CN110321415A - A kind of phone socket joint type phone robot system - Google Patents
A kind of phone socket joint type phone robot system Download PDFInfo
- Publication number
- CN110321415A CN110321415A CN201910386823.5A CN201910386823A CN110321415A CN 110321415 A CN110321415 A CN 110321415A CN 201910386823 A CN201910386823 A CN 201910386823A CN 110321415 A CN110321415 A CN 110321415A
- Authority
- CN
- China
- Prior art keywords
- keyword
- robot
- service
- business
- type
- 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 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 16
- 239000000284 extract Substances 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000005055 memory storage Effects 0.000 claims description 3
- 238000011946 reduction process Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 235000012054 meals Nutrition 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- 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
- 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
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- 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
-
- 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
- G10L2015/088—Word spotting
-
- 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)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of phone socket joint type phone robot systems, it is made of host and multiple extension sets, the host is primary server, it is provided with type of service in host and judges robot, the type of service judges to include that type of service judges sound bank in robot, it include the relevant keyword of type of service in the sound bank, the extension set is branch server, includes the sound bank containing different statement interludes in extension set.Phone robot system of the invention, phone is judged that user is identified as handling the type of different kinds of business by robot by type of service, it is forwarded under the submodule of the type of service, alleviate host server pressure in this way, treatment effeciency in face of mass data is higher, and does not easily cause congestion.
Description
Technical field
The present invention relates to telephone service technology related fields, specifically a kind of phone socket joint type phone robot system.
Background technique
IVR, interactive voice question-answer (human-computer dialogue) are the new trends of computer nowadays science Yu telecommunication science technology
Unified communications(UC-Communications integrated to optimize business
Processes, the communication service of real time integrated is to optimize operation flow) important content.The voice used in IVR technology is known
Not (ASR), is a cross discipline, and related field includes signal processing, pattern-recognition, probability theory and information theory, sounding
Mechanism and hearing mechanism, artificial intelligence etc..
Existing Intelligent dialogue robot is substantially based on server background, no particular hardware, is purchase mobile network
Guan Hou, the identification of webpage version and manipulation realized on windows computer, uniformly dials target phone using mobile gateway.Due to
All clients are used in the unified gateway of server end, more card working signal serious interferences, and network is easy to appear delay.
In addition, speech dialogue system is integrated in primary server by smart phone machine people, all interaction contents generated with user are equal
It is generated by the speech dialogue system, and different types of service, that handles accesses in face of a large number of users, generates magnanimity industry
Be engaged in data when, server inevitably can unbearable pressure, there is delay machine problem.
Summary of the invention
The purpose of the present invention is to provide a kind of phone socket joint type phone robot systems, to solve in above-mentioned background technique
The problem of proposition.
To achieve the above object, the invention provides the following technical scheme:
A kind of phone socket joint type phone robot system, is made of host and multiple extension sets, and the host is primary server, host
It is inside provided with type of service and judges robot, the type of service judges to include that type of service judges sound bank in robot, should
It include the relevant keyword of type of service in sound bank, the extension set is branch server, and business official communication is separately included in extension set
It askes robot, service inquiry robot, business handling robot, business and cancels robot and business complaint robot, the industry
Business consulting robot, service inquiry robot, business handling robot, business cancel robot and business complains robot difference
Cancel sound bank comprising business consultation sound bank, service inquiry sound bank, business handling sound bank, business and business complains voice
Library, above-mentioned business consultation sound bank, service inquiry sound bank, business handling sound bank, business cancel sound bank and business is complained
Voice segments corresponding with type of service are stored in sound bank.
As a further solution of the present invention: the type of service judges that the construction method of sound bank is: will include business
The recording of type word is converted to opposite a plurality of text information, pre-processes to text information, extracts keyword, establishes
Corresponding pattern base obtains sound bank by algorithm training and is saved in storage medium.
As a further solution of the present invention: being connected between the host and each extension set by socket server.
As a further solution of the present invention: a kind of method of phone socket joint type phone robot system includes following step
It is rapid:
The answer statement section of S11, host memory storage are broadcasted, and user speech is acquired, and carry out noise reduction process to user speech；
S12 converts text information for user speech identification, extracts keyword in text, and carry out matching knowledge with sound bank
Not；
S13, after the keyword and type of service of extraction judge Keywords matching in sound bank, according to keyword by delineation of activities
For corresponding type, and it is forwarded in the corresponding extension set of business handling robot and is handled.
As a further solution of the present invention: in step S13, if user not can solve problem in the extension set, transferring
Delineation of activities is re-started to artificial customer service or the upper menu of return.
As a further solution of the present invention: to user speech extract keyword method the following steps are included:
S21, voice keyword query table is preset, the voice keyword query table includes speech recognition keyword and phase
Corresponding application instruction；
S22, user speech input and above-mentioned voice keyword query table are compared, to determine above-mentioned corresponding application
It instructs and executes；
S23, it after extracting keyword, sends it to type of service and judges to be identified in robot, match.
As a further solution of the present invention: user speech input includes that received pronunciation keyword and change voice are crucial
Word；The received pronunciation keyword includes phone string and not specific speaker model；The change voice keyword includes that user is fixed
The phoneme data of justice, to be adjusted to voice parameter.
As a further solution of the present invention: a kind of method of phone socket joint type phone robot system further includes to user
Multiple keywords for belonging to different service types that voice extracts carry out order of priority by weight, comprising the following steps:
S31 carries out participle operation to keyword phrase text, and removes the stop words in text, retains to have in text and break
Crucial phrase in text is synthesized keyword set by the punctuation mark of sentence function；
S32 counts the word frequency of keyword in keyword set, by the word frequency of the keyword of statistics generate the word frequency of keyword to
Amount；
S33, the sequence of the lexical item in word frequency vector according to keyword count the cooccurrence relation in text between keyword, obtain
The co-occurrence vector of above-mentioned keyword is formed a pass by the vector of each keyword and other key words co-occurrences in keyword set
The co-occurrence matrix of keyword；
S34, is arranged the initial vector of keyword weight obtained by the co-occurrence matrix factor of keyword, keyword weight it is initial
Dimension in vector is identical as the columns in the co-occurrence matrix of keyword；
The initial vector of S35, co-occurrence matrix and keyword weight to keyword are handled, and obtain the co-occurrence square by keyword
The keyword weight vector that battle array factor obtains；
All elements in keyword weight vector are carried out phase with all corresponding elements in the word frequency vector of keyword by S36
Multiply, obtains the keyword weight vector generated by the word frequency vector of keyword weight vector F and keyword；
S37, using the IDF in formula TF IDF=TF IDF, to the word frequency of co-occurrence matrix factor and keyword by keyword because
Each element that element generates on keyword weight vector is calculated, and final keyword weight vector is obtained.
Compared with prior art, the beneficial effects of the present invention are: phone robot system of the invention, passes through industry for phone
Service type judges that user is identified as handling the type of different kinds of business by robot, is forwarded to the submodule of the type of service
Under block, alleviate host server pressure in this way, the treatment effeciency in face of mass data is higher, and does not easily cause congestion.
Detailed description of the invention
Fig. 1 is the structural diagram of the present invention.
Fig. 2 is flow chart of the method for the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, in the embodiment of the present invention, by taking telecommunications customer service as an example, a kind of phone socket joint type phone robot
System is made of host and multiple extension sets, and the host is primary server, is connected between host and each extension set by socket server
It connects, type of service is provided in host and judges robot, the type of service judges to include that type of service judges language in robot
Sound library includes the relevant keyword of type of service in the sound bank, and e.g., user seeks advice from telephone expenses, flow etc., belongs to consulting industry
Business, user handle flow package etc., belong to transacting business, and type of service judges that the construction method of sound bank is: will include business
The recording of type word is converted to opposite a plurality of text information, pre-processes to text information, extracts keyword, such as will
The sentences such as " looking into telephone expenses ", " Cha Liuliang ", " set meal is handled ", " consulting " extract the keywords such as " telephone expenses ", " looking into " " handling ", establish
Corresponding pattern base obtains sound bank by algorithm training and is saved in storage medium such as acoustic model and language model.
The extension set is branch server, and extension set is at least arranged five, separately includes business consultation robot, service inquiry
Robot, business handling robot, business cancel robot and business complains robot, the business consultation robot, business
Inquiry robot, business handling robot, business cancel robot and business complains robot to separately include business consultation voice
Library, service inquiry sound bank, business handling sound bank, business cancels sound bank and business complains sound bank, above-mentioned business consultation
Sound bank, service inquiry sound bank, business handling sound bank, business cancel sound bank and business is complained and is stored with not in sound bank
Same voice segments, if being stored with the statement interlude explained about business in business consultation sound bank, for voice broadcast about difference
The details of business, the interior storage of service inquiry sound bank are handled the statement interlude of information about the use of user's rate, set meal, can be broadcast
Situations such as reporting user telephone fee, flow.
Such as Fig. 2, after user puts through service calls, phone is directly connected to host, the answer statement section of host memory storage into
Row casting, guidance user speak, user speak acquisition after carry out noise reduction process, then convert text information for speech recognition,
Keyword in text is extracted, and carries out match cognization with sound bank, when the keyword and type of service of extraction judge sound bank
It by delineation of activities is corresponding type according to keyword after middle Keywords matching, as described in user " handle flow refuel packet ", then
Keywords matchings such as " handling " " flows " are judged in sound bank according to type of service, which is divided into business handling class
Type, and be forwarded in the corresponding extension set of business handling robot and handled, it, can if user not can solve problem in the extension set
Selection, which is forwarded to artificial customer service or returns to a upper menu, re-starts delineation of activities.Judge robot by user by type of service
It is identified as handling the type of different kinds of business, be forwarded under the submodule of the type of service, in this way alleviation host services
Device pressure, the treatment effeciency in face of mass data is higher, and does not easily cause congestion.
The method that keyword is extracted to user speech are as follows:
1) voice keyword query table, is preset, the voice keyword query table includes speech recognition keyword and phase
Corresponding application instruction；
2), user speech input and above-mentioned voice keyword query table are compared, to determine above-mentioned corresponding application
It instructs and executes；
Wherein, voice input includes received pronunciation keyword and change voice keyword；The received pronunciation keyword includes
Phone string and not specific speaker model；The change voice keyword includes the phoneme data that user defines, to pronunciation
Parameter is adjusted；
3) it after, extracting keyword, sends it to type of service and judges to be identified in robot, match.
When extracting multiple keywords for belonging to different service types for user's sentence priority can be carried out by weight
Sequence, method particularly includes:
1) participle operation, is carried out to keyword phrase text, and removes the stop words in text, retaining has punctuate in text
Crucial phrase in text is synthesized keyword set, is denoted as A by the punctuation mark of function；
2) word frequency for, counting keyword in keyword set A, by the word frequency of the keyword of statistics generate the word frequency of keyword to
Amount, is denoted as B；
3), the sequence of the lexical item in word frequency vector B according to keyword counts the cooccurrence relation in text between keyword, obtains
The co-occurrence vector of above-mentioned keyword is formed one by the vector of each keyword and other key words co-occurrences in keyword set A
The co-occurrence matrix of keyword, is denoted as C；
4) initial vector for the keyword weight that, setting is obtained by the co-occurrence matrix factor of keyword, is denoted as D, keyword weight
Initial vector D in dimension it is identical as the columns in the co-occurrence matrix C of keyword；
5), the initial vector D of the co-occurrence matrix C of keyword and keyword weight are handled, obtain the co-occurrence by keyword
The keyword weight vector that matrix factor obtains, is denoted as F；
6) all elements in keyword weight vector F, are subjected to phase with all corresponding elements in the word frequency vector B of keyword
Multiply, obtains the keyword weight vector generated by the word frequency vector B of keyword weight vector F and keyword, be denoted as G；
7), using the IDF in TF-IDF calculation formula TF IDF=TF IDF, to the co-occurrence matrix factor and key by keyword
Each element that the word frequency factor of word generates on keyword weight vector G is calculated, then obtain final keyword weight to
Amount；
After each keyword extracted assigns weighted value, it is divided in the highest type of weight according to weighted value size,
And it is forwarded to corresponding extension set, it is handled if user fails in the extension set, may be selected to be forwarded to artificial customer service or return simultaneously
It is forwarded in the type of service in next weight sequencing.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (8)
1. a kind of phone socket joint type phone robot system, it is characterised in that: be made of host and multiple extension sets, the host is
Primary server is provided with type of service in host and judges robot, and the type of service judges to include type of service in robot
Judge sound bank, include the relevant keyword of type of service in the sound bank, the extension set is branch server, is divided in extension set
It Bao Han not business consultation robot, service inquiry robot, business handling robot, business cancellation robot and business complaint machine
Device people, the business consultation robot, service inquiry robot, business handling robot, business cancel robot and business is thrown
Tell robot separately include business consultation sound bank, service inquiry sound bank, business handling sound bank, business cancel sound bank and
Business complains sound bank, and above-mentioned business consultation sound bank, service inquiry sound bank, business handling sound bank, business cancel voice
Library and business, which are complained in sound bank, is stored with voice segments corresponding with type of service.
2. a kind of phone socket joint type phone robot system according to claim 1, it is characterised in that: the type of service
Judging the construction method of sound bank is: the recording comprising type of service word being converted to opposite a plurality of text information, to text
This information is pre-processed, and keyword is extracted, and establishes corresponding pattern base, is obtained sound bank by algorithm training and is saved in
In storage medium.
3. a kind of phone socket joint type phone robot system according to claim 1, it is characterised in that: the host and each
It is connected between extension set by socket server.
4. a kind of method of phone socket joint type phone robot system according to claim 1 to 3, it is characterised in that:
The following steps are included:
The answer statement section of S11, host memory storage are broadcasted, and user speech is acquired, and carry out noise reduction process to user speech；
S12 converts text information for user speech identification, extracts keyword in text, and carry out matching knowledge with sound bank
Not；
S13, after the keyword and type of service of extraction judge Keywords matching in sound bank, according to keyword by delineation of activities
For corresponding type, and it is forwarded in the corresponding extension set of business handling robot and is handled.
5. a kind of method of phone socket joint type phone robot system according to claim 4, it is characterised in that: step
In S13, if user not can solve problem in the extension set, it is forwarded to artificial customer service or the upper menu of return re-starts business
It divides.
6. a kind of method of phone socket joint type phone robot system according to claim 4, it is characterised in that: to user
Voice extract keyword method the following steps are included:
S21, voice keyword query table is preset, the voice keyword query table includes speech recognition keyword and phase
Corresponding application instruction；
S22, user speech input and above-mentioned voice keyword query table are compared, to determine above-mentioned corresponding application
It instructs and executes；
S23, it after extracting keyword, sends it to type of service and judges to be identified in robot, match.
7. a kind of method of phone socket joint type phone robot system according to claim 4, it is characterised in that: Yong Huyu
Sound input includes received pronunciation keyword and change voice keyword；The received pronunciation keyword includes phone string and not special
Determine speaker model；The change voice keyword includes the phoneme data that user defines, to be adjusted to voice parameter.
8. a kind of method of phone socket joint type phone robot system according to claim 4, it is characterised in that: further include
Order of priority is carried out by weight to multiple keywords for belonging to different service types that user speech extracts, is divided into following step
It is rapid:
S31 carries out participle operation to keyword phrase text, and removes the stop words in text, retains to have in text and break
Crucial phrase in text is synthesized keyword set by the punctuation mark of sentence function；
S32 counts the word frequency of keyword in keyword set, by the word frequency of the keyword of statistics generate the word frequency of keyword to
Amount；
S33, the sequence of the lexical item in word frequency vector according to keyword count the cooccurrence relation in text between keyword, obtain
The co-occurrence vector of above-mentioned keyword is formed a pass by the vector of each keyword and other key words co-occurrences in keyword set
The co-occurrence matrix of keyword；
S34, is arranged the initial vector of keyword weight obtained by the co-occurrence matrix factor of keyword, keyword weight it is initial
Dimension in vector is identical as the columns in the co-occurrence matrix of keyword；
The initial vector of S35, co-occurrence matrix and keyword weight to keyword are handled, and obtain the co-occurrence square by keyword
The keyword weight vector that battle array factor obtains；
All elements in keyword weight vector are carried out phase with all corresponding elements in the word frequency vector of keyword by S36
Multiply, obtains the keyword weight vector generated by the word frequency vector of keyword weight vector F and keyword；
S37, using the IDF in formula TF IDF=TF IDF, to the word frequency of co-occurrence matrix factor and keyword by keyword because
Each element that element generates on keyword weight vector is calculated, and final keyword weight vector is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910386823.5A CN110321415A (en) | 2019-05-10 | 2019-05-10 | A kind of phone socket joint type phone robot system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910386823.5A CN110321415A (en) | 2019-05-10 | 2019-05-10 | A kind of phone socket joint type phone robot system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110321415A true CN110321415A (en) | 2019-10-11 |
Family
ID=68119289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910386823.5A Pending CN110321415A (en) | 2019-05-10 | 2019-05-10 | A kind of phone socket joint type phone robot system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110321415A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111163235A (en) * | 2020-02-06 | 2020-05-15 | 深圳震有科技股份有限公司 | Method and device for distinguishing and processing external line telephone incoming call through internal telephone |
| CN111988477A (en) * | 2020-09-02 | 2020-11-24 | 中国银行股份有限公司 | Incoming call processing method and device, server and storage medium |
| CN112185339A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice synthesis processing method and system for power supply intelligent client |
| CN112995420A (en) * | 2019-12-02 | 2021-06-18 | 浙江思考者科技有限公司 | Artificial intelligence changes artificial intelligence and changes manual scheme again |
| CN112995417A (en) * | 2019-12-02 | 2021-06-18 | 浙江思考者科技有限公司 | Method for converting artificial intelligence into artificial intelligence |
| CN113409789A (en) * | 2021-08-03 | 2021-09-17 | 深圳市一号互联科技有限公司 | Intelligent voice call method, device and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744951A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Method for ordering significance of keywords in text |
| US20150310858A1 (en) * | 2014-04-29 | 2015-10-29 | Microsoft Corporation | Shared hidden layer combination for speech recognition systems |
| CN107135247A (en) * | 2017-02-16 | 2017-09-05 | 江苏南大电子信息技术股份有限公司 | A kind of service system and method for the intelligent coordinated work of person to person's work |
| CN108418744A (en) * | 2018-02-06 | 2018-08-17 | 国网浙江省电力有限公司信息通信分公司 | A kind of electronics seat system for promoting electrical power services quality |
-
2019
- 2019-05-10 CN CN201910386823.5A patent/CN110321415A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744951A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Method for ordering significance of keywords in text |
| US20150310858A1 (en) * | 2014-04-29 | 2015-10-29 | Microsoft Corporation | Shared hidden layer combination for speech recognition systems |
| CN107135247A (en) * | 2017-02-16 | 2017-09-05 | 江苏南大电子信息技术股份有限公司 | A kind of service system and method for the intelligent coordinated work of person to person's work |
| CN108418744A (en) * | 2018-02-06 | 2018-08-17 | 国网浙江省电力有限公司信息通信分公司 | A kind of electronics seat system for promoting electrical power services quality |
Non-Patent Citations (1)
| Title |
|---|
| 韩冰等: "《数字音视频处理》", 31 October 2018, 西安电子科技大学出版社 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112995420A (en) * | 2019-12-02 | 2021-06-18 | 浙江思考者科技有限公司 | Artificial intelligence changes artificial intelligence and changes manual scheme again |
| CN112995417A (en) * | 2019-12-02 | 2021-06-18 | 浙江思考者科技有限公司 | Method for converting artificial intelligence into artificial intelligence |
| CN111163235A (en) * | 2020-02-06 | 2020-05-15 | 深圳震有科技股份有限公司 | Method and device for distinguishing and processing external line telephone incoming call through internal telephone |
| CN111988477A (en) * | 2020-09-02 | 2020-11-24 | 中国银行股份有限公司 | Incoming call processing method and device, server and storage medium |
| CN112185339A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice synthesis processing method and system for power supply intelligent client |
| CN113409789A (en) * | 2021-08-03 | 2021-09-17 | 深圳市一号互联科技有限公司 | Intelligent voice call method, device and system |
| CN113409789B (en) * | 2021-08-03 | 2021-10-29 | 深圳市一号互联科技有限公司 | Intelligent voice call method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110321415A (en) | A kind of phone socket joint type phone robot system | |
| JP6182272B2 (en) | Natural expression processing method, processing and response method, apparatus, and system | |
| JP7346609B2 (en) | Systems and methods for performing semantic exploration using natural language understanding (NLU) frameworks | |
| KR101872863B1 (en) | Business support method using a chatting bot | |
| KR20190077088A (en) | How to build and register a gates | |
| US10847136B2 (en) | System and method for mapping a customer journey to a category | |
| CN109074514A (en) | Pass through the deep learning of the robot of example and experience | |
| CN110310663A (en) | Words art detection method, device, equipment and computer readable storage medium in violation of rules and regulations | |
| CN108831439A (en) | Audio recognition method, device, equipment and system | |
| CN106453043A (en) | Multi-language conversion-based instant communication system | |
| CN109446305A (en) | The construction method and system of intelligent tour customer service system | |
| CN107784051A (en) | Online customer service answering system and method | |
| CN111694940A (en) | User report generation method and terminal equipment | |
| CN106875939A (en) | To the Chinese dialects voice recognition processing method and intelligent robot of wide fluctuations | |
| US11886818B2 (en) | Method and apparatus for detecting anomalies in mission critical environments | |
| Lee et al. | On natural language call routing | |
| US20200082822A1 (en) | System and method for mapping a customer journey to a category | |
| CN110275948A (en) | Free jump method, device and the medium of Self-Service | |
| CN110246494A (en) | Service request method, device and computer equipment based on speech recognition | |
| CN111128130A (en) | Voice data processing method and device and electronic device | |
| KR102381387B1 (en) | Method for generating chatbot training data | |
| CN108763288A (en) | A kind of barrage hold-up interception method and its relevant device | |
| CN113434663A (en) | Conference summary generation method based on edge calculation and related equipment | |
| CN103581395A (en) | Display method and electronic equipment | |
| CN110941955A (en) | Cross-language event classification method and device |
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 |