CN111833871A - Intelligent outbound system based on intention recognition and method thereof - Google Patents
Intelligent outbound system based on intention recognition and method thereof Download PDFInfo
- Publication number
- CN111833871A CN111833871A CN202010646720.0A CN202010646720A CN111833871A CN 111833871 A CN111833871 A CN 111833871A CN 202010646720 A CN202010646720 A CN 202010646720A CN 111833871 A CN111833871 A CN 111833871A
- Authority
- CN
- China
- Prior art keywords
- client
- voice
- module
- call
- information
- 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 34
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 15
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 239000013598 vector Substances 0.000 claims description 37
- 238000012216 screening Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000013145 classification model Methods 0.000 claims description 6
- 238000007726 management method Methods 0.000 description 13
- 239000011159 matrix material Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 102220562787 Tubulin beta-1 chain_W11F_mutation Human genes 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010354 integration 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- 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
- G10L2015/223—Execution procedure of a spoken command
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)
- Artificial Intelligence (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses an intelligent outbound system and method based on intention recognition, the system includes: the system comprises a task generating unit, an intelligent calling unit, an ASR voice recognition unit, a TTS voice synthesis unit, an intention recognition unit, a dialect storage unit and a dialect matching unit; the intelligent calling unit intelligently dials the telephone of the client; the ASR speech recognition unit converts speech information of a client into text information; an intention identifying unit analyzes the text information to identify a user intention; matching a corresponding reply text by the dialect matching unit; the TTS voice synthesis unit converts the reply text into reply voice; the intelligent calling unit plays the reply voice to the client. The intelligent outbound system and the method thereof based on intention recognition can automatically generate a call task, automatically dial a customer call, perform semantic analysis according to the voice of the customer to obtain the intention of the customer, and further match a reply word according to the intention of the customer to be played to the customer, and the whole process does not need manual participation.
Description
Technical Field
The invention relates to an intelligent outbound system based on intention recognition and a method thereof.
Background
With the development of big data, cloud computing and AI technologies, traditional artificial customer service is upgraded to intelligent customer service, the cost of establishing a customer service center by an enterprise is greatly reduced in a brand-new SaaS mode, the product functions are richer, the application scene also extends to a plurality of modules such as sales and marketing, and meanwhile, the customer service robot greatly improves the efficiency and accuracy of the artificial customer service. The AI technology is continuously developed, the application in the customer service field is gradually deepened, and the improvement of more comprehensive integration of service, marketing and management is provided for enterprise customers.
Disclosure of Invention
The invention provides an intelligent outbound system based on intention recognition and a method thereof, which adopts the following technical scheme:
an intelligent outbound system based on intent recognition, comprising: the system comprises a task generating unit, an intelligent calling unit, an ASR voice recognition unit, a TTS voice synthesis unit, an intention recognition unit, a dialect storage unit and a dialect matching unit;
the task generating unit generates a call task and sends the call task to the intelligent call unit;
the intelligent calling unit intelligently dials the telephone of the client according to the calling task generated by the task generating unit, collects the voice information of the client after the telephone is connected and sends the voice information to the ASR voice recognition unit;
the ASR speech recognition unit converts speech information of a client into text information and sends the text information to the intention recognition unit;
an intention identifying unit analyzes the text information to identify a user intention;
the dialect storage unit stores reply texts of reply clients;
the dialect matching unit matches a corresponding reply text from the dialect storage unit according to the intention of the client and sends the reply text to the TTS speech synthesis unit;
the TTS voice synthesis unit converts the received reply text into reply voice and sends the reply voice to the intelligent calling unit;
the intelligent calling unit plays the reply voice to the client.
Further, the task generating unit includes: the client information management module, the screening module and the generating module;
the client information management module stores and manages client information;
the screening module acquires the customer information from the customer information management module and screens the customer information meeting the conditions;
the generation module generates a call task according to the screened customer information.
Further, the intelligent calling unit includes: the system comprises a task analysis module, an opening voice storage module, a voice matching module, a calling module, a voice playing module and a voice receiving module;
the task analysis module analyzes the call task to obtain a call strategy and sends the call strategy to the voice matching module and the call module, wherein the call strategy comprises an opening voice type and a client telephone;
the open field voice storage module is used for storing a plurality of open field voices;
the voice matching module matches corresponding open voice from the open voice storage module according to the calling strategy and sends the open voice to the voice playing module;
the calling module is used for dialing the telephone of the customer according to the calling strategy;
the voice playing module is used for playing the matched open-field voice to the client after the calling module dials through the client telephone;
the speech receiving module is used for receiving speech information of a client and sending the speech information to the ASR speech recognition unit;
the voice playing module is also used for playing the reply voice converted by the TTS voice synthesis unit to the client.
Further, the intention identifying unit includes: the system comprises a named entity identification module, a word embedding module, a combination module and a classification module;
the named entity recognition module carries out word segmentation on the text information to obtain corpus information;
the word embedding module performs space vector mapping on the corpus information to obtain word vectors;
the combination module performs graph feature combination on the word vectors to generate new features and inputs the new features and the word vectors into the classification module;
and the classification module processes the new features and the word vectors through the trained classification model to obtain the intention of the client.
Further, the intention identifying unit further includes: a customer analysis module;
the client analysis module collects all client intentions of the current call of the client, analyzes the result of the current call, and sends the result of the current call to the client information management module to update the corresponding client information.
An intelligent outbound method based on intention recognition comprises the following steps:
generating a call task;
automatically dialing a call of a client according to the call task and acquiring voice information of the client after the call is connected;
converting the voice information into text information;
identifying a client intention according to the text information;
matching a corresponding reply text according to the intention of the client;
and converting the reply text into reply voice and playing the reply voice to the client.
Further, the specific method for generating the call task comprises the following steps:
acquiring customer information;
screening out client information meeting the conditions;
and generating a call task according to the client information meeting the conditions.
Further, the specific method for automatically dialing the call of the customer according to the call task and acquiring the voice information of the customer after the call is connected comprises the following steps:
analyzing the call task to obtain a call strategy, wherein the call strategy comprises an opening voice type and a customer telephone;
obtaining open-field voice according to the matching of the calling strategy;
dialing a customer telephone number according to the calling strategy;
playing the opening voice to the client after the client telephone is connected;
and collecting voice information of the client.
Further, the specific method for identifying the intention of the client according to the text information comprises the following steps:
performing word segmentation on the text information to obtain corpus information;
performing space vector mapping on the corpus information to obtain a word vector;
carrying out graph feature combination on the word vectors to generate new features;
and inputting the new features and the word vectors into the trained classification model to obtain the intention of the client.
Further, the intelligent call-out method based on intention recognition also comprises the following steps:
after the call is finished, collecting all the client intentions of the call of the client and analyzing the result of the call;
and updating the client information of the client according to the call result.
The intelligent outbound system and the method based on intention recognition have the advantages that the calling task can be automatically generated, the call of the client can be automatically dialed according to the calling task, the client intention can be obtained by semantic analysis according to the voice of the client, then the answering speech can be matched according to the client intention and played to the client, manual participation is not needed in the whole process, and the intelligent degree is high.
The intelligent outbound system and the method based on the intention recognition have the advantages that when the intention recognition is carried out, the named entity recognition module is used for carrying out word segmentation on text information to obtain corpus information, the word embedding module is used for carrying out space vector mapping on the corpus information to obtain word vectors, the combination module is used for carrying out image feature combination on the corpus information to generate new features, the new features are input into the classification module, and finally the classification module is used for processing the new features through the trained classification module to obtain the client intention. A combination module is added in a traditional semantic recognition mode to perform graph feature combination on word vectors and generate new features, and the new features are used as input of a classification module. The graph features can be used for more easily obtaining the context information and improving the accuracy of the classification of the subsequent classification module.
Drawings
FIG. 1 is a schematic diagram of an intelligent outbound system based on intent recognition of the present invention;
FIG. 2 is a schematic illustration of a combination of graph features of the present invention;
FIG. 3 is a schematic diagram of the intelligent outbound method of the present invention based on intent recognition;
the intelligent outbound call system based on intention recognition 100, a task generating unit 10, a client information management module 11, a screening module 12, a generating module 13, an intelligent calling unit 20, a task analyzing module 21, an open-field voice storage module 22, a voice matching module 23, a calling module 24, a voice playing module 25, a voice receiving module 26, an ASR voice recognition unit 30, a TTS voice synthesis unit 40, an intention recognition unit 50, a named entity recognition module 51, a word embedding module 52, a combination module 53, a classification module 54, a client analysis module 55, a word storage unit 60 and a word matching unit 70.
Detailed Description
The invention is described in detail below with reference to the figures and the embodiments.
Fig. 1 shows an intelligent outbound call system 100 based on intention recognition, which mainly includes: a task generating unit 10, an intelligent calling unit 20, an ASR (Automatic Speech Recognition) Speech Recognition unit 30, a TTS (Text To Speech) Speech synthesis unit 40, an intention Recognition unit 50, a grammar storage unit 60, and a grammar matching unit 70.
The task generating unit 10 generates a call task and transmits the call task to the intelligent call unit 20.
Specifically, the task generating unit 10 includes: a customer information management module 11, a filtering module 12 and a generating module 13. The customer information management module 11 stores and manages customer information. The screening module 12 obtains the customer information from the customer information management module 11 and screens out the customer information that meets the condition. The generating module 13 generates a call task according to the screened customer information.
The task generating unit 10 generates the call task mainly based on the client information, where the client information has different specific contents according to the category of the call task. The intelligent outbound system 100 based on intention recognition of the present invention can be applied to different application scenarios such as collection, call return and telephone sales. For example, the customer information includes loan information of the customer, such as loan amount, payment due, overdue amount, overdue time, and previous communication records. The information is stored in the client information management module 11, and the screening module 12 acquires the client information from the client information management module 11, and intelligently analyzes and judges the client information to identify the client needing call collection. The generating module 13 generates a call task according to the screened customer information needing call collection and sends the call task to the intelligent calling unit 20.
The intelligent calling unit 20 intelligently dials a call of a client according to the call task generated by the task generating unit 10 and collects voice information of the client after the call is connected to the ASR voice recognition unit 30. Specifically, the smart calling unit 20 includes: the system comprises a task analysis module 21, an open-field voice storage module 22, a voice matching module 23, a calling module 24, a voice playing module 25 and a voice receiving module 26. The task parsing module 21 parses the call task to obtain a call policy including open voice type and customer telephone number and sends it to the voice matching module 23 and the call module 24. The open field voice storage module 22 is used for storing a plurality of open field voices. The voice matching module 23 matches the corresponding open voice from the open voice storage module 22 according to the call policy and sends the open voice to the voice playing module 25. The call module 24 is used to place a call to the customer based on the call policy. The voice playing module 25 is used for playing the matched open voice to the client after the calling module 24 calls the client. The speech reception module 26 is used to receive the speech information of the customer and send it to the ASR speech recognition unit 30. The speech playing module 25 is further configured to play the reply speech converted by the TTS speech synthesis unit 40 to the client.
The intelligent calling unit 20 can analyze the call task generated by the task generating unit 10 to obtain a specific call policy, wherein the call policy mainly comprises the type of the open voice and the open voice played after the call module 24 makes a call to the user is determined by the user.
The ASR speech recognition unit 30 converts the speech information of the client into text information and sends it to the intention recognition unit 50.
The intention identifying unit 50 analyzes the text information to identify the intention of the user. Specifically, the intention identifying unit 50 includes: a named entity recognition module 51, a word embedding module 52, a combination module 53, and a classification module 54. The named entity recognition module 51 performs word segmentation on the text information to obtain corpus information, and in the invention, the named entity recognition module 51 performs word segmentation on the text information through a mainstream named entity recognition algorithm Bi-LSTM + CRF. In particular, over time, the forward and backward delivery over an expanded network is similar to that in a conventional network, except that the hidden state needs to be expanded for all time steps, and special processing is required at the beginning and end of the data points. In the present invention, the hidden state only needs to be reset to 0 at the beginning of the sentence when the whole sentence is scanned forward and backward. In the present invention, a plurality of sentences can be processed simultaneously. The Word embedding module 52 performs space vector mapping on the corpus information to obtain a Word vector, and in the present invention, the Word embedding module 52 performs space vector mapping on the corpus information through Word2vec to convert the text into a vector. The combining module 53 performs graph feature combination on the word vector processed by the word embedding module 52 to generate new features and inputs the new features and the word vector to the classifying module 54. The classification module 54 processes the new features and word vectors through a trained classification model to derive the client intent. The classification module 54 may classify the intention through mainstream intention recognition algorithms such as DSSM, text-CNN, BERT, and the like, which are mainstream. In the invention, the idea of a multi-scale convolution kernel Text-CNN is used, and a model constructed by the structure of the inclusion is referred to. The invention uses two layers of Incepotion structure, and 4 layers of convolution are deepest and are deeper than Text-CNN.
The specific method for combining the word vectors by the combination module 53 to obtain new features is as follows. As shown in fig. 2, each node (F1, F2, F3, and F4) in the graph is an input word vector, and when the graph is initialized, bidirectional directed edges are all constructed by default and are randomly assigned with corresponding weights. And then constructing an adjacency matrix according to the two-dimensional matrix, and generating a new characteristic according to the adjacency matrix. The new feature is a weighted sum of the corresponding word vector and its neighboring word vectors. F1' ═ W11F 1+ W2F 2+ W8F 3+ W10F 4, wherein W11, W2, W8 and W10 are weighted values. By analogy, new features F2 ', F3 ', and F4 ' are found, and the word vectors and the new features F1, F2, F3, F4, F1 ', F2 ', F3 ', and F4 ' are input to the classification module 54. Context information can be obtained more easily by using the graph characteristics, and the accuracy of subsequent network classification is improved.
The dialect storage unit 60 stores reply texts of reply clients. Each reply text corresponds to a client intent, and when the client intent is determined, the corresponding reply text is retrieved from the dialog storage unit 60. The utterance matching unit 70 matches a corresponding reply text from the utterance storage unit 60 according to the client intention and sends it to the TTS speech synthesis unit 40. The TTS speech synthesis unit 40 converts the received reply text into reply speech and sends it to the intelligent call unit 20. The smart call unit 20 plays the reply voice to the client.
As a preferred embodiment, the intention identifying unit 50 further includes: a customer analysis module 55. The client analysis module 55 collects all the client intentions of the current call of the client and analyzes the result of the current call, and sends the result of the current call to the client information management module 11 to update the corresponding client information. It can be understood that, in the call record, the behavior and attitude of the client greatly affect whether the task generating unit 10 needs to make a further telephone call to the client next time. Therefore, the client information management module 11 that returns the result of the current call to the task generating unit 10 updates the client information.
As shown in fig. 3, the invention also discloses an intelligent outbound method based on intention recognition, which comprises the following steps:
s1: a call task is generated.
Specifically, the specific method for generating the call task comprises the following steps: and acquiring the customer information. And screening out the client information meeting the conditions. And generating a call task according to the client information meeting the conditions.
S2: and automatically dialing the telephone of the customer according to the call task and acquiring the voice information of the customer after the telephone is connected.
Specifically, the specific method for automatically dialing the call of the customer according to the call task and acquiring the voice information of the customer after the call is connected comprises the following steps: and analyzing the call task to obtain a call strategy, wherein the call strategy comprises open voice and customer telephone. And obtaining the open-field voice according to the call strategy matching. And dialing the customer phone according to the call policy. And playing the open-field voice to the client after the client telephone is connected. And collecting voice information of the client.
S3: the speech information is converted into text information.
S4: the customer intent is identified from the textual information.
Specifically, the specific method of identifying the intention of the client from the text information is as follows: and performing word segmentation on the text information to obtain corpus information. And carrying out space vector mapping on the corpus information to obtain a word vector. And carrying out graph feature combination on the word vectors to generate new features. And inputting the new features and the word vectors into the trained classification model to obtain the intention of the client.
S5: and matching the corresponding reply text according to the intention of the client.
S6: and converting the reply text into reply voice and playing the reply voice to the client.
Further, after step S6, the intelligent outbound method based on intention recognition further includes:
and after the call is finished, collecting all the client intentions of the call of the client and analyzing the result of the call. And updating the client information of the client according to the call result.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It should be understood by those skilled in the art that the above embodiments do not limit the present invention in any way, and all technical solutions obtained by using equivalent alternatives or equivalent variations fall within the scope of the present invention.
Claims (10)
1. An intelligent outbound system based on intent recognition, comprising: the system comprises a task generating unit, an intelligent calling unit, an ASR voice recognition unit, a TTS voice synthesis unit, an intention recognition unit, a dialect storage unit and a dialect matching unit;
the task generating unit generates a call task and sends the call task to the intelligent call unit;
the intelligent calling unit intelligently dials the telephone of the client according to the calling task generated by the task generating unit, collects the voice information of the client after the telephone is connected and sends the voice information to the ASR voice recognition unit;
the ASR speech recognition unit converts speech information of a client into text information and sends the text information to the intention recognition unit;
the intention recognition unit analyzes the text information to recognize a user intention;
the dialect storage unit stores reply texts of reply clients;
the dialect matching unit matches a corresponding reply text from the dialect storage unit according to the client intention and sends the reply text to the TTS speech synthesis unit;
the TTS voice synthesis unit converts the received reply text into reply voice and sends the reply voice to the intelligent calling unit;
and the intelligent calling unit plays the reply voice to the client.
2. The intelligent outbound system of claim 1,
the task generating unit includes: the client information management module, the screening module and the generating module;
the client information management module stores and manages client information;
the screening module acquires the customer information from the customer information management module and screens the customer information meeting the conditions;
and the generation module generates the call task according to the screened customer information.
3. The intelligent outbound system of claim 2,
the intelligent calling unit comprises: the system comprises a task analysis module, an opening voice storage module, a voice matching module, a calling module, a voice playing module and a voice receiving module;
the task analysis module analyzes the call task to obtain a call strategy and sends the call strategy to the voice matching module and the call module, wherein the call strategy comprises an opening voice type and a client telephone;
the open field voice storage module is used for storing a plurality of open field voices;
the voice matching module matches corresponding open-field voice from the open-field voice storage module according to the calling strategy and sends the open-field voice to the voice playing module;
the calling module is used for dialing a telephone of a customer according to the calling strategy;
the voice playing module is used for playing the matched open-scene voice to the client after the calling module dials the client telephone;
the speech receiving module is used for receiving speech information of a client and sending the speech information to the ASR speech recognition unit;
the voice playing module is also used for playing the reply voice converted by the TTS voice synthesis unit to the client.
4. The intelligent outbound system of claim 3,
the intention identifying unit includes: the system comprises a named entity identification module, a word embedding module, a combination module and a classification module;
the named entity recognition module carries out word segmentation on the text information to obtain corpus information;
the word embedding module performs space vector mapping on the corpus information to obtain a word vector;
the combination module performs graph feature combination on the word vectors to generate new features and inputs the new features and the word vectors into the classification module;
and the classification module processes the new features and the word vectors through a trained classification model to obtain the client intention.
5. The intelligent outbound system of claim 4,
the intention identifying unit further includes: a customer analysis module;
the client analysis module collects all client intentions of the current call of the client, analyzes the result of the current call, and sends the result of the current call to the client information management module to update the corresponding client information.
6. An intelligent outbound method based on intention recognition is characterized by comprising the following steps:
generating a call task;
automatically dialing a call of a client according to the call task and acquiring voice information of the client after the call is connected;
converting the voice information into text information;
identifying a client intention according to the text information;
matching a corresponding reply text according to the client intention;
and converting the reply text into reply voice and playing the reply voice to the client.
7. The intelligent outbound method based on intent recognition according to claim 6,
the specific method for generating the call task comprises the following steps:
acquiring customer information;
screening out client information meeting the conditions;
and generating the call task according to the client information meeting the conditions.
8. The intelligent outbound method based on intent recognition according to claim 7,
the specific method for automatically dialing the call of the customer according to the call task and acquiring the voice information of the customer after the call is connected comprises the following steps:
analyzing the call task to obtain a call strategy, wherein the call strategy comprises an opening voice type and a customer telephone;
obtaining open-field voice according to the call strategy matching;
dialing a customer telephone according to the call strategy;
playing the opening voice to the client after the client telephone is connected;
and collecting the voice information of the client.
9. The intelligent outbound method based on intent recognition according to claim 8,
the specific method for identifying the intention of the client according to the text information comprises the following steps:
performing word segmentation on the text information to obtain corpus information;
performing space vector mapping on the corpus information to obtain a word vector;
carrying out graph feature combination on the word vectors to generate new features;
and inputting the new features and the word vectors into a trained classification model to obtain the client intention.
10. The intelligent outbound method based on intent recognition according to claim 9,
the intelligent outbound method based on intention recognition further comprises the following steps:
after the call is finished, collecting all the client intentions of the call of the client and analyzing the result of the call;
and updating the client information of the client according to the call result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010646720.0A CN111833871A (en) | 2020-07-07 | 2020-07-07 | Intelligent outbound system based on intention recognition and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010646720.0A CN111833871A (en) | 2020-07-07 | 2020-07-07 | Intelligent outbound system based on intention recognition and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111833871A true CN111833871A (en) | 2020-10-27 |
Family
ID=72900415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010646720.0A Pending CN111833871A (en) | 2020-07-07 | 2020-07-07 | Intelligent outbound system based on intention recognition and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111833871A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112532794A (en) * | 2020-11-24 | 2021-03-19 | 携程计算机技术（上海）有限公司 | Voice outbound method, system, equipment and storage medium |
| CN112804404A (en) * | 2021-01-28 | 2021-05-14 | 上海米鹊科技有限公司 | Method and system for realizing automatic voice interaction based on analog telephone |
| CN112866086A (en) * | 2021-01-06 | 2021-05-28 | 招商银行股份有限公司 | Information pushing method, device, equipment and storage medium for intelligent outbound |
| CN112866491A (en) * | 2020-12-31 | 2021-05-28 | 安徽迪科数金科技有限公司 | Multi-meaning intelligent question-answering method based on specific field |
| CN113114851A (en) * | 2021-03-24 | 2021-07-13 | 北京百度网讯科技有限公司 | Intelligent voice reply method, equipment and storage medium for incoming call |
| CN113314106A (en) * | 2021-05-19 | 2021-08-27 | 国网辽宁省电力有限公司 | Electric power information query and regulation function calling method based on voice and intention recognition |
| CN113382116A (en) * | 2021-06-11 | 2021-09-10 | 浙江百应科技有限公司 | User number encryption method and device and electronic equipment |
| CN113395395A (en) * | 2021-05-31 | 2021-09-14 | 浙江惠瀜网络科技有限公司 | AI-based intelligent voice return visit method |
| CN113596270A (en) * | 2021-08-18 | 2021-11-02 | 中国平安财产保险股份有限公司 | Outbound strategy configuration method, device and equipment based on intelligent voice customer service |
| CN113905137A (en) * | 2021-11-11 | 2022-01-07 | 北京沃东天骏信息技术有限公司 | Call method and device, and storage medium |
| CN114025050A (en) * | 2021-11-08 | 2022-02-08 | 浙江百应科技有限公司 | Speech recognition method and device based on intelligent outbound and text analysis |
| CN115022471A (en) * | 2022-05-18 | 2022-09-06 | 北京互连众信科技有限公司 | Intelligent robot voice interaction system and method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647200A (en) * | 2018-04-04 | 2018-10-12 | 顺丰科技有限公司 | Talk with intent classifier method and device, equipment and storage medium |
| CN109949805A (en) * | 2019-02-21 | 2019-06-28 | 江苏苏宁银行股份有限公司 | Intelligent collection robot and collection method based on intention assessment and finite-state automata |
-
2020
- 2020-07-07 CN CN202010646720.0A patent/CN111833871A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647200A (en) * | 2018-04-04 | 2018-10-12 | 顺丰科技有限公司 | Talk with intent classifier method and device, equipment and storage medium |
| CN109949805A (en) * | 2019-02-21 | 2019-06-28 | 江苏苏宁银行股份有限公司 | Intelligent collection robot and collection method based on intention assessment and finite-state automata |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112532794A (en) * | 2020-11-24 | 2021-03-19 | 携程计算机技术（上海）有限公司 | Voice outbound method, system, equipment and storage medium |
| CN112866491A (en) * | 2020-12-31 | 2021-05-28 | 安徽迪科数金科技有限公司 | Multi-meaning intelligent question-answering method based on specific field |
| CN112866086B (en) * | 2021-01-06 | 2023-01-31 | 招商银行股份有限公司 | Information pushing method, device, equipment and storage medium for intelligent outbound |
| CN112866086A (en) * | 2021-01-06 | 2021-05-28 | 招商银行股份有限公司 | Information pushing method, device, equipment and storage medium for intelligent outbound |
| CN112804404A (en) * | 2021-01-28 | 2021-05-14 | 上海米鹊科技有限公司 | Method and system for realizing automatic voice interaction based on analog telephone |
| CN113114851A (en) * | 2021-03-24 | 2021-07-13 | 北京百度网讯科技有限公司 | Intelligent voice reply method, equipment and storage medium for incoming call |
| CN113314106A (en) * | 2021-05-19 | 2021-08-27 | 国网辽宁省电力有限公司 | Electric power information query and regulation function calling method based on voice and intention recognition |
| CN113395395A (en) * | 2021-05-31 | 2021-09-14 | 浙江惠瀜网络科技有限公司 | AI-based intelligent voice return visit method |
| CN113382116A (en) * | 2021-06-11 | 2021-09-10 | 浙江百应科技有限公司 | User number encryption method and device and electronic equipment |
| CN113596270A (en) * | 2021-08-18 | 2021-11-02 | 中国平安财产保险股份有限公司 | Outbound strategy configuration method, device and equipment based on intelligent voice customer service |
| CN113596270B (en) * | 2021-08-18 | 2023-02-14 | 中国平安财产保险股份有限公司 | Outbound strategy configuration method, device and equipment based on intelligent voice customer service |
| CN114025050A (en) * | 2021-11-08 | 2022-02-08 | 浙江百应科技有限公司 | Speech recognition method and device based on intelligent outbound and text analysis |
| CN113905137A (en) * | 2021-11-11 | 2022-01-07 | 北京沃东天骏信息技术有限公司 | Call method and device, and storage medium |
| CN115022471A (en) * | 2022-05-18 | 2022-09-06 | 北京互连众信科技有限公司 | Intelligent robot voice interaction system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111833871A (en) | Intelligent outbound system based on intention recognition and method thereof | |
| CN108877839B (en) | Voice quality perception evaluation method and system based on voice semantic recognition technology | |
| CN107798032B (en) | Method and device for processing response message in self-service voice conversation | |
| CN108428447B (en) | Voice intention recognition method and device | |
| CN110751943A (en) | Voice emotion recognition method and device and related equipment | |
| CN110610705B (en) | Voice interaction prompter based on artificial intelligence | |
| US8135579B2 (en) | Method of analyzing conversational transcripts | |
| WO2002089455A1 (en) | System and method for maximum benefit routing | |
| CN102236639B (en) | Update the system and method for language model | |
| CN110516057B (en) | Petition question answering method and device | |
| CN112131359A (en) | Intention identification method based on graphical arrangement intelligent strategy and electronic equipment | |
| CN109145050B (en) | Computing device | |
| CN111429157A (en) | Method, device and equipment for evaluating and processing complaint work order and storage medium | |
| CN111833076A (en) | Intelligent collection system and method | |
| CN113596270B (en) | Outbound strategy configuration method, device and equipment based on intelligent voice customer service | |
| CN106356056B (en) | Audio recognition method and device | |
| CN112364622A (en) | Dialog text analysis method, dialog text analysis device, electronic device and storage medium | |
| CN116631412A (en) | Method for judging voice robot through voiceprint matching | |
| CN113726942A (en) | Intelligent telephone answering method, system, medium and electronic terminal | |
| CN106709018A (en) | Method and device for hitting preset problems | |
| CN112579751A (en) | User information filling method and device and computer equipment | |
| CN107807949A (en) | Intelligent interactive method, equipment and storage medium | |
| CN113194210B (en) | Voice call access method and device | |
| CN113724690A (en) | PPG feature output method, target audio output method and device | |
| CN114254088A (en) | Method for constructing automatic response model and automatic response method |
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 | ||
| CB02 | Change of applicant information |
Address after: Xinyada technology building, 3888 Jiangnan Avenue, Binjiang District, Hangzhou City, Zhejiang Province 310051 Applicant after: Sinyada Technology Co.,Ltd. Address before: Xinyada technology building, 3888 Jiangnan Avenue, Binjiang District, Hangzhou City, Zhejiang Province 310051 Applicant before: SUNYARD SYSTEM ENGINEERING Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201027 |
|
| RJ01 | Rejection of invention patent application after publication |