CN110134235B - Guiding type interaction method - Google Patents
Guiding type interaction method Download PDFInfo
- Publication number
- CN110134235B CN110134235B CN201910339023.8A CN201910339023A CN110134235B CN 110134235 B CN110134235 B CN 110134235B CN 201910339023 A CN201910339023 A CN 201910339023A CN 110134235 B CN110134235 B CN 110134235B
- Authority
- CN
- China
- Prior art keywords
- user
- information
- voice
- age
- guided
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000003993 interaction Effects 0.000 title claims abstract description 44
- 239000011159 matrix material Substances 0.000 claims description 32
- 238000012790 confirmation Methods 0.000 claims description 27
- 230000002452 interceptive effect Effects 0.000 claims description 22
- 230000009467 reduction Effects 0.000 claims description 19
- 238000001228 spectrum Methods 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims 2
- 230000009286 beneficial effect Effects 0.000 description 8
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000011410 subtraction method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0272—Voice signal separating
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Educational Technology (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides a guiding interaction method, which comprises the steps of collecting voice information input by a user; acquiring user characteristic information of a user; acquiring a corresponding guide instruction according to the acquired voice information and the user characteristic information of the user, and calling out a guide template corresponding to the acquired voice information and the user characteristic information from a pre-stored guide template library according to the guide instruction; the guide template comprises at least one guide statement; and guiding sentences in the guiding templates are played in sequence, and the user is guided to learn by calling different guiding templates, so that the learning efficiency of the user is improved.
Description
Technical Field
The invention relates to the technical field of guided education, in particular to a guided interaction method.
Background
When a user learns, the user generally learns by means of a related learning platform, but the learning platform generally guides different users to learn the same knowledge according to the same mode only according to a certain specific learning mode, and in the learning process of the user, after playing audio and video corresponding to knowledge points, the platform generally directly displays problems and results corresponding to the problems to the user.
Disclosure of Invention
The invention provides a guiding type interaction method which is used for guiding a user to learn and improving the learning efficiency of the user by calling different guiding templates.
The embodiment of the invention provides a guiding type interaction method, which comprises the following steps:
collecting voice information input by a user;
acquiring user characteristic information of the user;
acquiring a corresponding guide instruction according to the acquired voice information and the user characteristic information of the user, and calling out a guide template corresponding to the acquired voice information and the user characteristic information from a pre-stored guide template library according to the guide instruction;
the guide template comprises at least one guide statement;
and sequentially playing the guided sentences in the guide template.
In a possible implementation manner, the sequentially playing guided sentences in the guide template includes:
the guide template stores a preset sentence playing sequence;
and playing the guided sentences in the guide template according to the preset sentence playing sequence.
In a possible implementation manner, the sequentially playing guided sentences in the guide template includes:
a preset question-answer database corresponding to the guided sentences is stored in the guide template, when the user answers the guided sentences played by the guide template, answer results corresponding to the current guided sentences answered by the user are obtained, and next guided sentences corresponding to the question-answer results are played according to the question-answer database;
counting the number of the guided sentences answered by the user, judging whether the number of the guided sentences answered by the user is smaller than a preset number, if so, continuing to play the guided sentences answered by the user, and otherwise, ending the playing.
In one possible way of realisation,
before acquiring a corresponding guiding instruction according to the collected voice information and the user characteristic information of the user, judging the voice information input by the user, comprising the following steps:
dividing collected voice information input by a user at equal intervals, playing the divided voice information, judging whether the played split voice information is correct or not by the user, if so, identifying the divided voice information according to a pre-stored standard voice database, judging whether a characteristic value of the divided voice information is matched with a characteristic value of corresponding standard voice information in the standard voice database or not, and if so, extracting a guide instruction in the collected voice information;
otherwise, deleting the collected voice information input by the user and collecting the voice information again.
In one possible way of realisation,
in the process of recognizing the divided voice information, the recognized voice information is subjected to noise reduction treatment, and the method comprises the following steps:
carrying out frame processing on each voice message divided by equal interval time;
acquiring position information of an interaction terminal for acquiring the voice information input by the user, and calling a position map corresponding to the position information from a pre-stored position map library;
acquiring a preset area where the interaction end is located according to the position map, and acquiring a preselected scene of the preset area;
acquiring an environmental noise signal in the collected voice information input by the user;
determining the target scene from the preselected scene according to the environmental noise signal, and searching an environmental noise reduction parameter corresponding to the target scene according to a pre-stored noise reduction parameter database;
separating user voice from the collected voice information input by the user according to the environment noise reduction parameters;
acquiring a minimum frequency threshold and a maximum frequency threshold corresponding to the user in the separated user voice;
acquiring a stationary noise spectrum in the separated user voice;
and generating corresponding effective information by using the acquired minimum frequency threshold, maximum frequency threshold and stable noise spectrum based on a spectrum subtraction algorithm, and eliminating random noise of the effective information.
In one possible way of realisation,
the equal interval time is set by an interactive terminal for collecting the voice information of the user according to the speech speed of the user in a user-defined mode.
In one possible way of realisation,
when the guided sentences in the guide template are played in sequence, the playing progress of the guide data corresponding to the guided sentences needs to be adjusted and recorded, and the method comprises the following steps:
dividing preset region blocks on a display screen of an interaction end playing the guide data, wherein each region block has corresponding adjustment precision;
recording the adjustment operation of the user in each area block, and determining the fast forward and fast backward time corresponding to the adjustment operation according to the adjustment precision on each area block, wherein the adjustment operation comprises an adjustment angle and an adjustment length, and the adjustment length is the distance from an adjustment starting point to an adjustment end point;
and the playing progress of the guide data is jumped from the current playing time to the playing time corresponding to the fast forward and fast backward time corresponding to the adjusting operation, and the playing time after the adjusting operation is recorded.
In one possible way of realisation,
the user characteristic information further includes, user dialog attributes,
the user conversation attribute is obtained according to the conversation content of the user and the virtual human at the interaction end, and the obtaining of the conversation attribute comprises the following steps:
recording the conversation content of the user and the virtual human, and obtaining corresponding conversation question-answer information from the conversation content;
screening reply contents of the user from recorded dialogue contents of the user and the virtual person according to the sequence of the dialogue time of the user and the virtual person, carrying out hierarchical attribute frequency division on the screened reply contents, and determining the attribute of the reply contents corresponding to the attribute frequency as the dialogue attribute of the user when the attribute frequency of the reply contents is greater than or equal to a preset frequency;
when the user talks with the virtual person, the virtual person obtains corresponding preset reply content according to a prestored dialogue database based on the user dialogue attribute, and updates the dialogue database;
and if the virtual person cannot acquire the corresponding preset reply content, actively interrupting the chat by the virtual person, and outputting related prompt information to an interaction end.
In one possible way of realisation,
the step of the user conversing with the virtual man comprises the following steps:
the server receives the reply content input by the user and generated by the interactive terminal;
determining preset reply content of the virtual human corresponding to the received reply content input by the user according to a conversation database;
the server sends the preset reply content to the interaction end for the virtual man to reply;
before the user has a conversation with the avatar, the identity of the user needs to be verified, which includes:
the method comprises the steps that a registration server which registers a user sends identity information of the user to a confirmation server, the confirmation server stores the identity information of the user into a user information database, and an identity certificate of a user login server is agreed between the user and the confirmation server;
distributing an encryption key to the interaction terminal through an encryption key storage management server, encrypting the identity information A of the user after the interaction terminal obtains the encryption key, dividing an encryption key B taken out from the encryption key storage management server by a user server into four parts, namely B1, B2, B3 and B4 according to an agreed protocol, wherein B1 is a section of byte string used for being serially combined with a password original text; b2 is the key used for encryption, the length of which is determined by the length of the key used by the conventional encryption algorithm; b3 is a hashing algorithm used to be determined by the number of hashing algorithms contained in the hashing algorithm library; b4 is an encryption algorithm used depending on the number of encryption algorithms contained in the encryption algorithm library;
transmitting a final ciphertext to the confirmation server, wherein the final ciphertext is obtained by serially combining identity information A and B1 by the interaction end to obtain BB, calling a hash algorithm with a corresponding label in a hash algorithm library according to a value of B3 to calculate a hash value of BB as Bb, calling an encryption algorithm with the same value label in an encryption algorithm library according to a value of B4 and encrypting Bb by using a key B2, and the encrypted ciphertext is denoted as Ba, which is the encrypted final ciphertext;
authenticating that the confirmation server receives the final ciphertext Ba sent by the interaction terminal through the first communication module, finding a corresponding decryption algorithm from an encryption algorithm library of the confirmation server according to an encryption key B4, and decrypting the final ciphertext Ba to obtain a first hash value Bb by combining with an encryption key B2; the confirmation server is further configured to take the identity information a registered by the user from the user database, and calculate a hash value thereof by the same method as the interactive terminal, that is, after the identity information a and the B1 are serially combined, calculate a hash value thereof by using a hash value algorithm with the same number as the value of B3, and obtain a second hash value Bb'; the confirmation server compares whether the first hash value Bb is the same as the second hash value Bb', and if so, the authentication is successful; otherwise, authentication fails; the confirmation server sends an authentication result to the interactive terminal, wherein the authentication result comprises: authentication is successful and authentication is failed.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of a method for guided interaction according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
An embodiment of the present invention provides a method for guided interaction, as shown in fig. 1, including:
step 1: collecting voice information input by a user;
step 2: acquiring user characteristic information of a user;
and step 3: acquiring a corresponding guide instruction according to the acquired voice information and the user characteristic information of the user, and calling out a guide template corresponding to the acquired voice information and the user characteristic information from a pre-stored guide template library according to the guide instruction;
the guide template comprises at least one guide statement;
and 4, step 4: and sequentially playing the guided sentences in the guide template.
In this embodiment, the guidance instruction may be, for example, a user age instruction obtained according to the acquired collected voice information and the user feature information of the user, and a corresponding guidance template is called according to the user age instruction, where the specific process is as follows:
firstly, processing collected voice information to obtain a voice matrix of a user, wherein the voice matrix is to cut the collected voice information according to the same time interval, extracting the values of indexes such as tone, audio frequency, decibel and the like of each section of voice to form a corresponding matrix, obtaining the information matrix of the user according to the user characteristic information of the user, the user characteristic matrix is to store the collected user characteristics as a picture, then extracting the values of pixel points in the picture to form a corresponding matrix, then carrying out gray processing on the values of the pixel points to obtain the information characteristics of the corresponding user, and estimating the approximate age of the user by the obtained matrix according to the following formula:
where S is the estimated age of the user,
is a speech matrix of the user, VnIs the nth voice message in the voice matrix, n is the total number of voice messages,
maximizing the matrix, V, for speech informationnmaxThe maximum value of the nth speech information in the speech matrix in practice, (C)1C2…Cn) To integrate the matrices, CnP is the percentage of the proportion of the nth voice information in the voice matrix in the whole voice, k is the conversion factor of voice to age, t is the conversion factor of user information to age, m is the total number of the user information,
in the form of a matrix of user information,
is taken as a referenceA user information matrix of age users.
The conversion factor of the voice to the age can be obtained from the average age of the user and the average value of the voice matrix, and the conversion factor of the user information to the age can be obtained from the average age of the user and the average value of the user information matrix.
Classifying ages after the ages of the users are obtained according to equation estimation, determining the age instruction of the users, and calling corresponding guide templates, wherein the method comprises the following steps: dividing the estimated user age into four stages, wherein each stage has an intermediate age, and substituting the intermediate age into the following formula:
min(|S-S1|,|S-S2|,|S-S3|,|S-S4|)
wherein S1，S2，S3，S4For the middle age of each stage, finding the corresponding middle value according to the obtained value, namely determining the age stage of the user, so as to obtain the user age instruction, and calling out the corresponding guide module according to the user age instruction corresponding to the age stage of the user for outputting.
The user characteristic information may be, for example, a face image of a user, a point of interest of the user, and the like;
the guided sentence may be, for example, a question sentence for guiding the user, a sentence for guiding the user, or the like.
The guided sentences are set to inspire the thinking and cultivating interest of the users, for example, ten stories that the users listen to the sima light jar-pounding may ask 6 to 7 different questions according to the obtained ages of the users, and the questions answered by the users at different ages may be different.
The beneficial effects of the above technical scheme are: different guide templates are called to guide the user to learn, and the learning efficiency of the user is improved.
The embodiment of the invention provides a method for guiding interaction, which is used for sequentially playing guiding sentences in a guiding template and comprises the following steps:
the guide template stores a preset sentence playing sequence of the guide type sentences;
and playing the guided sentences in the guide template according to a preset sentence playing sequence.
In the above technical solution, the preset sentence order may be, for example, ordered according to the difficulty level of the problem, so that the user can learn from ease to difficulty in the learning process, which is convenient for understanding.
The beneficial effects of the above technical scheme are: through presetting the sentence sequence, the user can learn from shallow to deep conveniently.
The embodiment of the invention provides a method for guiding interaction, which is used for sequentially playing guiding sentences in a guiding template and comprises the following steps:
the method comprises the steps that a preset question-answer database corresponding to a guided sentence is stored in a guide template, when a user answers the guided sentence played by the guide template, an answer result corresponding to the current guided sentence answered by the user is obtained, and the next guided sentence corresponding to the question-answer result is played according to the question-answer database;
and counting the number of the guided sentences answered by the user, judging whether the number of the guided sentences answered by the user is less than the preset number, if so, continuing to play the guided sentences answered by the user, and otherwise, ending the playing.
In the above technical solution, the playing sequence of the guided sentences is different from the playing sequence of the guided sentences in the previous embodiment, the previous embodiment plays the guided sentences according to a preset sequence, and the technical solution plays the next guided sentence corresponding to the question and answer result according to the answer result corresponding to the current guided sentence answered by the user and the question and answer database;
the former is based on a set guiding sequence to guide a user to learn, and the guiding mode is single; the latter is based on the answer result of the user, and guides the user to learn according to the guidance type sentence corresponding to the answer result, and the guidance mode is variable.
It should be noted that, in the above technical solution, when the first guided sentence is played, for example, the guided sentence with the simplest playing difficulty degree may be played, and according to the response of the user to the first guided sentence, the grasping condition of the user to the question posed by the first guided sentence is determined, and according to the determination condition, the corresponding next guided sentence is obtained.
The user can only finish playing after answering all the guided sentences, and the method has the advantages of avoiding the user from missing the answer and improving the acquisition of the knowledge by the user.
The beneficial effects of the above technical scheme are: compared with the previous embodiment, the guiding mode is more flexible, and the learning efficiency of the user is further improved.
The embodiment of the invention provides a method for guiding interaction, which is used for judging voice information input by a user before acquiring a corresponding guiding instruction according to acquired voice information and user characteristic information of the user, and comprises the following steps:
dividing collected voice information input by a user at equal intervals, playing the divided voice information, judging whether the played split voice information is correct or not by the user, if so, identifying the divided voice information according to a pre-stored standard voice database, judging whether a characteristic value of the divided voice information is matched with a characteristic value of corresponding standard voice information in the standard voice database or not, and if so, extracting a guide instruction in the collected voice information;
otherwise, deleting the collected voice information input by the user and collecting the voice information again.
In the technical scheme, different languages and mapping tables of corresponding standard audio data are stored in a standard voice database; and because the speech speed of the user is inconsistent, the speech information is divided by the equal interval time and played again, so that the accuracy of the division and the definition of the collected speech can be ensured, the equal interval time is controlled within a recognizable range, and the accuracy of the speech recognition can be improved.
The beneficial effects of the above technical scheme are: the collected voice information is judged twice, so that the collected voice information is complete and accurate.
The embodiment of the invention provides a guiding interactive method, which is used for carrying out noise reduction processing on recognized voice information in the recognition process of the divided voice information and comprises the following steps:
carrying out frame processing on each voice message divided by equal interval time;
acquiring position information of an interaction terminal for acquiring voice information input by a user, and calling a position map corresponding to the position information from a pre-stored position map library;
acquiring a preset area where the interaction end is located according to the position map, and acquiring a preselected scene of the preset area;
acquiring an environmental noise signal in the collected voice information input by the user;
determining a target scene from the pre-selected scenes according to the environmental noise signals, and searching environmental noise reduction parameters corresponding to the target scene according to a pre-stored noise reduction parameter database;
separating user voice from the collected voice information input by the user according to the environment noise reduction parameters;
acquiring a minimum frequency threshold and a maximum frequency threshold corresponding to the user in the separated user voice;
acquiring a stable noise spectrum in the separated user voice;
and generating corresponding effective information by using the acquired minimum frequency threshold, maximum frequency threshold and stable noise spectrum based on a spectrum subtraction algorithm, and eliminating random noise of the effective information.
In the above technical solution, the noise reduction parameter database stores preselected scenes and noise reduction parameters corresponding to the preselected scenes, where the noise reduction parameters include noise spectrum parameters and noise reduction algorithms. The noise spectrum parameters are obtained by training the noise samples under the same scene according to the collected noise samples. The noise reduction algorithm includes, but is not limited to, comb filter method, wiener filter method, kalman filter method, spectral subtraction method, adaptive filter method, minimum mean square error estimation method, artificial neural network method, and the like.
In the above technical solution, the position information includes a longitude value and a latitude value where the interactive end is located, and the acquisition of the position information is acquired after the user triggers the interactive end.
It should be noted that, a preset scene is recorded in the preselection area, and the accuracy of the preselection area directly affects the accuracy of the determined scene, and further affects the matching degree of the calling parameter, and finally affects the voice noise reduction effect, so that a map with higher accuracy is selected.
Determining a target scene from the preselected scene according to the environmental noise signal, wherein the method can be realized by, for example, determining a first area including the place of the interaction terminal from the preselected area; determining the scene occupying the largest area in the first area as a target scene; according to the obtained preselection area, taking the position of the interaction end as the center and a certain distance as the radius, and setting the area in the range as a first area; determining scenes in the first area according to the information in the preselected area, and determining the percentage of the area of each scene in the first area; and determining the scene with the largest percentage of the area as the scene where the interactive end is positioned, namely the target scene.
Because the noise under different scenes has different characteristics, and the noise characteristics under different scenes are different, the noise of the voice signals under different scenes needs to be reduced by using different algorithms; for example, for scenes with loud music noise, such as dance halls and KTV, the corresponding noise reduction algorithm may be a wiener filtering method.
In the above technical solution, the obtaining of the stationary noise spectrum in the separated user speech may include, for example, obtaining the stationary noise spectrum within a minimum frequency threshold and a maximum frequency threshold in a predetermined time interval after delaying. For example, in order to obtain a smooth noise spectrum, it must be ensured that there is no random noise with a frequency greater than the maximum frequency threshold in the previous 15 ms. In this way, interference of the random noise spectrum can be eliminated.
The beneficial effects of the above technical scheme are: through the processing of making an uproar of falling to the speech information who gathers, avoid external noise to cause the influence to it to make the speech information who obtains, it is more clear.
Preferably, the equal interval time is set by an interactive terminal for collecting the voice information of the user in a self-defined manner according to the speed of the user.
The embodiment of the invention provides a method for guided interaction, which needs to adjust and record the playing progress of guide data corresponding to a guided sentence when the guided sentence in a guide template is played in sequence, and comprises the following steps:
dividing preset region blocks on a display screen of an interaction end for playing guide data, wherein each region block has corresponding adjustment precision;
recording the adjustment operation of a user in each area block, and determining the fast forward and fast backward time corresponding to the adjustment operation according to the adjustment precision on each area block, wherein the adjustment operation comprises an adjustment angle and an adjustment length, and the adjustment length is the distance from an adjustment starting point to an adjustment end point;
the playing progress of the guide data is jumped from the current playing time to the playing time corresponding to the fast forward and fast backward time corresponding to the adjusting operation, and the playing time after the adjusting operation is recorded.
According to the technical scheme, the plurality of area blocks are divided on the display screen, the adjusting precision corresponding to each area block is different, when the adjusting is carried out on the display screen, if the adjusting direction is not parallel to the direction of fast forward and fast backward preset by the area blocks, the adjusting length of the adjusting direction is projected to the fast forward and fast backward direction set by the area blocks, and the playing time after jumping is calculated according to the adjusting angle and the adjusting length.
The beneficial effects of the above technical scheme are: when the guide data is played, the user can conveniently learn the guide data by adjusting the playing progress on the display screen.
The embodiment of the invention provides a guiding interactive method, wherein the user characteristic information also comprises user dialogue attributes,
the user conversation attribute is obtained according to the conversation content of the virtual human of the user and the interactive end, and the obtaining of the conversation attribute comprises the following steps:
recording the conversation content of the user and the virtual person, and obtaining corresponding conversation question-answer information from the conversation content;
screening reply contents of the user from the recorded dialogue contents of the user and the virtual person according to the sequence of the dialogue time of the user and the virtual person, carrying out hierarchical attribute frequency division on the screened reply contents, and determining the attribute of the reply contents corresponding to the attribute frequency as the dialogue attribute of the user when the attribute frequency of the reply contents is greater than or equal to the preset frequency;
when a user talks with the virtual person, the virtual person obtains corresponding preset reply content according to a prestored dialogue database based on the user dialogue attribute, and updates the dialogue database at the same time;
if the virtual person cannot acquire the corresponding preset reply content, the virtual person actively interrupts the chat and outputs related prompt information to the interaction end.
In the technical scheme, the dialogue database stores dialogue scenes corresponding to user reply contents, the preset reply contents correspond to the dialogue scenes one by one, dialogue information of various users and the virtual human is recorded, and different replies which accord with the language style, the emotion style, the background knowledge and the memory of the users are made according to different dialogue information.
And performing level attribute frequency division on the reply content of the user, for example, if the reply content of the user has 10 pieces, wherein 8 pieces belong to the language straight white type content, and 2 pieces belong to the language politeness type content, determining that the preset reply content of the virtual human is to belong to the language straight white type content.
The beneficial effects of the above technical scheme are: by judging the user dialogue attribute, a more reasonable guide template can be called out to guide the user to learn.
The embodiment of the invention provides a guiding type interaction method, wherein the step of a user and a virtual human to have a conversation comprises the following steps:
the server receives reply content input by the user and generated by the interactive terminal;
determining preset reply content of the virtual human corresponding to the received reply content input by the user according to the conversation database;
the server sends the preset reply content to the interaction end for the virtual man to reply;
before a user and a virtual person have a conversation, the identity of the user needs to be verified, and the method comprises the following steps:
the method comprises the steps that a registration server of a registered user sends identity information of the user to a confirmation server, the confirmation server stores the identity information of the user into a user information database, and an identity certificate of a user login server is appointed between the user and the confirmation server;
distributing an encryption key to an interaction terminal through an encryption key storage management server, encrypting identity information A of a user after the interaction terminal obtains the encryption key, dividing an encryption key B taken out from the encryption key storage management server by a user server into four parts B1, B2, B3 and B4 according to an agreed protocol, wherein B1 is a section of byte string used for serially combining with a password original text; b2 is the key used for encryption, the length of which is determined by the length of the key used by the conventional encryption algorithm; b3 is a hashing algorithm used to be determined by the number of hashing algorithms contained in the hashing algorithm library; b4 is an encryption algorithm used depending on the number of encryption algorithms contained in the encryption algorithm library;
transmitting the final ciphertext to a confirmation server, wherein the final ciphertext is obtained by serially combining identity information A and B1 by an interaction end to obtain BB, calling a hash algorithm with a corresponding label in a hash algorithm library according to the value of B3 to calculate a hash value of BB as Bb, calling an encryption algorithm with the same label in an encryption algorithm library according to the value of B4 to encrypt Bb by using a key B2, and the encrypted ciphertext is marked as Ba, which is the encrypted final ciphertext;
the authentication confirmation server receives a final ciphertext Ba sent by the interaction terminal through the first communication module, searches a corresponding decryption algorithm from an encryption algorithm library of the confirmation server according to an encryption key B4, and decrypts the final ciphertext Ba with the combination of an encryption key B2 to obtain a first hash value Bb; the confirmation server is also used for taking the identity information A registered by the user from the user database and calculating the hash value of the identity information A by the same method as the interactive terminal, namely, after the identity information A and the B1 are combined in series, the hash value is calculated by using a hash value algorithm with the same number as the value of the B3, and a second hash value Bb' is obtained; the confirmation server compares whether the first hash value Bb and the second hash value Bb' are the same or not, and if yes, the authentication is successful; otherwise, authentication fails; the confirmation server sends the authentication result to the interactive terminal, and the authentication result comprises: authentication is successful and authentication is failed.
In the above technical solution, the interactive end includes, but is not limited to, a robot, a mobile phone, a notebook, and other interactive devices; the identity credentials include, but are not limited to, fingerprints, identification numbers, names, etc., and the way in which the identity of the user is verified may be fingerprint identification, scan identification, password identification, etc.
The technical scheme has the beneficial effects that: the use of the interaction terminal by irrelevant personnel is avoided, and the possibility that the interaction terminal is damaged is reduced.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method of guided interaction, comprising:
collecting voice information input by a user;
acquiring user characteristic information of the user;
acquiring a corresponding guide instruction according to the acquired voice information and the user characteristic information of the user, and calling out a guide template corresponding to the acquired voice information and the user characteristic information from a pre-stored guide template library according to the guide instruction;
the guide template comprises at least one guide statement;
sequentially playing the guided sentences in the guide template;
the guiding instruction is a user age instruction obtained according to the acquired voice information and the user characteristic information of the user, and a corresponding guiding template is called according to the user age instruction, and the specific process is as follows:
firstly, processing collected voice information to obtain a voice matrix of a user, wherein the voice matrix is to cut the collected voice information according to the same time interval, extracting the values of tone, audio and decibel indexes of each section of voice to form a corresponding matrix, obtaining the information matrix of the user according to the user characteristic information of the user, the information matrix of the user is to store the collected user characteristics as a picture, then extracting the values of pixel points in the picture to form a corresponding matrix, then carrying out gray processing on the values of the pixel points to obtain the information characteristics of the corresponding user, and estimating the approximate age of the user by the obtained matrix according to the following formula:
wherein
For the purpose of the estimated age of the user,
is a matrix of the speech of the user,
is the nth voice message in the voice matrix, n is the total number of voice messages,
the matrix is maximized for the voice information,
the maximum value of the nth speech information in the speech matrix in practice,
in order to integrate the matrices, the matrices are,
is the percentage of the proportion of the nth voice information in the voice matrix in the whole voice, p is the conversion factor of the voice to the age,
is used as a reference age value and is used as a reference age value,
is the conversion factor of the user information to the age, m is the total number of the user information,
in the form of a matrix of user information,
a user information matrix of users of a reference age;
the conversion factor of the voice to the age is obtained by the average age of the user and the average value of the voice matrix, and the conversion factor of the user information to the age is obtained by the average age of the user and the average value of the user information matrix;
classifying ages after the ages of the users are estimated according to a formula, determining the age instruction of the users, and calling a corresponding guide template, wherein the method comprises the following steps: dividing the estimated user age into four stages, wherein each stage has an intermediate age, and substituting the intermediate age into the following formula:
wherein
For each stepAnd finding the corresponding intermediate value according to the obtained value to determine the age stage of the user, thereby obtaining the user age instruction, and calling out the corresponding guide module to output according to the user age instruction corresponding to the age stage of the user.
2. The method of claim 1,
the playing of the guided sentences in the guide template in sequence comprises:
the guide template stores a preset sentence playing sequence of the guide type sentences;
and playing the guided sentences in the guide template according to the preset sentence playing sequence.
3. The method of claim 1, wherein said playing guided sentences in the guide template in sequence comprises:
a preset question-answer database corresponding to the guided sentences is stored in the guide template, when the user answers the guided sentences played by the guide template, answer results corresponding to the current guided sentences answered by the user are obtained, and next guided sentences corresponding to the answer results are played according to the question-answer database;
counting the number of the guided sentences answered by the user, judging whether the number of the guided sentences answered by the user is smaller than a preset number, if so, continuing to play the guided sentences answered by the user, and otherwise, ending the playing.
4. The method of claim 1, wherein before obtaining the corresponding guidance instruction according to the collected voice information and the user characteristic information of the user, determining the voice information input by the user comprises:
dividing collected voice information input by a user at equal intervals, playing the divided voice information, judging whether the played split voice information is correct or not by the user, if so, identifying the divided voice information according to a pre-stored standard voice database, judging whether a characteristic value of the divided voice information is matched with a characteristic value of corresponding standard voice information in the standard voice database or not, and if so, extracting a guide instruction in the collected voice information;
otherwise, deleting the collected voice information input by the user and collecting the voice information again.
5. The method of claim 4, wherein in the step of recognizing the divided voice information, performing noise reduction processing on the recognized voice information comprises:
carrying out frame processing on each voice message divided by equal interval time;
acquiring position information of an interaction terminal for acquiring the voice information input by the user, and calling a position map corresponding to the position information from a pre-stored position map library;
acquiring a preset area where the interaction end is located according to the position map, and acquiring a preselected scene of the preset area;
acquiring an environmental noise signal in the collected voice information input by the user;
determining a target scene from the preselected scene according to the environmental noise signal, and searching an environmental noise reduction parameter corresponding to the target scene according to a pre-stored noise reduction parameter database;
separating user voice from the collected voice information input by the user according to the environment noise reduction parameters;
acquiring a minimum frequency threshold and a maximum frequency threshold corresponding to the user in the separated user voice;
acquiring a stationary noise spectrum in the separated user voice;
and generating corresponding effective information by using the acquired minimum frequency threshold, maximum frequency threshold and stable noise spectrum based on a spectrum subtraction algorithm, and eliminating random noise of the effective information.
6. The method of claim 4,
said equal intervals being obtained by collecting speech information of said userInteractive terminalAnd self-defining the setting according to the speech speed of the user.
7. The method of claim 1, wherein when the guided sentences in the guide template are played in sequence, the playing progress of the guide material corresponding to the guided sentences needs to be adjusted and recorded, and the method comprises:
for playing said guide materialInteractive terminalThe display screen divides preset area blocks, and each area block has corresponding adjusting precision;
recording the adjustment operation of the user in each area block, and determining the fast forward and fast backward time corresponding to the adjustment operation according to the adjustment precision on each area block, wherein the adjustment operation comprises an adjustment angle and an adjustment length, and the adjustment length is the distance from an adjustment starting point to an adjustment end point;
and the playing progress of the guide data is jumped from the current playing time to the playing time corresponding to the fast forward and fast backward time corresponding to the adjusting operation, and the playing time after the adjusting operation is recorded.
8. The method of claim 1, wherein the user characteristic information further includes, a user dialog attribute,
the user dialog attribute is based on the user andinteractive terminalThe obtaining of the dialogue attribute comprises the following steps:
recording the conversation content of the user and the virtual human, and obtaining corresponding conversation question-answer information from the conversation content;
screening reply contents of the user from recorded dialogue contents of the user and the virtual person according to the sequence of the dialogue time of the user and the virtual person, carrying out hierarchical attribute frequency division on the screened reply contents, and determining the attribute of the reply contents corresponding to the attribute frequency as the dialogue attribute of the user when the attribute frequency of the reply contents is greater than or equal to a preset frequency;
when the user talks with the virtual person, the virtual person obtains corresponding preset reply content according to a prestored dialogue database based on the user dialogue attribute, and updates the dialogue database;
and if the virtual person cannot acquire the corresponding preset reply content, actively interrupting the chat by the virtual person, and outputting related prompt information to the interactive terminal.
9. The method of claim 8, wherein the step of the user conversing with the avatar comprises:
the server receives the reply content input by the user and generated by the interactive terminal;
determining preset reply content of the virtual human corresponding to the received reply content input by the user according to a conversation database;
and the server sends the preset reply content to the interactive end for the virtual man to reply.
10. The method of claim 8, wherein the step of the user conversing with the avatar comprises:
the server receives the reply content input by the user and generated by the interactive terminal;
determining preset reply content of the virtual human corresponding to the received reply content input by the user according to a conversation database;
the server sends the preset reply content to the interaction end for the virtual man to reply;
before the user has a conversation with the avatar, the identity of the user needs to be verified, which includes:
the method comprises the steps that a registration server which registers a user sends identity information of the user to a confirmation server, the confirmation server stores the identity information of the user into a user information database, and an identity certificate of a user login server is agreed between the user and the confirmation server;
distributing an encryption key to the interaction terminal through an encryption key storage management server, encrypting the identity information A of the user after the interaction terminal obtains the encryption key, dividing an encryption key B taken out from the encryption key storage management server by a user server into four parts, namely B1, B2, B3 and B4 according to an agreed protocol, wherein B1 is a section of byte string used for being serially combined with a password original text; b2 is the key used for encryption, the length of which is determined by the length of the key used by the conventional encryption algorithm; b3 is a hashing algorithm used to be determined by the number of hashing algorithms contained in the hashing algorithm library; b4 is an encryption algorithm used depending on the number of encryption algorithms contained in the encryption algorithm library;
transmitting a final ciphertext to the confirmation server, wherein the final ciphertext is obtained by serially combining identity information A and B1 by the interaction end to obtain BB, calling a hash algorithm with a corresponding label in a hash algorithm library according to a value of B3 to calculate a hash value of BB as Bb, calling an encryption algorithm with the same value label in an encryption algorithm library according to a value of B4 and encrypting Bb by using a key B2, and the encrypted ciphertext is denoted as Ba, which is the encrypted final ciphertext;
authenticating that the confirmation server receives the final ciphertext Ba sent by the interaction terminal through a first communication module, searching a corresponding decryption algorithm from an encryption algorithm library of the confirmation server according to an encryption key B4, and decrypting the final ciphertext Ba by combining an encryption key B2 to obtain a first hash value Bb; the confirmation server is also used for taking the identity information A registered by the user from the user database and calculating the hash value of the identity information A by the same method as the interactive terminal, namely, after the identity information A and the B1 are combined in series, the hash value is calculated by using a hash value algorithm with the same number as the value of B3, and a second hash value Bb' is obtained; the confirmation server compares whether the first hash value Bb is the same as the second hash value Bb', and if so, the authentication is successful; otherwise, authentication fails; the confirmation server sends an authentication result to the interactive terminal, wherein the authentication result comprises: authentication is successful and authentication is failed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910339023.8A CN110134235B (en) | 2019-04-25 | 2019-04-25 | Guiding type interaction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910339023.8A CN110134235B (en) | 2019-04-25 | 2019-04-25 | Guiding type interaction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110134235A CN110134235A (en) | 2019-08-16 |
| CN110134235B true CN110134235B (en) | 2022-04-12 |
Family
ID=67571150
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910339023.8A Active CN110134235B (en) | 2019-04-25 | 2019-04-25 | Guiding type interaction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110134235B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110610627A (en) * | 2019-09-29 | 2019-12-24 | 苏州思必驰信息科技有限公司 | Heuristic poetry learning method and device |
| CN112085422B (en) * | 2020-10-28 | 2021-06-22 | 杭州环研科技有限公司 | Environment-friendly online service system based on artificial intelligence |
| CN112967010A (en) * | 2021-02-07 | 2021-06-15 | 中国工商银行股份有限公司 | Service handling method and device based on digital human guide, electronic equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103000052A (en) * | 2011-09-16 | 2013-03-27 | 上海先先信息科技有限公司 | Man-machine interactive spoken dialogue system and realizing method thereof |
| CN104036786A (en) * | 2014-06-25 | 2014-09-10 | 青岛海信信芯科技有限公司 | Method and device for denoising voice |
| CN105138710A (en) * | 2015-10-12 | 2015-12-09 | 金耀星 | Chat agent system and method |
| CN105515780A (en) * | 2016-01-12 | 2016-04-20 | 浙江神州量子网络科技有限公司 | System and method for authenticating identity based on quantum key |
| CN106202165A (en) * | 2016-06-24 | 2016-12-07 | 北京小米移动软件有限公司 | The intellectual learning method and device of man-machine interaction |
| CN108563627A (en) * | 2018-03-02 | 2018-09-21 | 北京云知声信息技术有限公司 | Heuristic voice interactive method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140089863A (en) * | 2013-01-07 | 2014-07-16 | 삼성전자주식회사 | Display apparatus, Method for controlling display apparatus and Method for controlling display apparatus in Voice recognition system thereof |
-
2019
- 2019-04-25 CN CN201910339023.8A patent/CN110134235B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103000052A (en) * | 2011-09-16 | 2013-03-27 | 上海先先信息科技有限公司 | Man-machine interactive spoken dialogue system and realizing method thereof |
| CN104036786A (en) * | 2014-06-25 | 2014-09-10 | 青岛海信信芯科技有限公司 | Method and device for denoising voice |
| CN105138710A (en) * | 2015-10-12 | 2015-12-09 | 金耀星 | Chat agent system and method |
| CN105515780A (en) * | 2016-01-12 | 2016-04-20 | 浙江神州量子网络科技有限公司 | System and method for authenticating identity based on quantum key |
| CN106202165A (en) * | 2016-06-24 | 2016-12-07 | 北京小米移动软件有限公司 | The intellectual learning method and device of man-machine interaction |
| CN108563627A (en) * | 2018-03-02 | 2018-09-21 | 北京云知声信息技术有限公司 | Heuristic voice interactive method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110134235A (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6855527B2 (en) | Methods and devices for outputting information | |
| CN110134235B (en) | Guiding type interaction method | |
| US20190378494A1 (en) | Method and apparatus for outputting information | |
| CN109726624A (en) | Identity identifying method, terminal device and computer readable storage medium | |
| EP0146434A1 (en) | A speaker independent speech recognition process | |
| CN106649694A (en) | Method and device for identifying user's intention in voice interaction | |
| US11646026B2 (en) | Information processing system, and information processing method | |
| JP2020034895A (en) | Responding method and device | |
| MX2008015554A (en) | Media identification. | |
| Nawaz et al. | Deep latent space learning for cross-modal mapping of audio and visual signals | |
| CN109961152B (en) | Personalized interaction method and system of virtual idol, terminal equipment and storage medium | |
| CN117152308B (en) | Virtual person action expression optimization method and system | |
| CN114902217A (en) | System for authenticating digital content | |
| CN106653003A (en) | Voice recognition method and device | |
| CN110827834A (en) | Voiceprint registration method, system and computer readable storage medium | |
| CN112861784B (en) | Answering method and device | |
| CN110931020B (en) | Voice detection method and device | |
| CN113282509A (en) | Tone recognition method, device, computer equipment and medium, live broadcast room classification method and device | |
| CN108744498B (en) | Virtual game quick starting method based on double VR equipment | |
| CN111785280A (en) | Identity authentication method and device, storage medium and electronic equipment | |
| JP6589040B1 (en) | Speech analysis apparatus, speech analysis method, speech analysis program, and speech analysis system | |
| CN112820265A (en) | Speech synthesis model training method and related device | |
| CN111933117A (en) | Voice verification method and device, storage medium and electronic device | |
| CN111276113A (en) | Method and device for generating key time data based on audio | |
| CN111078992A (en) | Dictation content generation method 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 | ||
| CB02 | Change of applicant information |
Address after: 510000 unit on the fourth floor, 1st, 2nd, 3rd floor, west side, 1383-5, Guangzhou Avenue South, Haizhu District, Guangzhou City, Guangdong Province (office only) Applicant after: GUANGZHOU ZIB ARTIFICIAL INTELLIGENCE TECHNOLOGY CO.,LTD. Address before: Room a, unit 1902, 374-2, Beijing Road, Yuexiu District, Guangzhou, Guangdong 510000 Applicant before: GUANGZHOU ZIB ARTIFICIAL INTELLIGENCE TECHNOLOGY CO.,LTD. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |