CN109635100A - A kind of recommended method, device, electronic equipment and the storage medium of similar topic - Google Patents
A kind of recommended method, device, electronic equipment and the storage medium of similar topic Download PDFInfo
- Publication number
- CN109635100A CN109635100A CN201811582965.0A CN201811582965A CN109635100A CN 109635100 A CN109635100 A CN 109635100A CN 201811582965 A CN201811582965 A CN 201811582965A CN 109635100 A CN109635100 A CN 109635100A
- Authority
- CN
- China
- Prior art keywords
- topic
- recommendation
- knowledge point
- vector
- target
- 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.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present disclosure discloses recommended method, device, electronic equipment and the storage medium of a kind of similar topic, this method comprises: carrying out knowledge point classification to target topic, obtains ProbabilityDistribution Vector of the target topic on each knowledge point;It calculates and has similarity of the topic between the ProbabilityDistribution Vector on each knowledge point in the ProbabilityDistribution Vector and exam pool of the target topic;The recommendation topic of the target topic is generated, according to the similarity to improve the accuracy that similar topic is recommended.Wherein, by the way that topic is converted to knowledge point vector, by calculating the similarity between the vector of topic knowledge point, to measure the similarity of topic, avoids and be based purely on the distance between knowledge point label and text to find the problem of inaccurate and not comprehensive or even wrong recommendation that similar topic occurs is inscribed.
Description
Technical field
This disclosure relates to educate Internet technical field more particularly to a kind of recommended method of similar topic, device, electronics
Equipment and storage medium.
Background technique
Similar topic recommendation has non-in K12 (kindergarten through twelfth grade) education sector now
Often be widely applied, the application program that similar topic is recommended can inscribe according to the history mistake of student and generate similar topic, for student into
Row consolidates practice, or recommends similar topic etc. according to the topic of teacher's retrieval.
The core of similar topic recommended technology is that the similarity between calculating topic and topic, existing technical solution are general
It is the knowledge point label for using topic first, finds out the alternative topic below same knowledge point.It is based on text similarity, calculation question again
Similitude in mesh text and exam pool between the text of topic finds out the high topic of similarity as recommendation.
This method has that there are the following problems: first, the similitude of topic text is not equivalent to the similitude of topic.Cause
For the particularity of topic itself, a number is changed sometimes, the solution approach that will lead to whole problem is completely different.And have
Although topic statement completely it is different, the method and knowledge point used are closely similar.Second, recommend topic
Quality is often limited to the quality of label, recommends certain mistake if label is wrong.Even if label is reasonable, single knowledge
Point label often can not also cover all knowledge points that topic is related to.Therefore, the similar topic of the recommendation of the prior art will appear inaccurate
Really, in addition mistake problem.
Summary of the invention
The disclosure provides recommended method, device, electronic equipment and the storage medium of a kind of similar topic, solves the prior art
In the similar topic problem of recommending inaccuracy even wrong.
In a first aspect, the embodiment of the present disclosure provides a kind of recommended method of similar topic, comprising:
Knowledge point classification is carried out to target topic, obtains ProbabilityDistribution Vector of the target topic on each knowledge point;
It calculates and has probability distribution of the topic on each knowledge point in the ProbabilityDistribution Vector and exam pool of the target topic
Similarity between vector;
The recommendation topic of the target topic is generated according to the similarity.
Further, it calculates in the ProbabilityDistribution Vector and exam pool of the target topic and has topic on each knowledge point
Similarity between ProbabilityDistribution Vector, comprising: calculate and have topic in the ProbabilityDistribution Vector and exam pool of the target topic
Distance between the ProbabilityDistribution Vector on each knowledge point;
Correspondingly, being inscribed according to the recommendation that the similarity generates the target topic, comprising: generate institute according to the distance
State the recommendation topic of target topic.
Further, knowledge point classification is carried out to the target topic, obtains the target topic on each knowledge point
ProbabilityDistribution Vector, comprising:
It is handled by problem data of the neural network to the target topic, obtains the target topic in each knowledge
ProbabilityDistribution Vector on point, as the first ProbabilityDistribution Vector;
Wherein, the problem data includes text, formula and/or picture.
Further, if the target topic has knowledge point label, correspondingly, obtaining the target topic in each knowledge
After ProbabilityDistribution Vector on point, further includes:
The target topic is calculated in the corresponding ProbabilityDistribution Vector in each knowledge point according to the knowledge point label, as the
Two probability distribution;
The target topic is calculated on each knowledge point according to first probability distribution and second probability distribution
Combined chance distribution vector, and using the combined chance distribution vector as final ProbabilityDistribution Vector;Wherein, the knowledge
Point label is for showing knowledge point contents included by topic.
Further, after the recommendation topic that the target topic is generated according to the similarity, comprising:
The recommendation is inscribed and carries out duplicate removal;Wherein, the duplicate removal include: remove in recommendation topic duplicate topic and/
Or topic identical with the target topic.
Further, the recommendation is inscribed and carries out duplicate removal, comprising:
According to the distance between all topics index in recommendation topic and recommendation topic and the target topic it
Between range index the recommendation topic in carry out duplicate removal;And/or
Duplicate removal is carried out in recommendation topic using topic classifier.
Further, it is inscribed according to the recommendation that the similarity generates the target topic, comprising:
Number and the similarity are inscribed according to preset recommendation, generates the recommendation topic of respective number.
Further, after the recommendation topic that the target topic is generated according to the similarity, further includes:
The account of the history inscribed and requirement is done according to user to screen recommendation topic.
Further, the account of the history inscribed and requirement are done according to user to screen recommendation topic, including with
It is at least one lower:
The topic done in the account of the history removal preset time inscribed is done according to user;
It is higher than the topic of preset threshold according to great this memory curve removal memory degree of Chinese mugwort guest;
The difficulty of the target topic inscribed to wrong situation, adjustment recommendation is done according to user.
Second aspect, the embodiment of the present disclosure additionally provide a kind of recommendation apparatus of similar topic, comprising:
Vector calculation module obtains the target topic in each knowledge point for carrying out knowledge point classification to target topic
On ProbabilityDistribution Vector;
Similarity calculation module has topic in the ProbabilityDistribution Vector and exam pool for calculating the target topic each
The similarity between ProbabilityDistribution Vector on knowledge point;
Generation module is inscribed in recommendation, and the recommendation for generating the target topic according to the similarity is inscribed.
Further, the similarity calculation module, comprising: vector distance computing unit, for calculating the target topic
Purpose ProbabilityDistribution Vector is at a distance from topic existing in exam pool is between the ProbabilityDistribution Vector on each knowledge point;
Correspondingly, generation module is inscribed in the recommendation, comprising: generation unit is inscribed in recommendation, for generating institute according to the distance
State the recommendation topic of target topic.
Further, the similarity calculation module, comprising: primary vector computing unit, for passing through neural network pair
The problem data of the target topic is handled, and ProbabilityDistribution Vector of the target topic on each knowledge point is obtained, and is made
For the first probability distribution;
Wherein, the problem data includes text, formula and/or picture.
Further, the vector calculation module includes:
Secondary vector computing unit obtains the target topic and exists if having knowledge point label for the target topic
After ProbabilityDistribution Vector on each knowledge point, it is corresponding in each knowledge point that the target topic is calculated according to the knowledge point label
ProbabilityDistribution Vector, as the second ProbabilityDistribution Vector;
Resultant vector computing unit, for calculating the mesh according to first probability distribution and second probability distribution
Combined chance distribution vector of the title mesh on each knowledge point, and using the combined chance distribution vector as final probability point
Cloth vector;Wherein, the knowledge point label is for showing knowledge point contents included by topic.
Further, described device further include: deduplication module is inscribed in recommendation, for generating the target according to the similarity
After the recommendation topic of topic, the recommendation is inscribed and carries out duplicate removal;Wherein, the duplicate removal includes: and removes to repeat in the recommendation topic
Topic and/or topic identical with the target topic.
Further, the recommendation topic deduplication module includes:
Apart from duplicate removal unit, for being inscribed according to the distance between all topics index and the recommendation in recommendation topic
The distance between target topic index carries out duplicate removal in recommendation topic;And/or
Classifier duplicate removal unit, for carrying out duplicate removal in recommendation topic using topic classifier.
Further, generation module is inscribed in the recommendation, further includes: data setting unit is inscribed in recommendation, for according to preset
Number and the similarity are inscribed in recommendation, generate the recommendation topic of respective number.
Further, described device further include: screening module is inscribed in recommendation, for generating the target according to the similarity
After the recommendation topic of topic, the account of the history inscribed and requirement are done according to user, recommendation topic is screened.
Further, screening module is inscribed in the recommendation, specifically for doing the account of the history and requirement inscribed according to user
Recommendation topic is screened, including at least one of:
The topic done in the account of the history removal preset time inscribed is done according to user;
It is higher than the topic of preset threshold according to great this memory curve removal memory degree of Chinese mugwort guest;
The difficulty of the target topic inscribed to wrong situation, adjustment recommendation is done according to user.
The third aspect, the embodiment of the present disclosure additionally provide a kind of electronic equipment, and the electronic equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes a kind of recommended method of similar topic as described in disclosure any embodiment.
Fourth aspect, the embodiment of the present disclosure additionally provides a kind of storage medium comprising computer executable instructions, described
Computer executable instructions as computer processor when being executed for executing a kind of phase as described in disclosure any embodiment
Like the recommended method of topic.
The embodiment of the present disclosure obtains the target topic on each knowledge point by carrying out knowledge point classification to target topic
ProbabilityDistribution Vector;It is general on each knowledge point to calculate existing topic in the ProbabilityDistribution Vector and exam pool of the target topic
Similarity between rate distribution vector;The recommendation topic of the target topic is generated according to the similarity, is pushed away with improving similar topic
The accuracy recommended.Wherein, similar between the vector of topic knowledge point by calculating by the way that topic is converted to knowledge point vector
Degree, the similarity of Lai Hengliang topic avoid and are based purely on the distance between knowledge point label and text to find similar topic
The problem of being easy to appear inaccuracy and wrong recommendation topic.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the recommended method of the similar topic provided in one embodiment of the disclosure;
Fig. 2 is a kind of flow chart of the recommended method of the similar topic provided in another embodiment of the disclosure;
Fig. 3 is a kind of flow chart of the recommended method of the similar topic provided in another embodiment of the disclosure;
Fig. 4 is a kind of flow chart of the recommended method of the similar topic provided in another embodiment of the disclosure;
Fig. 5 is a kind of flow chart of the recommended method of the similar topic provided in another embodiment of the disclosure;
Fig. 6 is a kind of structural schematic diagram of the recommendation apparatus of the similar topic provided in another embodiment of the disclosure;
Fig. 7 is the structural schematic diagram of a kind of electronic equipment provided in another embodiment of the disclosure.
Specific embodiment
The disclosure is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the disclosure, rather than the restriction to the disclosure.It also should be noted that in order to just
Part relevant to the disclosure is illustrated only in description, attached drawing rather than entire infrastructure.
Fig. 1 is a kind of flow chart of the recommended method for similar topic that one embodiment of the disclosure provides, and the present embodiment can fit
The case where recommending for similar topic, this method can be executed by the recommendation apparatus of similar topic, be specifically comprised the following steps:
S110, knowledge point classification is carried out to target topic, obtains probability distribution of the target topic on each knowledge point
Vector.
Wherein, target topic is the reference topic for carrying out similar topic recommendation.Illustratively, if searching A topic
Similar topic, then correspondingly, A topic can be target topic.Knowledge point classification, available target are carried out to target topic
Included knowledge point in topic.Wherein, knowledge point generally refers to the knowledge on textbook or taken an examination, and can be curriculum information biography
The basic unit passed.Illustratively, knowledge point may include one or more main knowledge points, and main knowledge point correspondence may include one
A or multiple secondary knowledge points, secondary knowledge point can be corresponded to including one or more sub- knowledge points.Illustratively, in Junior Mathematics class
Mathematical knowledge point in journey may include: main knowledge point for several and formula, including the first secondary knowledge point be real number concept with point
Class, the second secondary knowledge point is real number and secondary radical;The first sub- knowledge point that first secondary knowledge point includes is opposite number, the second son
Knowledge point is absolute value, and the sub- knowledge point of third is inverse.The first sub- knowledge point that second secondary knowledge point includes is secondary radical
Property, the second sub- knowledge point are radical algorithm, and the sub- knowledge point of third is secondary radical hybrid operation.
After carrying out knowledge point classification to target topic, it is general on each knowledge point to further calculate the target topic
Rate distribution vector illustratively can use neural network and carry out to ProbabilityDistribution Vector of the target topic on each knowledge point
It calculates, it can convert the ProbabilityDistribution Vector on each knowledge point for target topic.
S120, existing probability of the topic on each knowledge point in the ProbabilityDistribution Vector and exam pool of the target topic is calculated
Similarity between distribution vector.
Wherein, it can store a large amount of topic in exam pool, illustratively, can store and all knowledge points of Junior Mathematics
Relevant topic.ProbabilityDistribution Vector of the topic on each knowledge point in exam pool can also be calculated with target topic in each knowledge
The same algorithm of ProbabilityDistribution Vector on point calculates, and further calculates ProbabilityDistribution Vector of the target topic on each knowledge point
It is similar between the two vector to calculate with similarity of the topic in exam pool between the ProbabilityDistribution Vector on each knowledge point
Property, for illustrating that two vectors correspond to the similarity between topic.Specifically, topic similarity is higher, illustrate what topic included
Knowledge point is more close.Illustratively, the similitude between two vectors is calculated, the modes such as vector distance or vector angle can be used
It is calculated.
S130, the recommendation topic that the target topic is generated according to the similarity.
Wherein, recommendation topic is topic similar with target topic, and the recommendation topic of generation can in the form of a list or preview
Mode etc. is recommended.Illustratively, similar topic can be shown in lists in a manner of ascending order according to the size of similarity
Show.For example, the high topic of similarity forward can show that the low topic of similarity is recommended rearward.
Optionally, it is general on each knowledge point to calculate existing topic in the ProbabilityDistribution Vector and exam pool of the target topic
Similarity between rate distribution vector, comprising: calculate existing topic in the ProbabilityDistribution Vector and exam pool of the target topic and exist
The distance between ProbabilityDistribution Vector on each knowledge point;
Correspondingly, being inscribed according to the recommendation that the similarity generates the target topic, comprising: generate institute according to the distance
State the recommendation topic of target topic.
Wherein, Euclidean distance (Euclidean Distance), Man Ha can specifically be calculated by calculating the distance between vector
Distance (Manhattan Distance) of pausing or Chebyshev are apart from (Chebyshev Distance) etc., in general, distance is got over
Closely, illustrate that the similarity between vector is higher, i.e., topic is more similar.
Optionally, it is inscribed according to the recommendation that the similarity generates the target topic, comprising:
Number and the similarity are inscribed according to preset recommendation, generates the recommendation topic of respective number.
Wherein it is possible to recommendation topic number is preset, and illustratively, if being set as 10, when recommending topic to generate,
Highest preceding 10 topics of similarity can be recommended according to the size of similarity.It can certainly be with TOP-N algorithm from pushing away
The N number of data recommended required for obtaining in topic are recommended, and are recommended.
The technical solution of the present embodiment obtains the target topic each by carrying out knowledge point classification to target topic
ProbabilityDistribution Vector on knowledge point;It calculates in the ProbabilityDistribution Vector and exam pool of the target topic and has topic in each knowledge
The similarity between ProbabilityDistribution Vector on point;It is carried out according to the recommendation topic that the similarity generates the target topic similar
Topic is recommended.Wherein, more complete come the similitude for measuring topic according to the similarity between the knowledge point ProbabilityDistribution Vector of topic
Face is accurate, can be convenient and user is helped to learn, and improves user experience.
Fig. 2 is a kind of flow chart of the recommended method for similar topic that another embodiment of the disclosure provides, in above-mentioned implementation
On the basis of example, optionally, knowledge point classification is carried out to the target topic, obtains the target topic on each knowledge point
ProbabilityDistribution Vector, comprising: handled by problem data of the neural network to the target topic, obtain the target topic
ProbabilityDistribution Vector of the mesh on each knowledge point, as the first probability distribution.As shown in Fig. 2, this method specifically includes:
S210, it is handled by problem data of the neural network to the target topic, obtains the target topic and exist
ProbabilityDistribution Vector on each knowledge point, as the first probability distribution.
Wherein, target topic may include problem data and/or knowledge point label.Problem data may include text, public affairs
The item content of the forms such as formula or picture.Specifically, when only including problem data in target topic, it illustratively, can be with
The text, formula and/or picture of topic are encoded respectively, specific format is converted into, is predicted using deep neural network
ProbabilityDistribution Vector of the topic on each knowledge point predict the ProbabilityDistribution Vector on each knowledge point using neural network
Faster, recognition accuracy is higher for calculating speed.
S220, existing probability of the topic on each knowledge point in the ProbabilityDistribution Vector and exam pool of the target topic is calculated
Similarity between distribution vector.
S230, the recommendation topic that the target topic is generated according to the similarity.
The technical solution of the present embodiment carries out knowledge point classification by problem data, obtains topic on each knowledge point
After ProbabilityDistribution Vector, similar topic is carried out by the similarity calculated between vector and is recommended, when can recommend to avoid similar topic
It is limited only by that topic label is easy error or label is single that knowledge point is caused to cover incomplete problem, the topic of recommendation is more
It is accurate and comprehensive to add.Meanwhile faster using neural computing ProbabilityDistribution Vector calculating speed, accuracy rate is also higher, realizes
It is quick, accurate and comprehensive that similar topic is recommended.
Fig. 3 is a kind of flow chart of the recommended method for similar topic that another embodiment of the disclosure provides, in above-mentioned implementation
On the basis of example, optionally, if the target topic includes problem data and knowledge point label, correspondingly, as shown in figure 3,
This method specifically includes:
S310, it is handled by problem data of the neural network to the target topic, obtains the target topic and exist
ProbabilityDistribution Vector on each knowledge point, as the first probability distribution.
S320, the target topic is calculated according to the knowledge point label in the corresponding ProbabilityDistribution Vector in each knowledge point,
As the second ProbabilityDistribution Vector.
S330, respectively known according to first ProbabilityDistribution Vector and second probability distribution calculating target topic
Know the combined chance distribution vector on point, and using the combined chance distribution vector as final ProbabilityDistribution Vector.
S340, existing probability of the topic on each knowledge point in the ProbabilityDistribution Vector and exam pool of the target topic is calculated
Similarity between distribution vector.
S350, the recommendation topic that the target topic is generated according to the similarity.
Wherein, when some topics have knowledge point label, the knowledge point label is known included by topic for showing
Know point content, similar topic is carried out according to the knowledge point label in topic completely in the prior art and is recommended.It in the present embodiment, can be with
Knowledge point label is converted to one-hot vector according to preset transformation rule, it is general by first as the second ProbabilityDistribution Vector
The combined chance distribution vector that rate distribution vector and the second ProbabilityDistribution Vector weighted average acquire is as final probability distribution
Vector carries out similarity calculation according to final ProbabilityDistribution Vector, and carries out similar topic and recommend.
The technical solution of the present embodiment, the synthesis being calculated using the knowledge point label and problem data that are carried in topic
ProbabilityDistribution Vector may be implemented more accurately completely as final ProbabilityDistribution Vector by vector similarity calculating
Similar topic is recommended, and is limited only by that topic label is easy to malfunction or label is single leads to knowledge when can be to avoid the recommendation of similar topic
Point covers incomplete problem.
Fig. 4 is a kind of flow chart of the recommended method for similar topic that another embodiment of the disclosure provides, in above-mentioned each reality
On the basis of applying example, optionally, after the recommendation topic that the target topic is generated according to the similarity, further includes: to described
Recommendation topic carries out duplicate removal.As shown in figure 4, this method specifically includes:
S410, knowledge point classification is carried out to target topic, obtains probability distribution of the target topic on each knowledge point
Vector.
S420, existing probability of the topic on each knowledge point in the ProbabilityDistribution Vector and exam pool of the target topic is calculated
Similarity between distribution vector.
S430, the recommendation topic that the target topic is generated according to the similarity.
S440, progress duplicate removal is inscribed to the recommendation.
Wherein, the duplicate removal includes: to remove in recommendation topic duplicate topic and/or identical with the target topic
Topic.It is understood that recommendation topic is to be generated according to the ProbabilityDistribution Vector similarity on each knowledge point, but recommending
In topic between some topics and recommend between topic and target topic may to be only that some numerical value is different or literal expression not
Together, and including knowledge point it is identical, therefore this kind of entitled duplicate topic needs to carry out duplicate removal without being recommended,
To realize the accurate screening inscribed to recommendation, more effectively recommended for user.
Optionally, the recommendation is inscribed and carries out duplicate removal, comprising:
According to the distance between all topics index in recommendation topic and recommendation topic and the target topic it
Between range index the recommendation topic in carry out duplicate removal;And/or
Duplicate removal is carried out in recommendation topic using topic classifier.
Wherein, range index illustratively, can be editing distance (Edit for showing text similarity between topic
Distance) or Jie Kade is apart from (Jaccard Distance).In general, editing distance is smaller, two topic texts
Similarity is bigger.Topic classifier confirms duplicate topic for classifying to topic.Illustratively, in order to more accurate
Duplicate removal, can also can recycle topic between the topic apart from lesser preset number after calculating range index
Classifier carries out duplicate removal, increases the accuracy of duplicate removal.Specifically, can the recommendation after duplicate removal inscribe number reach preset data it
When stop deduplication operation.
The technical solution of the embodiment of the present disclosure, by converting topic in each knowledge point ProbabilityDistribution Vector, then
According to the similarity between the knowledge point ProbabilityDistribution Vector of topic, the similitude of Lai Hengliang topic, and carries out similar topic and recommend.
Meanwhile removing in recommending topic and recommending between topic to recommending topic to carry out duplicate removal using range index or topic classifier
It is duplicate and with the duplicate topic of target topic, recommended with the similar topic of the carry out of more precise and high efficiency, improve the experience of user.
Fig. 5 is a kind of flow chart of the recommended method of the similar topic provided in another embodiment of the disclosure, at above-mentioned
On the basis of embodiment of anticipating, optionally, after the recommendation topic that the target topic is generated according to the similarity, further includes: root
The account of the history inscribed and requirement is done according to user to screen recommendation topic.As shown in figure 5, this method comprises:
S510, knowledge point classification is carried out to target topic, obtains probability distribution of the target topic on each knowledge point
Vector.
S520, existing probability of the topic on each knowledge point in the ProbabilityDistribution Vector and exam pool of the target topic is calculated
Similarity between distribution vector.
S530, the recommendation topic that the target topic is generated according to the similarity.
S540, done according to user the account of the history inscribed and requirement to the recommendation topic screen.
Wherein, account of the history includes the topic that user did, do that time inscribed and doing inscribes to wrong situation etc..User's
Requirement can be the rule that the pre-set topic in recommendation topic is screened.Illustratively, requirement
Can be corresponding with usage scenario, for student, requirement can be the time for having done topic, remember degree or right
Wrong situation etc..
Optionally, the account of the history inscribed and requirement are done according to user to screen recommendation topic, including following
At least one:
The topic done in the account of the history removal preset time inscribed is done according to user;
It is higher than the topic of preset threshold according to great this memory curve removal memory degree of Chinese mugwort guest;
The difficulty of the target topic inscribed to wrong situation, adjustment recommendation is done according to user.
Illustratively, when carrying out similar topic to student and recommending, the topic that had just done recently is remembered than more visible, does not need again
Again it does, therefore, can remove the topic done in the recent period in recommendation topic.Due to Chinese mugwort guest great this (H.Ebbinghaus) memory
Curve (also referred to as forgetting curve) is for describing the rule that human brain forgets new things.Therefore, it can filter out and remember
The topic that degree was done in the lower time can be recommended, and the topic done in the memory degree higher time is removed.?
For the case where malfunctioning when can be inscribed according to user to recommending topic to screen, the recommendation of topic is recommended in adjustment.Illustratively,
If student does wrong on target topic, the recommendation of low difficulty topic in recommending to mention can be promoted according to certain weight,
The lower topic of difficulty carries out recommendation and shows in recommendation can specifically being inscribed.
The technical solution of the present embodiment is done the account of the history inscribed and requirement according to user and is sieved to recommendation topic
Choosing, can meet a variety of requirements of user, and what is inscribed according to forgetting curve and doing is that student recommends suitable topic to wrong situation,
It can allow student learning easily and effectively.
Fig. 6 is a kind of structural schematic diagram of the recommendation apparatus for similar topic that another embodiment of the disclosure provides, such as Fig. 6 institute
Show, described device includes:
Vector calculation module 610 obtains the target topic in each knowledge for carrying out knowledge point classification to target topic
ProbabilityDistribution Vector on point;
Similarity calculation module 620 has topic in the ProbabilityDistribution Vector and exam pool for calculating the target topic
Similarity between the ProbabilityDistribution Vector on each knowledge point;
Generation module 630 is inscribed in recommendation, and the recommendation for generating the target topic according to the similarity is inscribed.
Optionally, the similarity calculation module 620, comprising: vector distance computing unit, for calculating the target topic
Purpose ProbabilityDistribution Vector is at a distance from topic existing in exam pool is between the ProbabilityDistribution Vector on each knowledge point;
Correspondingly, generation module 630 is inscribed in the recommendation, comprising: generation unit is inscribed in recommendation, for being generated according to the distance
The recommendation of the target topic is inscribed.
Optionally, the similarity calculation module 620, comprising: primary vector computing unit, for passing through neural network pair
The problem data of the target topic is handled, and ProbabilityDistribution Vector of the target topic on each knowledge point is obtained, and is made
For the first probability distribution;
Wherein, the problem data includes text, formula and/or picture.
Optionally, the vector calculation module 610 includes:
Secondary vector computing unit obtains the target topic and exists if having knowledge point label for the target topic
After ProbabilityDistribution Vector on each knowledge point, it is corresponding in each knowledge point that the target topic is calculated according to the knowledge point label
ProbabilityDistribution Vector, as the second ProbabilityDistribution Vector;
Resultant vector computing unit, for calculating the mesh according to first probability distribution and second probability distribution
Combined chance distribution vector of the title mesh on each knowledge point, and using the combined chance distribution vector as final probability point
Cloth vector;Wherein, the knowledge point label is for showing knowledge point contents included by topic.
Optionally, described device further include: deduplication module is inscribed in recommendation, is inscribed for generating the target according to the similarity
After purpose recommendation topic, the recommendation is inscribed and carries out duplicate removal;Wherein, the duplicate removal include: remove it is duplicate in recommendation topic
Topic and/or topic identical with the target topic.
Optionally, the recommendation topic deduplication module includes:
Apart from duplicate removal unit, for being inscribed according to the distance between all topics index and the recommendation in recommendation topic
The distance between target topic index carries out duplicate removal in recommendation topic;And/or
Classifier duplicate removal unit, for carrying out duplicate removal in recommendation topic using topic classifier.
Optionally, generation module 630 is inscribed in the recommendation, further includes: data setting unit is inscribed in recommendation, for according to preset
Number and the similarity are inscribed in recommendation, generate the recommendation topic of respective number.
Optionally, described device further include: screening module is inscribed in recommendation, is inscribed for generating the target according to the similarity
After purpose recommendation topic, the account of the history inscribed and requirement are done according to user, recommendation topic is screened.
Optionally, screening module is inscribed in the recommendation, specifically for doing the account of the history and requirement pair inscribed according to user
The recommendation topic is screened, including at least one of:
The topic done in the account of the history removal preset time inscribed is done according to user;
It is higher than the topic of preset threshold according to great this memory curve removal memory degree of Chinese mugwort guest;
The difficulty of the target topic inscribed to wrong situation, adjustment recommendation is done according to user.
The recommendation apparatus of similar topic provided by the embodiment of the present disclosure can be performed provided by disclosure any embodiment
The recommended method of similar topic has the corresponding functional module of execution method and beneficial effect.It is not detailed in the present embodiment to retouch
The technical detail stated, reference can be made to a kind of recommended method for similar topic that disclosure any embodiment provides.
With reference to Fig. 7, it illustrates the structural schematic diagrams for the electronic equipment 700 for being suitable for being used to realize the embodiment of the present disclosure.This
Terminal device in open embodiment can include but is not limited to such as mobile phone, laptop, digit broadcasting receiver,
PDA (personal digital assistant), PAD (tablet computer), PMP (portable media player), car-mounted terminal (such as vehicle mounted guidance
Terminal) etc. mobile terminal and such as number TV, desktop computer etc. fixed terminal.Electronic equipment shown in Fig. 7
An only example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in fig. 7, electronic equipment 700 may include processing unit (such as central processing unit, graphics processor etc.)
701, random access can be loaded into according to the program being stored in read-only memory (ROM) 702 or from storage device 708
Program in memory (RAM) 703 and execute various movements appropriate and processing.In RAM 703, it is also stored with electronic equipment
Various programs and data needed for 700 operations.Processing unit 701, ROM 702 and RAM 703 pass through the phase each other of bus 704
Even.Input/output (I/O) interface 705 is also connected to bus 704.
In general, following device can connect to I/O interface 705: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 706 of head, microphone, accelerometer, gyroscope etc.;Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 707 of dynamic device etc.;Storage device 708 including such as tape, hard disk etc.;And communication device 709.Communication device
709, which can permit electronic equipment 700, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 7 shows tool
There is the electronic equipment 700 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with
Alternatively implement or have more or fewer devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communication device 709, or from storage device 708
It is mounted, or is mounted from ROM 702.When the computer program is executed by processing unit 701, the embodiment of the present disclosure is executed
Method in the above-mentioned function that limits.
It should be noted that the above-mentioned computer-readable medium of the disclosure can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In open, computer-readable signal media may include in a base band or as the data-signal that carrier wave a part is propagated,
In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable and deposit
Any computer-readable medium other than storage media, the computer-readable signal media can send, propagate or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: electric wire, optical cable, RF (radio frequency) etc. are above-mentioned
Any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment;It is also possible to individualism, and not
It is fitted into the electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by the electricity
When sub- equipment executes, so that the electronic equipment: carrying out knowledge point classification to target topic, obtain the target topic in each knowledge
ProbabilityDistribution Vector on point;
It calculates and has probability distribution of the topic on each knowledge point in the ProbabilityDistribution Vector and exam pool of the target topic
Similarity between vector;
The recommendation topic of the target topic is generated according to the similarity.
The calculating of the operation for executing the disclosure can be write with one or more programming languages or combinations thereof
Machine program code, above procedure design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present disclosure can be realized by way of software, can also be by hard
The mode of part is realized.Wherein, module or the title of unit do not constitute the restriction to the unit itself under certain conditions.
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that the open scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from design disclosed above, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed in the disclosure
Can technical characteristic replaced mutually and the technical solution that is formed.
Note that above are only the preferred embodiment and institute's application technology principle of the disclosure.It will be appreciated by those skilled in the art that
The present disclosure is not limited to specific embodiments described here, be able to carry out for a person skilled in the art it is various it is apparent variation,
The protection scope readjusted and substituted without departing from the disclosure.Therefore, although being carried out by above embodiments to the disclosure
It is described in further detail, but the disclosure is not limited only to above embodiments, in the case where not departing from disclosure design, also
It may include more other equivalent embodiments, and the scope of the present disclosure is determined by the scope of the appended claims.
Claims (12)
1. a kind of recommended method of similar topic characterized by comprising
Knowledge point classification is carried out to target topic, obtains ProbabilityDistribution Vector of the target topic on each knowledge point;
It calculates and has ProbabilityDistribution Vector of the topic on each knowledge point in the ProbabilityDistribution Vector and exam pool of the target topic
Between similarity;
The recommendation topic of the target topic is generated according to the similarity.
2. the method according to claim 1, wherein calculating the ProbabilityDistribution Vector and exam pool of the target topic
In have similarity of the topic between the ProbabilityDistribution Vector on each knowledge point, comprising: calculate the probability of the target topic
Distribution vector is at a distance from topic existing in exam pool is between the ProbabilityDistribution Vector on each knowledge point;
Correspondingly, being inscribed according to the recommendation that the similarity generates the target topic, comprising: generate the mesh according to the distance
Title purpose recommendation topic.
3. obtaining institute the method according to claim 1, wherein carrying out knowledge point classification to the target topic
State ProbabilityDistribution Vector of the target topic on each knowledge point, comprising:
It is handled by problem data of the neural network to the target topic, obtains the target topic on each knowledge point
ProbabilityDistribution Vector, as the first probability distribution;
Wherein, the problem data includes text, formula and/or picture.
4. according to the method described in claim 3, it is characterized in that, if the target topic have knowledge point label, correspondingly,
The target topic is obtained after the ProbabilityDistribution Vector on each knowledge point, further includes:
The target topic is calculated in the corresponding ProbabilityDistribution Vector in each knowledge point, generally as second according to the knowledge point label
Rate distribution vector;
The target topic is calculated on each knowledge point according to first ProbabilityDistribution Vector and second probability distribution
Combined chance distribution vector, and using the combined chance distribution vector as final ProbabilityDistribution Vector;Wherein, the knowledge
Point label is for showing knowledge point contents included by topic.
5. the method according to claim 1, wherein generating the recommendation of the target topic according to the similarity
After topic, comprising:
The recommendation is inscribed and carries out duplicate removal;Wherein, the duplicate removal include: remove in recommendation topic duplicate topic and/or with
The identical topic of the target topic.
6. according to the method described in claim 5, carrying out duplicate removal it is characterized in that, inscribing to the recommendation, comprising:
It is inscribed between the target topic according to the distance between all topics index and the recommendation in recommendation topic
Range index carries out duplicate removal in recommendation topic;And/or
Duplicate removal is carried out in recommendation topic using topic classifier.
7. the method according to claim 1, wherein generating the recommendation of the target topic according to the similarity
Topic, comprising:
Number and the similarity are inscribed according to preset recommendation, generates the recommendation topic of respective number.
8. the method according to claim 1, wherein generating the recommendation of the target topic according to the similarity
After topic, further includes:
The account of the history inscribed and requirement is done according to user to screen recommendation topic.
9. according to the method described in claim 8, it is characterized in that, doing the account of the history inscribed and requirement according to user to institute
It states recommendation topic to be screened, including at least one of:
The topic done in the account of the history removal preset time inscribed is done according to user;
It is higher than the topic of preset threshold according to great this memory curve removal memory degree of Chinese mugwort guest;
The difficulty of the target topic inscribed to wrong situation, adjustment recommendation is done according to user.
10. a kind of recommendation apparatus of similar topic characterized by comprising
Vector calculation module obtains the target topic on each knowledge point for carrying out knowledge point classification to target topic
ProbabilityDistribution Vector;
Similarity calculation module has topic in the ProbabilityDistribution Vector and exam pool for calculating the target topic in each knowledge
The similarity between ProbabilityDistribution Vector on point;
Generation module is inscribed in recommendation, and the recommendation for generating the target topic according to the similarity is inscribed.
11. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
A kind of now recommended method of similar topic as described in any in claim 1-9.
12. a kind of storage medium comprising computer executable instructions, the computer executable instructions are by computer disposal
For executing a kind of recommended method of similar topic as described in any in claim 1-9 when device executes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811582965.0A CN109635100A (en) | 2018-12-24 | 2018-12-24 | A kind of recommended method, device, electronic equipment and the storage medium of similar topic |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811582965.0A CN109635100A (en) | 2018-12-24 | 2018-12-24 | A kind of recommended method, device, electronic equipment and the storage medium of similar topic |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109635100A true CN109635100A (en) | 2019-04-16 |
Family
ID=66076967
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811582965.0A Pending CN109635100A (en) | 2018-12-24 | 2018-12-24 | A kind of recommended method, device, electronic equipment and the storage medium of similar topic |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109635100A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110147434A (en) * | 2019-05-23 | 2019-08-20 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
CN110245860A (en) * | 2019-06-13 | 2019-09-17 | 桂林电子科技大学 | A method of the automatic scoring based on Virtual Experiment Platform Based |
CN110334204A (en) * | 2019-05-27 | 2019-10-15 | 湖南大学 | A kind of exercise similarity calculation recommended method based on user record |
CN110347791A (en) * | 2019-06-20 | 2019-10-18 | 广东工业大学 | A kind of topic recommended method based on multi-tag classification convolutional neural networks |
CN110362723A (en) * | 2019-05-31 | 2019-10-22 | 平安国际智慧城市科技股份有限公司 | A kind of topic character representation method, apparatus and storage medium |
CN110472044A (en) * | 2019-07-11 | 2019-11-19 | 平安国际智慧城市科技股份有限公司 | Knowledge point classification method, device, readable storage medium storing program for executing and the server of mathematical problem |
CN110598112A (en) * | 2019-09-17 | 2019-12-20 | 广东小天才科技有限公司 | Topic recommendation method and device, terminal equipment and storage medium |
CN110659311A (en) * | 2019-09-30 | 2020-01-07 | 浙江学海教育科技有限公司 | Topic pushing method and device, electronic equipment and storage medium |
CN111125339A (en) * | 2019-11-26 | 2020-05-08 | 华南师范大学 | Test question recommendation method based on formal concept analysis and knowledge graph |
CN112035605A (en) * | 2020-08-04 | 2020-12-04 | 广州视源电子科技股份有限公司 | Topic recommendation method, device, equipment and storage medium |
WO2021012861A1 (en) * | 2019-07-23 | 2021-01-28 | 苏宁云计算有限公司 | Method and apparatus for evaluating data query time consumption, and computer device and storage medium |
CN112559676A (en) * | 2019-09-25 | 2021-03-26 | 北京新唐思创教育科技有限公司 | Similar topic retrieval method and device and computer storage medium |
CN112667692A (en) * | 2019-10-16 | 2021-04-16 | 北京一起教育信息咨询有限责任公司 | Data processing method and device and electronic equipment |
CN113254126A (en) * | 2021-05-12 | 2021-08-13 | 北京字跳网络技术有限公司 | Information processing method and device and electronic equipment |
CN113269178A (en) * | 2021-05-20 | 2021-08-17 | 读书郎教育科技有限公司 | Intelligent recommendation method based on intelligent classroom chart interception questions |
WO2021253480A1 (en) * | 2020-06-19 | 2021-12-23 | 平安科技(深圳)有限公司 | Intelligent exercise recommendation method and apparatus, computer device and storage medium |
CN114428836A (en) * | 2021-12-30 | 2022-05-03 | 沈阳东软智能医疗科技研究院有限公司 | Information processing method and device, readable storage medium and electronic equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104834729A (en) * | 2015-05-14 | 2015-08-12 | 百度在线网络技术(北京)有限公司 | Title recommendation method and title recommendation device |
CN105930319A (en) * | 2016-05-09 | 2016-09-07 | 北京新唐思创教育科技有限公司 | Methods and devices for establishing question knowledge point obtaining model and obtaining question knowledge point |
CN107562918A (en) * | 2017-09-12 | 2018-01-09 | 北京点易通科技有限公司 | A kind of mathematical problem knowledge point discovery and batch label acquisition method |
CN108182177A (en) * | 2018-01-24 | 2018-06-19 | 谢德刚 | A kind of mathematics knowledge-ID automation mask method and device |
CN108376132A (en) * | 2018-03-16 | 2018-08-07 | 中国科学技术大学 | The determination method and system of similar examination question |
-
2018
- 2018-12-24 CN CN201811582965.0A patent/CN109635100A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104834729A (en) * | 2015-05-14 | 2015-08-12 | 百度在线网络技术(北京)有限公司 | Title recommendation method and title recommendation device |
CN105930319A (en) * | 2016-05-09 | 2016-09-07 | 北京新唐思创教育科技有限公司 | Methods and devices for establishing question knowledge point obtaining model and obtaining question knowledge point |
CN107562918A (en) * | 2017-09-12 | 2018-01-09 | 北京点易通科技有限公司 | A kind of mathematical problem knowledge point discovery and batch label acquisition method |
CN108182177A (en) * | 2018-01-24 | 2018-06-19 | 谢德刚 | A kind of mathematics knowledge-ID automation mask method and device |
CN108376132A (en) * | 2018-03-16 | 2018-08-07 | 中国科学技术大学 | The determination method and system of similar examination question |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110147434A (en) * | 2019-05-23 | 2019-08-20 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
CN110334204A (en) * | 2019-05-27 | 2019-10-15 | 湖南大学 | A kind of exercise similarity calculation recommended method based on user record |
CN110334204B (en) * | 2019-05-27 | 2022-10-18 | 湖南大学 | Exercise similarity calculation recommendation method based on user records |
CN110362723A (en) * | 2019-05-31 | 2019-10-22 | 平安国际智慧城市科技股份有限公司 | A kind of topic character representation method, apparatus and storage medium |
CN110362723B (en) * | 2019-05-31 | 2022-06-21 | 平安国际智慧城市科技股份有限公司 | Topic feature representation method, device and storage medium |
CN110245860A (en) * | 2019-06-13 | 2019-09-17 | 桂林电子科技大学 | A method of the automatic scoring based on Virtual Experiment Platform Based |
CN110245860B (en) * | 2019-06-13 | 2022-08-23 | 桂林电子科技大学 | Automatic scoring method based on virtual experiment platform |
CN110347791A (en) * | 2019-06-20 | 2019-10-18 | 广东工业大学 | A kind of topic recommended method based on multi-tag classification convolutional neural networks |
CN110472044A (en) * | 2019-07-11 | 2019-11-19 | 平安国际智慧城市科技股份有限公司 | Knowledge point classification method, device, readable storage medium storing program for executing and the server of mathematical problem |
WO2021012861A1 (en) * | 2019-07-23 | 2021-01-28 | 苏宁云计算有限公司 | Method and apparatus for evaluating data query time consumption, and computer device and storage medium |
CN110598112A (en) * | 2019-09-17 | 2019-12-20 | 广东小天才科技有限公司 | Topic recommendation method and device, terminal equipment and storage medium |
CN112559676B (en) * | 2019-09-25 | 2022-05-17 | 北京新唐思创教育科技有限公司 | Similar topic retrieval method and device and computer storage medium |
CN112559676A (en) * | 2019-09-25 | 2021-03-26 | 北京新唐思创教育科技有限公司 | Similar topic retrieval method and device and computer storage medium |
CN110659311B (en) * | 2019-09-30 | 2021-11-16 | 浙江学海教育科技有限公司 | Topic pushing method and device, electronic equipment and storage medium |
CN110659311A (en) * | 2019-09-30 | 2020-01-07 | 浙江学海教育科技有限公司 | Topic pushing method and device, electronic equipment and storage medium |
CN112667692A (en) * | 2019-10-16 | 2021-04-16 | 北京一起教育信息咨询有限责任公司 | Data processing method and device and electronic equipment |
CN111125339A (en) * | 2019-11-26 | 2020-05-08 | 华南师范大学 | Test question recommendation method based on formal concept analysis and knowledge graph |
CN111125339B (en) * | 2019-11-26 | 2023-05-09 | 华南师范大学 | Test question recommendation method based on formal concept analysis and knowledge graph |
WO2021253480A1 (en) * | 2020-06-19 | 2021-12-23 | 平安科技(深圳)有限公司 | Intelligent exercise recommendation method and apparatus, computer device and storage medium |
CN112035605A (en) * | 2020-08-04 | 2020-12-04 | 广州视源电子科技股份有限公司 | Topic recommendation method, device, equipment and storage medium |
CN113254126A (en) * | 2021-05-12 | 2021-08-13 | 北京字跳网络技术有限公司 | Information processing method and device and electronic equipment |
CN113269178A (en) * | 2021-05-20 | 2021-08-17 | 读书郎教育科技有限公司 | Intelligent recommendation method based on intelligent classroom chart interception questions |
CN113269178B (en) * | 2021-05-20 | 2023-09-05 | 读书郎教育科技有限公司 | Intelligent question recommendation method based on intelligent classroom chart-cutting questions |
CN114428836A (en) * | 2021-12-30 | 2022-05-03 | 沈阳东软智能医疗科技研究院有限公司 | Information processing method and device, readable storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109635100A (en) | A kind of recommended method, device, electronic equipment and the storage medium of similar topic | |
Yang et al. | Gpt4tools: Teaching large language model to use tools via self-instruction | |
Weller et al. | Mapping the open education landscape: Citation network analysis of historical open and distance education research | |
CN109886326B (en) | Cross-modal information retrieval method and device and storage medium | |
CN110222220B (en) | Image processing method, device, computer readable medium and electronic equipment | |
CN109685137A (en) | A kind of topic classification method, device, electronic equipment and storage medium | |
CN110222762A (en) | Object prediction method, apparatus, equipment and medium | |
CN105912500A (en) | Machine learning model generation method and machine learning model generation device | |
CN111401228B (en) | Video target labeling method and device and electronic equipment | |
CN109376419B (en) | Data model generation method and device, electronic equipment and readable medium | |
CN110209782B (en) | Question-answering model and answer sentence generation method and device, medium and electronic equipment | |
CN110489087A (en) | A kind of method, apparatus, medium and electronic equipment generating fractal structure | |
WO2023185391A1 (en) | Interactive segmentation model training method, labeling data generation method, and device | |
US11501655B2 (en) | Automated skill tagging, knowledge graph, and customized assessment and exercise generation | |
CN111738316B (en) | Zero sample learning image classification method and device and electronic equipment | |
CN112287659B (en) | Information generation method and device, electronic equipment and storage medium | |
CN111538830A (en) | French retrieval method, French retrieval device, computer equipment and storage medium | |
CN115270717A (en) | Method, device, equipment and medium for detecting vertical position | |
CN112380883B (en) | Model training method, machine translation method, device, equipment and storage medium | |
CN117171328A (en) | Text question-answering processing method and device, electronic equipment and storage medium | |
CN109657046B (en) | Content analysis processing method and device, electronic equipment and storage medium | |
CN110852042A (en) | Character type conversion method and device | |
CN113706663B (en) | Image generation method, device, equipment and storage medium | |
CN110705308A (en) | Method and device for recognizing field of voice information, storage medium and electronic equipment | |
CN111104951A (en) | Active learning method and device and terminal equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |