CN116389644B - Outbound system based on big data analysis - Google Patents
Outbound system based on big data analysis Download PDFInfo
- Publication number
- CN116389644B CN116389644B CN202211405149.9A CN202211405149A CN116389644B CN 116389644 B CN116389644 B CN 116389644B CN 202211405149 A CN202211405149 A CN 202211405149A CN 116389644 B CN116389644 B CN 116389644B
- Authority
- CN
- China
- Prior art keywords
- outbound
- value
- matching
- client
- conversation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000004891 communication Methods 0.000 claims abstract description 12
- 238000006243 chemical reaction Methods 0.000 claims description 22
- 230000036651 mood Effects 0.000 claims description 17
- 238000004088 simulation Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10L15/16—Speech classification or search using artificial neural networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Telephonic Communication Services (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an outbound system based on big data analysis, which belongs to the technical field of artificial intelligence and comprises a speaking module, a control module and a server; the voice operation module is used for optimizing the outbound robot, the control module is used for outbound control, a plurality of dialogue templates are set, and a template library is built according to the set dialogue templates; the method comprises the steps that an imported number list is obtained, the number list comprises numbers and corresponding client information, the number dialing is carried out through an outbound robot, after the numbers are dialed, voice information of a client is obtained, corresponding conversation templates are matched from a template library according to the obtained client information and the voice information, the matched conversation templates are input into the outbound robot, and the outbound robot carries out conversation communication with the client; through the mutual coordination between the speech operation module and the control module, the intelligent communication between the external calling system and the client is realized, the conversation language of the external calling robot is changed according to the real-time scene change, and the effective channel communication rate with the client is increased.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence, and particularly relates to an outbound system based on big data analysis.
Background
With the rapid development of artificial intelligence technology, it is becoming more and more common to use an outbound system to replace manual outbound for user terminals. Compared with the traditional manual call, the outbound call system has obvious advantages such as high working efficiency and low operation cost. In view of the significant advantages of the outbound system, the outbound system is widely applied in different business scenarios in many industries at present, for example, in the field of financial science and technology, a financial institution can collect users through the outbound system; in the e-commerce field, the e-commerce platform can perform satisfaction return visit and the like on the user through an outbound system.
However, the outbound robot in the current outbound system is dead when answering with the client, and has poor communication effect, so that the client can easily hear the opposite robot and hang up the call frequently.
Disclosure of Invention
In order to solve the problems of the scheme, the invention provides an outbound system based on big data analysis.
The aim of the invention can be achieved by the following technical scheme:
an outbound system based on big data analysis comprises a speaking module, a control module and a server;
the conversation module is used for optimizing the outbound robots, acquiring a large amount of conversation data based on big data analysis, screening the acquired conversation data to acquire a conversation material set, classifying the acquired conversation material set to acquire a corresponding classification set, acquiring the outbound robots, training and optimizing the outbound robots through the acquired classification set to acquire the correspondingly classified outbound robots, wherein an auxiliary model is arranged in the classified outbound robots, and the auxiliary model is used for assisting in asking and answering the outbound robots;
the control module is used for outbound control, a plurality of dialogue templates are set, and a template library is established according to the set dialogue templates; the method comprises the steps of obtaining an imported number list, wherein the number list comprises numbers and corresponding client information, dialing the numbers through an outbound robot, obtaining voice information of the clients after dialing the numbers, matching corresponding conversation templates from a template library according to the obtained client information and the voice information, inputting the matched conversation templates into the outbound robot, and carrying out conversation communication with the clients through the outbound robot.
Further, the working method of the auxiliary model comprises the following steps:
obtaining the language values of the clients, respectively marked as YQc, obtaining the alternative answers, and marking the alternative answers as i, wherein i=1, 2, … …,n, n is a positive integer; obtaining the language value and the matching language value of the alternative answers, which are marked as YYzi and YQzi respectively, according to the formulaCalculating a corresponding priority value, wherein alpha is a conversion value, according to the formula +.>The value is obtained by matching; and sorting the calculated priority values according to the order from big to small, selecting the alternative answers corresponding to the first priority value as target answers, matching the answering speech of the corresponding outbound robot according to the priority value corresponding to the target answers and the customer speech value, and transmitting the target answers and the answering areas to the outbound robot.
Further, the method for determining α includes:
obtaining a conversion value matching table and calculatingAnd inputting the calculated matching value into a conversion value matching table for matching to obtain a corresponding conversion value.
Further, the method for establishing the conversion value matching table comprises the following steps:
the formula is given byThe calculated value is marked as a matching value, a matching value interval is obtained, the matching value interval is divided into a plurality of single intervals in a manual mode, corresponding conversion values are set for each single interval, and a conversion value matching table is built in a summarizing mode.
Further, the method for matching the answering gas of the corresponding external caller according to the priority value corresponding to the target answering and the customer gas value comprises the following steps:
and converting the obtained priority value and the customer mood value into mood coordinates, inputting the obtained mood coordinates into a mood model for matching, and obtaining corresponding answering mood.
Further, the establishment method of the language model comprises the following steps:
setting a plurality of simulation coordinates according to a classification set, establishing a coordinate model, inputting the simulation coordinates into the coordinate model, combining the simulation coordinates according to the positions of the simulation coordinates and corresponding response language gas labels to obtain a plurality of combined areas, marking corresponding response language gas labels for each combined area, and marking the current coordinate model as a language gas model.
Further, the working method of the language model comprises the following steps:
and acquiring the input intonation coordinates, identifying a merging area corresponding to the intonation coordinates, and matching corresponding answering intonation according to the answering intonation labels corresponding to the merging area.
Further, the method for matching the corresponding dialogue template from the template library according to the obtained client information and the voice information comprises the following steps:
and analyzing the voice information of the client, adjusting the client information according to the analysis result, calculating the similarity between each dialogue template and the client information, and selecting the dialogue template with the highest similarity for output.
Compared with the prior art, the invention has the beneficial effects that:
through the mutual coordination between the speech operation module and the control module, the intelligent communication between the outbound system and the client is realized, the conversation language of the outbound robot is changed according to the real-time scene change, and the effective channel communication rate with the client is increased; the communication between the outbound robot and the client is not so dead, certain client information is supplemented through voice analysis, and the client information which is possibly wrong can be adjusted, so that the used dialogue template is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a functional block diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, an outbound system based on big data analysis comprises a speaking module, a control module and a server;
the voice operation module and the control module are both in communication connection with the server;
the speaking module is used for optimizing the outbound robot, and the specific method comprises the following steps:
based on big data analysis, a large amount of dialogue data is obtained, namely a large amount of personnel dialogue data is obtained from the Internet through the existing big data technology; screening the obtained dialogue data to obtain a conversation material set, classifying the obtained conversation material set to obtain a corresponding classification set, namely classifying according to the corresponding answering environment label; the method comprises the steps that an outbound robot is obtained, wherein the outbound robot is a robot in the existing outbound system, and can automatically dial, answer, record and the like according to an imported number; training and optimizing the outbound robots through the obtained classification set to obtain the outbound robots with corresponding classifications, wherein auxiliary models are arranged in the classified outbound robots and are used for assisting in asking and answering the outbound robots.
Screening the obtained dialogue data, namely setting corresponding answering environments according to the communication field of the enterprise outbound, such as answering environments related to merchant celebration activities, sales of sports shoes and the like, screening the obtained dialogue data according to the set answering environments, eliminating dialogue data which cannot appear in the dialogue environments, processing one piece of dialogue data into one element, marking corresponding answering environment labels, and integrating one piece of dialogue data into a conversation material set according to the flow by the existing recognition analysis technology. Processing a piece of dialogue data into an element, namely processing the dialogue data into training data, and according to the language value and the language value corresponding to the dialogue mark; the language value and the language value are analyzed through a dialogue analysis model, the language value is used for judging the language of a customer, the language value is used for judging the coincidence degree of a replying customer, namely, a replying two-party evaluation value is specifically built based on a neural network, the neural network comprises an error back propagation neural network, an RBF neural network and a deep convolution neural network, the selection can be carried out according to actual conditions, a corresponding training set is built through a manual mode for training, and the analysis is carried out through the dialogue analysis model after the training is successful, so that the corresponding language value and the language value are obtained; because neural networks are conventional in the art, the specific setup and training process is not described in detail.
Because answers to the same sentence in different languages may have great differences in the chinese dialogue, a distinction is required, otherwise, a one-to-many answer situation will occur when the subsequent external caller training optimization is performed.
The auxiliary model is used for carrying out auxiliary question answering on the outbound robot, namely, after the outbound robot is optimally trained through a classification set, the current outbound robot can analyze the language values of corresponding client sentences, the language values of alternative answers and the matched language values according to real-time conversations with clients, the matched language values are the most suitable client language values of the alternative answers, a plurality of alternative answers are arranged at the moment, the auxiliary model is used for carrying out priority analysis on the plurality of alternative answers according to the obtained client language values, the language values of the alternative answers and the matched language values, and selecting the corresponding alternative answers to answer according to analysis results; the auxiliary model is an algorithm model; the working method of the specific auxiliary model comprises the following steps:
obtaining the language values of clients, respectively marking YQc, obtaining the alternative answers, and marking the alternative answers as i, wherein i=1, 2, … …, n and n are positive integers; obtaining the language value and the matching language value of the alternative answers, which are marked as YYzi and YQzi respectively, according to the formulaCalculating a corresponding priority value, wherein alpha is a conversion value, according to the formula +.>The value is obtained by matching; and sorting the calculated priority values according to the order from big to small, selecting the alternative answers corresponding to the first priority value as target answers, matching the answering speech of the corresponding outbound robot according to the priority value corresponding to the target answers and the customer speech value, and transmitting the target answers and the answering areas to the outbound robot.
The method for determining alpha comprises the following steps:
obtaining a conversion value matching table and calculatingAnd inputting the calculated matching value into a conversion value matching table for matching to obtain a corresponding conversion value.
The method for establishing the conversion value matching table comprises the following steps:
the formula is given byThe calculated value is marked as a matching value, a possible matching value interval is obtained, the matching value interval is divided into a plurality of single intervals in a manual mode, and the interval spans are not required to be the same for the single intervals; and setting corresponding conversion values for each single interval, and summarizing to establish a conversion value matching table. The method is mainly characterized in that the method is mainly used for carrying out discussion setting through an expert group according to the similarity of the language and the weight relation between the language value, and finally a fixed conversion value matching table is formed.
The method for matching the answering voice of the corresponding external caller according to the priority value corresponding to the target answering and the voice value of the client comprises the following steps:
and converting the obtained priority value and the customer mood value into mood coordinates, inputting the obtained mood coordinates into a mood model for matching, and obtaining corresponding answering mood.
The establishment method of the language model comprises the following steps:
setting the answering dialects by a manual mode according to the dialects possibly possessed by different clients, wherein the setting is generally 5-6, and the setting can be adjusted according to the actual enterprise demands; setting a plurality of simulation coordinates according to the classification set, wherein the simulation coordinates comprise priority values and customer tone values, simulating a plurality of groups of dialogue data in the existing mode, calculating corresponding priority values according to a priority value calculation method to form simulation coordinates, and marking corresponding response tone labels on the simulation coordinates in a manual mode; establishing a coordinate model, inputting simulated coordinates into the coordinate model, merging the simulated coordinates according to the positions of the simulated coordinates and the corresponding answering gas labels to obtain a plurality of merging areas, marking the corresponding answering gas labels for each merging area, and marking the current coordinate model as a gas model.
And (3) carrying out simulated coordinate combination according to the positions of the simulated coordinates and the corresponding answering gas labels, namely combining the adjacent simulated coordinates with the same answering gas labels, marking the area corresponding to the simulated coordinates as a combined area, and particularly combining by the existing method.
The working method of the language model comprises the following steps:
and acquiring the input intonation coordinates, identifying a merging area corresponding to the intonation coordinates, and matching corresponding answering intonation according to the answering intonation labels corresponding to the merging area.
The control module is used for outbound control, and the specific method comprises the following steps:
setting a plurality of dialogue templates, wherein the dialogue templates are formulated according to the answering environment and possible client information, the client information comprises information such as age, academic, occupation, sex and the like, the specific dialogue templates are set according to a manual mode, or the existing dialogue templates are used/adapted, and the dialogue templates are used for application just after the client is connected, namely only at the front end; establishing a template library according to the set dialogue template;
the method comprises the steps of obtaining an imported number list, wherein the number list comprises numbers and corresponding client information, the client information can be incomplete, dialing the numbers through an outbound robot, after dialing the numbers, obtaining voice information of the clients, if the voice information of the clients is good, obtaining the voice information of the clients, matching corresponding dialogue templates from a template library according to the obtained client information and the voice information, inputting the matched dialogue templates into the outbound robot, and carrying out dialogue communication with the clients through the outbound robot. The beginning communicates with the customer according to the dialogue template and answers by combining the auxiliary model.
The method for matching the corresponding dialogue templates from the template library according to the obtained client information and the voice information comprises the following steps:
and analyzing the voice information of the client, adjusting the client information according to the analysis result, calculating the similarity between each dialogue template and the client information, and selecting the dialogue template with the highest similarity for output.
And calculating the similarity between each dialogue template and the client information, calculating the similarity between the client information and the adaptive client information range according to each dialogue template, and specifically calculating and matching by the existing method.
The voice information of the client is analyzed, namely the gender and age interval of the client are judged through the voice information of the client, and then the client information is adjusted, the identification can be realized through the existing voice identification method, because the voice information is blank when a lot of client information in the number list appears, when the voice information is blank or incomplete, certain information supplement can be carried out through voice analysis, and the client information which is possibly wrong can be adjusted, so that the used dialogue template is more accurate.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas which are obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and preset parameters and preset thresholds in the formulas are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (5)
1. An outbound system based on big data analysis is characterized by comprising a speaking module, a control module and a server;
the conversation module is used for optimizing the outbound robots, acquiring a large amount of conversation data based on big data analysis, screening the acquired conversation data to acquire a conversation material set, classifying the acquired conversation material set to acquire a corresponding classification set, acquiring the outbound robots, training and optimizing the outbound robots through the acquired classification set to acquire the correspondingly classified outbound robots, wherein an auxiliary model is arranged in the classified outbound robots, and the auxiliary model is used for assisting in asking and answering the outbound robots;
the control module is used for outbound control, a plurality of dialogue templates are set, and a template library is established according to the set dialogue templates; the method comprises the steps that an imported number list is obtained, the number list comprises numbers and corresponding client information, the number dialing is carried out through an outbound robot, after the numbers are dialed, voice information of a client is obtained, corresponding conversation templates are matched from a template library according to the obtained client information and the voice information, the matched conversation templates are input into the outbound robot, and the outbound robot carries out conversation communication with the client;
the working method of the auxiliary model comprises the following steps:
obtaining the language values of clients, respectively marking YQc, obtaining the alternative answers, and marking the alternative answers as i, wherein i=1, 2, … …, n and n are positive integers; obtaining the language value and the matching language value of the alternative answers, which are marked as YYzi and YQzi respectively, according to the formulaCalculating corresponding priority value, wherein alpha is a conversion value according to the formulaThe value is obtained by matching; sorting the calculated priority values according to the order from big to small, selecting the alternative answers corresponding to the first priority value as target answers, matching the answering speech sounds corresponding to the external calling robots according to the priority values corresponding to the target answers and the customer speech sound values, and transmitting the target answers and the answering areas to the external calling robots;
the method for determining alpha comprises the following steps:
obtaining a conversion value matching table and calculatingInputting the calculated matching value into a conversion value matching table for matching to obtain a corresponding conversion value;
the method for establishing the conversion value matching table comprises the following steps:
the formula is given byThe calculated value is marked as a matching value, a matching value interval is obtained, the matching value interval is divided into a plurality of single intervals in a manual mode, corresponding conversion values are set for each single interval, and a conversion value matching table is built in a summarizing mode.
2. The outbound system based on big data analysis of claim 1, wherein the method for matching the dialect of the corresponding outbound robot based on the priority value corresponding to the target dialect and the customer dialect value comprises:
and converting the obtained priority value and the customer mood value into mood coordinates, inputting the obtained mood coordinates into a mood model for matching, and obtaining corresponding answering mood.
3. The outbound system based on big data analysis of claim 2, wherein the method for creating the mood model comprises:
setting a plurality of simulation coordinates according to a classification set, establishing a coordinate model, inputting the simulation coordinates into the coordinate model, combining the simulation coordinates according to the positions of the simulation coordinates and corresponding response language gas labels to obtain a plurality of combined areas, marking corresponding response language gas labels for each combined area, and marking the current coordinate model as a language gas model.
4. The outbound system based on big data analysis of claim 3, wherein the method for operating the mood model comprises:
and acquiring the input intonation coordinates, identifying a merging area corresponding to the intonation coordinates, and matching corresponding answering intonation according to the answering intonation labels corresponding to the merging area.
5. The outbound system based on big data analysis of claim 1, wherein the method for matching corresponding dialogue templates from the template library based on the obtained client information and the voice information comprises:
and analyzing the voice information of the client, adjusting the client information according to the analysis result, calculating the similarity between each dialogue template and the client information, and selecting the dialogue template with the highest similarity for output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211405149.9A CN116389644B (en) | 2022-11-10 | 2022-11-10 | Outbound system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211405149.9A CN116389644B (en) | 2022-11-10 | 2022-11-10 | Outbound system based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116389644A CN116389644A (en) | 2023-07-04 |
| CN116389644B true CN116389644B (en) | 2023-11-03 |
Family
ID=86969892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211405149.9A Active CN116389644B (en) | 2022-11-10 | 2022-11-10 | Outbound system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116389644B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751943A (en) * | 2019-11-07 | 2020-02-04 | 浙江同花顺智能科技有限公司 | Voice emotion recognition method and device and related equipment |
| CN110990543A (en) * | 2019-10-18 | 2020-04-10 | 平安科技（深圳）有限公司 | Intelligent conversation generation method and device, computer equipment and computer storage medium |
| CN111916111A (en) * | 2020-07-20 | 2020-11-10 | 中国建设银行股份有限公司 | Intelligent voice outbound method and device with emotion, server and storage medium |
| CN114242109A (en) * | 2021-12-17 | 2022-03-25 | 中国平安财产保险股份有限公司 | Intelligent outbound method and device based on emotion recognition, electronic equipment and medium |
| CN114999533A (en) * | 2022-06-09 | 2022-09-02 | 平安科技（深圳）有限公司 | Intelligent question-answering method, device, equipment and storage medium based on emotion recognition |
-
2022
- 2022-11-10 CN CN202211405149.9A patent/CN116389644B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110990543A (en) * | 2019-10-18 | 2020-04-10 | 平安科技（深圳）有限公司 | Intelligent conversation generation method and device, computer equipment and computer storage medium |
| CN110751943A (en) * | 2019-11-07 | 2020-02-04 | 浙江同花顺智能科技有限公司 | Voice emotion recognition method and device and related equipment |
| CN111916111A (en) * | 2020-07-20 | 2020-11-10 | 中国建设银行股份有限公司 | Intelligent voice outbound method and device with emotion, server and storage medium |
| CN114242109A (en) * | 2021-12-17 | 2022-03-25 | 中国平安财产保险股份有限公司 | Intelligent outbound method and device based on emotion recognition, electronic equipment and medium |
| CN114999533A (en) * | 2022-06-09 | 2022-09-02 | 平安科技（深圳）有限公司 | Intelligent question-answering method, device, equipment and storage medium based on emotion recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116389644A (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108737667B (en) | Voice quality inspection method and device, computer equipment and storage medium | |
| CN111739516A (en) | Speech recognition system for intelligent customer service call | |
| CN107452385A (en) | A kind of voice-based data evaluation method and device | |
| CN111192060A (en) | Electric power IT service-based full-channel self-service response implementation method | |
| CN110175229B (en) | Method and system for on-line training based on natural language | |
| CN109065052B (en) | Voice robot | |
| CN103458056A (en) | Speech intention judging method based on automatic classification technology for automatic outbound system | |
| CN110516057B (en) | Petition question answering method and device | |
| CN110377726B (en) | Method and device for realizing emotion recognition of natural language text through artificial intelligence | |
| CN112235470B (en) | Incoming call client follow-up method, device and equipment based on voice recognition | |
| CN114818649A (en) | Service consultation processing method and device based on intelligent voice interaction technology | |
| CN113297365B (en) | User intention judging method, device, equipment and storage medium | |
| CN116389644B (en) | Outbound system based on big data analysis | |
| CN115905187A (en) | Intelligent proposition system for cloud computing engineering technician authentication | |
| CN113990288B (en) | Method for automatically generating and deploying voice synthesis model by voice customer service | |
| CN114710592B (en) | Calling system and method based on artificial intelligence | |
| CN110765242A (en) | Method, device and system for providing customer service information | |
| CN114239565A (en) | Deep learning-based emotion reason identification method and system | |
| CN112860873A (en) | Intelligent response method, device and storage medium | |
| CN114138947A (en) | Text processing method and device | |
| CN111985934A (en) | Intelligent customer service dialogue model construction method and application | |
| CN117411970B (en) | Man-machine coupling customer service control method and system based on sound processing | |
| CN116600053B (en) | Customer service system based on AI large language model | |
| CN117131183B (en) | Customer service automatic reply method and system based on session simulation | |
| CN117763120A (en) | Intention recognition system and method suitable for client chat records |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |