Question and answer method and system based on voice interaction, electronic device and storage medium

Abstract

The application discloses a question and answer method and system based on voice interaction, an electronic device and a storage medium. The method comprises the following steps: obtaining a user authorization state, obtaining user attribute information based on the authorization state, wherein the user attribute information is used to represent basic information of the user and scene information in which the user is currently located; obtaining a target question and answer resource according to the user attribute information; inquiring, through voice, whether the user is willing to participate in a question and answer of the target question and answer resource, and in response to the user's consent, voice broadcasting the target question and answer resource based on a preset playing rule; receiving voice input information of the user, converting the voice input information into text information, and determining an answer of the user to a current question and answer topic according to the text information. The application solves the inconvenience of the existing question and answer method based on text interaction in the related art, and improves the positivity of the user question and answer interaction.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of computer, and particularly relates to a question and answer method and system based on voice interaction, an electronic device and a storage medium. BACKGROUND

[0002] With the vigorous development of the Internet, online questionnaire survey and service evaluation have become an important means for people to maintain their rights and interests and improve service quality.

[0003] At present, the existing questionnaire survey and service evaluation are usually in the form of a questionnaire displayed in text on the user terminal screen. The user can only browse and input feedback and fill in by operating the terminal one by one. The user needs to stare at the terminal screen to provide feedback, which requires the user to spend some time and is not convenient to operate, resulting in low user enthusiasm. SUMMARY

[0004] The first purpose of the embodiment of the present application is to provide a question and answer method based on voice interaction, aiming to solve at least one problem existing in the prior art.

[0005] The embodiment of the present application is implemented in this way. A question and answer method based on voice interaction is applied to a client, comprising:

[0006] Obtaining a user authorization state, obtaining user attribute information based on the authorization state, the user attribute information being used to represent basic information of the user and scene information currently where the user is located;

[0007] Obtaining a target question and answer resource according to the user attribute information;

[0008] Asking the user by voice whether to participate in the question and answer of the target question and answer resource, and responding to the user's agreement, playing the target question and answer resource by voice based on a preset playing rule;

[0009] Receiving user voice input information, converting the voice input information into text information, and determining the answer of the user to the current question and answer topic according to the text information.

[0010] In one embodiment, the obtaining of the user authorization state and the obtaining of the user attribute information based on the authorization state comprises: obtaining user ID information, sending an authorization prompt of the user ID information, receiving a user authorization operation on the user ID information, judging whether the authorization operation is an agreement authorization, and obtaining user basic information and scene information currently where the user is located based on the user's agreement authorization.

[0011] In an embodiment, the basic information includes user historical operation behavior, and the obtaining the question and answer resource according to the user attribute information comprises: obtaining, according to the basic information and scene information, a question and answer resource matching the scene information from a database, obtaining historical question and answer resource interaction information of the user, determining the question and answer resource as a target question and answer resource if the question and answer resource does not belong to the historical question and answer resource interaction information, and re-obtaining a question and answer resource from the database if the question and answer resource belongs to the historical question and answer resource interaction information.

[0012] In an embodiment, after obtaining the user ID information, the manner of obtaining the user authorization state comprises: displaying an authorization button through a man-machine interaction interface of the client, and receiving an authorization operation of the user on the authorization button; and / or prompting the user to perform an authorization operation through voice of the client, and receiving an authorization operation input by voice of the user.

[0013] In an embodiment, the voice broadcasting of the target question and answer resource based on the preset playing rule comprises: identifying content of the target question and answer resource to obtain a plurality of question and answer questions, sequentially broadcasting the plurality of question and answer questions, and playing a next question and answer question after receiving user voice input information of each question and answer question and determining an answer; and the question and answer method further comprises: generating a result resource of the target question and answer resource according to the plurality of question and answer questions and corresponding answers.

[0014] In an embodiment, the preset playing rule comprises a plurality of broadcasting voice packages, an answer prompt, a remaining question prompt and an estimated question and answer time prompt, a broadcasting voice package is randomly determined from the plurality of broadcasting voice packages to broadcast a question and answer question when the plurality of question and answer questions are broadcasted; an answer prompt is voice broadcasted when no user voice input is received within a preset time; and a quantity of remaining question and answer questions and an estimated question and answer time are voice broadcasted before each question and answer question is broadcasted.

[0015] In an embodiment, the determining the answer of the current question and answer question by the user according to the text information comprises: comparing the text information with a pre-stored answer of the current question in a database, and determining an answer with the same or highest similarity as the text information as the answer of the current question and answer question.

[0016] Another purpose of the embodiment of the application is to provide a question and answer system based on voice interaction, applied to a client, comprising:

[0017] The request module is configured to obtain a user authorization state, and obtain user attribute information based on the authorization state, wherein the user attribute information is used to represent basic information of the user and scene information in which the user is currently located.

[0018] The question and answer resource acquisition module is configured to acquire a target question and answer resource according to the user attribute information.

[0019] The broadcast module is configured to inquire, by voice, whether the user is willing to participate in the question and answer of the target question and answer resource, and in response to the user's consent, broadcast the target question and answer resource by voice based on preset broadcast rules.

[0020] The answer processing module is configured to receive user voice input information, convert the voice input information into text information, and determine an answer of the user to a current question and answer topic according to the text information.

[0021] Another purpose of the embodiment of the present application is to provide an electronic device including a memory and a processor, wherein the memory stores a computer program, and the computer program is executed by the processor to enable the processor to perform the steps of the question and answer method based on voice interaction.

[0022] Still another purpose of the embodiment of the present application is a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to enable the processor to perform the steps of the question and answer method based on voice interaction.

[0023] The question and answer method, system, electronic device and storage medium based on voice interaction provided by the embodiment of the present application can push a questionnaire to a user for reply after obtaining authorization of the user, and the user can directly reply to the questionnaire and service evaluation by voice, without needing to stare at a terminal screen for reply, which has a good experience in a car scene and a telephone service scene, saves time of the user, and can collect real feedback of the user. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 The embodiment of the present application provides an implementation process of the question and answer method based on voice interaction.

[0025] Figure 2 The embodiment of the present application provides a core flowchart of the question and answer method based on voice interaction.

[0026] Figure 3 The embodiment of the present application provides a main module schematic diagram of the question and answer system based on voice interaction.

[0027] Figure 4 The embodiment of the present application provides an exemplary system architecture diagram that can be applied.

[0028] Figure 5 The structure schematic diagram of a computer system suitable for realizing a terminal device or a server of the embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0030] The terms used in the embodiments of the present application are merely for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein means and includes any or all possible combinations of one or more associated listed items.

[0031] It should be understood that although the terms first, second, etc. can be used in the embodiments of the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another.

[0032] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0033] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purpose of the present application, the specific embodiments, structures, features and effects according to the present application are described in detail below with reference to the drawings and preferred embodiments.

[0034] Figure 1 An implementation process of a question and answer method based on voice interaction provided by an embodiment of the present application is shown. For the convenience of description, only the parts related to the embodiments of the present application are shown, and the details are as follows:

[0035] A question and answer method based on voice interaction is applied to a client, comprising the following steps:

[0036] S101: Obtain a user authorization state, obtain user attribute information based on the authorization state, and the user attribute information is used to represent basic information of the user and scene information currently in which the user is located;

[0037] S102: Obtain a target question and answer resource according to the user attribute information;

[0038] S103: Ask the user whether to participate in the question and answer of the target question and answer resource through voice, and respond to the user's agreement to voice broadcast the target question and answer resource based on a preset playing rule;

[0039] S104: receiving user voice input information, converting the voice input information into text information, and determining the answer of the user to the current question and answer topic according to the text information.

[0040] In step S101, the user authorization state is obtained, and user attribute information is obtained based on the authorization state, the user attribute information being used to represent basic information of the user and scene information of a current scenario in which the user is located. After the user authorization is obtained, the attribute information corresponding to the user is obtained, and the attribute information can include basic information and scene information of an environment in which the user is currently located, so as to form a basic portrait of the user, so as to subsequently push question and answer resources personalized for the user and push question and answer resources suitable for a current scenario of the user.

[0041] In an embodiment, the obtaining of the user authorization state and the obtaining of the user attribute information based on the authorization state include: obtaining user ID information, sending an authorization prompt of the user ID information, causing the authorization prompt to be displayed on a terminal currently used by the user, receiving an authorization operation of the user on the user ID information, determining whether the authorization operation is an authorization agreement, and obtaining the user attribute information based on the user authorization agreement. Here, the user ID information (user account information) can be obtained, and then the login prompt or the authorization prompt and the authorization-related content of the user ID information are sent as the authorization prompt. After the user logs in or authorizes, the authorization operation of the user on the ID information is received, and it is determined whether the authorization operation is an authorization agreement. When the user agrees to the authorization, the basic information of the user and the scene information in which the user is currently located are further obtained based on the authorization, so as to subsequently push question and answer resources personalized for the user. For example, the user can actively log in to the user ID to obtain the authorization of the user. After the user logs in, the user ID information is obtained, and then the attribute information of the user is obtained. The user ID information can be obtained, and then it is prompted whether the user agrees to the authorization or the login. When the user authorization is obtained, the attribute information of the user is obtained. Here, the authorization operation of the user can be logging in to the user ID, agreeing to log in to the user ID, or disagreeing to log in to the user ID.

[0042] Further, after obtaining the user ID information, the manner of obtaining the user authorization state includes: displaying an authorization button through the man-machine interface of the client, receiving the user's authorization operation on the authorization button; and / or prompting the user to perform an authorization operation through the client, and receiving the user's voice input authorization operation. For example, after obtaining the user's ID information, an authorization button can be displayed on a mobile phone interface or a terminal device such as a vehicle-mounted terminal. The authorization button can prompt the user to perform a login operation or prompt the user whether to agree to login, disagree to login, and the like. In addition, the user can be prompted whether to agree to push the question and answer resources to the user when the user ID has been logged in. When the user operates the authorization button and receives the user's operation of whether to agree, a corresponding triggering operation is performed. In addition, after obtaining the user's ID information, the user can be prompted to perform an authorization operation in a voice interaction manner. For example, the user can be prompted to log in to the user ID account through a vehicle-mounted terminal or a mobile phone terminal, or the user can be prompted whether to agree to push the question and answer resources in a voice manner when the user is logged in. The user can directly interact with the terminal through voice to perform the authorization operation. In this way, the convenience of user interaction is improved, and the user can avoid being unable to operate the terminal when driving or walking, thereby improving the user experience.

[0043] In step S102, the target question and answer resource is obtained according to the user attribute information. After obtaining the user's authorization agreement, the user's target question and answer resource suitable for the user is obtained according to the user's attribute information and pushed to the user. In this embodiment, a plurality of question and answer resources can be pre-stored in the database. After obtaining the user's authorization, the question and answer resource is matched in the database and pushed to the user for questioning and answering. Alternatively, the question and answer resource can be directly uploaded to the database by the system, and the user information is obtained and pushed to the user. Here, the question and answer resource can be established by the background system and stored in the database. When the user attribute information is obtained, the question and answer resource can be called from the database and pushed to the user.

[0044] Specifically, the question and answer resource can be a questionnaire, a user service evaluation, and the like, which collects the user's views and experiences on a certain matter, problem or service, such as the use experience of a product. The question and answer resource can be in the form of a plurality of question and answer topics, and then stored in the database.

[0045] In an embodiment, the basic information includes user historical operation behavior, and the obtaining of the question and answer resource according to the user attribute information comprises: obtaining, from a database, a question and answer resource matching the scene information according to the basic information and the scene information, obtaining historical question and answer resource interaction information of the user, determining the question and answer resource as a target question and answer resource if the question and answer resource does not belong to the historical question and answer resource interaction information, and re-obtaining a question and answer resource from the database if the question and answer resource belongs to the historical question and answer resource interaction information. Specifically, the user historical question and answer resource reply record can be obtained through the user basic information, so that the question and answer resource can be avoided from being repeatedly pushed when the question and answer resource is pushed to the user, the user time is saved, the user is not annoyed, and the question and answer efficiency of the question and answer resource can be improved. The scene information here can include various scene information of the environment in which the user is currently located, such as being able to prepare multiple questionnaires, such as a questionnaire to be asked during working hours, a questionnaire to be asked during off-work hours, a questionnaire to be asked during the weekend, a questionnaire to be asked in a scenic spot, and a questionnaire to be asked in a shopping mall. Different questionnaires are used according to different scenes. Thus, the question and answer resource suitable for the current scene of the user can be pushed, and the user question and answer success rate can be improved.

[0046] In an embodiment, the basic information can further include gender, age, occupation, and the like, so as to push the question and answer resource more suitable for the user reply to the user.

[0047] In step S103, it is inquired through voice whether the user is willing to participate in the question and answer of the target question and answer resource, and the target question and answer resource is reported through voice based on a preset playing rule in response to the user's agreement. After the target question and answer resource is obtained, it is inquired through voice whether the user is willing to participate in the question and answer of the target question and answer resource, and the user is reported and pushed through voice reporting in response to the user's agreement, so that the user can be facilitated in interaction and the enthusiasm and interest of the user in question and answer can be improved when the user is driving or walking, and the like.

[0048] In an embodiment, the reporting of the target question and answer resource based on the preset playing rule comprises: identifying the content of the target question and answer resource to obtain a plurality of question and answer questions, sequentially reporting the plurality of question and answer questions, and receiving user voice input information of each question and answer question and playing the next question and answer question after the answer is determined, and the question and answer method further comprises: generating a result resource of the target question and answer resource according to the plurality of question and answer questions and the corresponding answers. Thus, the user can be given a certain reply time, and the question and answer effectiveness can be improved. After the answers to all the questions of a question and answer resource are determined, a result resource of the question and answer resource is generated, and then the result resource is stored in the database, so as to facilitate subsequent statistical analysis.

[0049] Further, the preset playing rule includes a plurality of broadcast voice packages, an answer prompt, a remaining question prompt and an estimated question answering time prompt, a broadcast voice package is randomly determined from the plurality of broadcast voice packages to broadcast the question and answer when the plurality of question and answers are broadcasted; the answer prompt is broadcasted by voice when no user voice input is received within a preset time; the number of remaining question and answers and the estimated question answering time are broadcasted by voice before each question and answer is broadcasted. In this way, the effectiveness and interest of the user in answering the questions can be improved.

[0050] In step S104, the user voice input information is received, the voice input information is converted into text information, and the answer of the user to the current question and answer is determined according to the text information. When the user receives the question and answer question of the question and answer resource broadcast by the terminal, the user can directly speak the corresponding answer by voice. When the voice output information of the user is received, the voice information is converted into text information by voice recognition, and then the answer of the user to the current question and answer is determined according to the detected text information. In this way, the answer of the user to the question and answer can be matched by voice.

[0051] Further, the answer of the user to the current question and answer is determined according to the text information, which includes: comparing the text information with the pre-stored answer of the current question in the database, and determining the answer with the highest similarity or the same as the text information as the answer of the current question and answer. Here, when each question and answer resource is established, each question and answer is correspondingly established with a certain option or answer, and the option or answer is stored in the database in a structured statement. When the voice answer of the user to the question is received, the text information is converted, and then the database is queried and compared, and the option or answer closest to the user's answer is found as the input answer of the user through the semantic recognition model. In this way, the accuracy of the user's answer can be improved.

[0052] Therefore, the question and answer method based on voice interaction provided by the embodiment of the application can push the questionnaire to the user for reply after obtaining the authorization of the user by constructing the questionnaire survey or service evaluation database, and the user can directly reply to the questionnaire survey and service evaluation by voice, without the user having to stare at the terminal screen for reply, which has a good experience in the car scene and telephone service scene, saves the time of the user, and can collect the real feedback of the user.

[0053] As Figure 2As shown, the core flowchart of the question and answer method based on voice interaction provided by the embodiment of the application is shown. Before the question and answer starts, a corresponding questionnaire can be obtained through the current scene and basic information of the user. Then, it is inquired through voice whether the user is willing to participate in the question and answer investigation. If the user does not agree, the flowchart ends. If the user agrees, the topic content is broadcasted through voice. Then, the user's answer is waited. After the user's voice answer is analyzed, the answer option is matched. After the answer of one topic is determined, it is judged whether there is a next topic. If there is, the voice broadcast is continued. After the answer options of all subsequent topics are determined, if there is no next topic, the user's answer is thanked through voice, and the flowchart ends.

[0054] In a specific embodiment, the question and answer method based on voice interaction is applied to a vehicle terminal. The question and answer resource is a questionnaire. A plurality of questionnaires can be established in a database in advance. The questionnaire can also be directly imported into the vehicle terminal through a system or a storage device. When the user is in the vehicle, after the user's authorization is obtained, a set of questionnaires is selected for the user according to the user's information to broadcast and complete the collection of the questionnaires through voice interaction of the user. Thus, the user's time can be saved. The interestingness of the questionnaire answering and the enthusiasm of the user can be improved.

[0055] In another specific scenario, the question and answer method based on voice interaction is applied to a mobile phone. The question and answer resource is an evaluation list for the user to make an evaluation on a service, such as "very satisfied", "satisfied", "dissatisfied", etc. The user's authorization can be the dialing of a corresponding telephone or the triggering of a corresponding dialogue service, etc. After the service ends, the service evaluation is realized through voice interaction with the user. Thus, the enthusiasm of the user's evaluation can be improved.

[0056] Figure 3 The main module schematic diagram of the question and answer system based on voice interaction provided by the embodiment of the application is shown. For the convenience of description, only the part related to the embodiment of the application is shown. The details are as follows:

[0057] A question and answer system 200 based on voice interaction is applied to a client and includes:

[0058] A request module 201 is configured to obtain a user authorization state, obtain user attribute information based on the authorization state, and use the user attribute information to represent the basic information of the user and the scene information in which the user is currently located;

[0059] A question and answer resource acquisition module 202 is configured to obtain a target question and answer resource according to the user attribute information;

[0060] A broadcast module 203 is configured to inquire through voice whether the user is willing to participate in the question and answer of the target question and answer resource. In response to the user's agreement, the target question and answer resource is broadcasted through voice based on a preset broadcast rule.

[0061] The answer processing module 204 is configured to receive user voice input information, convert the voice input information into text information, and determine an answer of the user to a current question and answer topic according to the text information.

[0062] For the request module 201, user authorization status is obtained, and user attribute information is obtained based on the authorization status, the user attribute information being used to represent basic information of the user and scene information of a current environment in which the user is located. After obtaining user authorization, the attribute information corresponding to the user is obtained, the attribute information including basic information and scene information of a current environment in which the user is located, so as to form a basic portrait of the user, so as to subsequently push question and answer resources to the user in a personalized manner, and push question and answer resources suitable for a current scene of the user.

[0063] In an embodiment, the obtaining of the user authorization status and the obtaining of the user attribute information based on the authorization status include: obtaining user ID information, sending an authorization prompt of the user ID information, causing the authorization prompt to be displayed on a terminal currently used by the user, receiving an authorization operation of the user on the user ID information, determining whether the authorization operation is an authorization agreement, and obtaining the user attribute information based on the authorization agreement of the user. Here, the user ID information (user account information) can be obtained, and then an authorization prompt such as a login prompt or an authorization prompt related to authorization is sent as the authorization prompt. After the user logs in or authorizes, the authorization operation of the user on the ID information is received, and it is determined whether the authorization operation is an authorization agreement. When the user agrees to the authorization, the user's basic information and the scene information of the current environment in which the user is located are further obtained based on the authorization, so as to subsequently push question and answer resources to the user in a personalized manner. For example, the user can actively log in to the user ID to obtain authorization of the user. After the user logs in, the user ID information is obtained, and then the attribute information of the user is obtained. Alternatively, after the user ID information is obtained, the user is prompted whether to agree to the authorization or login. After the user authorization is obtained, the attribute information of the user is obtained. Here, the authorization operation of the user can be logging in to the user ID, agreeing to log in to the user ID, or disagreeing to log in to the user ID.

[0064] Further, after obtaining the user ID information, the manner of obtaining the user authorization state includes: displaying an authorization button through the man-machine interface of the client, receiving the user's authorization operation on the authorization button; and / or prompting the user to perform an authorization operation through the client, and receiving the user's voice input authorization operation. For example, after obtaining the user's ID information, an authorization button can be displayed on a mobile phone interface or a terminal device such as a vehicle-mounted terminal. The authorization button can prompt the user to perform a login operation or prompt the user whether to agree to login, disagree to login, and the like. In addition, in the case where the user ID has been logged in, the user can be prompted whether to agree to push the question and answer resources to the user. After the user operates the authorization button and receives the user's operation of whether to agree, a corresponding triggering operation is performed. In addition, after obtaining the user's ID information, the user can be prompted to perform an authorization operation in a voice interaction manner. For example, the user can be prompted through a vehicle-mounted terminal or a mobile phone terminal to log in to the user ID account, or in the case where the user has logged in, the user can be prompted through voice whether to agree to push the question and answer resources. The user can directly interact with the terminal through voice to perform an authorization operation. In this way, the convenience of user interaction is improved, and the user can avoid being unable to operate the terminal when driving or walking, thereby improving the user experience.

[0065] For the question and answer resource obtaining module 202: used to obtain target question and answer resources according to the user attribute information. After obtaining the user's authorization agreement, the user's target question and answer resources suitable for the user can be obtained according to the user's attribute information and pushed to the user for questioning and answering. In this embodiment, a plurality of question and answer resources can be pre-stored in a database. After obtaining the user's authorization, the question and answer resources are matched in the database and pushed to the user for questioning and answering. Alternatively, the question and answer resources can be directly uploaded to the database by the system, and then pushed to the user after obtaining the user information. Here, the question and answer resources can be established by a background system and stored in the database. After obtaining the user attribute information, the question and answer resources can be called from the database and pushed to the user.

[0066] Specifically, the question and answer resources can be questionnaires, user service evaluations, and the like for collecting the user's views and experiences on a certain matter, problem, or service, such as the use experience of a product. The question and answer resources can be in the form of a plurality of question and answer topics, and then stored in the database.

[0067] In an embodiment, the basic information includes user historical operation behavior, and the obtaining the question and answer resource according to the user attribute information comprises: obtaining, according to the basic information and scene information, a question and answer resource matching the scene information from a database, obtaining historical question and answer resource interaction information of the user, if the question and answer resource does not belong to the historical question and answer resource interaction information, determining the question and answer resource as a target question and answer resource, and if the question and answer resource belongs to the historical question and answer resource interaction information, re-obtaining a question and answer resource from the database. Specifically, the user historical question and answer resource reply record can be obtained through the user basic information, so that the question and answer resource can be avoided from being repeatedly pushed when the question and answer resource is pushed to the user, the user time is saved, the user is not disgusted, and the question and answer efficiency of the question and answer resource can be improved. The scene information here can include various scene information of the environment where the user currently stays, such as being able to prepare multiple questionnaires, such as a questionnaire to be asked during working hours, a questionnaire to be asked during off-work hours, a questionnaire to be asked during the weekend, a questionnaire to be asked in a scenic spot, and a questionnaire to be asked in a shopping mall. Different questionnaires are used according to different scenes. Thus, the question and answer resource suitable for the current scene of the user can be pushed, and the user question and answer success rate can be improved.

[0068] In an embodiment, the basic information can further include gender, age, occupation, and the like, so as to push the question and answer resource more suitable for the user reply to the user.

[0069] For the broadcasting module 203: the user is asked by voice whether to participate in the question and answer of the target question and answer resource, and the target question and answer resource is broadcasted by voice based on a preset broadcasting rule in response to the user's agreement. After the target question and answer resource is obtained, the user is asked by voice whether to participate in the question and answer of the target question and answer resource, and the user is pushed by voice broadcasting, so that the user can interact conveniently in the scene of driving or walking, and the enthusiasm and interest of the user in the question and answer are improved.

[0070] In an embodiment, the broadcasting the target question and answer resource by voice based on the preset broadcasting rule comprises: identifying the content of the target question and answer resource to obtain a plurality of question and answer questions, sequentially broadcasting the plurality of question and answer questions, and when each question and answer question is broadcasted, receiving the user voice input information of each question and answer question and playing the next question and answer question after the answer is determined, and the question and answer method further comprises: generating a result resource of the target question and answer resource according to the plurality of question and answer questions and the corresponding answers. Thus, the user is given a certain reply time, and the question and answer effectiveness is improved. When the answers of all the questions of a question and answer resource are determined, a result resource of the question and answer resource is generated, and then the result resource is stored in the database, so as to facilitate subsequent statistical analysis.

[0071] Further, the preset playing rule comprises a plurality of broadcast voice packages, an answer prompt, a remaining question prompt and an estimated answer time prompt, a broadcast voice package is randomly determined from the plurality of broadcast voice packages to broadcast the question and answer question when the question and answer question is broadcast; the answer prompt is broadcast by voice when no user voice input is received within a preset time; and the number of remaining question and answer questions and the estimated answer time are broadcast by voice before each broadcast of the question and answer question. Thus, the effectiveness and interest of the user in answering the question can be improved.

[0072] For the answer processing module 204: used to receive user voice input information, convert the voice input information into text information, and determine the answer of the user to the current question and answer question according to the text information. When the user receives the question and answer question broadcast by the terminal, the user can directly speak the corresponding answer by voice. When the voice output information of the user is received, the voice information is converted into text information through voice recognition, and then the answer of the user to the current question and answer question is determined according to the detected text information. Thus, the answer of the user through voice can be matched with the answer option.

[0073] Further, the determining the answer of the user to the current question and answer question according to the text information comprises: comparing the text information with the pre-stored answer of the current question in the database, and determining the answer with the highest similarity or the same as the text information as the answer of the current question and answer question. Here, when each question and answer resource is established, each question and answer question is correspondingly established with a certain option or answer, and the option or answer is stored in the database in a structured statement. When the voice reply of the user to the question is received, the voice reply is converted into text information, and then the database is queried and compared, and the option or answer closest to the user's reply is found through a semantic recognition model as the input answer of the user. Thus, the accuracy of the user's reply can be improved.

[0074] Thus, the question and answer system based on voice interaction provided by the embodiments of the present application can push the questionnaire to the user for reply after the user authorizes by constructing a questionnaire survey or service evaluation database, and the user can directly reply to the questionnaire survey and service evaluation through voice, without the user having to stare at the terminal screen for reply, which has a good experience in the car and telephone service scenarios, saves the time of the user, and can collect the real feedback of the user.

[0075] In one specific embodiment, this voice-interactive question-and-answer system is applied to an in-vehicle terminal. The question-and-answer resource is a questionnaire. Several questionnaires can be pre-created in a database, or they can be directly imported into the in-vehicle terminal via the system or storage device. When the user is in the vehicle, after obtaining the user's authorization, a questionnaire can be selected and read aloud based on the user's information, and the user can interact with the system via voice to complete the questionnaire collection. This can save the user's time and increase the fun of answering the questionnaire and the user's enthusiasm.

[0076] In another specific scenario, this voice-interaction-based question-and-answer system is applied to mobile phones. The question-and-answer resources are a list of evaluations for users to rate the service, such as "very satisfied," "satisfied," and "unsatisfied." User authorization can be achieved by the user making a corresponding phone call or triggering a corresponding dialogue service. After the service is completed, the user can interact with the system via voice to evaluate the service. This increases the user's willingness to provide feedback.

[0077] This application also provides an electronic device, including: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the voice-interaction-based question-and-answer method of this application.

[0078] This application also provides a computer-readable medium storing a computer program thereon, which, when executed by a processor, implements the voice-interaction-based question-and-answer method of this application.

[0079] Figure 4 An exemplary system architecture 300 is shown that can be applied to the question-answering method or system based on voice interaction according to the embodiments of this application.

[0080] like Figure 4 As shown, system architecture 300 may include terminal devices 301, 302, and 303, a network 304, and a server 305. Network 304 serves as the medium for providing communication links between terminal devices 301, 302, and 303 and server 305. Network 304 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0081] Users can use terminal devices 301, 302, and 303 to interact with server 305 via network 304 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 301, 302, and 303, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0082] The terminal devices 301, 302, and 303 can be various electronic devices with display screens and supporting web browsing, including but not limited to in-vehicle smart screens, smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0083] The server 305 can be a server providing various services, such as a background management server providing support for messages sent by users using the terminal devices 301, 302, and 303. The background management server can perform analysis and the like after receiving a request from a terminal device, and feed back the processing result to the terminal device.

[0084] It should be noted that the question and answer method based on voice interaction provided by the embodiments of the present application is generally executed by the terminal devices 301, 302, and 303, and correspondingly, the question and answer system based on voice interaction is generally arranged in the terminal devices 301, 302, and 303.

[0085] It should be understood that, Figure 4 The number of terminal devices, networks, and servers in the system is merely illustrative. Any number of terminal devices, networks, and servers can be provided according to implementation needs.

[0086] Reference is made below to Figure 5 which shows a structural schematic diagram of a computer system 400 suitable for implementing the electronic device of the embodiments of the present application. Figure 5 The computer system shown is merely an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0087] As shown in Figure 5 , the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 402 or programs loaded from a storage portion 408 into a random access memory (RAM) 403. Various programs and data required for the operation of the system 400 are also stored in the RAM 403. The CPU 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0088] The following components are connected to the I / O interface 405: an input part 406 including a keyboard, a mouse, etc.; an output part 407 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage part 408 including a hard disk, etc.; and a communication part 409 including a network interface card such as a LAN card, a modem, etc. The communication part 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as necessary. A removable media 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 410 as necessary, so that a computer program read out therefrom is installed in the storage part 408 as necessary.

[0089] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication part 409, and / or installed from the removable media 411. When the computer program is executed by the central processing unit (CPU) 401, the above-described functions defined in the system of the present disclosure are executed.

[0090] It should be noted that computer-readable media in this disclosure can be computer-readable storage media, computer-readable signal media or any combination thereof. Computer-readable storage media can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, 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 above. In this disclosure, computer-readable storage media can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus or device. In this disclosure, a computer-readable signal medium can include a computer-readable storage medium in baseband or propagated as a carrier wave in a propagated data signal, which can contain or store a program for use by or in connection with an instruction execution system, apparatus or device. The propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination of the above. Computer-readable signal media can be any computer-readable medium that is not a computer-readable storage medium, and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the above.

[0091] The flow diagrams and block diagrams in the drawings are illustrations of possible architectures, functions, and operations of systems, methods, and computer program products in accordance with various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0092] The modules described in the embodiments of the present application can be implemented in the form of software or in the form of hardware. The described modules can also be arranged in a processor, for example, a processor can be described as including a determining module, an extracting module, a training module and a screening module. In some cases, the names of these modules do not constitute a limitation on the modules themselves, for example, the determining module can also be described as a "module for determining a candidate user set".

[0093] The above-described embodiments only express several implementation manners of the present application, which are described in detail and specifically, but should not be understood as a limitation on the patent scope of the present application. It should be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

[0094] The above only describes the preferred embodiments of the present application, and does not limit the present application, and any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A question-and-answer method based on voice interaction, applied to a client, characterized in that, include: Obtain the user's authorization status, and based on the authorization status, obtain user attribute information, which is used to represent the user's basic information and the user's current scene information; Obtain the target question-and-answer resources based on the user attribute information; The method involves asking the user via voice whether they are willing to participate in the question-and-answer session of the target question-and-answer resource. Upon the user's consent, the target question-and-answer resource is broadcast via voice based on a preset playback rule. This includes: identifying the content of the target question-and-answer resource to obtain a number of question-and-answer questions; broadcasting the number of question-and-answer questions sequentially; and receiving the user's voice input information for each question-and-answer question and confirming the answer before playing the next question-and-answer question. The question-and-answer method also includes generating the result resource of the target question-and-answer resource based on the number of question-and-answer questions and their corresponding answers. The preset playback rules include multiple broadcast voice packages, answer prompts, remaining question prompts, and estimated question-and-answer time prompts. When broadcasting the question-and-answer questions, one of the multiple broadcast voice packages is randomly selected to broadcast the question-and-answer questions. If no user voice input is received within a preset time, the answer prompt is broadcast. Before each broadcast of a question-and-answer question, the number of remaining questions and the estimated question-and-answer time are broadcast. Receive user voice input information, convert the voice input information into text information, and determine the user's answer to the current question based on the text information.

2. The question-and-answer method based on voice interaction according to claim 1, characterized in that, The step of obtaining user authorization status and obtaining user attribute information based on the authorization status includes: obtaining user ID information, sending an authorization prompt based on the user ID information, receiving the user's authorization operation based on the user ID information, determining whether the authorization operation is an agreement to authorization, and obtaining user basic information and the user's current scene information based on the user's agreement to authorization.

3. The question-and-answer method based on voice interaction according to claim 2, characterized in that, The basic information includes the user's historical operation behavior. Obtaining question-and-answer resources based on the user attribute information includes: obtaining question-and-answer resources that match the scenario information from the database based on the basic information and scenario information; obtaining the user's historical question-and-answer resource interaction information; if the question-and-answer resource does not belong to the historical question-and-answer resource interaction information, then the question-and-answer resource is determined as the target question-and-answer resource; if the question-and-answer resource belongs to the historical question-and-answer resource interaction information, then the question-and-answer resource is re-obtained from the database.

4. The question-and-answer method based on voice interaction according to claim 2, characterized in that, After obtaining the user ID information, the methods for obtaining the user's authorization status include: displaying an authorization button through the human-computer interaction interface of the client and receiving the user's authorization operation on the authorization button; and / or providing voice prompts to the user to perform the authorization operation through the client and receiving the user's voice input authorization operation.

5. The question-and-answer method based on voice interaction according to claim 1, characterized in that, The step of determining the user's answer to the current question based on the text information includes: comparing the text information with the answers to the current question pre-stored in the database, and determining the answer that is the same as or has the highest similarity to the text information as the answer to the current question.

6. A question-and-answer system based on voice interaction, applied to a client, characterized in that, include: The request module is used to obtain the user's authorization status and obtain user attribute information based on the authorization status. The user attribute information is used to represent the user's basic information and the user's current scene information. The question-and-answer resource acquisition module is used to acquire target question-and-answer resources based on the user attribute information; The broadcasting module is used to ask users via voice whether they are willing to participate in the question-and-answer session of the target question-and-answer resource. In response to user consent, it broadcasts the target question-and-answer resource via voice based on preset playback rules. This includes: identifying the content of the target question-and-answer resource to obtain several question-and-answer questions; broadcasting the several question-and-answer questions sequentially; and receiving user voice input information for each question-and-answer question and determining the answer before playing the next question-and-answer question. The question-and-answer method also includes generating a result resource of the target question-and-answer resource based on the several question-and-answer questions and their corresponding answers. The preset playback rules include multiple broadcast voice packages, answer prompts, remaining question prompts, and estimated question-and-answer time prompts. When broadcasting the several question-and-answer questions, one broadcast voice package is randomly selected from the multiple broadcast voice packages to broadcast the question-and-answer questions. If no user voice input is received within a preset time, an answer prompt is broadcast via voice. Before each question-and-answer broadcast, the number of remaining question-and-answer questions and the estimated question-and-answer time are broadcast via voice. The answer processing module is used to receive user voice input information, convert the voice input information into text information, and determine the user's answer to the current question based on the text information.

7. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the question-and-answer method based on voice interaction as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the steps of the question-and-answer method based on voice interaction as described in any one of claims 1 to 5.

Images