CN107181879B - Identification incoming call is intended to - Google Patents
Identification incoming call is intended to Download PDFInfo
- Publication number
- CN107181879B CN107181879B CN201710297217.7A CN201710297217A CN107181879B CN 107181879 B CN107181879 B CN 107181879B CN 201710297217 A CN201710297217 A CN 201710297217A CN 107181879 B CN107181879 B CN 107181879B
- Authority
- CN
- China
- Prior art keywords
- industry
- intention labels
- speech recognition
- intention
- incoming number
- 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
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
- H04M3/42025—Calling or Called party identification service
- H04M3/42034—Calling party identification service
- H04M3/42042—Notifying the called party of information on the calling party
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
- H04M2201/40—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition
-
- 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
- H04M3/42025—Calling or Called party identification service
- H04M3/42034—Calling party identification service
- H04M3/42059—Making use of the calling party identifier
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The object of the present invention is to provide a kind of method, apparatus and computer equipment, computer readable storage medium and computer program product for being intended to be identified to incoming call.It has been identified as the incoming number of harassing call for one, speech recognition is carried out respectively to its multiple dialog context；By the content matching industry keywords library of each speech recognition, to obtain the one or more industries to match, wherein the industry keywords library includes multiple industries and its corresponding one or more industry keywords；According to the content of each speech recognition, one or more intention labels corresponding to wherein each industry is respectively are determined；The weight of every profession and trade corresponding to the comprehensive multiple dialog context and the wherein weight of each intention labels of each industry, with industry and its intention labels corresponding to the determination incoming number.Compared with prior art, the present invention provides a kind of more accurate and refinement incoming call intention assessment schemes, are intended to prompt so as to provide more fine-grained incoming call for user.
Description
Technical field
The present invention relates to a kind of technologies for being intended to be identified to incoming call.
Background technique
At present by making a phone call the pusher for carrying out commodity or service when making a phone call the potential buyer of searching
It substantially dials at random, and do not know about the person of being pushed whether to have demand to the commodity or service oneself promoted.It is pushed away simultaneously
Pin person do not know the approximate contents of this kind of sales calls before answering the call yet, even if caller identification now can be into
The related prompt of row, such as can prompt user's current call is harassing call, or can carry out simple identification to strange number,
" distribution ", " intermediary ", " express delivery " etc., still, user usually still need to after receiving calls and carrying out one two communications
There can be certain understanding to the purpose of pusher to know whether oneself has demand.
Obviously, existing call prompting way still cannot really meet the use demand of user.Even if most of user sees
Prompt has been arrived, can not understand and judge whether it has corresponding demand, ability after often still needing to incoming call answering and simply linking up
Decide whether to continue this time to converse.In addition, some users directly hang up the incoming call after seeing incoming call prompting, it is also possible to miss it
The information of real demand.
Summary of the invention
The object of the present invention is to provide a kind of method, apparatus and computer equipment, meter for being intended to be identified to incoming call
Calculation machine readable storage medium storing program for executing and computer program product.
According to an aspect of the invention, there is provided a kind of be intended to incoming call to carry out knowledge method for distinguishing, wherein this method packet
Include following steps:
It has been identified as the incoming number of harassing call for one, voice knowledge is carried out respectively to its multiple dialog context
Not；
By the content matching industry keywords library of each speech recognition, to obtain the one or more industries to match,
In, the industry keywords library includes multiple industries and its corresponding one or more industry keywords；
According to the content of each speech recognition, one or more meanings corresponding to wherein each industry is respectively are determined
Icon label；
The weight of every profession and trade corresponding to the comprehensive multiple dialog context and wherein each intention labels of each industry
Weight, with industry and its intention labels corresponding to the determination incoming number.
According to an aspect of the present invention, a kind of device for being intended to be identified to incoming call is additionally provided, wherein the device
Include:
For being identified as the incoming number of harassing call for one, voice is carried out respectively to its multiple dialog context
The device of identification；
For by the content matching industry keywords library of each speech recognition, to obtain the one or more industries to match
Device, wherein the industry keywords library includes multiple industries and its corresponding one or more industry keywords；
For the content according to each speech recognition, the one or more corresponding to wherein each industry is respectively is determined
The device of intention labels；
For integrating the weight and wherein each intention of each industry of every profession and trade corresponding to the multiple dialog context
The weight of label, with the device of industry corresponding to the determination incoming number and its intention labels.
According to an aspect of the present invention, it additionally provides a kind of computer equipment, including memory, processor and is stored in
On memory and the computer program that can run on a processor, wherein the processor executes real when the computer program
Now one kind according to an aspect of the present invention is intended to incoming call to carry out knowledge method for distinguishing.
According to an aspect of the present invention, a kind of computer readable storage medium is additionally provided, computer is stored thereon with
Program, wherein realize that one kind according to an aspect of the present invention anticipates to incoming call when the computer program is executed by processor
Figure carries out knowledge method for distinguishing.
According to an aspect of the present invention, a kind of computer program product is additionally provided, when the computer program product
Realize that one kind according to an aspect of the present invention is intended to incoming call to carry out knowledge method for distinguishing when being executed by computer equipment.
Compared with prior art, the present invention provides a kind of more accurate and refinement incoming call intention assessment schemes, thus
More fine-grained incoming call can be provided for user and be intended to prompt.Specifically, the present invention " is pushed away by speech recognition from having got beat up
Extract relevant intent features in the call voice of pin " " intermediary " label, identification pusher be specifically promote what commodity or
Person's service, and then the label for being supplied in caller identification user can be improved to " selling insurance " according to recognition result and " promote
The more specific intention labels such as house property " " promoting parent-offspring's product ", allow user's selection is interested to answer.
It is also possible to it is interested in what commodity to deduce user according to the behavior of answering of user, so as to
It is pushed with carrying out more accurately information (such as advertisement), to promote user experience and improve conversion ratio.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, of the invention other
Feature, objects and advantages will become more apparent upon:
Fig. 1 shows the block diagram for being suitable for the exemplary computer system/server 12 for being used to realize embodiment of the present invention；
Fig. 2 shows a kind of method flow diagrams for being intended to be identified to incoming call according to an embodiment of the invention；
Fig. 3 shows effect diagram of the exemplary intention labels in incoming call prompting according to the present invention；
Fig. 4 shows a kind of schematic diagram of device for being intended to be identified to incoming call according to an embodiment of the invention.
The same or similar appended drawing reference represents the same or similar component in attached drawing.
Specific embodiment
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail
The processing or method described as flow chart.Although operations are described as the processing of sequence by flow chart, therein to be permitted
Multioperation can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of operations can be rearranged.When it
The processing can be terminated when operation completion, it is also possible to have the additional step being not included in attached drawing.The processing
It can correspond to method, function, regulation, subroutine, subprogram etc..
Alleged " computer equipment " within a context, also referred to as " computer ", referring to can be by running preset program or referring to
Enable to execute numerical value and calculate and/or the intelligent electronic device of the predetermined process process such as logic calculation, may include processor with
Memory executes the program instruction that prestores in memory by processor to execute predetermined process process, or by ASIC,
The hardware such as FPGA, DSP execute predetermined process process, or are realized by said two devices combination.Computer equipment includes but unlimited
In server, personal computer (PC), laptop, tablet computer, smart phone etc..
The computer equipment is for example including user equipment and the network equipment.Wherein, the user equipment includes but unlimited
In personal computer (PC), laptop, mobile terminal etc., the mobile terminal includes but is not limited to smart phone, PDA
Deng；The network equipment includes but is not limited to single network server, the server group of multiple network servers composition or is based on
The cloud consisting of a large number of computers or network servers of cloud computing (Cloud Computing), wherein cloud computing is distributed
One kind of calculating, a super virtual computer consisting of a loosely coupled set of computers.Wherein, the computer is set
It is standby can isolated operation realize the present invention, also can access network and pass through the interactive operation with other computer equipments in network
To realize the present invention.Wherein, network locating for the computer equipment includes but is not limited to internet, wide area network, Metropolitan Area Network (MAN), office
Domain net, VPN network etc..
It should be noted that the user equipment, the network equipment and network etc. are only for example, other are existing or from now on may be used
The computer equipment or network that can occur such as are applicable to the present invention, should also be included within the scope of protection of the present invention, and to draw
It is incorporated herein with mode.
The method (some of them illustrated by process) discussed herein below can by hardware, software, firmware, in
Between part, microcode, hardware description language or any combination thereof implement.When with software, firmware, middleware or microcode come real
Shi Shi, program code or code segment to implement necessary task can be stored in machine or computer-readable medium (such as
Storage medium) in.Necessary task can be implemented in (one or more) processor.
Specific structure and function details disclosed herein are only representative, and are for describing the present invention show
The purpose of example property embodiment.But the present invention can be implemented by many alternative forms, and be not interpreted as
It is limited only by the embodiments set forth herein.
Although it should be understood that may have been used term " first ", " second " etc. herein to describe each unit,
But these units should not be limited by these terms.The use of these items is only for by a unit and another unit
It distinguishes.For example, without departing substantially from the range of exemplary embodiment, it is single that first unit can be referred to as second
Member, and similarly second unit can be referred to as first unit.Term "and/or" used herein above include one of them or
Any and all combinations of more listed associated items.
Term used herein above is not intended to limit exemplary embodiment just for the sake of description specific embodiment.Unless
Context clearly refers else, otherwise singular used herein above "one", " one " also attempt to include plural number.Also answer
When understanding, term " includes " and/or "comprising" used herein above provide stated feature, integer, step, operation,
The presence of unit and/or component, and do not preclude the presence or addition of other one or more features, integer, step, operation, unit,
Component and/or combination thereof.
It should further be mentioned that the function action being previously mentioned can be attached according to being different from some replace implementations
The sequence indicated in figure occurs.For example, related function action is depended on, the two width figures shown in succession actually may be used
Substantially simultaneously to execute or can execute in a reverse order sometimes.
Present invention is further described in detail with reference to the accompanying drawing.
Fig. 1 shows the block diagram for being suitable for the exemplary computer system/server 12 for being used to realize embodiment of the present invention.
The computer system/server 12 that Fig. 1 is shown is only an example, should not function and use scope to the embodiment of the present invention
Bring any restrictions.
As shown in Figure 1, computer system/server 12 is showed in the form of universal computing device.Computer system/service
The component of device 12 can include but is not limited to: one or more processor or processing unit 16, system storage 28, connection
The bus 18 of different system components (including system storage 28 and processing unit 16).
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer system/server 12 typically comprises a variety of computer system readable media.These media, which can be, appoints
What usable medium that can be accessed by computer system/server 12, including volatile and non-volatile media, it is moveable and
Immovable medium.
Memory 28 may include the computer system readable media of form of volatile memory, such as random access memory
Device (RAM) 30 and/or cache memory 32.Computer system/server 12 may further include it is other it is removable/no
Movably, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing
Immovable, non-volatile magnetic media (Fig. 1 is not shown, commonly referred to as " hard disk drive ").It, can although being not shown in Fig. 1
To provide the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk "), and it is non-volatile to moving
Property CD (such as CD-ROM, DVD-ROM or other optical mediums) read and write CD drive.In these cases, each drive
Dynamic device can be connected by one or more data media interfaces with bus 18.Memory 28 may include at least one program
Product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform the present invention
The function of each embodiment.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 includes --- but being not limited to --- operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.Program mould
Block 42 usually executes function and/or method in embodiment described in the invention.
Computer system/server 12 can also be (such as keyboard, sensing equipment, aobvious with one or more external equipments 14
Show device 24 etc.) communication, it is logical that the equipment interacted with the computer system/server 12 can be also enabled a user to one or more
Letter, and/or with the computer system/server 12 any is set with what one or more of the other calculating equipment was communicated
Standby (such as network interface card, modem etc.) communicates.This communication can be carried out by input/output (I/O) interface 22.And
And computer system/server 12 can also pass through network adapter 20 and one or more network (such as local area network
(LAN), wide area network (WAN) and/or public network, such as internet) communication.As shown, network adapter 20 passes through bus
18 communicate with other modules of computer system/server 12.It should be understood that computer can be combined although being not shown in Fig. 1
Systems/servers 12 use other hardware and/or software module, including but not limited to: microcode, device driver, at redundancy
Manage unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
The program that processing unit 16 is stored in memory 28 by operation, thereby executing various function application and data
Processing.
For example, being stored with the computer program for executing various functions and processing of the invention in memory 28, handle
When unit 16 executes corresponding computer program, the present invention realizes the identification being intended to incoming call in network-side.
The present invention described in detail below realizes the concrete function/step for the identification being intended to incoming call in server.
Fig. 2 shows according to one embodiment of present invention, wherein specifically illustrating a kind of side for being intended to be identified to incoming call
Method flow chart.
The recognition methods is executed by network-side.However, although those skilled in the art will be understood that incoming call intention
Identification is performed by network-side, but since entire communication process is carried out in user terminal, therefore identification side of the invention
Method also needs the auxiliary of user terminal.Here, user terminal is typically such as mobile phone, network-side is typically such as server.As nothing is especially said
Bright, network-side is equal with server and uses in this specification.
As shown in Fig. 2, in step sl, for an incoming number through tentatively identifying, server repeatedly converses to it
Content carries out speech recognition respectively；In step s 2, server is by the content matching industry keywords library of each speech recognition, with
Obtain the one or more industries to match, wherein the industry keywords library includes multiple industries and its corresponding one
A or multiple industry keywords；In step s3, server determines wherein each row according to the content of each speech recognition
The corresponding one or more intention labels of industry difference；In step s 4, corresponding to the comprehensive multiple dialog context of server
Every profession and trade weight and the wherein weight of each intention labels of each industry, with row corresponding to the determination incoming number
Industry and its intention labels.
Specifically, in step sl, for an incoming number through tentatively identifying, server is to its multiple dialog context
Speech recognition is carried out respectively.
Here, the incoming number through tentatively identifying including but not limited to has been identified as the incoming number, of harassing call
Identification has the incoming number etc. of preliminary identification.For example only prompt user is the incoming number of harassing call for the former, and the latter is for example
It is identified as the incoming number of such as " intermediary ", " distribution ".The invention is intended to the harassing call on these ordinary meanings into one
Step provides refinement intention labels, so that the user for answering the incoming number can decide whether to answer this according to its specific requirements
Incoming call is rather than based solely upon the marks such as " intermediary ", " distribution " and blindly refuses the incoming call, or wastes time to find and be not inconsistent after answering
Close the demand of itself.
In addition, it should be noted that, present invention meaning " harassing call " does not include that " fraudulent call " etc. has illegal meaning
The phone of figure, these phones with illegal intention should be filtered by such as operator, not within the scope of discussion of the invention.
After user answers the incoming number through tentatively identifying, user equipment will record this time conversing for user, and will
Dialog context is uploaded to server.
Here, user equipment can only record the dialog context of folk prescription, such as only remember in order to preferably protect privacy of user
Record the dialog context of caller.It is included in the dialog context of usual caller for the incoming call of such as " intermediary ", " distribution " etc.
Enough information determines that its incoming call is intended to.
Present invention contemplates that other secret protection schemes.It is not answered currently for example, user equipment can be recorded only
The address list of user or the dialog context of the telephone number in message registration.That is, the incoming number should be strange number.
For an incoming number through tentatively identifying, server will carry out speech recognition to its multiple dialog context.For
More acurrate and more one incoming number of fining ground identification intention, server need to analyze its multiple dialog context
To determine most probable intention.Dialog context means the call that middle generation is hung up from user's incoming call answering to this call
Content.
Wherein, the speech recognition of dialog context is intended to convert the dialog context of audio to the dialog context of text.Language
Sound identification has been mature technology, and the present invention does not specifically describe herein.Any existing or future speech recognition technology such as may be used
Applied to the present invention, this should all be contained in.
Content through speech recognition can be the dialog context of written form, be also possible in the call to the written form
That holds is further processed, and such as extracts keyword set from it.It is extracted from a dialog context here, a keyword set can be
All keywords.
In step s 2, server matches in the content matching industry keywords library of each speech recognition with acquisition
One or more industries.
Here, network-side further includes an industry keywords library, including corresponding to multiple industries and each industry
One or more industry keywords.
For example, server can be by each keyword set of an incoming number through tentatively identifying respectively in the sector key
Matching inquiry is carried out in dictionary, to obtain the one or more industries to match.
Alternatively, server can also directly match the dialog context of written form with every profession and trade keyword,
To obtain the one or more industries to match.
Industry keywords to industry the mapping property of can be exemplified it is as follows:
" buy house, rent a house, house, real estate, room rate, house type ... " -> " real estate industry "
" automobile, buying car, test ride, the shop 4S " -> " automobile industry "
" investment, financing, gold, silver, stock " -> " Investment & Financing industry "
In step s3, server determines corresponding to wherein each industry is respectively according to the content of each speech recognition
One or more intention labels.
After determining industry corresponding to incoming number by each dialog context, the present invention is further determined accordingly
Specifically intended label under industry enables a user to the intention for accurately knowing the incoming number.
According to a preferred embodiment of the present invention, network-side can establish an intention labels library, including each row
Intention labels corresponding to industry and each industry.Server can be by each speech recognition content, such as keyword set or text
The dialog context of font formula, according to the industry identified in step s 2, matching inquiry wherein intention mark corresponding to every profession and trade
Label, to obtain the intention labels under identified every profession and trade.
Specifically such as, for a dialog context " it is interesting to investment in gold to may I ask you ", its identified corresponding industry
For " Investment & Financing ", server is further matched in each intention labels to the dialog context corresponding to " Investment & Financing "
Inquiry, to obtain the intention labels to match, such as " investment in gold ".Wherein, intention labels corresponding to " Investment & Financing " industry
It can " investment in gold ", " silver investment ", " equity investment ", " foreign exchange investment " etc..
According to a preferred embodiment of the present invention, network-side can be intended to rule for each specific industry building is corresponding
Then.
For example, each industry can set one group of kernel keyword, when server is special to corresponding in a dialog context
Determine industry and be matched to one or more kernel keywords, the corresponding intention labels of the matched kernel keyword of institute may act as this
The intention labels of dialog context.
Specifically, for example, for " Investment & Financing " industry, it is as follows to be intended to the rule property of can be exemplified:
" gold " -> " investment in gold "
" silver " -> " silver investment "
" stock " -> " equity investment "
" foreign exchange " -> " foreign exchange investment "
Accordingly, when server from be matched under " Investment & Financing " industry in dialog context kernel keyword such as " gold ",
Then it can determine that corresponding intention labels are " investment in gold " according to the above rule that is intended to.
Alternatively, it is intended that label was also possible to be generated in real time by kernel keyword.For example, still press upper example, when from logical
Kernel keyword is matched in words content under " Investment & Financing " industry such as " gold ", server is according to " industry "+" core key
Word " generates corresponding intention labels, such as " investment in gold ".
For another example, server is according to the specific feature of each industry, such as each industry is using there is particular keywords, from warp
Information corresponding with particular keywords are somebody's turn to do (s) is extracted in the dialog context of speech recognition, it is corresponding one or more to obtain
Intention labels.
Specifically, for example, after detecting particular keywords from dialog context, server from thereon hereinafter extract with
The corresponding information of the particular keywords is as intention labels.This is considered one kind and extracts meaning by semantic analysis
The mode of icon label.
For example, industry corresponding to current talking content has been determined as " real estate ", when detecting particular keywords
As after " house type ", " developer ", server search context is obtained such as " 2 bedrooms ", " Wanke ", and by " 2 bedrooms " and " ten thousand
Section " is used as intention labels.Preferably, industry " real estate " can also be used as intention labels together.
Here, server can extract its particular content information according to expression way corresponding to each particular keywords.
For example, when detecting particular keywords " area ", it is flat that server can hereinafter extract XX from it under " real estate " industry
The corresponding information of meter Zuo Wei, to obtain intention labels " real estate " and " XX square meter ".
It is above-mentioned respectively kernel keyword and particular keywords come can be in conjunction with obtaining by way of obtaining intention labels
The intention labels of dialog context.For example, server obtains intention labels " investment in gold " according to kernel keyword, according to specific pass
Keyword " price of gold " obtains intention labels " 276.39 ".
In step s 4, the weight of every profession and trade corresponding to the comprehensive multiple dialog context of server and wherein each industry
Each intention labels weight, with industry and its intention labels corresponding to the determination incoming number.
Here, one or more industries can be corresponding with for a dialog context, wherein each industry may be used again
To be corresponding with one or more intention labels.Server may further determine that the weight of wherein every profession and trade and intention labels.
Preferably, weight is determined based on word frequency.
For example, for dialog context T1, correspond to industry H1 and H2, wherein the weight of H1 can according to T1 at H1 institute
The word frequency for the every profession and trade keyword being fitted on determines that the word frequency of industry keywords C1 and C2 as corresponding to H1 are respectively 3,2, then
The weight of H1 can be (3+2) * 0.1=0.5, and the same manner determines that the weight of H2 is 0.1.The weight of intention labels equally can be with
It is determined according to the frequency of corresponding kernel keyword and/or particular keywords.For example, H1 is corresponding with intention labels Y1 and Y2, Y1
It is obtained by kernel keyword, then the weight of Y1 can be determined based on the word frequency of the kernel keyword, and such as 0.2, Y2 is by specific pass
Keyword obtains, then the weight of Y1 can be determined based on the particular keywords or the word frequency of its corresponding informance, and such as 0.1.
For an incoming number N1 through tentatively identifying, it is assumed that record has its 50 dialog contexts, and server can be right
Each dialog context determines corresponding industry weight and intention labels weight in the above manner.In turn, server integrates this
The intention labels and its weight of industry and its weight determined by 50 dialog contexts and wherein every profession and trade.For example, server
The therefrom highest industry of weight after determining synthesis, after weight addition mutually of the same trade, the weight highest of H1, and then determining H1
The highest intention labels of weight after synthesis in each intention labels, such as the weight highest of Y1, accordingly, server can determine the incoming call
The industry H1 and its intention labels Y1 of number N1.
Preferably, in order to more accurately identify that incoming call is intended to, only when the weight of top ranked intention labels is remote
Higher than the intention labels of secondary position weight when, for example, the former weight must be at least 10 times of the latter's weight or more, (ratio can
To be arranged according to application demand), server just can determine that the highest intention labels of the weight are the intention labels of number N1.
Later, if there is user receives the incoming call of number N1, intention labels Y1 then can be supplied to user by server,
As shown in figure 3, call interface can show Y1 (such as gold financing) at this time, more accurately to prompt user, for user's reference
Y1 simultaneously decides whether to answer the incoming call according to its specific requirements.Here, due to normally comprising industry in intention labels, therefore mention
When showing that user of incoming call is intended to, server can only provide intention labels.
Further, for answering the user that the N1 sends a telegram here according to Y1 prompt, it is believed that it feels emerging to intention labels Y1
Interest, and then information relevant to intention labels Y1 is pushed to it.
Fig. 4 is shown according to one embodiment of present invention, wherein specifically illustrating a kind of to incoming call intention progress identification device
Schematic diagram.
The identification device 40 is located at network side, can typically be installed in one or more server.However, ability
Although field technique personnel will be understood that the identification being intended to incoming call is performed by network-side, due to entirely conversing
Journey is to carry out in user terminal, therefore the present invention also needs the auxiliary of user terminal to the identification that incoming call is intended to.Here, user terminal is typical
Ground such as mobile phone, network-side is typically such as server.Unless otherwise instructed, network-side is equal with server and uses in this specification.
As shown in figure 4, identification device 40 includes speech recognition equipment 41, industry coalignment 42, label determining device 43
With intention determining device 44.
For an incoming number through tentatively identifying, speech recognition equipment 41 carries out language to its multiple dialog context respectively
Sound identification；Industry coalignment 42 is by the content matching industry keywords library of each speech recognition, to obtain one matched
Or multiple industries, wherein the industry keywords library includes that multiple industries and its corresponding one or more industries are crucial
Word；Label determining device 43 determines one corresponding to wherein each industry is respectively according to the content of each speech recognition
Or multiple intention labels；It is intended to the weight and wherein of every profession and trade corresponding to the comprehensive multiple dialog context of determining device 44
The weight of each intention labels of each industry, with industry and its intention labels corresponding to the determination incoming number.
Specifically, for an incoming number through tentatively identifying, speech recognition equipment 41 is to its multiple dialog context point
It carry out not speech recognition.
Here, the incoming number through tentatively identifying including but not limited to has been identified as the incoming number, of harassing call
Identification has the incoming number etc. of preliminary identification.For example only prompt user is the incoming number of harassing call for the former, and the latter is for example
It is identified as the incoming number of such as " intermediary ", " distribution ".The invention is intended to the harassing call on these ordinary meanings into one
Step provides refinement intention labels, so that the user for answering the incoming number can decide whether to answer this according to its specific requirements
Incoming call is rather than based solely upon the marks such as " intermediary ", " distribution " and blindly refuses the incoming call, or wastes time to find and be not inconsistent after answering
Close the demand of itself.
In addition, it should be noted that, present invention meaning " harassing call " does not include that " fraudulent call " etc. has illegal meaning
The phone of figure, these phones with illegal intention should be filtered by such as operator, not within the scope of discussion of the invention.
After user answers the incoming number through tentatively identifying, user equipment will record this time conversing for user, and will
Dialog context is uploaded to server.
Here, user equipment can only record the dialog context of folk prescription, such as only remember in order to preferably protect privacy of user
Record the dialog context of caller.It is included in the dialog context of usual caller for the incoming call of such as " intermediary ", " distribution " etc.
Enough information determines that its incoming call is intended to.
Present invention contemplates that other secret protection schemes.It is not answered currently for example, user equipment can be recorded only
The address list of user or the dialog context of the telephone number in message registration.That is, the incoming number should be strange number.
For an incoming number through tentatively identifying, speech recognition equipment 41 will carry out voice to its multiple dialog context
Identification.In order to more acurrate and more identify to fining the intention of an incoming number, identification device 40 needs repeatedly to converse to it
Content is analyzed to determine most probable intention.Dialog context means to be hung up from user's incoming call answering to this call
The dialog context of middle generation.
Wherein, the speech recognition of dialog context is intended to convert the dialog context of audio to the dialog context of text.Language
Sound identification has been mature technology, and the present invention does not specifically describe herein.Any existing or future speech recognition technology such as may be used
Applied to the present invention, this should all be contained in.
Content through speech recognition can be the dialog context of written form, be also possible in the call to the written form
That holds is further processed, and such as extracts keyword set from it.It is extracted from a dialog context here, a keyword set can be
All keywords.
Then, industry coalignment 42 is by the content matching industry keywords library of each speech recognition, to be matched
One or more industries.
Here, network-side further includes an industry keywords library, including corresponding to multiple industries and each industry
One or more industry keywords.
For example, industry coalignment 42 can be by each keyword set of an incoming number through tentatively identifying respectively at this
Matching inquiry is carried out in industry keywords library, to obtain the one or more industries to match.
Alternatively, industry coalignment 42 can also directly by the dialog context of written form and every profession and trade keyword into
Row matching, to obtain the one or more industries to match.
Industry keywords to industry the mapping property of can be exemplified it is as follows:
" buy house, rent a house, house, real estate, room rate, house type ... " -> " real estate industry "
" automobile, buying car, test ride, the shop 4S " -> " automobile industry "
" investment, financing, gold, silver, stock " -> " Investment & Financing industry "
Then, label determining device 43 determines corresponding to wherein each industry difference according to the content of each speech recognition
One or more intention labels.
After determining industry corresponding to incoming number by each dialog context, the present invention is further determined accordingly
Specifically intended label under industry enables a user to the intention for accurately knowing the incoming number.
According to a preferred embodiment of the present invention, network-side can establish an intention labels library, including each row
Intention labels corresponding to industry and each industry.Label determining device 43 can be by each speech recognition content, such as key
The dialog context of word set or written form, according to the industry identified by industry coalignment 42, matching inquiry wherein every profession and trade
Corresponding intention labels, to obtain the intention labels under identified every profession and trade.
Specifically such as, for a dialog context " it is interesting to investment in gold to may I ask you ", know through industry coalignment 42
Its other corresponding industry is " Investment & Financing ", and label determining device 43 is further corresponding in " Investment & Financing " to the dialog context
Each intention labels in carry out matching inquiry, to obtain the intention labels that match, such as " investment in gold ".Wherein, " investment reason
Intention labels corresponding to wealth " industry can " investment in gold ", " silver investment ", " equity investment ", " foreign exchange investment " etc..
According to a preferred embodiment of the present invention, label determining device 43 can be corresponding for each specific industry building
It is intended to rule.
For example, each industry can set one group of kernel keyword, when label determining device 43 is in a dialog context
One or more kernel keywords, the corresponding intention labels of the matched kernel keyword of institute are matched to corresponding to specific industry
Using the intention labels as this dialog context.
Specifically, for example, for " Investment & Financing " industry, it is as follows to be intended to the rule property of can be exemplified:
" gold " -> " investment in gold "
" silver " -> " silver investment "
" stock " -> " equity investment "
" foreign exchange " -> " foreign exchange investment "
Accordingly, when label determining device 43 is from being matched to kernel keyword such as under " Investment & Financing " industry in dialog context
" gold " then can determine that corresponding intention labels are " investment in gold " according to the above rule that is intended to.
Alternatively, it is intended that label was also possible to be generated in real time by kernel keyword.For example, still press upper example, when from logical
Words content in be matched under " Investment & Financing " industry kernel keyword such as " gold ", label determining device 43 according to " industry "+
" kernel keyword " generates corresponding intention labels, such as " investment in gold ".
For another example, label determining device 43 is according to the specific feature of each industry, such as each industry is using there is specific pass
Keyword extracts information corresponding with particular keywords are somebody's turn to do (s) from the dialog context through speech recognition, corresponding to obtain
One or more intention labels.
Specifically, for example, after detecting particular keywords from dialog context, label determining device 43 is from its context
It is middle to extract information corresponding with the particular keywords as intention labels.This is considered one kind and passes through semantic analysis
To extract the mode of intention labels.
For example, industry corresponding to current talking content has been determined as " real estate ", when detecting particular keywords
As after " house type ", " developer ", label determining device 43 searches for context and obtains such as " 2 bedrooms ", " Wanke ", and by " two occupy
Room " and " Wanke " are used as intention labels.Preferably, industry " real estate " can also be used as intention labels together.
Here, label determining device 43 can be extracted according to expression way corresponding to each particular keywords its it is specific in
Hold information.For example, under " real estate " industry, when detecting particular keywords " area ", label determining device 43 can be from
It hereinafter extracts XX square meter as corresponding information, to obtain intention labels " real estate " and " XX square meter ".
It is above-mentioned respectively kernel keyword and particular keywords come can be in conjunction with obtaining by way of obtaining intention labels
The intention labels of dialog context.For example, label determining device 43 obtains intention labels " investment in gold " according to kernel keyword, root
Intention labels " 276.39 " are obtained according to particular keywords " price of gold ".
Then, it is intended that the weight of every profession and trade corresponding to the comprehensive multiple dialog context of determining device 44 and wherein each row
The weight of each intention labels of industry, with industry and its intention labels corresponding to the determination incoming number.
Here, one or more industries can be corresponding with for a dialog context, wherein each industry may be used again
To be corresponding with one or more intention labels.Being intended to determining device 44 may further determine that wherein every profession and trade and intention labels
Weight.Preferably, weight is determined based on word frequency.
For example, for dialog context T1, correspond to industry H1 and H2, wherein the weight of H1 can according to T1 at H1 institute
The word frequency for the every profession and trade keyword being fitted on determines that the word frequency of industry keywords C1 and C2 as corresponding to H1 are respectively 3,2, then
The weight of H1 can be (3+2) * 0.1=0.5, and the same manner determines that the weight of H2 is 0.1.The weight of intention labels equally can be with
It is determined according to the frequency of corresponding kernel keyword and/or particular keywords.For example, H1 is corresponding with intention labels Y1 and Y2, Y1
It is obtained by kernel keyword, then the weight of Y1 can be determined based on the word frequency of the kernel keyword, and such as 0.2, Y2 is by specific pass
Keyword obtains, then the weight of Y1 can be determined based on the particular keywords or the word frequency of its corresponding informance, and such as 0.1.
For an incoming number N1 through tentatively identifying, it is assumed that record has its 50 dialog contexts, it is intended that determining device
44 can determine corresponding industry weight and intention labels weight in the above manner to each dialog context.In turn, it is intended that
Industry and its weight determined by this comprehensive 50 dialog contexts of determining device 44 and the wherein intention labels of every profession and trade and its
Weight.Such as, it is intended that determining device 44 therefrom determines the highest industry of weight after synthesis, after being added such as weight mutually of the same trade,
The weight highest of H1, so determine it is comprehensive in each intention labels of H1 after the highest intention labels of weight, such as the weight highest of Y1,
Accordingly, it is intended that determining device 44 can determine the industry H1 and its intention labels Y1 of incoming number N1.
Preferably, in order to more accurately identify that incoming call is intended to, only when the weight of top ranked intention labels is remote
Higher than the intention labels of secondary position weight when, for example, the former weight must be at least 10 times of the latter's weight or more, (ratio can
To be arranged according to application demand), it is intended that determining device 44 just can determine that the highest intention labels of the weight are the meaning of number N1
Icon label.
Identification device 40 can also include a label suggestion device (not shown).Number N1 is determined being intended to determining device 44
Intention labels after, if there is user receives the incoming call of number N1, label suggestion device can then be mentioned intention labels Y1
User is supplied, as shown in figure 3, call interface can show Y1 (such as gold financing) at this time, more accurately to prompt user, is supplied
User is referring to Y1 and is decided whether to answer the incoming call according to its specific requirements.Here, due to being normally comprised in intention labels
Industry, therefore when prompt user of incoming call intention, label suggestion device can only provide intention labels.
The present invention can be using any combination of one or more computer-readable media.Computer-readable medium can be with
It is computer-readable signal media or computer readable storage medium.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.
The more specific example (non exhaustive list) of computer readable storage medium includes: being electrically connected with one or more conducting wires
Connect, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), erasable type may be programmed it is read-only
Memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this document, computer readable storage medium, which can be, any include or stores
The tangible medium of program, the program can be commanded execution system, device or device use or in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
It should be noted that the present invention can be carried out in the assembly of software and/or software and hardware, for example, this hair
Specific integrated circuit (ASIC) can be used in bright each device or any other is realized similar to hardware device.In addition, of the invention
Some steps or function hardware can be used to realize, for example, as with processor cooperate thereby executing each step or function
Circuit.
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 in the present invention.The multiple units or device stated in system claims can also be led to by a unit or device
Software or hardware are crossed to realize.
Claims (16)
1. a kind of be intended to incoming call to carry out knowledge method for distinguishing, wherein method includes the following steps:
It is directed to an incoming number through tentatively identifying, speech recognition is carried out respectively to its multiple dialog context；
By the content matching industry keywords library of each speech recognition, to obtain the one or more industries to match, wherein
The industry keywords library includes multiple industries and its corresponding one or more industry keywords；
According to the content of each speech recognition, one or more intention marks corresponding to wherein each industry is respectively are determined
Label；
The weight of every profession and trade corresponding to the comprehensive multiple dialog context and the wherein power of each intention labels of each industry
Weight, with industry and its intention labels corresponding to the determination incoming number.
2. according to the method described in claim 1, wherein, each industry is corresponding with one or more intention labels；
Wherein, the content according to each speech recognition determines one or more corresponding to wherein each industry is respectively
The step of a intention labels, specifically includes:
By the intention labels of the content matching of each speech recognition wherein each industry, to obtain corresponding to corresponding industry
One or more intention labels.
3. method according to claim 1 or 2, wherein the content according to each speech recognition determines wherein
Each industry respectively corresponding one or more intention labels the step of specifically include:
To the kernel keyword of the content matching of each speech recognition wherein each industry, by the matched core key of institute
Word determines one or more intention labels corresponding to corresponding industry.
4. method according to claim 1 or 2, wherein the content according to each speech recognition determines wherein
Each industry respectively corresponding one or more intention labels the step of specifically include:
From the content of each speech recognition according to the particular keywords of wherein each industry, corresponding information is extracted, to obtain
Obtain one or more intention labels corresponding to corresponding industry.
5. method according to claim 1 or 2, wherein every profession and trade corresponding to the synthesis multiple dialog context
Weight and wherein the weight of each intention labels of each industry the step of specifically include:
By each in the multiple dialog context the weight of corresponding every profession and trade merge and will be wherein each
The weight of each intention labels of industry merges.
6. method according to claim 1 or 2, wherein the incoming number through tentatively identifying is not present in currently connecing
It listens in the address list or message registration of user.
7. method according to claim 1 or 2, wherein after the intention labels for determining the incoming number, this method
It is further comprising the steps of:
When user is connected to the incoming call of the incoming number, Xiang Suoshu user prompts identified intention labels.
8. method according to claim 1 or 2, wherein the incoming number through tentatively identifying includes following at least appointing
One:
It has been identified as the incoming number of harassing call；
The incoming number for having preliminary identification is identified.
9. a kind of be intended to the device that is identified to incoming call, wherein the device includes:
For being directed to an incoming number through tentatively identifying, the device of speech recognition is carried out respectively to its multiple dialog context；
For by the content matching industry keywords library of each speech recognition, to obtain the dress of the one or more industries to match
It sets, wherein the industry keywords library includes multiple industries and its corresponding one or more industry keywords；
For the content according to each speech recognition, one or more intentions corresponding to wherein each industry is respectively are determined
The device of label；
For integrating the weight and wherein each intention labels of each industry of every profession and trade corresponding to the multiple dialog context
Weight, with the device of industry corresponding to the determination incoming number and its intention labels.
10. device according to claim 9, wherein each industry is corresponding with one or more intention labels；
Wherein, the content according to each speech recognition determines one or more corresponding to wherein each industry is respectively
The operation of a intention labels specifically includes:
By the intention labels of the content matching of each speech recognition wherein each industry, to obtain corresponding to corresponding industry
One or more intention labels.
11. device according to claim 9 or 10, wherein the content according to each speech recognition determines it
In the operations of each industry corresponding one or more intention labels respectively specifically include:
To the kernel keyword of the content matching of each speech recognition wherein each industry, by the matched core key of institute
Word determines one or more intention labels corresponding to corresponding industry.
12. device according to claim 9 or 10, wherein the content according to each speech recognition determines it
In the operations of each industry corresponding one or more intention labels respectively specifically include:
From the content of each speech recognition according to the particular keywords of wherein each industry, corresponding information is extracted, to obtain
Obtain one or more intention labels corresponding to corresponding industry.
13. device according to claim 9 or 10, wherein after the intention labels for determining the incoming number, the dress
It sets further include:
When for being connected to the incoming call of the incoming number in user, Xiang Suoshu user prompts the device of identified intention labels.
14. device according to claim 9 or 10, wherein the incoming number through tentatively identifying include it is following at least
Any one:
It has been identified as the incoming number of harassing call；
The incoming number for having preliminary identification is identified.
15. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, wherein the processor is realized when executing the computer program as described in any item of the claim 1 to 8
Method.
16. a kind of computer readable storage medium, is stored thereon with computer program, wherein the computer program is processed
Such as method described in any item of the claim 1 to 8 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710297217.7A CN107181879B (en) | 2017-04-28 | 2017-04-28 | Identification incoming call is intended to |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710297217.7A CN107181879B (en) | 2017-04-28 | 2017-04-28 | Identification incoming call is intended to |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107181879A CN107181879A (en) | 2017-09-19 |
| CN107181879B true CN107181879B (en) | 2019-10-25 |
Family
ID=59832074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710297217.7A Active CN107181879B (en) | 2017-04-28 | 2017-04-28 | Identification incoming call is intended to |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107181879B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107864301B (en) * | 2017-10-26 | 2020-05-12 | 平安科技（深圳）有限公司 | Client label management method, system, computer equipment and storage medium |
| CN108769434A (en) * | 2018-05-24 | 2018-11-06 | 郑州村村联网络技术有限公司 | Call processing method, apparatus and system |
| CN108933870B (en) * | 2018-07-26 | 2021-06-11 | 平安科技（深圳）有限公司 | Dialing control method and device for sales call, computer equipment and storage medium |
| CN110266900B (en) * | 2019-06-11 | 2023-04-07 | 平安科技（深圳）有限公司 | Method and device for identifying customer intention and customer service system |
| CN110891124B (en) * | 2019-12-11 | 2021-04-23 | 厦门韭黄科技有限公司 | System for artificial intelligence pick-up call |
| CN113507541A (en) * | 2021-07-02 | 2021-10-15 | 马上消费金融股份有限公司 | Incoming call intention display method and device |
| CN114331252A (en) * | 2021-10-12 | 2022-04-12 | 广州汇智通信技术有限公司 | Mobile phone number repairing method, express delivery distribution system and computer program |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8625749B2 (en) * | 2006-03-23 | 2014-01-07 | Cisco Technology, Inc. | Content sensitive do-not-disturb (DND) option for a communication system |
| TW200826610A (en) * | 2006-12-07 | 2008-06-16 | Inventec Corp | System and method for identifying harassing and spam calls |
| CN104618554A (en) * | 2014-12-18 | 2015-05-13 | 惠州Tcl移动通信有限公司 | Method and terminal for automatically saving unknown caller number by recognizing voice content |
| CN104580758A (en) * | 2015-01-19 | 2015-04-29 | 北京奇虎科技有限公司 | Incoming call comment information acquisition method and device |
| CN105100366B (en) * | 2015-07-13 | 2018-03-20 | 小米科技有限责任公司 | Harassing call number determines methods, devices and systems |
| CN105933497B (en) * | 2016-06-30 | 2019-04-12 | 百度在线网络技术（北京）有限公司 | A kind of call blocking method and apparatus of multi-mode |
-
2017
- 2017-04-28 CN CN201710297217.7A patent/CN107181879B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107181879A (en) | 2017-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107181879B (en) | Identification incoming call is intended to | |
| CN110069608B (en) | Voice interaction method, device, equipment and computer storage medium | |
| TWI711967B (en) | Method, device and equipment for determining broadcast voice | |
| CN103077714B (en) | Information identification method and apparatus | |
| US7899698B2 (en) | Real-time sales support and learning tool | |
| US20190362724A1 (en) | Method and apparatus for voiceprint creation and registration | |
| JP2021009701A (en) | Interface intelligent interaction control method, apparatus, system, and program | |
| EP4053802A1 (en) | Video classification method and apparatus, device and storage medium | |
| CN103678269A (en) | Information processing method and device | |
| CN110457679A (en) | Construction method, device, computer equipment and the storage medium of user's portrait | |
| CN104794122A (en) | Position information recommending method, device and system | |
| CN107423055A (en) | Method, apparatus, equipment and the storage medium of adaptive terminal device resolution | |
| CN107526723A (en) | A kind of method, apparatus, server and the storage medium of semantic disambiguation | |
| CN108171576A (en) | Order processing method, apparatus, electronic equipment and computer readable storage medium | |
| CN111028834A (en) | Voice message reminding method and device, server and voice message reminding equipment | |
| CN109241385A (en) | Searching method, equipment and storage medium | |
| CN108257596A (en) | It is a kind of to be used to provide the method and apparatus that information is presented in target | |
| CN107463929A (en) | Processing method, device, equipment and the computer-readable recording medium of speech data | |
| CN104040574A (en) | Systems, methods, and computer program products for capturing natural responses to advertisements | |
| CN109346060A (en) | Audio recognition method, device, equipment and storage medium | |
| CN108595141A (en) | Pronunciation inputting method and device, computer installation and computer readable storage medium | |
| CN109033456A (en) | A kind of condition query method, apparatus, electronic equipment and storage medium | |
| CN115330498B (en) | Data processing method and related device in man-machine interactive shopping service system | |
| CN111881381A (en) | Display method, device, equipment and storage medium | |
| CN108920715A (en) | Intelligent householder method, device, server and the storage medium of customer service |
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 |