CN107800894A - A kind of phonetic prompt method and terminal device for telephony service system - Google Patents

A kind of phonetic prompt method and terminal device for telephony service system Download PDF

Info

Publication number
CN107800894A
CN107800894A CN201711037115.8A CN201711037115A CN107800894A CN 107800894 A CN107800894 A CN 107800894A CN 201711037115 A CN201711037115 A CN 201711037115A CN 107800894 A CN107800894 A CN 107800894A
Authority
CN
China
Prior art keywords
insurance
factor
prompting
classes
data
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.)
Granted
Application number
CN201711037115.8A
Other languages
Chinese (zh)
Other versions
CN107800894B (en
Inventor
彭小明
李培彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN201711037115.8A priority Critical patent/CN107800894B/en
Priority to PCT/CN2017/112903 priority patent/WO2019085095A1/en
Publication of CN107800894A publication Critical patent/CN107800894A/en
Application granted granted Critical
Publication of CN107800894B publication Critical patent/CN107800894B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/42025—Calling or Called party identification service
    • H04M3/42034—Calling party identification service
    • H04M3/42059—Making use of the calling party identifier
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
    • H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
    • H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
    • H04M3/4936—Speech interaction details
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/527—Centralised call answering arrangements not requiring operator intervention

Abstract

The invention provides a kind of intelligent voice prompt method and terminal device, suitable for technical field of data processing, this method includes：Destination object telephone number is obtained, and identifies insure insurance kind and the affiliated insurance type insured；By record data, insurance kind of insuring and insure the node date, factor screening model corresponding to input to insurance type, draw the class prompting factor corresponding to insurance type difference；If obtained total factor quantity is less than or equal to setting factor beforehand quantity, the speech data for reading out each prompting factor in the prompting factor is reported；If total factor quantity is more than setting factor beforehand quantity, the prompting factor of relative importance value highest setting factor beforehand quantity is filtered out, then the speech data of the prompting factor filtered out is reported.While ensure that the prompting factor of final output is that destination object is actually required, is not in report excessive situation again, drastically increases the intelligence degree that intelligent voice system is handled telephone service.

Description

A kind of phonetic prompt method and terminal device for telephony service system
Technical field
The invention belongs to technical field of data processing, more particularly to intelligent voice prompt method and terminal device.
Background technology
Existing intelligent voice system can at least include welcome words and one when carrying out the telephone service processing of client The voice menu of rank, each voice menu can at least include a specific business service again.It is each by voice broadcast successively The business service of level speech menu, prompt and guide client to operate business service accordingly, and according to incoming call client Operation jump to corresponding business service and responded, to meet the needs of client is to business service.
However as business event quantity, type continuous growth with refinement so that the structure of intelligent voice system and Comprising content also become increasingly complex with it is huge.After caller client, business is carried out under the guiding of existing intelligent voice system Services selection with during operation, it is necessary to which to expend a large amount of useless waiting times non-needed for oneself to wait intelligent voice system to report Business service so that client can not timely get the business service needed for oneself, while can cause the electricity to each client Call business processing time is all longer, adds the operating load of intelligent voice system.
To sum up, existing intelligent voice system intelligence degree when carrying out the telephone service processing of client is low, can not The business service needed for it is provided the user in time.
The content of the invention
In view of this, it is existing to solve the embodiments of the invention provide a kind of intelligent voice prompt method and terminal device The problem of intelligence degree that intelligent voice system is handled telephone service in technology is low.
The first aspect of the embodiment of the present invention provides a kind of intelligent voice prompt method, including：
The telephone number of call opposite end destination object is obtained, client is carried out to the destination object using the telephone number Attribute data matches, and reads the insurance mark and record data in the client properties data matched；To institute State insurance mark to be parsed, identify that M kinds that the destination object has been insured insure insurance kind and the M kinds are insured insurance kind institute The N classes insurance type of category, and the insurance node date corresponding to the insurance mark is read out, wherein M, N is whole more than zero Number；
By the record data, it is described insure insurance kind and it is described insurance the node date, input to the N classes insure Factor screening model corresponding to type, prompting factor screening is carried out respectively to insuring type described in N classes, draw the N classes insurance The N1 classes prompting factor corresponding to type difference, wherein, the prompting factor is used to represent the required business service played, and N1 is big In zero, the integer less than or equal to M；
Total factor quantity statistics is carried out to the obtained N1 classes prompting factor；If total factor quantity is less than or equal to setting factor beforehand Quantity, the speech data of each prompting factor in the N1 classes prompting factor is read out, it is right using default voice message template The speech data read out carries out voice joint, and the voice joint is obtained into prompting voice data and sent to call pair The client terminal at end is reported；
If total factor quantity is more than setting factor beforehand quantity, the N1 classes are prompted in the factor using the record data All prompting factors carry out priority ordered, filter out the prompting of setting factor beforehand number of bits before relative importance value highest because Son, and speech data corresponding to reading, using the default voice message template to described in the corresponding speech data progress Voice joint, and by the voice joint obtain prompting voice data send to call opposite end client terminal reported.
The second aspect of the embodiment of the present invention provides a kind of intelligent voice prompt terminal device, the intelligent voice prompt Terminal device includes memory, processor, and the computer program that can be run on the processor is stored with the memory, Described in the computing device following steps are realized during computer program.
The telephone number of call opposite end destination object is obtained, client is carried out to the destination object using the telephone number Attribute data matches, and reads the insurance mark and record data in the client properties data matched；To institute State insurance mark to be parsed, identify that M kinds that the destination object has been insured insure insurance kind and the M kinds are insured insurance kind institute The N classes insurance type of category, and the insurance node date corresponding to the insurance mark is read out, wherein M, N is whole more than zero Number；
By the record data, it is described insure insurance kind and it is described insurance the node date, input to the N classes insure Factor screening model corresponding to type, prompting factor screening is carried out respectively to insuring type described in N classes, draw the N classes insurance The N1 classes prompting factor corresponding to type difference, wherein, the prompting factor is used to represent the required business service played, and N1 is big In zero, the integer less than or equal to M；
Total factor quantity statistics is carried out to the obtained N1 classes prompting factor；If total factor quantity is less than or equal to setting factor beforehand Quantity, the speech data of each prompting factor in the N1 classes prompting factor is read out, it is right using default voice message template The speech data read out carries out voice joint, and the voice joint is obtained into prompting voice data and sent to call pair The client terminal at end is reported；
If total factor quantity is more than setting factor beforehand quantity, the N1 classes are prompted in the factor using the record data All prompting factors carry out priority ordered, filter out the prompting of setting factor beforehand number of bits before relative importance value highest because Son, and speech data corresponding to reading, using the default voice message template to described in the corresponding speech data progress Voice joint, and by the voice joint obtain prompting voice data send to call opposite end client terminal reported.
The third aspect of the embodiment of the present invention provides a kind of computer-readable recording medium, including：It is stored with computer Program, it is characterised in that the computer program realizes intelligent voice prompt method as described above when being executed by processor Step.
Existing beneficial effect is the embodiment of the present invention compared with prior art：Pass through the telephone number matches of destination object The record data of destination object, insurance kind of insuring, insurance node date and the insurance type insured are determined, and utilizes and carries These data and factor screening model taken out are analyzed the situation of insuring of destination object, realize and system is included The prompting factor screening, so as to ensure that the prompting factor finally given is the business service needed for destination object.Finally Predetermined number judgement is carried out to the obtained prompting factor, and priority ordered screening is carried out when beyond predetermined number, so as to protect Having demonstrate,proved the prompting factor quantity finally given will not be excessive, and is all the destination object demand possibility highest prompting factor.Cause This, the embodiment of the present invention is not in again while ensure that the prompting factor of final output is that destination object is actually required Excessive situation is reported, drastically increases the intelligence degree that intelligent voice system is handled telephone service so that target pair As in telephony access intelligent voice system, it is possible to obtain timely and effectively business service voice broadcast.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art In the required accompanying drawing used be briefly described, it should be apparent that, drawings in the following description be only the present invention some Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these Accompanying drawing obtains other accompanying drawings.
Fig. 1 is the implementation process schematic diagram for the intelligent voice prompt method that the embodiment of the present invention one provides；
Fig. 2 is the implementation process schematic diagram for the intelligent voice prompt method that the embodiment of the present invention two provides；
Fig. 3 is the implementation process schematic diagram for the intelligent voice prompt method that the embodiment of the present invention three provides；
Fig. 4 is the implementation process schematic diagram for the intelligent voice prompt method that the embodiment of the present invention four provides；
Fig. 5 is the implementation process schematic diagram for the intelligent voice prompt method that the embodiment of the present invention five provides；
Fig. 6 is the structural representation for the Intelligent voice prompting device that the embodiment of the present invention six provides；
Fig. 7 is the schematic diagram for the intelligent voice prompt terminal device that the embodiment of the present invention seven provides.
Embodiment
In describing below, in order to illustrate rather than in order to limit, it is proposed that such as tool of particular system structure, technology etc Body details, thoroughly to understand the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific The present invention can also be realized in the other embodiments of details.In other situations, omit to well-known system, device, electricity Road and the detailed description of method, in case unnecessary details hinders description of the invention.
In order to illustrate technical solutions according to the invention, illustrated below by specific embodiment.
Fig. 1 shows the implementation process figure for the intelligent voice prompt method that the embodiment of the present invention one provides, and details are as follows：
S101, the telephone number of call opposite end destination object is obtained, client's category is carried out to destination object using telephone number Property Data Matching, and read the insurance mark and record data in the client properties data that match.Insurance is identified Parsed, identify that M kinds that destination object has been insured are insured the N classes insurance type that insurance kind and M kinds are insured belonging to insurance kind, and The insurance node date corresponding to insurance mark is read out, wherein M, N is the integer more than zero.
Wherein, destination object refers to the terminal device access intelligent voice system that use can call, with intelligent sound The user (client i.e. in the embodiment of the present invention) that system is conversed.Client properties data include but is not limited to：Client buys All related datas (the declaration form data for all insurances such as bought) for the insurance crossed, client are carried out by intelligent voice system The record data for the business service crossed and the personal information (such as telephone number and name) of client.Insurance mark is used In the insurance kind that record client specifically buys.Record data, history corresponding to the business handled for recording customer phone Operation data, the vehicle insurance handled such as customer phone report a case to the security authorities and the business such as case progress queries corresponding to historical operating data. Wherein, these historical operating datas can be stored in the form of identifying between the added-time, as long as the i.e. mark containing some business, Then illustrate that customer phone handled this business, while pass through the time corresponding to mark, it may be determined that go out client and handle the business Time, as vehicle insurance that customer phone is carried out report a case to the security authorities operation when, one vehicle insurance of record is reported a case to the security authorities mark and time for reporting a case to the security authorities of vehicle insurance To record data, to illustrate that user once carried out the business operation that vehicle insurance is reported a case to the security authorities at the time point of record.
Due to when client is insured, may require that the personal information of record client and the related data of purchase insurance, Meanwhile when client carries out business service operation using intelligent voice system, the operation data of client can also be recorded, obtained To record data, therefore, in embodiments of the present invention, client properties data are the numbers that has stored and can be directly obtained According to.Because client properties data are to be stored in specific data format (such as binary format) in storage medium, therefore, Record client's purchase it is specific insure insurance kind when, the data for insurance kind conversion corresponding data form of insuring can also be stored. In the embodiment of the present invention, before S101, the insurance kind of insuring of client can be converted to client properties data storage data form Insurance mark is stored, therefore, by identifying the insurance kind of insuring for carrying out data format parsing and can obtain client to insurance.By A variety of different insurance kinds may be bought in same client, therefore in embodiments of the present invention, the insurance mark of client can be same When correspond to a variety of different insurance kinds of insuring.
The principle for understanding insurance mark is further understood for the ease of reader, a kind of specific data as insurance mark are deposited Storage mode embodiment, illustrated so that client have purchased term life and vehicle loss danger simultaneously as an example, while assume client Attribute data is stored with binary data format.Because each insurance company can be set to the insurance kind that it is provided Corresponding unique code, such as the insurance kind code of term life can be arranged to 32, vehicle loss danger is arranged to 20, therefore, The insurance kind code table set by insurance company can determine that client buys insurance kind code corresponding to insurance kind, now can be by periodically Life insurance and vehicle loss danger corresponding to insurance kind code 32 and 20 be converted to corresponding to binary data 000001 and 00101, and stored as insurance mark data.Identify client insure species when, can read out insurance mark In 000001 and 00101, and translation resolution is carried out to it, obtains insurance kind code 32 and 20, then pass through insurance kind code table The specific insurance kind of insuring of client is determined in inquiry, so as to complete the resolving to insurance mark.
In S101, intelligent voice system, first can be by the telephone number of incoming call with depositing after caller client calling is received Telephone number in the client properties data of storage carries out contrast matching, and the visitor included with same phone number of sending a telegram here that will be found out Family attribute data is defined as the client properties data of incoming call client.Determine send a telegram here client client properties data and then Insurance mark and record data are read out from client properties data, by being parsed insurance mark to identify Insurance kind that what client had insured insure, and carry out insuring type using the insurance kind of insuring prestored-insurance type association data and look into Ask, determine the insurance type insured belonging to insurance kind that each client has insured.
As shown in the above description, each client may buy a variety of different insurance kinds, therefore in the embodiment of the present invention In M be integer more than 0, simultaneously as each insurance kind of insuring at least belongs to a kind of insurance type, and different insure Insurance kind can belong to same insurance type simultaneously again, and such as term life, share out bonus danger, universal life insurance and Investment-linked insurance belong to people After longevity insures type, therefore M and N actual size need to be inquired about according to insurance kind of insuring-insurance type association data of storage It is determined that but it is unquestionable, because each insurance kind of insuring at least belongs to a kind of insurance type, therefore N is whole more than 0 Number.
S102, by record data, insurance kind of insuring and insurance node date, input to N classes and insure corresponding to type Factor screening model, prompting factor screening is carried out respectively to N classes insurance type, draw N1 classes corresponding to N classes insurance type difference Prompt the factor, wherein, prompt the factor be used for represent needed for broadcasting business service, N1 be more than zero, it is whole less than or equal to M Number.
In embodiments of the present invention, prompt the factor to be used for the business service for representing required broadcasting, determine required report The prompting factor after, need to only read and report speech data corresponding to the prompting factor, you can complete report to business service.Cause Sub- screening model is used to carry out prompting factor screening to insurance type according to default screening rule, to obtain each insurance The prompting factor corresponding to type, wherein, screening rule corresponding to each insurance type all can be different, required to use Specific data also can difference, therefore, when carrying out prompting factor screening to each insurance type, be required for first according to should Screening rule corresponding to kind insurance type determines required data, then prompt the screening of the factor.
Specifically, get record data, insurance kind of insuring and after the insurance node date, factor screening model is first Screening rule corresponding to every kind of insurance type in N classes insurance type can be first found out, and according to needed for being determined screening rule Data, such as vehicle insurance type, whether it is to report a case to the security authorities for the first time in current vehicle insurance Effective Period of Insurance that it is needed according to client Rule carries out prompting factor screening, and the mark of reporting a case to the security authorities of the vehicle insurance in record data can be used for identifying whether client is to work as Number of reporting a case to the security authorities in preceding vehicle insurance Effective Period of Insurance, therefore, for vehicle insurance type, its data needed to use includes operation note number According to.After determining to insure the data needed for type, further according to screening rule, processing judgement is carried out to the data needed for these, The factor is prompted corresponding to every kind of insurance type (because the screening rule of every kind of insurance type is all complex, to prompting to draw The screening process of the factor is relatively complicated, therefore specific screening rule screening process is not described in detail in the embodiment of the present invention one, Referring in detail to the embodiment of the present invention two to the embodiment of the present invention four).
It should be understood that ground, due to every kind of insurance type subordinate insure insurance kind concrete condition can difference, such as people For longevity insurance type, it includes special insurance kind (such as share out bonus danger, universal life insurance and Investment-linked insurance) and no special insurance kind (as eventually Body life insurance, term life and endowment insurance etc.), and for the insurance kind of insuring of different situations, entered using same screening rule Row screening is more difficult.Therefore, in the embodiment of the present invention, can to insure type subordinate different concrete conditions insurance kind of insuring, Different screening rules is set, to obtain the prompting factor that every kind of concrete condition distinguishes unique corresponding types, therefore, in the present invention In embodiment, the type of the prompting factor that every kind of insurance type finally gives also can with comprising insurance kind of insuring different specific feelings Condition and it is different, i.e., after being screened using screening rule, it is every kind of insurance type may correspond to simultaneously multiclass difference The prompting factor.But it is specifically unique belonging to it for each insurance kind of specifically insuring, such as universal life insurance category In special insurance kind, i.e., the type of the prompting factor is unique corresponding to each specific insurance kind of insuring, therefore, of the invention real Apply in example, N1 is the integer less than or equal to M more than or equal to zero.Wherein, in order that factor screening model can identify exactly Go out the insurance kind concrete condition of insuring of every kind of insurance type subordinate, in the embodiment of the present invention, every kind of insurance type can all be deposited in advance What a is stored up to insure the inquiry tables of data of insurance kind concrete condition, such as life insurance type, it is special that what a can prestore Insurance kind table, by the inquiry tables of data, inquiry classification can be carried out to concrete condition corresponding to insurance kind of insuring, it is follow-up right to ensure The realization of the different screenings of different concrete conditions.
S103, total factor quantity statistics is carried out to the obtained N1 classes prompting factor.If total factor quantity is less than or equal to pre- If factor quantity, the speech data of each prompting factor in the N1 classes prompting factor is read out, using default voice message template, Voice joint is carried out to the speech data read out, and voice joint is obtained into prompting voice data and sent to the visitor of call opposite end Family terminal is reported.
Because each client insures insurance kind purchase situation difference, the number of the corresponding prompting factor finally screened Amount would also vary from, as some clients simply have purchased single insurance kind, what it was obtained after factor screening model discrimination carries Show that the quantity of the factor is typically less, and for some clients that have purchased a variety of different insurance kinds of insuring simultaneously, it is screened The quantity of the prompting factor finally given is typically more.Intelligent voice system carry out business service report when, if report Business service quantity is excessive, can equally expend client's substantial amounts of waiting time, increases the operating load of intelligent voice system.In order to The waiting time of client is reduced, reduces the operating load of intelligent voice system, the intelligence handled with the telephone service improved to client Can change degree, in the embodiment of the present invention, after the final N1 classes prompting factor is obtained, can count all prompting factors it is total because Quantum count, and judge whether its quantity exceeds setting factor beforehand quantity, if without departing from illustrating that current total factor quantity belongs to In acceptable report quantitative range, at this point it is possible to be reported to these prompting factors.
In the embodiment of the present invention, voice joint refers to carry out using default sound template and the speech data of the prompting factor Combination, to obtain needing the prompting voice data reported.
Further, a kind of preferred embodiment as the present invention, can preset a variety of different voice message templates, Used for choosing.Such as preset two voice message templates and be respectively：" XXXX (insurance companies are sent a telegraph in welcome to first template Name), would you please simply say the business handled required for you, such as：" XXXX is sent a telegraph in welcome, and may I ask you is for xx " and the second template Want xx", wherein xx is used to insert the prompting factor during voice joint.
Assuming that setting factor beforehand quantity is more than 3.It is such as " connection when the prompting factor quantity finally filtered out, which is more than 0, is less than 3 Setting loss person surveys in system ", " vehicle insurance is reported a case to the security authorities " and " revocation vehicle insurance report a case to the security authorities ", preferably the first template carries out voice joint, obtain as Lower prompting voice data：" XXXX (insurance company's name) is sent a telegraph in welcome, woulds you please simply say the business handled required for you, such as： Setting loss person is surveyed in contact, vehicle insurance is reported a case to the security authorities, cancels vehicle insurance reports a case to the security authorities ", and when the prompting factor quantity finally filtered out is 1, such as wrap Include as " vehicle insurance is reported a case to the security authorities ", now preferably the second template carries out voice joint, obtains following prompting voice data：" welcome is sent a telegraph XXXX, may I ask you is to want vehicle insurance to report a case to the security authorities", to improve voice message efficiency.
S104, if total factor quantity is more than setting factor beforehand quantity, N1 classes are prompted in the factor using record data All prompting factors carry out priority ordered, filter out the prompting factor of setting factor beforehand number of bits before relative importance value highest, and read Corresponding speech data is taken, voice joint is carried out to corresponding speech data using default voice message template, and voice is spelled Connect to obtain the client terminal that prompting voice data is sent to call opposite end to be reported.
When judging that total factor quantity is more than setting factor beforehand quantity, illustrate current total factor quantity beyond acceptable Report quantitative range in, now need to prompting the factor screened to enter to be met the prompting factor of setting factor beforehand quantity Row is reported.A kind of specific implementation of priority ordered is carried out to the prompting factor as the present invention, it is contemplated that different time sections The business service demand of interior client can difference, can be read out from record data in the embodiment of the present invention default recently Business service operation note in duration, and the business service number of operations of business service is carried out according to corresponding to the prompting factor Priority ordered.Wherein nearest preset duration occurrence need to be set by technical staff according to actual conditions.
After the prompting factor for determining finally to need to report, the speech data for reading the prompting factor simultaneously carries out voice spelling Connect, concrete operation step is identical with S103, and here is omitted.
In embodiments of the present invention, after going out its client properties data by the telephone number matches of destination object, visitor is utilized Family attribute data extracts the operation note of destination object, insurance kind of insuring, insurance node date and the insurance type insured, and The situation of insuring of destination object is analyzed using these data and factor screening model for extracting, realized to being The screening for the prompting factor included of uniting, so as to ensure that the prompting factor finally given is the business clothes needed for destination object Business.Predetermined number judgement finally is carried out to the obtained prompting factor, and priority ordered screening is carried out when beyond predetermined number, So as to ensure that the prompting factor quantity finally given will not be excessive, and be all destination object demand possibility highest prompting because Son.Therefore, the embodiment of the present invention again will not while ensure that the prompting factor of final output is that destination object is actually required Occur reporting excessive situation, drastically increase the intelligence degree that intelligent voice system is handled telephone service so that mesh Object is marked in telephony access intelligent voice system, it is possible to obtain timely and effectively business service voice broadcast.
As a kind of S102 preferred embodiment, as the embodiment of the present invention two, as shown in Fig. 2 including：
S1021, when N classes, which are insured, includes vehicle insurance type in type, extracted from record data in current vehicle insurance Record data section in Effective Period of Insurance, and judge in record data section whether to be reported a case to the security authorities mark comprising vehicle insurance.
In view of client after vehicle insurance is bought, typically only there occurs can just be sent a telegram here when car accident carry out vehicle insurance Report a case to the security authorities, and general can all send a telegram here again carries out inquiring about case flow progress within several consecutive days after vehicle insurance is reported a case to the security authorities, and carry out Business service operates.Therefore, in embodiments of the present invention, when N classes, which are insured, includes vehicle insurance type in type, can determine first Client currently insures the term of validity of effective vehicle insurance declaration form, such as on November 10,11 days to 2017 November in 2016, then from operation The record data section in the term of validity time started to current time is extracted in record data, if current time is 2017 During September 10 days, the record data in September 11 days to 2017 November in 2016 10 days is extracted from record data Section, and detect in record data section and whether to be reported a case to the security authorities mark comprising vehicle insurance.
S1022, if record data Duan Zhongwei reports a case to the security authorities mark comprising vehicle insurance, the vehicle insurance purchase in client properties data Buy the record data prompting factor related to vehicle insurance to screen, obtain the first kind prompting factor.
In embodiments of the present invention, it is vehicle insurance that intelligent voice system, which can carry out caller client the operation note that vehicle insurance is reported a case to the security authorities, Report a case to the security authorities mark, i.e., when caller client, which carries out vehicle insurance, reports a case to the security authorities, vehicle insurance can be write into record data and reported a case to the security authorities and identify and record Report a case to the security authorities the time.Therefore, when record data Duan Zhongwei reports a case to the security authorities mark comprising vehicle insurance, illustrate for effective car of currently insuring Dangerous declaration form client did not carried out vehicle insurance also and reported a case to the security authorities.As a kind of S1022 specific implementation, related to vehicle insurance carry can be read Show the factor, such as " vehicle insurance is reported a case to the security authorities ", " consulting vehicle insurance " and " vehicle insurance recommendation ", these prompting factors are grasped according to big data Working frequency sorts, and filters out the required prompting factor, wherein the prompting factor quantity of screening needed for specific, can be by technical staff Sets itself according to the actual requirements.As S1022 another specific implementation, on the basis of former implementation, Without being ranked up to " vehicle insurance is reported a case to the security authorities ", but directly as one of required prompting factor, to facilitate client straight when needed Driving danger is tapped into report a case to the security authorities.
S1023, if being reported a case to the security authorities mark comprising vehicle insurance in record data section, read vehicle insurance and report a case to the security authorities the reporting a case to the security authorities the time of mark, To current time and report a case to the security authorities the time carry out mathematic interpolation, and by the difference drawn with storage case flow time table carry out case Part flow stages match, and determine the case flow stages residing for current time.
In embodiments of the present invention, case flow stages are broadly divided into：Survey the core damage stage and compensate processing stage, its In, the case flow that core damages the stage and correspond to determine to the compensation amount of money since being reported a case to the security authorities vehicle insurance is surveyed, it is corresponding to compensate processing stage From compensating after the amount of money determines to the case flow of reparation payments completion.
When being reported a case to the security authorities mark comprising vehicle insurance in record data section, that is, illustrate that client had carried out vehicle insurance and reported a case to the security authorities, case Handling process has been started up.Although each case handling process time requirement of the insurance company to vehicle insurance case difference, such as Some insurance companies mandates must wind up the case from the time of reporting a case to the security authorities in 72 hours, have some then to require from 5 working days of time of reporting a case to the security authorities It is interior to wind up the case, but for the insurance company of each, its case handling process time requirement is fixed, and above-mentioned Case flow stages are also identical, therefore are directed to each insurance company, and technical staff can be according to insurance company to case The time requirement of part handling process and case flow stages make case flow time table, so that intelligent voice system is inquired about Case flow stages residing for current time.
S1024, when the case flow stages of current time damage the stage to survey core, the contact in the extraction prompting factor is looked into Damage person is surveyed, vehicle insurance is reported a case to the security authorities and cancels vehicle insurance and is reported a case to the security authorities, the factor is prompted as the first kind.In the case flow stages of current time During to compensate processing stage, case progress and amount of money inquiry, vehicle insurance in the extraction prompting factor are reported a case to the security authorities and cancelled vehicle insurance and report a case to the security authorities, The factor is prompted as the first kind.
Survey the core damage stage and compensate the processing stage main distinction and be to compensate whether the amount of money determines.Surveying core damage rank Section carries out setting loss assessment, it is necessary to survey setting loss person to vehicle, to determine to compensate the amount of money, therefore, at any time may in this stage client Contact is needed to survey setting loss person.For compensating processing stage, insurance company can be carried out to the data of client and the data of accident Examination ＆ verification, and examine and compensate whether the amount of money meets regulation requirement.Therefore, when current time is in and surveys the core damage stage, it is necessary to will " setting loss person is surveyed in contact " adds to the first kind and prompts the factor, and is in current time and compensates processing stage, it is necessary to by " case Progress and amount of money inquiry " adds to the first kind and prompts the factor.
In embodiments of the present invention, by judging this incoming call of client before whether to effective vehicle insurance declaration form of currently insuring Carried out vehicle insurance to report a case to the security authorities, to select corresponding prompting factor screening rule.When not carrying out vehicle insurance and reporting a case to the security authorities, driving is entered to client The related prompting factor in danger is screened, and the factor is prompted to obtain the required first kind, and when having carried out vehicle insurance and reporting a case to the security authorities, according to Case flow time table is determined accordingly to identify the case flow stages residing for current time according to the specific stage The prompting factor so that the embodiment of the present invention can be realized to the processing of vehicle insurance type Intelligent Recognition, and filtered out for client The prompting factor of actual demand is best suitable for, improves intelligence degree of the intelligent voice system to customer phone business processing.
As a kind of S102 preferred embodiment, as the embodiment of the present invention three, as shown in figure 3, including：
S1025, when N classes, which are insured, includes life insurance type in type, using special insurance kind table to life insurance type The insurance kind of insuring of subordinate is classified, and identifies the special insurance kind that is included in the insurance kind of insuring of life insurance type subordinate and non- Special insurance kind, and key node date inquiries are carried out to the insurance node date, determine key node day corresponding to special insurance kind Phase.
From the above-mentioned explanation on S102, the concrete condition of the insurance kind of insuring of every kind of insurance type subordinate can be poor It is different, in embodiments of the present invention, by the concrete condition of the insurance kind of insuring of life insurance type subordinate be divided into special insurance kind and The no special major class of insurance kind two, and a special insurance kind table has been prestored, after carrying out special insurance kind inquiry using the table, you can Realize and the insurance kind of insuring of life insurance type subordinate is classified.
For each special insurance kind, it all has a key node date, by with this key node day Computation of Period is carried out based on phase, it is possible to achieve the inquiry to the concrete condition of these special insurance kinds.Such as dividend danger, Day in anniversary dividend strategy is given birth to client, therefore for danger of sharing out bonus, its declaration form because insurance company can come into force in annual declaration form It is exactly its key point date to imitate day, after annual day in insurance in-force anniversary, you can the dividend strategy situation of inquiry dividend danger. For universal life insurance, computation of Period is carried out due to it and by starting point of the declaration form effective date, therefore, its declaration form effective date is just It is its key point date.And for Investment-linked insurance, its payment flexibly can additional premium, and being paid every time with premium at any time It is that starting point re-starts computation of Period to take successfully day, therefore is renewed for Investment-linked insurance, and its premium successfully day of pay the fees is exactly its key The point date.
S1026, using key node date and the effective time table of storage, when calculating effective prompting of special insurance kind Between, and when judging that current time is in the range of effective prompt time of special insurance kind, by the account inquiries of special insurance kind Prompting is as the second class prompting factor.
As shown in the above description, client need to only send a telegram here after the key node date of special insurance kind, you can it is special to carry out The inquiry of insurance kind concrete condition.In the embodiment of the present invention, in order to realize whether Intelligent Recognition client can carry out special insurance kind tool The inquiry of body situation, and when recognition result is to inquire about, account inquiries prompting corresponding to special insurance kind is subjected to voice and broadcast Report.An effective time table can be preset first, effective time corresponding to each special insurance kind is record in the table, then pass through pass The key node date is calculated with the table, you can draws effective prompt time of special insurance kind.Such as set when corresponding to dividend danger Effective time 30 days, declaration form come into force the phase for August 1 day when, then annual August No. 1 to No. 31, the effective prompting for danger of as sharing out bonus Time.
As a kind of S1026 specific implementation, including：
If special defects insurance kind is danger of sharing out bonus, on the key node date using declaration form effective date T1 as danger of sharing out bonus, reads and share out bonus Effective time n days of danger, and using annual T1+n days declaration form effective date as dangerous effective prompt time of sharing out bonus, it is preferable that n is 30。
If special defects insurance kind is universal life insurance, the key node date using declaration form effective date T2 as universal life insurance, and by T2+H Effective prompt time of the preceding n1 days as universal life insurance of every month after year, it is preferable that H 3, n1 11.
If special defects insurance kind is Investment-linked insurance, premium will be renewed and paid the fees the key node date of successful day T3 as Investment-linked insurance, Read the effective time n2 days of Investment-linked insurance, and effective prompt time using T3 to T3+n2 days as Investment-linked insurance, it is preferable that n2 is 5。
N, n1 and n2 is the positive integer more than zero.
Because the purchase relation between three kinds of special insurance kinds is mutual exclusion, i.e., client is only capable of purchase wherein in the same period A certain kind.After effective prompt time of special insurance kind is determined, judge whether current time belongs to the special insurance kind of purchase Corresponding effectively prompt time scope, if belonging to, prompt the account inquiries prompting of special insurance kind to the factor as the second class, such as Purchase is danger of sharing out bonus, and current time is August 10, belongs to effective prompt time of above-mentioned dividend danger August No. 1 to No. 31, this When, the prompting factor of " dividend account inquiries " can be prompted to the factor as the second class in the embodiment of the present invention.
S1027, node date input node Dates Study model will be insured, when obtaining effective prompting of no special insurance kind Between, and when judging that current time is in the range of effective prompt time of no special insurance kind, by the information of no special insurance kind Inquiry prompting is as the 3rd class prompting factor.
In S1027, mainly in life insurance type no special insurance kind (such as whole-life insurance, term life and Endowment insurance etc.) handled, to obtain the prompting factor of no special insurance kind.Compared with special insurance kind, danger in no special insurance kind State between kind and insurance kind is general, and it is also identical to insure possible situation corresponding to the node date, will not be as insurance for any special risk With the presence of its special state, (such as the state for danger dividend strategy of sharing out bonus, there is multiple profit in universal life insurance to each insurance kind accumulated in kind Distribution of income state be present in state, Investment-linked insurance), therefore, with identical factor screening rule can be prompted directly to handle non-spy Different danger.Therefore, in the node Dates Study model treatment of the embodiment of the present invention, specific insurance kind knowledge will not be carried out to insurance kind of insuring Not, but directly all insurance node dates is inputted to node Dates Study model and analyzed.
In the embodiment of the present invention, node Dates Study model can save after the insurance node date is got to each insurance Effective time corresponding to the point date is inquired about, and calculates no special insurance kind according to insurance node date and effective time Effective prompt time, then current time judge whether to be in effective prompt time, to extract the required prompting factor.
Ground connection should be managed, because the insurance node date of no special insurance kind is more, there is guarantor on such as common insurance node date Single payment day, declaration form effective date, day expiration of policy, client submit day of reporting a case to the security authorities Claims Resolution material day, client's Claims Resolution, declaration form loan also Money day, the date for changing business personnel and save from damage business handling day etc., and effective time corresponding to each insurance node date There may be effective prompt times that are multiple, therefore can generating more in the embodiment of the present invention.Node Dates Study model can ought The preceding time contrasts one by one with these effective prompt times, determines the prompting factor corresponding to each insurance node date respectively.
As a kind of S1027 specific implementation, as shown in table 1：
Table 1
In the table 1 of the embodiment of the present invention, effective time corresponding to a variety of insurance node dates has been preset, and accordingly The factor is prompted, can be directly according to insurance node date and table 1 after insurance node date input node Dates Study model In effective time calculate effective prompt time on each insurance node date, and judging that current time goes out at current time When in effective prompt time, corresponding information inquiry is extracted, to show that the 3rd class prompts the factor.
Further, as a preferred embodiment of the present invention, while effective prompt time is calculated, can also increase Add the inquiry judging of some situations of being insured to client, and further the prompting factor is screened according to judged result, to carry Rise the prompting factor finally given and the matching degree of client.Effective time such as declaration form payment day is+60 and more than 15 Day situation, the judgement to client's payment of insurance money situation can be increased, if client and paying insurance premium, without prompting " quickly paying dues ", now only need to filter out " premium to account is inquired about ".
In the embodiment of the present invention, by being general to enter for standard to state of the life insurance type between insurance kind and insurance kind Row division, obtains special insurance kind table, and using special insurance kind table marked off from life insurance type special insurance kind with it is no special Insurance kind, the characteristics of further in accordance with insurance kind two kinds of insurance kinds are carried out with the calculating of effective prompt time respectively, and meet have in current time When imitating prompt time scope, the corresponding prompting factor is extracted.Thrown so that the embodiment of the present invention can be realized according to client Insurance kind carries out the prompting factor screening for changing, and improves intelligent journey of the intelligent voice system to customer phone business processing Degree.Meanwhile the embodiment of the present invention can insure situation to prompting the factor further to screen with client, so that screening obtains The prompting factor higher with customer demand matching degree.
As a kind of S102 preferred embodiment, as the embodiment of the present invention four, as shown in figure 4, including：
S1028, when N classes, which are insured, includes life insurance type in type, detect in client properties data whether include paper Matter letters bounce mark, existence gold do not get any one or more special identifier in mark and identity card failure indication.
For life insurance type, in addition to the insurance business service consultation that above-mentioned several embodiments are mentioned is handled, go back It there may be following several more special situations：1st, because trade connection address is wrongly write, cause the papery letters of declaration form can not Normal send is passed, so as to the situation of bounce occur.2nd, client has forgotten the existence gold for also having in the declaration form oneself insured and not getting. 3rd, the identity card term of validity used when client is insured mistake, so as to cause the information asymmetry insured.Papery letters bounce Mark, existence gold does not get mark and identity card failure indication is corresponding with three kinds of special circumstances respectively.
For these special circumstances, the traditional processing method of insurance company is all manually to be linked up with customer phone, informs visitor The presence of these special circumstances of family, and prompt client to modify, therefore go to complete this, it is necessary to expend larger human cost Work.In the embodiment of the present invention, in order to increase the processing intelligence degree to customer phone business, in caller client, also can Detection client whether there is above-mentioned special circumstances.
S1029, if not getting mark and identity card comprising papery letters bounce mark, existence gold in client properties data Any one or more special identifier in failure indication, from prompting the factor in extract included in client properties data it is special The consulting modification prompting of mark, and as the 4th class prompting factor.
Special identifier is included in client properties data when detecting, that is, when above-mentioned special circumstances be present, can there will be Concrete condition informs client, is repaiied specifically, can all be separately provided a corresponding consulting for each above-mentioned special circumstances Change prompting, such as special circumstances 1, corresponding consulting modification prompting could be arranged to " your declaration form papery letters contact ground Location is wrong, please change contact address ", it could be arranged to that " you, which have, does not get for the corresponding consulting modification prompting of special circumstances 2 Existence gold, if the golden collar that needs to survive takes consulting ", change prompting for the corresponding consulting of special circumstances 3 and could be arranged to " your identity card is out of date, please change certificate ".It should be understood that ground, due between above-mentioned three kinds of special circumstances and being not present mutual exclusion Relation, therefore, the probability that three kinds of special circumstances occur are independent, and both possible one was all not present, it is also possible to exists simultaneously.
In the embodiment of the present invention, by using intelligent voice system automatic detection client with the presence or absence of contact address it is wrong, The special circumstances that existence gold is not got and the identity card term of validity has been crossed, and when detecting to exist special circumstances, extract spy Consulting modification prompting, reports for subsequent voice and informs user corresponding to different situation.
As a preferred embodiment of the present invention five, such as Fig. 5, including：
S501, the speech data of destination object is gathered, speech recognition and keyword match are carried out to speech data.
S502, when identify include predetermined keyword in speech data when, send manual service prompting voice data to logical The client terminal of opposite end is talked about, and receives destination object in preset time and is based on the return of manual service prompting voice data really When recognizing incoming instruction, call is forwarded to manual service account.
Due in the embodiment of the present invention one to four, finally report be all setting factor beforehand quantity business service, and these The business service of finite number is not well positioned to meet the actual requirement of client sometimes, is intended to do together as client this time sends a telegram here Multiple different business are managed, but contain a part of industry needed for client in the business service of intelligent voice system report Business.In order to meet user's actual need, in the embodiment of the present invention, some keywords can be preset, such as switching, manual service and visitor Clothes, during caller client in real time detection client speech data, and detect include these keywords when, automatically It is forwarded to manual service.
As another preferred embodiment of the present invention, in addition to：The speech data of destination object is gathered, to speech data Speech recognition and factor Keywords matching are carried out, and when identifying that speech data includes factor keyword, reports the factor and closes Service business corresponding to keyword.
In the embodiment of the present invention, whether meeting has said business service during detecting caller client in real time, and is detecting When saying business service to client, business service corresponding to automatic report, to help client quickly to carry out the operation of business service.
Corresponding to the method for foregoing embodiments, Fig. 6 shows Intelligent voice prompting device provided in an embodiment of the present invention Structured flowchart, for convenience of description, it illustrate only the part related to the embodiment of the present invention.The intelligent voice prompt of Fig. 6 examples Device can be the executive agent for the intelligent voice prompt method that previous embodiment one provides.
Reference picture 6, the Intelligent voice prompting device include：
Data acquisition module 61, for obtaining the telephone number of call opposite end destination object, utilize the telephone number pair The destination object carries out client properties Data Matching, and read the insurance in the client properties data matched identify with And record data.The insurance mark is parsed, identify M kinds that the destination object has been insured insure insurance kind with And the N classes that the M kinds are insured belonging to insurance kind insure type, and the insurance node date corresponding to the insurance mark is read out, its Middle M, N are the integer more than zero.
Factor screening module 62, for by the record data, it is described insure insurance kind and it is described insurance node day Phase, input to factor screening model corresponding to N classes insurance type, the prompting factor is carried out respectively to insuring type described in N classes Screening, show that the N classes insure the N1 classes prompting factor corresponding to type difference, wherein, the prompting factor is used to represent required The business service of broadcasting, N1 are the integer less than or equal to M more than zero.
First voice broadcast module 63, total factor quantity statistics is carried out for the N1 classes prompting factor to obtaining.If it is total because Quantum count is less than or equal to setting factor beforehand quantity, reads out the voice number of each prompting factor in the N1 classes prompting factor According to using default voice message template, carrying out voice joint to the speech data read out, and the voice joint is obtained The client terminal sent to prompting voice data to call opposite end is reported.
Second voice broadcast module 64, if being more than setting factor beforehand quantity for total factor quantity, utilize the operation note Data prompt the N1 classes all prompting factors in the factor to carry out priority ordered, are preset before filtering out relative importance value highest The prompting factor of factor number of bits, and speech data corresponding to reading, using the default voice message template to described Corresponding speech data carries out the voice joint, and the voice joint is obtained into prompting voice data and sent to call opposite end Client terminal reported.
Further, factor screening module includes：
When the N classes, which are insured, includes vehicle insurance type in type, extracted from the record data in current vehicle Record data section in dangerous Effective Period of Insurance, and judge in the record data section whether to be reported a case to the security authorities mark comprising vehicle insurance Know.
If the record data Duan Zhongwei reports a case to the security authorities mark comprising vehicle insurance, according to the vehicle insurance in the client properties data The purchaser record data prompting factor related to vehicle insurance is screened, and obtains the first kind prompting factor.
If being reported a case to the security authorities mark comprising vehicle insurance in the record data section, read the vehicle insurance and report a case to the security authorities when reporting a case to the security authorities of mark Between, to current time and it is described report a case to the security authorities the time carry out mathematic interpolation, and by the difference drawn with storage case flow time Table carries out case flow stages matching, determines the case flow stages residing for current time.
When the case flow stages of current time damage the stage to survey core, the contact extracted in the prompting factor is surveyed Setting loss person, vehicle insurance report a case to the security authorities and cancelled vehicle insurance and report a case to the security authorities, and the factor is prompted as the first kind.In the case flow rank of current time When section is compensates processing stage, the case progress prompted in the factor and amount of money inquiry are extracted, the vehicle insurance is reported a case to the security authorities and institute State revocation vehicle insurance to report a case to the security authorities, the factor is prompted as the first kind.
Further, factor screening module also includes：
When the N classes, which are insured, includes life insurance type in type, using special insurance kind table to the life insurance class The insurance kind of insuring of type subordinate is classified, and identifies the special insurance kind included in the insurance kind of insuring of the life insurance type subordinate And no special insurance kind, and key node date inquiries are carried out to the insurance node date, determine the special insurance kind pair The key node date answered.
Using the key node date and the effective time table of storage, effective prompting of the special insurance kind is calculated Time, and when judging that current time is in the range of effective prompt time of the special insurance kind, by the special insurance kind Account inquiries prompting as the second class prompting the factor.
Node date input node Dates Study model is insured by described, when obtaining effective prompting of the no special insurance kind Between, and when judging that current time is in the range of effective prompt time of the no special insurance kind, by the no special danger The information inquiry prompting of kind is as the 3rd class prompting factor.
Further, the Intelligent voice prompting device also includes：
When the N classes, which are insured, includes life insurance type in type, detect and whether included in the client properties data Papery letters bounce mark, existence gold do not get any one or more special mark in mark and identity card failure indication Know.
If mark is not got comprising papery letters bounce mark, existence gold in the client properties data and identity card loses Any one or more special identifier in criterion knowledge, extract in the client properties data and include from the prompting factor Special identifier consulting modification prompting, and as the 4th class prompting the factor.
Further, the Intelligent voice prompting device also includes：
The speech data of the destination object is gathered, speech recognition and keyword match are carried out to the speech data.
When identify include predetermined keyword in the speech data when, send manual service prompting voice data to conversing The client terminal of opposite end, and receive the destination object in preset time and be based on the manual service suggestion voice number According to return confirmation incoming instruction when, call is forwarded to manual service account.
Each module realizes the process of respective function in Intelligent voice prompting device provided in an embodiment of the present invention, can specifically join The description of embodiment illustrated in fig. 1 one is stated before examination, and here is omitted.
It should be understood that the size of the sequence number of each step is not meant to the priority of execution sequence, each process in above-described embodiment Execution sequence should determine that the implementation process without tackling the embodiment of the present invention forms any limit with its function and internal logic It is fixed.
It will also be appreciated that although term " first ", " second " etc. are used in some embodiment of the present invention in the text Various elements are described, but these elements should not be limited by these terms.These terms are used only to an element Distinguished with another element.For example, the first contact can be named as the second contact, and similarly, the second contact can be by The first contact is named as, without departing from the scope of various described embodiments.First contact and the second contact are all contacts, but It is that they are not same contacts.
Fig. 7 is the schematic diagram for the intelligent voice prompt terminal device that one embodiment of the invention provides.As shown in fig. 7, the reality Applying the intelligent voice prompt terminal device 7 of example includes：Processor 70, memory 71, being stored with the memory 71 can be in institute State the computer program 72 run on processor 70.The processor 70 is realized above-mentioned each when performing the computer program 72 Step in intelligent voice prompt embodiment of the method, such as step 101 shown in Fig. 1 is to 104.Or the processor 70 is held The function of each module/unit in above-mentioned each device embodiment, such as module 61 shown in Fig. 6 are realized during the row computer program 72 To 64 function.
The intelligent voice prompt terminal device 7 can be desktop PC, notebook, palm PC and cloud service The computing devices such as device.The intelligent voice prompt terminal device may include, but be not limited only to, processor 70, memory 71.Ability Field technique personnel are appreciated that Fig. 7 is only the example of intelligent voice prompt terminal device 7, do not form and intelligent sound is carried Show the restriction of terminal device 7, can include than illustrating more or less parts, either combine some parts or different Part, such as the intelligent voice prompt terminal device can also include input-output equipment, network access equipment, bus etc..
Alleged processor 70 can be CPU (Central Processing Unit, CPU), can also be Other general processors, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field- Programmable Gate Array, FPGA) either other PLDs, discrete gate or transistor logic, Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor Deng.
The memory 71 is the computer-readable recording medium of at least one type, can be the intelligent voice prompt The internal storage unit of terminal device 7, such as the hard disk or internal memory of intelligent voice prompt terminal device 7.The memory 71 Can be on the External memory equipment of the intelligent voice prompt terminal device 7, such as the intelligent voice prompt terminal device 7 The plug-in type hard disk of outfit, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) Card, flash card (Flash Card) etc..Further, the memory 71 can also both include the intelligent voice prompt terminal The internal storage unit of equipment 7 also includes External memory equipment.The memory 71 be used for store the computer program and Other programs and data needed for the intelligent voice prompt terminal device.The memory 71 can be also used for temporarily storing The data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each work( Can unit, module division progress for example, in practical application, can be as needed and by above-mentioned function distribution by different Functional unit, module are completed, i.e., the internal structure of described device are divided into different functional units or module, more than completion The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used To be that unit is individually physically present, can also two or more units it is integrated in a unit, it is above-mentioned integrated Unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.In addition, each function list Member, the specific name of module are not limited to the protection domain of the application also only to facilitate mutually distinguish.Said system The specific work process of middle unit, module, the corresponding process in preceding method embodiment is may be referred to, will not be repeated here.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and is not described in detail or remembers in some embodiment The part of load, it may refer to the associated description of other embodiments.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein Member and algorithm steps, it can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually Performed with hardware or software mode, application-specific and design constraint depending on technical scheme.Professional and technical personnel Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, can be with Realize by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute The division of module or unit is stated, only a kind of division of logic function, there can be other dividing mode when actually realizing, such as Multiple units or component can combine or be desirably integrated into another system, or some features can be ignored, or not perform.Separately A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be by some interfaces, device Or INDIRECT COUPLING or the communication connection of unit, can be electrical, mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs 's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated module/unit realized in the form of SFU software functional unit and as independent production marketing or In use, it can be stored in a computer read/write memory medium.Based on such understanding, the present invention realizes above-mentioned implementation All or part of flow in example method, by computer program the hardware of correlation can also be instructed to complete, described meter Calculation machine program can be stored in a computer-readable recording medium, and the computer program can be achieved when being executed by processor The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation Code can be source code form, object identification code form, executable file or some intermediate forms etc..The computer-readable medium It can include：Any entity or device, recording medium, USB flash disk, mobile hard disk, the magnetic of the computer program code can be carried Dish, CD, computer storage, read-only storage (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It is it should be noted that described The content that computer-readable medium includes can carry out appropriate increasing according to legislation in jurisdiction and the requirement of patent practice Subtract, such as in some jurisdictions, electric carrier signal and electricity are not included according to legislation and patent practice, computer-readable medium Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to foregoing reality Example is applied the present invention is described in detail, it will be understood by those within the art that：It still can be to foregoing each Technical scheme described in embodiment is modified, or carries out equivalent substitution to which part technical characteristic；And these are changed Or replace, the essence of corresponding technical scheme is departed from the spirit and scope of various embodiments of the present invention technical scheme, all should Within protection scope of the present invention.

Claims (10)

  1. A kind of 1. intelligent voice prompt method, it is characterised in that including：
    The telephone number of call opposite end destination object is obtained, client properties are carried out to the destination object using the telephone number Data Matching, and read insurance mark and record data in the client properties data matched；To the guarantor Danger mark is parsed, and identifies that M kinds that the destination object has been insured insure insurance kind and the M kinds are insured belonging to insurance kind N classes insure type, and read out the insurance node date corresponding to the insurance mark, and wherein M, N is the integer more than zero；
    By the record data, it is described insure insurance kind and it is described insurance the node date, input to the N classes insure type Corresponding factor screening model, prompting factor screening is carried out respectively to insuring type described in N classes, draw the N classes insurance type Respectively corresponding to N1 classes prompting the factor, wherein, it is described prompting the factor be used for represent needed for broadcasting business service, N1 be more than Zero, the integer less than or equal to M；
    Total factor quantity statistics is carried out to the obtained N1 classes prompting factor；If total factor quantity is less than or equal to setting factor beforehand number Amount, the speech data of each prompting factor in the N1 classes prompting factor is read out, using default voice message template, to reading The speech data taken out carries out voice joint, and the voice joint is obtained into prompting voice data and sent to call opposite end Client terminal reported；
    If total factor quantity is more than setting factor beforehand quantity, institute in the factor is prompted the N1 classes using the record data There is the prompting factor to carry out priority ordered, filter out the prompting factor of setting factor beforehand number of bits before relative importance value highest, and Speech data corresponding to reading, the voice spelling is carried out to the corresponding speech data using the default voice message template Connect, and by the voice joint obtain prompting voice data send to call opposite end client terminal reported.
  2. 2. intelligent voice prompt method as claimed in claim 1, it is characterised in that described by the record data, institute Insure insurance kind and the insurance node date are stated, is inputted to factor screening model corresponding to N classes insurance type, to N classes The insurance type carries out prompting factor screening respectively, draws the N1 classes prompting factor corresponding to the N classes insurance type difference, bag Include：
    When the N classes, which are insured, includes vehicle insurance type in type, extract from the record data and protected in current vehicle insurance Record data section in single term of validity, and judge in the record data section whether to be reported a case to the security authorities mark comprising vehicle insurance；
    If the record data Duan Zhongwei reports a case to the security authorities mark comprising vehicle insurance, the vehicle insurance purchase in the client properties data The record data prompting factor related to vehicle insurance is screened, and obtains the first kind prompting factor；
    If being reported a case to the security authorities mark comprising vehicle insurance in the record data section, read the vehicle insurance and report a case to the security authorities the reporting a case to the security authorities the time of mark, it is right Current time and the time of reporting a case to the security authorities carry out mathematic interpolation, and the difference drawn and the case flow time table of storage are carried out Case flow stages match, and determine the case flow stages residing for current time；
    When the case flow stages of current time damage the stage to survey core, setting loss is surveyed in the contact extracted in the prompting factor Member, vehicle insurance are reported a case to the security authorities and cancelled vehicle insurance and report a case to the security authorities, and the factor is prompted as the first kind；It is in the case flow stages of current time When compensating processing stage, extract the case progress in the prompting factor and amount of money inquiry, the vehicle insurance are reported a case to the security authorities and described removed Pin vehicle insurance is reported a case to the security authorities, and the factor is prompted as the first kind.
  3. 3. intelligent voice prompt method as claimed in claim 1, it is characterised in that described by the record data, institute Insure insurance kind and the insurance node date are stated, is inputted to factor screening model corresponding to N classes insurance type, to N classes The insurance type carries out prompting factor screening respectively, draws the N1 classes prompting factor corresponding to the N classes insurance type difference, also Including：
    When the N classes, which are insured, includes life insurance type in type, using special insurance kind table under the life insurance type The insurance kind of insuring of category is classified, identify the special insurance kind that is included in the insurance kind of insuring of the life insurance type subordinate and No special insurance kind, and key node date inquiries are carried out to the insurance node date, determine corresponding to the special insurance kind The key node date；
    Using the key node date and the effective time table of storage, when calculating effective prompting of the special insurance kind Between, and when judging that current time is in the range of effective prompt time of the special insurance kind, by the special insurance kind Account inquiries prompting is as the second class prompting factor；
    By the insurance node date input node Dates Study model, effective prompt time of the no special insurance kind is obtained, And when judging that current time is in the range of effective prompt time of the no special insurance kind, by the no special insurance kind Information inquiry prompting is as the 3rd class prompting factor.
  4. 4. intelligent voice prompt method as claimed in claim 1, it is characterised in that also include：
    When the N classes, which are insured, includes life insurance type in type, detect in the client properties data whether include papery Letters bounce mark, existence gold do not get any one or more special identifier in mark and identity card failure indication；
    If mark and identity card failure mark are not got comprising papery letters bounce mark, existence gold in the client properties data Any one or more special identifier in knowledge, the spy included in the client properties data is extracted from the prompting factor The consulting modification prompting very identified, and as the 4th class prompting factor.
  5. 5. intelligent voice prompt method as claimed in claim 1, it is characterised in that carried the voice joint described Show speech data send to call opposite end client terminal reported after, in addition to：
    The speech data of the destination object is gathered, speech recognition and keyword match are carried out to the speech data；
    When identify include predetermined keyword in the speech data when, send manual service prompting voice data to opposite end of conversing The client terminal, and receive the destination object in preset time and returned based on the manual service prompting voice data During the confirmation incoming instruction returned, call is forwarded to manual service account.
  6. 6. a kind of intelligent voice prompt terminal device, it is characterised in that the intelligent voice prompt processing terminal equipment includes depositing Reservoir, processor, the computer program that can be run on the processor, the computing device are stored with the memory Following steps are realized during the computer program：
    The telephone number of call opposite end destination object is obtained, client properties are carried out to the destination object using the telephone number Data Matching, and read insurance mark and record data in the client properties data matched；To the guarantor Danger mark is parsed, and identifies that M kinds that the destination object has been insured insure insurance kind and the M kinds are insured belonging to insurance kind N classes insure type, and read out the insurance node date corresponding to the insurance mark, and wherein M, N is the integer more than zero；
    By the record data, it is described insure insurance kind and it is described insurance the node date, input to the N classes insure type Corresponding factor screening model, prompting factor screening is carried out respectively to insuring type described in N classes, draw the N classes insurance type Respectively corresponding to N1 classes prompting the factor, wherein, it is described prompting the factor be used for represent needed for broadcasting business service, N1 be more than Zero, the integer less than or equal to M；
    Total factor quantity statistics is carried out to the obtained N1 classes prompting factor；If total factor quantity is less than or equal to setting factor beforehand number Amount, the speech data of each prompting factor in the N1 classes prompting factor is read out, using default voice message template, to reading The speech data taken out carries out voice joint, and the voice joint is obtained into prompting voice data and sent to call opposite end Client terminal reported；
    If total factor quantity is more than setting factor beforehand quantity, institute in the factor is prompted the N1 classes using the record data There is the prompting factor to carry out priority ordered, filter out the prompting factor of setting factor beforehand number of bits before relative importance value highest, and Speech data corresponding to reading, the voice spelling is carried out to the corresponding speech data using the default voice message template Connect, and by the voice joint obtain prompting voice data send to call opposite end client terminal reported.
  7. 7. intelligent voice prompt terminal device as claimed in claim 6, it is characterised in that described by the operation note number According to, it is described insure insurance kind and it is described insurance the node date, input to the N classes insurance type corresponding to factor screening model, Carry out prompting factor screening respectively to insuring type described in N classes, draw N classes insurance type respectively corresponding to the prompting of N1 classes because Son, specifically include：
    When the N classes, which are insured, includes vehicle insurance type in type, extract from the record data and protected in current vehicle insurance Record data section in single term of validity, and judge in the record data section whether to be reported a case to the security authorities mark comprising vehicle insurance；
    If the record data Duan Zhongwei reports a case to the security authorities mark comprising vehicle insurance, the vehicle insurance purchase in the client properties data The record data prompting factor related to vehicle insurance is screened, and obtains the first kind prompting factor；
    If being reported a case to the security authorities mark comprising vehicle insurance in the record data section, read the vehicle insurance and report a case to the security authorities the reporting a case to the security authorities the time of mark, it is right Current time and the time of reporting a case to the security authorities carry out mathematic interpolation, and the difference drawn and the case flow time table of storage are carried out Case flow stages match, and determine the case flow stages residing for current time；
    When the case flow stages of current time damage the stage to survey core, setting loss is surveyed in the contact extracted in the prompting factor Member, vehicle insurance are reported a case to the security authorities and cancelled vehicle insurance and report a case to the security authorities, and the factor is prompted as the first kind；It is in the case flow stages of current time When compensating processing stage, extract the case progress in the prompting factor and amount of money inquiry, the vehicle insurance are reported a case to the security authorities and described removed Pin vehicle insurance is reported a case to the security authorities, and the factor is prompted as the first kind.
  8. 8. intelligent voice prompt terminal device as claimed in claim 6, it is characterised in that described by the operation note number According to, it is described insure insurance kind and it is described insurance the node date, input to the N classes insurance type corresponding to factor screening model, Carry out prompting factor screening respectively to insuring type described in N classes, draw N classes insurance type respectively corresponding to the prompting of N1 classes because Son, specifically include：
    When the N classes, which are insured, includes life insurance type in type, using special insurance kind table under the life insurance type The insurance kind of insuring of category is classified, identify the special insurance kind that is included in the insurance kind of insuring of the life insurance type subordinate and No special insurance kind, and key node date inquiries are carried out to the insurance node date, determine corresponding to the special insurance kind The key node date；
    Using the key node date and the effective time table of storage, when calculating effective prompting of the special insurance kind Between, and when judging that current time is in the range of effective prompt time of the special insurance kind, by the special insurance kind Account inquiries prompting is as the second class prompting factor；
    By the insurance node date input node Dates Study model, effective prompt time of the no special insurance kind is obtained, And when judging that current time is in the range of effective prompt time of the no special insurance kind, by the no special insurance kind Information inquiry prompting is as the 3rd class prompting factor.
  9. 9. intelligent voice prompt terminal device as claimed in claim 6, it is characterised in that calculating described in the computing device Following steps are also realized during machine program：
    The speech data of the destination object is gathered, speech recognition and keyword match are carried out to the speech data；
    When identify include predetermined keyword in the speech data when, send manual service prompting voice data to opposite end of conversing The client terminal, and receive the destination object in preset time and returned based on the manual service prompting voice data During the confirmation incoming instruction returned, call is forwarded to manual service account.
  10. 10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, and its feature exists In when the computer program is executed by processor the step of realization such as any one of claim 1 to 5 methods described.
CN201711037115.8A 2017-10-30 2017-10-30 Intelligent voice prompt method and terminal equipment Active CN107800894B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201711037115.8A CN107800894B (en) 2017-10-30 2017-10-30 Intelligent voice prompt method and terminal equipment
PCT/CN2017/112903 WO2019085095A1 (en) 2017-10-30 2017-11-24 Intelligent voice prompting method and apparatus, electronic device, and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711037115.8A CN107800894B (en) 2017-10-30 2017-10-30 Intelligent voice prompt method and terminal equipment

Publications (2)

Publication Number Publication Date
CN107800894A true CN107800894A (en) 2018-03-13
CN107800894B CN107800894B (en) 2020-01-10

Family

ID=61548133

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711037115.8A Active CN107800894B (en) 2017-10-30 2017-10-30 Intelligent voice prompt method and terminal equipment

Country Status (2)

Country Link
CN (1) CN107800894B (en)
WO (1) WO2019085095A1 (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109544382A (en) * 2018-10-31 2019-03-29 平安医疗健康管理股份有限公司 It is a kind of that method for processing business and relevant device are handled based on data processing
CN109903098A (en) * 2019-03-12 2019-06-18 安徽赛迪信息技术有限公司 A kind of identification of client identity and automatic clustering system
CN110196895A (en) * 2019-04-19 2019-09-03 平安科技（深圳）有限公司 User data information self-service query method, apparatus, computer equipment and storage medium
CN111163234A (en) * 2019-12-31 2020-05-15 北京金山安全软件有限公司 Service call processing method and device, electronic equipment and storage medium
WO2020140681A1 (en) * 2019-01-03 2020-07-09 深圳壹账通智能科技有限公司 Numerical value calculation method and apparatus, computer device, and storage medium
CN113537774A (en) * 2021-07-16 2021-10-22 精英数智科技股份有限公司 Method and system for detecting whether coal mine enterprise policy is valid
CN114125161A (en) * 2021-11-29 2022-03-01 阳光保险集团股份有限公司 Business handling method and system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090080640A1 (en) * 2007-09-20 2009-03-26 Adam Waalkes System and method for retaining calls into a call center
CN104064182A (en) * 2014-06-24 2014-09-24 中国人民财产保险股份有限公司 A voice recognition system and method based on classification rules
CN106709696A (en) * 2016-11-21 2017-05-24 中国平安财产保险股份有限公司 Self-service claim settlement realization method and system
CN107105109A (en) * 2016-02-23 2017-08-29 平安科技（深圳）有限公司 voice broadcast method and system

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8811593B1 (en) * 2013-09-04 2014-08-19 Applied Business Technologies Call center agent centric speech decoding system and method with quality assurance function
CN106228135A (en) * 2016-07-21 2016-12-14 深圳市喜悦智慧数据有限公司 The warning of a kind of identity-based identification/report danger method and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090080640A1 (en) * 2007-09-20 2009-03-26 Adam Waalkes System and method for retaining calls into a call center
CN104064182A (en) * 2014-06-24 2014-09-24 中国人民财产保险股份有限公司 A voice recognition system and method based on classification rules
CN107105109A (en) * 2016-02-23 2017-08-29 平安科技（深圳）有限公司 voice broadcast method and system
CN106709696A (en) * 2016-11-21 2017-05-24 中国平安财产保险股份有限公司 Self-service claim settlement realization method and system

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109544382A (en) * 2018-10-31 2019-03-29 平安医疗健康管理股份有限公司 It is a kind of that method for processing business and relevant device are handled based on data processing
WO2020140681A1 (en) * 2019-01-03 2020-07-09 深圳壹账通智能科技有限公司 Numerical value calculation method and apparatus, computer device, and storage medium
CN109903098A (en) * 2019-03-12 2019-06-18 安徽赛迪信息技术有限公司 A kind of identification of client identity and automatic clustering system
CN110196895A (en) * 2019-04-19 2019-09-03 平安科技（深圳）有限公司 User data information self-service query method, apparatus, computer equipment and storage medium
CN110196895B (en) * 2019-04-19 2022-05-17 平安科技（深圳）有限公司 User data information self-service query method and device, computer equipment and storage medium
CN111163234A (en) * 2019-12-31 2020-05-15 北京金山安全软件有限公司 Service call processing method and device, electronic equipment and storage medium
CN111163234B (en) * 2019-12-31 2021-01-22 北京金山安全软件有限公司 Service call processing method and device, electronic equipment and storage medium
CN113537774A (en) * 2021-07-16 2021-10-22 精英数智科技股份有限公司 Method and system for detecting whether coal mine enterprise policy is valid
CN113537774B (en) * 2021-07-16 2023-04-07 精英数智科技股份有限公司 Method and system for detecting whether policy of coal mine enterprise is effective or not
CN114125161A (en) * 2021-11-29 2022-03-01 阳光保险集团股份有限公司 Business handling method and system

Also Published As

Publication number Publication date
WO2019085095A1 (en) 2019-05-09
CN107800894B (en) 2020-01-10

Similar Documents

Publication Publication Date Title
CN107800894A (en) A kind of phonetic prompt method and terminal device for telephony service system
CN108596771A (en) Method, apparatus, user terminal and the block chain node device of insurance underwriting
CN108520073A (en) Air control data integration method, device, equipment and computer readable storage medium
CN110083623B (en) Business rule generation method and device
CN107784517A (en) A kind of customer information screening method and terminal device
CN107945030A (en) Collocation method, device, computer equipment and the storage medium of premium formula
CN107688645A (en) A kind of declaration form data processing method and terminal device
US8650052B1 (en) Configurable insurance policy forms inference
CN108830696A (en) Reference reports analyzing and processing method, device, computer equipment and storage medium
US20060184995A1 (en) Creating a privacy policy from a process model and verifying the compliance
CN108376364A (en) A kind of method, equipment and the terminal device of payment system reconciliation
CN108304522A (en) Comparison method, device and the terminal device of difference between a kind of database
US20130339846A1 (en) Multiparty document generation and management
CN108885631B (en) Method and system for contract management in a data marketplace
CN108764633A (en) A kind of method for allocating tasks, system and terminal device
CN107944870A (en) Transaction business processing method, system and terminal device based on e-commerce
CN108446968A (en) A kind of method, apparatus and terminal device of accounting entry
CN109801156A (en) A kind of lending risk management and control method and lending risk management and control equipment
CN109993417A (en) A kind of service condition mark adding method, device and storage medium
CN111639690A (en) Fraud analysis method, system, medium, and apparatus based on relational graph learning
CN107958059A (en) Intelligent answer method, apparatus, terminal and computer-readable recording medium
CN116090867A (en) Index rule generation method and device, electronic equipment and storage medium
CN108364230A (en) A kind of account is withdrawn deposit method, apparatus, terminal device and storage medium
CN109345193A (en) Declaration form based on information security saves checking method and terminal device from damage
WO2024060759A1 (en) Supply chain financial asset auditing method and apparatus, and device and 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
GR01 Patent grant
GR01 Patent grant