CN109064315A - Overdue bill intelligence collection method, apparatus, computer equipment and storage medium - Google Patents
Overdue bill intelligence collection method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109064315A CN109064315A CN201810870736.2A CN201810870736A CN109064315A CN 109064315 A CN109064315 A CN 109064315A CN 201810870736 A CN201810870736 A CN 201810870736A CN 109064315 A CN109064315 A CN 109064315A
- Authority
- CN
- China
- Prior art keywords
- overdue
- collection
- client
- voice
- target
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Telephonic Communication Services (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of overdue bill intelligence collection method, apparatus, computer equipment and storage mediums, this method comprises: being divided according to customer risk grade classification strategy to the overdue customer information for entering to urge case, overdue client's list is obtained, overdue client's list includes overdue customer information and overdue type identification corresponding with overdue customer information；It obtains collection corresponding with overdue type identification and talks about art template, overdue customer information is added to the corresponding position of collection words art template, target collection is obtained and talks about art；Telephony platform is called, target collection words art is simultaneously converted into target collection voice, obtains overdue client to the overdue collection result of target collection voice feedback by the telephone number of the overdue client of automatically dial.Improve collection working efficiency, reduce collection cost and because collection strategy use it is improper caused by customer complaint rate.
Description
Technical field
The present invention relates to technical field of information processing more particularly to a kind of overdue bill intelligence collection method, apparatus, calculate
Machine equipment and storage medium.
Background technique
With the transformation of people's consumption consciousness and consumption habit and advocating for national policy, the money-lending businesses such as consumptive loan
Business is quickly grown, and the overdue loan refund problem occurred thereupon is also more and more prominent.It does not refund for overdue in the industry at present
Loan collection be the overdue loan that financial industry is handled based on artificial collection means mostly.This kind of artificial collection mode is not
Only need to expend the training that great amount of cost puts into collection personnel, there is also the lower problems of collection working efficiency.In addition, collection
Personnel can have collection strategy use improper the problem of causing customer complaint or even lawsuit risk during collection, give
Company brings massive losses, carries out with being unfavorable for loan transaction stability and high efficiency.
Summary of the invention
The embodiment of the present invention provides a kind of overdue bill intelligence collection method, apparatus, computer equipment and storage medium, with
Solve the problems, such as existing collection low efficiency and higher cost when current manual's collection.
A kind of overdue bill intelligence collection method, comprising:
Original case is screened according to collection rule, is obtained into urging case, it is described to enter case is urged to carry overdue visitor
Family information, the overdue customer information include the telephone number of overdue client；
Enter the overdue customer information of case is urged to divide to described according to customer risk grade classification strategy, obtain overdue
Client's list, overdue client's list include overdue customer information and overdue type corresponding with the overdue customer information
Mark；
Collection words art template corresponding with the overdue type identification is obtained, the overdue customer information is added to institute
The corresponding position of collection words art template is stated, target collection is obtained and talks about art；
Telephony platform is called, target collection words art is simultaneously converted into target by the telephone number of the overdue client of automatically dial
Collection voice obtains overdue client to the overdue collection result of the target collection voice feedback.
A kind of overdue bill intelligence collection device, comprising:
Enter to urge case to obtain module, for being screened according to collection rule to original case, obtains into urging case, it is described
Enter to urge case to carry overdue customer information, the overdue customer information includes the telephone number of overdue client；
Overdue client's list obtains module, for entering to urge the overdue of case to described according to customer risk grade classification strategy
Customer information is divided, and overdue client's list is obtained, and overdue client's list includes overdue customer information and exceedes with described
The corresponding overdue type identification of phase customer information；
Target collection talks about art and obtains module, for obtaining collection words art template corresponding with the overdue type identification,
The overdue customer information is added to the corresponding position of the collection words art template, target collection is obtained and talks about art；
Overdue collection result obtains module, and for calling telephony platform, the telephone number of the overdue client of automatically dial simultaneously will
The target collection words art is converted into target collection voice, obtains overdue client and urges the overdue of target collection voice feedback
Receive result.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize above-mentioned overdue bill intelligence collection side when executing the computer program
The step of method.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program realizes the step of above-mentioned overdue bill intelligence collection method when being executed by processor.
Above-mentioned overdue bill intelligence collection method, apparatus, computer equipment and storage medium, by collection rule to original
Case is screened, will not meet collection rule original case delete, obtain meet collection rule enter to urge case.Then root
The overdue customer information for entering to urge case is divided according to customer risk grade classification strategy, obtains different overdue customer types pair
The overdue client's list answered includes overdue type identification in overdue client's list.It obtains and exceedes then according to overdue type identification
Phase type identification corresponding collection words art template and overdue customer information generate target collection and talk about art, by telephony platform from
Dynamic dial technology carries out phone collection to overdue client, obtains overdue collection as a result, determining whether overdue client has refund wish.
If carrying agreement mark in overdue collection result, efficient income information is sent to the terminal device of overdue client, raising is urged
Working efficiency is received, collection cost is reduced.If being carried in overdue collection result and disagreeing mark, to the call language of overdue client
Sound carries out Application on Voiceprint Recognition and Emotion identification, Emotion identification result is finally fed back to operator attendance, so that operator attendance is according to feelings
Thread recognition result carries out phone collection to overdue client, reduces because of the improper complaint for causing customer complaint of collection strategy use
Rate.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is an application scenario diagram of overdue bill intelligence collection method in one embodiment of the invention；
Fig. 2 is a flow chart of overdue bill intelligence collection method in one embodiment of the invention；
Fig. 3 is a specific flow chart of step S40 in Fig. 2；
Fig. 4 is a specific flow chart of step S43 in Fig. 3；
Fig. 5 is another flow chart of overdue bill intelligence collection method in one embodiment of the invention；
Fig. 6 is another flow chart of overdue bill intelligence collection method in one embodiment of the invention；
Fig. 7 is a specific flow chart of step S46 in Fig. 6；
Fig. 8 is a specific flow chart of step S47 in Fig. 6；
A schematic diagram of overdue bill intelligence collection device in Fig. 9 one embodiment of the invention；
Figure 10 is a schematic diagram of computer equipment in one embodiment of the 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 some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Overdue bill intelligence collection method provided in an embodiment of the present invention, can be applicable in the application environment such as Fig. 1, this exceedes
Phase bill intelligence collection method is applied in intelligent collection system, which includes client and server, wherein
Client is communicated by network with server.Wherein, client is also known as user terminal, refers to corresponding with server, is
The program of client's offer local service.Client it is mountable but be not limited to various personal computers, laptop, intelligent hand
Machine, tablet computer and portable wearable device.Server can use the either multiple server compositions of independent server
Server cluster is realized.
In one embodiment, it as shown in Fig. 2, providing a kind of overdue bill intelligence collection method, is applied in this way in Fig. 1
In server for be illustrated, include the following steps:
S10: original case is screened according to collection rule, obtains into case is urged, enters to urge case to carry overdue visitor
Family information, overdue customer information include the telephone number of overdue client.
Wherein, collection rule, which refers to, needs to carry out the rule of the case of collection for judging whether original case belongs to.It is original
Case refers to the case that the needs of operation system storage are refunded.Enter to urge case to refer to and meet collection rule, repayment date is being answered not refund
Case.
Specifically, intelligent collection system obtains the original case that operation system is sent, and original case carries the original case
Part answers repayment date, and intelligent collection system screens original case using collection rule after obtaining original case, screens
Out in the case for answering repayment date not refund, it is determined as into urging case.What intelligent collection system obtained, which enter that case is urged to carry, exceedes
Phase customer information, the overdue customer information refer to the personal information of overdue client, the name of including but not limited to overdue client, bank
Card account, repayment amount, refund date and telephone number.Wherein, overdue client, which refers to, is answering repayment date not complete the visitor to refund
Family.
Further, during sending intelligent collection system for original case from operation system in order to prevent, client
The case where information leakage, occurs, and operation system can be before being sent to intelligent collection system for original case, using RSA Algorithm pair
Original case is encrypted.Ciphering process is specifically, intelligent collection system randomly chooses two biggish prime number A and B, calculating element
The product N of number A and prime number B.Then select the product of an integer e and (A-1) * (B-1) relatively prime, and e is less than (A-1) * (B-1),
D is finally calculated according to formula d*e ≡ 1 (mod (A-1) (B-1)).Then (N, e) is known as public key, and (N, d) is known as private key.Intelligent collection
System retains private key, public key is sent to operation system, operation system carries out the content in original case using this public key
Encryption, generates corresponding ciphertext.Correspondingly, before step S10, i.e., intelligent collection system is according to collection rule to original case
It is screened, before obtaining the step of urging case, intelligent collection system is decrypted original case using private key.
It is highly-safe since RSA Algorithm is current most powerful and most common public key encryption algorithm, it can resist
So far therefore known most of cryptographic attack is encrypted and decrypted original case using RSA Algorithm, can
To improve safety of the data in transmission process.
S20: dividing the overdue customer information for entering to urge case according to customer risk grade classification strategy, obtains overdue
Client's list, overdue client's list include overdue customer information and overdue type identification corresponding with overdue customer information.
Wherein, customer risk grade classification strategy refers to exceedes according to the overdue repayment amount of client, overdue refund number of days and history
At least one of indexs such as phase refund number carry out the strategy of risk class division to client.Overdue client's list refers to according to visitor
Family risk class partition strategy carries out the obtained list including overdue customer information after grade classification to entering to urge case.This is overdue
Customer name is applied alone in the overdue customer information of storage and overdue type identification corresponding with overdue customer information.Wherein, overdue client
Information includes but is not limited to that the name of overdue client, bank card account number, repayment amount, date of refunding, telephone number, history are overdue
Refund number of days and the overdue refund number of history.Overdue type identification refers to the mark for the overdue customer type of unique identification.This exceedes
Phase type identification can be any one of specific character string, specific digital or specific letter or a variety of groups
It closes.
Overdue customer type in the present embodiment includes but is not limited to high-order client, low order client, is used to exceed client, lost contact visitor
Family and lousy customer.Wherein, high-order client refers to that overdue refund number of days is more than 60 days clients.Low order client refers to overdue refund number of days
Client no more than 60 days.It is used to exceed client and refer to that the overdue refund number of history in 6 months has reached 4 clients.Lost contact visitor
Family refers to that basis enters the client for urging the telephone number in case that can not relate to.Lousy customer has pointed to the specified refund time always not
The also client of money.In order to facilitate differentiation, each overdue customer name single pair answers an overdue type identification.Such as: low order client
Corresponding low order customer type identifies L, and high-order client correspond to high-order customer type mark H, used to exceed that client is corresponding to be used to exceed customer type
F is identified, lost contact client corresponds to lost contact customer type mark O, and lousy customer corresponds to lousy customer's type identification Z.
Specifically, intelligent collection system obtains urge case after, can from enter to urge case carry overdue customer information in obtain
Take the overdue refund number of days of the corresponding history of overdue client and the overdue refund number of history.It is then based on pre-set customer risk
Grade classification strategy judges the overdue refund number of days of the corresponding history of overdue client and the overdue refund number of history, determines
The corresponding overdue customer type of overdue client in case is urged, the corresponding overdue client's list of different overdue type identifications is generated.It should
Include overdue customer information and overdue type identification in overdue client's list, conveniently obtains and exceed subsequently through overdue type identification
Art template is talked about in the corresponding collection of phase type identification, is completed to entering to urge the corresponding overdue client of case to carry out refund collection.
S30: obtaining collection corresponding with overdue type identification and talk about art template, and overdue customer information is added to collection words
The corresponding position of art template obtains target collection and talks about art.
Wherein, collection words art template refers to pre-set for carrying out refund collection to overdue client in intelligent collection system
If art template.Wherein, each collection words art template is associated with an overdue type identification, to be looked into based on overdue type identification
Find corresponding collection words art template.In the present embodiment, collection words art template is stored in the form of text in intelligent collection system,
Subsequent overdue customer information is added in collection words art template is facilitated to generate target collection words art.
Specifically, after obtaining overdue type identification, intelligent collection system can according to the overdue type identification of acquisition choose with
Art template is talked about in the corresponding collection of overdue type identification, then by the name in overdue customer information, bank card account number, repayment amount
It is added in collection words art template corresponding with the overdue type identification with the date of refunding, obtains target collection and talk about art.Wherein,
Target collection words art refers to the overdue visitor for specific overdue customer type being made of overdue customer information and collection words art template
Art is talked about in the collection at family.
Intelligent collection system is for more easily services client, for the overdue client of different overdue customer types, system
Art template is talked about in fixed different collection.Such as: art is talked about in the corresponding collection of low order client are as follows: Mr. XXX/Ms, hello！Your XX bank
The overdue xxxx member of the credit card that tail number is xxxx, please refunds before xxxx days as early as possible, asks if having no objection and agreeing to refund
Confirmation ... waits client to answer ..., if there are also other problems please call the inquiry of 95511 customer phones, thank you comes
Electricity！
Art is talked about in the corresponding collection of high-order client are as follows: Mr. XXX/Ms, hello！The credit card that your XX bank tail number is xxxx
Overdue xxxx member, for the personal reference for avoiding influencing you, please refunds before xxxx days as early as possible, please be true if had no objection
Recognize ... and client is waited to answer ..., if client, which has a question, is directly transferred to operator attendance processing, please by 0.
In the present embodiment, art template is talked about by overdue customer information and collection corresponding with overdue type identification, is obtained
Art is talked about in target collection, and when avoiding artificial collection, the situation for causing client to be discontented with since collection strategy use is improper occurs, and is simultaneously
Phone collection is carried out to overdue client by telephony platform in step S40, data source is provided.
S40: calling telephony platform, and target collection words art is simultaneously converted into target by the telephone number of the overdue client of automatically dial
Collection voice obtains overdue client to the overdue collection result of target collection voice feedback.
Specifically, intelligent collection system obtains target collection and talks about postoperative, overdue client letter of the meeting from overdue client's list
The telephone number of overdue client is obtained in breath.After obtaining the telephone number of target collection words art and overdue client, intelligent collection
System can call built-in telephony platform, which is integrated with auto dialing technology, telephony platform can by it is integrated from
Dynamic dial technology dials the corresponding terminal device of telephone number of overdue client, after the terminal device of overdue client is connected, intelligence
Target collection can be talked about art and be converted to target collection voice by energy collection system, and the terminal of overdue client is sent to by telephony platform
Equipment carries out electricity to overdue client to realize so that overdue client can hear the target collection voice by the terminal device
Talk about collection.In the present embodiment, which is specially mobile phone, the smartwatch with call function or other equipment.
In the present embodiment, target collection words art is converted to collection voice, overdue client is carried out using the collection voice
Phone collection avoids collection so that phone collection carries out phone collection to overdue client according to the collection words art of preset standard
The mood of oneself is added during phone collection in personnel, causes adverse effect to overdue collection result.
Meanwhile intelligent collection system can also obtain the call voice of overdue client accessed by built-in telephony platform,
So that the call voice to overdue client is analyzed, overdue collection result is obtained.Intelligent collection system passes through built-in phone
Platform carries out phone collection to overdue client, and being implemented without manual intervention can be completed the function of phone collection, improves collection
Working efficiency.
In overdue bill intelligence collection method provided by the embodiment of the present invention, first by collection rule to original case
Screened, will not meet collection rule original case delete, obtain meet collection rule enter to urge case, effectively reduce intelligence
Energy collection system obtains volume of transmitted data from operation system, saves data transmission period, improves collection efficiency.Then, according to intelligence
The energy pre-set customer risk grade classification strategy of collection system divides the overdue customer information for entering to urge case, obtains
The corresponding overdue client's list of the overdue customer type of difference, identifies for convenience, includes overdue type mark in overdue client's list
Know.Then, collection words art template corresponding with overdue type identification and overdue customer information are obtained according to overdue type identification, it is raw
Art is talked about at the target collection for specific overdue client, so that target collection words art has specific aim.Finally overdue client is believed
The telephone number of overdue client and target collection words art are sent to the telephony platform built in intelligent collection system in breath, pass through phone
Platform carries out phone collection to overdue client, obtains overdue collection and urges as a result, being implemented without manual intervention and phone can be completed
The function of receipts improves collection working efficiency.
In one embodiment, as shown in figure 3, step S40, calls telephony platform, the connection electricity of the overdue client of automatically dial
It talks about and target collection words art is converted into target collection voice, obtain overdue collection of the overdue client to target collection voice feedback
As a result, specifically comprising the following steps:
S41: the telephone number based on overdue client calls telephony platform to pull out the telephone number of overdue client automatically
Number.
Built-in telephony platform refers to telephony platform built-in in intelligent collection system in the present embodiment, collects in the telephony platform
At auto dialing technology.The auto dialing technology is CTI technology, wherein CTI technology is from traditional computer telephone integration
A kind of technology that (Computer Telephony Integration) technology develops, CTI technology can be by computer skills
Art is applied in telephone system, automatically can carry out identifying processing to the command information in phone, and related by establishing
Speech channel connection, and the technology of scheduled recording file and calling of transferring is transmitted to user.
Specifically, which can be sent to interior by intelligent collection system after the telephone number for obtaining overdue client
The telephony platform set, telephony platform can pass through integrated auto dialing technology pair after the telephone number for getting overdue client
Auto dialing is carried out to the telephone number of overdue client.In the present embodiment, intelligent collection system passes through in built-in telephony platform
Auto dialing technology realize the corresponding terminal device of telephone number of the overdue client of automatic dialing, be implemented without artificial dry
The function of dialing can be completed in advance.
S42: the connection signal of the corresponding terminal device feedback of telephone number is obtained, based on signal is connected, using TTS technology
Target collection words art is converted to corresponding target collection voice, target collection voice is sent to terminal device.
Wherein, it connects signal and refers to that the corresponding terminal device of telephone number feeds back to the signal of telephony platform after the switch, it should
Connecting signal can be used to identify whether the corresponding terminal device of telephone number is connected.TTS technology refer to by computer oneself generate or
The technology that the externally input text information of person is changed into Chinese characters spoken language and exports.Target collection voice, which refers to, talks about target collection in art
Content transformation at collection voice.
Specifically, telephone number of the telephony platform based on overdue client carries out the corresponding terminal device of the telephone number
Auto dialing, after the corresponding terminal device of the telephone number is connected, which can send a connection signal to phone
Platform indicates that the corresponding terminal device of the telephone number has turned on.Telephony platform, can be by the connection after obtaining connection signal
Signal feeds back to the server of intelligent collection system, and the server of intelligent collection system can be talked about target collection by TTS technology
Art is converted to corresponding target collection voice, and target collection voice is sent to terminal device by telephony platform, so as to carry
The overdue client of the terminal device can hear the target collection voice, to realize intelligent sound collection, be not necessarily to manual intervention collection
Process improves collection efficiency, and helps to reduce collection cost.
Further, target collection words art is converted to corresponding target collection voice by using TTS technology, so that urging
Receive token sound, avoid when artificial collection the collection personnel tone it is improper cause client discontented or collection personnel speech utterance not
Standard and generation the case where influence collection effect.
S43: the call voice of receiving terminal apparatus feedback carries out semantic analysis to call voice, obtains overdue collection knot
Fruit.
Specifically, the call from overdue client that intelligent collection system can be fed back by telephony platform receiving terminal apparatus
Voice.Intelligent collection system can carry out the call voice of overdue client after the call voice for getting terminal device feedback
Whether semantic analysis judges in the call voice of overdue client containing pre-set " good ", " OK ", " can with " and " meeting of grade
The unidirectional keyword of refunding is agreed in the carryings such as just also ".If containing " good ", " OK ", " can with " and " waiting can be just in call voice
Also " etc. unidirectional keyword of refunding is agreed in carryings, then it represents that overdue client agrees to refund, and overdue collection result is to be ready to refund.
If agreeing to the unidirectional keyword of refund without containing carryings such as " good ", " OK ", " can with " and " waiting can just also " in call voice,
Indicate that overdue client disagrees refund, overdue collection result is to be unwilling to refund.
Step S41- step S43, intelligent collection system is by built-in telephony platform to the telephone number pair of overdue client
The terminal device answered carries out auto dialing, and after dial-up success, target collection words art is converted to target collection by TTS technology
Voice is sent to the corresponding terminal device of overdue client, completes the dialogue with overdue client, obtains overdue collection as a result, reaching
The effect of overdue bill intelligence collection does not need artificial collection, reduces the cost of labor of collection process, improves collection efficiency.
In one embodiment, as shown in figure 4, in step S43, semantic analysis is carried out to call voice, obtains overdue collection
As a result, specifically comprising the following steps:
S431: being scanned call voice, judges whether call voice includes pre-set target keyword.
Wherein, target keyword refers to whether pre-set client overdue for identification agrees to also in intelligent collection system
The keyword of money.I.e. the target keyword is to carry to agree to unidirectional keyword of refunding.
Specifically, the call voice that intelligent collection system is sent by the terminal device that telephony platform gets overdue client
Afterwards, call voice can word for word be scanned according to the keyword identification technology in intelligent collection system, obtains call voice
Phonetic feature.Judge to whether there is and the matched word of target keyword in call voice.Keyword identification in the present embodiment
Technology carries out mesh to call voice using preparatory trained HMM (Hidden Markov Model hidden markov model)
Mark keyword identification.Wherein, in advance trained HMM model be in advance it is trained be stored in intelligent collection system, be used for
With the presence or absence of the model of target keywords such as " good ", " OK ", " can with " and " waiting just to go back " in identification call voice.This implementation
In example, using whether there is target keyword in trained HMM model identification call voice in advance, it is accurate that identification can be improved
Rate.
Alternatively, intelligent collection system converts text technology by voice, text is converted by call voice.Then, it uses
Participle tool carries out cutting, removal stop words (participle, preposition and pronoun etc.), symbol, number to the corresponding text of the call voice
The words such as word and letter, obtain word to be identified.The word to be identified refers to removal stop words, symbol, number in the corresponding text of call voice
The word obtained after word and letter.Finally, similarity calculation is carried out to word to be identified and target keyword using similarity algorithm,
If similarity reaches preset value, it is determined that include target keyword in call voice.Wherein.Similarity algorithm in the present embodiment
Including but not limited to cosine similarity algorithm.
S432: if in call voice including target keyword, the overdue collection result for carrying and agreeing to mark is obtained.
Wherein, agree to that mark refers to for indicating that overdue client agrees to the mark refunded.Specifically, when including in call voice
When the target keywords such as " good ", " OK ", " can with " and " waiting can just also ", then it represents that overdue client agrees to refund, overdue with this
Client carries out the overdue collection result obtained after telephonic communication to agree to refund.It is urged in order to facilitate intelligent collection system according to overdue
Receive result and execute subsequent step, intelligent collection system in determining call voice comprising after target keyword, can be to the overdue visitor
The overdue collection result at family marks corresponding agreement mark, such as " OK " or " 1 ".
S433: if not including in call voice has target keyword, acquisition carries the overdue collection for disagreeing mark
As a result.
Wherein, mark is disagreed to refer to for indicating that overdue client disagrees the mark of refund.Specifically, when in call voice
When not comprising target keywords such as " good ", " OK ", " can with " and " waiting can just also ", then it represents that overdue client disagrees refund,
Carrying out the overdue collection result obtained after telephonic communication with the overdue client is to disagree refund, and intelligent collection system is determining logical
After not including target keyword in language sound, corresponding to the overdue collection result of the overdue client mark mark can be disagreed,
Such as " no " or " 0 ".
Step S431- step S433, intelligent collection system by being scanned to call voice, judge be in call voice
It is no to determine whether overdue client agrees to refund containing target keyword, reach and overdue bill intelligence can be realized without manual intervention
The purpose of energy collection.Subsequent step is executed according to overdue collection result in order to facilitate intelligent collection system, intelligent collection system exists
It determines in overdue customer voice call with the presence or absence of after target keyword, corresponding agreement can be matched to overdue collection result and identified
Perhaps disagreeing mark facilitates intelligent collection system to identify or disagree the corresponding subsequent step of mark execution according to agreement.
In one embodiment, in order to further ensure the validity of telephonic communication, intelligent collection system with overdue client
After telephonic communication finishes and overdue collection result is refunded for agreement, it can also be sent corresponding short by way of short message and mail
Believing with mail reminds overdue client to refund.It therefore, further include the email address of overdue client in overdue client's list, such as
Shown in Fig. 5, in step S43, after the step of obtaining overdue collection result, overdue bill intelligence collection method further include:
S44: if overdue collection result carries agreement mark, it is based on collection information model and overdue customer information, is obtained
Take efficient income information.
Wherein, collection information model, which refers to, pre-sets and is stored in intelligent collection system, for prompting overdue visitor
The information model that family is refunded on time.Such as collection information model are as follows: Mr. XXX/Ms, you are good！According to telephonic communication, you are true
Repayment amount xxxx member will be completed before xxxx days by recognizing the credit card that your safety bank tail number is xxxx；If there are also other to ask
Topic please call the inquiry of 95511 customer phones, the incoming call of thank you！
Efficient income information, which refers to, is added to overdue customer information obtained in collection information model for specific overdue visitor
The collection information at family.
Specifically, when overdue collection result carries agreement mark, intelligent collection system can obtain collection information model
With overdue customer information, name, bank card account number, repayment amount and the date of refunding in overdue customer information are added to collection
In information model, the efficient income information for being directed to the specific overdue client is obtained.
S45: efficient income information is sent to by the telephone number of overdue client or the email address of overdue client
Corresponding terminal device.
Intelligent collection system can be believed efficient income by the telephone number of overdue client after obtaining efficient income information
Breath is sent to the corresponding terminal device of telephone number of the overdue client.In addition, if further including overdue visitor in overdue client's list
When the email address at family, intelligent collection system can obtain the corresponding email address of the overdue client from overdue client's list, so
The corresponding terminal device of the email address that efficient income information is sent to the overdue client in the form of mail afterwards.Using short message
Or mail two ways sends efficient income information to overdue client, may further ensure that overdue client can receive and check
The efficient income information improves collection quality.
In one embodiment, when intelligent collection system is after getting the overdue collection result for carrying and disagreeing mark,
The case where carrying out further to the overdue client, confirms, first confirms that whether the call voice comes from overdue client's sheet
People, if overdue client itself, then execute subsequent step；If not overdue client itself, then give under line with urging staff
Collection.Wherein, with urging staff to refer to by finding overdue client itself, when in face of overdue client progress overdue loan collection
Staff.As shown in fig. 6, in step S43, after the step of obtaining overdue collection result, overdue bill intelligence collection method
Further include:
S46: if the carrying of overdue collection result disagrees mark, Application on Voiceprint Recognition is carried out to call voice, determines call language
Whether the speaker of sound is overdue client itself.
Wherein, Application on Voiceprint Recognition is also referred to as Speaker Identification, by recognizing the vocal print of speaker, determines the identity of speaker.
Specifically, if the overdue collection result obtained, which carries, disagrees mark, then it represents that overdue client disagrees also
Money.At this point, intelligent collection system will use built-in sound groove recognition technology in e and identify to the call voice of overdue client, determine
The call voice whether be overdue client itself sound.If it is determined that call voice is not the sound of overdue client itself, then table
Show that the corresponding contact person of the telephone number changes, needs to contact overdue client itself with the method urged using under line, to urge
Promote the overdue client itself and pays off overdue loan in time.If it is determined that call voice is the sound of overdue client itself, step is executed
S47 carries out Emotion identification to call voice, obtains the Emotion identification result of overdue client.
S47: if the artificial overdue client itself of speaking of call voice, calls pre-stored Emotion identification model to logical
Language sound carries out Emotion identification, obtains Emotion identification result corresponding with overdue collection result.
Specifically, it if intelligent collection system determines that the speaker of call voice is overdue client itself, needs to logical
Language sound is further analyzed, and mood of the overdue client itself when receiving phone collection is determined, so that subsequent artefacts attend a banquet
When carrying out telephonic communication with overdue client, phone ditch is carried out using the collection strategy and overdue client of looking after overdue customer anger
It is logical, avoid the problem that collection personnel cause customer complaint because collection strategy use is improper during collection.
Step S46- step S47, intelligent collection system is after acquisition carries and disagrees the overdue collection result of mark, meeting
Application on Voiceprint Recognition is carried out to the call voice of overdue client first, confirms whether the call voice comes from me；If call voice comes
From overdue client itself, then Emotion identification is carried out to call voice, obtains Emotion identification as a result, operator attendance is facilitated to take appropriately
Collection strategy and overdue client carry out telephonic communication, reduce customer complaint rate.
In one embodiment, as shown in fig. 7, step S46, carries out Application on Voiceprint Recognition to call voice, determine call voice
Whether speaker is overdue client itself, is specifically comprised the following steps:
S461: pre-processing call voice, obtains voice to be identified.
Wherein, voice to be identified refers to call voice is pre-processed after obtain voice.Specifically, call voice is carried out
It before Application on Voiceprint Recognition, needs to pre-process call voice, removes the noise in call voice (including quiet in voice communication
Sound and environmental noise), obtain voice to be identified.Wherein, pretreated process specifically includes: firstly, carrying out to call voice pre-
Exacerbation processing；Then framing and multiplying window are carried out to preemphasis treated call voice；Finally, using end-point detection technology
Call voice is handled, the noise in call voice is removed, to obtain voice to be identified.
S462: speech feature extraction is carried out to voice to be identified, obtains the corresponding phonetic feature to be identified of voice to be identified.
Specifically, after obtaining voice to be identified, voice to be identified is passed through into Fast Fourier Transform (FFT), logarithm operation and discrete
After cosine transform processing, phonetic feature to be identified is obtained.The phonetic feature to be identified is MFCC feature.
S463: phonetic feature to be identified and the corresponding raw tone feature of overdue client are carried out using Application on Voiceprint Recognition model
Application on Voiceprint Recognition determines whether the speaker of call voice is overdue client itself.
Wherein, Application on Voiceprint Recognition model refers to the preparatory trained call voice for identification being stored in intelligent collection system
Speaker whether be overdue client itself model.The Application on Voiceprint Recognition model of existing a variety of maturations, including but not limited to GMM-
UBM (Gaussian mixture model-universal background model, mixed model-universal background model)
Model and i-vector (identity-vector, authentication vector) model.Application on Voiceprint Recognition model in the present embodiment uses
I-vector model is as Application on Voiceprint Recognition model.Raw tone feature refers to the pre-stored overdue client's of intelligent collection system
The corresponding phonetic feature of speech utterance.It is to be appreciated that the speech utterance of the overdue client is by opposite with step S461-S462
After the pretreatment and feature extraction answered, corresponding raw tone feature can be got, and by the raw tone feature with exceed
Phase customer information associated storage is corresponding without carrying out in identification process to call directly when subsequent progress Application on Voiceprint Recognition
Processing, to improve recognition efficiency.
Specifically, after obtaining phonetic feature to be identified, intelligent collection system can be looked into according to the customer information of overdue client
Look for pre-stored raw tone feature corresponding with the overdue customer information in intelligent collection system.Then, by the overdue visitor
The phonetic feature to be identified and raw tone feature at family are input in preparatory trained Application on Voiceprint Recognition model, obtain language to be identified
Sound feature and the corresponding i-vector vector of raw tone feature；Phonetic feature to be identified and raw tone feature are calculated again
The space length of corresponding i-vector vector, if space length is greater than the distance threshold being arranged according to the actual situation,
It can determine the artificial overdue client itself of speaking of call voice.Space vector distance in the present embodiment uses COS distance meter
Formula is calculated to calculate.
Step S461- step S463, by obtaining the corresponding phonetic feature to be identified of call voice, using Application on Voiceprint Recognition mould
Type identifies phonetic feature to be identified and the corresponding raw tone feature of overdue client, determines that the speaker of call voice is
No is overdue client itself, if overdue client itself, then it represents that overdue client is unwilling to refund, and needs through subsequent step pair
Call voice carries out Emotion identification, and seat personnel is facilitated to understand the reason of overdue client does not refund by the way of manually linking up.
In one embodiment, as shown in figure 8, step S47, call pre-stored Emotion identification model to call voice into
Row Emotion identification obtains Emotion identification corresponding with overdue collection result as a result, specifically comprising the following steps:
S471: phonetic feature to be identified is input in Emotion identification model, obtain phonetic feature to be identified it is corresponding to
Confirm that mood, mood to be confirmed carry score of being in a bad mood.
Wherein, Emotion identification model is the client overdue for identification for training and being stored in advance in intelligent collection system
The model of mood.Emotion identification model in the present embodiment uses the Emotion identification model based on vector machine.Mood packet to be confirmed
Include but be not limited to the happiness when speaker that Emotion identification model identifies speaks, indignation, sadness, tired make an uproar peaceful wait mood quietly.
Specifically, it after confirming the sound for artificial overdue client itself of speaking of call voice according to phonetic feature to be identified, intelligently urges
Phonetic feature to be identified is input in preparatory trained Emotion identification model by receipts system, carries out feelings to phonetic feature to be identified
Thread identification, to obtain the mood score of various to be confirmed moods of the corresponding overdue client of call voice when speaking.This implementation
Emotion identification model in example after obtaining phonetic feature to be identified, can respectively in phonetic feature to be identified happiness, indignation,
Sad, tired peace of making an uproar waits mood to be confirmed quietly and carries out the calculating of mood score, obtains the different corresponding moods of mood to be confirmed and obtains
Point.It is smaller using the Emotion identification model computation complexity based on vector machine, final result can be determined according to a small number of supporting vectors,
Facilitate the sample that grasps the key link in the training process, reject redundant samples, there is preferable robustness.
S472: the mood score carried to mood to be confirmed calculates, and obtains Emotion identification result.
Wherein, Emotion identification result refers to that the mood score carried to mood to be confirmed calculates, and acquisition can be indicated finally
The result of overdue client mood when by collection.Specifically, it is obtained in the mood for obtaining mood to be confirmed different in call voice
After point, Emotion identification model can the mood score that carries of more each mood to be confirmed, by the maximum mood to be confirmed of mood score
It is exported as final Emotion identification result.Intelligent collection system can be by the Emotion identification result and corresponding overdue customer information
It is sent to operator attendance, electricity is carried out to overdue client using suitable collection strategy according to Emotion identification result convenient for operator attendance
Words are linked up.
Step S471- step S472, phonetic feature to be identified is input in Emotion identification model, voice to be identified is obtained
The corresponding mood to be confirmed of feature；According to the mood score that mood to be confirmed carries, the Emotion identification result of overdue client is obtained.
Intelligent decision is carried out by mood of the Emotion identification model to overdue client, the accuracy of Emotion identification is improved and judges speed,
Operator attendance is facilitated to carry out telephonic communication to overdue client using suitable collection strategy according to Emotion identification result.
In overdue bill intelligence collection method provided by the embodiment of the present invention, first by collection rule to original case
Screened, will not meet collection rule original case delete, obtain meet collection rule enter to urge case.Then according to intelligence
The energy pre-set customer risk grade classification strategy of collection system divides the overdue customer information for entering to urge case, obtains
The corresponding overdue client's list of the overdue customer type of difference facilitates the subsequent overdue customer types of difference that are directed to using different collections
It talks about art and overdue client carries out telephonic communication.It is obtained and overdue type then according to the overdue type identification in overdue client's list
Corresponding collection words art template and overdue customer information are identified, art is talked about in the target collection generated for specific overdue client, is passed through
The auto dialing technology of telephony platform carries out phone collection to overdue client, obtains overdue collection as a result, determining that overdue client is
It is no to have refund wish, collection working efficiency is improved, collection cost is reduced.If carrying agreement mark in overdue collection result,
Efficient income information is sent to the terminal device of overdue client；If being carried in overdue collection result and disagreeing mark, to exceeding
The call voice of phase client carries out Application on Voiceprint Recognition and Emotion identification, and Emotion identification result is finally fed back to operator attendance, so that
Operator attendance carries out phone collection to overdue client according to Emotion identification result, reduces because collection strategy use is improper and causes visitor
The rate of complaints that family is complained.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of overdue bill intelligence collection device is provided, the overdue bill intelligence collection device with it is upper
Overdue bill intelligence collection method in embodiment is stated to correspond.As shown in figure 9, this can only be urged, to search device include into urging case to obtain
Modulus block 10, overdue client's list obtain module 20, target collection words art obtains module 30 and overdue collection result acquisition module
40.Detailed description are as follows for each functional module:
Enter to urge case to obtain module 10 to obtain into case is urged, enter for screening original case according to collection rule
Case is urged to carry overdue customer information, overdue customer information includes the telephone number of overdue client.
Overdue client's list obtains module 20, for according to customer risk grade classification strategy to the overdue visitor for entering to urge case
Family information is divided, and obtains overdue client's list, overdue client's list include overdue customer information and with overdue customer information
Corresponding overdue type identification.
Target collection talks about art and obtains module 30, talks about art template for obtaining collection corresponding with overdue type identification, will
Overdue customer information is added to the corresponding position of collection words art template, obtains target collection and talks about art.
Overdue collection result obtains module 40, and for calling telephony platform, the telephone number of the overdue client of automatically dial is simultaneously
Target collection words art is converted into target collection voice, obtains overdue client to the overdue collection knot of target collection voice feedback
Fruit.
Further, it includes Automatic Dialing Unit 41, target voice acquisition transmission list that overdue collection result, which obtains module 40,
Member 42 and overdue collection result acquiring unit 43.
Automatic Dialing Unit 41 calls telephony platform to the connection of overdue client for the telephone number based on overdue client
It is that phone carries out auto dialing.
Target voice obtains transmission unit 42, for obtaining the connection signal of the corresponding terminal device feedback of telephone number,
Based on signal is connected, target collection words art is converted to by corresponding target collection voice using TTS technology, by target collection voice
It is sent to terminal device.
Overdue collection result acquiring unit 43 carries out call voice for the call voice of receiving terminal apparatus feedback
Semantic analysis obtains overdue collection result.
Further, overdue collection result acquiring unit 43 includes target keyword judging unit 431, the first overdue collection
As a result acquiring unit 432 and the second overdue collection result acquiring unit 433.
Target keyword judging unit 431 judges whether call voice includes preparatory for being scanned to call voice
The target keyword of setting.
First overdue collection result acquiring unit 432, if acquisition is taken for including target keyword in call voice
With the overdue collection result for agreeing to mark.
Second overdue collection result acquiring unit 433 obtains if having target keyword for not including in call voice
Carry the overdue collection result for disagreeing mark.
It further, further include the email address of overdue client in overdue client's list, the overdue bill intelligence collection dress
Set further includes that efficient income information acquisition unit 44, efficient income information transmitting unit 45, Application on Voiceprint Recognition unit 46 and mood are known
Other unit 47.
Efficient income information acquisition unit 44 is believed if carrying agreement mark for overdue collection result based on collection
Template and overdue customer information are ceased, efficient income information is obtained.
Efficient income information transmitting unit 45, for by the telephone number of overdue client or exceeding efficient income information
The email address of phase client is sent to corresponding terminal device.
Application on Voiceprint Recognition unit 46 carries out vocal print to call voice if disagreeing mark for the carrying of overdue collection result
Identification, determines whether the speaker of call voice is overdue client itself.
Emotion identification unit 47, if the artificial overdue client itself of speaking for call voice, is called pre-stored
Emotion identification model carries out Emotion identification to call voice, obtains Emotion identification result corresponding with overdue collection result.
Further, Application on Voiceprint Recognition unit 46 includes call voice unit 461 to be processed, speech feature extraction unit 462
With vocal print identification model judging unit 463.
Call voice unit 461 to be processed obtains voice to be identified for pre-processing to call voice.
Speech feature extraction unit 462 obtains voice pair to be identified for carrying out speech feature extraction to voice to be identified
The phonetic feature to be identified answered.
Sound-groove model judging unit 463, for using Application on Voiceprint Recognition model to phonetic feature to be identified and overdue client couple
The raw tone feature answered carries out Application on Voiceprint Recognition, determines whether the speaker of call voice is overdue client itself.
Further, Emotion identification unit 47 includes that Emotion identification model judging unit 471 and Emotion identification result obtain
Unit 472.
Emotion identification model judging unit 471 is obtained for phonetic feature to be identified to be input in Emotion identification model
The corresponding mood to be confirmed of phonetic feature to be identified, mood carrying to be confirmed are in a bad mood score.
Emotion identification result acquiring unit 472, the mood score for carrying to mood to be confirmed calculate, and obtain feelings
Thread recognition result.
Specific restriction about overdue bill intelligence collection device may refer to above for overdue bill intelligence collection
The restriction of method, details are not described herein.Modules in above-mentioned overdue bill intelligence collection device can be fully or partially through
Software, hardware and combinations thereof are realized.Above-mentioned each module can be embedded in the form of hardware or independently of the place in computer equipment
It manages in device, can also be stored in a software form in the memory in computer equipment, in order to which processor calls execution or more
The corresponding operation of modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 10.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data being related in overdue bill intelligence collection method.The network of the computer equipment connects
Mouth with external terminal by network connection for being communicated.To realize a kind of overdue account when the computer program is executed by processor
Single intelligence collection method.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor realize overdue bill in above-described embodiment when executing computer program
The step of intelligent collection method, such as step S10 shown in Fig. 2 to step S40.Alternatively, when processor executes computer program
Realize above-described embodiment in overdue bill intelligence collection device each module/unit function, such as module shown in Fig. 9 10 to
Module 40.To avoid repeating, which is not described herein again.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step of above-described embodiment overdue bill intelligence collection method, such as step shown in Fig. 2 when being executed by processor
Rapid S10 to step S40.Alternatively, realizing overdue bill intelligence collection in above-described embodiment when computer program is executed by processor
The function of each module/unit of device, such as module shown in Fig. 9 10 is to module 40.To avoid repeating, which is not described herein again.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of overdue bill intelligence collection method characterized by comprising
Original case is screened according to collection rule, is obtained into urging case, it is described to enter case is urged to carry overdue client's letter
Breath, the overdue customer information includes the telephone number of overdue client；
Enter the overdue customer information of case is urged to divide to described according to customer risk grade classification strategy, obtains overdue client
List, overdue client's list include overdue customer information and overdue type mark corresponding with the overdue customer information
Know；
Obtain collection corresponding with the overdue type identification and talk about art template, by the overdue customer information be added to described in urge
The corresponding position of words art template is received, target collection is obtained and talks about art；
Telephony platform is called, target collection words art is simultaneously converted into target collection by the telephone number of the overdue client of automatically dial
Voice obtains overdue client to the overdue collection result of the target collection voice feedback.
2. overdue bill intelligence collection method as described in claim 1, which is characterized in that the calling telephony platform, automatically
It puts through the telephone number of overdue client and target collection words art is converted into target collection voice, obtain overdue client to institute
State the overdue collection result of target collection voice feedback, comprising:
Based on the telephone number of the overdue client, telephony platform is called to pull out the telephone number of the overdue client automatically
Number；
The connection signal for obtaining the corresponding terminal device feedback of the telephone number, is based on the connection signal, using TTS technology
Target collection words art is converted to corresponding target collection voice, the target collection voice is sent to the terminal and is set
It is standby；
The call voice for receiving the terminal device feedback, carries out semantic analysis to the call voice, obtains overdue collection knot
Fruit.
3. overdue bill intelligence collection method as claimed in claim 2, which is characterized in that described to be carried out to the call voice
Semantic analysis obtains overdue collection result, comprising:
The call voice is scanned, judges whether the call voice includes pre-set target keyword；
If in the call voice including the target keyword, the overdue collection result for carrying and agreeing to mark is obtained；
If not including in the call voice has the target keyword, acquisition carries the overdue collection knot for disagreeing mark
Fruit.
4. overdue bill intelligence collection method as described in claim 1, which is characterized in that also wrapped in overdue client's list
Include the email address of overdue client；
After the acquisition overdue collection result the step of, the overdue bill intelligence collection method further include:
If the overdue collection result carries agreement mark, had based on collection information model and overdue customer information, acquisition
Imitate collection information；
Efficient income information is sent to correspondence by the telephone number of the overdue client or the email address of overdue client
Terminal device.
5. overdue bill intelligence collection method as described in claim 1, which is characterized in that obtain overdue collection result described
The step of after, the overdue bill intelligence collection method further include:
If the overdue collection result carrying disagrees mark, Application on Voiceprint Recognition is carried out to the call voice, is determined described logical
Whether the speaker of language sound is overdue client itself；
If the artificial overdue client itself of speaking of the call voice, calls pre-stored Emotion identification model to described logical
Language sound carries out Emotion identification, obtains Emotion identification result corresponding with the overdue collection result.
6. overdue bill intelligence collection method as claimed in claim 5, which is characterized in that described to be carried out to the call voice
Application on Voiceprint Recognition determines whether the speaker of the call voice is overdue client itself, comprising:
The call voice is pre-processed, voice to be identified is obtained；
Speech feature extraction is carried out to the voice to be identified, obtains the corresponding phonetic feature to be identified of the voice to be identified；
The phonetic feature to be identified and the corresponding raw tone feature of the overdue client are carried out using Application on Voiceprint Recognition model
Application on Voiceprint Recognition determines whether the speaker of the call voice is overdue client itself.
7. such as overdue bill intelligence collection method described in claim 5 or 6, which is characterized in that the calling is pre-stored
Emotion identification model carries out Emotion identification to the call voice, obtains Emotion identification corresponding with the overdue collection result
As a result, comprising:
The phonetic feature to be identified is input in the Emotion identification model, it is corresponding to obtain the phonetic feature to be identified
Mood to be confirmed, the mood to be confirmed carry score of being in a bad mood；
The mood score carried to the mood to be confirmed calculates, and obtains Emotion identification result.
8. a kind of overdue bill intelligence collection device characterized by comprising
Enter to urge case to obtain module, for being screened according to collection rule to original case, obtains into urging case, it is described to enter to urge
Case carries overdue customer information, and the overdue customer information includes the telephone number of overdue client；
Overdue client's list obtains module, for entering to urge the overdue client of case to described according to customer risk grade classification strategy
Information is divided, and obtains overdue client's list, overdue client's list include overdue customer information and with the overdue visitor
The corresponding overdue type identification of family information；
Target collection talks about art and obtains module, for obtaining collection words art template corresponding with the overdue type identification, by institute
It states overdue customer information and is added to the corresponding position of the collection words art template, obtain target collection and talk about art；
Overdue collection result obtains module, and for calling telephony platform, the telephone number of the overdue client of automatically dial simultaneously will be described
Target collection words art is converted into target collection voice, obtains overdue client to the overdue collection knot of the target collection voice feedback
Fruit.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The step of any one of 7 overdue bill intelligence collection method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization overdue bill intelligence collection side as described in any one of claim 1 to 7 when the computer program is executed by processor
The step of method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810870736.2A CN109064315A (en) | 2018-08-02 | 2018-08-02 | Overdue bill intelligence collection method, apparatus, computer equipment and storage medium |
| PCT/CN2018/106251 WO2020024389A1 (en) | 2018-08-02 | 2018-09-18 | Method for collecting overdue payment, device, computer apparatus, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810870736.2A CN109064315A (en) | 2018-08-02 | 2018-08-02 | Overdue bill intelligence collection method, apparatus, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109064315A true CN109064315A (en) | 2018-12-21 |
Family
ID=64832876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810870736.2A Pending CN109064315A (en) | 2018-08-02 | 2018-08-02 | Overdue bill intelligence collection method, apparatus, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109064315A (en) |
| WO (1) | WO2020024389A1 (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859032A (en) * | 2019-01-22 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Funds on account collection method, apparatus, equipment and storage medium based on intelligent sound |
| CN109858917A (en) * | 2019-02-13 | 2019-06-07 | 苏州意能通信息技术有限公司 | A kind of anti-fake system and its method based on artificial intelligence |
| CN109949805A (en) * | 2019-02-21 | 2019-06-28 | 江苏苏宁银行股份有限公司 | Intelligent collection robot and collection method based on intention assessment and finite-state automata |
| CN110009480A (en) * | 2019-03-06 | 2019-07-12 | 平安科技（深圳）有限公司 | The recommended method in judicial collection path, device, medium, electronic equipment |
| CN110072201A (en) * | 2019-04-15 | 2019-07-30 | 平安科技（深圳）有限公司 | Note transmission method, device, computer equipment and storage medium |
| CN110084636A (en) * | 2019-03-19 | 2019-08-02 | 平安普惠企业管理有限公司 | Improve telemarketing efficiency method, device, computer equipment and storage medium |
| CN110166639A (en) * | 2019-04-15 | 2019-08-23 | 中国平安人寿保险股份有限公司 | Voice collection method, apparatus, computer equipment and storage medium |
| CN110265062A (en) * | 2019-06-13 | 2019-09-20 | 上海指旺信息科技有限公司 | Collection method and device after intelligence based on mood detection is borrowed |
| CN110264335A (en) * | 2019-05-16 | 2019-09-20 | 上海维信荟智金融科技有限公司 | Odd corpus electricity based on overdue number of days urges distribution method and system |
| CN110322899A (en) * | 2019-06-18 | 2019-10-11 | 平安银行股份有限公司 | User's intelligent method for classifying, server and storage medium |
| CN110336786A (en) * | 2019-05-23 | 2019-10-15 | 平安科技（深圳）有限公司 | Message method, device, computer equipment and storage medium |
| CN110362712A (en) * | 2019-06-18 | 2019-10-22 | 中国平安财产保险股份有限公司 | Continuity processing method, device, equipment and the medium of document data |
| CN110378575A (en) * | 2019-06-28 | 2019-10-25 | 上海上湖信息技术有限公司 | Overdue event returned money collection method and device, computer readable storage medium |
| CN110570295A (en) * | 2019-07-25 | 2019-12-13 | 深圳壹账通智能科技有限公司 | Resource collection method and device, computer equipment and storage medium |
| CN110782335A (en) * | 2019-09-19 | 2020-02-11 | 平安科技（深圳）有限公司 | Method, device and storage medium for processing credit data based on artificial intelligence |
| CN110807699A (en) * | 2019-10-12 | 2020-02-18 | 上海上湖信息技术有限公司 | Overdue event payment collection method and device and computer readable storage medium |
| CN110910231A (en) * | 2019-11-06 | 2020-03-24 | 上海百事通信息技术股份有限公司 | Debt clearing and collecting management platform |
| CN110929005A (en) * | 2019-10-18 | 2020-03-27 | 平安科技（深圳）有限公司 | Emotion analysis-based task follow-up method, device, equipment and storage medium |
| CN110991806A (en) * | 2019-11-06 | 2020-04-10 | 上海百事通信息技术股份有限公司 | Debt clearing and collecting management system |
| CN111028074A (en) * | 2019-12-06 | 2020-04-17 | 深圳乐信软件技术有限公司 | Overdue bill updating and inquiring method, system, server and storage medium |
| CN111192136A (en) * | 2019-12-24 | 2020-05-22 | 中信百信银行股份有限公司 | Credit service collection method and device, electronic equipment and storage medium |
| CN111199470A (en) * | 2019-12-12 | 2020-05-26 | 北京淇瑀信息科技有限公司 | Method and device for controlling post-loan management frequency and electronic equipment |
| CN111243605A (en) * | 2020-01-13 | 2020-06-05 | 北京三快在线科技有限公司 | Service processing method, device, equipment and storage medium |
| CN111260466A (en) * | 2020-01-20 | 2020-06-09 | 北京合信力科技有限公司 | Method and device for processing reach task |
| CN111294470A (en) * | 2020-02-05 | 2020-06-16 | 北京三快在线科技有限公司 | Call processing method, device, equipment and storage medium |
| CN111461505A (en) * | 2020-03-18 | 2020-07-28 | 黑龙江正泽信服务外包有限公司 | Artificial labeling system for intelligent matching of collection urging information |
| CN111833076A (en) * | 2020-07-07 | 2020-10-27 | 信雅达系统工程股份有限公司 | Intelligent collection system and method |
| CN111835926A (en) * | 2020-07-23 | 2020-10-27 | 中国平安财产保险股份有限公司 | Intelligent voice outbound method, device, equipment and medium based on voice interaction |
| CN112217877A (en) * | 2020-09-23 | 2021-01-12 | 上海维信荟智金融科技有限公司 | Micro-service architecture based collection and case allocation method and system |
| CN112435117A (en) * | 2020-11-27 | 2021-03-02 | 平安普惠企业管理有限公司 | Loan overdue case collection method and device, electronic equipment and storage medium |
| CN113284497A (en) * | 2020-12-31 | 2021-08-20 | 一汽资本控股有限公司 | Method and device for urging collection of customers and intelligent collection urging system |
| CN113824828A (en) * | 2021-10-29 | 2021-12-21 | 平安普惠企业管理有限公司 | Dialing method and device, electronic equipment and computer readable storage medium |
| CN116341879A (en) * | 2023-05-26 | 2023-06-27 | 杭州度言软件有限公司 | Overdue asset collection intelligent case division method and system |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738824A (en) * | 2020-06-16 | 2020-10-02 | 中国建设银行股份有限公司 | Method, device and system for screening financial data processing modes |
| CN112053097A (en) * | 2020-09-30 | 2020-12-08 | 北京百度网讯科技有限公司 | Loan collection method and device, electronic equipment and storage medium |
| CN113159901A (en) * | 2021-04-29 | 2021-07-23 | 天津狮拓信息技术有限公司 | Method and device for realizing financing lease service session |
| CN113343058B (en) * | 2021-05-31 | 2024-02-27 | 璟滔信息科技(昆山)有限公司 | Voice session supervision method, device, computer equipment and storage medium |
| CN113657901B (en) * | 2021-07-23 | 2024-04-16 | 上海钧正网络科技有限公司 | Method, system, terminal and medium for managing fee owed users |
| CN113724065B (en) * | 2021-08-31 | 2023-12-29 | 华道数据处理(苏州)有限公司 | Auxiliary collecting method, device, equipment and storage medium based on flow guidance |
| CN116452323B (en) * | 2023-04-28 | 2024-01-30 | 广州市良策网络技术有限公司 | Risk assessment method, system, equipment and storage medium |
| CN117319559B (en) * | 2023-11-24 | 2024-02-02 | 杭州度言软件有限公司 | Method and system for prompting receipt based on intelligent voice robot |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106572067A (en) * | 2015-10-12 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Voice flow transmission method and system |
| CN106683672A (en) * | 2016-12-21 | 2017-05-17 | 竹间智能科技（上海）有限公司 | Intelligent dialogue method and system based on emotion and semantics |
| CN107240013A (en) * | 2017-04-19 | 2017-10-10 | 中国建设银行股份有限公司 | The method and apparatus that a kind of credit card collection is refunded |
| CN108090826A (en) * | 2017-11-13 | 2018-05-29 | 平安科技（深圳）有限公司 | A kind of phone collection method and terminal device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7747695B1 (en) * | 2007-10-29 | 2010-06-29 | West Corporation | System, method and computer readable medium for providing notifications |
| CN107194807A (en) * | 2017-06-29 | 2017-09-22 | 喀什博雅成信网络科技有限公司 | The intelligent collection system and method for one kind loan |
| CN107507088A (en) * | 2017-08-29 | 2017-12-22 | 深圳市佰仟金融服务有限公司 | Collection management method and server |
-
2018
- 2018-08-02 CN CN201810870736.2A patent/CN109064315A/en active Pending
- 2018-09-18 WO PCT/CN2018/106251 patent/WO2020024389A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106572067A (en) * | 2015-10-12 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Voice flow transmission method and system |
| CN106683672A (en) * | 2016-12-21 | 2017-05-17 | 竹间智能科技（上海）有限公司 | Intelligent dialogue method and system based on emotion and semantics |
| CN107240013A (en) * | 2017-04-19 | 2017-10-10 | 中国建设银行股份有限公司 | The method and apparatus that a kind of credit card collection is refunded |
| CN108090826A (en) * | 2017-11-13 | 2018-05-29 | 平安科技（深圳）有限公司 | A kind of phone collection method and terminal device |
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859032A (en) * | 2019-01-22 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Funds on account collection method, apparatus, equipment and storage medium based on intelligent sound |
| CN109858917A (en) * | 2019-02-13 | 2019-06-07 | 苏州意能通信息技术有限公司 | A kind of anti-fake system and its method based on artificial intelligence |
| CN109949805B (en) * | 2019-02-21 | 2021-03-23 | 江苏苏宁银行股份有限公司 | Intelligent collection urging robot based on intention recognition and finite state automaton and collection urging method |
| CN109949805A (en) * | 2019-02-21 | 2019-06-28 | 江苏苏宁银行股份有限公司 | Intelligent collection robot and collection method based on intention assessment and finite-state automata |
| CN110009480A (en) * | 2019-03-06 | 2019-07-12 | 平安科技（深圳）有限公司 | The recommended method in judicial collection path, device, medium, electronic equipment |
| CN110084636A (en) * | 2019-03-19 | 2019-08-02 | 平安普惠企业管理有限公司 | Improve telemarketing efficiency method, device, computer equipment and storage medium |
| CN110072201A (en) * | 2019-04-15 | 2019-07-30 | 平安科技（深圳）有限公司 | Note transmission method, device, computer equipment and storage medium |
| CN110166639A (en) * | 2019-04-15 | 2019-08-23 | 中国平安人寿保险股份有限公司 | Voice collection method, apparatus, computer equipment and storage medium |
| CN110072201B (en) * | 2019-04-15 | 2022-02-15 | 平安科技（深圳）有限公司 | Short message sending method and device, computer equipment and storage medium |
| CN110264335A (en) * | 2019-05-16 | 2019-09-20 | 上海维信荟智金融科技有限公司 | Odd corpus electricity based on overdue number of days urges distribution method and system |
| CN110336786A (en) * | 2019-05-23 | 2019-10-15 | 平安科技（深圳）有限公司 | Message method, device, computer equipment and storage medium |
| CN110336786B (en) * | 2019-05-23 | 2022-02-11 | 平安科技（深圳）有限公司 | Message sending method, device, computer equipment and storage medium |
| CN110265062A (en) * | 2019-06-13 | 2019-09-20 | 上海指旺信息科技有限公司 | Collection method and device after intelligence based on mood detection is borrowed |
| CN110362712A (en) * | 2019-06-18 | 2019-10-22 | 中国平安财产保险股份有限公司 | Continuity processing method, device, equipment and the medium of document data |
| CN110322899A (en) * | 2019-06-18 | 2019-10-11 | 平安银行股份有限公司 | User's intelligent method for classifying, server and storage medium |
| CN110322899B (en) * | 2019-06-18 | 2023-09-22 | 平安银行股份有限公司 | User intelligent classification method, server and storage medium |
| CN110378575A (en) * | 2019-06-28 | 2019-10-25 | 上海上湖信息技术有限公司 | Overdue event returned money collection method and device, computer readable storage medium |
| CN110378575B (en) * | 2019-06-28 | 2022-04-01 | 上海上湖信息技术有限公司 | Overdue event refund collection method and device and computer readable storage medium |
| CN110570295A (en) * | 2019-07-25 | 2019-12-13 | 深圳壹账通智能科技有限公司 | Resource collection method and device, computer equipment and storage medium |
| CN110782335A (en) * | 2019-09-19 | 2020-02-11 | 平安科技（深圳）有限公司 | Method, device and storage medium for processing credit data based on artificial intelligence |
| CN110782335B (en) * | 2019-09-19 | 2023-08-15 | 平安科技（深圳）有限公司 | Method, device and storage medium for processing credit data based on artificial intelligence |
| WO2021051592A1 (en) * | 2019-09-19 | 2021-03-25 | 平安科技（深圳）有限公司 | Method, device, and storage medium for processing data on basis of artificial intelligence |
| CN110807699B (en) * | 2019-10-12 | 2022-06-03 | 上海上湖信息技术有限公司 | Overdue event payment collection method and device and computer readable storage medium |
| CN110807699A (en) * | 2019-10-12 | 2020-02-18 | 上海上湖信息技术有限公司 | Overdue event payment collection method and device and computer readable storage medium |
| CN110929005A (en) * | 2019-10-18 | 2020-03-27 | 平安科技（深圳）有限公司 | Emotion analysis-based task follow-up method, device, equipment and storage medium |
| CN110991806A (en) * | 2019-11-06 | 2020-04-10 | 上海百事通信息技术股份有限公司 | Debt clearing and collecting management system |
| CN110910231A (en) * | 2019-11-06 | 2020-03-24 | 上海百事通信息技术股份有限公司 | Debt clearing and collecting management platform |
| CN111028074A (en) * | 2019-12-06 | 2020-04-17 | 深圳乐信软件技术有限公司 | Overdue bill updating and inquiring method, system, server and storage medium |
| CN111028074B (en) * | 2019-12-06 | 2024-03-19 | 深圳乐信软件技术有限公司 | Method, system, server and storage medium for updating and inquiring overdue bill |
| CN111199470A (en) * | 2019-12-12 | 2020-05-26 | 北京淇瑀信息科技有限公司 | Method and device for controlling post-loan management frequency and electronic equipment |
| CN111192136A (en) * | 2019-12-24 | 2020-05-22 | 中信百信银行股份有限公司 | Credit service collection method and device, electronic equipment and storage medium |
| CN111243605A (en) * | 2020-01-13 | 2020-06-05 | 北京三快在线科技有限公司 | Service processing method, device, equipment and storage medium |
| CN111260466A (en) * | 2020-01-20 | 2020-06-09 | 北京合信力科技有限公司 | Method and device for processing reach task |
| CN111294470B (en) * | 2020-02-05 | 2021-06-29 | 北京三快在线科技有限公司 | Call processing method, device, equipment and storage medium |
| CN111294470A (en) * | 2020-02-05 | 2020-06-16 | 北京三快在线科技有限公司 | Call processing method, device, equipment and storage medium |
| CN111461505A (en) * | 2020-03-18 | 2020-07-28 | 黑龙江正泽信服务外包有限公司 | Artificial labeling system for intelligent matching of collection urging information |
| CN111833076A (en) * | 2020-07-07 | 2020-10-27 | 信雅达系统工程股份有限公司 | Intelligent collection system and method |
| CN111835926A (en) * | 2020-07-23 | 2020-10-27 | 中国平安财产保险股份有限公司 | Intelligent voice outbound method, device, equipment and medium based on voice interaction |
| CN112217877A (en) * | 2020-09-23 | 2021-01-12 | 上海维信荟智金融科技有限公司 | Micro-service architecture based collection and case allocation method and system |
| CN112435117A (en) * | 2020-11-27 | 2021-03-02 | 平安普惠企业管理有限公司 | Loan overdue case collection method and device, electronic equipment and storage medium |
| CN113284497A (en) * | 2020-12-31 | 2021-08-20 | 一汽资本控股有限公司 | Method and device for urging collection of customers and intelligent collection urging system |
| CN113824828A (en) * | 2021-10-29 | 2021-12-21 | 平安普惠企业管理有限公司 | Dialing method and device, electronic equipment and computer readable storage medium |
| CN113824828B (en) * | 2021-10-29 | 2024-03-08 | 河北科燃信息科技股份有限公司 | Dialing method and device, electronic equipment and computer readable storage medium |
| CN116341879A (en) * | 2023-05-26 | 2023-06-27 | 杭州度言软件有限公司 | Overdue asset collection intelligent case division method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020024389A1 (en) | 2020-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109064315A (en) | Overdue bill intelligence collection method, apparatus, computer equipment and storage medium | |
| CN109949805B (en) | Intelligent collection urging robot based on intention recognition and finite state automaton and collection urging method | |
| CN111028827B (en) | Interaction processing method, device, equipment and storage medium based on emotion recognition | |
| US10249304B2 (en) | Method and system for using conversational biometrics and speaker identification/verification to filter voice streams | |
| US10057419B2 (en) | Intelligent call screening | |
| WO2021051506A1 (en) | Voice interaction method and apparatus, computer device and storage medium | |
| US7805310B2 (en) | Apparatus and methods for implementing voice enabling applications in a converged voice and data network environment | |
| CN112202978A (en) | Intelligent outbound call system, method, computer system and storage medium | |
| CN107818798A (en) | Customer service quality evaluating method, device, equipment and storage medium | |
| CN109429523A (en) | Speaker verification method, apparatus and system | |
| CN105206269A (en) | Voice processing method and device | |
| CH709795A1 (en) | Method and filter system of unwanted incoming phone calls. | |
| CN104185868A (en) | Voice authentication and speech recognition system and method | |
| CN111696558A (en) | Intelligent outbound method, device, computer equipment and storage medium | |
| CN112131358A (en) | Scene flow structure and intelligent customer service system applied by same | |
| CN110766442A (en) | Client information verification method, device, computer equipment and storage medium | |
| CN112487381A (en) | Identity authentication method and device, electronic equipment and readable storage medium | |
| CN108364638A (en) | A kind of voice data processing method, device, electronic equipment and storage medium | |
| CN111263016A (en) | Communication assistance method, communication assistance device, computer equipment and computer-readable storage medium | |
| CN113779217A (en) | Intelligent voice outbound service method and system based on human-computer interaction | |
| CN109858917A (en) | A kind of anti-fake system and its method based on artificial intelligence | |
| US9875236B2 (en) | Analysis object determination device and analysis object determination method | |
| CN113744742A (en) | Role identification method, device and system in conversation scene | |
| CN111833907A (en) | Man-machine interaction method, terminal and computer readable storage medium | |
| CN110472007A (en) | Information-pushing method, device, equipment and storage medium |
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 |