CN108897860A - Information-pushing method, device, electronic equipment and computer readable storage medium - Google Patents
Information-pushing method, device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN108897860A CN108897860A CN201810699428.8A CN201810699428A CN108897860A CN 108897860 A CN108897860 A CN 108897860A CN 201810699428 A CN201810699428 A CN 201810699428A CN 108897860 A CN108897860 A CN 108897860A
- Authority
- CN
- China
- Prior art keywords
- processed
- relevant information
- information
- similarity value
- target object
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of information-pushing method, device, electronic equipment and computer readable storage medium, the information-pushing method, including：Obtain the relevant information of object to be processed；Relevant information based on object to be processed filters out at least one target object with the object matching to be processed；And the relevant information of at least one target object filtered out is pushed.In the application, the accurate push for the relevant information for treating process object is realized.
Description
Technical field
This application involves technical field of data processing, more particularly to a kind of information-pushing method, device, electronic equipment and
Computer readable storage medium.
Background technique
Scientific cooperation recommendation be it is a kind of using the existing science and technology information resource such as paper, patent be Research Management or research
The method that personnel recommend the researcher of their Focus Areas, it can help them quickly to find and understand that field is relevant to grind
Study carefully personnel and research contents, promotes to carry out further exchange and cooperation, bring better knowledge and resource-sharing, improve scientific research matter
Amount accelerates scientific research process, obtains bigger scientific achievement.
Scientific cooperation is divided into whole cooperation and two class of complementary cooperation, the former refer in entire cooperative process between individual it is close
Cooperation, each other it is assumed that respecting each other, trusting, joint development, these partners generally fall into common research neck for verifying mutually
Domain；The latter emphasizes the complementarity of knowledge or technical ability from each other, and cooperation interdisciplinary belongs to such mostly.
For whole cooperation, i.e. cooperation between the same or similar scholar of research field.The recommended method of such cooperation
It is often based on Scientific Articles or patent data, is mainly had based in author's (inventor) cooperative relationship and author (inventor) research
Hold two class recommended methods, the former emphasizes the proximity of social relationships, and the partner of recommendation often mutually recognizes, understands, and is easy to produce
Raw practical cooperation, problem be more effectively promote the researcher of different background to cooperate, and the latter is based on research contents, can be compared with
Avoid social relationships bring well and recommends problem.
Based on the method for author's cooperative relationship, usually using author as node, using the cooperative relationship between author as side, establishes and make
Person's cooperative network, with methods of social network, especially link prediction technique, according to indexs various in network, prediction is worked as
It is preceding do not connect while node future generate even while a possibility that, recommended according to prediction result, basic procedure such as Fig. 1 institute
Show.However this method generally is suitable for the network of connection, it is relatively poor for the prediction effect of not connected network, and recommend to be based on section
Society relationship between personnel is ground, the scientific research personnel of recommendation is not necessarily identical research field, helps researcher limited.
Method based on content is mainly the professional knowledge content according to researcher, is dug using data mining and text
The technologies such as pick are recommended.Its basic thinking of the recommended method is, from the text envelope of the delivered scientific achievement of researcher
Breath indicates to set out, and characterizes the research contents of author using high frequency words or keyword building model, and then obtain studying between author
Similarity, to be recommended according to similarity.Mainly from keyword level with TF-IDF LDA topic model etc.
The research contents of author is characterized, basic procedure is as shown in Figure 2.However this kind of method usually requires first to extract keyword or height
Frequency word, and then recommended with TF-IDF etc., such method less focuses on semantic feature, and the keyword of selection is different surely fine
Characterization article content, keyword number, stop words selection can all influence recommendation effect；LDA(Latent
Dirichlet Allocation, document subject matter generate model) topic model needs to be previously set different theme quantity, passes through
Selection optimum value is run multiple times, and each run requires successive ignition, time-consuming.For different field, the above method will be weighed
It newly selects different keywords or rebuilds new model, usual complexity is high, low efficiency, is not suitable for processing large data.
Summary of the invention
The application provides information-pushing method, device, electronic equipment and computer readable storage medium, treats place to realize
Manage the accurate push of the relevant information of object.
In a first aspect, this application provides a kind of information-pushing methods, including：
Obtain the relevant information of object to be processed；
Relevant information based on object to be processed filters out at least one target object with the object matching to be processed；
And the relevant information of at least one target object filtered out is pushed.
Second aspect, this application provides a kind of information push-delivery apparatus, including：
Acquiring unit, for obtaining the relevant information of object to be processed；
Screening unit is filtered out with the object matching to be processed at least for the relevant information based on object to be processed
One target object；
Push unit is used for and pushes the relevant information of at least one target object filtered out.
The third aspect, this application provides a kind of computer readable storage medium, on the computer readable storage medium
It is stored with computer program, which realizes above-mentioned information-pushing method when being executed by processor.
Fourth aspect, this application provides a kind of electronic equipment, including：Processor, memory, communication interface and communication are total
Line, the processor, the memory and the communication interface complete mutual communication by the communication bus；
The memory executes the processor for storing at least one executable instruction, the executable instruction
The corresponding operation of the information-pushing method stated.
Compared with prior art, the application has at least the following advantages：
Obtain the relevant information of object to be processed；And the relevant information of the object to be processed based on the acquisition is filtered out and is somebody's turn to do
At least one target object of object matching to be processed；And then by the relevant information of at least one target object filtered out into
Row push, realizes the accurate push for the relevant information for treating process object.
Detailed description of the invention
Fig. 1 is the scientific cooperation recommended method flow chart based on cooperative relationship of the application provided in the prior art；
Fig. 2 is the scientific cooperation recommended method flow chart based on research contents of the application provided in the prior art；
Fig. 3 is the flow chart of information-pushing method provided by the embodiment of the present application；
Fig. 4 is the specific processing flow schematic diagram of information-pushing method provided by the embodiments of the present application；
Fig. 5 is the flow diagram for the information-pushing method that the application specific embodiment provides；
Fig. 6 is the flow diagram of scientific research personnel library building provided by the embodiments of the present application；
Fig. 7 is the flow diagram of text sparse distribution formula characterization generating process provided by the embodiments of the present application；
Fig. 8 is the flow diagram of scientific research personnel's feature database building provided by the embodiments of the present application；
Fig. 9 is the flow diagram that scientific cooperation provided by the embodiments of the present application is recommended；
Figure 10 is the structural schematic diagram of information push-delivery apparatus provided by the embodiments of the present application；
Figure 11 is the structural schematic diagram of the electronic equipment provided by the embodiments of the present application based on data push method.
Specific embodiment
The application proposes a kind of information-pushing method, device and storage medium, with reference to the accompanying drawing, specifically real to the application
The mode of applying is described in detail.
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the application, and cannot be construed to the limitation to the application.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in the description of the present application
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or wirelessly coupling.It is used herein to arrange
Diction "and/or" includes one or more associated wholes for listing item or any cell and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term), there is meaning identical with the general understanding of those of ordinary skill in the application fields.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless idealization or meaning too formal otherwise will not be used by specific definitions as here
To explain.
To keep the purposes, technical schemes and advantages of the application clearer, below in conjunction with attached drawing to the application embodiment party
Formula is described in further detail.
As shown in figure 3, being the flow diagram of information-pushing method provided by the present application, this method comprises the following steps：
Step S301 obtains the relevant information of object to be processed；
Step S302, the relevant information based on object to be processed filter out at least one with the object matching to be processed
Target object；
Step S303 pushes the relevant information of at least one target object filtered out.
In the present embodiment, by the relevant information for obtaining object to be processed；And the phase of the object to be processed based on the acquisition
Close at least one target object of information sifting out with the object matching to be processed；And then at least one target for filtering out this
The relevant information of object is pushed, and the accurate push for the relevant information for treating process object is realized.
Based on technical solution provided by above-mentioned the embodiment of the present application, below with a specific embodiment to the technical solution
Exhaustive is carried out, as shown in figure 4, being the specific process flow diagram of information-pushing method provided by the embodiments of the present application, the party
Method includes：
Step S401 obtains the relevant information of object to be processed.
In this step, the relevant information of object to be processed is obtained, including：
Obtain the identification information of the object to be processed；
Preset characteristics of objects database is inquired based on the identification information, obtains the correlation of the object to be processed
Information.
Step S402 determines similarity value based on the relevant information of object to be processed.
In this step, similarity value is determined based on the relevant information of object to be processed, including：
Relevant information traverse object property data base based on object to be processed, determines the relevant information of the object to be processed
The similarity value of relevant information corresponding with object each in characteristics of objects database.
Step S403 filters out at least one target pair with the object matching to be processed based on determining similarity value
As.
In this step, which may include following any mode：
(1) determining each similarity value is screened based on default similarity threshold；
The corresponding object of each similarity value institute for being greater than default similarity threshold is chosen as target object.
In this way, a default similarity threshold is configured, the default similarity threshold and determination based on the configuration
Each similarity value is compared, and determines the size relation of each similarity value Yu the similarity threshold；It filters out and is greater than the default phase
Like the similarity value of degree threshold value, and object corresponding to each similarity value filtered out is determined as target object.
(2) it is ranked up based on determining each similarity value size；
Sequence based on each similarity value successively chooses the corresponding object of preset quantity similarity value institute as mesh
Mark object.
In this way, it is ranked up based on each similarity value size of the determination, sortord can be by big
Be arranged successively to small, be also possible to it is ascending be arranged successively, do not limit its specific arrangement mode certainly；With it is descending according to
For secondary arrangement, quantity configuration is chosen based on preparatory similarity value, in each similarity value according to size order arrangement
Preset quantity similarity value is successively chosen, and object corresponding to each similarity value filtered out is determined as target pair
As.
Wherein, for above-mentioned characteristics of objects database, building process includes：
The relevant information of the object is determined based on the corresponding relationship of preset object and text data；
Characteristics of objects database is constructed based on the relevant information of determining each object.
Wherein, the corresponding relationship based on preset object and text data determines the relevant information of the object, packet
It includes：
The text data of the object is determined based on the corresponding relationship of preset object and text data；
The corresponding sparse distribution formula characterization of each word for forming the text data is determined based on the text data；
And each word for forming the text data corresponding sparse distribution formula characterization is merged, obtain the object
Relevant information.
Further, the relevant information in the application is that the sparse distribution formula of existing object characterizes vector.
Step S404 pushes the relevant information of at least one target object filtered out.
Specifically, the relevant information of each target object filtered out is pushed, so that receiving end can be based on
The relevant information of each target object filtered out is target object needed for the object select to be processed as partner.
In the application, the relevant information based on object to be processed carries out corresponding profession matching, recommends, and realizes to target
The accurate push of the relevant information of object.
For technical solution provided by above-mentioned the embodiment of the present application, detailed explain is carried out with a specific embodiment below
It states, in this specific embodiment, above- mentioned information method for pushing can be divided into five processing steps, as shown in figure 5, specifically including：
The first step, data prediction.Firstly, obtained from database the whole papers of certain field within a certain period of time and specially
Sharp data reject duplicate data；Secondly, to paper text data (title, abstract, text) and patent text data (mark
Topic, abstract, claim, specification) it is extracted；Finally, extracting author (inventor) data, and save author (inventor)
With the corresponding relationship of text.
Second step establishes scientific research personnel library.The author's name of extraction and name of inventor are disambiguated respectively first.Wherein make
The disambiguation of person's name can use the progress of paper data, and name of inventor, which disambiguates, can use patent data progress, then to belonging to
Same mechanism, author of the same name and inventor merge, i.e., they are the same scientific research personnel, finally merge whole authors and
Inventor forms scientific research personnel library.
In this step, scientific research personnel generally includes the author of paper and the inventor of patent.Make firstly, being extracted from paper
The name of person disambiguates author's name using author's name's disambiguation algorithm and paper data；Inventor is extracted from patent
Name, name of inventor is disambiguated using name of inventor's disambiguation algorithm and patent data.Will through disambiguate treated
Author's name and name of inventor merge, and using the scientific research institution library of building, will be in same mechanism, with the scientific research people of name
Member merges into scientific research personnel's processing, and data that treated form scientific research personnel library；Scientific research is had recorded in the scientific research personnel library
The name of personnel, the paper delivered, Patent and cooperative relationship, process flow such as Fig. 6.
Third step establishes text feature library.The paper text data of extraction and patent text data are merged, still
Retain the relationship between scientific research personnel and content of text, text is indicated with sparse distribution formula characterization, it is special to form text
Levy library.
In this step, the generation in text feature library is based on the paper text data and patent text data after merging.Paper
Text data has extracted the autograph, abstract or text of paper, denomination of invention, abstract, the power of patent text data pick-up patent
Benefit requirement, patent specification.It can individually select abstract or text as text, it can also be plus topic, or by three
It is combined together as the text of a paper, the method that the present invention selects does not need to segment text data, removes and stop
The processing such as word, word frequency statistics can be characterized directly by specified text generation sparse distribution formula, specifically：According to the text of selection
This range, determines the bigger corpus comprising the text, corpus all in corpus is cut into independent text piece
Section, is arranged in two-dimensional matrix, so that the identical text (very more comprising identical word number between text fragments) of expression theme
Segment is located at the same position in matrix, and position of the text fragments on matrix similar in theme is close, in such corpus
Each word corresponds to this two-dimensional matrix, wherein the numerical value on the text fragments corresponding position comprising this word is 1, it is no
It is then 0, in a row by obtained matrix conversion, i.e. the form of vector notices that the vector is higher-dimension and sparse, that is, the word
Sparse distribution formula characterization.The sparse distribution formula for forming each word of text characterization is merged, and is guaranteed dilute after merging
Degree (value is ratio shared by the component of " 1 ") is dredged in the range of restriction, when degree of rarefication is more than threshold value, is gone out by " 1 " at each
The height of occurrence number is retained, to guarantee that degree of rarefication is limiting in range, to obtain the sparse distribution formula table of full text
Sign, forms text feature library, and process flow is as shown in Figure 7.
4th step establishes scientific research personnel's feature database.First according to the relationship of scientific research personnel and text in text feature library, obtain
To the relevant full text of each scientific research personnel (text of the paper text delivered or the patent of application), then by these texts
Sparse distribution formula characterizes (sparse distributed representations, SDR) and carries out join operation, obtains scientific research people
The sparse distribution formula characterization of member, to indicate the research contents of scientific research personnel；The sparse distribution formula of whole scientific research personnel, which characterizes, to be constituted
Scientific research personnel feature database.
In this step, using the scientific research personnel library and text feature library of building, obtain belonging to each scientific research personnel's
The sparse distribution formula of full text (text of its paper delivered and the patent of application) characterizes, by each scientific research personnel whole
Text sparse distribution formula characterize merge, and ensure that synthesis sparse distribution formula characterization vector sparse degree, when vector not
When enough sparse (excessive " 1 "), preferentially remain on the position repeated in multiple text sparse distribution formula characterization vectors
" 1 " is characterized using finally obtained sparse distribution formula characterization vector as the sparse distribution formula of scientific research personnel, by whole scientific research personnel
Sparse distribution formula characterization constitute scientific research personnel's feature database, as shown in Figure 8.
5th step, scientific cooperation are recommended.It is characterized according to the sparse distribution formula of scientific research personnel and carries out similarity calculation, according to meter
It calculates result and carries out descending arrangement, the corresponding scientific research personnel of top N chosen in arrangement recommends as a result.
In this step, after obtaining scientific research personnel's feature database, the sparse distribution formula for therefrom extracting scientific research personnel characterizes vector,
And it is ranked up, recommended according to the similarity that sparse distribution formula characterizes vector.
In specific recommendation process, to choose partner for researcher A, then in scientific research personnel's feature database
Selection carries out similarity calculation with researcher A each scientific research personnel never cooperated respectively, due to sparse distribution formula
Characterizing vector, each has specific semantic, and " 1 " of same position is more, shows that vector is more close semantically, therefore can be with
The number that same position is all " 1 " is directlyed adopt, that is, is overlapped number to carry out similarity calculation, conventional similarity measurements also may be selected
Amount such as Jaccard similarity, Euclidean distance etc. do not limit the similarity calculating method.Certainly, regardless of which kind of side used
Method, it is clear that similarity is higher, and the research contents of scientific research personnel is more similar, more meaningful to recommended, as shown in Figure 9.
Based on above-mentioned information-pushing method provided herein, present invention also provides a kind of information push-delivery apparatus, such as
Shown in Figure 10, including：
Acquiring unit 1001, for obtaining the relevant information of object to be processed；
Screening unit 1002 filters out and the object matching to be processed for the relevant information based on object to be processed
At least one target object；
Push unit 1003 is used for and pushes the relevant information of at least one target object filtered out.
Acquiring unit 1001, specifically for obtaining the identification information of the object to be processed；Based on the identity mark
Know information and inquire preset characteristics of objects database, obtains the relevant information of the object to be processed.
Screening unit 1002, for determining similarity value based on the relevant information of object to be processed；And based on determining phase
At least one target object with the object matching to be processed is filtered out like angle value.
Screening unit 1002 is determined specifically for the relevant information traverse object property data base based on object to be processed
The similarity value of the relevant information of the object to be processed relevant information corresponding with object each in the characteristics of objects database.
Screening unit 1002 screens determining each similarity value also particularly useful for based on default similarity threshold；
The corresponding object of each similarity value institute for being greater than default similarity threshold is chosen as target object.
Screening unit 1002 is ranked up also particularly useful for based on determining each similarity value size；Based on each similarity
The sequence of value successively chooses the corresponding object of preset quantity similarity value institute as target object.
Wherein, the relevant information is that the sparse distribution formula of existing object characterizes vector.
The embodiment of the present application provides a kind of electronic equipment, and as shown in figure 11, electronic equipment 2000 shown in Figure 11 includes：
Processor 2001 and transceiver 2004.Wherein, processor 2001 is connected with transceiver 2004, is such as connected by bus 2002.It can
Choosing, electronic equipment 2000 can also include memory 2003.It should be noted that transceiver 2004 is not limited in practical application
One, the structure of the electronic equipment 2000 does not constitute the restriction to the embodiment of the present application.
Wherein, processor 2001 is applied in the embodiment of the present application, for realizing screening unit 1002 shown in Fig. 10
Function.Transceiver 2004 includes Receiver And Transmitter, and transceiver 2004 is applied in the embodiment of the present application, for realizing Fig. 3
Shown in acquiring unit 1001 function.
Processor 2001 can be CPU, general processor, DSP, ASIC, FPGA or other programmable logic device, crystalline substance
Body pipe logical device, hardware component or any combination thereof.It, which may be implemented or executes, combines described by present disclosure
Various illustrative logic blocks, module and circuit.Processor 2001 is also possible to realize the combination of computing function, such as wraps
It is combined containing one or more microprocessors, DSP and the combination of microprocessor etc..
Bus 2002 may include an access, and information is transmitted between said modules.Bus 2002 can be pci bus or
Eisa bus etc..Bus 2002 can be divided into address bus, data/address bus, control bus etc..Only to be used in Figure 11 convenient for indicating
One thick line indicates, it is not intended that an only bus or a type of bus.
Memory 2003 can be ROM or can store the other kinds of static storage device of static information and instruction, RAM
Or the other kinds of dynamic memory of information and instruction can be stored, it is also possible to EEPROM, CD-ROM or other CDs
Storage, optical disc storage (including compression optical disc, laser disc, optical disc, Digital Versatile Disc, Blu-ray Disc etc.), magnetic disk storage medium
Or other magnetic storage apparatus or can be used in carry or store have instruction or data structure form desired program generation
Code and can by any other medium of computer access, but not limited to this.
Optionally, memory 2003 is used to store the application code for executing application scheme, and by processor 2001
It is executed to control.Processor 2001 is real shown in Figure 10 to realize for executing the application code stored in memory 2003
The movement of the information push-delivery apparatus of example offer is provided.
The embodiment of the present application provides a kind of computer readable storage medium, stores on the computer readable storage medium
There is computer program, which realizes above-mentioned information-pushing method when being executed by processor.
Those skilled in the art of the present technique be appreciated that can be realized with computer program instructions these structure charts and/or
The combination of each frame and these structure charts and/or the frame in block diagram and/or flow graph in block diagram and/or flow graph.This technology neck
Field technique personnel be appreciated that these computer program instructions can be supplied to general purpose computer, special purpose computer or other
The processor of programmable data processing method is realized, to pass through the processing of computer or other programmable data processing methods
The scheme specified in frame or multiple frames of the device to execute structure chart and/or block diagram and/or flow graph disclosed in the present application.
Wherein, the modules of the application device can integrate in one, can also be deployed separately.Above-mentioned module can close
And be a module, multiple submodule can also be further split into.
It will be appreciated by those skilled in the art that attached drawing is the schematic diagram of a preferred embodiment, module or stream in attached drawing
Journey is not necessarily implemented necessary to the application.
It will be appreciated by those skilled in the art that the module in device in embodiment can describe be divided according to embodiment
It is distributed in the device of embodiment, corresponding change can also be carried out and be located in one or more devices different from the present embodiment.On
The module for stating embodiment can be merged into a module, can also be further split into multiple submodule.
Above-mentioned the application serial number is for illustration only, does not represent the advantages or disadvantages of the embodiments.
The above disclosure is just a few specific examples of the present application, still, the application is not limited to this, any ability
What the technical staff in domain can think variation should all fall into the protection scope of the application.
Claims (12)
1. a kind of information-pushing method, which is characterized in that including：
Obtain the relevant information of object to be processed；
Relevant information based on object to be processed filters out at least one target object with the object matching to be processed；
And the relevant information of at least one target object filtered out is pushed.
2. the method as described in claim 1, which is characterized in that the relevant information for obtaining object to be processed, including：
Obtain the identification information of the object to be processed；
Preset characteristics of objects database is inquired based on the identification information, obtains the related letter of the object to be processed
Breath.
3. method according to claim 1 or 2, which is characterized in that the relevant information based on object to be processed filters out
With at least one target object of the object matching to be processed, including：
Similarity value is determined based on the relevant information of object to be processed；
And at least one target object with the object matching to be processed is filtered out based on determining similarity value.
4. method as claimed in claim 3, which is characterized in that the relevant information based on object to be processed determines similarity
Value, including：
Relevant information traverse object property data base based on object to be processed, determine the relevant information of the object to be processed with
The similarity value of the corresponding relevant information of each object in the characteristics of objects database.
5. method as claimed in claim 4, which is characterized in that based on determining similarity value filter out with it is described to be processed right
As at least one matched target object, specifically include：
Determining each similarity value is screened based on default similarity threshold；
The corresponding object of each similarity value institute for being greater than default similarity threshold is chosen as target object.
6. method as claimed in claim 4, which is characterized in that based on determining similarity value filter out with it is described to be processed right
As at least one matched target object, specifically include：
It is ranked up based on determining each similarity value size；
Sequence based on each similarity value successively chooses the corresponding object of preset quantity similarity value institute as target pair
As.
7. the method as described in any one of claim 2-6, which is characterized in that the building of the characteristics of objects database
Journey, including：
The relevant information of the object is determined based on the corresponding relationship of preset object and text data；
Characteristics of objects database is constructed based on the relevant information of determining each object.
8. the method for claim 7, which is characterized in that the corresponding relationship based on preset object and text data
Determine the relevant information of the object, including：
The text data of the object is determined based on the corresponding relationship of preset object and text data；
The corresponding sparse distribution formula characterization of each word for forming the text data is determined based on the text data；
And each word for forming the text data corresponding sparse distribution formula characterization is merged, obtain the correlation of the object
Information.
9. such as method of any of claims 1-8, which is characterized in that the relevant information is the sparse of existing object
Distribution characterization vector.
10. a kind of information push-delivery apparatus, which is characterized in that including：
Acquiring unit, for obtaining the relevant information of object to be processed；
Screening unit, for the relevant information based on object to be processed filter out with the object matching to be processed at least one
Target object；
Push unit is used for and pushes the relevant information of at least one target object filtered out.
11. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, the program realize information-pushing method of any of claims 1-9 when being executed by processor.
12. a kind of electronic equipment, which is characterized in that including：Processor, memory, communication interface and communication bus, the processing
Device, the memory and the communication interface complete mutual communication by the communication bus；
The memory makes the processor execute such as right for storing at least one executable instruction, the executable instruction
It is required that the corresponding operation of information-pushing method described in any one of 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810699428.8A CN108897860B (en) | 2018-06-29 | 2018-06-29 | Information pushing method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810699428.8A CN108897860B (en) | 2018-06-29 | 2018-06-29 | Information pushing method and device, electronic equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108897860A true CN108897860A (en) | 2018-11-27 |
| CN108897860B CN108897860B (en) | 2022-05-27 |
Family
ID=64347374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810699428.8A Active CN108897860B (en) | 2018-06-29 | 2018-06-29 | Information pushing method and device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108897860B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110941662A (en) * | 2019-06-24 | 2020-03-31 | 上海市研发公共服务平台管理中心 | Graphical method, system, storage medium and terminal for scientific research cooperative relationship |
| CN111931059A (en) * | 2020-08-19 | 2020-11-13 | 创新奇智(成都)科技有限公司 | Object determination method and device and storage medium |
| CN112202889A (en) * | 2020-09-30 | 2021-01-08 | 深圳前海微众银行股份有限公司 | Information pushing method and device and storage medium |
| CN112612817A (en) * | 2020-12-07 | 2021-04-06 | 深圳价值在线信息科技股份有限公司 | Data processing method and device, terminal equipment and computer readable storage medium |
| CN114579871A (en) * | 2022-05-06 | 2022-06-03 | 南京因由数字科技有限公司 | Recommendation method and device based on patent information, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815297A (en) * | 2016-12-09 | 2017-06-09 | 宁波大学 | A kind of academic resources recommendation service system and method |
| CN107465766A (en) * | 2017-09-21 | 2017-12-12 | 掌阅科技股份有限公司 | Information-pushing method, electronic equipment and computer-readable storage medium |
-
2018
- 2018-06-29 CN CN201810699428.8A patent/CN108897860B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815297A (en) * | 2016-12-09 | 2017-06-09 | 宁波大学 | A kind of academic resources recommendation service system and method |
| CN107465766A (en) * | 2017-09-21 | 2017-12-12 | 掌阅科技股份有限公司 | Information-pushing method, electronic equipment and computer-readable storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110941662A (en) * | 2019-06-24 | 2020-03-31 | 上海市研发公共服务平台管理中心 | Graphical method, system, storage medium and terminal for scientific research cooperative relationship |
| CN111931059A (en) * | 2020-08-19 | 2020-11-13 | 创新奇智(成都)科技有限公司 | Object determination method and device and storage medium |
| CN112202889A (en) * | 2020-09-30 | 2021-01-08 | 深圳前海微众银行股份有限公司 | Information pushing method and device and storage medium |
| CN112202889B (en) * | 2020-09-30 | 2023-05-23 | 深圳前海微众银行股份有限公司 | Information pushing method, device and storage medium |
| CN112612817A (en) * | 2020-12-07 | 2021-04-06 | 深圳价值在线信息科技股份有限公司 | Data processing method and device, terminal equipment and computer readable storage medium |
| CN112612817B (en) * | 2020-12-07 | 2024-02-27 | 深圳价值在线信息科技股份有限公司 | Data processing method, device, terminal equipment and computer readable storage medium |
| CN114579871A (en) * | 2022-05-06 | 2022-06-03 | 南京因由数字科技有限公司 | Recommendation method and device based on patent information, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108897860B (en) | 2022-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108897860A (en) | Information-pushing method, device, electronic equipment and computer readable storage medium | |
| Garimella et al. | Quantifying controversy on social media | |
| CN106776711B (en) | Chinese medical knowledge map construction method based on deep learning | |
| Omar et al. | Multi-label arabic text classification in online social networks | |
| Hinde et al. | Bidirectional citation searching to completion: an exploration of literature searching methods | |
| Jäschke et al. | Tag recommendations in folksonomies | |
| JP2022133385A (en) | System for inferring temporal signal showing remarkable relation between visualization of semantic information and life science entity, method, and computer readable medium | |
| CN106055539B (en) | The method and apparatus that name disambiguates | |
| CA2903889C (en) | System and method for natural language processing | |
| Shams et al. | A non-parametric LDA-based induction method for sentiment analysis | |
| Kumara et al. | Web-service clustering with a hybrid of ontology learning and information-retrieval-based term similarity | |
| CN109472021A (en) | Critical sentence screening technique and device in medical literature based on deep learning | |
| Nicholls et al. | Understanding news story chains using information retrieval and network clustering techniques | |
| Chopra et al. | Sentiment analyzing by dictionary based approach | |
| TW201415254A (en) | Method and system for recommending semantic annotations | |
| Bettencourt-Silva et al. | Discovering new social determinants of health concepts from unstructured data: framework and evaluation | |
| Efron et al. | Building topic models in a federated digital library through selective document exclusion | |
| CN105205075B (en) | From the name entity sets extended method of extension and recommended method is inquired based on collaboration | |
| CN104008097A (en) | Method and device for achieving query understanding | |
| Xu et al. | Measuring semantic relatedness between flickr images: from a social tag based view | |
| CN110781211B (en) | Data analysis method and device | |
| KR20160136014A (en) | Method and system for topic clustering of big data | |
| Luo et al. | Automatic structuring of ontology terms based on lexical granularity and machine learning: Algorithm development and validation | |
| Pazos Arias et al. | A multi-criteria approach for automatic ontology recommendation using collective knowledge | |
| Chiatti et al. | Reducing the search space in ontology alignment using clustering techniques and topic identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |