CN116520993A - Intelligent customer service interaction method and system based on video face tag - Google Patents

Abstract

The embodiment of the application provides an intelligent customer service interaction method and system based on video facing slip, wherein the method comprises the following steps: acquiring the appeal information input by a target user, and classifying the appeal information based on a preset classification model; matching the dialogue template based on the classified result, and sending the dialogue template to the target user; and acquiring video facing material submitted by the target user according to the dialogue template. When the video facing slip material is collected, intelligent customer service based on intelligent classification and intelligent matching dialogue templates replaces the answering personnel, labor cost is saved, and bearing capacity is improved.

Description

Intelligent customer service interaction method and system based on video face tag

Technical Field

The application relates to the technical field of intelligent customer service, in particular to an intelligent customer service interaction method and system based on video face labels.

Background

The existing video face tag technical scheme is that after receiving the incoming call of a user, information inquiry and collection are carried out by answering personnel through dispatch. The dispatch refers to dispatching an order called by a user to a corresponding auditor according to the idle/busy state of the auditor.

The specific flow is as follows:

1. when a user handles online business such as finance, insurance and the like, the business is generally carried out on mobile phone Application (APP), and when a mechanism needs to collect supplementary materials, a video face sign entry is issued to the user;

2. the user calls in from the video face sign-on port;

3. assigning to specific answering personnel via a dispatch system;

4. if no answering person is online or the answering person is all busy, the user needs to wait;

5. after the connection, the receiving personnel confirms the materials and submits the results to the system;

6. and (5) ending.

The defects of the scheme are that the seat is required to be arranged for receiving the video surface dispatch, the labor cost is high, and the receiving capacity is limited; and if the answering staff are all busy or no one is online, the user experience is poor.

Disclosure of Invention

In view of the above problems, the embodiment of the application provides an intelligent customer service interaction method and system based on video face labels, and intelligent customer service based on intelligent classification and intelligent matching dialogue templates replaces the answering personnel, so that the labor cost is saved, and the receiving capacity is improved.

In a first aspect, an embodiment of the present application provides an intelligent customer service interaction method based on video facemarks, including the steps of:

acquiring the appeal information input by a target user, and classifying the appeal information based on a preset classification model;

matching the dialogue template based on the classified result, and sending the dialogue template to the target user;

and acquiring video facing material submitted by the target user according to the dialogue template.

In the embodiment of the application, the appeal information is classified through a preset classification model, corresponding dialogue templates are matched according to different classification results, and a target user is guided to submit video face tag materials based on the dialogue templates. When the video face tag material is collected, the intelligent customer service based on the intelligent classification and intelligent matching dialogue templates replaces the answering personnel, so that the labor cost is saved, and the problems that the answering of the video face tag call is needed to be carried out by arranging manpower in the current scheme, the communication efficiency is lower, the bearing capacity has an upper limit, and the service expansion is restricted are solved. According to the embodiment of the application, through intelligent customer service access, the intelligent customer service access device can be timely connected and timely respond, and compared with the situation that a manual seat is busy or not online, the user experience is improved.

Optionally, the method further comprises the step of: when the target user triggers the intelligent customer service, the user identification of the target user is obtained, and authentication is carried out on the user identification.

Optionally, the appeal information includes audio class appeal information; acquiring the appeal information input by the target user, and classifying the appeal information based on a preset classification model specifically comprises the following steps: the method comprises the steps of obtaining audio class appeal information input by a target user, converting the audio class appeal information into text class appeal information, and classifying the text class appeal information based on a preset classification model. In this embodiment, the target user may input the audio-class appeal information, thereby improving convenience.

The dialog templates include text-based dialog templates; matching the dialogue template based on the classified result, and sending the dialogue template to the target user specifically comprises: the text class conversation template is converted into an audio class conversation template based on the classification result, and the audio class conversation template is sent to the target user.

Optionally, the method further comprises the step of: and performing preliminary examination on the video facing slip material.

Optionally, performing the preliminary audit of the video facestock includes:

and identifying the video surface label material by using a preset image classification model, comparing the identification result with the dialogue template, and outputting a comparison result.

Optionally, the video facestock material includes audio type reply information; the preliminary auditing of the video facestock material further includes:

and identifying the audio class reply information by using a preset audio emotion identification model, and outputting an emotion identification result.

Optionally, the preliminary auditing of the video facestock further includes:

and identifying the audio class reply information by using a preset audio lie detection model, and outputting a lie detection identification result.

In the embodiment, the video facing slip material is subjected to preliminary auditing, and the comparison result, the emotion recognition result and the lie detection recognition result are output, so that the time is saved for secondary auditing of subsequent auditors, and the efficiency is improved.

Optionally, the method further comprises the step of: the appeal information and video facestock are stored.

In a second aspect, an embodiment of the present application further provides an intelligent customer service interaction system based on a video facial mask, including:

the first acquisition module is used for acquiring the appeal information input by the target user and classifying the appeal information based on a preset classification model;

the matching module is used for matching the dialogue template based on the classification result and sending the dialogue template to the target user;

and the second acquisition module is used for acquiring the video facial mask material submitted by the target user according to the dialogue template.

According to the intelligent customer service interaction method and system based on the video facial mask, the appeal information is classified through the preset classification model, corresponding dialogue templates are matched according to different classification results, and a target user is guided to submit video facial mask materials based on the dialogue templates. When the video face tag material is collected, the intelligent customer service based on the intelligent classification and intelligent matching dialogue templates replaces the answering personnel, so that the labor cost is saved, and the problems that the answering of the video face tag call is needed to be carried out by arranging manpower in the current scheme, the communication efficiency is lower, the bearing capacity has an upper limit, and the service expansion is restricted are solved. According to the embodiment of the application, through intelligent customer service access, the intelligent customer service access device can be timely connected and timely respond, and compared with the situation that a manual seat is busy or not online, the user experience is improved. The method has the advantages that the method also carries out primary auditing on the video face label material, outputs comparison results, emotion recognition results and lie detection recognition results, saves time for secondary auditing by subsequent auditors, and improves efficiency.

These and other aspects of the present application will be more readily apparent from the following description of the embodiments.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 shows a flow chart of an intelligent customer service interaction method based on video facing slip according to an embodiment of the present application.

Fig. 2 shows a schematic structural diagram of an intelligent customer service interaction system based on video facing slip according to an embodiment of the present application.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.

In order to better understand the solution of the present application, the following description will make clear and complete descriptions of the technical solution of the embodiment of the present application with reference to the accompanying drawings in the embodiment of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

In the embodiments of the present application, it should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In the description of embodiments of the present application, words such as "example" or "such as" are used to indicate exemplary, illustrative, or descriptive matter. Any embodiment or design described herein as "example" or "such as" is not necessarily to be construed as preferred or advantageous over another embodiment or design. The use of words such as "example" or "such as" is intended to present relative concepts in a clear manner.

In addition, the term "plurality" in the embodiments of the present application means two or more, and in view of this, the term "plurality" may be understood as "at least two" in the embodiments of the present application. "at least one" may be understood as one or more, for example as one, two or more. For example, including at least one means including one, two or more, and not limiting what is included, e.g., including at least one of A, B and C, then A, B, C, A and B, A and C, B and C, or A and B and C, may be included.

It should be noted that, in the embodiment of the present application, "and/or" describe the association relationship of the association object, which means that three relationships may exist, for example, a and/or B may be represented: a exists alone, A and B exist together, and B exists alone. The character "/", unless otherwise specified, generally indicates that the associated object is an "or" relationship.

As shown in fig. 1, an embodiment of the present application provides an intelligent customer service interaction method based on video facemarks, including the steps of:

s1, acquiring appeal information input by a target user, and classifying the appeal information based on a preset classification model;

s2, matching the dialogue template based on the classification result, and sending the dialogue template to the target user;

s3, obtaining the video face tag material submitted by the target user according to the dialogue template.

Each piece of appeal information corresponds to one or more types of customer service problems, and corresponding dialogue templates are preset for each type of customer service problem and used for guiding a target user to submit video facing materials. When the complaint information corresponds to a plurality of customer service problems, the embodiment matches a plurality of corresponding dialogue templates, and the order in which the dialogue templates are sent to the target user can be set according to the actual needs, which is not limited herein. Video facestock includes video presentations, voice to answer questions, documents, and the like. When the video facial mask material is video display, the embodiment can perform screenshot retention backup. When the video facebook material is voice, the embodiment can convert the voice into text to be kept for backup.

In the embodiment of the application, the appeal information is classified through a preset classification model, one or more corresponding dialogue templates are matched according to different classification results, and a target user is guided to submit video face tag materials based on the one or more dialogue templates. When the video face tag material is collected, the intelligent customer service based on the intelligent classification and intelligent matching dialogue template replaces the answering personnel, so that the labor cost is saved, and the problems that the answering of the video face tag call is required to be carried out by arranging manpower in the current scheme, the communication efficiency is lower, the bearing capacity has an upper limit, and the service expansion is restricted are solved. According to the embodiment of the application, through intelligent customer service access, the intelligent customer service access device can be timely connected and timely respond, and compared with the situation that a manual seat is busy or not online, the user experience is improved.

In some embodiments, the intelligent customer service interaction method based on the video facing slip further comprises the steps of: when the target user triggers the intelligent customer service, the user identification of the target user is obtained, and authentication is carried out on the user identification. Preferably, this step may be set before step S1, and step S1 is performed when the authentication result indicates that it is passed; and when the authentication result shows that the authentication is not passed, informing the target user that the authentication is not passed.

The user identification may be a user identification card number (Identity Document, ID), a telephone number, or the like. The user identification can be obtained by means of an account number and a password, for example, the account number is a mobile phone number or an identity card number, and when a target user logs in by using the account number and the password, the user identification of the target user can be obtained. The user identification may be used to identify target users, each of which corresponds to a unique user identification. In this embodiment, the manner in which the target user triggers the intelligent customer service is not limited. Preferably, the intelligent customer service is triggered by the user through a mobile phone APP mode, and also can be triggered by the user through a phone call mode. APP is an application program, and mobile phone APP refers to software and application installed on a smart phone, so that the defects and individuation of an original system are perfected, the functions of the mobile phone are perfected, and a main means for richer use experience is provided for users. The operation of the mobile phone software needs to have a corresponding mobile phone system, and the main mobile phone systems include iOS of apple company, android (Android) system of google company, a Seban platform and a Microsoft platform.

In this embodiment, when the target user triggers the intelligent customer service, the user identifier of the target user is obtained to be used for authenticating the target user, and step S1 is executed if the authentication result is displayed to pass.

In other embodiments, the appeal information includes raw textual class appeal information. The step S1 specifically comprises the following steps: and acquiring original text class appeal information input by a target user, and classifying the original text class appeal information based on a preset classification model.

In still other implementations, the appeal information includes audio class appeal information. The step S1 specifically comprises the following steps: the method comprises the steps of obtaining audio class appeal information input by a target user, converting the audio class appeal information into text class appeal information, and classifying the converted text class appeal information based on a preset classification model.

In still other implementations, the appeal information includes audio class appeal information and raw text class appeal information. The step S1 specifically comprises the following steps: the method comprises the steps of obtaining audio class appeal information input by a target user, converting the audio class appeal information into text class appeal information, combining original text class appeal information with the converted text class appeal information, and classifying the combined text class appeal information based on a preset classification model.

In this embodiment, the solicitation information may be in either text or audio form. When the appeal information is in the audio form, the appeal information can be converted into the text form, and the appeal information in the text form is classified based on a preset classification model. According to the embodiment, the demand information in the audio form can be received, convenience is improved, and user experience is improved. In this embodiment, the user may choose to input the complaint information in text and/or audio form, which improves flexibility.

In still other embodiments, the dialog templates include text-based dialog templates. The step S2 specifically comprises the following steps: the text class dialog templates are matched based on the results of the classification and sent to the target user.

In still other embodiments, the dialog templates include text-based dialog templates. The step S2 specifically comprises the following steps: the text class conversation template is converted into an audio class conversation template based on the classification result, and the audio class conversation template is sent to the target user.

In still other embodiments, the dialog templates include text-based dialog templates. The step S2 specifically comprises the following steps: and matching the text type dialogue templates based on the classification result, converting the text type dialogue templates into audio type dialogue templates, combining the audio type dialogue templates and the text type dialogue templates, and sending the combined audio type dialogue templates and the combined text type dialogue templates to the target user.

In still other embodiments, the dialog templates include audio-type dialog templates. The step S2 specifically comprises the following steps: and matching the audio class dialogue templates based on the classified results, and sending the audio class dialogue templates to the target user.

In still other embodiments, the dialog templates include audio-type dialog templates. The step S2 specifically comprises the following steps: the audio class dialog templates are matched based on the classification results, the audio class dialog templates are converted into text class dialog templates, and the text class dialog templates are sent to the target user.

In still other embodiments, the dialog templates include audio-type dialog templates. The step S2 specifically comprises the following steps: and matching the audio class dialogue templates based on the classified results, converting the audio class dialogue templates into text class dialogue templates, and sending the audio class dialogue templates and the corresponding text class dialogue templates to the target user.

In still other embodiments, the dialog templates include a text-type dialog template and an audio-type dialog template corresponding to the text-type dialog template. The step S2 specifically comprises the following steps: and matching the text type conversation template and the audio type conversation template based on the classified results, and transmitting the text type conversation template and the audio type conversation template to the target user.

In this embodiment, the dialog templates include text dialog templates and/or audio dialog templates, and may be converted between text form and audio form, so that the text dialog templates and/or audio dialog templates are output based on the selection of the target user, thereby improving flexibility and user experience.

In still other embodiments, the intelligent customer service interaction method based on the video facing slip further comprises step S4, and preliminary auditing is performed on the video facing slip material.

As one embodiment, performing a preliminary audit of video facestock includes:

and identifying the video surface label material by using a preset image classification model, comparing the identification result with the dialogue template, and outputting a comparison result.

Wherein the image classification model may be an existing model. As an example, the dialogue template displays and inputs "business license", the preset image classification model is used for identifying the video facing material, the identification result is "license proof", and the output comparison result is "comparison error".

In the embodiment, the preset image classification model is utilized to identify the video facing slip material, and the identified result is compared with the dialogue template, so that the video facing slip material can be subjected to preliminary auditing, the time is saved for secondary auditing of subsequent auditing personnel, and the efficiency is improved.

As another embodiment, the video facestock includes audio-type reply information. The preliminary auditing of the video facestock material further includes: and identifying by using a preset audio emotion identification model, and outputting an emotion identification result.

Wherein the audio emotion recognition model may be an existing model. According to the embodiment, the preset audio emotion recognition model can be utilized to recognize the audio type reply information, the emotion state of the target user is detected, and the emotion recognition result is output, so that the subsequent auditor can better adjust the working mode, the complaint rate is reduced, and the satisfaction degree is improved.

As yet another embodiment, the preliminary auditing of the video facial mask material further includes: and identifying the audio class reply information by using a preset audio lie detection model, and outputting a lie detection identification result.

Wherein the audio lie detection model may be an existing model. The embodiment utilizes the preset audio lie detection model to identify the audio reply information, detects whether the target user is in a lie state, outputs a lie detection identification result, and provides a reference for secondary audit of subsequent auditors.

In still other embodiments, the intelligent customer service interaction method based on the video facing slip further comprises: the appeal information and video facestock are stored.

In one embodiment, when the appeal information is audio class appeal information, the audio class appeal information is converted to text class appeal information for storage.

As another embodiment, the intelligent customer service interaction method based on the video facing slip further includes: and storing the comparison result, the emotion recognition result and the lie detection recognition result.

In this embodiment, the complaint information, the video facial mask material, the comparison result, the emotion recognition result and the lie detection recognition result are stored, and the auditor carries out secondary audit according to the stored material, so as to give audit advice, thereby improving the efficiency, improving the upper limit of the bearing capacity, preventing the occurrence of poor experience caused by the fact that the user can not submit the material after calling for many times, and improving the user experience.

In order to better illustrate the working principle and technical effects of the intelligent customer service interaction method based on the video facing slip provided by the embodiment, the following examples are listed:

after the target user a completes user name and password filling in the corresponding mobile phone APP and clicks to log in, the embodiment obtains the user identifier of the target user a, and after the user identifier of the target user a is authenticated, the authentication result is displayed.

The target user a says that: "I are in supermarket, I want to borrow money". The embodiment classifies the appeal information of the target user A, and matches the dialogue template B according to the classification result.

In this embodiment, the first question "please upload your identity card copy" is output to the target user a based on the dialogue template B, and the target user a uploads the identity card copy. In this embodiment, the second question "please show your business license" is output to the target user a, and the target user a shows the business license before the camera, which can be used to capture a screenshot of the business license. In this embodiment, a third problem "please show your business environment in video" is output to the target user a, and the target user a shows the business environment such as a shelf, goods, staff, etc. in front of the camera, and the present embodiment can capture a screenshot of the business environment. In this embodiment, the fourth question "please ask you why overdue pays before" is output to the target user a, and the target user a can reply by voice, and in this embodiment, the voice reply is saved.

The embodiment utilizes the preset image classification model to identify the identity card copy of the target user A, the screenshot of the business license and the screenshot of the operating environment, compares the identification result with the dialogue template B, and displays the comparison result correctly.

The embodiment also utilizes a preset audio emotion recognition model to recognize the voice reply of the target user A and outputs an emotion recognition result.

The embodiment also utilizes a preset audio lie detection model to identify the voice reply of the target user A and outputs a lie detection identification result.

The embodiment stores the appeal information, the video facial mask material, the comparison result, the emotion recognition result and the lie detection recognition result of the target user A so as to facilitate secondary auditing by subsequent auditors.

As shown in fig. 2, this embodiment further provides an intelligent customer service interaction system based on video facemarks, including:

the first acquisition module is used for acquiring the appeal information input by the target user and classifying the appeal information based on a preset classification model;

the matching module is used for matching the dialogue template based on the classification result and sending the dialogue template to the target user;

and the second acquisition module is used for acquiring the video facial mask material submitted by the target user according to the dialogue template.

Each piece of appeal information corresponds to one or more types of customer service problems, and corresponding dialogue templates are preset for each type of customer service problem and used for guiding a target user to submit video facing materials. When the complaint information corresponds to a plurality of customer service problems, the embodiment matches a plurality of corresponding dialogue templates, and the order in which the dialogue templates are sent to the target user can be set according to the actual needs, which is not limited herein. Video facestock includes video presentations, voice to answer questions, documents, and the like. When the video facial mask material is video display, the embodiment can perform screenshot retention backup. When the video facebook material is voice, the embodiment can convert the voice into text to be kept for backup.

In the embodiment of the application, the appeal information is classified through a preset classification model, one or more corresponding dialogue templates are matched according to different classification results, and a target user is guided to submit video face tag materials based on the one or more dialogue templates. When the video face tag material is collected, the intelligent customer service based on the intelligent classification and intelligent matching dialogue template replaces the answering personnel, so that the labor cost is saved, and the problems that the answering of the video face tag call is required to be carried out by arranging manpower in the current scheme, the communication efficiency is lower, the bearing capacity has an upper limit, and the service expansion is restricted are solved. According to the embodiment of the application, through intelligent customer service access, the intelligent customer service access device can be timely connected and timely respond, and compared with the situation that a manual seat is busy or not online, the user experience is improved.

In some embodiments, the intelligent customer service interaction system based on the video surface tag further comprises an authentication module, which is used for acquiring a user identifier of the target user and authenticating the user identifier when the target user triggers the intelligent customer service. Preferably, the authentication module may be configured to be executed before the first acquisition module, and execute the first acquisition module when the authentication result is displayed to pass; and when the authentication result shows that the authentication is not passed, informing the target user that the authentication is not passed.

The user identification may be a user identification card number (Identity Document, ID), a telephone number, or the like. The user identification can be obtained by means of an account number and a password, for example, the account number is a mobile phone number or an identity card number, and when a target user logs in by using the account number and the password, the user identification of the target user can be obtained. The user identification may be used to identify target users, each of which corresponds to a unique user identification. In this embodiment, the manner in which the target user triggers the intelligent customer service is not limited. Preferably, the intelligent customer service is triggered by the user through a mobile phone APP mode, and also can be triggered by the user through a phone call mode. APP is an application program, and mobile phone APP refers to software and application installed on a smart phone, so that the defects and individuation of an original system are perfected, the functions of the mobile phone are perfected, and a main means for richer use experience is provided for users. The operation of the mobile phone software needs to have a corresponding mobile phone system, and the main mobile phone systems include iOS of apple company, android (Android) system of google company, a Seban platform and a Microsoft platform.

In this embodiment, when the target user triggers the intelligent customer service, the user identifier of the target user is acquired to be used for authenticating the target user, and the first acquisition module is executed when the authentication result is displayed to pass.

In other embodiments, the appeal information includes raw textual class appeal information. The first acquisition module is specifically configured to: and acquiring original text class appeal information input by a target user, and classifying the original text class appeal information based on a preset classification model.

In still other implementations, the appeal information includes audio class appeal information. The first acquisition module is specifically configured to: the method comprises the steps of obtaining audio class appeal information input by a target user, converting the audio class appeal information into text class appeal information, and classifying the converted text class appeal information based on a preset classification model.

In still other implementations, the appeal information includes audio class appeal information and raw text class appeal information. The first acquisition module is specifically configured to: the method comprises the steps of obtaining audio class appeal information input by a target user, converting the audio class appeal information into text class appeal information, combining original text class appeal information with the converted text class appeal information, and classifying the combined text class appeal information based on a preset classification model.

In this embodiment, the solicitation information may be in either text or audio form. When the appeal information is in the audio form, the appeal information can be converted into the text form, and the appeal information in the text form is classified based on a preset classification model. According to the embodiment, the demand information in the audio form can be received, convenience is improved, and user experience is improved. In this embodiment, the user may select to input the complaint information in text form and/or audio form, thereby improving flexibility.

In still other embodiments, the dialog templates include text-based dialog templates. The matching module is specifically used for: the text class dialog templates are matched based on the results of the classification and sent to the target user.

In still other embodiments, the dialog templates include text-based dialog templates. The matching module is specifically used for: the text class conversation template is converted into an audio class conversation template based on the classification result, and the audio class conversation template is sent to the target user.

In still other embodiments, the dialog templates include text-based dialog templates. The matching module is specifically used for: and matching the text type dialogue templates based on the classification result, converting the text type dialogue templates into audio type dialogue templates, combining the audio type dialogue templates and the text type dialogue templates, and sending the combined audio type dialogue templates and the combined text type dialogue templates to the target user.

In still other embodiments, the dialog templates include audio-type dialog templates. The matching module is specifically used for: and matching the audio class dialogue templates based on the classified results, and sending the audio class dialogue templates to the target user.

In still other embodiments, the dialog templates include audio-type dialog templates. The matching module is specifically used for: the audio class dialog templates are matched based on the classification results, the audio class dialog templates are converted into text class dialog templates, and the text class dialog templates are sent to the target user.

In still other embodiments, the dialog templates include audio-type dialog templates. The matching module is specifically used for: and matching the audio class dialogue templates based on the classified results, converting the audio class dialogue templates into text class dialogue templates, and sending the audio class dialogue templates and the corresponding text class dialogue templates to the target user.

In still other embodiments, the dialog templates include a text-type dialog template and an audio-type dialog template corresponding to the text-type dialog template. The matching module is specifically used for: and matching the text type conversation template and the audio type conversation template based on the classified results, and transmitting the text type conversation template and the audio type conversation template to the target user.

In this embodiment, the dialog templates include text dialog templates and/or audio dialog templates, and may be converted between text form and audio form, so that the text dialog templates and/or audio dialog templates are output based on the selection of the target user, thereby improving flexibility and user experience.

In still other embodiments, the video-facing-based intelligent customer service interaction system further comprises a preliminary auditing module for preliminary auditing of the video facing material.

As one embodiment, performing a preliminary audit of video facestock includes:

and identifying the video surface label material by using a preset image classification model, comparing the identification result with the dialogue template, and outputting a comparison result.

Wherein the image classification model may be an existing model. As an example, the dialogue template displays and inputs "business license", the preset image classification model is used for identifying the video facing material, the identification result is "license proof", and the output comparison result is "comparison error".

In the embodiment, the preset image classification model is utilized to identify the video facing slip material, and the identified result is compared with the dialogue template, so that the video facing slip material can be subjected to preliminary auditing, the time is saved for auditing by subsequent auditing personnel, and the efficiency is improved.

As another embodiment, the video facestock includes audio-type reply information. The preliminary auditing of the video facestock material further includes: and identifying by using a preset audio emotion identification model, and outputting an emotion identification result.

Wherein the audio emotion recognition model may be an existing model. According to the embodiment, the preset audio emotion recognition model can be utilized to recognize the audio type reply information, the emotion state of the target user is detected, and the emotion recognition result is output, so that the subsequent auditor can better adjust the working mode, the complaint rate is reduced, and the satisfaction degree is improved.

As yet another embodiment, the preliminary auditing of the video facial mask material further includes: and identifying the audio class reply information by using a preset audio lie detection model, and outputting a lie detection identification result.

Wherein the audio lie detection model may be an existing model. The embodiment utilizes the preset audio lie detection model to identify the audio reply information, detects whether the target user is in a lie state, outputs a lie detection identification result, and provides a reference for secondary audit of subsequent auditors.

In still other embodiments, the video-facing-based intelligent customer service interaction system further includes a storage module for storing the appeal information and the video facing material.

In one embodiment, when the requirement information is audio class requirement information, the storage module is further configured to convert the audio class requirement information into text class requirement information for storage.

As another embodiment, the storage module is further configured to store the comparison result, the emotion recognition result, and the lie detection recognition result.

In this embodiment, the complaint information, the video facial mask material, the comparison result, the emotion recognition result and the lie detection recognition result are stored, and the auditor carries out secondary audit according to the stored material, so as to give audit advice, thereby improving the efficiency, improving the upper limit of the bearing capacity, preventing the occurrence of poor experience caused by the fact that the user can not submit the material after calling for many times, and improving the user experience.

The foregoing description is not intended to limit the preferred embodiments of the present application, but is not intended to limit the scope of the present application, and any such modifications, equivalents and adaptations of the embodiments described above in accordance with the principles of the present application should and are intended to be within the scope of the present application, as long as they do not depart from the scope of the present application.

Claims (10)

1. The intelligent customer service interaction method based on the video face tag is characterized by comprising the following steps:

acquiring the appeal information input by a target user, and classifying the appeal information based on a preset classification model;

matching a dialogue template based on the classified result, and sending the dialogue template to the target user;

and acquiring video facial mask materials submitted by the target user according to the dialogue template.

2. The method of claim 1, wherein the method further comprises the step of:

and when the target user triggers the intelligent customer service, acquiring a user identifier of the target user, and authenticating the user identifier.

3. The method of claim 1, wherein the appeal information comprises audio class appeal information; the obtaining the appeal information input by the target user, and classifying the appeal information based on the preset classification model specifically comprises the following steps:

the audio class appeal information input by the target user is obtained, the audio class appeal information is converted into text class appeal information, and the text class appeal information is classified based on a preset classification model.

4. The method of claim 1, wherein the dialog template comprises a text-based dialog template; the step of matching the dialogue template based on the classification result and sending the dialogue template to the target user specifically comprises the following steps:

and matching a text type dialogue template based on the classification result, converting the text type dialogue template into an audio type dialogue template, and sending the audio type dialogue template to the target user.

5. The method of claim 1, wherein the method further comprises the step of: and performing preliminary auditing on the video facing slip material.

6. The method of claim 5, wherein the preliminary auditing of the video facestock material comprises:

and identifying the video facial mask material by using a preset image classification model, comparing the identification result with the dialogue template, and outputting a comparison result.

7. The method of claim 5, wherein the video facestock material comprises audio-type reply information; the preliminary auditing of the video facestock material further includes:

and identifying the audio class reply information by using a preset audio emotion identification model, and outputting an emotion identification result.

8. The method of claim 7, wherein the preliminary auditing the video facestock material further comprises:

and identifying the audio class reply information by using a preset audio lie detection model, and outputting a lie detection identification result.

9. The method of claim 1, wherein the method further comprises the step of: storing the appeal information and the video facestock material.

10. An intelligent customer service interaction system based on video facing slip, which is characterized by comprising:

the first acquisition module is used for acquiring the appeal information input by the target user and classifying the appeal information based on a preset classification model;

the matching module is used for matching a dialogue template based on the classification result and sending the dialogue template to the target user;

and the second acquisition module is used for acquiring the video facial mask material submitted by the target user according to the dialogue template.