CN112185391A - Automatic modification processing method for customer service record - Google Patents
Automatic modification processing method for customer service record Download PDFInfo
- Publication number
- CN112185391A CN112185391A CN202011058890.3A CN202011058890A CN112185391A CN 112185391 A CN112185391 A CN 112185391A CN 202011058890 A CN202011058890 A CN 202011058890A CN 112185391 A CN112185391 A CN 112185391A
- Authority
- CN
- China
- Prior art keywords
- customer service
- voice
- record
- service record
- customer
- 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
- 230000004048 modification Effects 0.000 title claims abstract description 12
- 238000012986 modification Methods 0.000 title claims abstract description 12
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000004044 response Effects 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 5
- 235000009508 confectionery Nutrition 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 208000031361 Hiccup Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000013067 intermediate product Substances 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
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an automatic modification processing method for a customer service record, which is applied to an intelligent customer service scene, carries out voice recognition on received voice data of a user by an intelligent voice customer service, carries out natural voice processing, and provides corresponding customer service by the intelligent voice customer service according to the semantics of the user. And matching corresponding customer service voice data from a preset template database according to the voice data sent by the user and responding to the user. Performing voice recognition on the voice contents stated by the two parties in the response process in real time and converting the voice contents into characters to form a primary customer service record; and automatically correcting the content which does not accord with the record specification in the initial customer service record to obtain a perfect customer service record which accords with the specification of the customer service record. The invention can improve the processing efficiency of the customer service record and improve the customer service efficiency.
Description
Technical Field
The invention relates to the technical field of intelligent clients, in particular to an automatic modification processing method for a customer service record.
Background
For customer service work, intelligent voice is one of the trends in future development, and the customer service process is generally recorded through video shooting, so that the process of customer service is comprehensively mastered for supervision and evidence storage. With the continuous development and application popularization of artificial intelligence technology, the application of intelligent voice to the recognition of continuous voice of multiple persons tends to mature. The intelligent voice technology is applied to the customer service or face check scene, the current customer service mode is greatly changed, the voice contents stated by the customer service personnel and the customers are automatically recognized into characters in real time in the process of customer service, and the certified customer service writing text can be obtained. However, the existing technology for recognizing the speech into the text has the following disadvantages: the word recognition is inaccurate; the records are not standardized; the recognition is serious in spoken language, is not suitable for solemn and formal scenes, and has limited application scenes.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide an automatic modification processing method for a customer service record, which can improve the processing efficiency of the customer service record and improve the customer service efficiency.
In order to solve the technical problem, the invention provides an automatic modification processing method for a customer service record, which comprises the following steps:
step S10, answering the voice signal of the client through the intelligent power supply seat;
step S11, the intelligent voice customer service carries out voice recognition to the received voice data of the customer, carries out natural voice processing, and determines the service type according to the semantics of the customer;
step S12, according to the voice data sent by the client, matching the corresponding customer service voice template from the preset voice template library corresponding to the service type, and adopting the voice in the customer service voice template to respond to the client;
step S13, real-time voice recognition is carried out to the voice content stated by the two parties in the response process and converted into characters, and a preliminary customer service record is formed;
and step S14, automatically correcting the content which does not conform to the record standard in the preliminary customer service record to obtain a perfect customer service record which conforms to the customer service record regulation.
Preferably, further comprising:
presetting a voice template library corresponding to each class of service type, wherein the voice template library comprises corresponding customer service voice templates;
presetting a voice style corresponding to each customer service voice template, wherein the voice style comprises the following steps: a full and pure man's voice, a soft, sweet and beautiful woman's voice, a standard genuine english woman's voice;
presetting a hotword corresponding to each service type and a weight corresponding to each hotword, wherein the hotwords comprise: name of person, place name, proper noun of service.
Preferably, the step S11 further includes:
and determining the corresponding service type according to the hot words contained in the voice data of the client.
Preferably, the step S14 further includes:
and performing entity word correction, punctuation correction, regulation correction and smooth optimization processing of spoken language on the content in the preliminary customer service record.
Preferably, after the step S14, the method further includes:
extracting important contents aiming at the text intelligently modified by the customer service, and giving out text contents and positions corresponding to the dispute focus for highlighting;
and analyzing the course of the dispute according to the customer service condition, and correcting the currently applied customer service technical template.
Preferably, in the step S13, the identity of the voice data sender is distinguished by adopting a radio device or adding marks to the voice key frames.
The embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides an automatic modification processing method for a customer service record, which is applied to an intelligent customer service scene, and is used for carrying out voice recognition on received voice data of a user by an intelligent voice customer service, carrying out natural voice processing and providing corresponding customer service by the intelligent voice customer service according to the semantics of the user. And matching corresponding customer service voice data from a preset template database according to the voice data sent by the user and responding to the user. Performing voice recognition on the voice contents stated by the two parties in the response process in real time and converting the voice contents into characters to form a primary customer service record; and automatically correcting the content which does not accord with the record specification in the initial customer service record to obtain a perfect customer service record which accords with the specification of the customer service record. By implementing the invention, the customer service record is more in line with the standard, the workload of manual re-checking is reduced, and the processing efficiency of the customer service record is improved; meanwhile, the system can assist the customer service to perform customer service event analysis and improve the customer service efficiency.
Drawings
Fig. 1 is a main flow diagram of an embodiment of an automatic customer service record modification processing method according to the present invention;
FIG. 2 is a schematic view of a comparison of the text referenced in FIG. 1 before and after correction;
FIG. 3 is a schematic illustration of highlighting a dispute point in text as referred to in FIG. 1.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
For those skilled in the art to more clearly understand the objects, technical solutions and advantages of the present invention, the following description will be further provided in conjunction with the accompanying drawings and examples.
Fig. 1 is a main flow diagram illustrating an embodiment of an automatic customer service record modification processing method according to the present invention; referring to fig. 2 and fig. 3 together, in this embodiment, the method for automatically modifying a customer service record includes the following steps:
step S10, answering the voice signal of the client through the intelligent power supply seat;
step S11, the intelligent voice customer service carries out voice recognition to the received voice data of the customer, carries out natural voice processing, and determines the service type according to the semantics of the customer;
in a specific example, the step S11 further includes:
determining a corresponding service type according to a hotword contained in voice data of a client, wherein the hotword comprises: name of person, place name, proper noun of service.
Step S12, according to the voice data sent by the client, matching the corresponding customer service voice template from the preset voice template library corresponding to the service type, and adopting the voice in the customer service voice template to respond to the client;
step S13, real-time voice recognition is carried out to the voice content stated by the two parties in the response process and converted into characters, and a preliminary customer service record is formed;
preferably, in the step S13, the identity of the voice data sender is distinguished by adopting a radio device or adding marks to the voice key frames.
Specifically, in some examples, the method of the present invention may be used to identify the voice content during the customer service process to obtain the corresponding text records. The voice recognition means a service of converting a recording file or a real-time audio stream into characters, can support languages such as Chinese and English, supports voice recognition under a noise environment and with background sounds, supports a machine to automatically separate different voices, and supports fast customization of hot words in recognition to improve accuracy. The voice recognition service is divided into three sub-services of recording file recognition, real-time voice recognition and one-sentence speech recognition, provides diversified calling modes such as RESTful API/SDK and the like, and can be adapted in various different practical use scenes. Here, in the customer service process, the identities of people of each party, such as a customer and a customer service person, need to be distinguished, for example, the identities can be distinguished according to a radio device such as a microphone, or a voice is dotted (a voice key frame is marked) to distinguish the identities of the parties. And performing voice recognition on the voice content, and converting the voice content into corresponding character records which can be distinguished by the identities of all parties.
And step S14, automatically correcting the content which does not conform to the record standard in the preliminary customer service record to obtain a perfect customer service record which conforms to the customer service record regulation.
Preferably, the step S14 further includes:
and performing entity word correction, punctuation correction, regulation correction and smooth optimization processing of spoken language on the content in the preliminary customer service record.
As shown in fig. 2, in this step, the entity words in the text records may be modified, such as modifying legal terms, name of person, place, company, etc., for example, "home" is modified to "jiade place". The punctuations of the character records can be corrected, and meanwhile, the punctuations of the title numbers are newly added, for example, the punctuations of the title numbers are added when the law is quoted, and the numbers when the law is quoted are corrected into the standard digital form, for example, the regulations of No. 1 of the statement law of the people's republic of China and No. 169 of the statement law of the people's republic of China are corrected into the regulations of No. one hundred thirty-four first money and No. one hundred sixty-nine of the statement law of the people's republic of China. In addition, smooth optimization is performed on the spoken language, such as recording the original text as hiccup. Whether all parties hear clearly or not. After smooth optimization, the result is that whether each person hears clearly or not is obtained. "and the like.
It can be understood that, during implementation, the speech recognition processing of the customer service can be configured in a scene, a customer service specification library can be set, various scenes can be set in the customer service specification library, and when different customer service types are involved, the format of the character record is adjusted according to the scene mode, so that the character record is corrected, and the customer service record meeting the specification is obtained.
In addition, the method can also be applied to other fields, such as automatic correction of court trial records in the court trial process through expansion.
Preferably, after the step S14, the method further includes:
extracting important contents aiming at the text intelligently modified by the customer service, and giving out text contents and positions corresponding to the dispute focus for highlighting;
and analyzing the course of the dispute according to the customer service condition, and correcting the currently applied customer service technical template.
It can be understood that after the corrected customer service record is obtained, text analysis is performed on the customer service record, events related to the customer service are analyzed, and the focus of the customer service is determined. Specifically, when analyzing the customer service record, different customer service record analysis strategies can be preset according to the service business range of the customer service staff. For example, semantic analysis can be performed on the customer service record in real time, so as to summarize events related to the current customer service, such as an event of power failure in the customer service of the power system, an event of power fee error, and the like. After determining the event related to the customer service, analyzing the customer service record based on the analysis strategy corresponding to the event, and specifically matching various problems possibly occurring in the event with the customer service record, thereby determining the dialect required to be performed by the customer service staff in the customer service process. For example, for the reason of power failure in the power system, whether the power system is arreared or not can be determined firstly, and then a customer service staff is prompted or guided to carry out corresponding speaking and inquiring about the customer; if the customer answers the non-arrearage according to the matching of the customer service record, the customer service staff can be guided to do corresponding operation on whether the customer service staff fails or not, and therefore the customer service staff is assisted to provide efficient customer service.
In some examples, the event may be determined from a service business scope, semantic analysis, event correspondence analysis policy determination, event-related problem determination, and so on, and finally a problem correspondence dialog may be obtained; the specific analysis strategy is related to an application scenario, for example, a power failure event may be caused by reasons such as arrearage and equipment failure, and then the specific analysis strategy may be eliminated from simple to complex by using an elimination method, or may be eliminated by counting common reasons, and the like.
In addition, the customer service record auxiliary system can be applied to court trial scenes, and corresponding reference is provided for judges by recording records in the court trial process and analyzing the obtained court trial records. Specifically, when analyzing the court trial records, the types of cases of the court trial, such as jurisdictional cases, criminal cases, civil cases, administrative cases, executive cases, or other cases, may be determined first, different case analysis strategies may be preset for different case types, corresponding analysis strategies may be determined according to the case types, the court trial records are analyzed, the case causes of the cases are analyzed, and a dispute focus is determined from the court trial records (generally, legal litigation is all caused by disputes, and the pre-cause consequence causing disputes is the dispute focus of the cases). In the concrete implementation, corresponding legal vocabularies can be matched for description according to the respective speaking contents of each party in the court trial record, such as the original report, the reported party and the witness, namely, the expression of non-legal professional vocabularies in the court trial record is matched with the professional vocabularies for representation, finally, the dispute focus can be determined according to the professional vocabularies, meanwhile, the sentences are extracted according to the contents related to the dispute focus, the dispute focus elements are determined from the sentences, and the case dispute focus is marked with emphasis.
After the dispute focus is determined, the content of the dispute focus can be marked and displayed. For example, the focus elements extracted from the dispute focus section content may be highlighted to highlight case emphasis. As shown in fig. 3, the dispute sentences in the loan behaviors are highlighted in yellow, and corresponding labels are set for the sentences.
It is understood that, in the above method, before step S10, it is further required to:
presetting a voice template library corresponding to each class of service type, wherein the voice template library comprises corresponding customer service voice templates;
presetting a voice style corresponding to each customer service voice template, wherein the voice style comprises the following steps: a full and pure man's voice, a soft, sweet and beautiful woman's voice, a standard genuine english woman's voice;
presetting hot words corresponding to each service type and weights corresponding to the hot words; by setting a different weight for each hotword, the probability of being identified may be increased or decreased.
Meanwhile, in the embodiment of the invention, the distributed ASR service is carried out by adopting a load balancing technology, so that the service capability of the ASR can be linearly and transversely expanded. To ensure availability, please have to ensure that the CPU level of the load is below 60%, and additionally perform N +1 deployment.
It can be understood that, in the embodiment of the present invention, the voice content stated by the customer service staff and the customer is subjected to voice recognition in real time and converted into characters to form a preliminary customer service record, and the content which does not meet the record specification in the preliminary customer service record is automatically corrected to obtain a perfect customer service record which meets the customer service record specification. The customer service record system takes each service as a unit, organizes and connects customer service information, customer service voice files, process information, intermediate products, final results and the like of the customer service in series, uses voice to replace manual word typing, clearly and intuitively expresses the customer service in the customer service according to requirements, can conveniently and quickly know the customer service process through the text record of the customer service without watching the recorded video again, and improves the analysis efficiency of the customer service.
The embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides an automatic modification processing method for a customer service record, which is applied to an intelligent customer service scene, and is used for carrying out voice recognition on received voice data of a user by an intelligent voice customer service, carrying out natural voice processing and providing corresponding customer service by the intelligent voice customer service according to the semantics of the user. And matching corresponding customer service voice data from a preset template database according to the voice data sent by the user and responding to the user. Performing voice recognition on the voice contents stated by the two parties in the response process in real time and converting the voice contents into characters to form a primary customer service record; and automatically correcting the content which does not accord with the record specification in the initial customer service record to obtain a perfect customer service record which accords with the specification of the customer service record. By implementing the invention, the customer service record is more in line with the standard, the workload of manual re-checking is reduced, and the processing efficiency of the customer service record is improved; meanwhile, the system can assist the customer service to perform customer service event analysis and improve the customer service efficiency.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (6)
1. An automatic modification processing method for a customer service record is characterized by comprising the following steps:
step S10, answering the voice signal of the client through the intelligent power supply seat;
step S11, the intelligent voice customer service carries out voice recognition to the received voice data of the customer, carries out natural voice processing, and determines the service type according to the semantics of the customer;
step S12, according to the voice data sent by the client, matching the corresponding customer service voice template from the preset voice template library corresponding to the service type, and adopting the voice in the customer service voice template to respond to the client;
step S13, real-time voice recognition is carried out to the voice content stated by the two parties in the response process and converted into characters, and a preliminary customer service record is formed;
and step S14, automatically correcting the content which does not conform to the record standard in the preliminary customer service record to obtain a perfect customer service record which conforms to the customer service record regulation.
2. The method of claim 1, further comprising:
presetting a voice template library corresponding to each class of service type, wherein the voice template library comprises corresponding customer service voice templates;
presetting a voice style corresponding to each customer service voice template, wherein the voice style comprises the following steps: a full and pure man's voice, a soft, sweet and beautiful woman's voice, a standard genuine english woman's voice;
presetting a hotword corresponding to each service type and a weight corresponding to each hotword, wherein the hotwords comprise: name of person, place name, proper noun of service.
3. The method of claim 2, wherein the step S11 further comprises:
and determining the corresponding service type according to the hot words contained in the voice data of the client.
4. The method according to any one of claims 1 to 3, wherein the step S14 further comprises:
and performing entity word correction, punctuation correction, regulation correction and smooth optimization processing of spoken language on the content in the preliminary customer service record.
5. The method of claim 4, further comprising, after the step S14:
extracting important contents aiming at the text intelligently modified by the customer service, and giving out text contents and positions corresponding to the dispute focus for highlighting;
and analyzing the course of the dispute according to the customer service condition, and correcting the currently applied customer service technical template.
6. The method according to claim 5, wherein in the step S13, the identity of the voice data sender is distinguished by adopting a radio device or adding marks to the voice key frames.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011058890.3A CN112185391A (en) | 2020-09-30 | 2020-09-30 | Automatic modification processing method for customer service record |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011058890.3A CN112185391A (en) | 2020-09-30 | 2020-09-30 | Automatic modification processing method for customer service record |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112185391A true CN112185391A (en) | 2021-01-05 |
Family
ID=73945502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011058890.3A Pending CN112185391A (en) | 2020-09-30 | 2020-09-30 | Automatic modification processing method for customer service record |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112185391A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010139744A (en) * | 2008-12-11 | 2010-06-24 | Ntt Docomo Inc | Voice recognition result correcting device and voice recognition result correction method |
| JP2010256498A (en) * | 2009-04-22 | 2010-11-11 | Nec Corp | Conversion model generating apparatus, voice recognition result conversion system, method and program |
| CN103020047A (en) * | 2012-12-31 | 2013-04-03 | 威盛电子股份有限公司 | Method for revising voice response and natural language dialogue system |
| CN107622054A (en) * | 2017-09-26 | 2018-01-23 | 科大讯飞股份有限公司 | The error correction method and device of text data |
| WO2018107605A1 (en) * | 2016-12-16 | 2018-06-21 | 广州视源电子科技股份有限公司 | System and method for converting audio/video data into written records |
| CN109003608A (en) * | 2018-08-07 | 2018-12-14 | 北京东土科技股份有限公司 | Court's trial control method, system, computer equipment and storage medium |
| CN110738981A (en) * | 2019-10-22 | 2020-01-31 | 集奥聚合(北京)人工智能科技有限公司 | interaction method based on intelligent voice call answering |
| CN110942769A (en) * | 2018-09-20 | 2020-03-31 | 九阳股份有限公司 | Multi-turn dialogue response system based on directed graph |
| CN111475616A (en) * | 2020-03-13 | 2020-07-31 | 平安科技（深圳）有限公司 | Multi-turn dialogue method and device based on dialogue state prediction and computer equipment |
-
2020
- 2020-09-30 CN CN202011058890.3A patent/CN112185391A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010139744A (en) * | 2008-12-11 | 2010-06-24 | Ntt Docomo Inc | Voice recognition result correcting device and voice recognition result correction method |
| JP2010256498A (en) * | 2009-04-22 | 2010-11-11 | Nec Corp | Conversion model generating apparatus, voice recognition result conversion system, method and program |
| CN103020047A (en) * | 2012-12-31 | 2013-04-03 | 威盛电子股份有限公司 | Method for revising voice response and natural language dialogue system |
| CN103279508A (en) * | 2012-12-31 | 2013-09-04 | 威盛电子股份有限公司 | Method for voice response correction and natural language conversational system |
| WO2018107605A1 (en) * | 2016-12-16 | 2018-06-21 | 广州视源电子科技股份有限公司 | System and method for converting audio/video data into written records |
| CN107622054A (en) * | 2017-09-26 | 2018-01-23 | 科大讯飞股份有限公司 | The error correction method and device of text data |
| CN109003608A (en) * | 2018-08-07 | 2018-12-14 | 北京东土科技股份有限公司 | Court's trial control method, system, computer equipment and storage medium |
| CN110942769A (en) * | 2018-09-20 | 2020-03-31 | 九阳股份有限公司 | Multi-turn dialogue response system based on directed graph |
| CN110738981A (en) * | 2019-10-22 | 2020-01-31 | 集奥聚合(北京)人工智能科技有限公司 | interaction method based on intelligent voice call answering |
| CN111475616A (en) * | 2020-03-13 | 2020-07-31 | 平安科技（深圳）有限公司 | Multi-turn dialogue method and device based on dialogue state prediction and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112804400B (en) | Customer service call voice quality inspection method and device, electronic equipment and storage medium | |
| US7711105B2 (en) | Methods and apparatus for processing foreign accent/language communications | |
| US6789093B2 (en) | Method and apparatus for language translation using registered databases | |
| US20110004473A1 (en) | Apparatus and method for enhanced speech recognition | |
| US7415415B2 (en) | Computer generated prompting | |
| US20100104087A1 (en) | System and Method for Automatically Generating Adaptive Interaction Logs from Customer Interaction Text | |
| CN110019688A (en) | The method that robot is trained | |
| CN111062221A (en) | Data processing method, data processing device, electronic equipment and storage medium | |
| KR20220081120A (en) | Artificial intelligence call center system and method for providing system-based service | |
| Kopparapu | Non-linguistic analysis of call center conversations | |
| KR102030551B1 (en) | Instant messenger driving apparatus and operating method thereof | |
| CN110059166A (en) | Natural expression processing method, response method, equipment and the system of natural intelligence | |
| CN110046232A (en) | Natural expression processing method, response method, equipment and the system of natural intelligence | |
| CN110059168A (en) | The method that man-machine interactive system based on natural intelligence is trained | |
| CN114328867A (en) | Intelligent interruption method and device in man-machine conversation | |
| CN113744742A (en) | Role identification method, device and system in conversation scene | |
| CN113810548A (en) | Intelligent call quality inspection method and system based on IOT | |
| CN110008317A (en) | Natural expression processing method, response method, equipment and the system of natural intelligence | |
| CN110059167A (en) | Natural expression processing method, response method, equipment and the system of natural intelligence | |
| US11557288B2 (en) | Hindrance speech portion detection using time stamps | |
| CN115019787B (en) | Interactive homonym disambiguation method, system, electronic equipment and storage medium | |
| CN112185391A (en) | Automatic modification processing method for customer service record | |
| KR102291113B1 (en) | Apparatus and method for producing conference record | |
| Dinkar et al. | From local hesitations to global impressions of a speaker’s feeling of knowing | |
| CN113822029A (en) | Customer service assistance method, device and system |
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 |