CN109299399A - Learning content recommendation method and terminal equipment - Google Patents
Learning content recommendation method and terminal equipment Download PDFInfo
- Publication number
- CN109299399A CN109299399A CN201811540311.1A CN201811540311A CN109299399A CN 109299399 A CN109299399 A CN 109299399A CN 201811540311 A CN201811540311 A CN 201811540311A CN 109299399 A CN109299399 A CN 109299399A
- Authority
- CN
- China
- Prior art keywords
- label
- repetition
- user
- target
- target labels
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000000605 extraction Methods 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 4
- 208000029152 Small face Diseases 0.000 claims 1
- 230000015654 memory Effects 0.000 description 21
- 238000004590 computer program Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 244000078534 Vaccinium myrtillus Species 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 235000017848 Rubus fruticosus Nutrition 0.000 description 1
- 235000003095 Vaccinium corymbosum Nutrition 0.000 description 1
- 235000017537 Vaccinium myrtillus Nutrition 0.000 description 1
- 235000021029 blackberry Nutrition 0.000 description 1
- 235000021014 blueberries Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention relates to the technical field of terminal equipment, and discloses a learning content recommendation method and terminal equipment, wherein the method comprises the following steps: receiving a search request of a user, wherein the search request carries a search problem; extracting at least one keyword from the search question; acquiring at least one label corresponding to each keyword by using a label distribution model; combining all the keywords, and counting the number of times of repetition corresponding to each label; selecting at least one label corresponding to the repetition times to obtain at least one target label; the target repetition times corresponding to the target label are all the repetition times which are arranged in front when the repetition times are sorted from large to small and are within a preset number range; recommending learning content corresponding to each target label for the user; therefore, the real search intention corresponding to the search problem can be determined according to the label, the targeted learning content is provided for the user, the search requirement of the user can be met, and the real recommendation meaning is achieved.
Description
Technical field
The present invention relates to terminal device technical fields, and in particular to a kind of recommended method and terminal device of learning Content.
Background technique
Currently, Most students can carry out problem search using study class application program (Application, APP), together
When, study class APP can also obtain the search problem of user's upload, and be recommended in other study according to the search problem to user
Hold, to help user to expand learning knowledge face.But at present study class APP when carrying out learning Content recommendation, may be to
User recommends the relevant relatively common learning Content of the search problem, will not take notice of whether recommended learning Content is user
Required content, the way of recommendation is more single, causes recommendation effect poor, does not play and really recommends meaning.
Summary of the invention
The embodiment of the invention discloses a kind of recommended method of learning Content and terminal devices, for solving existing study
The poor problem of the excessively single caused recommendation effect of commending contents mode.
First aspect present invention discloses a kind of recommended method of learning Content, it may include:
The searching request of user is received, described search request carries search problem;
At least one keyword is extracted from described search problem;
Using label distribution model, at least one corresponding label of each keyword is obtained;
In conjunction with all keywords, the corresponding number of repetition of each label is counted;
The corresponding label of at least one described number of repetition is selected, at least one target labels is obtained;Wherein, the mesh
The corresponding target number of repetition of mark label is that all numbers of repetition come front when according to sorting from large to small and are
Number of repetition within the scope of preset quantity;
Recommend the corresponding learning Content of each target labels for user.
As an alternative embodiment, in first aspect present invention, it is described to select at least one described repetition
The corresponding label of number, obtaining at least one target labels includes:
Obtain the temperature index value of hot value and corresponding subject and topic type that each label is retrieved;
Calculate the corresponding weight of the hot value, the subject weight corresponding with the temperature index value of topic type, Yi Jisuo
State the corresponding weight of number of repetition;
According to the corresponding weight of the hot value, subject weight corresponding with the temperature index value of topic type, Yi Jisuo
The corresponding weight of number of repetition is stated, the corresponding total weight of the number of repetition is calculated;
The corresponding label of at least one described total weight is selected, obtains at least one target labels, wherein the target
The total weight of the corresponding target of label is that all total weights come front when sorting from large to small according to weighted value and are
Total weight within the scope of preset quantity.
As an alternative embodiment, in first aspect present invention, it is described to select at least one described repetition
The corresponding label of number, obtains at least one target labels, comprising:
Obtain the corresponding grade's information of user and age information;
It determines to match respectively with grade's information and the age information from the corresponding label of the number of repetition
At least one target labels.
As an alternative embodiment, in first aspect present invention, the searching request for receiving user, packet
It includes:
After listening r/w cell entered for needing to enter for, output display is all described to listen r/w cell;
Detect whether to receive the input voice of user, the input voice is carried for requesting search target dictation single
The search problem of member, it is any one listened in r/w cell that the target, which listens r/w cell,;
When detecting the input voice, the searching request for receiving user is determined.
As an alternative embodiment, in first aspect present invention, it is described to recommend each target for user
After the corresponding learning Content of label, which comprises
Identify whether the age indicated by the age information is in default the range of age;
When in described default the range of age, the corresponding learning Content of each target labels is sent to parent
Terminal, so that parent's terminal assists user to learn the learning Content.
Second aspect of the present invention discloses a kind of terminal device, it may include:
Receiving unit, for receiving the searching request of user, described search request carries search problem;
Extraction unit, for extracting at least one keyword from described search problem;
Acquiring unit obtains at least one corresponding label of each keyword for utilizing label distribution model;
Statistic unit, for counting the corresponding number of repetition of each label in conjunction with all keywords;
Selecting unit obtains at least one target mark for selecting the corresponding label of at least one described number of repetition
Label;Wherein, the corresponding target number of repetition of the target labels is all numbers of repetition when according to sorting from large to small
It comes front and is the number of repetition within the scope of preset quantity;
Recommendation unit, for recommending the corresponding learning Content of each target labels for user.
As an alternative embodiment, the selecting unit is for selecting at least in second aspect of the present invention
The corresponding label of one number of repetition, obtains the mode of at least one target labels specifically:
The selecting unit, for obtaining the heat of hot value and corresponding subject and topic type that each label is retrieved
Spend index value;And calculate the corresponding weight of the hot value, the subject weight corresponding with the temperature index value of topic type,
And the corresponding weight of the number of repetition;And according to the corresponding weight of the hot value, the temperature of the subject and topic type
The corresponding weight of index value and the corresponding weight of the number of repetition calculate the corresponding total weight of the number of repetition;With
And the corresponding label of at least one described total weight is selected, obtain at least one target labels, wherein the target labels
The corresponding total weight of target is that all total weights come front when sorting from large to small according to weighted value and are default
Total weight in quantitative range.
As an alternative embodiment, the selecting unit is for selecting at least in second aspect of the present invention
The corresponding label of one number of repetition, obtains the mode of at least one target labels specifically:
The selecting unit, for obtaining the corresponding grade's information of user and age information;And from the number of repetition
It determines to distinguish at least one matched target labels with grade's information and the age information in corresponding label.
As an alternative embodiment, the receiving unit is for receiving user's in second aspect of the present invention
The mode of searching request specifically:
The receiving unit, after listening r/w cell entered for needing to enter for, output shows all dictations
Unit;And detecting whether to receive the input voice of user, the input voice is carried for requesting search target dictation
The search problem of unit, it is any one listened in r/w cell that the target, which listens r/w cell,;And it is described defeated when detecting
When entering voice, the searching request for receiving user is determined.
As an alternative embodiment, in second aspect of the present invention, the terminal device further include:
Transmission unit, for the recommendation unit be user recommend the corresponding learning Content of each target labels it
Afterwards, identify whether the age indicated by the age information is in default the range of age;And when in the default age
When in range, the corresponding learning Content of each target labels is sent to parent's terminal, so that parent's terminal is assisted
User learns the learning Content.
The third aspect of the embodiment of the present invention discloses a kind of terminal device, it may include:
It is stored with the memory of executable program code;
The processor coupled with the memory;
The processor calls the executable program code stored in the memory, executes the embodiment of the present invention the
A kind of recommended method of learning Content disclosed in one side.
Fourth aspect of the embodiment of the present invention discloses a kind of computer readable storage medium, stores computer program, wherein
The computer program makes computer execute a kind of recommended method of learning Content disclosed in first aspect of the embodiment of the present invention.
The 5th aspect of the embodiment of the present invention discloses a kind of computer program product, when the computer program product is calculating
When being run on machine, so that the computer executes some or all of any one method of first aspect step.
The aspect of the embodiment of the present invention the 6th disclose a kind of using distribution platform, and the application distribution platform is for publication calculating
Machine program product, wherein when the computer program product is run on computers, so that the computer executes first party
Some or all of any one method in face step.
Compared with prior art, the embodiment of the present invention has the advantages that
In embodiments of the present invention, the searching request that Client-initiated carries search problem is received, is then asked from search
Middle at least one keyword of extraction is sought, label distribution model is further utilized, obtains at least one corresponding mark of each keyword
Label, and all keywords are combined, the number of repetition that each label occurs in all keywords is counted, and select at least
The corresponding label of one number of repetition, to obtain at least one target labels, wherein assuming that according to sorting from large to small
When having number of repetition, the preset quantity number of repetition for coming front (i.e. number of repetition is higher) is determined, then should
The corresponding label of preset quantity number of repetition is last only to recommend the target labels are corresponding to learn to user as target labels
Content can carry out keyword extraction to search problem, then comprehensively consider the corresponding label of each keyword, true according to label
The corresponding real search intention of search problem is made, has targetedly learning Content to provide for user, can satisfy use
The search at family needs, and improves recommendation effect, really recommends meaning to play.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the flow diagram of the recommended method of learning Content disclosed in one embodiment of the invention;
Fig. 2 is the flow diagram of the recommended method of learning Content disclosed in another embodiment of the present invention;
Fig. 3 is the structural schematic diagram of terminal device disclosed in one embodiment of the invention;
Fig. 4 is the structural schematic diagram of terminal device disclosed in another embodiment of the present invention;
Fig. 5 is the structural schematic diagram of terminal device disclosed in further embodiment of this invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
It should be noted that the term " includes " of the embodiment of the present invention and " having " and their any deformation, it is intended that
Be to cover it is non-exclusive include, for example, containing the process, method, system, product or equipment of a series of steps or units not
Those of be necessarily limited to be clearly listed step or unit, but may include be not clearly listed or for these processes, side
The intrinsic other step or units of method, product or equipment.
The embodiment of the invention discloses a kind of recommended methods of learning Content, targetedly learn for providing to have for user
Content is practised, can satisfy the search needs of user, improves recommendation effect, really recommends meaning to play.The embodiment of the present invention
Also accordingly disclose a kind of terminal device.
Terminal device involved in the embodiment of the present invention can be private tutor's machine, smart phone, tablet computer etc., terminal device
Operating system may include but be not limited to Android operation system, IOS operating system, Symbian (Saipan) operating system,
Black Berry (blackberry, blueberry) operating system, Windows Phone8 operating system etc., the embodiment of the present invention is without limitation.Under
Face in conjunction with specific embodiments describes to technical solution of the present invention in detail for from the angle of terminal device.
Embodiment one
Referring to Fig. 1, Fig. 1 is the flow diagram of the recommended method of learning Content disclosed in one embodiment of the invention;Such as
Shown in Fig. 1, the recommended method of the learning Content can include:
101, terminal device receives the searching request of user, which carries search problem.
Wherein, terminal device can be built-in with study class APP, be provided with function of search in APP, user usually or
It when doing one's assignment, if encountering the problem of being ignorant of or not understanding, can be scanned for by APP, to obtain corresponding answer.
Wherein it is possible to be provided with search column in APP, user can input searching request in search column, in turn, terminal device detection
The searching request that user inputs in search column.
As an alternative embodiment, being additionally provided with button of taking pictures beside search column, and then terminal device receives
The searching request of user may include: clicking operation of the terminal device detection user to the button of taking pictures, and grasp in response to the click
Make the camera built in calling terminal device, open interface of taking pictures, is searched by the preview area in interface of taking pictures to including above-mentioned
The content of text of Suo Wenti carries out image preview, obtains preview image, when detecting the photographing instruction of user's input, to preview
Image is taken pictures, and obtains image of taking pictures, above-mentioned search problem is identified from image of taking pictures.Pass through the embodiment, user
Search problem can be inputted by shooting style, operate it is more convenient, it is especially more or the form of expression is complex in text
Search problem when, input mode of taking pictures is more convenient.
In another optional embodiment, the searching request that terminal device receives user may include: built in terminal device
There is near-field communication (Near Field Communication, NFC) module, terminal device is opened study class APP, believed by account
Breath logs on to study class APP, detects and adds the selection operation in type selecting to face-to-face plusing good friend function in good friend, in response to this
Selection operation calls built-in NFC module, is read from another terminal device for being equally built-in with NFC module using the NFC module
User name of another terminal device on same study class APP is taken, which is input to search column, passes through user's search column
To the user name, corresponding user is scanned for, when searching the corresponding user of the user name, by the corresponding use of the user name
Family is added to buddy list, finds the user from buddy list according to user's operation and opens the chat window with the user
Mouthful, the search problem that the other user sends is received from the chat window.It, can be on study class APP by the embodiment
Increase social functions, the search problem for needing to solve then is obtained from good friend.
102, terminal device extracts at least one keyword from search problem.
As an alternative embodiment, terminal device identifies the key after extracting keyword in search problem
Whether sensitive vocabulary matches word with any of sensitive list, wherein sensitive list passes through remote-control by parent's terminal
It is arranged when private tutor's equipment, includes several sensitive vocabulary in sensitive list;If any of the keyword and sensitive list are quick
Sense vocabulary matches, then sends to parent's terminal for informing that the user to be ready retrieving the sensitive vocabulary in sensitive list;If should
When the sensitive vocabulary of any of keyword and sensitive list mismatches, step 103 is executed.It, can be with by the embodiment
It prevents user from voluntarily searching for some sensitive vocabulary inconsistent with its age, influences the development of its thought, or even influence its growth.
103, terminal device utilizes label distribution model, obtains at least one corresponding label of each keyword.
It is appreciated that there are many labels for setting in embodiments of the present invention, for example, subject, topic type etc. can be arranged
Label, for example, Chinese language is correspondingly arranged a kind of label, mathematics is correspondingly arranged a kind of label, further can also be on Chinese language basis
On label is set again, if a kind of label is arranged in Chinese idiom, a kind of label is arranged in classic poetry.In order to make it easy to understand, it is considered that subject
The label being correspondingly arranged is level-one label, and the label that the topic type of section now is correspondingly arranged is second level label, for example, Chinese language
Level-one label is Y, and the corresponding second level label of classic poetry under Chinese language is Y3.Wherein, level-one label or second level label are ok
Individually it is counted as a label, that is to say, that label as mentioned in the embodiments of the present invention can be level-one label or second level
Label.
Further, three-level label can also be set on the basis of the above, for example, the Tang poetry under Chinese language classic poetry
It is correspondingly arranged a three-level label, the such poems of the Song Dynasty under Chinese language classic poetry are correspondingly arranged another three-level label, similarly, three-level label
It can also be individually counted as a label, i.e., label as mentioned in the embodiments of the present invention can also be three-level label.It can be with
Understand, in the embodiment of the present invention according to actual needs, level Four label and the above label of level Four can also be set, it is no longer superfluous herein
It states.
104, terminal device combines all keywords, counts the corresponding number of repetition of each label.
It is appreciated that a keyword is corresponding at least one label, it may in the corresponding label of any two keyword
There are identical labels, so that corresponding label will have number of repetition.For example, there are three keywords altogether, wherein closes
Keyword 1 corresponds to two labels, respectively label 1 and label 2, corresponding three labels of keyword 2, respectively label 1, label 2 and
Label 5,3 corresponding label 2 of keyword and label 3, then the number of repetition of label 1 is 2, the number of repetition of label 2 is 3, label 3
Number of repetition be 1, the number of repetition of label 5 is 1.
105, terminal device selects the corresponding label of at least one number of repetition, obtains at least one target labels;Its
In, the corresponding target number of repetition of the target labels be all numbers of repetition come when according to sorting from large to small front and
For the number of repetition within the scope of preset quantity.
In conjunction with the example in step 104, to label 1 to the number of repetition of label 3 and label 5 according to sorting from large to small,
Then being respectively as follows: label 2- number of repetition is 3, and label 1- number of repetition is 2, and label 3- number of repetition is 1, label 5- number of repetition
It is 1.If preset quantity is 3, it is determined that the target labels come out are respectively label 2, label 1 and label 3.
As an alternative embodiment, terminal device selects the corresponding label of at least one number of repetition, obtain
At least one target labels may include:
Obtain the temperature index value of hot value and corresponding subject and topic type that each label is retrieved;
Calculate the corresponding weight of hot value, subject weight corresponding with the temperature index value of topic type and number of repetition pair
The weight answered;
According to the corresponding weight of hot value, subject weight corresponding with the temperature index value of topic type and number of repetition pair
The weight answered calculates the corresponding total weight of number of repetition;
The corresponding label of at least one total weight is selected, obtains at least one target labels, wherein the target labels pair
The total weight of the target answered is that all total weights come front when sorting from large to small according to weighted value and are preset quantity model
Enclose interior total weight.
In the above-described embodiment, there are corresponding search hot value and label are corresponding for the corresponding learning Content of label
The temperature index value of subject and topic type, wherein the hot value of search can be counted according to determining the case where search by user
The temperature index value of searching times on network, subject and topic type refers to that this subject is liked with what topic type was socially subject to
Degree etc..
106, terminal device is that user recommends the corresponding learning Content of each target labels.
In embodiments of the present invention, the searching request that Client-initiated carries search problem is received, is then asked from search
Middle at least one keyword of extraction is sought, label distribution model is further utilized, obtains at least one corresponding mark of each keyword
Label, and all keywords are combined, the number of repetition that each label occurs in all keywords is counted, and select at least
The corresponding label of one number of repetition, to obtain at least one target labels, wherein assuming that according to sorting from large to small
When having number of repetition, the preset quantity number of repetition for coming front (i.e. number of repetition is higher) is determined, then should
The corresponding label of preset quantity number of repetition is last only to recommend the target labels are corresponding to learn to user as target labels
Content can carry out keyword extraction to search problem, then comprehensively consider the corresponding label of each keyword, true according to label
The corresponding real search intention of search problem is made, has targetedly learning Content to provide for user, can satisfy use
The search at family needs, and improves recommendation effect, really recommends meaning to play.
Embodiment two
Referring to Fig. 2, Fig. 2 is the flow diagram of the recommended method of learning Content disclosed in another embodiment of the present invention;
As shown in Fig. 2, the recommended method of the learning Content can include:
201, terminal device receives the searching request of user, which carries search problem.
As an alternative embodiment, the searching request that terminal device receives user may include:
After listening r/w cell entered for needing to enter for, output all tins of r/w cells of display;
Detect whether to receive the input voice of user, which carries for requesting search target to listen r/w cell
Search problem, it is any one listened in r/w cell which, which listens r/w cell,;
When detecting above-mentioned input voice, the searching request for receiving user is determined.
In the above-described embodiment, user can be to the dictation list for being ignorant of or not knowing encountered in dictation process
Member is retrieved, with further study understanding.
202, terminal device extracts at least one keyword from search problem.
203, terminal device utilizes label distribution model, obtains at least one corresponding label of each keyword.
204, terminal device combines all keywords, counts the corresponding number of repetition of each label.
205, terminal device obtains the corresponding grade's information of user and age information.
206, terminal device is determined to match respectively with grade's information and age information from the corresponding label of number of repetition
At least one target labels.
It is appreciated that terminal device first can determine target labels according to grade's information and age information, to select
The learning Content to match with user's grade's information and age information.
207, terminal device is that user recommends the corresponding learning Content of each target labels.
208, whether the age indicated by terminal device identification age information is in default the range of age.
Wherein, when in default the range of age, step 209 is turned to;When being not in default the range of age, terminate this
Process.
209, the corresponding learning Content of each target labels is sent to parent's terminal by terminal device, so that parent's terminal
User is assisted to learn above-mentioned learning Content.
Through the foregoing embodiment, the searching request that Client-initiated carries search problem is received, then from searching request
Middle at least one keyword of extraction further utilizes label distribution model, obtains at least one corresponding label of each keyword,
And all keywords are combined, the number of repetition that each label occurs in all keywords is counted, then in conjunction with user's
Grade's information and age information, so that at least one target labels is obtained, to select and user's grade's information and age information
The learning Content to match, it can be seen that keyword extraction can be carried out to search problem, then comprehensively consider each keyword
Corresponding label determines the corresponding real search intention of search problem according to label, has specific aim to provide for user
Learning Content, can satisfy the search needs of user, improve recommendation effect, really recommend meaning to play.
Embodiment three
Referring to Fig. 3, Fig. 3 is the structural schematic diagram of terminal device disclosed in one embodiment of the invention;As shown in figure 3, should
Terminal device can include:
Receiving unit 310, for receiving the searching request of user, described search request carries search problem;
Extraction unit 320, for extracting at least one keyword from described search problem;
Acquiring unit 330 obtains at least one corresponding mark of each keyword for utilizing label distribution model
Label;
Statistic unit 340, for counting the corresponding number of repetition of each label in conjunction with all keywords;
Selecting unit 350 obtains at least one target for selecting the corresponding label of at least one described number of repetition
Label;Wherein, the corresponding target number of repetition of the target labels is all numbers of repetition according to sorting from large to small
When come front and for the number of repetition within the scope of preset quantity;
Recommendation unit 360, for recommending the corresponding learning Content of each target labels for user.
Implement above-mentioned terminal device, carry the searching request of search problem by receiving Client-initiated, then from searching
At least one keyword is extracted in rope request, label distribution model is further utilized, obtains each keyword corresponding at least one
A label, and all keywords are combined, the number of repetition that each label occurs in all keywords is counted, and select
The corresponding label of at least one number of repetition, to obtain at least one target labels, wherein assuming that according to arranging from big to small
When all numbers of repetition of sequence, the preset quantity number of repetition that will come front (i.e. number of repetition is higher) is determined, then
It is last only to recommend the target labels corresponding to user using the corresponding label of preset quantity number of repetition as target labels
Learning Content can carry out keyword extraction to search problem, the corresponding label of each keyword then be comprehensively considered, according to mark
Label determine the corresponding real search intention of search problem, have targetedly learning Content, Neng Gouman to provide for user
The search of sufficient user needs, and improves recommendation effect, really recommends meaning to play.
As an alternative embodiment, above-mentioned selecting unit 350 is for selecting at least one described number of repetition
Corresponding label obtains the mode of at least one target labels specifically:
Above-mentioned selecting unit 350, for obtaining the hot value and corresponding subject and topic type that each label is retrieved
Temperature index value;And calculate the corresponding weight of the hot value, the subject power corresponding with the temperature index value of topic type
Weight and the corresponding weight of the number of repetition;And according to the corresponding weight of the hot value, the subject and topic type
The corresponding weight of temperature index value and the corresponding weight of the number of repetition calculate the corresponding total weight of the number of repetition;
And the corresponding label of at least one described total weight is selected, obtain at least one target labels, wherein the target mark
Signing the corresponding total weight of target is that all total weights come front when sorting from large to small according to weighted value and are pre-
If total weight in quantitative range.
As an alternative embodiment, being additionally provided with button of taking pictures beside search column, receiving unit 310 is for connecing
Receive the mode of the searching request of user specifically: detect user to the clicking operation of the button of taking pictures, in response to the clicking operation
The camera built in terminal device is called, interface of taking pictures is opened, by the preview area in interface of taking pictures to including above-mentioned search
The content of text of problem carries out image preview, obtains preview image, when detecting the photographing instruction of user's input, to preview graph
As taking pictures, image of taking pictures is obtained, above-mentioned search problem is identified from image of taking pictures.Pass through the embodiment, Yong Huke
To input search problem by shooting style, operate it is more convenient, it is especially more or the form of expression is more complicated in text
When search problem, input mode of taking pictures is more convenient.
In another optional embodiment, receiving unit 310 may include: that terminal is set for receiving the searching request of user
Standby to be built-in with near-field communication (Near Field Communication, NFC) module, receiving unit 310 opens study class APP,
Study class APP is logged on to by account information, detects to add in type selecting in good friend and the selection of face-to-face plusing good friend function is grasped
Make, built-in NFC module is called in response to the selection operation, using the NFC module from another end for being equally built-in with NFC module
User name of another terminal device on same study class APP is read in end equipment, which is input to search column, is passed through
User's search column scans for the corresponding user of the user name, when searching the corresponding user of the user name, by the user
The corresponding user of name is added to buddy list, finds the user from buddy list according to user's operation and opens and the user
Chat window, from the chat window receive the other user send search problem.By the embodiment, can learn
Increase social functions on class APP, the search problem for needing to solve then is obtained from good friend.
As an alternative embodiment, extraction unit 320 from described search problem for extracting at least one pass
After keyword, identify whether the keyword matches with any of sensitive list sensitivity vocabulary, wherein sensitive list is by family
Long terminal includes several sensitive vocabulary by being arranged when remote-control private tutor's equipment, in sensitive list;If the keyword with it is quick
The sensitive vocabulary of any of sense list matches, then sends to parent's terminal for informing that the user to be ready retrieving sensitive list
In sensitive vocabulary;If the sensitive vocabulary of any of the keyword and sensitive list mismatches, acquiring unit 330 is triggered
Execute corresponding steps.By the embodiment, it can prevent user from voluntarily searching for some sensitive words inconsistent with its age
It converges, influences the development of its thought, or even influence its growth.
Example IV
Referring to Fig. 4, Fig. 4 is the structural schematic diagram of terminal device disclosed in another embodiment of the present invention;End shown in Fig. 4
End equipment is optimized on the basis of terminal device shown in Fig. 3, above-mentioned in terminal device shown in Fig. 4
Selecting unit 350 obtains the side of at least one target labels for selecting the corresponding label of at least one described number of repetition
Formula specifically:
Above-mentioned selecting unit 350, for obtaining the corresponding grade's information of user and age information;And from the repetition
It determines to distinguish at least one matched target labels with grade's information and the age information in the corresponding label of number.
In turn, above-mentioned terminal device further include: transmission unit 410.
Wherein, above-mentioned transmission unit 410, for being that user recommends each target labels in above-mentioned recommendation unit 360
After corresponding learning Content, identify whether the age indicated by the age information is in default the range of age;And when
When in described default the range of age, the corresponding learning Content of each target labels is sent to parent's terminal, so that
Parent's terminal assists user to learn the learning Content.
As an alternative embodiment, the mode for the searching request that above-mentioned receiving unit 310 is used to receive user has
Body are as follows:
Above-mentioned receiving unit 310, after listening r/w cell entered for needing to enter for, output display is all described to be listened
R/w cell;And detecting whether to receive the input voice of user, the input voice is carried for requesting search target to be listened
The search problem of r/w cell, it is any one listened in r/w cell that the target, which listens r/w cell,;And it is described when detecting
When inputting voice, the searching request for receiving user is determined.
By implementing Fig. 4 terminal device, the searching request that Client-initiated carries search problem is received, then from search
At least one keyword is extracted in request, further utilize label distribution model, obtain each keyword it is corresponding at least one
Label, and combine all keywords, count the number of repetition that each label occurs in all keywords, then in conjunction with
Grade's information and age information at family, so that at least one target labels is obtained, to select and user's grade's information and age
The learning Content that information matches, it can be seen that keyword extraction can be carried out to search problem, then comprehensively consider each pass
The corresponding label of keyword determines the corresponding real search intention of search problem according to label, has needle to provide for user
It to the learning Content of property, can satisfy the search needs of user, improve recommendation effect, really recommend meaning to play.
Embodiment five
Referring to Fig. 5, Fig. 5 is the structural schematic diagram of terminal device disclosed in further embodiment of this invention;End shown in fig. 5
End equipment can include: at least one processor 510, such as CPU, communication bus is for realizing the communication link between these components
It connects.Memory 520 can be high speed RAM memory, be also possible to non-labile memory (non-volatile
Memory), a for example, at least magnetic disk storage.Memory 520 optionally can also be that at least one is located remotely from aforementioned place
Manage the storage device of device 510.Wherein, processor 510 can be in conjunction with terminal device described in Fig. 3 to Fig. 4, in memory 510
Batch processing code is stored, and processor 510 calls the program code stored in memory 520, for performing the following operations:
The searching request of user is received, described search request carries search problem;
At least one keyword is extracted from described search problem;
Using label distribution model, at least one corresponding label of each keyword is obtained;
In conjunction with all keywords, the corresponding number of repetition of each label is counted;
The corresponding label of at least one described number of repetition is selected, at least one target labels is obtained;Wherein, the mesh
The corresponding target number of repetition of mark label is that all numbers of repetition come front when according to sorting from large to small and are
Number of repetition within the scope of preset quantity;
Recommend the corresponding learning Content of each target labels for user.
As an alternative embodiment, above-mentioned processor 510 is also used to execute following steps:
Obtain the temperature index value of hot value and corresponding subject and topic type that each label is retrieved;
Calculate the corresponding weight of the hot value, the subject weight corresponding with the temperature index value of topic type, Yi Jisuo
State the corresponding weight of number of repetition;
According to the corresponding weight of the hot value, subject weight corresponding with the temperature index value of topic type, Yi Jisuo
The corresponding weight of number of repetition is stated, the corresponding total weight of the number of repetition is calculated;
The corresponding label of at least one described total weight is selected, obtains at least one target labels, wherein the target
The total weight of the corresponding target of label is that all total weights come front when sorting from large to small according to weighted value and are
Total weight within the scope of preset quantity.
As an alternative embodiment, above-mentioned processor 510 is also used to execute following steps:
Obtain the corresponding grade's information of user and age information;
It determines to match respectively with grade's information and the age information from the corresponding label of the number of repetition
At least one target labels.
As an alternative embodiment, above-mentioned processor 510 is also used to execute following steps:
After listening r/w cell entered for needing to enter for, output display is all described to listen r/w cell;
Detect whether to receive the input voice of user, the input voice is carried for requesting search target dictation single
The search problem of member, it is any one listened in r/w cell that the target, which listens r/w cell,;
When detecting the input voice, the searching request for receiving user is determined.
As an alternative embodiment, above-mentioned processor 510 is also used to execute following steps:
After recommending the corresponding learning Content of each target labels for user, identify indicated by the age information
Age whether be in default the range of age;
When in described default the range of age, the corresponding learning Content of each target labels is sent to parent
Terminal, so that parent's terminal assists user to learn the learning Content.
A kind of computer readable storage medium is also disclosed in the embodiment of the present invention, stores computer program, wherein the meter
Calculation machine program makes computer execute a kind of recommended method of learning Content disclosed in Fig. 1 to Fig. 2.
A kind of computer program product is also disclosed in the embodiment of the present invention, when the computer program product is transported on computers
When row, so that the computer executes some or all of any one method step disclosed in Fig. 1 to Fig. 2.
The embodiment of the present invention is also disclosed a kind of using distribution platform, and the application distribution platform is used to issue computer program
Product, wherein when the computer program product is run on computers, so that the computer executes Fig. 1 to Fig. 2 and discloses
Some or all of any one method step.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of storing data.
Detailed Jie has been carried out to the recommended method and terminal device of a kind of learning Content disclosed by the embodiments of the present invention above
It continues, used herein a specific example illustrates the principle and implementation of the invention, and the explanation of above embodiments is only
It is to be used to help understand method and its core concept of the invention;At the same time, for those skilled in the art, according to this hair
Bright thought, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not manage
Solution is limitation of the present invention.
Claims (10)
1. a kind of recommended method of learning Content characterized by comprising
The searching request of user is received, described search request carries search problem;
At least one keyword is extracted from described search problem;
Using label distribution model, at least one corresponding label of each keyword is obtained;
In conjunction with all keywords, the corresponding number of repetition of each label is counted;
The corresponding label of at least one described number of repetition is selected, at least one target labels is obtained;Wherein, the target mark
Signing corresponding target number of repetition is that all numbers of repetition come front when according to sorting from large to small and are default
Number of repetition in quantitative range;
Recommend the corresponding learning Content of each target labels for user.
2. the method according to claim 1, wherein described, to select at least one described number of repetition corresponding
Label, obtaining at least one target labels includes:
Obtain the temperature index value of hot value and corresponding subject and topic type that each label is retrieved;
Calculate the corresponding weight of the hot value, the subject weight corresponding with the temperature index value of topic type and described heavy
Again corresponding weight is counted;
According to the corresponding weight of the hot value, subject weight corresponding with the temperature index value of topic type and described heavy
Again corresponding weight is counted, the corresponding total weight of the number of repetition is calculated;
The corresponding label of at least one described total weight is selected, obtains at least one target labels, wherein the target labels
The corresponding total weight of target is that all total weights come front when sorting from large to small according to weighted value and are default
Total weight in quantitative range.
3. the method according to claim 1, wherein described, to select at least one described number of repetition corresponding
Label obtains at least one target labels, comprising:
Obtain the corresponding grade's information of user and age information;
Determined from the corresponding label of the number of repetition with grade's information and the age information respectively it is matched to
Few target labels.
4. method according to any one of claims 1 to 3, which is characterized in that the searching request for receiving user, packet
It includes:
After listening r/w cell entered for needing to enter for, output display is all described to listen r/w cell;
Detect whether to receive the input voice of user, the input voice is carried for requesting search target to listen r/w cell
Search problem, it is any one listened in r/w cell that the target, which listens r/w cell,;
When detecting the input voice, the searching request for receiving user is determined.
5. according to the method described in claim 3, it is characterized in that, described recommend each target labels corresponding for user
After learning Content, which comprises
Identify whether the age indicated by the age information is in default the range of age;
When in described default the range of age, the corresponding learning Content of each target labels is sent to parent's end
End, so that parent's terminal assists user to learn the learning Content.
6. a kind of terminal device characterized by comprising
Receiving unit, for receiving the searching request of user, described search request carries search problem;
Extraction unit, for extracting at least one keyword from described search problem;
Acquiring unit obtains at least one corresponding label of each keyword for utilizing label distribution model;
Statistic unit, for counting the corresponding number of repetition of each label in conjunction with all keywords;
Selecting unit obtains at least one target labels for selecting the corresponding label of at least one described number of repetition;Its
In, the corresponding target number of repetition of the target labels is before all numbers of repetition come when according to sorting from large to small
Face and be the number of repetition within the scope of preset quantity;
Recommendation unit, for recommending the corresponding learning Content of each target labels for user.
7. terminal device according to claim 6, which is characterized in that the selecting unit is for selecting at least one institute
The corresponding label of number of repetition is stated, the mode of at least one target labels is obtained specifically:
The selecting unit, the temperature for obtaining hot value and corresponding subject and topic type that each label is retrieved refer to
Numerical value;And calculate the corresponding weight of the hot value, the subject weight corresponding with the temperature index value of topic type and
The corresponding weight of the number of repetition;And according to the corresponding weight of the hot value, the temperature index of the subject and topic type
It is worth corresponding weight and the corresponding weight of the number of repetition, calculates the corresponding total weight of the number of repetition;And choosing
The corresponding label of at least one described total weight is selected out, obtains at least one target labels, wherein the target labels are corresponding
The total weight of target is that all total weights come front when sorting from large to small according to weighted value and are preset quantity model
Enclose interior total weight.
8. terminal device according to claim 6, which is characterized in that the selecting unit is for selecting at least one institute
The corresponding label of number of repetition is stated, the mode of at least one target labels is obtained specifically:
The selecting unit, for obtaining the corresponding grade's information of user and age information;And it is corresponding from the number of repetition
Label in determine and grade's information and the age information distinguish at least one matched target labels.
9. according to the described in any item terminal devices of claim 6 to 8, which is characterized in that the receiving unit is used for receiving
The mode of the searching request at family specifically:
The receiving unit, after listening r/w cell entered for needing to enter for, output display is all described to listen r/w cell;
And detecting whether to receive the input voice of user, the input voice is carried for requesting search target to listen r/w cell
Search problem, it is any one listened in r/w cell that the target, which listens r/w cell,;And when detecting the input language
When sound, the searching request for receiving user is determined.
10. terminal device according to claim 8, which is characterized in that the terminal device further include:
Transmission unit, after being used to recommend the corresponding learning Content of each target labels in the recommendation unit for user,
Identify whether the age indicated by the age information is in default the range of age;And when in the default age model
When enclosing interior, the corresponding learning Content of each target labels is sent to parent's terminal, so that parent's terminal assists to use
Family learns the learning Content.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811540311.1A CN109299399B (en) | 2018-12-17 | 2018-12-17 | Learning content recommendation method and terminal equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811540311.1A CN109299399B (en) | 2018-12-17 | 2018-12-17 | Learning content recommendation method and terminal equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109299399A true CN109299399A (en) | 2019-02-01 |
CN109299399B CN109299399B (en) | 2021-07-23 |
Family
ID=65142929
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811540311.1A Active CN109299399B (en) | 2018-12-17 | 2018-12-17 | Learning content recommendation method and terminal equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109299399B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111081103A (en) * | 2019-05-17 | 2020-04-28 | 广东小天才科技有限公司 | Dictation answer obtaining method, family education equipment and storage medium |
CN111400471A (en) * | 2020-03-13 | 2020-07-10 | 江苏满运软件科技有限公司 | Question recommendation method, system, electronic device and storage medium |
CN111726789A (en) * | 2019-03-21 | 2020-09-29 | 上海博泰悦臻电子设备制造有限公司 | First mobile terminal, friend adding method and system |
CN111753153A (en) * | 2019-11-25 | 2020-10-09 | 广东小天才科技有限公司 | Error problem information collection method, electronic device, storage medium, and program product |
WO2022068123A1 (en) * | 2020-09-29 | 2022-04-07 | 深圳市创新佳电子标签有限公司 | Nfc social software system |
CN115660913A (en) * | 2022-11-09 | 2023-01-31 | 读书郎教育科技有限公司 | System and method for customizing learning content for user |
CN116595249A (en) * | 2023-04-28 | 2023-08-15 | 广东津虹数字科技有限公司 | Personality recommendation method, system, electronic device and computer program product |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150234927A1 (en) * | 2012-11-06 | 2015-08-20 | Tencent Technology (Shenzhen) Company Limited | Application search method, apparatus, and terminal |
CN105740404A (en) * | 2016-01-28 | 2016-07-06 | 上海晶赞科技发展有限公司 | Label association method and device |
CN105893440A (en) * | 2015-12-15 | 2016-08-24 | 乐视网信息技术(北京)股份有限公司 | Associated application recommendation method and apparatus |
-
2018
- 2018-12-17 CN CN201811540311.1A patent/CN109299399B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150234927A1 (en) * | 2012-11-06 | 2015-08-20 | Tencent Technology (Shenzhen) Company Limited | Application search method, apparatus, and terminal |
CN105893440A (en) * | 2015-12-15 | 2016-08-24 | 乐视网信息技术(北京)股份有限公司 | Associated application recommendation method and apparatus |
CN105740404A (en) * | 2016-01-28 | 2016-07-06 | 上海晶赞科技发展有限公司 | Label association method and device |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111726789A (en) * | 2019-03-21 | 2020-09-29 | 上海博泰悦臻电子设备制造有限公司 | First mobile terminal, friend adding method and system |
CN111081103A (en) * | 2019-05-17 | 2020-04-28 | 广东小天才科技有限公司 | Dictation answer obtaining method, family education equipment and storage medium |
CN111753153A (en) * | 2019-11-25 | 2020-10-09 | 广东小天才科技有限公司 | Error problem information collection method, electronic device, storage medium, and program product |
CN111400471A (en) * | 2020-03-13 | 2020-07-10 | 江苏满运软件科技有限公司 | Question recommendation method, system, electronic device and storage medium |
CN111400471B (en) * | 2020-03-13 | 2022-09-27 | 江苏满运软件科技有限公司 | Question recommendation method, system, electronic device and storage medium |
WO2022068123A1 (en) * | 2020-09-29 | 2022-04-07 | 深圳市创新佳电子标签有限公司 | Nfc social software system |
CN115660913A (en) * | 2022-11-09 | 2023-01-31 | 读书郎教育科技有限公司 | System and method for customizing learning content for user |
CN116595249A (en) * | 2023-04-28 | 2023-08-15 | 广东津虹数字科技有限公司 | Personality recommendation method, system, electronic device and computer program product |
CN116595249B (en) * | 2023-04-28 | 2024-03-22 | 广东津虹数字科技有限公司 | Personality recommendation method, system, electronic device and computer program product |
Also Published As
Publication number | Publication date |
---|---|
CN109299399B (en) | 2021-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109299399A (en) | Learning content recommendation method and terminal equipment | |
US20210232763A1 (en) | Graphical systems and methods for human-in-the-loop machine intelligence | |
CN108509463B (en) | Question response method and device | |
US11449785B2 (en) | Method and system for artificial intelligence learning using messaging service and method and system for relaying answer using artificial intelligence | |
US20160048772A1 (en) | Tailoring Question Answering System Output Based on User Expertise | |
CN107111475A (en) | Manage and understand the user mutual determined for inputting | |
CN105912629A (en) | Intelligent question and answer method and device | |
CN108139918A (en) | Using every user as basic custom program feature | |
Choetkiertikul et al. | Who will answer my question on stack overflow? | |
CN109635196A (en) | Intelligent search method based on polysemous words and family education equipment | |
CN110895568B (en) | Method and system for processing court trial records | |
CN107861927A (en) | Document annotation method and device, readable storage medium and computer equipment | |
US20190362025A1 (en) | Personalized query formulation for improving searches | |
CN110187780A (en) | Long text prediction technique, device, equipment and storage medium | |
CN110532469B (en) | Information recommendation method, device, equipment and storage medium | |
CN109086420A (en) | Select the method, apparatus and storage medium of reading material | |
CN108108249A (en) | Data inputting method and device | |
CN109615009A (en) | Learning content recommendation method and electronic equipment | |
CN108733718A (en) | Display methods, device and the display device for search result of search result | |
CN108776864A (en) | The appraisal procedure and device of user comment value | |
WO2021135322A1 (en) | Automatic question setting method, apparatus and system | |
CN109636378B (en) | Account identification method and device and electronic equipment | |
CN109635214A (en) | Learning resource pushing method and electronic equipment | |
Mitchell et al. | Using structured decision making to manage disease risk for Montana wildlife | |
Ye et al. | Tooleyes: Fine-grained evaluation for tool learning capabilities of large language models in real-world scenarios |
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 |