CN111312252A - Method for inviting address book personnel through AI voice - Google Patents
Method for inviting address book personnel through AI voice Download PDFInfo
- Publication number
- CN111312252A CN111312252A CN202010168217.9A CN202010168217A CN111312252A CN 111312252 A CN111312252 A CN 111312252A CN 202010168217 A CN202010168217 A CN 202010168217A CN 111312252 A CN111312252 A CN 111312252A
- Authority
- CN
- China
- Prior art keywords
- voice
- intention
- contact
- client
- inviting
- 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 26
- 230000006399 behavior Effects 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 230000005540 biological transmission Effects 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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 TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a method for inviting address book personnel through AI voice.A client collects voice data and transmits the voice data to a voice recognition module through network connection to recognize text content; transmitting the identified text content to an intention analysis module through network connection, and analyzing intention behaviors and content; the intention analysis module returns an analysis result to the client, and the client searches the contact information matched with the intention behavior and the content in the address book according to the intention behavior and the content; and after finding out the contact in the address list, transmitting the contact to a back-end server through network transmission, and pushing invitation information to the invited client equipment by the back-end server according to the unique identification ID of the client equipment. The invention can be applied to various occasions (such as driving), and does not need to manually invite friends in the address list, thereby greatly improving the safety.
Description
Technical Field
The invention relates to a method for inviting address book personnel through AI voice, belonging to the technical field of intelligent terminals.
Background
On an intelligent terminal, a friend inviting mode is applied to a plurality of APPs, and the friend inviting message can be sent to friends in an address list through multiple screen clicking operations, but in some special scenes, such as a driving scene, safety risks can be increased by manually inviting friends in the address list.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method for inviting address book personnel through AI voice in a special scene, which is low in safety risk.
In order to achieve the purpose, the invention is realized by the following technical scheme:
the invention relates to a method for inviting address book personnel through AI voice.A client collects voice data and transmits the voice data to a voice recognition module through network connection to recognize text content;
transmitting the identified text content to an intention analysis module through network connection, and analyzing intention behaviors and content;
the intention analysis module returns an analysis result to the client, and the client searches the contact information matched with the intention behavior and the content in the address book according to the intention behavior and the content;
and after finding out the contact in the address list, transmitting the contact to a back-end server through network transmission, and pushing invitation information to the invited client equipment by the back-end server according to the unique identification ID of the client equipment.
Before or while the client collects the voice data, the client accesses the names of all the contact persons in the address list to form a word stock, and the word stock is used for narrowing the retrieval range in subsequent retrieval and improving the accuracy of name identification.
The specific processing method of the voice recognition module is as follows:
pre-treating;
extracting characteristic parameters;
and matching the pattern.
The preprocessing specifically comprises the steps of pre-filtering, sampling, quantizing, windowing, end point detection and pre-emphasis.
The extracted characteristic parameters must satisfy the following requirements:
(1) the extracted characteristic parameters can effectively represent the voice characteristics and have distinctiveness;
(2) the parameters of each order have independence;
(3) the characteristic parameters need to be calculated conveniently so as to ensure the real-time realization of the voice recognition.
The pattern matching method comprises the following steps: firstly, for each word in the system, making a codebook as a reference template of the word, wherein M words are shared, so that M codebooks are shared to form a template library; in recognition, for an arbitrarily input speech feature vector sequence X ═ X1,X2,…,XNAnd calculating the total average distortion error of each feature vector in the sequence to each codebook in the template library, finding out the codebook corresponding to the minimum distortion error, and outputting the corresponding word as the identification result.
The intention analyzing module analyzes intention behaviors and contents, the AI module can carry out training, keyword invitation can be used as a behavior, and the invited contents are used as an invited object, and the specific method comprises the following steps:
classifying the recognized text content into strong intentions and weak intentions, and analyzing the intentions by using a rule module and an intention word list;
if the invitation strong intention exists, entering the next step of name matching; if the invitation intention is not resolved, the voice entry collection needs to be re-established.
After receiving the result of the intention analysis, the client matches the contact information of the address list according to the result, and the specific method comprises the following steps:
finding out the most matched contact in the address list, transmitting the most matched contact to a back-end server through network transmission, and transmitting an invitation message to mobile terminal equipment of an invitee by the back-end server through a message push service; the invitation will yield 3 results, matching to multiple contacts, one contact, not matching to a contact; selecting to invite a few contacts when the contacts are multiple; when only one contact exists, the invitation is defaulted; when no person is invited in the address list, the user can give a text prompt and a voice prompt in time.
The invention takes all personnel names in the address book as a voice basic library, converts the dialect into characters by using voice recognition, trains the invitation intention in the AI module, transmits the characters converted by the voice to the AI module, returns the invitation intention and the name, then performs matching in the basic library, performs fuzzy matching through the characters and initials, and has 1 or more matching results as the final result.
Drawings
Fig. 1 is a flowchart of a method for inviting contact list persons through AI voice.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
The method for inviting the address book personnel through AI voice comprises the following steps: all personnel names in the address book are used as a voice basic library, dialogs are converted into characters by using a voice recognition technology (a third party), then an invitation intention is trained in an AI module (the third party), the characters converted from the voice are transmitted to the AI module, the invitation intention and the names are returned, then matching is carried out in the basic library, fuzzy matching is carried out through the characters and initials, and the final result has 1 or more matching results.
Referring to fig. 1, a method for inviting a person in an address book by AI voice, wherein a client collects voice data and transmits the voice data to a voice recognition module for processing through network connection.
After the voice recognition module finishes processing, the recognized text content is transmitted to the intention analysis module through network connection, intention behaviors and content are analyzed, an analysis result is returned to the client side, and the client side searches contact information matched with the intention behaviors and the content in the address book according to the intention behaviors and the content.
Before or while the client collects the voice data, the client can access the names of all the contact persons in the address list to form a word stock, and the word stock is subsequently used for narrowing the retrieval range during retrieval and improving the accuracy of name identification.
The client collects voice data and transmits the voice data to the voice recognition module through network connection for processing, and the processing comprises the following steps:
preprocessing of voice signals, feature extraction and mode matching. The preprocessing includes pre-filtering, sampling and quantizing, windowing, end point detection, pre-emphasis, and the like. One of the most important loops of speech signal recognition is feature parameter extraction. The extracted characteristic parameters must satisfy the following requirements:
(1) the extracted characteristic parameters can effectively represent the voice characteristics and have good distinguishability;
(2) the parameters of each order have good independence;
(3) the characteristic parameters need to be calculated conveniently so as to ensure the real-time realization of the voice recognition.
The client collects voice data and transmits the voice data to the voice recognition module through network connection for processing, and then the method further comprises the following steps:
analyzing the result content of the voice recognition, wherein the intention analysis is essentially a process of classifying information, strong intentions and weak intentions exist, and the intentions are analyzed by using a rule module and an intention word list. If the invitation intention exists, the next step of name matching is carried out, if the invitation intention is not resolved, the voice recording and collection are required again, and the flow is repeated again to express the clear intention.
After the client receives the result of the intention analysis, the process of matching the contact information of the address list according to the result comprises the following steps:
finding out the most matched contact in the address list, transmitting the most matched contact to a back-end server through network transmission, and transmitting an invitation message to mobile end equipment of an invitee by the server through a message push service; this invitation will result in result 3, matching to multiple contacts, one contact, not matching to a contact. The case of multiple contacts can choose to invite the fourth contact, if there is only one contact, the invitation is defaulted; if the address list has no invited people, giving a text and voice prompt in time;
after finding the contact in the address list, transmitting the contact to a back-end server through network transmission, wherein the server further comprises through a message push service:
the message pushing service pushes the invitation information to the invited client equipment through a network service protocol according to the unique identification ID of the client equipment.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A method for inviting address book personnel through AI voice is characterized in that: the client collects voice data and transmits the voice data to the voice recognition module through network connection, and text content is recognized;
transmitting the identified text content to an intention analysis module through network connection, and analyzing intention behaviors and content;
the intention analysis module returns an analysis result to the client, and the client searches the contact information matched with the intention behavior and the content in the address book according to the intention behavior and the content;
and after finding out the contact in the address list, transmitting the contact to a back-end server through network transmission, and pushing invitation information to the invited client equipment by the back-end server according to the unique identification ID of the client equipment.
2. The method for inviting directory people through AI voice according to claim 1, wherein: before or at the same time of acquiring the voice data by the client, the client accesses the names of all contacts in the address list to form a word stock which is used for narrowing the retrieval range in the subsequent retrieval.
3. The method for inviting directory people through AI voice according to claim 1, wherein: the specific processing method of the voice recognition module is as follows:
pre-treating;
extracting characteristic parameters;
and matching the pattern.
4. The method of claim 3 for inviting contact list people through AI voice, wherein: the pre-processing specifically comprises the steps of pre-filtering, sampling, quantizing, windowing, end point detection and pre-emphasis.
5. The method of claim 3 for inviting contact list people through AI voice, wherein: the extracted characteristic parameters must satisfy the following requirements:
(1) the extracted characteristic parameters can effectively represent the voice characteristics and have distinctiveness;
(2) the parameters of each order have independence;
(3) the characteristic parameters need to be calculated conveniently so as to ensure the real-time realization of the voice recognition.
6. The method of claim 3 for inviting contact list people through AI voice, wherein: the pattern matching method is as follows: firstly, for each word in the system, making a codebook as a reference template of the word, wherein M words are shared, so that M codebooks are shared to form a template library; in recognition, for an arbitrarily input speech feature vector sequence X ═ X1,X2,…,XNAnd calculating the total average distortion error of each feature vector in the sequence to each codebook in the template library, finding out the codebook corresponding to the minimum distortion error, and outputting the corresponding word as the identification result.
7. The method for inviting directory people through AI voice according to claim 1, wherein: the intention analyzing module analyzes intention behaviors and contents, the AI module can carry out training, keyword invitation can be used as a behavior, and the invited contents are used as an invited object, and the specific method comprises the following steps:
classifying the recognized text content into strong intentions and weak intentions, and analyzing the intentions by using a rule module and an intention word list;
if the invitation strong intention exists, entering the next step of name matching; if the invitation intention is not resolved, the voice entry collection needs to be re-established.
8. The method for inviting directory people through AI voice according to claim 1, wherein: after receiving the result of the intention analysis, the client matches the contact information of the address list according to the result, and the specific method comprises the following steps:
finding out the most matched contact in the address list, transmitting the most matched contact to a back-end server through network transmission, and transmitting an invitation message to mobile terminal equipment of an invitee by the back-end server through a message push service; the invitation will yield 3 results, matching to multiple contacts, one contact, not matching to a contact; selecting to invite a few contacts when the contacts are multiple; when only one contact exists, the invitation is defaulted; when no person is invited in the address list, the user can give a text prompt and a voice prompt in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010168217.9A CN111312252A (en) | 2020-03-11 | 2020-03-11 | Method for inviting address book personnel through AI voice |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010168217.9A CN111312252A (en) | 2020-03-11 | 2020-03-11 | Method for inviting address book personnel through AI voice |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111312252A true CN111312252A (en) | 2020-06-19 |
Family
ID=71162261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010168217.9A Pending CN111312252A (en) | 2020-03-11 | 2020-03-11 | Method for inviting address book personnel through AI voice |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111312252A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113489762A (en) * | 2021-06-17 | 2021-10-08 | 南京爱沓信息技术有限公司 | Artificial intelligent voice invitation sharing navigation method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243853A1 (en) * | 2007-03-30 | 2008-10-02 | Verizon Services Corp. | Method and system for notifying an invitee user when an inviting user accesses a social networking application |
| CN101593519A (en) * | 2008-05-29 | 2009-12-02 | 夏普株式会社 | Detect method and apparatus and the search method and the system of voice keyword |
| CN107680598A (en) * | 2017-09-04 | 2018-02-09 | 百度在线网络技术（北京）有限公司 | Information interacting method, device and its equipment based on good friend's vocal print address list |
| CN108665890A (en) * | 2017-03-28 | 2018-10-16 | 三星电子株式会社 | Operate method, electronic equipment and the system for supporting the equipment of speech-recognition services |
| CN109830234A (en) * | 2019-03-19 | 2019-05-31 | 深圳市尼欧科技有限公司 | A kind of intelligent vehicle-carried information interaction device and exchange method |
-
2020
- 2020-03-11 CN CN202010168217.9A patent/CN111312252A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243853A1 (en) * | 2007-03-30 | 2008-10-02 | Verizon Services Corp. | Method and system for notifying an invitee user when an inviting user accesses a social networking application |
| CN101593519A (en) * | 2008-05-29 | 2009-12-02 | 夏普株式会社 | Detect method and apparatus and the search method and the system of voice keyword |
| CN108665890A (en) * | 2017-03-28 | 2018-10-16 | 三星电子株式会社 | Operate method, electronic equipment and the system for supporting the equipment of speech-recognition services |
| CN107680598A (en) * | 2017-09-04 | 2018-02-09 | 百度在线网络技术（北京）有限公司 | Information interacting method, device and its equipment based on good friend's vocal print address list |
| CN109830234A (en) * | 2019-03-19 | 2019-05-31 | 深圳市尼欧科技有限公司 | A kind of intelligent vehicle-carried information interaction device and exchange method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113489762A (en) * | 2021-06-17 | 2021-10-08 | 南京爱沓信息技术有限公司 | Artificial intelligent voice invitation sharing navigation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111488433B (en) | Artificial intelligence interactive system suitable for bank and capable of improving field experience | |
| US8135579B2 (en) | Method of analyzing conversational transcripts | |
| CN110459210A (en) | Answering method, device, equipment and storage medium based on speech analysis | |
| CN112468659B (en) | Quality evaluation method, device, equipment and storage medium applied to telephone customer service | |
| CN105261356A (en) | Voice recognition system and method | |
| CN109003600B (en) | Message processing method and device | |
| CN113051384B (en) | User portrait extraction method based on dialogue and related device | |
| CN111462758A (en) | Method, device and equipment for intelligent conference role classification and storage medium | |
| CN112364622B (en) | Dialogue text analysis method, device, electronic device and storage medium | |
| CN111128182A (en) | Intelligent voice recording method and device | |
| CN111627448A (en) | System and method for realizing trial and talk control based on voice big data | |
| CN116562270A (en) | Natural language processing system supporting multi-mode input and method thereof | |
| CN113744742A (en) | Role identification method, device and system in conversation scene | |
| CN116665676A (en) | Semantic recognition method for intelligent voice outbound system | |
| CN111312252A (en) | Method for inviting address book personnel through AI voice | |
| CN117939238A (en) | Character recognition method, system, computing device and computer-readable storage medium | |
| CN108899035B (en) | Message processing method and device | |
| CN116303951A (en) | Dialogue processing method, device, electronic equipment and storage medium | |
| CN116127011A (en) | Intention recognition method, device, electronic equipment and storage medium | |
| CN115293129A (en) | Group chat-oriented dialogue structure analysis model training method, analysis method and device | |
| CN113314103A (en) | Illegal information identification method and device based on real-time speech emotion analysis | |
| CN113936666A (en) | Audio data identification method and system based on BS (browser/server) architecture and readable storage medium | |
| CN113489762B (en) | Artificial intelligent voice invitation sharing navigation method | |
| CN111091035A (en) | Subject identification method and electronic equipment | |
| CN118523969B (en) | Campus phishing early warning method and system based on DPI and readable medium |
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 |
Application publication date: 20200619 |
|
| RJ01 | Rejection of invention patent application after publication |