CN109657150A - A method of target literature register is pushed to target user - Google Patents
A method of target literature register is pushed to target user Download PDFInfo
- Publication number
- CN109657150A CN109657150A CN201811594254.5A CN201811594254A CN109657150A CN 109657150 A CN109657150 A CN 109657150A CN 201811594254 A CN201811594254 A CN 201811594254A CN 109657150 A CN109657150 A CN 109657150A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- digraph
- target
- target user
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of method for pushing target literature register to target user, the described method includes: obtaining data set to be analyzed, the corresponding theme of each element in the data set to be analyzed, it include a kind of data and two class data in each element, one kind data are the data relevant to the theme directly issued, and the two classes data are the comment data for a kind of data;Digraph is constructed for each element in the data set to be analyzed, obtains directed graph set;Each digraph in the directed graph set is analyzed, the temperature user of the corresponding digraph is chosen;For any two digraph, identical temperature user, then regard as target user for the temperature user if it exists;Obtain the information reader of target user;Target literature register is issued to the target user according to the information reader.The present invention has intelligence degree height, target user's accurate positioning, multiple remarkable advantages such as applied widely.
Description
Technical field
The present invention relates to the communications field more particularly to a kind of methods for pushing target literature register to target user.
Background technique
In internet area, information, which pushes, has become a highly important research topic, and the positioning of target user
Precision can largely determine the success rate of information push.For example, advertisement, lives if target user does not have
Jump property personality, is all not very concerned about, then the effect of obvious advertisement will be not satisfactory even for anything.For this purpose, for
The acquisition of target user is the technical task for having higher market value and application value, however, shortage pair in the prior art
The relevant technologies of precise positioning are carried out in target user.
In addition, obtaining the various aspects such as behavior pattern, preference, interest, the habit of user by the analysis for mass data
Information, so that providing more humanized service for user is the highly desirable technical effect reached of people.But existing skill
But lack the excavation for target user's information, parser in art, it is difficult to which the preference that therefrom automatically abstracting goes out target user is practised
It is used to wait significant datas, it is also difficult to provide more intelligentized service for target user.
Summary of the invention
In order to solve the above technical problem, the present invention provides a kind of methods for pushing target literature register to target user.
The present invention is realized with following technical solution:
A method of target literature register is pushed to target user, comprising:
Data set to be analyzed is obtained, each element corresponds to a theme in the data set to be analyzed, wraps in each element
A kind of data and two class data are included, one kind data are the data relevant to the theme directly issued, the two classes number
According to for the comment data for a kind of data;
Digraph is constructed for each element in the data set to be analyzed, obtains directed graph set;
Each digraph in the directed graph set is analyzed, the temperature user of the corresponding digraph is chosen;
For any two digraph, identical temperature user, then regard as target for the temperature user and use if it exists
Family;
Obtain the information reader of target user;
Target literature register is issued to the target user according to the information reader.
Further, the information reader includes the academic background of reader, borrows documentation & info, recommend documentation & info, comment
Documentary Information;The academic background includes the education level and the corresponding profession coding of highest educational background of reader;Wherein, described
Profession is encoded to six digit word strings, meets the regulation of subject classification and code national standard.
Further, each element building digraph in the data set to be analyzed includes:
A kind of data and two class data in each element are obtained, and construct digraph, the digraph can be expressed
For wherein representing a kind of number that two class data of user identifier publication issue another user identifier for user identifier
According to comment relationship;
Calculate the sincere degree weight and support weight of each edge in digraph G;
According to the comprehensive weight on side described in the sincere degree weight and the support weight calculation.
It further, further include the choosing method of temperature user, comprising:
Initialize the hot value on each vertex in digraph;
Arbitrarily one vertex of selection, according to the current fever thermometer on the vertex and each related top for being directed toward the vertex
Temperature after the iteration on the vertex is calculated, and using temperature after the iteration as the current temperature on the vertex;
Continue to calculate the current temperature on other vertex according to above-mentioned steps, until in the digraph each vertex it is current
Temperature tends towards stability;
Choose temperature user of the maximum N number of user of current temperature as the digraph.
Further, target user then issues preset target literature register to the target user, if institute if one
State target user be it is multiple, then using the information reader of single target user as element, constitute a source information collection.
It further, further include the method that target literature register is issued to the target user according to source information collection, comprising:
To the either objective element that the source information is concentrated, obtain between the object element and related non-targeted element
The degree of correlation.
Target literature register is issued to the corresponding target user of the object element according to the degree of correlation.
Further, it is concentrated from the source information and obtains the corresponding all related non-targeted element of the object element;
Obtain the academic degree of correlation between object element and each related non-targeted element;
Obtain the life degree of correlation between object element and each related non-targeted element;
Obtain the synthesis pertinence between object element and each related non-targeted element;
It is related non-targeted element sequence according to the sequence of synthesis pertinence from high to low, obtains sequencing table.
It is further, described to issue target literature register to the corresponding target user of the object element according to the degree of correlation,
Include:
Obtaining the top n element in sequencing table is to recommend element;
Obtain the recommendation documentation & info of the corresponding target user of each recommendation element;
It is obtained recommending document record sheet according to the recommendation documentation & info, the recommendation document record sheet includes recommending document
With the recommended number for recommending document, the record recommended in document record sheet according to recommended number from high to low
Sequence arranges;
It chooses and the preceding T recommendation document in document record sheet is recommended to constitute target literature register;
The target literature register is distributed to the corresponding target user of object element.
In the description of the invention, it is to be understood that term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description the invention and simplifies description, rather than indicate
Or imply that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore cannot understand
For the limitation to the invention.In addition, term " first ", " second " etc. are used for description purposes only, and should not be understood as indicating
Or it implies relative importance or implicitly indicates the quantity of indicated technical characteristic." first ", " second " etc. are defined as a result,
Feature can explicitly or implicitly include one or more of the features.In the description of the invention, unless separately
It is described, the meaning of " plurality " is two or more.
In the description of the invention, it should be noted that unless otherwise clearly defined and limited, term " peace
Dress ", " connected ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integrally
Connection;It can be mechanical connection, be also possible to be electrically connected;Can be directly connected, can also indirectly connected through an intermediary,
It can be the connection inside two elements.For the ordinary skill in the art, on being understood by concrete condition
State concrete meaning of the term in the invention.
The beneficial effects of the present invention are:
The embodiment of the invention provides a kind of methods for pushing target literature register to target user, can be to be analyzed
Precise positioning goes out for each higher user of theme participation in data set, and then is filtered out and have by way of taking intersection
The user of activity personality, this certain customers is higher generally for fangle acceptance, can be used as push relevant information
Target user, the present invention can also carry out data analysis only by the information reader for target user, can be full automatic
Recommend document for target user, improves the reading experience of target user, have preferable market value.
Detailed description of the invention
Fig. 1 is a kind of method flow diagram that target literature register is pushed to target user provided in this embodiment;
Fig. 2 is the flow chart that each element provided in this embodiment in the data set to be analyzed constructs digraph;
Fig. 3 is the flow chart for the method that weight is sincerely spent in quantization provided in this embodiment;
Fig. 4 is the flow chart of the method for quantization support weight provided in this embodiment;
Fig. 5 is the choosing method flow chart of temperature user provided in this embodiment.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, the present invention will be made below further detailed
Description.
The embodiment of the present invention provides a kind of method for pushing target literature register to target user, as shown in Figure 1, the side
Method includes:
S101. data set to be analyzed is obtained, the corresponding theme of each element, each element in the data set to be analyzed
In include a kind of data and two class data, one kind data are the data relevant to the theme directly issued, described two
Class data are the comment data for a kind of data.
S102. digraph is constructed for each element in the data set to be analyzed, obtains directed graph set.
S103. each digraph in the directed graph set is analyzed, the temperature for choosing the corresponding digraph is used
Family.
The temperature user may be considered that temperature relevant with theme where the digraph is relatively high, compared with influence power
Big user.
S104. for any two digraph, identical temperature user, then regard as mesh for the temperature user if it exists
Mark user.
Single theme is analyzed, can only obtain the general temperature situation of single theme, selected part temperature is used
Family, but temperature user not necessarily high quality user, the reason is that, temperature user may be very special only for some
Theme it is interested, it is other to be indifferent to without exception, also seldom participate in, for this temperature user, if as target user to
It, which pushes other information, such as advertisement, books, document, video, music etc., may all be unable to get preferable push effect, because
This, innovatively accounts for from multiple themes in the embodiment of the present invention, and at least two themes actively will be joined
With user regard as target user, the embodiment of the present invention thinks, user can be illustrated to a certain extent by participating in multiple themes
For activity personality, relevant information is pushed to it will obtain preferably push effect.
S105. the information reader of target user is obtained.
The information reader includes the academic background of reader, borrows documentation & info, recommends documentation & info, comment document letter
Breath.Specifically, the academic background includes the education level and the corresponding profession coding of highest educational background of reader.Wherein, described
Profession is encoded to six digit word strings, meets the regulation of subject classification and code national standard.For example, reader " Zhang Shengnan " is most
Well educated is master, and it is engineering (08)-computer (0809)-network engineering (080903) that profession is learned during master.Then
The profession coding of " Zhang Shengnan " is 080903.
S106. target literature register is issued to the target user according to the information reader.
Further, it is as shown in Figure 2 to construct digraph for each element in the data set to be analyzed, comprising:
S1021. a kind of data and two class data in each element are obtained, and construct digraph G, the digraph can be with
It is represented as G={ V, E }, wherein V is user identifier, and E represents two class data of user identifier publication to another user
Identify the comment relationship of a kind of data of publication.
For example, if user spark has issued an a kind of data, user tony, samby and dazzi carry out it
Comment has then obtained including four vertex, the data network elements of three directed edges, and directed edge is to be directed toward spark from tony,
Samby is directed toward three sides that spark and dazzi is directed toward spark.The direction of directed edge institute is directed toward by the user for issuing two class data
State the user of the corresponding a kind of data of two class data.
It specifically, may include the use of two class data of multiple users for issuing a kind of data and multiple publications in digraph
Family, and the user that the user for issuing a kind of data can also simultaneously as two class data of publication, the embodiment of the present invention do not limit
The specific generation method of digraph.
S1022. the sincere degree weight and support weight of each edge in digraph G are calculated.
Specifically, the weight of each edge is evaluated in the embodiment of the present invention in terms of sincere degree and support two.Sincerely degree
The number of words of the reply of end user is measured by each edge starting user, the embodiment of the present invention thinks that the number of words replied is got over
It is more, indicate that the answer of starting user more has sincerity.Support is by each edge starting user in the reply of end user
The sentiment analysis result of appearance is measured, if the content of the reply of starting user has more front color, support is higher,
Conversely, support angle.
Specifically, the embodiment of the present invention further provides the method that weight is sincerely spent in quantization, as shown in Figure 3, comprising:
S1. sincere metrization table is constructed, the sincere metrization table includes that number of words section and the number of words section are corresponding
Sincerely degree weight.
For example, number of words in 1-50, then sincerely degree weight is 0.2, if number of words, in 50-100, sincerely spending weight is 0.5, if
Number of words is greater than 100, then sincerely degree weight is 1.
S2. starting user is obtained in each edge to the number of words of the reply of end user.
S3. the number of words section where the number of words is inquired according to the sincere metrization table, and it is corresponding sincerely to obtain its
Spend weight.
Specifically, the embodiment of the present invention further provides the method for quantization support weight, as shown in Figure 4, comprising:
S10. according to starting user in preset emotion word lists extraction each edge to the target in the reply of end user
Emotion word.
Specifically, the emotion word lists can be configured previously according to big data statistical result, the emotion word
Table has recorded emotion word and the corresponding weight of emotion word, the emotion word include certainly word, negative word and in
Vertical word, wherein the weight of neutral word is 0.5, the weight of word negates the weight of word greater than 0.5 less than 0.5 certainly.
Such as negative word " idiot " respective weights 0.9, it negate word " small fool " respective weights 0.6.Weight is heavier, then
The negative tone of negative word is fiercer.For example word " is absolutely correct " respective weights 0.4 certainly, word " should to " is right certainly
Answer weight 0.3.Weight is heavier, then the affirmative tone of word is fiercer certainly.
S20. the corresponding weight of target emotion word is obtained.
S30. take the total value of the corresponding weight of target complete emotion word as support weight.
S1023. the comprehensive weight on the side according to the sincere degree weight and the support weight calculation.
Specifically, the comprehensive weight=α sincerely spends weight+β support weight.α and β is adjustment parameter, can basis
Actual conditions are adjusted, but its total value is 1.
Specifically, the embodiment of the present invention is before step 103, and there are one the steps that digraph simplifies.Because if starting point
User has carried out multiple reply to end user, then starting user direction a plurality of of end user can be generated in digraph G to be had
First digraph is simplified for the ease of the screening of later period temperature user to line segment so that starting user and end user it
Between a plurality of directed line segment merge into a directed line segment, the comprehensive weight of the directed line segment after the merging is more before merging
The total value of the weight of directed line segment.
Further, the choosing method of temperature user is provided in the embodiment of the present invention, as shown in Figure 5, comprising:
S1031. the hot value on each vertex in digraph is initialized.
Initial hot value is 1. in the embodiment of the present invention
S1032. a vertex is arbitrarily selected, according to the current of each related top on the vertex and the direction vertex
Temperature calculates temperature after the iteration on the vertex, and using temperature after the iteration as the current temperature on the vertex.
Specifically, after iteration temperature hot value according to formulaWherein h
(v) be the vertex current temperature, h (u) is directed to the current temperature of the related top on the vertex, and h ' (v) is the top
Temperature after the iteration of point, χ is adjustment factor, identifies degree the considerations of for various current temperatures, and U is each of the vertex
The set that related top is constituted, Z (u- > v) are temperature transmission function, the topological structure with the related top for being directed toward the vertex
It is related.
In a feasible embodimentWherein QuvThe directed line of vertex v is directed toward for vertex u
The comprehensive weight of section, ∑ QuThe total value of all comprehensive weights of the directed line segment of related other nodes is directed toward for vertex u.
S1033. continue to calculate the current temperature on other vertex according to the method for step S1032, until in the digraph
The current temperature on each vertex tends towards stability.
Specifically, the sequencing of temperature can be different according to the actual situation after each vertex calculating iteration, this hair
Bright embodiment does not limit it clearly.The current hot value to tend towards stability before and after iteration is less than preset threshold.
S1034. temperature user of the maximum N number of user of current temperature as the digraph is chosen.
Specifically, N can be configured according to actual needs.
The embodiment of the invention provides a kind of methods for obtaining target user, can be precisely fixed in data set to be analyzed
Position goes out for each higher user of theme participation, and then the use with activity personality is filtered out by way of taking intersection
Family, this certain customers is higher generally for fangle acceptance, can be used as the target user of push relevant information, the present invention
Intelligent Target user's acquisition methods that embodiment provides have intelligence degree height, and accurate positioning is applied widely etc. multiple aobvious
Write advantage.
Target user in step S104 then issues preset target literature register to the target user if one,
If the target user be it is multiple, using the information reader of single target user as element, constitute a source information collection, this hair
Bright embodiment further provides the method for issuing target literature register to the target user according to source information collection, comprising:
S1061. the either objective element concentrated to the source information, obtains the object element and related non-targeted element
Between the degree of correlation.
S1062. target literature register is issued to the corresponding target user of the object element according to the degree of correlation.
Specifically, the degree of correlation obtained between the object element and related non-targeted element, comprising:
S10611. it is concentrated from the source information and obtains the corresponding all related non-targeted element of the object element.
It specifically, can be non-targeted according to the corresponding correlation of the acquisition object element of the education level in reader's academic background
Element.Under normal conditions, education level is related to reading taste and reading content, therefore from the identical reader of education level
Middle carry out relatedness computation, the target literature register obtained from are more reasonable.
Reader in the embodiment of the present invention in related non-targeted element and object element has identical education level.
S10612. the academic degree of correlation between object element and each related non-targeted element is obtained.
Specifically, the academic degree of correlation is related with the profession coding of target user, for science in the embodiment of the present invention
The degree of correlation is defined as follows:Wherein, Sm(u, v) identifies two elements u, v
Between the academic degree of correlation.
S10613. the life degree of correlation between object element and each related non-targeted element is obtained.
Specifically, the life degree of correlation describe each target user for being derived from the reading habit of target user it
Between the degree of correlation.The life degree of correlation is defined as follows:
Wherein, a is document, BuIt (a) is member
The document that the corresponding target user of plain u borrowed, Cu(a) document commented on for the corresponding target user of element u, RuIt (a) is member
The document that the corresponding target user of plain u recommended.
S10614. the synthesis pertinence between object element and each related non-targeted element is obtained.
Specifically, the synthesis pertinence=μ science degree of correlation+λ life degree of correlation.Wherein μ and λ is weight coefficient,
It can be configured according to the actual situation, but the total value of μ and λ is always 1.
S10615. it is that related non-targeted element sorts according to the sequence of synthesis pertinence from high to low, obtains sequencing table.
Specifically, described to issue target literature register, packet to the corresponding target user of the object element according to the degree of correlation
It includes:
S10621. obtaining the top n element in sequencing table is to recommend element.
S10622. the recommendation documentation & info of the corresponding target user of each recommendation element is obtained.
S10623. it is obtained recommending document record sheet according to the recommendation documentation & info, the recommendation document record sheet includes
Recommend document and it is described recommend document recommended number, it is described recommend document record sheet in record according to recommended number by
High to low sequence arrangement.
For example, there is the corresponding target user of M recommendation element to recommend the same document, then the recommended number of the document
As M.
S10624. it chooses and the preceding T recommendation document in document record sheet is recommended to constitute target literature register.
S10625. the target literature register is distributed to the corresponding target user of object element.
The embodiment of the present invention has preferable intelligence, carries out data point only by the information reader for target user
Analysis full automatic can recommend document for target user, improve the reading experience of target user, have preferable market price
Value.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of method for pushing target literature register to target user characterized by comprising
Data set to be analyzed is obtained, each element corresponds to a theme in the data set to be analyzed, includes one in each element
Class data and two class data, one kind data are the data relevant to the theme directly issued, and the two classes data are
For the comment data of a kind of data;
Digraph is constructed for each element in the data set to be analyzed, obtains directed graph set;
Each digraph in the directed graph set is analyzed, the temperature user of the corresponding digraph is chosen;
For any two digraph, identical temperature user, then regard as target user for the temperature user if it exists;
Obtain the information reader of target user;
Target literature register is issued to the target user according to the information reader.
2. according to the method described in claim 1, it is characterized by:
The information reader includes the academic background of reader, borrows documentation & info, recommends documentation & info, comment documentation & info;Institute
State the education level and the corresponding profession coding of highest educational background that academic background includes reader;Wherein, the profession is encoded to six
Digit word string meets the regulation of subject classification and code national standard.
3. according to the method described in claim 1, it is characterized by:
Each element in the data set to be analyzed constructs digraph
A kind of data and two class data in each element are obtained, and construct digraph, the digraph can be represented as,
In be user identifier, represent commenting for a kind of data that two class data of user identifier publication issue another user identifier
By relationship;
Calculate the sincere degree weight and support weight of each edge in digraph G;
According to the comprehensive weight on side described in the sincere degree weight and the support weight calculation.
4. method according to claim 1, which is characterized in that further include the choosing method of temperature user, comprising:
Initialize the hot value on each vertex in digraph;
Arbitrarily one vertex of selection calculates institute according to the current temperature of the vertex and each related top for being directed toward the vertex
Temperature after the iteration on vertex is stated, and using temperature after the iteration as the current temperature on the vertex;
Continue to calculate the current temperature on other vertex according to above-mentioned steps, until in the digraph each vertex current temperature
It tends towards stability;
Choose temperature user of the maximum N number of user of current temperature as the digraph.
5. method according to claim 1, it is characterised in that:
Target user then issues preset target literature register to the target user, if the target user is if one
It is multiple, then using the information reader of single target user as element, constitute a source information collection.
6. method according to claim 5, it is characterised in that:
It further include the method that target literature register is issued to the target user according to source information collection, comprising:
To the either objective element that the source information is concentrated, the correlation between the object element and related non-targeted element is obtained
Degree.
Target literature register is issued to the corresponding target user of the object element according to the degree of correlation.
7. method according to claim 6, it is characterised in that:
It is concentrated from the source information and obtains the corresponding all related non-targeted element of the object element;
Obtain the academic degree of correlation between object element and each related non-targeted element;
Obtain the life degree of correlation between object element and each related non-targeted element;
Obtain the synthesis pertinence between object element and each related non-targeted element;
It is related non-targeted element sequence according to the sequence of synthesis pertinence from high to low, obtains sequencing table.
8. method according to claim 7, it is characterised in that:
It is described to issue target literature register to the corresponding target user of the object element according to the degree of correlation, comprising:
Obtaining the top n element in sequencing table is to recommend element;
Obtain the recommendation documentation & info of the corresponding target user of each recommendation element;
It is obtained recommending document record sheet according to the recommendation documentation & info, the recommendation document record sheet includes recommending document and institute
State the recommended number for recommending document, sequence of the record recommended in document record sheet according to recommended number from high to low
Arrangement;
It chooses and the preceding T recommendation document in document record sheet is recommended to constitute target literature register;
The target literature register is distributed to the corresponding target user of object element.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010421457.5A CN111475734A (en) | 2018-12-25 | 2018-12-25 | Method for pushing target document directory |
CN201811594254.5A CN109657150B (en) | 2018-12-25 | 2018-12-25 | Method for pushing target document directory to target user |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811594254.5A CN109657150B (en) | 2018-12-25 | 2018-12-25 | Method for pushing target document directory to target user |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010421457.5A Division CN111475734A (en) | 2018-12-25 | 2018-12-25 | Method for pushing target document directory |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109657150A true CN109657150A (en) | 2019-04-19 |
CN109657150B CN109657150B (en) | 2020-07-14 |
Family
ID=66116724
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010421457.5A Withdrawn CN111475734A (en) | 2018-12-25 | 2018-12-25 | Method for pushing target document directory |
CN201811594254.5A Active CN109657150B (en) | 2018-12-25 | 2018-12-25 | Method for pushing target document directory to target user |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010421457.5A Withdrawn CN111475734A (en) | 2018-12-25 | 2018-12-25 | Method for pushing target document directory |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN111475734A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2579189A1 (en) * | 2011-10-06 | 2013-04-10 | Thomson Licensing | Method and apparatus for generating an explanation for a recommendation |
CN103399883A (en) * | 2013-07-19 | 2013-11-20 | 百度在线网络技术(北京)有限公司 | Method and system for performing personalized recommendation according to user interest points/concerns |
CN106055627A (en) * | 2016-05-27 | 2016-10-26 | 西安电子科技大学 | Recognition method of key nodes of social network in topic field |
-
2018
- 2018-12-25 CN CN202010421457.5A patent/CN111475734A/en not_active Withdrawn
- 2018-12-25 CN CN201811594254.5A patent/CN109657150B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2579189A1 (en) * | 2011-10-06 | 2013-04-10 | Thomson Licensing | Method and apparatus for generating an explanation for a recommendation |
CN103399883A (en) * | 2013-07-19 | 2013-11-20 | 百度在线网络技术(北京)有限公司 | Method and system for performing personalized recommendation according to user interest points/concerns |
CN106055627A (en) * | 2016-05-27 | 2016-10-26 | 西安电子科技大学 | Recognition method of key nodes of social network in topic field |
Non-Patent Citations (2)
Title |
---|
搜狐: "连定位目标受众都不会?你的Facebook广告费都打水漂了!", 《HTTPS://WWW.SOHU.COM/A/245516412_99997247》 * |
林泽鸿: "基于论坛活跃用户的图书推荐研究", 《图书馆理论与实践》 * |
Also Published As
Publication number | Publication date |
---|---|
CN111475734A (en) | 2020-07-31 |
CN109657150B (en) | 2020-07-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Hakim | ‘The Spornosexual’: the affective contradictions of male body-work in neoliberal digital culture | |
Ellis et al. | The quest for ground truth in musical artist similarity | |
Pocock et al. | Choosing and Using Citizen Science: a guide to when and how to use citizen science to monitor biodiversity and the environment | |
Steglich et al. | Applying siena | |
CN104317959B (en) | Data digging method based on social platform and device | |
CN109800390B (en) | Method and device for calculating personalized emotion abstract | |
CN101460942A (en) | Method and system for computerized searching and matching using emotional preference | |
CN105849764A (en) | Systems and methods for identifying influencers and their communities in a social data network | |
Konstantakis et al. | A personalized heritage-oriented recommender system based on extended cultural tourist typologies | |
CN110263982A (en) | The optimization method and device of ad click rate prediction model | |
CN109325171A (en) | User interest analysis method and system based on domain knowledge | |
Tian et al. | Recipe recommendation with hierarchical graph attention network | |
CN106909560A (en) | Point of interest sort method | |
de Oliveira et al. | Measuring the effects of repeated and diversified influence mechanism for information adoption on Twitter | |
Cox | Angling quality, effort response, and exploitation in recreational fisheries: field and modeling studies on British Columbia rainbow trout (Oncorhynchus mykiss) lakes | |
CN109657150A (en) | A method of target literature register is pushed to target user | |
CN109325674A (en) | Soft dress Fabric Hand Test system based on CSS theory | |
JP2019040605A (en) | Feeling interactive method based on humor creation and robot system | |
CN108446359A (en) | Information recommendation method and device | |
CN108205551A (en) | A kind of song recommendations method and song recommendations system | |
CN110442746A (en) | A kind of intelligent music method for pushing and storage medium based on random forests algorithm | |
CN109710846A (en) | A method of document register is pushed to positive target user | |
KR101402779B1 (en) | Analysis system and method for personality patterns of behavior using saju information | |
CN109766477A (en) | A method of obtaining positive target user | |
CN110472071A (en) | Multimedia file recommendation method, device, the network equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200618 Address after: No. 1688-1491 Jinshi mountain area, Shanghai Applicant after: Changyi rent network technology (Shanghai) Co., Ltd Address before: 310000 Room 209, 2nd Floor, Building 1180 Binan Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant before: HANGZHOU MINGZHIYUN EDUCATION TECHNOLOGY Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |