CN111723231B - Question prediction method and device - Google Patents
Question prediction method and device Download PDFInfo
- Publication number
- CN111723231B CN111723231B CN201910211883.3A CN201910211883A CN111723231B CN 111723231 B CN111723231 B CN 111723231B CN 201910211883 A CN201910211883 A CN 201910211883A CN 111723231 B CN111723231 B CN 111723231B
- Authority
- CN
- China
- Prior art keywords
- question
- search
- user
- questions
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90348—Query processing by searching ordered data, e.g. alpha-numerically ordered data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/908—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Abstract
A method and device for predicting the title obtain the vector or set of the current user's search title; generating a target question set according to the vector or the set of the questions; the questions in the target question set are ordered to obtain a recommended sequence, the problem that the OCR result is relatively strong in the question searching process in the prior art is solved, the user is not required to photograph, repair and wait each question, and the question searching time of the user is greatly saved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and apparatus for predicting a question.
Background
With the continuous fusion of image processing and data analysis, the product of photographing and searching questions is online as early as 2013. The shooting and question searching in the related art is mainly realized based on three parts of the camera module, the text recognition and the search module, and especially, the user is required to continuously adjust the angle to shoot the questions as completely as possible in the shooting process of the camera module so as to facilitate the shooting of the camera module, thereby increasing the difficulty for the question searching process of the user.
Disclosure of Invention
The application provides a method and a device for predicting questions, which are used for solving the problem that the question searching process in the prior art depends on an OCR result to be stronger.
The application provides the following scheme:
in a first aspect, the present application provides a method for predicting a topic, including: acquiring a vector or a set of search topics of a current user; generating a target question set according to the vector or the set of the questions; and sequencing the topics in the target topic collection to obtain a recommendation sequence.
In some embodiments, the generating the target topic set according to the topic vector or the topic set specifically includes: acquiring search question data, wherein the search question data comprises at least one question content and a search question sequence in a user history search question process; and in the search question data, searching according to the inverted index and the similarity, acquiring a search question sequence similar to the vector or the set of the questions, extracting the questions positioned behind the current questions in the search question sequence as target questions, and generating a target question set.
In some embodiments, the acquiring the search question data further includes: performing dimension reduction on the search question data by using a graph-based data mining method and a network representation learning method to obtain a search question vector; the nodes of the question searching vector are question information, and the direction of the question searching vector is the question searching sequence.
In some embodiments, the ranking the topics in the target topic set to obtain a recommendation sequence further includes: training the search question data to generate a click rate prediction model; predicting the click rate of the target title according to the title and the click rate prediction model; and generating the recommendation sequence according to a preset click rate sequence.
In some embodiments, the subject prediction method further comprises: and displaying a preset number of target topics to the current user according to the recommendation sequence.
In some embodiments, when the preset number is greater than one, further comprising: simultaneously displaying the preset number of topics to a user; or each time a question is presented to the user.
In some embodiments, when a topic is presented to the user each time, further comprising: acquiring a control instruction of the current user; when the control instruction is a first control instruction, providing an answer and analysis of a current display question for the current user; and when the control instruction is a second control instruction, replacing the current display title for the current user. In some embodiments, before presenting the preset number of target topics to the current user according to the recommendation sequence, the method further includes: and acquiring a control instruction of the current user for providing the target title.
In some embodiments, the presentation of predicted topics is exited after a preset number of presentation topics are replaced to the current user and/or upon acquisition of a user exit instruction.
In a second aspect, the present application provides a topic prediction apparatus, comprising: the acquisition module is used for acquiring vectors or sets of the current user search questions; the generating module is used for generating a target question set according to the vector or the set of the questions; and the recommending module is used for sequencing the topics in the target topic set to obtain a recommending sequence.
According to the specific embodiment provided by the application, the application discloses the following technical effects:
in the embodiment of the application, a large amount of search question data can be matched with the questions searched by the current user, the target questions to be searched by the user are predicted by means of data mining and the like, a recommendation sequence is generated, the predicted questions can be recommended to the user by combining a recommendation function, when the recommended questions are consistent with the questions required by the user, the user can acquire answers and analysis only through a first control instruction without photographing, repairing and waiting each question by the user, the search question time of the user is greatly saved, and the recommendation sequence is generated by arranging the descending order of the click rate, so that the problem that 1-5 questions cannot be acquired in time when the user uses different auxiliary materials due to single recommendation content is avoided.
Of course, it is not necessary for any one product to practice the application to achieve all of the advantages set forth above at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a diagram illustrating a related art user selecting topic information;
FIG. 2 is a diagram of providing answers and resolution to a user in the related art;
FIG. 3 is a flow chart of a method of topic prediction in accordance with an embodiment of the present application;
FIG. 4 is a flow chart of a method of topic prediction in accordance with one embodiment of the present application;
FIG. 5 is a schematic diagram of a search topic vector of the present application;
FIG. 6 is a flow chart of a method of topic prediction in accordance with another embodiment of the present application;
FIG. 7 is a flow chart of a method of topic prediction in accordance with yet another embodiment of the present application;
FIG. 8 is a schematic diagram of the current subject matter in one embodiment of the application;
FIG. 9 is a schematic diagram of a subject matter in an embodiment of the application;
FIG. 10 is a schematic diagram of a recommendation interface in accordance with an embodiment of the present application;
FIG. 11 is a schematic illustration of a recommendation interface in accordance with another embodiment of the present application;
fig. 12 is a block diagram of the topic prediction device of the present embodiment.
Detailed Description
It should be noted that, in the related art, the shooting search is generally implemented based on a camera module, a text recognition module and a search module. Specifically, when a user is required to take a picture and search for a question, at this time, a camera module provides a shooting service such as focusing for the user, and at the same time, the user is required to select a frame in a shooting area and a picture area to select a portion only including the question information, as shown in fig. 1. And then the text recognition module extracts the characters in the pictures obtained by photographing, so that the search module can search in the database according to the characters extracted by the text recognition module, and a return interface shown in fig. 2 is obtained.
However, in the related art, there are drawbacks as follows: 1) The inquiry time is longer: the user is required to take a picture of the target title before searching, so that each title is subjected to the processes of taking a picture, identifying texts and searching; 2) The operation cost is higher: in the photographing process, a user is required to photograph the photo, and frame selection operation is also required to be carried out on the photographed photo, so that the complexity of the user is increased; 3) Strongly dependent OCR results: recognition results of OCR (Optical Character Recognition ) often result in returning results that are inconsistent with the original questions due to errors in user operation, such as incomplete questions, unclear questions, meaningless information being taken, and the like.
Therefore, these problems seriously affect the user's experience of using the photographing and searching function, not only waste time, but also easily return to erroneous results, and thus improvement is required.
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which are derived by a person skilled in the art based on embodiments of the application, fall within the scope of protection of the application.
FIG. 3 is a flow chart of a method of topic prediction in accordance with an embodiment of the present application. As shown in fig. 1, the title prediction method includes:
s101: a vector or set of current user search topics is obtained.
It should be noted that the present application is proposed based on the existing method for searching questions, and when obtaining the questions of the current user searching questions, the method can be implemented by the user through a camera module, a text recognition module and a search module in the related technology.
Further, the vector or set of current user search topics may be a vector or set of current user search topic processes, i.e., the content of the current user search topics may be nodes in the vector or points in the set, and the order of the current user search topics may be the order of the nodes in the direction or set of the vector.
S102: and generating a target question set according to the vector or the set of the questions.
In this embodiment, as shown in fig. 4, the generating a target topic set according to the vector or the set of topics may further include:
s201: and acquiring search question data.
The search question data comprise at least one question content and search question sequence in the user history search question process.
When each user searches questions through the question searching application program, the current questions searched through shooting and the sequence of continuous search questions are stored, a large number of user question searching contents and question searching sequences generate question searching data, and the volume of the question searching data is huge along with the increase of the question searching users and the increase of the operation time of the question searching application program.
It should be further noted that, the search question data may also be pre-stored by a developer in advance. In this embodiment, acquiring the search question data further includes: and (3) reducing the dimension of the search question data by using a graph-based data mining method and a network representation method to obtain a search question vector.
The nodes of the search question vector can be question information, and the direction of the search question vector can be the search question sequence.
For example, as shown in FIG. 5, the order in which the user is entitled in the order of the order number plus or minus may be expressed by the search topic vector, respectively. It should be understood that in the prior art, the contents of questions in many tutoring materials are the same and are distinguished only by changing the sequence of questions, so that the question sequence of the user can be determined more simply by adopting the mode of searching the question vector without knowing the contents of the tutoring materials of the user.
S202: in the search question data, according to the inverted index and the similarity search, a search question sequence similar to the vector or the collection of questions is obtained, the questions after the current questions in the search question sequence are extracted to be used as target questions, and the target question collection is generated.
That is, after the search question data is obtained, according to the history learning behavior of at least one user and the result of the latest shooting search question, the search question sequence similar to the vector or the set of the search questions of the user is obtained first by using the inverted index and the similarity searching mode, then the questions in the sequence after the current question are extracted, so that the questions possibly needed to be shot and solved by the current user are recalled from the search question data, and the set of the questions is taken as the target question set.
Specifically, firstly, due to the huge quantity of search question data and the irregularity of search questions of a user, the search question data is required to be subjected to dimension reduction to obtain search question vectors, then inverted indexes are carried out in the search question data to obtain a first candidate similar target question set, and after the obtained first candidate similar target question set is obtained, the first candidate similar question set is screened to obtain a second candidate similar question set. Further, combining similarity calculation to obtain a final target question set.
S103: and sequencing the topics in the target topic collection to obtain a recommendation sequence.
In this embodiment, as shown in fig. 6, the ranking of the topics in the target topic set to obtain the recommendation sequence may further include:
s301: training the search question data to generate a click rate prediction model.
It should be noted that, a deep learning model may be constructed according to the above-mentioned search question data, that is, a click rate prediction model may be generated according to the search question data, where the question content and the search question sequence are used as inputs, and the click rate of each question as a target question is used as an output.
S302: and predicting the click rate of the target title according to the title and the click rate prediction model.
S303: and generating a recommendation sequence according to the preset click rate sequence.
Specifically, the topics searched by the current user are input into the click rate prediction model, the click rates of a plurality of target topics possibly appearing behind the topics can be obtained, and then a recommendation sequence is generated according to the sequence of the preset click rates.
In the embodiment of the present application, the click rate order may be a descending order, that is, the recommendation sequence is generated according to the descending order of the click rate, in other words, the title of the first bit in the recommendation sequence is the title with the highest click rate.
In the embodiment of the application, after the recommended sequence is obtained, a preset number of target topics can be displayed to the current user according to the recommended sequence.
For example, one question may be presented at a time in the interface, and the user may change the question by turning a page (selecting the next question or changing the question), or one to five questions may be presented at a time in the interface. It should be appreciated that in order to be able to fully present the content of the title to the user in the display interface, it is preferable to recommend one title at a time in the interface.
In this embodiment, when a title is displayed in the interface once, as shown in fig. 7, the method further includes:
s401: and acquiring a control instruction of the current user.
S402: and when the control instruction is a first control instruction, providing the answer and analysis of the current display question for the current user.
S403: and when the control instruction is a second control instruction, replacing the current display title for the current user.
Specifically, referring to fig. 8, when the interface recommends a question for the user, a first control command button and a second control command button may be simultaneously presented under the interface, where the first control command may be a view button, specifically, may be represented by words such as "see", "determine", "analyze", etc., and the second control command may be a page-turning button, specifically, may be represented by words such as "change a question", "page-turning", "next question". When the user clicks the first control command button, the user selects and analyzes the currently recommended title, at this time, the answer and analysis of the currently recommended title are shown for the user, and when the user clicks the second control command button, the currently recommended title is not the title selected by the user, and the next recommended title for the user needs to be continued according to the recommendation sequence.
It should be appreciated that the presentation of the predicted title is exited after a preset number of presentation titles are replaced to the current user and/or upon the user's exit instruction being obtained.
That is, when presenting the recommended questions to the current user, if the user obtains that the questions in the recommended sequence are not the questions that the user wants to search by turning pages, the user can automatically exit the presentation interface and return to the photographing and searching interface, or if the user inputs an exit instruction, the user can also exit the presentation interface and return to the photographing and searching interface.
Further, before presenting the preset number of target topics to the current user according to the recommendation sequence, the method further comprises: and acquiring a control instruction of the current user for providing the target title.
That is, while the answer and analysis of the current question are performed, a control button for example, to "re-shoot a question" may be further provided, so that when the user triggers the control button, a control instruction that the user needs to provide the target question is obtained, and at this time, the user may directly recommend the target question to the user without taking a picture, as shown in fig. 8-10.
Therefore, the method for predicting the topics can predict the target topics to be searched by the user through a large number of search topic data and the topics searched by the current user in a data processing mode, generates a recommendation sequence, and can recommend the predicted topics to the user by combining a recommendation function, when the recommended topics are consistent with the topics required by the user, the user can acquire answers and analysis through only a first control instruction without photographing, repairing and waiting each topic by the user, so that the search topic time of the user is greatly saved, and 1-5 topics can be recommended to the user through the recommendation sequence arranged in descending order, so that the problem that the topics cannot be acquired in time when the user uses different auxiliary materials due to single recommendation content is avoided.
It should be understood that after acquiring the title searched by the current user, the method further includes: and providing answers and resolution of the questions for the current user.
That is, after the user uses the photographing function to search questions each time, the answer and the analysis of the current search questions are provided for the user, so that the function of searching the questions is realized.
According to another embodiment of the present application, as shown in fig. 11, the method comprises the steps of:
s501: the user performs shooting and searching.
S502: and displaying and analyzing the question answers.
S503: judging whether the user clicks to beat a question again.
If yes, step S504 is performed, and if no, the process ends.
S504: and displaying the recommended target topics.
S505: it is determined whether the user clicks to see.
If yes, return to step S502; if not, step S506 is performed.
S506: and displaying the next target title.
S507: it is determined whether the user clicks to see.
If yes, return to step S502; if not, step S501 is performed.
Specifically, after the user enters the application program, shooting and searching questions are performed first, and question answers and analysis are displayed to the user. Then, judging whether the user clicks to shoot a question again, when the user selects to shoot a question again, indicating that the user needs to continue searching the question, at this time, displaying recommended target questions to the user, so as to save the time of shooting the question searching of the user, avoiding the problems of fuzzy shooting, picture completion and the like, then judging whether the user clicks to see, if so, indicating that the recommended questions accord with the user's selection, continuing to display answers and analysis of the recommended questions for the user, if not, displaying next target questions for the user, giving a plurality of selected spaces for the user, and if the questions in the recommendation list are all questions which are not needed by the user, returning to shooting the question searching, wherein the user can still search the questions through the function of shooting the question searching.
Fig. 12 is a block diagram of the topic prediction device of the present embodiment. As shown in fig. 11, the topic prediction apparatus 100 includes: the system comprises an acquisition module 10, a generation module 20 and a recommendation module 30.
The acquisition module 10 is used for acquiring a vector or a set of current user search questions; the generating module 20 is configured to generate a target topic set according to the vector or the set of topics; the recommendation module 30 is configured to sort topics in the target topic collection to obtain a recommendation sequence.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is similar to a method embodiment, the description is relatively simple, and reference is made to the description of the method embodiment for relevant points. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present application without undue burden.
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other. In view of the foregoing, this description should not be construed as limiting the application.
Claims (8)
1. A method for predicting a topic, comprising:
acquiring a vector or a set of search topics of a current user;
generating a target question set according to the vector or the set of the questions;
sequencing the topics in the target topic collection to obtain a recommendation sequence;
the generating a target question set according to the question vector or the question set specifically comprises the following steps:
acquiring search question data, wherein the search question data comprises at least one question content and a search question sequence in a user history search question process;
in the search question data, according to inverted index and similarity search, obtaining a search question sequence similar to the vector or the collection of the questions, extracting the questions after the current questions in the search question sequence as target questions, and generating a target question collection;
the obtaining the search question data further comprises:
performing dimension reduction on the search question data by using a graph-based data mining method and a network representation learning method to obtain a search question vector;
the nodes of the question searching vector are question information, and the direction of the question searching vector is the question searching sequence.
2. The method of claim 1, wherein the ranking the topics in the target set of topics to obtain a recommendation sequence further comprises:
training the search question data to generate a click rate prediction model;
predicting the click rate of the target title according to the title and the click rate prediction model;
and generating the recommendation sequence according to a preset click rate sequence.
3. The topic prediction method of claim 1 further comprising:
and displaying a preset number of target topics to the current user according to the recommendation sequence.
4. The topic prediction method of claim 3, further comprising, when the preset number is greater than one:
simultaneously displaying the preset number of topics to a user; or (b)
One title is presented to the user at a time.
5. The method of claim 3, further comprising, when each time a question is presented to a user:
acquiring a control instruction of the current user;
when the control instruction is a first control instruction, providing an answer and analysis of a current display question for the current user;
and when the control instruction is a second control instruction, replacing the current display title for the current user.
6. The method of claim 3, further comprising, prior to presenting a preset number of target topics to the current user according to the recommendation sequence:
and acquiring a control instruction of the current user for providing the target title.
7. The topic prediction method of claim 3, further comprising:
and after replacing a preset number of display questions for the current user and/or when a user exit instruction is acquired, exiting the display of the predicted questions.
8. A topic prediction apparatus comprising:
the acquisition module is used for acquiring vectors or sets of the current user search questions;
the generating module is used for generating a target question set according to the vector or the set of the questions;
the recommendation module is used for sequencing the topics in the target topic collection to obtain a recommendation sequence;
the generation module is specifically configured to obtain question searching data, where the question searching data includes at least one question content and a question searching sequence in a user history question searching process; in the search question data, according to inverted index and similarity search, obtaining a search question sequence similar to the vector or the collection of the questions, extracting the questions after the current questions in the search question sequence as target questions, and generating a target question collection; the obtaining the search question data further comprises: performing dimension reduction on the search question data by using a graph-based data mining method and a network representation learning method to obtain a search question vector; the nodes of the question searching vector are question information, and the direction of the question searching vector is the question searching sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910211883.3A CN111723231B (en) | 2019-03-20 | 2019-03-20 | Question prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910211883.3A CN111723231B (en) | 2019-03-20 | 2019-03-20 | Question prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111723231A CN111723231A (en) | 2020-09-29 |
| CN111723231B true CN111723231B (en) | 2023-10-17 |
Family
ID=72562416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910211883.3A Active CN111723231B (en) | 2019-03-20 | 2019-03-20 | Question prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111723231B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110021019A (en) * | 2009-08-25 | 2011-03-04 | (주)윕스 | Apparatus and method for recommending of search formula |
| 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 |
| JP2016040660A (en) * | 2014-08-12 | 2016-03-24 | 日本電信電話株式会社 | Content recommendation device, content recommendation method, and content recommendation program |
| CN106651696A (en) * | 2016-11-16 | 2017-05-10 | 福建天泉教育科技有限公司 | Approximate question push method and system |
| CN106875309A (en) * | 2017-04-01 | 2017-06-20 | 福建云课堂教育科技有限公司 | A kind of course recommends method and system |
| CN107292785A (en) * | 2017-06-27 | 2017-10-24 | 北京粉笔蓝天科技有限公司 | One kind is set a question method and system |
| CN107562769A (en) * | 2017-05-24 | 2018-01-09 | 广东工业大学 | A kind of online answer topic recommends method and device |
| CN108062333A (en) * | 2016-11-08 | 2018-05-22 | 小船出海教育科技（北京）有限公司 | The treating method and apparatus of problem data inferior |
| CN108171629A (en) * | 2017-12-28 | 2018-06-15 | 北京中税网控股股份有限公司 | A kind of course recommends method and device |
| CN108287900A (en) * | 2018-01-23 | 2018-07-17 | 广东小天才科技有限公司 | A kind of hand-held photographing device searches topic method, system and hand-held photographing device |
| CN108304562A (en) * | 2018-02-08 | 2018-07-20 | 广东小天才科技有限公司 | One kind searching topic method, searches topic device and intelligent terminal |
| CN109271401A (en) * | 2018-09-26 | 2019-01-25 | 杭州大拿科技股份有限公司 | Method, apparatus, electronic equipment and storage medium are corrected in a kind of search of topic |
| CN109325132A (en) * | 2018-12-11 | 2019-02-12 | 平安科技（深圳）有限公司 | Expertise recommended method, device, computer equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5048852B2 (en) * | 2011-02-25 | 2012-10-17 | 楽天株式会社 | Search device, search method, search program, and computer-readable recording medium storing the program |
| US20140186817A1 (en) * | 2012-12-31 | 2014-07-03 | Fujitsu Limited | Ranking and recommendation of open education materials |
| CN105630946B (en) * | 2015-12-23 | 2019-03-19 | 百度在线网络技术（北京）有限公司 | A kind of field intersection recommended method and device based on big data |
| KR101816665B1 (en) * | 2016-02-25 | 2018-01-09 | (주)뤼이드 | Method, apparatus and computer program for analysis educational data of multiple-choice question |
-
2019
- 2019-03-20 CN CN201910211883.3A patent/CN111723231B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110021019A (en) * | 2009-08-25 | 2011-03-04 | (주)윕스 | Apparatus and method for recommending of search formula |
| JP2016040660A (en) * | 2014-08-12 | 2016-03-24 | 日本電信電話株式会社 | Content recommendation device, content recommendation method, and content recommendation program |
| 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 |
| CN108062333A (en) * | 2016-11-08 | 2018-05-22 | 小船出海教育科技（北京）有限公司 | The treating method and apparatus of problem data inferior |
| CN106651696A (en) * | 2016-11-16 | 2017-05-10 | 福建天泉教育科技有限公司 | Approximate question push method and system |
| CN106875309A (en) * | 2017-04-01 | 2017-06-20 | 福建云课堂教育科技有限公司 | A kind of course recommends method and system |
| CN107562769A (en) * | 2017-05-24 | 2018-01-09 | 广东工业大学 | A kind of online answer topic recommends method and device |
| CN107292785A (en) * | 2017-06-27 | 2017-10-24 | 北京粉笔蓝天科技有限公司 | One kind is set a question method and system |
| CN108171629A (en) * | 2017-12-28 | 2018-06-15 | 北京中税网控股股份有限公司 | A kind of course recommends method and device |
| CN108287900A (en) * | 2018-01-23 | 2018-07-17 | 广东小天才科技有限公司 | A kind of hand-held photographing device searches topic method, system and hand-held photographing device |
| CN108304562A (en) * | 2018-02-08 | 2018-07-20 | 广东小天才科技有限公司 | One kind searching topic method, searches topic device and intelligent terminal |
| CN109271401A (en) * | 2018-09-26 | 2019-01-25 | 杭州大拿科技股份有限公司 | Method, apparatus, electronic equipment and storage medium are corrected in a kind of search of topic |
| CN109325132A (en) * | 2018-12-11 | 2019-02-12 | 平安科技（深圳）有限公司 | Expertise recommended method, device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 赵晓峰.面向基础教育题库的推荐系统.中国优秀硕士学位论文全文数据库_信息科技辑.2018,I138-1926. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111723231A (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101278406B1 (en) | System and method for assisting search requests with vertical suggestions | |
| US20200193382A1 (en) | Employment resource system, method and apparatus | |
| US9576305B2 (en) | Detecting competitive product reviews | |
| CN110909145B (en) | Training method and device for multi-task model | |
| CN111061946A (en) | Scenario content recommendation method and device, electronic equipment and storage medium | |
| US20110191336A1 (en) | Contextual image search | |
| US11544135B2 (en) | Systems and methods for the analysis of user experience testing with AI acceleration | |
| CN108153915B (en) | Internet-based educational information rapid acquisition method | |
| CN112749328B (en) | Searching method, searching device and computer equipment | |
| CN111723231B (en) | Question prediction method and device | |
| CN110188277B (en) | Resource recommendation method and device | |
| US11909100B2 (en) | Systems and methods for the analysis of user experience testing with AI acceleration | |
| CN111581435A (en) | Video cover image generation method and device, electronic equipment and storage medium | |
| US10489460B2 (en) | Method and apparatus for providing local search suggestion | |
| CN115269961A (en) | Content search method and related device | |
| US11494793B2 (en) | Systems and methods for the generation, administration and analysis of click testing | |
| CN114245232A (en) | Video abstract generation method and device, storage medium and electronic equipment | |
| EP4014115A1 (en) | Systems and methods for the analysis of user experience testing with ai acceleration | |
| CN115130453A (en) | Interactive information generation method and device | |
| CN111104026A (en) | Method and device for recommending service | |
| CN111523028A (en) | Data recommendation method, device, equipment and storage medium | |
| CN112257438B (en) | Language knowledge processing method and device with association mechanism | |
| CN113205091B (en) | Question identification method, device, equipment and medium | |
| CN116775813B (en) | Service searching method, device, electronic equipment and readable storage medium | |
| KR101791086B1 (en) | Mind Mining Analysis Method Using Links Between View Data |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230612 Address after: 6001, 6th Floor, No.1 Kaifeng Road, Shangdi Information Industry Base, Haidian District, Beijing, 100085 Applicant after: Beijing Baige Feichi Technology Co.,Ltd. Address before: 100085 4th floor, Huiyuan development building, 1 Kaifa Road, Haidian District, Beijing Applicant before: XIAOCHUANCHUHAI EDUCATION TECHNOLOGY (BEIJING) CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |