CN111949777A

CN111949777A - Intelligent voice conversation method and device based on crowd classification and electronic equipment

Info

Publication number: CN111949777A
Application number: CN202010721609.3A
Authority: CN
Inventors: 袁倩蕾; 刘宗全; 张家兴
Original assignee: Beijing Qibao Xinan Technology Co ltd
Current assignee: Beijing Qibao Xinan Technology Co ltd
Priority date: 2020-07-24
Filing date: 2020-07-24
Publication date: 2020-11-17

Abstract

The invention discloses an intelligent voice conversation method, an intelligent voice conversation device and electronic equipment based on crowd classification, wherein the method comprises the following steps: carrying out inquiry dialogue with a user according to a preset inquiry dialogue; determining the crowd classification of the user according to the response of the user to the preset inquiry call; acquiring a recommended word operation corresponding to the user crowd classification; and carrying out recommendation conversation with the user according to the recommendation conversation. According to the method, an inquiry dialogue is firstly carried out with a user according to a preset inquiry dialogue, the basic situation of the user is known through the response of the user to the preset inquiry dialogue, the product requirement, the product interest points and the like of the user are further determined, and then the crowd classification of the user is determined according to the product requirement, the product interest points and the like of the user; and then adopt different recommended words to the people of different crowd classification, when improving the intelligent of electricity selling robot, realize the individualized electricity selling to the user, can effectively improve user conversion rate, reduce user's hang-up or complain.

Description

Intelligent voice conversation method and device based on crowd classification and electronic equipment

Technical Field

The invention relates to the technical field of voice intelligence, in particular to an intelligent voice conversation method and device based on crowd classification, electronic equipment and a computer readable medium.

Background

Intelligent Speech Interaction (Intelligent Speech Interaction) is based on technologies such as Speech recognition, Speech synthesis and natural language understanding, and gives Intelligent man-machine Interaction experience of 'being able to listen, speak and understand you' type to enterprises in various practical application scenes. The method is suitable for a plurality of application scenes, including scenes such as telephone sales, intelligent question answering, intelligent quality inspection, real-time speech subtitles, interview recording and the like. The method is applied to multiple fields of finance, insurance, judicial sciences, e-commerce and the like.

For telemarketing example, the telemarketing robot typically uses the same telephone challenge technique to perform multiple rounds of conversations with all users. However, in practice, each user has different basic conditions (such as sex, age, etc.), and the demand and interest points of the product are different. Obviously, such an electric pinning robot lacks sufficient intelligence to enable personalized electric pinning to a user. The conversion rate of the user is influenced, even the user feels dislike, and phenomena of hang-up, complaint and the like occur.

Disclosure of Invention

The invention aims to solve the technical problems that the intelligent performance of the electric marketing robot is insufficient and the electric marketing robot cannot perform personalized electric marketing on users.

In order to solve the above technical problem, a first aspect of the present invention provides an intelligent voice conversation method based on crowd classification, where the method includes:

carrying out inquiry dialogue with a user according to a preset inquiry dialogue;

determining the crowd classification of the user according to the response of the user to the preset inquiry call;

acquiring a recommended word operation corresponding to the user crowd classification;

and carrying out recommendation conversation with the user according to the recommendation conversation.

In a preferred embodiment of the present invention, before the query session with the user according to the preset query technique, the method further includes:

creating a query technology library;

and acquiring a corresponding preset inquiry dialogue from the inquiry dialogue library according to the service type.

According to a preferred embodiment of the present invention, before the obtaining of the recommended dialect corresponding to the user's crowd classification, the method further comprises:

setting conversational strategies corresponding to different crowd classifications;

and configuring a corresponding recommended dialect according to the dialect strategy to generate a recommended dialect library.

According to a preferred embodiment of the present invention, the determining the user's crowd classification according to the user's response to the preset inquiry dialogue comprises:

converting the user response to the query operation into a text file;

extracting a preset keyword result of the text file;

and inputting the preset keyword result of the text file into a crowd classification model to obtain the crowd classification of the user.

According to a preferred embodiment of the present invention, before the preset keyword result of the text file is input into the crowd classification model, the method further includes:

acquiring the response of a sampled group to a preset inquiry telephone;

converting responses of sample populations to the query technique into sample text files;

extracting a preset keyword result of the sample text file;

and training a preset training model according to a preset keyword result of the sample file to obtain the crowd classification model.

According to a preferred embodiment of the present invention, the training of the preset training model according to the preset keyword result of the sample file includes:

classifying sample crowds according to preset classification rules and preset keyword results of the sample files to obtain crowd classification results;

and inputting the preset keyword result of the sample file and the corresponding crowd classification result into the preset training model for training to obtain the crowd classification model.

According to a preferred embodiment of the present invention, the preset keywords include: at least one of age, gender, family structure, location, and occupation.

In order to solve the above technical problem, a second aspect of the present invention provides an intelligent voice conversation apparatus based on crowd classification, the apparatus comprising:

the first dialogue module is used for inquiring dialogue with a user according to a preset inquiry dialogue;

the analysis determining module is used for determining the crowd classification of the user according to the response of the user to the preset inquiry call;

the acquisition module is used for acquiring recommended dialogues corresponding to the crowd classification of the user;

and the second dialogue module is used for carrying out recommendation dialogue with the user according to the recommendation dialogue.

According to a preferred embodiment of the invention, the device further comprises:

the first establishing module is used for establishing a query tactics library;

and the sub-acquisition module is used for acquiring the corresponding preset inquiry telephone from the inquiry telephone library according to the service type.

the setting module is used for setting conversational strategies corresponding to different crowd classifications;

and the configuration module is used for configuring the corresponding recommended dialect according to the dialect strategy to generate a recommended dialect library.

According to a preferred embodiment of the present invention, the analysis determination module comprises:

the conversion module is used for converting the response of the user to the inquiry call into a text file;

the extraction module is used for extracting preset keywords of the text file;

and the input module is used for inputting the preset keywords of the text file into a crowd classification model to obtain the crowd classification of the user.

the first acquisition module is used for acquiring the response of the sample personal group to a preset inquiry telephone;

the first conversion module is used for converting the responses of the sample population to the query technology into a sample text file;

the first extraction module is used for extracting a preset keyword result of the sample text file;

and the training module is used for training a preset training model according to the preset keyword result of the sample file to obtain the crowd classification model.

According to a preferred embodiment of the invention, the training module comprises:

the classification module is used for classifying the sample crowd according to a preset classification rule and a preset keyword result of the sample file to obtain a crowd classification result;

and the input module is used for inputting the preset keyword result of the sample file and the corresponding crowd classification result into the preset training model for training to obtain the crowd classification model.

To solve the above technical problem, a third aspect of the present invention provides an electronic device, comprising:

a processor; and

a memory storing computer executable instructions that, when executed, cause the processor to perform the method described above.

In order to solve the above technical problem, a fourth aspect of the present invention proposes a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs that, when executed by a processor, implement the above method.

According to the method, an inquiry dialogue is firstly carried out with a user according to a preset inquiry dialogue, the basic situation of the user is known through the response of the user to the preset inquiry dialogue, the product requirement, the product interest points and the like of the user are further determined, and then the crowd classification of the user is determined according to the product requirement, the product interest points and the like of the user; and then adopt different recommended words to the people of different crowd classification, when improving the intelligent of electricity selling robot, realize the individualized electricity selling to the user, can effectively improve user conversion rate, reduce user's hang-up or complain.

Drawings

In order to make the technical problems solved by the present invention, the technical means adopted and the technical effects obtained more clear, the following will describe in detail the embodiments of the present invention with reference to the accompanying drawings. It should be noted, however, that the drawings described below are only illustrations of exemplary embodiments of the invention, from which other embodiments can be derived by those skilled in the art without inventive step.

FIG. 1 is a flow chart of an intelligent voice conversation method based on crowd classification according to the present invention;

FIG. 2 is a schematic flow chart illustrating the process of determining the user's demographic classification based on the user's response to a predetermined query technique according to the present invention;

FIG. 3 is a schematic diagram of a structural framework of an intelligent voice conversation apparatus based on crowd classification according to the present invention;

FIG. 4 is a block diagram of an exemplary embodiment of an electronic device in accordance with the present invention;

FIG. 5 is a schematic diagram of one embodiment of a computer-readable medium of the present invention.

Detailed Description

Exemplary embodiments of the present invention will now be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments of the invention may be embodied in many specific forms, and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art.

The structures, properties, effects or other characteristics described in a certain embodiment may be combined in any suitable manner in one or more other embodiments, while still complying with the technical idea of the invention.

In describing particular embodiments, specific details of structures, properties, effects, or other features are set forth in order to provide a thorough understanding of the embodiments by one skilled in the art. However, it is not excluded that a person skilled in the art may implement the invention in a specific case without the above-described structures, performances, effects or other features.

The flow chart in the drawings is only an exemplary flow demonstration, and does not represent that all the contents, operations and steps in the flow chart are necessarily included in the scheme of the invention, nor does it represent that the execution is necessarily performed in the order shown in the drawings. For example, some operations/steps in the flowcharts may be divided, some operations/steps may be combined or partially combined, and the like, and the execution order shown in the flowcharts may be changed according to actual situations without departing from the gist of the present invention.

The block diagrams in the figures generally represent functional entities and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

The same reference numerals denote the same or similar elements, components, or parts throughout the drawings, and thus, a repetitive description thereof may be omitted hereinafter. It will be further understood that, although the terms first, second, third, etc. may be used herein to describe various elements, components, or sections, these elements, components, or sections should not be limited by these terms. That is, these phrases are used only to distinguish one from another. For example, a first device may also be referred to as a second device without departing from the spirit of the present invention. Furthermore, the term "and/or", "and/or" is intended to include all combinations of any one or more of the listed items.

Referring to fig. 1, fig. 1 is a flowchart of an intelligent voice conversation method based on crowd classification according to the present invention, as shown in fig. 1, the method includes:

s1, performing inquiry dialogue with the user according to the preset inquiry dialogue;

the preset inquiry telephone is used for knowing basic conditions of the age, the gender, the family structure, the occupation and the like of the user so as to determine the demand of the user for the product and the product suitable for the user. For example, the preset dialogs may be "how old you are? "," what occupation you are engaged in at present? "and the like. The preset inquiry call technology can be a single round of conversation with the user or a plurality of rounds of conversations with the user.

For different service types, corresponding products are different, and the basic user conditions reflecting the product demand of users are also different. For example, for an insurance business, the degree of demand of the user for an insurance product can be reflected by age, family structure, occupation, and the like. For the financial credit business, the requirement degree of the user on the financial credit product can be reflected through age, credit investigation condition, occupation, borrowing history and the like. Therefore, in one embodiment, different preset interrogatories should be set for different service types to know the degree of demand of the user for the corresponding product. Before the query dialog is performed with the user according to the preset query technique, the method further includes:

s10, creating a query tactical library;

the query language library comprises preset query languages corresponding to the service types, namely different service types correspond to different preset query languages.

And S11, acquiring a corresponding preset inquiry dialogue from the inquiry dialogue library according to the service type.

Specifically, the service type may be associated with the corresponding preset interrogation technique through an identifier such as a number or a character string. The corresponding preset interrogatories are obtained by the same identifier.

S2, determining the crowd classification of the user according to the response of the user to the preset inquiry call;

in the step, the basic situation of the user is known through the response of the user to the preset inquiry telephone technology, so that the product demand, the product interest points and the like of the user are determined, and the crowd classification of the user is determined according to the product demand, the product interest points and the like of the user; in one example, the user's demographic classification may be determined by a demographic classification model. Specifically, as shown in fig. 2, the present step includes:

s21, converting the response of the user to the query operation into a text file;

specifically, the response audio of the user to the query technology can be converted into a text file through the existing technology of converting the words through voice, such as a deep full-sequence convolutional neural network, so that a basis is provided for subsequent processing.

S22, extracting a preset keyword result of the text file;

and the preset keyword result is a question and answer result of the preset keyword. The preset keywords correspond to preset interrogations. For example, the preset dialogs are "how old you are? ", the keyword is preset as age. The preset call asking technique is "do you have several people at home? If yes, the keyword is preset as a family structure. In one example, the preset keywords include: at least one of age, gender, family structure, location, and occupation.

When the preset keyword result is extracted, synonyms and near synonyms of the preset keyword can be selected to form a preset keyword candidate set, for example, if the preset keyword is age, the preset keyword candidate set can include: age, years, etc. The text file is analyzed, then the preset keywords are obtained through word-by-word fuzzy matching according to the preset keyword candidate set, and results of the preset keywords are output, such as 28-year-old and 3-mouth family.

And S23, inputting the preset keyword result of the text file into a crowd classification model to obtain the crowd classification of the user.

The preset crowd classification model is used for classifying the crowd of the user according to the basic condition of the user (namely the preset keyword result of the response of the user to the preset inquiry telephone). The preset crowd classification model may be created through steps S231 to S234 before this step.

S231, obtaining responses of sample crowds to a preset inquiry call;

in specific implementation, when a preset population classification model is constructed, historical response data of a certain number of sample populations to a preset inquiry call technology needs to be acquired.

S232, converting responses of sample crowds to the inquiry telephone art into sample text files;

s233, extracting a preset keyword result of the sample text file;

steps S232 and S233 are the same as steps S21 and S22, respectively, and are not repeated here.

S234, training a preset training model according to the preset keyword result of the sample file to obtain the crowd classification model.

In one example, the step first classifies sample crowds according to preset classification rules and preset keyword results of the sample files to obtain crowd classification results; the preset classification rule is a crowd classification rule set according to the demand degree of a user for a product, for example, for a certain type of insurance products, in the preset classification rule, the users with the age of 35-45 years are classified into crowds with the demand degree of 70-80 grades, and the users with the age of 45-55 years are classified into crowds with the demand degree of 80-90 grades.

Secondly, inputting the preset keyword result of the sample file and the corresponding crowd classification result into the preset training model for training to obtain the crowd classification model. In specific implementation, after data preprocessing operations such as data cleaning, data integration and data labeling are performed on the response data of the preset inquiry technique by the user, the finally generated preset keyword result and the corresponding crowd classification result data sample are input into a preset training model for training so as to obtain the crowd classification model, and technicians in the field of the preset training model can flexibly select the preset training model according to actual requirements without specific limitation.

In another example, the multidimensional user information may be determined according to the response of the user to the preset query technique, and then the user's crowd classification may be determined according to the matching of the multidimensional user information and the product demand degree.

The multidimensional user information may include: at least one of user personal information, family structure information, and family asset status. The user personal information may specifically include: age, gender, occupation, academic calendar, etc. The multidimensional user information can be determined by the user response to the multi-round preset inquiry call. The method specifically comprises the following steps:

s210, response information of the user to each preset inquiry call is obtained.

In this embodiment, multiple rounds of dialog are applicable to a closed scene, which is a way to clarify the basic situation information of a user in a man-machine dialog. The multiple rounds of dialogue may not necessarily be in the form of multiple dialogue interactions with the user, for example, if sufficient information has been provided in the user's response, or additional information from other sources is sufficient to account for the user's basic situation, then there may not be multiple dialogue interactions with the user.

In this embodiment, the user response information may be the personal basic information of the user, or may be the family structure information of the user, the information that the user knows about the product, and the like.

S211, matching the response information with a preset slot position in a preset inquiry call;

the preset slot position is effective response information to a preset inquiry telephone art in the multi-turn conversation process. A preset slot position corresponds to information which needs to be acquired for determining the product demand of a user. For example, for a preset dialogs, "how many years are you? "its corresponding default slot is" xx years old "or a number within 100. If the response of the user is information except the preset slot position, such as 'inconvenient to say', the matching is failed.

S212, if the user response information is successfully matched with the preset slot position, extracting the user response information.

The slot positions are divided into two slot position types of a word slot and an interface slot, and if the user response information is successfully matched with the preset slot position, the user response information is extracted.

And S213, determining the multi-dimensional information of the user according to the extracted user response information.

Specifically, according to the matching condition of the multi-round response information of the user and the preset slot position, a plurality of successfully matched user response information are extracted to form multi-dimensional user information. For example, in a multi-turn conversation, the system asks the user "do you home a few people? The "user answers" asking what to do, the slot matching with "home structure" fails. The system then asks the user "how do you get in home? The "user answers" i'm income 10 ten thousand in a year ", and the slot position of" income per year "is successfully matched. One hundred thousand years of annual income is taken as the multi-dimensional information of the user.

In the invention, a multi-dimensional matching table of user information and the demand degree of a certain product can be preset, and different matching tables are set for different products. For example, for financial products, the age of a user is set to be 20-30 years old, the product demand degree matched by users with income of more than 10 ten thousand years is set as a secondary demand, the age of the user is set to be 30-50 years old, and the product demand degree matched by users with income of more than 40 ten thousand years is set as a tertiary demand. And determining the demand grade of the user for the product according to the matching of the multidimensional user information and the product demand degree, and further determining the crowd classification of the user. For example, users of the same demand level are classified into the same demographic classification.

Or, a matching table of multi-dimensional user information and different product demand degrees is preset, and different matching tables are set for different multi-dimensional user information. And determining the product types required by the users according to the matching of the multi-dimensional user information and the product demand degree, and further determining the crowd classification of the users. For example, users who desire the same product are classified into the same demographic group.

S3, acquiring recommended dialogues corresponding to the user crowd classification;

before this step, the recommended dialogs corresponding to different people classes can be set. The method specifically comprises the following steps:

s31, setting corresponding speaking strategies of different people groups;

wherein the conversational strategy comprises: intonation of the dialect, speech rate and content of the dialect, etc. For example, the language term with high product demand can be set to be soft and the language speed is slow for the crowd classification with high product demand, and the language content can be a product recommendation language set according to the demand of the crowd classification for the product, for example, the language content can be set as a simple introduction to the performance and the advantage of the product for the crowd classification with high product demand, and the language content can be set as a specific introduction to the price, the performance and the advantage of the product for the crowd classification with low product demand. The verbal content may also be a recommendation for a product that has a need for crowd classification. For example, if the crowd classification has a need for the first insurance product, the jargon content of the crowd classification is set as the introduction jargon of the first insurance product.

And S32, configuring the corresponding recommended dialect according to the dialect strategy to generate a recommended dialect library.

Different groups of people are provided with different recommended dialects according to the dialectical strategy, and the recommended dialects correspond to different product introductions. Each different conversation recommendation forms a conversation recommendation library.

And S4, carrying out recommendation conversation with the user according to the recommendation conversation.

Fig. 3 is a schematic diagram of an architecture of an intelligent voice conversation apparatus based on crowd classification according to the present invention, as shown in fig. 3, the apparatus includes:

a first creation module 30 for creating a query-tactical library;

the sub-obtaining module 301 is configured to obtain a corresponding preset query language from the query language library according to the service type.

A first dialogue module 31, configured to perform an inquiry dialogue with a user according to a preset inquiry strategy;

an analysis determination module 32, configured to determine a user's crowd classification according to the user's response to the preset query technique;

an obtaining module 33, configured to obtain a recommended word technique corresponding to the user's crowd classification;

and the second dialogue module 34 is used for carrying out recommendation dialogue with the user according to the recommendation dialogue.

Further, the apparatus further comprises:

a setting module 35, configured to set conversational strategies corresponding to different people categories;

and a configuration module 36, configured to configure a corresponding recommended word operation according to the word operation policy to generate a recommended word operation library.

In one embodiment, the analysis determination module 32 includes:

a conversion module 321, configured to convert the user response to the query operation into a text file;

an extracting module 322, configured to extract preset keywords of the text file;

and the input module 323 is used for inputting the preset keywords of the text file into the crowd classification model to obtain the crowd classification of the user.

Further, the apparatus further comprises:

Illustratively, the training module includes:

In the present invention, the preset keywords include: at least one of age, gender, family structure, location, and occupation.

Those skilled in the art will appreciate that the modules in the above-described embodiments of the apparatus may be distributed as described in the apparatus, and may be correspondingly modified and distributed in one or more apparatuses other than the above-described embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.

In the following, embodiments of the electronic device of the present invention are described, which may be regarded as an implementation in physical form for the above-described embodiments of the method and apparatus of the present invention. Details described in the embodiments of the electronic device of the invention should be considered supplementary to the embodiments of the method or apparatus described above; for details which are not disclosed in embodiments of the electronic device of the invention, reference may be made to the above-described embodiments of the method or the apparatus.

Fig. 4 is a block diagram of an exemplary embodiment of an electronic device according to the present invention. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 4, the electronic device 400 of the exemplary embodiment is represented in the form of a general-purpose data processing device. The components of electronic device 400 may include, but are not limited to: at least one processing unit 410, at least one memory unit 420, a bus 430 connecting different electronic device components (including the memory unit 420 and the processing unit 410), a display unit 440, and the like.

The storage unit 420 stores a computer-readable program, which may be a code of a source program or a read-only program. The program may be executed by the processing unit 410 such that the processing unit 410 performs the steps of various embodiments of the present invention. For example, the processing unit 410 may perform the steps as shown in fig. 1.

The storage unit 420 may include readable media in the form of volatile storage units, such as a random access memory unit (RAM)4201 and/or a cache memory unit 4202, and may further include a read only memory unit (ROM) 4203. The storage unit 420 may also include a program/utility 4204 having a set (at least one) of program modules 4205, such program modules 4205 including, but not limited to: operating the electronic device, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 430 may be any bus representing one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 400 may also communicate with one or more external devices 300 (e.g., keyboard, display, network device, bluetooth device, etc.), enable a user to interact with the electronic device 400 via the external devices 400, and/or enable the electronic device 400 to communicate with one or more other data processing devices (e.g., router, modem, etc.). Such communication may occur via input/output (I/O) interfaces 450, and may also occur via a network adapter 460 with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network such as the Internet). The network adapter 460 may communicate with other modules of the electronic device 400 via the bus 430. It should be appreciated that although not shown in FIG. 4, other hardware and/or software modules may be used in the electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID electronics, tape drives, and data backup storage electronics, among others.

FIG. 5 is a schematic diagram of one computer-readable medium embodiment of the present invention. As shown in fig. 5, the computer program may be stored on one or more computer readable media. The computer readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electronic device, apparatus, or device that is electronic, magnetic, optical, electromagnetic, infrared, or semiconductor, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. The computer program, when executed by one or more data processing devices, enables the computer-readable medium to implement the above-described method of the invention, namely: carrying out inquiry dialogue with a user according to a preset inquiry dialogue; determining the crowd classification of the user according to the response of the user to the preset inquiry call; acquiring a recommended word operation corresponding to the user crowd classification; and carrying out recommendation conversation with the user according to the recommendation conversation.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments of the present invention described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a data processing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned method according to the present invention.

The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution electronic device, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including object oriented programming languages such as Java, C + + or the like and conventional procedural programming languages, such as "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

In summary, the present invention can be implemented as a method, an apparatus, an electronic device, or a computer-readable medium executing a computer program. Some or all of the functions of the present invention may be implemented in practice using a general purpose data processing device such as a microprocessor or a Digital Signal Processor (DSP).

While the foregoing embodiments have described the objects, aspects and advantages of the present invention in further detail, it should be understood that the present invention is not inherently related to any particular computer, virtual machine or electronic device, and various general-purpose machines may be used to implement the present invention. The invention is not to be considered as limited to the specific embodiments thereof, but is to be understood as being modified in all respects, all changes and equivalents that come within the spirit and scope of the invention.

Claims

1. An intelligent voice conversation method based on crowd classification, the method comprising:

2. The method of claim 1, wherein prior to conducting an interrogation session with a user according to a predetermined interrogation technique, the method further comprises:

creating a query technology library;

3. The method of any of claims 1-2, wherein prior to obtaining the recommended dialect corresponding to the user's demographic classification, the method further comprises:

4. The method of any one of claims 1-3, wherein determining the user's demographic classification based on the user's response to the preset interrogatories comprises:

converting the user response to the query operation into a text file;

extracting a preset keyword result of the text file;

5. The method according to any one of claims 1-4, wherein before entering the predetermined keyword results of the text file into a people classification model, the method further comprises:

acquiring the response of a sampled group to a preset inquiry telephone;

extracting a preset keyword result of the sample text file;

6. The method according to any one of claims 1-5, wherein the training of a preset training model according to preset keyword results of the sample file comprises:

7. The method according to any one of claims 1-6, wherein the preset keywords comprise: at least one of age, gender, family structure, location, and occupation.

8. An intelligent voice conversation apparatus based on crowd classification, the apparatus comprising:

9. An electronic device, comprising:

a processor; and

a memory storing computer-executable instructions that, when executed, cause the processor to perform the method of any of claims 1-7.

10. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the method of any of claims 1-7.