CN109063182B - Content recommendation method based on voice search questions and electronic equipment - Google Patents
Content recommendation method based on voice search questions and electronic equipment Download PDFInfo
- Publication number
- CN109063182B CN109063182B CN201810967578.2A CN201810967578A CN109063182B CN 109063182 B CN109063182 B CN 109063182B CN 201810967578 A CN201810967578 A CN 201810967578A CN 109063182 B CN109063182 B CN 109063182B
- Authority
- CN
- China
- Prior art keywords
- target
- question
- voice
- subject
- word
- 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
Images
Abstract
A content recommendation method and electronic equipment based on voice search questions are disclosed, wherein the method comprises the following steps: extracting a target problem from input search question voice; judging whether answer information matched with the target question is searched; if the answer information matched with the target question is not searched, determining a target subject to which the target question belongs according to keywords identified from the target question; determining target content with the highest matching degree with the target question from all teaching content corresponding to the target subject; and outputting the target content. By implementing the embodiment of the invention, the learning interest of the user can be attracted by using the teaching content which is most matched with the target question when the voice question searching fails, so that the learning efficiency is improved.
Description
Technical Field
The invention relates to the technical field of electronic equipment, in particular to a content recommendation method based on a voice search question and electronic equipment.
Background
Research and investigation show that children of low ages are still incapable of independently reading and understanding tool books and learning materials, so that the children are used to directly ask parents when encountering problems, and the parents cannot necessarily quickly give more professional answers, so that the learning efficiency of the children of low ages is low.
The family education machine with the voice question searching function can directly identify voice questions input by a user and return corresponding answers, so that the family education machine is widely applied to teaching guidance of children of low ages. However, in practice, it is found that due to interference factors such as environmental noise or irregular pronunciation of the user, a recognition error may occur when the family education machine recognizes a voice problem, so that the voice search fails, and the user is required to input the voice problem again. However, for the young children, it is easy for them to ignore and also difficult to understand the prompt information that the family education machine outputs when the voice question is required to be input again. If the times of the failure of the search questions are more, the learning interest of the children is easy to be reduced, so that the learning efficiency is still low when the children of the low ages use the family education machine to perform learning tutoring.
Disclosure of Invention
The embodiment of the invention discloses a content recommendation method based on voice search questions and electronic equipment, which can improve the learning interest of a low-age user so as to improve the learning efficiency.
The first aspect of the embodiment of the invention discloses a content recommendation method based on a voice search question, which comprises the following steps:
extracting a target problem from input search question voice;
judging whether answer information matched with the target question is searched;
if the answer information matched with the target question is not searched, determining a target subject to which the target question belongs according to keywords identified from the target question;
determining target content with the highest matching degree with the target question from all teaching content corresponding to the target subject;
and outputting the target content.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, after determining that the answer information matching the target question is not searched, and before determining the target subject to which the target question belongs according to the keyword identified from the target question, the method further includes:
outputting voice prompt information, wherein the voice prompt information is used for prompting a user to input a problem again through voice;
judging whether a voice message input by a user is detected within a specified time length after the voice prompt message is output;
if the voice message is acquired within the specified duration, taking the voice message as a new question searching voice, and executing the target question contained in the extracted and input question searching voice;
and if the voice message is not acquired within the specified duration, executing the target subject to which the target problem belongs according to the keywords identified from the target problem.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the determining whether answer information matching the target question is searched includes:
determining the association degree between the target question and each answer information in a preset answer set;
selecting answer information with the highest relevance degree with the target question from the answer set as candidate answers;
and judging whether the association degree of the candidate answer and the target question exceeds a specified threshold value, if not, judging that answer information matched with the target question is not searched.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the determining, from all teaching contents corresponding to the target subject, a target content with a highest matching degree with the target question includes:
judging whether the subject type of the target subject is a language type, and if not, identifying the identity of the user inputting the search question voice;
calling a user wrong question set of the target subject corresponding to the identity, wherein the user wrong question set at least comprises a wrong question, a user answer corresponding to the wrong question and a standard answer corresponding to the wrong question;
identifying a target wrong question with the highest matching degree with the target question in all wrong questions contained in the user wrong question set;
and determining the target wrong questions, the user answers corresponding to the target wrong questions and the standard answers corresponding to the target wrong questions as the target contents with the highest matching degree with the target questions in all the teaching contents corresponding to the target subject.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, if the subject type of the target subject is a language class, the method further includes:
judging whether the target question is used for inquiring word attributes of target words or not according to keywords identified from the target question, wherein the target words are words to be inquired and are cut from the target question, and the word attributes at least comprise the sound, shape and meaning of the words;
if the target question is used for inquiring the word attribute of the target word, inquiring the associated word with the highest matching degree with the target word in all words contained in the dictionary of the target subject;
determining the associated words and the word attributes of the associated words as target contents with the highest matching degree with the target question in all teaching contents corresponding to the target subject;
and if the target question is not used for inquiring the word attribute of the target word, executing the identification of the user who inputs the search question voice.
A second aspect of an embodiment of the present invention discloses an electronic device, including:
an extraction unit for extracting a target question from an input question-searching voice;
the first judgment unit is used for judging whether answer information matched with the target question is searched;
a first determining unit, configured to determine, when the first determining unit determines that the answer information matching the target question is not searched, a target subject to which the target question belongs according to a keyword identified from the target question;
the second determining unit is used for determining target content with the highest matching degree with the target question from all teaching content corresponding to the target subject;
an output unit for outputting the target content.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the electronic device further includes:
the prompting unit is used for outputting voice prompting information after the first judging unit judges that the answer information matched with the target question is not searched, and the voice prompting information is used for prompting a user to input the question again through voice;
the second judgment unit is used for judging whether the voice message input by the user is detected within the specified time length after the voice prompt information is output by the prompt unit;
the extracting unit is further configured to, when the second determining unit determines that the voice message is acquired within the specified duration, take the voice message as a new search question voice, and perform an operation of extracting a target question included in the input search question voice;
the first determining unit is specifically configured to determine, when the first determining unit determines that the answer information matched with the target question is not searched for and the second determining unit determines that the voice message is not acquired within the specified duration, a target subject to which the target question belongs according to a keyword identified from the target question.
As an optional implementation manner, in a second aspect of the embodiment of the present invention, the first determining unit includes:
the first determining subunit is used for determining the association degree between the target question and each answer information in a preset answer set;
the selecting subunit is used for selecting the candidate answer with the highest relevance degree with the target question from the answer set;
a threshold judgment subunit, configured to judge whether a degree of association between the candidate answer and the target question exceeds a specified threshold;
and the second determining subunit is configured to determine that answer information matching the target question does not exist when the threshold determining subunit determines that the degree of association between the candidate answer and the target question does not exceed the specified threshold.
As an optional implementation manner, in a second aspect of the embodiment of the present invention, the second determining unit includes:
a subject judging subunit, configured to judge whether a subject type of the target subject is a language class;
the first identification subunit is used for identifying the identity of the user who inputs the search question voice when the subject judgment subunit judges that the subject type of the target subject is not a language class;
the calling subunit is used for calling a user wrong question set of the target subject corresponding to the identity, wherein the user wrong question set at least comprises a wrong question, a user answer corresponding to the wrong question and a standard answer corresponding to the wrong question;
the second identification subunit is configured to identify a target error question with the highest matching degree with the target problem in all the error questions included in the user error question set;
and the third determining subunit is used for determining the target wrong question, the user answer corresponding to the target wrong question and the standard answer corresponding to the target wrong question as the target content with the highest matching degree with the target question in all the teaching contents corresponding to the target subject.
As an optional implementation manner, in a second aspect of the embodiment of the present invention, the second determining unit further includes:
a topic judging subunit, configured to, when the subject judging subunit judges that the subject type of the target subject is a language class, judge, according to a keyword identified from the target question, whether the target question is used to query word attributes of a target word, where the target word is a word to be queried and is cut from the target question, and the word attributes at least include a sound, a shape, and a meaning of the word;
a query subunit, configured to query, when the question determining subunit determines that the target question is used to query the word attribute of the target word, a related word with the highest matching degree with the target word among all words contained in the dictionary of the target subject;
the third determining subunit is further configured to determine the associated word and the word attribute of the associated word as a target content with a highest matching degree with the target question in all the teaching contents corresponding to the target subject;
and the first identifying subunit is further configured to, when the subject judging subunit judges that the subject type of the target subject is a language class and the question judging subunit judges that the target question is not used for querying the word attribute of the target word, perform the operation of identifying the identity of the user who inputs the search question speech.
A third aspect of an embodiment of the present invention discloses an electronic device, including:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to execute any one of the methods disclosed in the first aspect of the embodiments of the present invention.
A fourth aspect of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute any one of the methods disclosed in the first aspect of the embodiments of the present invention.
A fifth aspect of the embodiments of the present invention discloses a computer program product, which, when running on a computer, causes the computer to execute any one of the methods disclosed in the first aspect of the embodiments of the present invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
extracting a target question from input search question voice, and if answer information matched with the target question is judged not to be searched, determining a target subject to which the target question belongs according to keywords identified from the target question; and then, determining the target content with the highest matching degree with the target question from all the teaching contents corresponding to the target subject, and outputting the target content. Therefore, in the embodiment of the invention, the electronic equipment can return the teaching content which is most matched with the target problem input by the user when the voice question searching fails, so that the most matched teaching content can be used for attracting the learning interest of the young user when the voice question searching fails, and the learning efficiency is further improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a content recommendation method based on a voice search question according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating another content recommendation method based on a speech search question according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating another content recommendation method based on a speech search question according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure;
FIG. 5 is a schematic structural diagram of another electronic device disclosed in the embodiments of the present invention;
FIG. 6 is a schematic structural diagram of another electronic device disclosed in the embodiments of the present invention;
fig. 7 is a schematic structural diagram of another electronic device disclosed in the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses a content recommendation method based on voice search questions and electronic equipment, which can improve the learning interest of a low-age user so as to improve the learning efficiency. The following are detailed below.
Example one
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a content recommendation method based on a voice search topic according to an embodiment of the present invention. The content recommendation method based on the voice search question depicted in fig. 1 is applicable to electronic devices such as mobile phones, tablet computers, and teaching machines, which have a voice interaction function and can perform the voice search question, and the embodiment of the present invention is not limited thereto. The operating system of the electronic device may include, but is not limited to, an Android operating system, an IOS operating system, a Symbian operating system, a blackberry operating system, a Windows Phone8 operating system, and the like. The following describes the content recommendation method based on the voice search question by taking a family education machine as an example, and should not be construed as limiting the method. As shown in fig. 1, the content recommendation method based on a voice search question may include the following steps:
101. the family education machine extracts a target question from the input question-searching voice.
In the embodiment of the invention, the family education machine can receive the voice question searching starting instruction input by the user, and the user can input the voice question searching starting instruction in the modes of voice input or clicking keys displayed on a screen and the like; the audio collected after the voice question searching starting instruction is received can be used as the question searching voice input by the user by the family education machine, and the question searching voice is subjected to voice recognition, so that the target problem is extracted from the question searching voice.
102. The family education machine judges whether answer information matched with the target question is searched, if yes, step 103 is executed, and if not, step 104 is executed.
In the embodiment of the invention, an answer set comprising a large number of questions and corresponding answers can be established in advance, and after the home education machine identifies the target question from the question searching voice, the similarity between the target question and each question in the answer set can be calculated; assuming that the similarity between a certain question and the target question is higher than a specified threshold, the answer information corresponding to the question may be considered as answer information matching the target question. As another optional implementation, the family education machine may also directly calculate the association degree between the target question and each piece of answer information, that is, for a certain piece of answer information, calculate the probability that the answer information is the answer to the target question. If the association degree of the answer information with the target question is higher than a specified threshold, the answer information may be regarded as answer information matching the target question.
However, due to various interference factors and the influence of the accuracy of the speech recognition algorithm, the target problem recognized by the family education machine from the search question speech may not coincide with the problem that the user actually wants to search. For example, the question to be searched, which is input by the user through the search question voice, is "i want to see videos on rational numbers", and the target question recognized by the home teaching machine from the search question voice is "i want to see videos on free numbers", so that it is difficult for the home teaching machine to search for a question having a similarity higher than a specified threshold with the target question from the answer set, and also to search for answer information matching the target question.
103. The family education machine outputs the answer information matched with the target question.
104. And the family education machine determines the target subject to which the target question belongs according to the keywords identified in the target question.
In the embodiment of the invention, the keyword library corresponding to each subject can be established in advance. For example, the mathematical keyword library may include phrases such as "equality", "rational number", "side length", etc., and the Chinese keyword library may include phrases such as "," ancient poetry "," radical ", etc.; the words recorded in the keyword library corresponding to each subject are set according to the high-frequency words commonly used by the subject. The family education machine can filter stop words which do not contribute to retrieval from the target problem, the stop words can include language words such as 'o', 'bar' and the like, then the target problem is divided into a plurality of participles, the part of speech of each participle is recognized, word groups with the part of speech being nouns are selected from the stop words, and the word groups are matched with keyword libraries corresponding to all disciplines, so that the target disciplines to which the target problem belongs are determined. By implementing the embodiment, the interference of words and phrases which do not contribute to the retrieval on the determination of the target subject can be reduced by filtering stop words, and the accuracy and the speed of identifying the target subject can be improved.
In the above embodiment, the segmentation manner for segmenting a plurality of segmented words from the target problem may include a forward maximum matching method, an inverse maximum matching method, a bidirectional maximum matching method, a language model method, and the like, and the embodiment of the present invention is not limited.
105. And the family education machine determines the target content with the highest matching degree with the target question from all the teaching contents corresponding to the target subject.
In the embodiment of the invention, each subject can be provided with a corresponding teaching database, and the database can comprise teaching data such as teaching videos, teaching texts, word books or subject libraries and the like related to the subject. As an optional implementation manner, a retrieval index may be set in advance for each teaching material, for example, the retrieval indexes of the teaching video and the teaching text may be a video title and a text title, the retrieval index of the word book is each word, and the retrieval index of the question bank is a question in the question bank. After the family education machine acquires all the teaching contents corresponding to the target subject, the matching degree between the target problem and the retrieval indexes of the various teaching materials is calculated, and the matching degree can be related to pronunciation and/or semantics. Continuing with the example that the identified target question is "i want to see videos about the wander", if the pronunciation weight is higher when calculating the matching degree, the target content determined by the family education machine may be "videos of rational numbers"; if the semantic weight is high, the target content determined by the family education machine can be 'video of freedom'.
106. The family education machine outputs the target content.
In the embodiment of the invention, the family education machine can output the target content in the modes of playing videos or displaying texts or reading teaching audios and the like on the display screen, and the specific output mode can be determined according to the type of the target content.
It can be seen that, in the content recommendation method based on the voice search question described in fig. 1, the family education machine may identify a target question from the search question voice input by the user, and after answer information matching the target question is not searched, identify a target subject of the target question according to a keyword in the target question, thereby identifying a target content that matches the target question most among teaching contents corresponding to the target subject, and output the target content, and may output a content that is most relevant to the target question queried by the user when the search question fails, so as to divert the attention of the user and improve the learning interest of the user; and when the search for the question fails, related learning content can be provided for the user, the time when the search for the question fails is not wasted, and the learning efficiency of the user when learning and tutoring are carried out by utilizing the family education machine is improved.
Example two
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating a content recommendation method based on a voice search topic according to an embodiment of the present invention. As shown in fig. 2, the content recommendation method based on the voice search question may include the following steps:
201. the family education machine extracts a target question from the input question-searching voice.
202. The family education machine judges whether answer information matched with the target question is searched, if yes, step 203 is executed, and if not, step 204 is executed.
In the embodiment of the present invention, as an optional implementation manner, the manner in which the family education machine executes step 202 may specifically be:
and the family education machine determines the association degree between the target question and each answer information in the preset answer set.
The home education machine selects answer information with the highest relevance degree with the target question from the answer set as candidate answers;
and the family education machine judges whether the association degree of the candidate answers and the target question exceeds a specified threshold, if so, judges that answer information matched with the target question is searched, and if not, judges that answer information matched with the target question is not searched.
Each answer information in the answer set corresponds to one question, so that the home education machine can represent the target question and each question in the answer set as a word vector respectively, then calculate the similarity between the word vector corresponding to the target question and the word vector corresponding to each question (for example, calculate the distance between the word vector and the word vector in the word vector space), determine the answer information corresponding to the question with the highest similarity as the answer information with the highest relevance to the target question, and take the answer information as a candidate answer; if the association degree of the candidate answer and the target question is lower than a specified threshold, the association degree of each answer information in the answer set and the target question is considered to be lower, each answer information may not be answer information matched with the target question, at this time, it is determined that answer information matched with the target question is not searched, and the accuracy rate of matching the searched answer information and the target question can be improved.
203. The family education machine outputs the answer information matched with the target question.
204. The family education machine outputs the voice prompt information and judges whether the voice message input by the user is detected within a specified time length after the voice prompt information is output, if so, step 205 is executed, and if not, step 206 is executed.
In this embodiment of the present invention, after the family education machine performs step 202 to determine that answer information matching the target question is not searched, step 204 is performed to determine whether the user inputs the question searching voice again within a specified time duration, where the specified time duration may be set to any time duration such as 30 seconds, 1 minute, and the like, which is not limited in the embodiment of the present invention. If the user inputs the search question voice again within the specified duration, the family education machine executes step 201 to continue to identify the target question contained in the search question voice, if the user does not input the search question voice again within the specified duration, the user can be considered to ignore the voice prompt information, and therefore, steps 206 to 208 are executed to provide the user with the target content most relevant to the target question. Alternatively, the phonetic prompt message may be a fixed phonetic sentence pattern, such as "please re-enter the phonetic question". Or, the voice prompt information can also be generated according to a preset voice template, the voice template can be 'please re-input', and the family education machine splices the prompt voice corresponding to 'please re-input' and the search question voice to generate the voice prompt information.
205. The family education machine takes the voice message as a new search question voice and proceeds to step 201.
206. And the family education machine determines the target subject to which the target question belongs according to the keywords identified in the target question.
207. And the family education machine determines the target content with the highest matching degree with the target question from all the teaching contents corresponding to the target subject.
208. The family education machine outputs the target content.
It can be seen that in the method described in fig. 2, the family education machine can output answer information when answer information corresponding to a target question is searched according to the search question voice; and when the corresponding answer information is not searched, identifying the target subject to which the target question belongs, searching out the target content most relevant to the target question in the target subject, and outputting the target content to the user, so that the learning interest of the user can be improved, and the learning efficiency can be improved. Further, in the method described in fig. 2, when the corresponding answer information is not searched, the family education machine may further output voice prompt information to prompt the user to input the search question voice again. Further, in the method described in fig. 2, the family education machine determines whether answer information matched with the target question is searched by determining whether the association degree of the candidate answer exceeds a specified threshold, so that the accuracy of matching the searched answer information with the target question can be improved.
EXAMPLE III
Referring to fig. 3, fig. 3 is a schematic flowchart illustrating a content recommendation method based on a voice search topic according to an embodiment of the present invention. As shown in fig. 3, the content recommendation method based on the voice search question may include the following steps:
301. the family education machine extracts a target question from the input question-searching voice.
302. The family education machine judges whether answer information matched with the target question is searched, if yes, step 303 is executed, and if not, step 304 is executed.
303. The family education machine outputs the answer information matched with the target question.
304. The family education machine outputs the voice prompt information and judges whether the voice message input by the user is detected within a specified time after the voice prompt information is output, if so, step 305 is executed, and if not, step 306 is executed.
305. The family education machine takes the voice message as a new search question voice and proceeds to step 301.
306. And the family education machine determines the target subject to which the target question belongs according to the keywords identified in the target question.
307. The family education machine determines whether the subject type of the target subject is a language class, if so, performs step 308, and if not, performs step 310.
In the embodiment of the present invention, the language disciplines include, but are not limited to, disciplines such as chinese, english, japanese, and the like.
308. The home education machine judges whether the target question is used for inquiring the word property of the target word or not according to the keywords recognized from the target question, if so, step 309 is executed, and if not, step 310 is executed.
In the embodiment of the invention, the target words are words to be inquired which are cut from the target question, and the word attributes of a certain word at least comprise the sound, shape and meaning of the word. As an optional implementation manner, the family education machine may search whether the target question includes keywords related to the word attributes, such as "radical", "pronunciation", "meaning", "how to read", and other words or phrases related to the query word attributes, and if the keywords related to the word attributes are searched, the target question may be considered to be used for querying the word attributes of the target word; and, after the target question is divided into a plurality of participles, the part of speech of each participle is recognized, so as to judge whether the word structure of the word before the word is determined as the target word according to the part of speech of each participle, if so, the word before the word is determined as the target word, if the word structure of the word cannot exist, the sentence pattern structure of the target question is recognized according to the part of speech of each participle, and the subject in the sentence pattern structure is determined as the target word. For example, suppose that a question to be searched in the search question voice input by the user is "what the radical is worn", a target question recognized by the home teaching machine from the search question voice is "what the radical of dye is", the target question is divided into several parts, and "dye/radical/what" is obtained, and the home teaching machine cannot search answer information matching the target question; according to the keyword 'radical' recognized from the target question, the target subject to which the target question belongs can be judged to be the language subject, and the target question is used for inquiring the word attribute of the target word; from the word segmentation result of the target question and the part of speech of each segmented word, it can be derived that the word structure of "is present in the target question, and therefore" dye "is determined as the target word.
309. The family education machine inquires the related word with the highest matching degree with the target word among all the words contained in the dictionary of the target subject, determines the related word and the word attribute of the related word as the target content with the highest matching degree with the target question among all the teaching contents corresponding to the target subject, and executes step 313.
In the embodiment of the invention, the family education machine searches the target content from the dictionary of the target subject. When the recognized target question is "what the radical of the dye" is, the family education machine determines the target subject to which the target question belongs as a Chinese language according to the key sub "radical", so when the target word is "dye", if pronunciation is considered in calculating the matching degree, the searched related words can be "band", "stay", "wear", and other Chinese words with similar pronunciation to "dye".
By implementing the steps 308 to 309, when the target subject to which the target question belongs is a language class, the family education machine queries the target content from the word book, and can consolidate the basic knowledge of language learning for the user when the question searching fails.
310. The family education machine identifies the identity of the user who inputs the search question voice and calls a user wrong question set of the target subject corresponding to the identity.
In the embodiment of the invention, the user wrong question set at least comprises a wrong question, a user answer corresponding to the wrong question and a standard answer corresponding to the wrong question. The family education machine can extract sound characteristics from the search question voice and match the sound characteristics with the pre-stored standard user sound characteristics, so that the identity of the user is determined, namely the family education machine identifies the identity of the user through the search question voice. In addition, the family education machine can maintain different user wrong question sets according to the condition that different users carry out exercise training on the family education machine, and each subject of each user can correspond to one user wrong question set.
311. And the family education machine identifies the target wrong question with the highest matching degree with the target question in all wrong questions contained in the user wrong question set.
312. The home education machine determines the target wrong question, the user answer corresponding to the target wrong question, and the standard answer corresponding to the target wrong question as the target content having the highest matching degree with the target question among all the teaching contents corresponding to the target subject, and performs step 313.
In the embodiment of the invention, the family education machine calculates the matching degree of the target question and each wrong question in the wrong questions, determines the most matched target wrong question from the matching degrees, and confirms the target wrong question, the user answer corresponding to the target wrong question and the standard answer corresponding to the target wrong question as the target content, so that a user can review the wrong questions belonging to the same subject as the target question when the problem search fails, and the knowledge learning effect is consolidated.
313. The family education machine outputs the target content.
It can be seen that in the method described in fig. 3, the family education machine can identify a target question in the search question voice, and output answer information matching the target question when the answer information is searched; when answer information matched with the target question is not searched, identifying a target subject to which the target question belongs, and inquiring target content from the word book when the target subject is in a language class; when the target subject is not a language class, the target content is inquired from the wrong question set, so that the basic knowledge of language learning can be consolidated for the user through the word book or the knowledge learning effect can be consolidated for the user through the wrong question set when the problem searching fails.
Example four
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. As shown in fig. 4, the electronic device may include:
an extracting unit 401 is configured to extract a target question from an input question-searching speech.
In the embodiment of the present invention, the extracting unit 401 may use the audio collected after receiving the voice question searching start instruction as the question searching voice input by the user; the user may input the voice question searching start instruction by means of voice input or by clicking a key displayed on a screen, and the like, which is not limited in the embodiment of the present invention.
A first judging unit 402, configured to judge whether answer information matching the target question extracted by the extracting unit 401 is searched.
In an embodiment of the present invention, the first determining unit 402 may calculate similarity between the target question and each question in a preset answer set, where the answer set includes a plurality of questions and corresponding answers. Assuming that the similarity between a certain question and the target question is higher than a specified threshold, the first determining unit 402 may consider the answer information corresponding to the question as the answer information matching the target question. Alternatively, the first determining unit 402 may also directly calculate a degree of association between the target question and each piece of answer information, and if the degree of association between the answer information and the target question is higher than a specified threshold, the answer information may be regarded as answer information matching the target question.
A first determining unit 403, configured to determine a target subject to which the target question belongs according to the keyword identified from the target question when the first judging unit 402 judges that answer information matching the target question is not searched.
In this embodiment of the present invention, the first determining unit 403 may filter stop words that do not contribute to the search from the target problem, then divide the target problem into a plurality of segments, identify a part of speech of each segment, select phrases whose part of speech is a noun from the segments, and match the phrases with the keyword libraries corresponding to the respective disciplines, thereby determining the target disciplines to which the target problem belongs.
The segmentation method for segmenting a plurality of segmented words from the target problem may include a forward maximum matching method, an inverse maximum matching method, a bidirectional maximum matching method, a language model method, and the like, and the embodiment of the present invention is not limited.
A second determining unit 404, configured to determine, from all teaching contents corresponding to the target subject determined by the first determining unit 403, a target content with the highest matching degree with the target question.
In the embodiment of the invention, each subject can be provided with a corresponding teaching database, and the database can comprise teaching data such as teaching videos, teaching texts, word books or subject libraries and the like related to the subject. The second determining unit 404 may calculate a matching degree between the target question and the search index of the above-mentioned various teaching materials, and the matching degree may be related to pronunciation and/or semantic meaning. In some possible embodiments, the retrieval indexes of the teaching videos and the teaching texts can be video titles and text titles, the retrieval indexes of the word books are words, and the retrieval indexes of the question bank are questions in the question bank.
An output unit 405, configured to output the target content determined by the second determining unit 404.
It can be seen that, with the electronic device shown in fig. 4, the target question may be identified from the search question speech input by the user, and after answer information matching with the target question is not searched, the target subject of the target question may be identified according to the keyword in the target question, so as to identify the target content that matches the target question most in the teaching content corresponding to the target subject, and output the target content, and when the search question fails, the content that is most relevant to the target question queried by the user may be output, so as to divert the attention of the user and improve the learning interest of the user. And when the search for the question fails, related learning content can be provided for the user, the time when the search for the question fails is not wasted, and the learning efficiency of the user when learning and tutoring are carried out by utilizing the family education machine is improved.
EXAMPLE five
Referring to fig. 5, fig. 5 is a schematic structural diagram of another electronic device according to an embodiment of the disclosure. The electronic device shown in fig. 5 is optimized from the electronic device shown in fig. 4. Compared to the electronic device shown in fig. 4, the electronic device shown in fig. 5 may further include:
a prompting unit 406, configured to output voice prompt information used for prompting the user to input the question again by voice after the first judging unit 402 judges that the answer information matching the target question is not searched. The voice prompt message may be a fixed voice sentence pattern, or may be generated according to a preset voice template.
A second judging unit 407, configured to judge whether the voice message input by the user is detected within a specified time period after the voice prompt information is output by the prompting unit 406.
The extracting unit 401 is further configured to, when the second determining unit 407 determines that the voice message is acquired within the specified duration, take the voice message as a new search question voice, and perform an operation of extracting a target question included in the input search question voice;
the first determining unit 403 is specifically configured to determine the target subject to which the target question belongs according to the keyword identified from the target question when the first determining unit 402 determines that answer information matching the target question is not searched, and the second determining unit 407 determines that the voice message is not acquired within the specified duration.
Optionally, in the electronic device shown in fig. 5, the first determining unit 402 may specifically include:
the first determining subunit 4021 is configured to determine a degree of association between the target question extracted by the extracting unit 401 and each piece of answer information in a preset answer set.
In this embodiment of the present invention, the first determining subunit 4021 may respectively represent the target question and each question in the answer set as a word vector, and then calculate a similarity between the word vector corresponding to the target question and the word vector corresponding to each question, where the similarity is a correlation between the target question and each answer information corresponding to each question.
The selecting subunit 4022 is configured to select, according to the association degree between the target question and each piece of answer information determined by the first determining subunit 4021, a candidate answer with the highest association degree with the target question from the answer set.
The threshold determining subunit 4023 is configured to determine whether the association degree between the candidate answer selected by the selecting subunit 4022 and the target question exceeds a specified threshold.
The second determining subunit 4024 is configured to determine that answer information matching the target question does not exist when the threshold determining subunit 4023 determines that the degree of association between the candidate answer and the target question does not exceed a specified threshold. Optionally, the second determining subunit 4024 is further configured to determine that answer information matching the target question exists when the threshold determining subunit 4023 determines that the association degree between the candidate answer and the target question exceeds a specified threshold.
Therefore, the electronic equipment shown in fig. 5 can improve the learning interest of the user and improve the learning efficiency. Further, when the electronic device shown in fig. 5 is implemented, if the corresponding answer information is not searched, the voice prompt information may be output to prompt the user to input the search question voice again. When the voice message input by the user is still not received within a long enough time (specified time length) after the voice prompt information is output, the step of inquiring the target content most relevant to the target question from the target subject is executed, so that the probability of success of the question searching can be improved by inquiring the user for many times. Further, in the method described in fig. 2, the family education machine determines whether answer information matched with the target question is searched by determining whether the association degree of the candidate answer exceeds a specified threshold, so that the accuracy of matching the searched answer information with the target question can be improved.
EXAMPLE six
Referring to fig. 6, fig. 6 is a schematic structural diagram of another electronic device according to an embodiment of the disclosure. The electronic device shown in fig. 6 is optimized from the electronic device shown in fig. 5. Compared with the electronic device shown in fig. 5, in the electronic device shown in fig. 6, the second determining unit 404 may specifically include:
a subject determination sub-unit 4041 configured to determine whether the subject type of the target subject determined by the first determination unit 403 is a language class;
a first identifying subunit 4042, configured to identify an identity of the user who inputs the search question voice when the subject determining subunit 4041 determines that the subject type of the target subject is not a language class;
the retrieving subunit 4043 is configured to retrieve a user wrong question set of the target subject corresponding to the identity identifier identified by the first identifying subunit 4042, where the user wrong question set at least includes a wrong question, a user answer corresponding to the wrong question, and a standard answer corresponding to the wrong question;
a second identifying subunit 4044, configured to identify a target error question with the highest matching degree with the target problem in all error questions included in the user error question set retrieved by the retrieving subunit 4043;
a third determining subunit 4045, configured to determine the target error question identified by the second identifying subunit 4044, the user answer corresponding to the target error question, and the standard answer corresponding to the target error question as the target content with the highest matching degree with the target question in all the teaching contents corresponding to the target subject.
Optionally, in the electronic device shown in fig. 6, the second determining unit 404 may further include:
a topic judgment subunit 4046, configured to, when the subject judgment subunit 4041 judges that the subject type of the target subject is a language class, judge whether the target question is used to query word attributes of the target word according to the keywords identified from the target question; the target words are words to be inquired cut from the target question, and the word attributes at least comprise the sound, shape and meaning of the words.
In this embodiment of the present invention, the topic determination subunit 4046 may search whether the target question includes a keyword related to a word attribute, and if so, may consider that the target question is used to query the word attribute of the target word. Further, the topic determination subunit 4046 may be configured to, after the target question is divided into a plurality of segments, identify the part of speech of each segment, determine whether or not the "word structure" exists in the target question based on the part of speech of each segment, determine, if so, the word preceding the "word as the target word, and if not, identify the sentence pattern structure of the target question based on the part of speech of each segment, and determine the subject in the sentence pattern structure as the target word. When the topic judgment sub-unit 4046 judges that the target question is for inquiring the word property of the target word, the identified target word is sent to the inquiry sub-unit 4047 described below.
A query subunit 4047, configured to query, when the topic determination subunit 4046 determines that the target question is used to query the word attribute of the target word, a related word with the highest matching degree with the target word in all words included in the dictionary of the target subject;
the third determining subunit 4045 is further configured to determine the related word and the word attribute of the related word that are queried by the querying subunit 4047 as the target content with the highest matching degree with the target question in all the teaching contents corresponding to the target subject.
And the first identifying sub-unit 4042 is further configured to perform an operation of identifying the identity of the user who inputs the search question speech when the subject determination sub-unit 4041 determines that the subject type of the target subject is a language class and the topic determination sub-unit 4046 determines that the target question is not used for querying the word attribute of the target word.
It can be seen that, when the electronic device shown in fig. 6 is implemented, a target question in the search question speech can be identified, and answer information matched with the target question is output when the answer information is searched; when answer information matched with the target question is not searched, identifying a target subject to which the target question belongs, and inquiring target content from the word book when the target subject is in a language class; when the target subject is not a language class, the target content is inquired from the wrong question set, so that the basic knowledge of language learning can be consolidated for the user through the word book or the knowledge learning effect can be consolidated for the user through the wrong question set when the problem searching fails.
EXAMPLE seven
Referring to fig. 7, fig. 7 is a schematic structural diagram of another electronic device according to an embodiment of the disclosure. As shown in fig. 7, the electronic device may include:
a memory 701 in which executable program code is stored;
a processor 702 coupled to the memory 701;
the processor 702 calls the executable program code stored in the memory 701 to execute the content recommendation method based on the voice search question shown in any one of fig. 1 to 3.
It should be noted that the electronic device shown in fig. 7 may further include components, which are not shown, such as a power supply, an input key, a camera, a speaker, a screen, an RF circuit, a Wi-Fi module, a bluetooth module, and a sensor, which are not described in detail in this embodiment.
The embodiment of the invention discloses a computer-readable storage medium which stores a computer program, wherein the computer program enables a computer to execute a content recommendation method based on a voice search question, which is shown in any one of figures 1-3.
An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute a content recommendation method based on a voice search question as shown in any one of fig. 1 to 3.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Those skilled in the art should also appreciate that the embodiments described in this specification are exemplary and alternative embodiments, and that the acts and modules illustrated are not required in order to practice the invention.
In various embodiments of the present invention, it should be understood that the sequence numbers of the above-mentioned processes do not imply an inevitable order of execution, and the execution order of the processes should be determined by their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present invention, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part or all of the steps of the above-described method of each embodiment of the present invention.
It will be understood by those skilled in the art that all or part of the steps in the methods of the embodiments described above may be implemented by instructions associated with a program, which may be stored in a computer-readable storage medium, where the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), compact disc-Read-Only Memory (CD-ROM), or other Memory, magnetic disk, magnetic tape, or magnetic tape, Or any other medium which can be used to carry or store data and which can be read by a computer.
The content recommendation method and the electronic device based on the voice search question disclosed in the embodiments of the present invention are described in detail above, and a specific example is applied in the present disclosure to explain the principle and the implementation of the present invention. Meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (8)
1. A content recommendation method based on voice search questions is characterized by comprising the following steps:
extracting a target problem from input search question voice;
judging whether answer information matched with the target question is searched;
if the answer information matched with the target question is not searched, determining a target subject to which the target question belongs according to keywords identified from the target question;
judging whether the subject type of the target subject is a language type;
if the subject type of the target subject is a language class, judging whether the target question is used for inquiring word attributes of target words according to keywords identified from the target question, wherein the target words are words to be inquired and are cut from the target question, and the word attributes at least comprise the sound, shape and meaning of the words; if the target question is used for inquiring the word attribute of the target word, inquiring the associated word with the highest matching degree with the target word in all words contained in the dictionary of the target subject; determining the associated words and the word attributes of the associated words as target contents with the highest matching degree with the target question in all teaching contents corresponding to the target subject;
if the subject type of the target subject is not a language class, identifying the identity of the user inputting the search question voice; calling a user wrong question set of the target subject corresponding to the identity, wherein the user wrong question set at least comprises a wrong question, a user answer corresponding to the wrong question and a standard answer corresponding to the wrong question; identifying a target wrong question with the highest matching degree with the target question in all wrong questions contained in the user wrong question set; determining the target wrong questions, user answers corresponding to the target wrong questions and standard answers corresponding to the target wrong questions as target contents with the highest matching degree with the target questions in all teaching contents corresponding to the target subject;
and outputting the target content.
2. The content recommendation method based on voice search questions according to claim 1, wherein after determining that the answer information matching the target question is not searched, and before determining the target subject to which the target question belongs according to the keyword identified from the target question, the method further comprises:
outputting voice prompt information, wherein the voice prompt information is used for prompting a user to input a problem again through voice;
judging whether a voice message input by a user is detected within a specified time length after the voice prompt message is output;
if the voice message is acquired within the specified duration, taking the voice message as a new question searching voice, and executing the target question contained in the extracted and input question searching voice;
and if the voice message is not acquired within the specified duration, executing the target subject to which the target problem belongs according to the keywords identified from the target problem.
3. The content recommendation method based on voice search question according to claim 1 or 2, wherein said determining whether answer information matching with the target question is searched comprises:
determining the association degree between the target question and each answer information in a preset answer set;
selecting answer information with the highest relevance degree with the target question from the answer set as candidate answers;
and judging whether the association degree of the candidate answer and the target question exceeds a specified threshold value, if not, judging that answer information matched with the target question is not searched.
4. The method for recommending content based on voice search questions according to claim 1, further comprising:
and if the subject type of the target subject is a language class and the target question is not used for inquiring the word attribute of the target word, performing the identification for identifying the user who inputs the search question voice.
5. An electronic device, comprising:
an extraction unit for extracting a target question from an input question-searching voice;
the first judgment unit is used for judging whether answer information matched with the target question is searched;
a first determining unit, configured to determine, when the first determining unit determines that the answer information matching the target question is not searched, a target subject to which the target question belongs according to a keyword identified from the target question;
the second determining unit is used for determining target content with the highest matching degree with the target question from all teaching content corresponding to the target subject;
an output unit for outputting the target content;
wherein the second determination unit includes:
a subject judging subunit, configured to judge whether a subject type of the target subject is a language class;
a topic judging subunit, configured to, when the subject judging subunit judges that the subject type of the target subject is a language class, judge, according to a keyword identified from the target question, whether the target question is used to query word attributes of a target word, where the target word is a word to be queried and is cut from the target question, and the word attributes at least include a sound, a shape, and a meaning of the word;
a query subunit, configured to query, when the question determining subunit determines that the target question is used to query the word attribute of the target word, a related word with the highest matching degree with the target word among all words contained in the dictionary of the target subject;
a third determining subunit, configured to determine the associated word and the word attribute of the associated word as a target content with a highest matching degree with the target question in all the teaching contents corresponding to the target subject;
the first identification subunit is used for identifying the identity of the user who inputs the search question voice when the subject judgment subunit judges that the subject type of the target subject is not a language class;
the calling subunit is used for calling a user wrong question set of the target subject corresponding to the identity, wherein the user wrong question set at least comprises a wrong question, a user answer corresponding to the wrong question and a standard answer corresponding to the wrong question;
the second identification subunit is configured to identify a target error question with the highest matching degree with the target problem in all the error questions included in the user error question set;
the third determining subunit is further configured to determine the target wrong question, the user answer corresponding to the target wrong question, and the standard answer corresponding to the target wrong question as the target content with the highest matching degree with the target question in all the teaching contents corresponding to the target subject.
6. The electronic device of claim 5, further comprising:
the prompting unit is used for outputting voice prompting information after the first judging unit judges that the answer information matched with the target question is not searched, and the voice prompting information is used for prompting a user to input the question again through voice;
the second judgment unit is used for judging whether the voice message input by the user is detected within the specified time length after the voice prompt information is output by the prompt unit;
the extracting unit is further configured to, when the second determining unit determines that the voice message is acquired within the specified duration, take the voice message as a new search question voice, and perform an operation of extracting a target question included in the input search question voice;
the first determining unit is specifically configured to determine, when the first determining unit determines that the answer information matched with the target question is not searched for and the second determining unit determines that the voice message is not acquired within the specified duration, a target subject to which the target question belongs according to a keyword identified from the target question.
7. The electronic device according to claim 5 or 6, wherein the first determination unit includes:
the first determining subunit is used for determining the association degree between the target question and each answer information in a preset answer set;
the selecting subunit is used for selecting the candidate answer with the highest relevance degree with the target question from the answer set;
a threshold judgment subunit, configured to judge whether a degree of association between the candidate answer and the target question exceeds a specified threshold;
and the second determining subunit is configured to determine that answer information matching the target question does not exist when the threshold determining subunit determines that the degree of association between the candidate answer and the target question does not exceed the specified threshold.
8. The electronic device according to claim 5, wherein the first identifying subunit is further configured to perform the operation of identifying the identity of the user who inputs the search question speech when the discipline judging subunit judges that the discipline type of the target discipline is a language class and the topic judging subunit judges that the target question is not used for querying the word property of the target word.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810967578.2A CN109063182B (en) | 2018-08-23 | 2018-08-23 | Content recommendation method based on voice search questions and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810967578.2A CN109063182B (en) | 2018-08-23 | 2018-08-23 | Content recommendation method based on voice search questions and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109063182A CN109063182A (en) | 2018-12-21 |
| CN109063182B true CN109063182B (en) | 2020-11-06 |
Family
ID=64756678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810967578.2A Active CN109063182B (en) | 2018-08-23 | 2018-08-23 | Content recommendation method based on voice search questions and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063182B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027536B (en) * | 2019-02-18 | 2023-12-22 | 广东小天才科技有限公司 | Question searching method based on electronic equipment and electronic equipment |
| CN110766326A (en) * | 2019-10-24 | 2020-02-07 | 深圳小蛙出海科技有限公司 | Test question pushing and evaluating training method, computer device, system and printing terminal |
| CN111522981A (en) * | 2020-04-16 | 2020-08-11 | 广东小天才科技有限公司 | Method and device for assisting user in information retrieval |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914567A (en) * | 2014-04-23 | 2014-07-09 | 北京奇虎科技有限公司 | Objective test question answer matching method and objective test question answer matching device |
| CN106021615A (en) * | 2016-07-01 | 2016-10-12 | 广东小天才科技有限公司 | Method and device for optimizing title search |
| CN106571144A (en) * | 2016-11-08 | 2017-04-19 | 广东小天才科技有限公司 | Searching method based on voice recognition and apparatus thereof |
| CN107832396A (en) * | 2017-10-30 | 2018-03-23 | 江西博瑞彤芸科技有限公司 | Information retrieval method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100723404B1 (en) * | 2005-03-29 | 2007-05-30 | 삼성전자주식회사 | Apparatus and method for processing speech |
| CN105096677A (en) * | 2015-08-19 | 2015-11-25 | 北京京东方多媒体科技有限公司 | Teaching system and work method thereof |
-
2018
- 2018-08-23 CN CN201810967578.2A patent/CN109063182B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914567A (en) * | 2014-04-23 | 2014-07-09 | 北京奇虎科技有限公司 | Objective test question answer matching method and objective test question answer matching device |
| CN106021615A (en) * | 2016-07-01 | 2016-10-12 | 广东小天才科技有限公司 | Method and device for optimizing title search |
| CN106571144A (en) * | 2016-11-08 | 2017-04-19 | 广东小天才科技有限公司 | Searching method based on voice recognition and apparatus thereof |
| CN107832396A (en) * | 2017-10-30 | 2018-03-23 | 江西博瑞彤芸科技有限公司 | Information retrieval method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109063182A (en) | 2018-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145153B (en) | Intention category identification method and device | |
| US11182435B2 (en) | Model generation device, text search device, model generation method, text search method, data structure, and program | |
| CN111159363A (en) | Knowledge base-based question answer determination method and device | |
| CN107608960B (en) | Method and device for linking named entities | |
| CN107305541A (en) | Speech recognition text segmentation method and device | |
| TWI554984B (en) | Electronic device | |
| CN111783518A (en) | Training sample generation method and device, electronic equipment and readable storage medium | |
| CN108920450B (en) | Knowledge point reviewing method based on electronic equipment and electronic equipment | |
| KR20160026892A (en) | Non-factoid question-and-answer system and method | |
| CN109063182B (en) | Content recommendation method based on voice search questions and electronic equipment | |
| CN109979450B (en) | Information processing method and device and electronic equipment | |
| CN109710732B (en) | Information query method, device, storage medium and electronic equipment | |
| CN109165336B (en) | Information output control method and family education equipment | |
| CN110147494B (en) | Information searching method and device, storage medium and electronic equipment | |
| CN108121455A (en) | Identify method and device for correcting | |
| CN109635125B (en) | Vocabulary atlas building method and electronic equipment | |
| KR101333485B1 (en) | Method for constructing named entities using online encyclopedia and apparatus for performing the same | |
| CN111400513A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN106021532B (en) | Keyword display method and device | |
| CN105244024B (en) | A kind of audio recognition method and device | |
| CN108345694B (en) | Document retrieval method and system based on theme database | |
| CN112487159B (en) | Search method, search device, and computer-readable storage medium | |
| CN106653006A (en) | Search method and device based on voice interaction | |
| AlMousa et al. | Nlp-enriched automatic video segmentation | |
| JP3794597B2 (en) | Topic extraction method and topic extraction program recording medium |
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 |