CN107800894B

CN107800894B - Intelligent voice prompt method and terminal equipment

Info

Publication number: CN107800894B
Application number: CN201711037115.8A
Authority: CN
Inventors: 彭小明; 李培彬
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2017-10-30
Filing date: 2017-10-30
Publication date: 2020-01-10
Anticipated expiration: 2037-10-30
Also published as: WO2019085095A1; CN107800894A

Abstract

The invention provides an intelligent voice prompt method and terminal equipment, which are applicable to the technical field of data processing, and the method comprises the following steps: acquiring a telephone number of a target object, and identifying an insurance application type and an insurance type to which the insurance application type is applied; inputting the operation record data, the insurance application seeds and the insurance node dates into a factor screening model corresponding to the insurance types to obtain class prompt factors corresponding to the insurance types respectively; if the obtained total factor number is less than or equal to the preset factor number, reading voice data of each prompt factor in the prompt factors for broadcasting; and if the total factor number is larger than the preset factor number, screening out the prompt factors with the highest priority and the preset factor number, and broadcasting the voice data of the screened prompt factors. The condition of excessive broadcasting can not occur while the finally output prompt factors are actually required by the target object, and the intelligent degree of the intelligent voice system for processing the telephone service is greatly improved.

Description

Intelligent voice prompt method and terminal equipment

Technical Field

The invention belongs to the technical field of data processing, and particularly relates to an intelligent voice prompt method and terminal equipment.

Background

When a telephone service of a customer is processed, an existing intelligent voice system at least comprises a welcome language and a level voice menu, and each voice menu at least comprises a specific service. Through voice broadcasting the business services of all levels of voice menus in sequence, the client is prompted and guided to carry out corresponding operation on the business services, and the client jumps to the corresponding business services to respond according to the operation of the incoming call client, so that the requirement of the client on the business services is met.

However, as the number and types of business businesses are continuously increased and refined, the structure of the intelligent voice system and the contained content are more and more complex and huge. After a call is made by a client, when business service selection and operation are performed under the guidance of the existing intelligent voice system, a large amount of useless waiting time needs to be consumed to wait for the intelligent voice system to broadcast the business service which is not required by the client, so that the client cannot acquire the required business service in time, the telephone business processing time of each client is long, and the operation load of the intelligent voice system is increased.

In summary, the existing intelligent voice system has low intelligent degree when processing the telephone service of the customer, and cannot provide the required service for the customer in time.

Disclosure of Invention

In view of this, embodiments of the present invention provide an intelligent voice prompting method and a terminal device, so as to solve the problem in the prior art that an intelligent voice system has a low intelligent degree for processing a telephone service.

A first aspect of an embodiment of the present invention provides an intelligent voice prompt method, including:

acquiring a telephone number of a target object at a call opposite end, performing customer attribute data matching on the target object by using the telephone number, and reading an insurance identifier and operation record data in the matched customer attribute data; analyzing the insurance identification, identifying M insurance types which are applied to the target object and N insurance types which the M insurance types belong to, and reading insurance node dates corresponding to the insurance identification, wherein M, N are integers which are larger than zero;

inputting the operation record data, the insurance application seeds and the insurance node dates to a factor screening model corresponding to the N types of insurance types, and respectively screening prompt factors of the N types of insurance types to obtain N1 types of prompt factors corresponding to the N types of insurance types, wherein the prompt factors are used for representing service to be played, and N1 is an integer which is greater than zero and less than or equal to M;

carrying out total factor quantity statistics on the obtained N1 prompting factors; if the total factor number is less than or equal to the preset factor number, reading voice data of each prompting factor in the N1 prompting factors, performing voice splicing on the read voice data by using a preset voice prompting template, and transmitting the voice spliced prompting voice data to a client terminal of a call opposite terminal for broadcasting;

if total factor quantity is greater than preset factor quantity, utilize operation record data is right all prompting factors in the N1 class prompting factors carry out priority sequencing, select the preceding factor quantity digit of presetting that the priority is the highest prompting factor to read corresponding voice data, utilize it is right to predetermine the voice prompt template corresponding voice data carries out the pronunciation concatenation, and will the pronunciation concatenation obtains the client terminal that suggestion voice data sent to the conversation opposite terminal and reports.

A second aspect of the embodiments of the present invention provides an intelligent voice prompt terminal device, where the intelligent voice prompt terminal device includes a memory and a processor, where the memory stores a computer program that can be run on the processor, and the processor implements the following steps when executing the computer program.

A third aspect of an embodiment of the present invention provides a computer-readable storage medium, including: a computer program is stored, characterized in that the computer program realizes the steps of the intelligent voice prompt method as described above when being executed by a processor.

Compared with the prior art, the embodiment of the invention has the following beneficial effects: the operation record data, the insurance type, the insurance node date and the insurance type of the target object are determined through the phone number matching of the target object, the insurance situation of the target object is analyzed by using the extracted data and the factor screening model, the screening of the prompt factors contained in the system is realized, and the finally obtained prompt factors are all the business services required by the target object. And finally, judging the preset number of the obtained prompt factors, and performing priority sorting screening when the preset number is exceeded, thereby ensuring that the number of the finally obtained prompt factors is not excessive and is the prompt factor with the highest possibility of target object demand. Therefore, the embodiment of the invention ensures that the finally output prompt factor is actually required by the target object, and simultaneously avoids the situation of excessive broadcasting, thereby greatly improving the intelligent degree of the intelligent voice system for processing the telephone service, and ensuring that the target object can obtain timely and effective voice broadcasting of the service when the telephone is accessed into the intelligent voice system.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a schematic flow chart illustrating an implementation process of an intelligent voice prompt method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart illustrating an implementation process of an intelligent voice prompt method according to a second embodiment of the present invention;

fig. 3 is a schematic flow chart illustrating an implementation of an intelligent voice prompt method according to a third embodiment of the present invention;

fig. 4 is a schematic flow chart illustrating an implementation of the intelligent voice prompt method according to the fourth embodiment of the present invention;

fig. 5 is a schematic flow chart illustrating an implementation of the intelligent voice prompt method according to the fifth embodiment of the present invention;

fig. 6 is a schematic structural diagram of an intelligent voice prompt apparatus according to a sixth embodiment of the present invention;

fig. 7 is a schematic diagram of an intelligent voice prompt terminal device according to a seventh embodiment of the present invention.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

In order to explain the technical means of the present invention, the following description will be given by way of specific examples.

Fig. 1 shows a flowchart of an implementation of the intelligent voice prompt method according to an embodiment of the present invention, which is detailed as follows:

s101, obtaining a telephone number of a target object at a call opposite end, matching client attribute data of the target object by using the telephone number, and reading insurance identification and operation record data in the matched client attribute data. Analyzing the insurance identification, identifying M insurance types which are applied to the target object and N insurance types which the M insurance types belong to, and reading insurance node dates corresponding to the insurance identification, wherein M, N are integers which are larger than zero.

The target object refers to a user (i.e., a client in the embodiment of the present invention) who accesses the intelligent voice system and communicates with the intelligent voice system by using a terminal device capable of making a call. Customer attribute data includes, but is not limited to: all relevant data of the insurance purchased by the customer (such as policy data of all the purchased insurance), operation record data of business services performed by the customer through the intelligent voice system, and personal information (such as telephone number, name and the like) of the customer. The insurance indicia is used to record the risk categories specifically purchased by the customer. The operation record data is used for recording historical operation data corresponding to the business handled by the client telephone, such as the vehicle insurance report and the case progress inquiry. The historical operation data can be stored in a form of identification plus time, namely, as long as the identification of a certain service is contained, the service is processed by a client telephone, and meanwhile, the time for the client to process the service can be determined by the time corresponding to the identification.

In the embodiment of the invention, the client attribute data is stored and can be directly acquired because the client requires to record the personal information of the client and relevant data for purchasing insurance when the client commits insurance, and simultaneously records the operation data of the client to obtain the operation record data when the client uses the intelligent voice system to perform business service operation. Since the customer attribute data is stored in the storage medium in a specific data format (such as binary format, etc.), when recording the specific insurance application purchased by the customer, the data converted from the insurance application into the corresponding data format is also stored. In the embodiment of the present invention, before S101, the insurance application of the client is converted into the insurance identifier in the client attribute data storage data format for storage, so that the insurance application of the client can be obtained by performing data format analysis on the insurance identifier. Since the same customer may purchase a plurality of different insurance types, in the embodiment of the present invention, the insurance identification of the customer may correspond to a plurality of different insurance application types at the same time.

In order to facilitate the reader to further understand the principle of the insurance mark, a specific data storage mode embodiment as the insurance mark is described by taking the example that the customer purchases the regular life insurance and the vehicle loss insurance at the same time, and meanwhile, the customer attribute data is assumed to be stored in a binary data format. Since each insurance company sets a unique code corresponding to the risk type provided by the insurance company, for example, the risk type code of the regular life risk can be set as 32, and the vehicle loss risk can be set as 20, the risk type code corresponding to the purchase risk of the customer can be determined through the risk type code table set by the insurance company, and at this time, the risk type codes 32 and 20 corresponding to the regular life risk and the vehicle loss risk can be converted into corresponding binary data 000001 and 00101, and stored as insurance identification data. When the insurance application types of the client are identified, 000001 and 00101 in the insurance identification are read out and are converted and analyzed to obtain the insurance codes 32 and 20, and the insurance application types of the client are determined through inquiry of the insurance code table, so that the analysis process of the insurance identification is completed.

In S101, after receiving an incoming call from a client, the intelligent voice system first compares and matches the telephone number of the incoming call with the telephone numbers in the stored client attribute data, and determines the found client attribute data containing the same telephone number as the incoming call as the client attribute data of the incoming call client. After the client attribute data of the calling client is determined, the insurance identification and the operation record data are read from the client attribute data, the insurance type which is applied by the client is identified by analyzing the insurance identification, and the insurance type query is carried out by utilizing the prestored insurance type-insurance type association data to determine the insurance type which the insurance type applied by each client belongs to.

As can be seen from the above description, each customer may purchase a plurality of different insurance types, so M in the embodiment of the present invention is an integer greater than 0, and since each insurance application type is at least classified into one insurance type, different insurance application types may be simultaneously classified into the same insurance type, such as regular life insurance, dividend insurance, universal insurance and connection insurance, the actual sizes of M and N should be determined by querying the stored insurance application type-insurance type association data, but certainly, since each insurance application type is at least classified into one insurance type, N is an integer greater than 0.

S102, inputting the operation record data, the insurance application types and the insurance node dates into a factor screening model corresponding to the N types of insurance types, and respectively screening the prompting factors of the N types of insurance types to obtain N1 prompting factors corresponding to the N types of insurance types, wherein the prompting factors are used for representing the service to be played, and N1 is an integer which is greater than zero and less than or equal to M.

In the embodiment of the invention, the prompt factor is used for representing the business service to be broadcasted, and after the prompt factor to be broadcasted is determined, the broadcasting of the business service can be completed only by reading and broadcasting the voice data corresponding to the prompt factor. The factor screening model is used for screening prompt factors for insurance types according to preset screening rules to obtain the prompt factors corresponding to each insurance type, wherein the screening rules corresponding to each insurance type are different, and specific data required to be used are different.

Specifically, after the operation record data, insurance application types and insurance node dates are obtained, the factor screening model firstly finds out the screening rule corresponding to each insurance type in the N types of insurance types, and determines the required data according to the screening rule, for example, for a car insurance type, the factor screening is prompted according to whether a customer is a rule of first reporting in the validity period of the current car insurance policy, and the car insurance report identifier in the operation record data can be used for identifying whether the customer is the number of reporting in the validity period of the current car insurance policy, so for the car insurance type, the required data includes the operation record data. After the data required by the insurance types are determined, the required data are processed and judged according to the screening rules to obtain the prompt factors corresponding to each insurance type (because the screening rules of each insurance type are complex, and the screening process of the prompt factors is complicated, the detailed screening process of the screening rules is omitted in the first embodiment of the invention, and the second embodiment of the invention and the fourth embodiment of the invention are referred to in detail).

It should be understood that the specific situation of the insurance types under each insurance type may be different, for example, for the life insurance type, the insurance types include special insurance types (such as red-separating insurance, universal insurance, continuous insurance, and the like) and non-special insurance types (such as lifetime insurance, periodic life insurance, double insurance, and the like), and for the insurance types under different situations, the screening using the same screening rule is difficult. Therefore, in the embodiment of the present invention, different filtering rules are set for insurance types under different specific situations of the insurance type, so as to obtain the prompt factor with the only corresponding type for each specific situation, and therefore, in the embodiment of the present invention, the type of the prompt factor finally obtained for each insurance type is also different according to different specific situations of the included insurance types, that is, after the filtering is performed by using the filtering rules, each insurance type may correspond to different types of prompt factors at the same time. However, each specific insurance application is unique to the specific situation, for example, the universal insurance application belongs to a special insurance application, that is, the type of the cue factor corresponding to each specific insurance application is unique, so in the embodiment of the present invention, N1 is an integer greater than or equal to zero and less than or equal to M. In order to enable the factor screening model to accurately identify the specific conditions of insurance types subordinate to each insurance type, in the embodiment of the invention, a query data table of the specific conditions of the insurance types is pre-stored for each insurance type, for example, a special insurance type table is pre-stored for the life insurance type, and the specific conditions corresponding to the insurance types can be queried and classified through the query data table so as to ensure the implementation of different subsequent screening for different specific conditions.

And S103, carrying out total factor quantity statistics on the obtained N1 prompting factors. And if the total factor quantity is less than or equal to the preset factor quantity, reading voice data of each prompting factor in the N1 prompting factors, performing voice splicing on the read voice data by using a preset voice prompting template, and transmitting the voice spliced prompting voice data to a client terminal of the opposite call end for broadcasting.

Because the purchasing conditions of insurance varieties of each customer are different, the number of the corresponding finally screened prompt factors is different, for example, if some customers only purchase a single insurance variety, the number of the prompt factors obtained after the factor screening model is screened is generally less, and for some customers who purchase a plurality of different insurance varieties simultaneously, the number of the finally screened prompt factors is generally more. When the intelligent voice system broadcasts the service, if the number of the service broadcasted is too large, a large amount of waiting time of the client is consumed, and the operation load of the intelligent voice system is increased. In order to reduce the waiting time of the client and reduce the operation load of the intelligent voice system so as to improve the intelligent degree of the telephone service processing of the client, in the embodiment of the invention, after the final N1 prompting factors are obtained, the total factor number of all the prompting factors is counted, whether the total factor number exceeds the preset factor number is judged, if not, the current total factor number belongs to the range of acceptable broadcasting number, and at the moment, the prompting factors can be broadcasted.

In the embodiment of the invention, voice splicing refers to combining preset voice templates and voice data of prompt factors to obtain prompt voice data needing to be broadcasted.

Further, as a preferred embodiment of the present invention, a plurality of different voice prompt templates may be preset for selection. For example, two voice prompt templates are preset as follows: the first template "welcome call XXXX (insurance company name), please simply say the business you need to do, for example: xx "and a second template" welcome to the phone XXXX asking you for xx? ", wherein xx is used for filling in the cue factor when the speech is spliced.

It is assumed that the number of predetermined factors is greater than 3. When the number of the finally screened prompt factors is more than 0 and less than 3, such as 'contact survey loss assessment personnel', 'vehicle insurance application' and 'vehicle insurance application revocation', the first template is preferably selected for voice splicing, and the following prompt voice data are obtained: "welcome to call XXXX (insurance company name), please simply say the business you need to do, for example: contacting the surveyed loss assessment personnel, the vehicle insurance report and the vehicle insurance report revocation ", and when the number of the finally screened prompting factors is 1, such as the number of the finally screened prompting factors is 'vehicle insurance report', preferably performing voice splicing by using a second template to obtain the following prompting voice data: "welcome to call XXXX asking you about a car insurance application? ", to improve the efficiency of voice prompt.

And S104, if the total factor number is larger than the preset factor number, performing priority sequencing on all prompting factors in the N1 prompting factors by using the operation record data, screening out the prompting factor with the highest priority and the number of the front preset factor, reading corresponding voice data, performing voice splicing on the corresponding voice data by using a preset voice prompting template, and transmitting the voice spliced prompting voice data to a client terminal of a call opposite terminal for broadcasting.

When the total factor number is larger than the preset factor number, the current total factor number is beyond the range of the acceptable broadcast number, and at this time, the prompt factors need to be screened to obtain the prompt factors meeting the preset factor number for broadcast. As a specific implementation manner of the present invention for performing priority ranking on the prompt factors, considering that business service requirements of customers in different time periods are different, in the embodiment of the present invention, a business service operation record in a latest preset time period is read from operation record data, and priority ranking is performed according to the business service operation times of the business service corresponding to the prompt factors. Wherein the specific value of the latest preset time length needs to be set by a technician according to the actual situation.

After the final prompt factor needing to be broadcasted is determined, the voice data of the prompt factor is read and voice splicing is carried out, the specific operation steps are the same as those of S103, and the detailed description is omitted here.

In the embodiment of the invention, after the client attribute data of the target object is matched through the telephone number of the target object, the operation record, the insurance application type, the insurance node date and the insurance application type of the target object are extracted by using the client attribute data, and the insurance application condition of the target object is analyzed by using the extracted data and the factor screening model, so that the prompt factors contained in the system are screened, and the finally obtained prompt factors are ensured to be the business services required by the target object. And finally, judging the preset number of the obtained prompt factors, and performing priority sorting screening when the preset number is exceeded, thereby ensuring that the number of the finally obtained prompt factors is not excessive and is the prompt factor with the highest possibility of target object demand. Therefore, the embodiment of the invention ensures that the finally output prompt factor is actually required by the target object, and simultaneously avoids the situation of excessive broadcasting, thereby greatly improving the intelligent degree of the intelligent voice system for processing the telephone service, and ensuring that the target object can obtain timely and effective voice broadcasting of the service when the telephone is accessed into the intelligent voice system.

As a preferred implementation manner of S102, as shown in fig. 2, the second embodiment of the present invention includes:

and S1021, when the insurance types of the N types comprise the vehicle insurance types, extracting an operation record data segment within the validity period of the current vehicle insurance policy from the operation record data, and judging whether the operation record data segment comprises a vehicle insurance application case identifier.

Considering that after a customer buys a car insurance, the customer generally calls for a car insurance report only when a car accident occurs, and generally calls again within a few natural days after the car insurance report to inquire the schedule of the case flow and perform business service operation. Therefore, in the embodiment of the present invention, when the N-type insurance types include a vehicle insurance type, a valid period of a vehicle insurance policy currently in which a customer makes an insurance policy valid is determined, for example, from 11/2016 to 10/11/2017, an operation record data segment from a valid period start time to a current time is extracted from the operation record data, and when the current time is 9/10/2017, an operation record data segment from 11/2016 to 10/9/2017 is extracted from the operation record data, and whether the operation record data segment includes a vehicle insurance declaration identification is detected.

And S1022, if the operation record data section does not contain the vehicle insurance application case identification, screening the prompting factors related to the vehicle insurance according to the vehicle insurance purchase record data in the customer attribute data to obtain the first type of prompting factors.

In the embodiment of the invention, the intelligent voice system records the operation of the incoming call of the customer for the vehicle insurance reporting as the vehicle insurance reporting identification, namely writes the vehicle insurance reporting identification into the operation record data and records the reporting time when the incoming call of the customer for the vehicle insurance reporting. Therefore, when the operation record data segment does not contain the vehicle insurance registration report identification, the vehicle insurance policy client which is effective for the current insurance application is not yet made a vehicle insurance registration. As a specific implementation manner of S1022, prompting factors related to the vehicle insurance, such as "vehicle insurance report", "vehicle insurance consult", and "vehicle insurance recommendation", etc., are read, the prompting factors are sorted according to the operation frequency of the big data, and the required prompting factors are screened out, wherein the number of the specifically required prompting factors can be set by a technician according to the actual requirement. As another specific implementation manner of S1022, on the basis of the former implementation manner, the "car insurance coverage" does not need to be sorted, but is directly used as one of the required prompting factors, so as to facilitate the customer to directly perform the car insurance coverage when needed.

S1023, if the operation record data section contains the vehicle insurance reporting case identification, reading the reporting time of the vehicle insurance reporting case identification, calculating the difference between the current time and the reporting time, matching the obtained difference with the stored case flow time table in the case flow stage, and determining the case flow stage of the current time.

In the embodiment of the invention, the case flow stage mainly comprises the following steps: the system comprises a loss checking stage and a claim payment processing stage, wherein the loss checking stage corresponds to a case flow from the beginning of a vehicle insurance application to the determination of a claim payment amount, and the claim payment processing stage corresponds to a case flow from the determination of the claim payment amount to the completion of the claim payment.

When the operation record data segment contains the vehicle insurance reporting case identification, namely the fact that the client has already carried out the vehicle insurance reporting case is explained, the case processing flow is started. Although the requirement of each insurance company on the case processing flow time of the car insurance cases is different, if some insurance companies require that the case must be settled within 72 hours from the reporting time and some require that the case must be settled within 5 working days from the reporting time, the requirement of the case processing flow time of each insurance company is fixed, and the case flow stages are the same, so that for each insurance company, a technician can work out a case flow time table according to the requirement of the insurance company on the case processing flow time and the case flow stages so as to inquire the case flow stage at the current time by an intelligent voice system.

And S1024, when the case flow stage at the current time is a damage investigation stage, extracting the first type of prompting factors which are related to the damage assessment personnel, the vehicle insurance report and the vehicle insurance cancellation report. And when the case flow stage of the current time is the reimbursement processing stage, extracting case progress and money inquiry, vehicle insurance application and vehicle insurance revocation application in the prompt factors as a first class of prompt factors.

The major difference between the reconnaissance damage stage and the claim processing stage is whether the claim amount is determined. In the damage checking stage, a damage assessment is carried out on the vehicle by a damage assessment person to determine the amount of the claim, so that the client may need to contact the damage assessment person at any time in the stage. For the reimbursement processing stage, the insurance company will audit the customer's data and the accident data and verify whether the reimbursement amount meets the specified requirements. Therefore, when the current time is in the damage investigation and verification stage, the first type prompting factor needs to be added with 'contact with the person who finds the damage', and when the current time is in the reimbursement processing stage, the first type prompting factor needs to be added with 'case progress and money inquiry'.

In the embodiment of the invention, the corresponding prompt factor screening rule is selected by judging whether the client carries out the automobile insurance reporting on the currently-guaranteed effective automobile insurance policy before the current incoming call. When the vehicle insurance application is not carried out, prompting factors related to the vehicle insurance are screened for the client to obtain the required first class of prompting factors, and when the vehicle insurance application is carried out, the case flow stage of the current time is identified according to the case flow time table, and the corresponding prompting factors are determined according to the specific stage, so that the embodiment of the invention can realize intelligent identification processing of the vehicle insurance type, screen out the prompting factors which are most suitable for the actual requirements for the client, and improve the intelligent degree of the intelligent voice system for processing the telephone service of the client.

As a preferred implementation manner of S102, as shown in fig. 3, as a third embodiment of the present invention, the method includes:

s1025, when the N types of insurance types comprise life insurance types, classifying insurance application types under the life insurance types by using the special risk type table, identifying special risk types and non-special risk types contained in the insurance application types under the life insurance types, and inquiring key node dates of insurance nodes to determine key node dates corresponding to the special risk types.

As can be seen from the above description about S102, the specific situations of the insurance types under each insurance type are different, and in the embodiment of the present invention, the specific situations of the insurance types under the life insurance type are divided into two categories, i.e., a special insurance type and a non-special insurance type, and a special insurance table is stored in advance, and after the special insurance type is queried by using the table, the classification of the insurance types under the life insurance type can be realized.

For each special risk, the special risk has a key node date, and the specific conditions of the special risk can be inquired by performing periodic calculation on the basis of the key node date. For example, for dividend insurance, since insurance companies distribute dividend to customers on the annual policy effective date of each year, the policy effective date is the key point date of the dividend insurance, and the allocation of dividend to dividend insurance can be inquired after the annual insurance effective yearly date of each year. For the universal insurance, the policy validation date is the key point date of the policy since the policy validation date is also taken as the starting point for the periodic calculation. For continuous insurance, the payment is flexible, the premium can be added at any time, and the periodic calculation is carried out again by taking the successful date of the premium payment as a starting point every time, so that the successful date of the premium payment is the key point date of the continuous insurance.

And S1026, calculating the effective prompting time of the special dangerous species by using the date of the key node and the stored effective time length table, and taking the account inquiry prompt of the special dangerous species as a second-class prompting factor when the current time is judged to be within the effective prompting time range of the special dangerous species.

As can be seen from the above description, the customer only needs to call after the key node date of the special risk category to inquire the specific situation of the special risk category. In the embodiment of the invention, in order to realize intelligent identification of whether a customer can inquire the specific condition of the special dangerous species, and when the identification result is that the customer can inquire, the voice broadcast is carried out on the account inquiry prompt corresponding to the special dangerous species. Firstly, an effective time length table is preset, the effective time length corresponding to each special dangerous type is recorded in the table, and then the effective prompting time of the special dangerous type can be obtained by calculating the key node date and the table. For example, if the effective duration corresponding to the risk of dividend is 30 days and the policy preservation life is 8 months and 1 day, then 8 months and No. 1 to No. 31 of each year are the effective prompting time of the risk of dividend.

As a specific implementation manner of S1026, the method includes:

if the special risk category is the dividend risk, taking the policy validation date T1 as the key node date of the dividend risk, reading the valid duration n days of the dividend risk, and taking the policy validation date T1+ n days of each year as the valid prompt time of the dividend risk, wherein n is preferably 30.

If the special risk category is universal risk, taking the policy effective date T2 as the key node date of the universal risk, and taking the first n1 days of each month after T2+ H year as the effective prompting time of the universal risk, preferably, H is 3, and n1 is 11.

If the special risk category is the risk, taking the renewal premium payment success date T3 as the key node date of the risk, reading the effective duration n2 days of the risk, taking the T3-T3 + n2 days as the effective prompt time of the risk, and preferably, n2 is 5.

n, n1, and n2 are all positive integers greater than zero.

Because the purchasing relationship between the three special risk types is mutually exclusive, namely, only one of the three special risk types can be purchased in the same time period by the client. After the effective prompting time of the special risk is determined, whether the current time belongs to the effective prompting time range corresponding to the purchased special risk is judged, if the current time belongs to the effective prompting time range, the account inquiry prompting of the special risk is used as a second type prompting factor, if the special risk is purchased, the current time is 8 months and 10, and the account inquiry prompting time belongs to the effective prompting time from 8 months and 1 to 31 of the dividend risk, and at the moment, the prompting factor of 'dividend account inquiry' is used as the second type prompting factor in the embodiment of the invention.

S1027, the insurance node date is input into the node date analysis model to obtain the effective prompt time of the non-special dangerous species, and when the current time is judged to be within the effective prompt time range of the non-special dangerous species, the information query prompt of the non-special dangerous species is used as a third prompt factor.

In S1027, non-specific risk species (such as lifetime risk, periodic lifetime risk, and two-full insurance) in the life insurance type are mainly processed to obtain the prompting factor of the non-specific risk species. Compared with special risk types, the states between the risk types in the non-special risk types are universal, the possible situations corresponding to insurance node dates are the same, and the special states (such as the state of dividend danger of dividend distribution, the state of universal danger of repeated profit roll and the state of benefit distribution in case of continuous insurance) of each risk type in the special risk types cannot be similar to the special states of each risk type in the special risk types, so that the non-special danger can be directly processed by using the same prompt factor screening rule. Therefore, in the node date analysis model processing of the embodiment of the invention, the specific risk species identification is not carried out on the insurance application risk species, but all insurance node dates are directly input into the node date analysis model for analysis.

In the embodiment of the invention, after the insurance node date is obtained, the node date analysis model inquires the effective duration corresponding to each insurance node date, calculates the effective prompt time of non-special dangerous species according to the insurance node date and the effective duration, and judges whether the effective prompt time is in the current time so as to extract the required prompt factor.

It should be understood that, because there are many dates of insurance nodes without special risk categories, for example, the common dates of insurance nodes include policy payment date, policy validation date, policy expiration date, date of filing and claim material by customers, date of filing and claim reporting by customers, date of repayment of policy loan, date of changing operators, and date of transacting security services, and there may be many valid durations corresponding to each date of insurance nodes, there are many valid prompt times generated in the embodiment of the present invention. The node date analysis model compares the current time with the effective prompt time one by one, and respectively determines the prompt factors corresponding to each insurance node date.

As a specific implementation of S1027, as shown in table 1:

TABLE 1

In table 1 of the embodiment of the present invention, valid durations corresponding to various insurance node dates and corresponding prompt factors are preset, after the insurance node dates are input into the node date analysis model, the valid prompt time of each insurance node date can be directly calculated according to the insurance node dates and the valid durations in table 1, and when it is determined that the current time is within the valid prompt time, the corresponding information query prompt is extracted to obtain a third class of prompt factors.

Further, as a preferred embodiment of the present invention, while calculating the effective prompt time, some query judgments on the client insurance application condition may be added, and the prompt factors are further screened according to the judgment result, so as to improve the matching degree between the finally obtained prompt factors and the client. If the effective time of the insurance policy payment day is +60 days and more than 15 days, the judgment on the payment condition of the client insurance fee can be added, if the client pays the insurance fee, the client does not need to prompt the fast payment, and only needs to screen out the insurance fee to be paid to the account for inquiry.

In the embodiment of the invention, the life insurance type is divided by taking the state between the dangerous species and the dangerous species as a standard to obtain the special dangerous species table, the special dangerous species table is used for dividing the special dangerous species and the non-special dangerous species from the life insurance type, the effective prompt time of the two dangerous species is calculated respectively according to the characteristics of the dangerous species, and the corresponding prompt factor is extracted when the current time meets the effective prompt time range. Therefore, the embodiment of the invention can realize targeted prompt factor screening according to the security risk types of the clients and improve the intelligent degree of the intelligent voice system for processing the telephone service of the clients. Meanwhile, the embodiment of the invention can further screen the prompt factors according to the client insurance application condition, so that the prompt factors with higher matching degree with the client requirements can be obtained through screening.

As a preferred implementation manner of S102, as shown in fig. 4, a fourth embodiment of the present invention includes:

s1028, when the N types of insurance types comprise life insurance types, detecting whether the client attribute data comprise any one or more special identifications of a paper mail refund identification, a survivor fund unreceived identification and an identity card invalidation identification.

For the life insurance type, in addition to the insurance business service consultation handling mentioned in the above embodiments, there may be several more specific cases: 1. due to the fact that the contact address of the client is wrongly written, the paper letter of the insurance policy cannot be normally delivered, and therefore the condition of letter quitting occurs. 2. The client forgets that the insurance policy which is applied by the client has unreceived survival funds. 3. The validity period of the identity card used by the client for insurance application is over, so that the information of insurance application is asymmetric. The letter quitting mark, the survivor gold non-receiving mark and the identity card failure mark of the paper letter correspond to three special cases respectively.

For these special cases, the conventional processing method of insurance companies is to manually communicate with the client by telephone to inform the client of the existence of these special cases and prompt the client to modify, so that it needs to consume a large amount of labor cost to complete the work. In the embodiment of the invention, in order to increase the processing intelligentization degree of the telephone service of the client, whether the client has the special condition or not is also detected when the client calls.

S1029, if the client attribute data includes any one or more special marks of a paper letter trust-returning mark, a survival fund non-drawing mark and an identity card invalidation mark, extracting a consultation modification prompt of the special mark included in the client attribute data from the prompt factors, and using the consultation modification prompt as a fourth type prompt factor.

When it is detected that the client attribute data includes the special identifier, that is, the special condition exists, the existing specific condition is notified to the client, specifically, for each special condition, a corresponding consultation modification prompt is independently set, for example, for special condition 1, the corresponding consultation modification prompt may be set to "your insurance policy paper letter contact address is wrong, please modify the contact address", for special condition 2, the corresponding consultation modification prompt may be set to "you have no fund to be drawn, and whether the fund needs to draw the consultation", and for special condition 3, the corresponding consultation modification prompt may be set to "your identity card is expired, please change the certificate". It should be understood that, since there is no mutual exclusion relationship between the above three special cases, the probabilities of occurrence of the three special cases are independent, and may be either none or both.

In the embodiment of the invention, the intelligent voice system is used for automatically detecting whether the client has special conditions of contact address error, survival fund unreceived and identity card validity period, and extracting the consultation modification prompt corresponding to the special conditions when the special conditions are detected, so that the follow-up voice report can be provided for informing the user.

As a fifth preferred embodiment of the present invention, as shown in fig. 5, the method includes:

s501, voice data of the target object are collected, and voice recognition and keyword matching are carried out on the voice data.

S502, when the voice data is recognized to contain the preset keywords, sending the manual service prompting voice data to a client terminal of a call opposite terminal, and switching the call to a manual service account when receiving an access confirmation instruction returned by the target object based on the manual service prompting voice data within the preset time.

In the first to fourth embodiments of the present invention, the finally broadcasted services are service services with the preset factor number, and the limited number of service services sometimes cannot well meet the actual requirements of the client, for example, the client wants to handle a plurality of different services together when the client calls this time, but the service broadcasted by the intelligent voice system includes a part of services required by the client. In order to meet the actual requirements of users, in the embodiment of the invention, some keywords such as switching, manual service and customer service are preset, the voice data of the customers are detected in real time in the incoming call process of the customers, and the keywords are automatically switched to the manual service when being detected to be included.

As another preferred embodiment of the present invention, the present invention further comprises: and acquiring voice data of the target object, performing voice recognition and factor keyword matching on the voice data, and broadcasting service services corresponding to the factor keywords when the voice data is recognized to contain the factor keywords.

In the embodiment of the invention, whether the business service is spoken in the incoming call process of the client can be detected in real time, and when the business service is spoken by the client, the corresponding business service is automatically reported so as to help the client to quickly operate the business service.

Fig. 6 shows a block diagram of the intelligent voice prompt apparatus provided in the embodiment of the present invention, which corresponds to the method in the above embodiment, and for convenience of description, only the parts related to the embodiment of the present invention are shown. The intelligent voice prompt device illustrated in fig. 6 may be an execution subject of the intelligent voice prompt method provided in the first embodiment.

Referring to fig. 6, the intelligent voice guidance apparatus includes:

the data acquisition module 61 is configured to acquire a telephone number of a target object at a call opposite end, perform client attribute data matching on the target object by using the telephone number, and read an insurance identifier and operation record data in the client attribute data that are matched. Analyzing the insurance identification, identifying M insurance types which are applied to the target object and N insurance types which the M insurance types belong to, and reading insurance node dates corresponding to the insurance identification, wherein M, N are integers which are larger than zero.

And a factor screening module 62, configured to input the operation record data, the insurance application seeds, and the insurance node dates to a factor screening model corresponding to the N types of insurance types, and perform prompt factor screening on the N types of insurance types respectively to obtain N1 types of prompt factors corresponding to the N types of insurance types, where the prompt factors are used to represent service to be played, and N1 is an integer greater than zero and less than or equal to M.

And the first voice broadcasting module 63 is configured to perform total factor quantity statistics on the obtained N1 prompting factors. And if the total factor quantity is less than or equal to the preset factor quantity, reading voice data of each prompting factor in the N1 prompting factors, performing voice splicing on the read voice data by using a preset voice prompting template, and sending the voice spliced prompting voice data to a client terminal of the opposite call terminal for broadcasting.

Second voice broadcast module 64 for if total factor quantity is greater than and predetermines factor quantity, utilize operation record data is right all suggestion factors in the suggestion factor of N1 type carry out priority sequencing, select the highest preceding factor quantity position of predetermineeing of priority the suggestion factor to read corresponding voice data, utilize predetermine voice prompt template right corresponding voice data carries out the pronunciation concatenation, and will the pronunciation concatenation is reported to the customer end terminal of conversation opposite terminal by the suggestion voice data transmission.

Further, the factor screening module comprises:

and when the N types of insurance types comprise the vehicle insurance types, extracting an operation record data segment within the validity period of the current vehicle insurance policy from the operation record data, and judging whether the operation record data segment comprises a vehicle insurance application case identifier.

And if the operation record data section does not contain the vehicle insurance application case identification, screening the prompting factors related to the vehicle insurance according to the vehicle insurance purchase record data in the customer attribute data to obtain a first class of prompting factors.

And if the operation record data section contains the vehicle insurance reporting case identification, reading the reporting time of the vehicle insurance reporting case identification, calculating the difference between the current time and the reporting time, matching the obtained difference with a stored case flow time table in a case flow stage, and determining the case flow stage of the current time.

And when the case flow stage at the current time is a damage investigation stage, extracting the contact investigation loss assessment personnel, the vehicle insurance application and the vehicle insurance application in the prompting factors as the first type of prompting factors. And when the case flow stage at the current time is a reimbursement processing stage, extracting case progress and money inquiry, the vehicle insurance application and the vehicle insurance revocation application in the prompt factors as the first type of prompt factors.

Further, the factor screening module further comprises:

when the N types of insurance types comprise life insurance types, classifying insurance application types under the life insurance types by using a special risk type table, identifying special risk types and non-special risk types contained in the insurance application types under the life insurance types, and performing key node date query on the insurance node dates to determine key node dates corresponding to the special risk types.

And calculating the effective prompting time of the special dangerous species by using the date of the key node and a stored effective time length table, and taking the account inquiry prompt of the special dangerous species as a second class prompting factor when judging that the current time is within the effective prompting time range of the special dangerous species.

And inputting the insurance node date into a node date analysis model to obtain the effective prompt time of the non-special dangerous species, and taking the information inquiry prompt of the non-special dangerous species as a third class prompt factor when judging that the current time is within the effective prompt time range of the non-special dangerous species.

Further, this intelligent voice prompt device still includes:

and when the N types of insurance types comprise life insurance types, detecting whether the client attribute data comprises any one or more special identifications of a paper mail refund identification, a survivor fund unreceived identification and an identity card invalidation identification.

And if the client attribute data contains any one or more special marks of a paper letter refunding mark, a survivor fund unreceived mark and an identity card invalidation mark, extracting a consultation modification prompt of the special marks contained in the client attribute data from the prompt factors, and using the consultation modification prompt as a fourth type of prompt factor.

Further, this intelligent voice prompt device still includes:

and collecting voice data of the target object, and performing voice recognition and keyword matching on the voice data.

And when recognizing that the voice data contains a preset keyword, sending manual service prompting voice data to the client terminal of the opposite call end, and switching the call to a manual service account when receiving an access confirmation instruction returned by the target object based on the manual service prompting voice data within preset time.

The process of implementing each function by each module in the intelligent voice prompt device provided by the embodiment of the present invention may specifically refer to the description of the first embodiment shown in fig. 1, and is not described herein again.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

It will also be understood that, although the terms first, second, etc. may be used herein to describe various elements in some embodiments of the invention, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first contact may be termed a second contact, and, similarly, a second contact may be termed a first contact, without departing from the scope of the various described embodiments. The first contact and the second contact are both contacts, but they are not the same contact.

Fig. 7 is a schematic diagram of an intelligent voice prompt terminal device according to an embodiment of the present invention. As shown in fig. 7, the intelligent voice guidance terminal device 7 of this embodiment includes: a processor 70, a memory 71, said memory 71 having stored therein a computer program 72 operable on said processor 70. The processor 70, when executing the computer program 72, implements the steps of the above-described various embodiments of the intelligent voice guidance method, such as the steps 101 to 104 shown in fig. 1. Alternatively, the processor 70, when executing the computer program 72, implements the functions of the modules/units in the above-described device embodiments, such as the functions of the modules 61 to 64 shown in fig. 6.

The intelligent voice prompt terminal device 7 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The intelligent voice prompt terminal equipment can include, but is not limited to, a processor 70 and a memory 71. It will be understood by those skilled in the art that fig. 7 is only an example of the intelligent voice prompt terminal device 7, and does not constitute a limitation to the intelligent voice prompt terminal device 7, and may include more or less components than those shown, or combine some components, or different components, for example, the intelligent voice prompt terminal device may further include an input-output device, a network access device, a bus, etc.

The Processor 70 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 71 is at least one type of computer readable storage medium, and may be an internal storage unit of the intelligent voice prompt terminal device 7, such as a hard disk or a memory of the intelligent voice prompt terminal device 7. The memory 71 may also be an external storage device of the intelligent voice-operated terminal device 7, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are equipped on the intelligent voice-operated terminal device 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the intelligent voice prompt terminal device 7. The memory 71 is used for storing the computer program and other programs and data required by the intelligent voice prompt terminal equipment. The memory 71 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims

1. An intelligent voice prompt method is characterized by comprising the following steps:

inputting the operation record data, the insurance application seeds and the insurance node dates to a factor screening model corresponding to the N types of insurance types, and respectively screening prompt factors of the N types of insurance types to obtain N1 types of prompt factors corresponding to the N types of insurance types, wherein the prompt factors are used for expressing the refined service to be played, and N1 is an integer which is greater than zero and less than or equal to M;

if the total factor number is greater than the preset factor number, performing priority ordering on all prompting factors in the N1 prompting factors by using the operation record data, screening out the prompting factors with the highest priority and the number of the front preset factors, reading corresponding voice data, performing voice splicing on the corresponding voice data by using the preset voice prompting template, sending the voice spliced prompting voice data to a client terminal of a call opposite terminal for broadcasting, wherein the priority ordering comprises reading out the business service operation record within the latest preset time length from the operation record data, and performing priority ordering according to the business service operation times of the business service corresponding to the prompting factors;

inputting the operation record data, the insurance application seeds and the insurance node dates into a factor screening model corresponding to the N types of insurance types, and respectively screening prompt factors of the N types of insurance types to obtain N1 types of prompt factors corresponding to the N types of insurance types, wherein the method comprises the following steps:

when the N types of insurance types comprise the vehicle insurance types, extracting an operation record data segment within the validity period of the current vehicle insurance policy from the operation record data, and judging whether the operation record data segment comprises a vehicle insurance application case identifier or not;

if the operation record data segment does not contain the vehicle insurance application case identification, screening the prompting factors related to the vehicle insurance according to the vehicle insurance purchase record data in the customer attribute data to obtain first class prompting factors;

if the operation record data segment contains the vehicle insurance reporting case identification, reading the reporting time of the vehicle insurance reporting case identification, calculating the difference between the current time and the reporting time, matching the obtained difference with the stored case flow time table in the case flow stage, and determining the case flow stage of the current time;

when the case flow stage at the current time is a damage investigation stage, extracting the contact investigation loss assessment personnel, the vehicle insurance application and the vehicle insurance application in the prompt factors as the first class of prompt factors; when the case flow stage of the current time is a reimbursement processing stage, extracting case progress and money inquiry, the vehicle insurance application and the vehicle insurance revocation application in the prompt factors as the first type of prompt factors;

the inputting the operation record data, the insurance application seeds and the insurance node dates into the factor screening model corresponding to the N types of insurance types, and respectively screening the N types of insurance types by using the prompt factors to obtain N1 types of prompt factors corresponding to the N types of insurance types, further comprising:

when the N types of insurance types comprise life insurance types, classifying insurance application types under the life insurance types by using a special risk type table, identifying special risk types and non-special risk types contained in the insurance application types under the life insurance types, and performing key node date query on insurance node dates to determine key node dates corresponding to the special risk types;

calculating the effective prompting time of the special dangerous species by using the date of the key node and a stored effective time length table, and taking the account inquiry prompt of the special dangerous species as a second class prompting factor when judging that the current time is within the effective prompting time range of the special dangerous species;

2. The intelligent voice prompt method according to claim 1, further comprising:

when the N types of insurance types comprise life insurance types, detecting whether the client attribute data comprises any one or more special identifications of a paper mail refund identification, a survivor fund unreceived identification and an identity card invalidation identification;

3. The intelligent voice prompt method according to claim 1, wherein after the voice splicing is performed to obtain prompt voice data and the prompt voice data is sent to a client terminal of a call opposite terminal for broadcasting, the method further comprises:

collecting voice data of the target object, and performing voice recognition and keyword matching on the voice data;

4. An intelligent voice prompt terminal device, characterized in that the intelligent voice prompt terminal device comprises a memory and a processor, the memory stores a computer program capable of running on the processor, and the processor executes the computer program to realize the following steps:

the inputting the operation record data, the insurance application seeds and the insurance node dates into the factor screening model corresponding to the N types of insurance types, and respectively screening the N types of insurance types to obtain N1 types of prompt factors corresponding to the N types of insurance types, specifically including:

the inputting the operation record data, the insurance application seeds and the insurance node dates into the factor screening model corresponding to the N types of insurance types, and respectively screening the N types of insurance types to obtain N1 types of prompt factors corresponding to the N types of insurance types, specifically further comprising:

5. The intelligent voice-prompted terminal device of claim 4, wherein the processor, when executing the computer program, further performs the steps of:

6. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 3.