CN116545965A - Automatic voice information replying method of social APP - Google Patents
Automatic voice information replying method of social APP Download PDFInfo
- Publication number
- CN116545965A CN116545965A CN202310514238.5A CN202310514238A CN116545965A CN 116545965 A CN116545965 A CN 116545965A CN 202310514238 A CN202310514238 A CN 202310514238A CN 116545965 A CN116545965 A CN 116545965A
- Authority
- CN
- China
- Prior art keywords
- information
- dialogue
- user
- voice
- reply
- 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 37
- 238000004891 communication Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000006978 adaptation Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Abstract
The invention discloses a voice information automatic replying method of a social APP, which belongs to the technical field of communication and comprises the following steps: acquiring user characteristics of a user end, user characteristics of a dialogue end and historical call record information; analyzing the acquired dialogue end information; and generating corresponding reply voice information according to the analysis content. According to the technical scheme, the corresponding reply information can be generated by receiving the information and recording personal information and historical communication of an information sender, the received information can be automatically replied in some inconvenient scenes, the source application of the information can be determined according to the content keyword or the source number of the information, when the source application cannot be determined or the source application cannot be determined, at least one available information interaction application associated with the source contact is obtained by inquiring a contact list according to the source contact of the information, and the at least one information interaction application is determined to be an application available for replying the information.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to an automatic voice information replying method of a social APP.
Background
With the development of communication technology, communication applications such as short message applications and instant messaging applications have been accepted by more and more users. For example, the user can transmit text, multimedia (including video, audio, etc.) and other information with his family, friends or colleagues through the instant messaging application, so as to realize the communication function.
At present, in order to improve the efficiency of information reply, the existing scheme can provide a shortcut reply function, and a shortcut reply candidate can be generated according to the information from the sender through the shortcut reply function, so that a user can directly select the required shortcut reply candidate to reply the information.
The quick reply candidates of the existing schemes are generally content generated on the basis of analyzing information from the sender. For example, if the information from the sender is "eat" the communication application may analyze the content of the information using natural language processing techniques, and generate quick reply candidates such as "eat", "eat nothing" according to the analysis result of the content of the information.
However, the above-described generation process of the quick reply candidates uses only a single information content analysis result, which tends to bring lower accuracy and richness to the quick reply candidates. For example, the quick reply candidates such as "eat", "not eat" describe only a rough judgment reply result, and do not consider the deep information of the judgment reply result, so that the rough judgment reply result reflects an unconscious attitude, and thus cannot fit the accurate reply intention of the user. In fact, when the user replies to the information from his home, friend or colleague, the user often carries deep information in the reply result, for example, the reason of "not eating" is because he/she watches video or shopping, and the user continues watching television after "eating", and the user also watches television while eating.
Currently, various social class apps (such as WeChat, QQ and the like) enter lives of people, and the social class apps generally have a function of sending voice messages. In the related art, when the user A, B uses voice message to chat, the user a needs to press a certain virtual key for a long time when sending a voice message to the user B, and then speaks the voice content, and after speaking, the user can end the long-time pressing of the virtual key, and then sends the voice message to the user B. The above process requires manual operation by a user, is inconvenient for scenes such as driving, and brings about certain potential safety hazard
Disclosure of Invention
The invention aims to provide an automatic voice information reply method of a social APP, which overcomes the defects in the prior art.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
an automatic voice information replying method of a social APP comprises the following steps:
acquiring user characteristics of a user end, user characteristics of a dialogue end and historical call record information;
analyzing the acquired dialogue end information;
and generating corresponding reply voice information according to the analysis content.
By adopting the technical scheme, the information to be replied is replied based on the historical call record, so that the replied voice information can be attached to the information to be replied, the purposes of no deviation and no question running are achieved, the replied voice information is matched with the common habit of a user through acquiring the user characteristics of a user end and the user characteristics of a conversation end, and the conversation scale is analyzed and mastered according to the user characteristics of the conversation end.
Further defined, the user characteristics of the user end include gender, age and region.
According to the user characteristics of the user end, the user characteristics can be determined, and the information to be replied can be combined, so that the content expressed by the replied voice message and the manner are plump and vivid.
Further defined, the user characteristics of the dialog end include name and addition path information.
By combining the user name of the dialogue end and the addition path information, the familiarity degree and the relationship of the people at the dialogue end can be judged, and whether automatic reply is needed or not is selected according to the familiarity degree and the relationship of the people.
Further defined, the parsing step includes:
analyzing text information or an additional voice section from the dialogue end information, and analyzing user characteristics of the dialogue end from the text information or the additional voice section;
different reply format types are generated according to different dialogue end users.
According to different dialogue end users, generating corresponding reply modes, if the dialogue end user is the first call and the call content is the promotion type, no reply information or rejection information is generated, if the dialogue end user has a history call record, inconvenient reply types are directly generated, such as: during driving.
Further limiting, determining text candidates corresponding to the reply voice information according to the user characteristics of the dialogue end and the corresponding text of the information to be replied.
The method can generate the reply voice information and generate the visualized information at the same time, and a user can inspect the reply information according to the visualized voice mode, and if the reply information does not accord with psychological expectation, the content can be changed in a clicking mode, so that the reply information can be inspected before being sent.
Further limiting, determining the user characteristics corresponding to the information to be replied according to the communication content in the communication window corresponding to the information to be replied or the network data of the corresponding user on the Internet.
Further determinations of user characteristics are made in connection with network information, such as distinguishing group chat windows or individual chat windows, to avoid private conversation leakage.
Further defined, at least two word candidates are generated once, and the type of the transmission information can be selected again after the word candidates are clicked.
By generating a plurality of alternatives of reply information, reply types which are more suitable for dialogue scenes can be conveniently selected.
Further defined, the dialogue reply strategy for replying to the voice information comprises:
acquiring each historical service dialogue in the historical dialogue information of the user end user, and identifying the voice information of the historical service dialogue to obtain the voice information as a sample reply voice;
acquiring precondition information of the dialogue end user which replies the same in the historical dialogue information of the user end user, classifying the precondition information, and taking the precondition information as sample reply voice;
training the dialogue reply strategy model according to the dialogue reply strategy of the sample voice.
Further defined, the reply policy further includes a semantic recognition, the semantic recognition method including:
acquiring a question-answer sentence pattern in each history service dialogue in history dialogue information of a user end user, wherein one question-answer sentence pattern comprises a question and an answer;
and determining a target problem with highest similarity with the semantic recognition result in the plurality of problems, and generating the reply information conforming to the speaking style based on a target answer corresponding to the problem.
Compared with the prior art, the method and the device can generate corresponding reply information by receiving the information and recording the personal information and the historical communication of the information sender, and can automatically reply the received information in some inconvenient scenes.
Drawings
Fig. 1 is a flowchart of a method for automatically replying voice information of a social APP according to the present invention.
Detailed Description
The present invention is further illustrated by the following examples, which are not intended to be limiting, but any modifications, equivalents, improvements, etc. within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
The message reply method and apparatus according to the exemplary embodiments of the present invention call an application that is available for replying to a message and is different from a current application to perform message reply after a mobile terminal (e.g., a smart phone, a tablet computer, etc.) receives the message.
The "smart phone, tablet" may also take the specific form of other computers, which may be personal computers, laptop computers, cellular phones, camera phones, smart phones, personal digital assistants, media players, navigation devices, email devices, game consoles, tablet computers, wearable devices, or a combination of any of several of these devices.
Or, the mobile terminal may be implemented in various forms. For example, the terminals described in the present invention may include mobile terminals such as mobile phones, smart phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), navigation devices, and the like, and fixed terminals such as digital TVs, desktop computers, and the like. In the following, it is assumed that the terminal is a mobile terminal, however, it will be understood by those skilled in the art that the configuration according to the embodiment of the present invention can be applied to a fixed type terminal in addition to elements particularly used for a moving purpose. The mobile terminal in this embodiment may implement the voice information transmitting apparatus and/or the voice information receiving apparatus in each embodiment of the present invention.
Here, the received message may be a short message, a multimedia message, or the like sent to a short message inbox, or may be a message received through an information interaction application (for example, a flyway application, a micro-message application, a QQ application, a super QQ application, or the like). Further, applications that may be used to reply to messages may include short message applications, flyletter applications, weChat applications, QQ applications, super QQ applications, and the like.
In addition, the received message to be replied can be not only a common short message or a multimedia message, but also a message sent by other information interaction applications (for example, a flyletter application, a WeChat application, a QQ application, a super QQ application and the like).
In addition, in the case that the information interaction application provides a short message interface and is set to a mode of receiving a message in a short message mode when offline, when the information interaction application providing the short message interface transmits a message and the receiver does not enable the application, the message can be transmitted to the short message inbox of the receiver in a short message or multimedia message mode. For example, when the contact person uses the flyway application to send the message to the user, if the user does not start the flyway application currently, the message sent by the contact person using the flyway application can be automatically forwarded to the short message inbox in the form of a short message or a multimedia message. Since providing a short message interface and setting an offline message receiving manner in an application belongs to a known technology, a detailed description thereof will not be provided.
The invention can determine the source application of the message according to the content keyword or the source number of the message, and when the source application cannot be determined or the source application cannot be determined, according to the source contact of the message, the available at least one information interaction application associated with the source contact is obtained by inquiring the contact list, and the at least one information interaction application is determined to be an application available for replying information.
As shown in fig. 1, an automatic voice information reply method of a social APP includes:
acquiring user characteristics of a user end, user characteristics of a dialogue end and historical call record information;
analyzing the acquired dialogue end information;
and generating corresponding reply voice information according to the analysis content.
The method comprises the steps of replying information to be replied based on a historical call record, enabling reply voice information to be attached to the information to be replied, achieving the purposes of no deviation and no question running, enabling the reply voice information to be consistent with common habits of users through obtaining user characteristics of a user end and user characteristics of a conversation end, and analyzing and grasping conversation scales according to the user characteristics of the conversation end.
The user characteristics of the user end comprise gender, age and region.
According to the user characteristics of the user end, the information to be replied can be combined, and the information is expressed by the replied voice message
The volume and the mode are more plump and lifelike.
The user characteristics of the dialogue end comprise names and adding path information.
By combining the user name of the dialogue end and the addition path information, the familiarity degree and the relationship of the people at the dialogue end can be judged, and whether automatic reply is needed or not is selected according to the familiarity degree and the relationship of the people.
The analyzing step comprises the following steps:
analyzing text information or an additional voice section from the dialogue end information, and analyzing user characteristics of the dialogue end from the text information or the additional voice section;
different reply format types are generated according to different dialogue end users.
According to different dialogue end users, generating corresponding reply modes, if the dialogue end user is the first call and the call content is the promotion type, no reply information or rejection information is generated, if the dialogue end user has a history call record, inconvenient reply types are directly generated, such as: during driving.
And determining text candidates corresponding to the replied voice information according to the user characteristics of the dialogue end and the corresponding text of the information to be replied.
The method can generate the reply voice information and generate the visualized information at the same time, and a user can inspect the reply information according to the visualized voice mode, and if the reply information does not accord with psychological expectation, the content can be changed in a clicking mode, so that the reply information can be inspected before being sent.
And determining the user characteristics corresponding to the information to be replied according to the communication content in the communication window corresponding to the information to be replied or the network data of the corresponding user on the Internet.
Further determinations of user characteristics are made in connection with network information, such as distinguishing group chat windows or individual chat windows, to avoid private conversation leakage.
At least two word candidate items are generated once, and the type of the information to be sent can be selected again after the word candidate items are clicked.
By generating a plurality of alternatives of reply information, reply types which are more suitable for dialogue scenes can be conveniently selected.
The dialogue reply strategy for replying the voice information comprises the following steps: acquiring each historical service dialogue in the historical dialogue information of the user end user, and identifying the voice information of the historical service dialogue to obtain the voice information as a sample reply voice; acquiring precondition information of the dialogue end user which replies the same in the historical dialogue information of the user end user, classifying the precondition information, and taking the precondition information as sample reply voice; training the dialogue reply strategy model according to the dialogue reply strategy of the sample voice.
The reply strategy also comprises semantic recognition, and the semantic recognition method comprises the following steps: acquiring a question-answer sentence pattern in each history service dialogue in history dialogue information of a user end user, wherein one question-answer sentence pattern comprises a question and an answer; and determining a target problem with highest similarity with the semantic recognition result in the plurality of problems, and generating the reply information conforming to the speaking style based on a target answer corresponding to the problem.
According to the technical scheme, the corresponding reply information can be generated by receiving the information and recording the personal information and the historical communication of the information sender, and the received information can be automatically replied in some inconvenient scenes.
These program instructions may be embodied in a computer, special purpose processor, or programmable or dedicated hardware, such that the instructions executed therein facilitate the performance of the functions described above. As will be appreciated by one of skill in the art, a computer, processor, or programmable hardware includes a storage device that can store or receive software or computer code that, when accessed and executed by a computer, processor, or hardware, implements the methods described in the present invention.
The present invention has been described in detail above. The description of the specific embodiments is only intended to aid in understanding the method of the present invention and its core ideas. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the invention can be made without departing from the principles of the invention and these modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (9)
1. The automatic voice information replying method of the social APP is characterized by comprising the following steps of: comprising the following steps:
acquiring user characteristics of a user end, user characteristics of a dialogue end and historical call record information;
analyzing the acquired dialogue end information;
and generating corresponding reply voice information according to the analysis content.
2. The method for automatically replying to voice information of social APP according to claim 1, wherein: the user characteristics of the user end comprise gender, age and region.
3. The method for automatically replying to voice information of social APP according to claim 1, wherein: the user characteristics of the dialogue end comprise names and adding path information.
4. The method for automatically replying to voice information of social APP according to claim 1, wherein: the analyzing step comprises the following steps:
analyzing text information or an additional voice section from the dialogue end information, and analyzing user characteristics of the dialogue end from the text information or the additional voice section;
different reply format types are generated according to different dialogue end users.
5. The method for automatically replying to voice information of social APP according to claim 1, wherein: and determining text candidates corresponding to the replied voice information according to the user characteristics of the dialogue end and the corresponding text of the information to be replied.
6. The method for automatically replying to voice information of social APP according to claim 1, wherein: and determining the user characteristics corresponding to the information to be replied according to the communication content in the communication window corresponding to the information to be replied or the network data of the corresponding user on the Internet.
7. The method for automatically replying to voice information of social APP according to claim 5, wherein: at least two word candidate items are generated once, and the type of the information to be sent can be selected again after the word candidate items are clicked.
8. The method for automatically replying to voice information of a social APP according to any one of claims 1 to 7, wherein: the dialogue reply strategy for replying the voice information comprises the following steps:
acquiring each historical service dialogue in the historical dialogue information of the user end user, and identifying the voice information of the historical service dialogue to obtain the voice information as a sample reply voice;
acquiring precondition information of the dialogue end user which replies the same in the historical dialogue information of the user end user, classifying the precondition information, and taking the precondition information as sample reply voice;
training the dialogue reply strategy model according to the dialogue reply strategy of the sample voice.
9. The method for automatically replying to voice information of social APP according to claim 8, wherein: the reply strategy also comprises semantic recognition, and the semantic recognition method comprises the following steps:
the sentence pattern comprises a question and an answer;
and determining a target problem with highest similarity with the semantic recognition result in the plurality of problems, and generating the reply information conforming to the speaking style based on a target answer corresponding to the problem.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310514238.5A CN116545965A (en) | 2023-05-08 | 2023-05-08 | Automatic voice information replying method of social APP |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310514238.5A CN116545965A (en) | 2023-05-08 | 2023-05-08 | Automatic voice information replying method of social APP |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116545965A true CN116545965A (en) | 2023-08-04 |
Family
ID=87455551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310514238.5A Pending CN116545965A (en) | 2023-05-08 | 2023-05-08 | Automatic voice information replying method of social APP |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116545965A (en) |
-
2023
- 2023-05-08 CN CN202310514238.5A patent/CN116545965A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11379529B2 (en) | Composing rich content messages | |
| CN107846350B (en) | Method, computer readable medium and system for context-aware network chat | |
| US10446142B2 (en) | Crafting feedback dialogue with a digital assistant | |
| US9183535B2 (en) | Social network model for semantic processing | |
| JP6469117B2 (en) | Dynamic solicitation using self-adjusting display | |
| US11017767B2 (en) | Hierarchical attention for spoken dialogue state tracking | |
| US20170279964A1 (en) | System and Method For User Notification Regarding Detected Events | |
| US20120143948A1 (en) | Social networking feed extensibility based on data types | |
| US10621181B2 (en) | System and method for screening social media content | |
| KR20150037935A (en) | Generating string predictions using contexts | |
| US9369425B2 (en) | Email and instant messaging agent for dialog system | |
| WO2015196987A1 (en) | Natural language supported data query method, open platform and user terminal | |
| CN111063355A (en) | Conference record generation method and recording terminal | |
| CN106847256A (en) | A kind of voice converts chat method | |
| KR20160012965A (en) | Method for editing text and electronic device supporting the same | |
| CN111565143A (en) | Instant messaging method, equipment and computer readable storage medium | |
| CN108306813B (en) | Session message processing method, server and client | |
| US20180006977A1 (en) | Exposing task information to online service providers | |
| CN112765460A (en) | Conference information query method, device, storage medium, terminal device and server | |
| CN113392178A (en) | Message reminding method, related device, equipment and storage medium | |
| CN112532507B (en) | Method and device for presenting an emoticon, and for transmitting an emoticon | |
| US20110055230A1 (en) | Community-Based Knowledge Sharing | |
| US20180365319A1 (en) | Identifying relationships from communication content | |
| CN110727775B (en) | Method and apparatus for processing information | |
| CN106558311A (en) | Voice content reminding method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |