CN112735420A - Question and answer method and device based on intelligent sound box, intelligent sound box and medium - Google Patents

Question and answer method and device based on intelligent sound box, intelligent sound box and medium Download PDF

Info

Publication number
CN112735420A
CN112735420A CN201910974071.4A CN201910974071A CN112735420A CN 112735420 A CN112735420 A CN 112735420A CN 201910974071 A CN201910974071 A CN 201910974071A CN 112735420 A CN112735420 A CN 112735420A
Authority
CN
China
Prior art keywords
current
voice
sound box
answer
intelligent sound
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910974071.4A
Other languages
Chinese (zh)
Other versions
CN112735420B (en
Inventor
赵涛涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201910974071.4A priority Critical patent/CN112735420B/en
Publication of CN112735420A publication Critical patent/CN112735420A/en
Application granted granted Critical
Publication of CN112735420B publication Critical patent/CN112735420B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R3/00—Circuits for transducers, loudspeakers or microphones
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2430/00—Signal processing covered by H04R, not provided for in its groups

Abstract

The application discloses a question and answer method and device based on an intelligent sound box, the intelligent sound box and a medium, and relates to the field of artificial intelligence. The specific implementation scheme is as follows: acquiring current problem voice consulted by a current user from a current intelligent sound box; determining a relative intelligent sound box and an auxiliary intelligent sound box of the current user according to the identity type of the current user; sending the current problem voice to the relative intelligent sound box and the auxiliary intelligent sound box; and determining the current answer voice of the current question voice according to the response information of the relatives intelligent sound box and the auxiliary intelligent sound box. According to the method and the device, the relatives intelligent sound box and the auxiliary intelligent sound box are determined according to the current user identity, and the current question voice is sent to the relatives intelligent sound box and the auxiliary intelligent sound box, so that the current answer voice is obtained. A new question and answer mechanism is provided based on the intelligent sound box, and the accurate response rate of the question and answer voice is improved.

Description

Question and answer method and device based on intelligent sound box, intelligent sound box and medium
Technical Field
The application relates to the technical field of computers, in particular to an artificial intelligence technology, and particularly relates to a question and answer method and device based on an intelligent sound box, the intelligent sound box and a medium.
Background
The intelligent sound box combines the artificial intelligence technology, and various problems in life are gradually solved. In the intelligent question and answer provided by the intelligent sound box, the best matching answer can be searched in the answer library according to the voice question and answer of the user and fed back to the user. For example, for a voice question and answer of "today's weather", the smart speaker searches for an answer from the weather class database and feeds back to the user.
However, the prior art can only provide answers in an answer library, and the content of the answer library is limited, so that the problem of the eight-door five-family can not be solved.
Disclosure of Invention
The embodiment of the application discloses a question and answer method and device based on an intelligent sound box, the intelligent sound box and a medium, and the accurate response rate of the question and answer voice can be improved.
In a first aspect, an embodiment of the present application discloses a question and answer method based on a smart speaker, including:
acquiring current problem voice consulted by a current user from a current intelligent sound box;
determining a relative intelligent sound box and an auxiliary intelligent sound box of the current user according to the identity type of the current user;
sending the current problem voice to the relatives smart sound box and the auxiliary smart sound box;
and determining the current answer voice of the current question voice according to the response information of the relatives intelligent sound box and the auxiliary intelligent sound box.
One embodiment of the above application has the following advantages or benefits: according to the identity type of the current user, a parent intelligent sound box and an auxiliary intelligent sound box are determined, response information of the parent user and the auxiliary user is obtained through interaction with the parent intelligent sound box and the auxiliary intelligent sound box, and the current answer voice is determined according to the response information. A new question and answer mechanism is provided by connecting different intelligent sound boxes, the precision response rate of the question and answer is improved, and the application range of the question and answer is also improved.
In addition, according to the question and answer method based on the smart sound box of the above embodiment of the present application, the following additional technical features may also be provided:
optionally, determining the family smart speaker and the auxiliary smart speaker of the current user according to the identity type of the current user includes:
if the identity type of the current user is child or parent, taking the intelligent sound box associated with the parent or child of the current user as the relatives intelligent sound box;
an auxiliary smart speaker is selected from smart speakers associated with other parents or other children.
One embodiment in the above application has the following advantages or benefits: the children answer the questions of the parents or the parents answer the questions of the children, the difference of the adept contents of the children and the parents is fully considered, and the answering efficiency and accuracy are improved.
Optionally, selecting an auxiliary smart speaker from smart speakers associated with other parents or other children includes:
the auxiliary smart speakers are selected from the smart speakers associated with other parents or other children based on the domain to which the current problem speech pertains, the areas of expertise of other parents or other children, and the liveness of other parents or other children.
One embodiment in the above application has the following advantages or benefits: the intelligent sound box is further accurately selected by combining the adequacy field and the liveness of the user, so that the answer accuracy is further improved.
Optionally, determining the current answer voice of the current question voice according to the response information of the relatives smart sound box and the auxiliary smart sound box, including:
if the relatives answer voice fed back by the relatives intelligent sound box is received, taking the relatives answer voice as the current answer voice of the current question voice;
and otherwise, selecting the current answer voice of the current question voice from the auxiliary answer voices fed back by the at least two auxiliary intelligent sound boxes according to the feedback time of the at least two auxiliary intelligent sound boxes.
One embodiment in the above application has the following advantages or benefits: and determining the final current answer voice according to the response information from two angles of family state difference and answer effectiveness, and further improving the quality of the answer voice.
Optionally, after determining the current answer voice of the current question voice, the method further includes:
if the current answer voice comes from the auxiliary intelligent sound box, displaying the scoring and excellence fields of the answer user to which the current answer voice belongs, and displaying the current answer voice.
One embodiment in the above application has the following advantages or benefits: the answer voice content is further enriched by providing the consulting user with a rating and a field of excellence to assist the user.
Optionally, before displaying the scoring and excellence areas of the user to which the current answer voice belongs, the method further includes:
and determining the adequacy field of the answer user according to the historical answer voice of the answer user to which the current answer voice belongs and the score of the historical answer voice.
One embodiment in the above application has the following advantages or benefits: and determining the adequacy field of the answering user through the historical answering records of the answering user, and providing answers for questions in the corresponding field to further improve the matching degree of the question answering party and the answering party.
Optionally, after determining the current answer voice of the current question voice, the method further includes:
acquiring the current grade of the current user on the current answer voice;
and updating the score of the user to which the current answer voice belongs according to the current score.
One embodiment in the above application has the following advantages or benefits: the content richness of the answer voice is improved by determining the scores of the answer users.
Optionally, after obtaining the current score of the current user on the current answer voice, the method further includes:
and if the current score is larger than a score threshold value, generating a question-answer pair voice comprising the current question voice and the current answer voice, and determining the answer of a new question according to the question-answer pair voice.
One embodiment in the above application has the following advantages or benefits: by constructing high-quality question-answer pair voices for sharing to subsequent users with similar identity types and the same question, the determination efficiency of the subsequent question-answer voices can be improved.
Optionally, before sending the current question voice to the relatives smart speaker, the method further includes:
and if the relative intelligent sound box of the current user is the current intelligent sound box, determining whether answer voice of the current question voice exists in the voice of the local question and answer of the current intelligent sound box.
One embodiment in the above application has the following advantages or benefits: if the user asks questions through the relatives intelligent sound box, answer voices are searched for in the voices through local question and answer of the relatives intelligent sound box, and accurate and quick search of the question and answer voices is achieved.
In a second aspect, an embodiment of the present application discloses a question answering device based on smart speaker, including:
the voice acquisition module is used for acquiring current problem voice consulted by the current user from the current intelligent sound box;
the sound box determining module is used for determining the relatives intelligent sound box and the auxiliary intelligent sound box of the current user according to the identity type of the current user;
the voice sending module is used for sending the current problem voice to the relatives intelligent sound box and the auxiliary intelligent sound box;
and the voice determining module is used for determining the current answer voice of the current question voice according to the response information of the relatives intelligent sound box and the auxiliary intelligent sound box.
In a third aspect, an embodiment of the present application discloses a smart speaker, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the smart speaker-based question answering method disclosed in any embodiment of the present application.
In a fourth aspect, embodiments of the present application disclose a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method for question answering based on a smart sound box provided in any of the embodiments of the present application.
Other effects of the above-described alternative will be described below with reference to specific embodiments.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
fig. 1 is a schematic flowchart of a question-answering method based on a smart sound box according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a question and answer method based on a smart sound box disclosed in the second embodiment of the present application;
fig. 3 is a schematic structural diagram of a question answering device based on an intelligent sound box disclosed in the third embodiment of the present application;
fig. 4 is a block diagram of an intelligent sound box according to a fourth embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Example one
Fig. 1 is a schematic flowchart of a question-answering method based on a smart speaker disclosed in an embodiment of the present application, which is applicable to a case of performing voice question-answering through the smart speaker. The method can be executed by a question answering device based on the intelligent loudspeaker box, can be realized in a hardware and/or software mode, and can be configured in the intelligent loudspeaker box. The method specifically comprises the following steps:
s110, obtaining current problem voice of current user consultation from the current intelligent sound box.
In the embodiment of the application, the current problem voice is the problem voice data of the current user collected by the current smart sound box. Among the current problems may be household life-like problems such as household appliance use, furniture use, plumbing, water and gas, cooking, flower and bird fish or childbearing problems.
And S120, determining the relative intelligent sound box and the auxiliary intelligent sound box of the current user according to the identity type of the current user.
In the embodiment of the application, the relative account of the intelligent sound box user and the corresponding equipment information are determined according to the address book in the intelligent sound box, so that the relative relationship between the users and the equipment are established. For example, a first user, a second user and a third user respectively have a first intelligent sound box, a second intelligent sound box and a third intelligent sound box, and can determine that the first user and the second user are in a relationship of relatives based on the address book in the intelligent sound boxes, and the first user and the third user are in a relationship of strangers, so that the first intelligent sound box is the relatives intelligent sound box of the second user, and correspondingly, the second intelligent sound box is the relatives intelligent sound box of the first user; the first intelligent sound box and the third user are strange to each other.
Specifically, according to the identity type of the current user, the intelligent sound box which has a relationship with the current user is used as a family intelligent sound box, and an auxiliary intelligent sound box is selected from the intelligent sound boxes which have a strange relationship with the current user. The identity types of the users can include children and parents, and also can include children, young people and old people.
According to the method and the device, the relatives among the users and the loudspeaker box equipment are established, the questions are solved for the users through the relatives intelligent loudspeaker boxes and the auxiliary intelligent loudspeaker boxes according to the established relationships, namely the questions are solved by connecting different intelligent loudspeaker boxes, and particularly the relatives intelligent loudspeaker boxes are matched with one another, so that a new question answering mechanism is provided.
And S130, sending the current problem voice to the relatives intelligent sound box and the auxiliary intelligent sound box.
In this embodiment of the application, the current question voice may be sent to the parent smart sound box and the auxiliary smart sound box corresponding to the current user by the server, so that the parent smart sound box and the auxiliary smart sound box respond to the current question voice.
And S140, determining the current answer voice of the current question voice according to the response information of the relatives intelligent sound box and the auxiliary intelligent sound box.
In this embodiment of the application, the response information refers to response voice fed back for the question voice, the response voice is preferably obtained from the response information fed back by the relatives smart sound box, and if the relatives smart sound box of the current user is not found, the response information fed back by the auxiliary smart sound box is determined.
Optionally, if a relatives answer voice fed back by a relatives smart sound box is received, taking the relatives answer voice as a current answer voice of the current question voice; and otherwise, selecting the current answer voice of the current question voice from the auxiliary answer voices fed back by the at least two auxiliary intelligent sound boxes according to the feedback time of the at least two auxiliary intelligent sound boxes. The final current answer voice is determined according to the response information from two aspects of family state difference and answer effectiveness, and the quality of the answer voice is further improved.
Specifically, for the received current question voice of the current user, both the relatives smart sound box and the auxiliary smart sound box respond to the current question voice, and then the relatives smart sound box preferentially selects to determine the answer voice, and the answer voice is taken as the current answer voice matched with the current question voice. It should be noted that, if there is no parent smart speaker for the current user, the auxiliary smart speaker may be used to answer the question voice, and the answer voice is used as the current answer voice matching with the current question voice. Or, if a certain auxiliary smart speaker answers before the parent smart speaker, the answer of the auxiliary smart speaker may be used as the main answer, and the answer of the parent smart speaker may be used as the supplementary answer.
When the answer is selected from the responses of different auxiliary intelligent sound boxes, the auxiliary answer voice fed back by the auxiliary intelligent sound box with shorter feedback time interval is preferentially selected according to the feedback time of the auxiliary intelligent sound box, and the auxiliary answer voice is taken as the current answer voice. For example, current question voice is sent to 10 auxiliary smart sound boxes, the time sequence of the 10 auxiliary smart sound boxes for feeding back the current question voice is judged, and the auxiliary answer voice fed back by the auxiliary smart sound box fed back firstly is used as the current answer voice.
The embodiment utilizes the characteristic that the relatives and the users are more familiar with each other and more know the requirement of the opposite side, and the relatives and the users preferentially assist the users to answer; and moreover, the timeliness and the expansibility of the question and answer are also considered, the question and answer mechanism has the advantages of accuracy and timeliness, wide coverage, capability of answering complex and various questions in family life and high user satisfaction, and the questions which are not answered in time or cannot be answered by the relatives are given through the auxiliary users.
According to the technical scheme, the parent intelligent sound box and the auxiliary intelligent sound box are determined according to the identity type of the current user, the response information of the parent user and the response information of the auxiliary user are obtained through interaction with the parent intelligent sound box and the auxiliary intelligent sound box, and the current answer voice is determined according to the response information. A new question and answer mechanism is provided by connecting different intelligent sound boxes, the question and answer accuracy and timeliness are improved, and the viscosity of a user is high. Compared with the intelligent sound box which solves the user questions based on the existing fixed data in the database, the intelligent sound box solves the questions mutually among the users of the intelligent sound box, particularly solves the questions mutually among the relatives, improves the coverage of the questions and answers, and enriches the functions of the intelligent sound box.
In the embodiment of the present application, S120 may include: if the identity type of the current user is child or parent, taking the intelligent sound box associated with the parent or child of the current user as the relatives intelligent sound box; an auxiliary smart speaker is selected from smart speakers associated with other parents or other children.
And solving the problem for the user with the second identity type by adopting the user with the first identity type, wherein the first identity type is different from the second identity type. Specifically, the questions of the child user can be solved by the parent user, and the questions of the parent user can be solved by the child user node. Note that "child user" and "parent user" refer to a young user or a young user and, correspondingly, "parent user" may refer to a young user or an old user, in order to distinguish the user identity types. The two need not have a relationship. The embodiment makes full use of the particularity of the family life questions, users with different identity types have different adequacy contents, and users with the same identity type generally have similar adequacy contents, namely the success rate of answering questions between users with the same identity type is lower than that between users with different identity types, namely the difference of the adequacy fields of children and parents is fully considered, and the answering efficiency is further improved.
Optionally, selecting an auxiliary smart speaker from smart speakers associated with other parents or other children includes: the auxiliary smart speakers are selected from the smart speakers associated with other parents or other children based on the domain to which the current problem speech pertains, the areas of expertise of other parents or other children, and the liveness of other parents or other children. Through combining user's strong field and liveness, the supplementary intelligent audio amplifier of accurate selection to the accuracy of answer is further improved.
Example two
On the basis of the first embodiment, the embodiment provides a new question answering method based on the intelligent sound box. Fig. 2 is a schematic flow chart of a question and answer method based on a smart speaker disclosed in the second embodiment of the present application, where the method specifically includes the following steps:
s210, obtaining current problem voice of the current user consultation from the current intelligent sound box.
In the embodiment of the application, the current user can be the old, the young and the children, and the identity information of the current user is judged according to the current problem voice. For example, the current user identity of the intelligent sound box can be judged by analyzing the current problem voice consulted by the current user and judging the information such as the tone, the tone and the like of the user in the current problem voice; and if the intelligent sound box user is the old, recording the information of the intelligent sound box into an old database.
Furthermore, the intelligent sound box with the address book can automatically help the user to build a family circle, the family circle can acquire the relatives and friends account numbers of the user and the corresponding equipment information, so that the corresponding relation between the user and the parents of the user is built, and the information of the user is stored in a young people database; storing the parent information of the user in an old man database. The data of the corresponding relationship between children and parents can be definitely judged, and the corresponding relationship is stored in a child and parent database. And for the intelligent sound box without the address book, judging the storage mode of the user information according to the voice information recorded by the sound box. If the main audio frequency recorded by the loudspeaker box is the sound of the young people, recording the user information to a database of the young people; and if the information recorded by the loudspeaker box is the voice of the old, recording the user information to the database of the old.
S220, determining the relative intelligent sound box and the auxiliary intelligent sound box of the current user according to the identity type of the current user.
And S230, sending the current problem voice to the relatives intelligent sound box and the auxiliary intelligent sound box.
And S240, determining the current answer voice of the current question voice according to the response information of the relatives intelligent sound box and the auxiliary intelligent sound box.
And S250, acquiring the current score of the current user on the current answer voice.
In this embodiment of the application, after the current smart speaker plays the current answer voice, the current user may score the current answer voice, for example, the score may be selected from 0 to 10, the response of the current user to the answer user is satisfactory, and 8.5 may be selected as the current score of the current answer voice.
And S260, if the current score is larger than the score threshold value, generating a question-answer voice comprising the current question voice and the current answer voice, and determining the answer of a new question according to the question-answer voice.
Taking an example in which the score threshold is set to 6, if the score of the current answer voice is 8.5, a question-answer pair voice including the current question voice and the current answer voice is generated. Subsequently, after the accumulated high-quality question-answer pair voice reaches a certain number, when new question voice is obtained, the answer can be inquired in the pre-generated question-answer pair voice data, so that the question-answer efficiency is improved. It should be noted that, in this embodiment, the method for answering the voice data by using question answering and the method for matching the answer between the speakers are not specifically limited, for example, the main answer is obtained by using question answering to the voice answer, and the auxiliary answer is obtained by using speaker interaction.
In this embodiment, the question-answer and voice data may be classified and stored in fine granularity, for example, the question-answer and voice data answered by the parent user is stored in a first question-answer table, the question-answer and voice answered by the child user is stored in a second question-answer table, and accordingly, if the new question voice comes from the parent user, the answer is searched in the second question-answer table; if the new question is spoken by a child user, the answer is looked up in the first question-answer pair. The differences of children and parents in good fields are fully considered, and the answering efficiency is further improved.
In addition, before sending the current question voice to the relatives smart speaker, the method may further include: and if the relative intelligent sound box of the current user is the current intelligent sound box, determining whether answer voice of the current question voice exists in the voice of the local question and answer of the current intelligent sound box. Specifically, in consideration of mobility among users, the smart sound box may store a high-score question-answer pair associated with a high-score answer of a local user, and the user may ask a question through the relatives smart sound box, and at this time, directly search an answer from the question-answer pair voice locally stored by the relatives smart sound box. It should be noted that the smart sound box may also locally store the high-score question-answer pairs associated with the high-score questions of the local user.
According to the technical scheme of the embodiment, high-quality question-answer pair voice is constructed according to the scores of the question users on the answer voice, and the answer efficiency can be further improved by adopting the question-answer pair voice.
In this embodiment of the present application, S250 may further include: and updating the score of the user to which the current answer voice belongs according to the current score. The content richness of the answer voice is improved by determining the scores of the answer users.
In the embodiment of the application, the current score of the answering user is obtained, and if the answering user replies for the first time, the intelligent sound box records the current score of the current user to the answering user into a question-answer database; and if the answer user does not reply for the first time, the current score of the answer user is acquired and combined with the historical score of the answer user, and the current score is weighted and scored to be used as the comprehensive score of the answer user. For example, if the history score of the answering user is 8.2 points, and the score of the current answering voice replied by the current user to the answering user is 8 points, the composite score corresponding to the answering user is 8.1 points.
Optionally, the area of excellence of the answering user is determined according to the historical answering voice of the answering user to which the current answering voice belongs and the score of the historical answering voice. And determining the adequacy field of the answering user through the historical answering records of the answering user, and providing answers for questions in the corresponding field to further improve the matching degree of the question answering party and the answering party.
Specifically, the adequacy field of the answer user can be determined by extracting the historical high score of the answer user, namely, the related field of which the historical answer voice is highly scored is used as the adequacy field of the answer user, the determined adequacy field is not unique, and the adequacy field can be updated in real time according to the subsequent historical score of the answer user. For example, if the score is low when the score is 0-5, the score is high when the score is 6-10, and the history score obtained when a certain answering user answers the question with the "Hangzhou bang dish method" is high, the answering user can be considered to be more proficient in the field of the "Hangzhou bang dish", and the field is taken as the adept field of the answering user.
Optionally, if the current answer voice is from the auxiliary smart sound box, the scoring and the areas of excellence of the answer user to which the current answer voice belongs are displayed, and the current answer voice is displayed. And determining the adequacy field of the answering user through the historical answering records of the answering user, and providing answers for questions in the corresponding field to further improve the matching degree of the question answering party and the answering party. Specifically, before the current intelligent sound box plays the current answer voice, the historical scores and the field of excellence of the answer user are played, and the regional information of the answer user can be played, such as "users from Hangzhou, score 8.2, proficient Hangzhou vegetable"; if the answer user is the first answer, only 'user from Hangzhou state' is displayed, and the scoring and proficiency field of the user are not displayed.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a third disclosure of an intelligent speaker-based question answering device in an embodiment of the present application, which is applicable to a case of performing voice question answering through an intelligent speaker. The device is configured in the intelligent sound box, and the question answering method based on the intelligent sound box can be realized according to any embodiment of the application. The device specifically comprises the following steps:
a voice obtaining module 310, configured to obtain a current problem voice of a current user consultation from a current smart sound box;
the sound box determining module 320 is configured to determine, according to the identity type of the current user, a parent smart sound box and an auxiliary smart sound box of the current user;
a voice sending module 330, configured to send the current question voice to the parent smart sound box and the auxiliary smart sound box;
the voice determining module 340 is configured to determine a current answer voice of the current question voice according to the response information of the relatives smart sound box and the auxiliary smart sound box.
Optionally, the speaker determining module 320 is specifically configured to:
if the identity type of the current user is child or parent, taking the intelligent sound box associated with the parent or child of the current user as the relatives intelligent sound box;
an auxiliary smart speaker is selected from smart speakers associated with other parents or other children.
Optionally, the speaker determining module 320 is further specifically configured to:
the auxiliary smart speakers are selected from the smart speakers associated with other parents or other children based on the domain to which the current problem speech pertains, the areas of expertise of other parents or other children, and the liveness of other parents or other children.
Optionally, the voice determining module 340 is specifically configured to:
if the relatives answer voice fed back by the relatives intelligent sound box is received, taking the relatives answer voice as the current answer voice of the current question voice;
and otherwise, selecting the current answer voice of the current question voice from the auxiliary answer voices fed back by the at least two auxiliary intelligent sound boxes according to the feedback time of the at least two auxiliary intelligent sound boxes.
Further, the apparatus further comprises:
and a domain determining module 350, configured to determine the area of excellence of the responding user according to the historical responding voice of the responding user to which the current responding voice belongs and the score of the historical responding voice.
And the voice display module 360 is configured to display the scoring and proficiency field of the answer user to which the current answer voice belongs and display the current answer voice if the current answer voice is from the auxiliary smart sound box.
Further, the apparatus further comprises:
a score obtaining module 370, configured to obtain a current score of the current user on the current answer voice;
and a score updating module 380, configured to update, according to the current score, a score of a user to which the current answer voice belongs.
Further, the voice determining module 340 is further specifically configured to:
and if the current score is larger than a score threshold value, generating a question-answer pair voice comprising the current question voice and the current answer voice, and determining the answer of a new question according to the question-answer pair voice.
Further, the voice determining module 340 is further specifically configured to:
and if the relative intelligent sound box of the current user is the current intelligent sound box, determining whether answer voice of the current question voice exists in the voice of the local question and answer of the current intelligent sound box.
According to the technical scheme of the embodiment, through the mutual cooperation of the functional modules, the voice acquisition, the loudspeaker box determination, the voice sending and the voice determination are realized. According to the embodiment of the invention, the parent intelligent sound box and the auxiliary intelligent sound box are determined according to the identity type of the current user, the response information of the parent user and the auxiliary user is obtained through interaction with the parent intelligent sound box and the auxiliary intelligent sound box, and the current answer voice is determined according to the response information. A new question and answer mechanism is provided by connecting different intelligent sound boxes, the precision response rate of the question and answer is improved, and the application range of the question and answer is also improved.
Example four
The present application also provides, in accordance with embodiments of the present application, a smart speaker and a non-transitory computer readable storage medium having computer instructions stored thereon.
Fig. 4 is a block diagram of a smart speaker based on a question and answer method of the smart speaker according to an embodiment of the present application. Smart speakers are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Smart speakers may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable speakers, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 4, the smart speaker includes: one or more processors 401, memory 402, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executed within the smart speaker, including instructions stored in or on the memory to display graphical information of the GUI on an external input/output device (such as a display speaker coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple smart enclosures may be connected, with each enclosure providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 4, one processor 401 is taken as an example.
Memory 402 is a non-transitory computer readable storage medium as provided herein. The memory stores instructions executable by at least one processor, so that the at least one processor executes the question answering method based on the smart sound box provided by the application. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the smart speaker-based question answering method provided by the present application.
Memory 402, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the smart speaker-based question answering method in the embodiments of the present application. The processor 401 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions and modules stored in the memory 402, that is, the question-answering method based on the smart sound box in the above method embodiment is implemented.
The memory 402 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the smart speaker based on the question and answer of the smart speaker, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 402 optionally includes memory located remotely from processor 401, which may be connected to a smart speaker based question answering over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The intelligent sound box based on the question and answer method of the intelligent sound box can further comprise: an input device 403 and an output device 404. The processor 401, the memory 402, the input device 403 and the output device 404 may be connected by a bus or other means, and fig. 4 illustrates an example of a connection by a bus.
Input device 403 may receive entered numeric or character information and generate key signal inputs related to user settings and function controls of the smart speaker based on the question and answer of the smart speaker, such as a touch screen, keypad, mouse, track pad, touch pad, pointer stick, one or more mouse buttons, track ball, joystick, or other input device. The output devices 404 may include a display speaker, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display enclosure may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some embodiments, the display speaker may be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, sound box, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme of the embodiment of the application, the relatives intelligent sound box and the auxiliary intelligent sound box are determined according to the identity type of the current user, the obtained current question voice is respectively sent to the relatives intelligent sound box and the auxiliary intelligent sound box, and the feedback response information is collected, so that the current answer voice corresponding to the current question voice is determined. The problem of limited data storage in the question-answering database is solved, the problem that cannot be found in the question-answering database is subjected to supplementary search, and the technical effect of improving the accurate response rate of the question-answering voice is achieved.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (12)

1. A question and answer method based on an intelligent sound box is characterized by comprising the following steps:
acquiring current problem voice consulted by a current user from a current intelligent sound box;
determining a relative intelligent sound box and an auxiliary intelligent sound box of the current user according to the identity type of the current user;
sending the current problem voice to the relatives smart sound box and the auxiliary smart sound box;
and determining the current answer voice of the current question voice according to the response information of the relatives intelligent sound box and the auxiliary intelligent sound box.
2. The method of claim 1, wherein determining the parent smart speaker and the auxiliary smart speaker of the current user based on the identity type of the current user comprises:
if the identity type of the current user is child or parent, taking the intelligent sound box associated with the parent or child of the current user as the relatives intelligent sound box;
an auxiliary smart speaker is selected from smart speakers associated with other parents or other children.
3. The method of claim 2, wherein selecting an auxiliary smart speaker from smart speakers associated with other parents or other children comprises:
the auxiliary smart speakers are selected from the smart speakers associated with other parents or other children based on the domain to which the current problem speech pertains, the areas of expertise of other parents or other children, and the liveness of other parents or other children.
4. The method of claim 1, wherein determining a current answer voice for the current question voice from the response information of the parent smart speaker and the auxiliary smart speaker comprises:
if the relatives answer voice fed back by the relatives intelligent sound box is received, taking the relatives answer voice as the current answer voice of the current question voice;
and otherwise, selecting the current answer voice of the current question voice from the auxiliary answer voices fed back by the at least two auxiliary intelligent sound boxes according to the feedback time of the at least two auxiliary intelligent sound boxes.
5. The method of claim 1, wherein after determining a current answer speech for the current question speech, further comprising:
if the current answer voice comes from the auxiliary intelligent sound box, displaying the scoring and excellence fields of the answer user to which the current answer voice belongs, and displaying the current answer voice.
6. The method of claim 5, wherein before presenting the scoring and areas of excellence of the user to which the current answer speech pertains, further comprising:
and determining the adequacy field of the answer user according to the historical answer voice of the answer user to which the current answer voice belongs and the score of the historical answer voice.
7. The method of claim 1, wherein after determining a current answer speech for the current question speech, further comprising:
acquiring the current grade of the current user on the current answer voice;
and updating the score of the user to which the current answer voice belongs according to the current score.
8. The method of claim 7, wherein after obtaining the current rating of the current user for the current answer speech, further comprising:
and if the current score is larger than a score threshold value, generating a question-answer pair voice comprising the current question voice and the current answer voice, and determining the answer of a new question according to the question-answer pair voice.
9. The method of claim 1, wherein prior to sending the current question voice to the parent smart speaker, further comprising:
and if the relative intelligent sound box of the current user is the current intelligent sound box, determining whether answer voice of the current question voice exists in the voice of the local question and answer of the current intelligent sound box.
10. A question answering device based on intelligent sound box is characterized in that the device comprises:
the voice acquisition module is used for acquiring current problem voice consulted by the current user from the current intelligent sound box;
the sound box determining module is used for determining the relatives intelligent sound box and the auxiliary intelligent sound box of the current user according to the identity type of the current user;
the voice sending module is used for sending the current problem voice to the relatives intelligent sound box and the auxiliary intelligent sound box;
and the voice determining module is used for determining the current answer voice of the current question voice according to the response information of the relatives intelligent sound box and the auxiliary intelligent sound box.
11. An intelligent sound box, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a smartspeaker based question answering method of any one of claims 1-9.
12. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method for question answering based on a smart sound box of any one of claims 1 to 9.
CN201910974071.4A 2019-10-14 2019-10-14 Question and answer method and device based on intelligent sound box, intelligent sound box and medium Active CN112735420B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910974071.4A CN112735420B (en) 2019-10-14 2019-10-14 Question and answer method and device based on intelligent sound box, intelligent sound box and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910974071.4A CN112735420B (en) 2019-10-14 2019-10-14 Question and answer method and device based on intelligent sound box, intelligent sound box and medium

Publications (2)

Publication Number Publication Date
CN112735420A true CN112735420A (en) 2021-04-30
CN112735420B CN112735420B (en) 2022-11-11

Family

ID=75588539

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910974071.4A Active CN112735420B (en) 2019-10-14 2019-10-14 Question and answer method and device based on intelligent sound box, intelligent sound box and medium

Country Status (1)

Country Link
CN (1) CN112735420B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101217515A (en) * 2008-01-03 2008-07-09 腾讯科技（深圳）有限公司 A system and method based on question sorting and push
US20130283164A1 (en) * 2012-04-20 2013-10-24 Padmanabhan Mahalingam System for Controlling Association of Microphone and Speakers
CN103455592A (en) * 2013-08-30 2013-12-18 广州网易计算机系统有限公司 Question answering method, device and system
CN104133817A (en) * 2013-05-02 2014-11-05 深圳市世纪光速信息技术有限公司 Online community interaction method and device and online community platform
CN107222384A (en) * 2016-03-22 2017-09-29 深圳新创客电子科技有限公司 Electronic equipment and its intelligent answer method, electronic equipment, server and system
CN109871439A (en) * 2019-02-18 2019-06-11 华南理工大学 A kind of Ask-Answer Community problem method for routing based on deep learning

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101217515A (en) * 2008-01-03 2008-07-09 腾讯科技（深圳）有限公司 A system and method based on question sorting and push
US20130283164A1 (en) * 2012-04-20 2013-10-24 Padmanabhan Mahalingam System for Controlling Association of Microphone and Speakers
CN104133817A (en) * 2013-05-02 2014-11-05 深圳市世纪光速信息技术有限公司 Online community interaction method and device and online community platform
CN103455592A (en) * 2013-08-30 2013-12-18 广州网易计算机系统有限公司 Question answering method, device and system
CN107222384A (en) * 2016-03-22 2017-09-29 深圳新创客电子科技有限公司 Electronic equipment and its intelligent answer method, electronic equipment, server and system
CN109871439A (en) * 2019-02-18 2019-06-11 华南理工大学 A kind of Ask-Answer Community problem method for routing based on deep learning

Also Published As

Publication number Publication date
CN112735420B (en) 2022-11-11

Similar Documents

Publication Publication Date Title
KR102064203B1 (en) Emoji recommendation method and device
CN109145123B (en) Knowledge graph model construction method, intelligent interaction method and system and electronic equipment
CN103915095B (en) The method of speech recognition, interactive device, server and system
AU2016201139A1 (en) Conversational question and answer
CN104618806A (en) Method, device and system for acquiring comment information of video
CN111159380B (en) Interaction method and device, computer equipment and storage medium
KR102505352B1 (en) User communication method, device, apparatus and storage medium in live room
CN112133281A (en) Voice broadcasting method and device, electronic equipment and storage medium
CN110689903B (en) Method, device, equipment and medium for evaluating intelligent sound box
CN109948151A (en) The method for constructing voice assistant
CN108073675A (en) The search result being included in afterwards in session assistant's context is independently provided
CN110209778A (en) A kind of method and relevant apparatus of dialogue generation
CN112000781A (en) Information processing method and device in user conversation, electronic equipment and storage medium
CN111951782A (en) Voice question and answer method and device, computer readable storage medium and electronic equipment
KR20140004290A (en) Recommandation method of friend and ctreation method of dynammic community using interest graph of music in social network
CN106874451A (en) A kind of method of the personal exclusive corpus of automatic foundation
CN112735420B (en) Question and answer method and device based on intelligent sound box, intelligent sound box and medium
CN112650844A (en) Tracking method and device of conversation state, electronic equipment and storage medium
CN111427444B (en) Control method and device of intelligent device
CN111159382B (en) Method and device for constructing and using session system knowledge model
CN110674338B (en) Voice skill recommendation method, device, equipment and storage medium
CN110633357A (en) Voice interaction method, device, equipment and medium
WO2010131013A1 (en) Collaborative search engine optimisation
CN112165627A (en) Information processing method, device, storage medium, terminal and system
CN111681052B (en) Voice interaction method, server and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant