plurality of pieces of dialogue information to obtain the combined dialogue text.
8. The method of claim 1, wherein said merging the plurality of pieces of dialog information to obtain a merged dialog text comprises:
judging whether the plurality of pieces of dialogue information comprise voice information or not;
if the judgment result is that the plurality of pieces of dialogue information comprise voice information, acquiring a character result after the voice information is converted into characters;
and combining the text information and the character result in the plurality of pieces of dialogue information to obtain the combined dialogue text.
9. The method of claim 8, wherein the obtaining the text result after the voice message is converted into the text comprises:
inquiring whether a character result obtained after the asynchronously generated voice information is converted into characters exists or not;
and if so, reading the text result.
10. The method of claim 9, wherein after querying whether there is a textual result after the voice message is converted to text, the method further comprises:
if not, identifying the voice information through an automatic voice identification technology to obtain a character result after the voice information is converted into characters.
11. The method of claim 9, wherein the textual results are generated asynchronously by:
monitoring conversation information in instant messaging;
when the dialogue information is voice information, recognizing the voice information through an automatic voice recognition technology to obtain a character result after the voice information is converted into characters;
and storing the text result.
12. An apparatus for processing a plurality of pieces of dialog information in instant messaging, the apparatus comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a plurality of pieces of dialogue information in instant messaging when a preset trigger condition is met, and the plurality of pieces of dialogue information comprise text information and/or voice information;
the merging unit is used for merging the plurality of pieces of dialogue information acquired by the acquisition unit to obtain a merged dialogue text;
the extraction unit is used for carrying out abstract extraction on the combined conversation text obtained by the combination unit to obtain abstract information comprising key words;
a determining unit configured to determine target dialogue information corresponding to the keyword obtained by the extracting unit from the plurality of pieces of dialogue information obtained by the obtaining unit;
and the display unit is used for displaying the abstract information obtained by the extraction unit and linking the keyword to the target conversation information determined by the determination unit.
13. The apparatus of claim 12, wherein the summary information further comprises auxiliary words; the display unit is specifically configured to display auxiliary words included in the summary information in a first manner, and display keywords included in the summary information in a second manner.
14. The apparatus of claim 12, wherein the apparatus further comprises:
and the skipping unit is used for skipping to the target dialogue information when receiving the preset operation of the keyword after the summary information is displayed by the display unit.
15. The apparatus of claim 12, wherein the trigger condition comprises:
receiving a first instruction, wherein the first instruction is used for indicating to enter a first type of chat interface; and/or the presence of a gas in the gas,
the number of pieces of unread dialog information is greater than a first threshold value; and/or the presence of a gas in the gas,
and receiving a second instruction, wherein the second instruction is used for instructing to execute the acquisition of the plurality of pieces of session information in the instant messaging.
16. The apparatus of claim 15, wherein the first type is a group chat type of a multi-person chat or a single chat type of a two-person chat.
17. The apparatus according to claim 12, wherein the obtaining unit is specifically configured to obtain all unread dialog information in the instant messaging; or, obtaining a preset number of pieces of unread dialog information in the instant messaging.
18. The apparatus of claim 12, wherein the merging unit comprises:
a judging subunit, configured to judge whether the plurality of pieces of dialog information include voice information;
and the first merging subunit is configured to merge text information in the plurality of pieces of dialog information to obtain the merged dialog text, if the judgment result of the judging subunit is that the plurality of pieces of dialog information do not include the voice information.
19. The apparatus of claim 12, wherein the merging unit comprises:
a judging subunit, configured to judge whether the plurality of pieces of dialog information include voice information;
the obtaining subunit is configured to obtain a text result after the voice information is converted into text if the judgment result of the judging subunit is that the plurality of pieces of dialog information include the voice information;
and the second merging subunit is used for merging the text information in the plurality of pieces of dialogue information and the character result acquired by the acquiring subunit to obtain the merged dialogue text.
20. The apparatus of claim 19, wherein the acquisition subunit comprises:
the query module is used for querying whether a character result obtained after the asynchronously generated voice information is converted into characters exists or not;
and the reading module is used for reading the character result if the query result of the query module exists.
21. The apparatus of claim 20, wherein the acquisition subunit further comprises:
and the recognition module is used for recognizing the voice information through an automatic voice recognition technology to obtain a character result of the voice information converted into the characters if the query module queries whether the character result of the voice information converted into the characters exists or not and the query module does not query whether the character result of the voice information converted into the characters exists or not.
22. The apparatus of claim 20, wherein the textual result is generated asynchronously by:
monitoring conversation information in instant messaging;
when the dialogue information is voice information, recognizing the voice information through an automatic voice recognition technology to obtain a character result after the voice information is converted into characters;
and storing the text result.
23. A computer-readable storage medium, on which a computer program is stored which, when executed in a computer, causes the computer to carry out the method of any one of claims 1-11.
24. A computing device comprising a memory having stored therein executable code and a processor that, when executing the executable code, implements the method of any of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011561850.0A CN112600750A (en) | 2020-12-25 | 2020-12-25 | Method and device for processing multiple pieces of dialogue information in instant messaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011561850.0A CN112600750A (en) | 2020-12-25 | 2020-12-25 | Method and device for processing multiple pieces of dialogue information in instant messaging |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112600750A true CN112600750A (en) | 2021-04-02 |
Family
ID=75202063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011561850.0A Pending CN112600750A (en) | 2020-12-25 | 2020-12-25 | Method and device for processing multiple pieces of dialogue information in instant messaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112600750A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407686A (en) * | 2021-06-03 | 2021-09-17 | 北京得间科技有限公司 | Interactive display method, computing equipment and computer storage medium for dialogue novel |
| CN113595868A (en) * | 2021-06-28 | 2021-11-02 | 深圳云之家网络有限公司 | Voice message processing method and device based on instant messaging and computer equipment |
| CN114363280A (en) * | 2022-03-18 | 2022-04-15 | 深圳市欧乐智能实业有限公司 | Mobile phone chat auxiliary system based on multi-section voice summary type transmission |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105577530A (en) * | 2016-01-07 | 2016-05-11 | 天脉聚源（北京）科技有限公司 | Group chat information overviewing method and apparatus |
| CN106558311A (en) * | 2015-09-30 | 2017-04-05 | 北京奇虎科技有限公司 | Voice content reminding method and device |
| CN106919635A (en) * | 2016-06-13 | 2017-07-04 | 阿里巴巴集团控股有限公司 | A kind of group chat record queries method, device and electronic equipment |
| CN110059241A (en) * | 2019-04-25 | 2019-07-26 | 网易（杭州）网络有限公司 | Information query method and device, computer readable storage medium, electronic equipment |
| CN111767396A (en) * | 2020-05-18 | 2020-10-13 | 北京沃东天骏信息技术有限公司 | Data processing method, device, equipment and computer readable storage medium |
-
2020
- 2020-12-25 CN CN202011561850.0A patent/CN112600750A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106558311A (en) * | 2015-09-30 | 2017-04-05 | 北京奇虎科技有限公司 | Voice content reminding method and device |
| CN105577530A (en) * | 2016-01-07 | 2016-05-11 | 天脉聚源（北京）科技有限公司 | Group chat information overviewing method and apparatus |
| CN106919635A (en) * | 2016-06-13 | 2017-07-04 | 阿里巴巴集团控股有限公司 | A kind of group chat record queries method, device and electronic equipment |
| CN110059241A (en) * | 2019-04-25 | 2019-07-26 | 网易（杭州）网络有限公司 | Information query method and device, computer readable storage medium, electronic equipment |
| CN111767396A (en) * | 2020-05-18 | 2020-10-13 | 北京沃东天骏信息技术有限公司 | Data processing method, device, equipment and computer readable storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407686A (en) * | 2021-06-03 | 2021-09-17 | 北京得间科技有限公司 | Interactive display method, computing equipment and computer storage medium for dialogue novel |
| CN113407686B (en) * | 2021-06-03 | 2022-11-15 | 北京得间科技有限公司 | Interactive display method, computing equipment and computer storage medium for dialogue novel |
| CN113595868A (en) * | 2021-06-28 | 2021-11-02 | 深圳云之家网络有限公司 | Voice message processing method and device based on instant messaging and computer equipment |
| CN114363280A (en) * | 2022-03-18 | 2022-04-15 | 深圳市欧乐智能实业有限公司 | Mobile phone chat auxiliary system based on multi-section voice summary type transmission |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112600750A (en) | Method and device for processing multiple pieces of dialogue information in instant messaging | |
| US20170169822A1 (en) | Dialog text summarization device and method | |
| US7092496B1 (en) | Method and apparatus for processing information signals based on content | |
| US20170199870A1 (en) | Method and Apparatus for Automatic Translation of Input Characters | |
| US8831209B2 (en) | Conference call dialing | |
| US8458152B2 (en) | System and method for providing highly readable text on small mobile devices | |
| CN111158831A (en) | Data processing method, device, equipment and medium based on instant messaging application | |
| CN103379460A (en) | Method and terminal for processing voice message | |
| CN113569037A (en) | Message processing method and device and readable storage medium | |
| US20060271365A1 (en) | Methods and apparatus for processing information signals based on content | |
| CN102984050A (en) | Method, client and system for searching voices in instant messaging | |
| CN109782997B (en) | Data processing method, device and storage medium | |
| CN113094143A (en) | Cross-application message sending method and device, electronic equipment and readable storage medium | |
| CN112929253A (en) | Virtual image interaction method and device | |
| CN111859900A (en) | Message display method and device and electronic equipment | |
| US11491396B2 (en) | Information processing method and electronic device | |
| US10824790B1 (en) | System and method of extracting information in an image containing file for enhanced utilization and presentation | |
| CN111970295B (en) | Multi-terminal-based call transaction management method and device | |
| CN109388695B (en) | User intention recognition method, apparatus and computer-readable storage medium | |
| CN114880498B (en) | Event information display method and device, equipment and medium | |
| CN113743102B (en) | Method and device for recognizing characters and electronic equipment | |
| US10540987B2 (en) | Summary generating device, summary generating method, and computer program product | |
| CN115292462A (en) | Character generation method and device, mobile terminal, readable storage medium and chip | |
| CN112487164A (en) | Artificial intelligence interaction method | |
| CN112417095A (en) | Voice message processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210402 |