CN116089701A - Personalized recommendation method and device - Google Patents
Personalized recommendation method and device Download PDFInfo
- Publication number
- CN116089701A CN116089701A CN202211478596.7A CN202211478596A CN116089701A CN 116089701 A CN116089701 A CN 116089701A CN 202211478596 A CN202211478596 A CN 202211478596A CN 116089701 A CN116089701 A CN 116089701A
- Authority
- CN
- China
- Prior art keywords
- keyword
- keywords
- activation value
- links
- nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a personalized recommendation method and device, and particularly relates to the technical field of Internet. The application specifically comprises the following steps: extracting keywords from a target object text browsing record, taking the keywords as first keywords, determining the corresponding node positions of the first keywords in a preset semantic tree, wherein the preset semantic tree consists of a plurality of nodes and links among the nodes, one node corresponds to one word, the links among the nodes mark the relation among the words, selecting at least one second keyword according to the node positions corresponding to the first keywords and the preset semantic tree, recommending the text to the target object according to the at least one second keyword, expanding the keywords in a semantic manner, and recommending the user in a personalized manner according to the original keywords and the words obtained after semantic expansion, wherein the recommended content can more easily meet user preference, and the satisfaction degree of the user on personalized recommendation is improved.
Description
Technical Field
The application relates to the technical field of internet, in particular to a personalized recommendation method and device.
Background
With the rapid growth of the internet changing the nature of many businesses, the customer needs can be better understood and knowledge in terms of product and service customization integrated through the use of large amounts of transactional data collected by the information system. Personalized recommendations have the ability to provide customized content and services for individuals based on knowledge of individual preferences and behaviors, or to customize e-commerce interactions between businesses and each customer using technology and customer information. It uses profiles built from past usage behavior to provide relevant personalized recommendations.
In the prior art, a mode of extracting keywords from a historical browsing record of a user and conducting personalized recommendation on the user according to the keywords is adopted, but the personalized recommendation content is single due to the fact that the recommendation is conducted only according to the keywords, and further the defect that the requirements of the user cannot be met is overcome.
It can be seen that how to improve the satisfaction of the user with respect to the personalized recommendation is a problem to be solved by those skilled in the art.
Disclosure of Invention
In view of this, the embodiments of the present application provide a personalized recommendation method and apparatus, which aim to improve the satisfaction of users for personalized recommendation.
In a first aspect, the present application provides a personalized recommendation method, including:
extracting keywords from a target object text browsing record, and taking the keywords as first keywords;
determining the corresponding node position of the first keyword in a preset semantic tree, wherein the preset semantic tree consists of a plurality of nodes and links among the nodes, one node corresponds to one word, and the links among the nodes mark the relationship among the words;
selecting at least one second keyword according to the node position corresponding to the first keyword and the preset semantic tree;
and recommending text to the target object according to the at least one second keyword.
Optionally, the method further comprises:
recording the number of times the first keyword appears in the text browsing record;
determining an activation value of the first keyword according to the occurrence times of the first keyword in the text browsing record, wherein the activation value of the first keyword is positively correlated with the occurrence times of the first keyword in the text browsing record;
the selecting at least one second keyword according to the node position corresponding to the first keyword and the preset semantic tree includes:
determining the number of target link bars according to the activation value of the first keyword;
and selecting words corresponding to nodes with the number of the links smaller than or equal to the number of the target links, which are required by linking the nodes corresponding to the first keywords, as second keywords.
Optionally, the determining the number of the target links according to the activation value of the first keyword includes:
if the activation value of the first keyword is smaller than the first preset threshold, determining the number of target links according to the activation value of the first keyword;
if the activation value of the first keyword is greater than or equal to the first preset threshold, determining the number of target links according to the first preset threshold.
Optionally, the determining the number of the target links according to the activation value of the first keyword includes:
and when the condition that the activation value of the first keyword is larger than or equal to the second preset threshold value is met, determining the number of target link bars according to the activation value of the first keyword.
Optionally, recommending text to the target object according to the at least one second keyword includes:
constructing a keyword set according to the first keyword and the at least one second keyword;
matching to obtain texts with the times of occurrence of the keywords in the keyword set in the texts being greater than a fourth preset threshold value;
and recommending the matched text to the target object.
In a second aspect, an embodiment of the present application provides a personalized recommendation device, including:
the keyword extraction unit is used for extracting keywords from the target object text browsing record, and taking the keywords as first keywords;
the first determining unit is used for determining the node position corresponding to the first keyword in a preset semantic tree, the preset semantic tree consists of a plurality of nodes and links among the nodes, one node corresponds to one word, and the links among the nodes mark the relationship among the words;
the selecting unit is used for selecting at least one second keyword according to the node position corresponding to the first keyword and the preset semantic tree;
and the recommending unit is used for recommending the text to the target object according to the at least one second keyword.
Optionally, the apparatus further includes:
a recording unit, configured to record the number of occurrences of the first keyword in the text browsing record;
a second determining unit, configured to determine an activation value of the first keyword according to a number of occurrences of the first keyword in the text browsing record, where the activation value of the first keyword is positively correlated with the number of occurrences of the first keyword in the text browsing record;
the selecting unit is specifically configured to determine the number of target links according to the activation value of the first keyword; and selecting words corresponding to nodes with the number of the links smaller than or equal to the number of the target links, which are required by linking the nodes corresponding to the first keywords, as second keywords.
Optionally, the selecting unit is specifically configured to determine, if the activation value of the first keyword is smaller than the first preset threshold, the number of target links according to the activation value of the first keyword; if the activation value of the first keyword is greater than or equal to the first preset threshold, determining the number of target links according to the first preset threshold.
Optionally, the selecting unit is specifically configured to determine the number of target links according to the activation value of the first keyword when the condition that the activation value of the first keyword is greater than or equal to the second preset threshold is satisfied.
Optionally, the recommendation unit is specifically configured to construct a keyword set according to the first keyword and the at least one second keyword; matching to obtain texts with the times of occurrence of the keywords in the keyword set in the texts being greater than a fourth preset threshold value; and recommending the matched text to the target object.
The application discloses a personalized recommendation method, which comprises the following steps: extracting keywords from a target object text browsing record, taking the keywords as first keywords, determining the corresponding node positions of the first keywords in a preset semantic tree, wherein the preset semantic tree consists of a plurality of nodes and links among the nodes, one node corresponds to one word, the links among the nodes mark the relation among the words, selecting at least one second keyword according to the node positions corresponding to the first keywords and the preset semantic tree, recommending the text to the target object according to the at least one second keyword, expanding the keywords in a semantic manner, and recommending the user in a personalized manner according to the original keywords and the words obtained after semantic expansion, wherein the recommended content can more easily meet user preference, and the satisfaction degree of the user on personalized recommendation is improved.
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 required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a flow chart of a personalized recommendation method provided in an embodiment of the present application;
fig. 2 is a flow chart of a preset semantic tree construction method according to an embodiment of the present application;
fig. 3 is a flow chart of another personalized recommendation method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a personalized recommendation device according to an embodiment of the present application.
Detailed Description
As described above, as the rapid growth of the internet has changed the nature of many businesses, the customer needs can be better understood and knowledge in product and service customization integrated through the use of large amounts of transactional data collected by the information system. Personalized recommendations have the ability to provide customized content and services for individuals based on knowledge of individual preferences and behaviors, or to customize e-commerce interactions between businesses and each customer using technology and customer information. It uses profiles built from past usage behavior to provide relevant personalized recommendations. At present, a mode of extracting keywords from a historical browsing record of a user and conducting personalized recommendation on the user according to the keywords is generally adopted, but the personalized recommendation content is single due to the fact that the recommendation is conducted only according to the keywords, and further the defect that the requirements of the user cannot be met is overcome.
The inventor provides that keywords are firstly extracted from a target object text browsing record, the keywords are used as first keywords, then the corresponding node positions of the first keywords in a preset semantic tree are determined, wherein the preset semantic tree consists of a plurality of nodes and links among the nodes, one node corresponds to one word, the links among the nodes mark the relation among the words, at least one second keyword is selected according to the node positions corresponding to the first keywords and the preset semantic tree, and finally the text is recommended to the target object according to the at least one second keyword, so that the keywords are subjected to semantic expansion, personalized recommendation is carried out on users according to the original keywords and the words obtained after the semantic expansion, further, the recommended content can more easily meet user preference, and the satisfaction degree of the users on personalized recommendation is improved.
In order to make the present application solution better understood by those skilled in the art, the following description will clearly and completely describe the technical solution in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Referring to fig. 1, the flowchart of a personalized recommendation method provided in an embodiment of the present application includes:
s101: and extracting keywords from the target object text browsing record, and taking the keywords as first keywords.
Firstly, acquiring a text browsing record of a target object, extracting keywords corresponding to the text browsing record, wherein the extracted keywords are related to interests and hobbies of the target user, and taking the extracted keywords as first keywords, wherein the first keywords are used for recommending texts to the target object.
S102: and determining the corresponding node position of the first keyword in a preset semantic tree.
The preset semantic tree consists of a plurality of nodes and links among the nodes, one node corresponds to one word, the links among the nodes mark the relationship among the words, for example, one node in the preset semantic tree corresponds to 'basketball', and the other node corresponds to 'sport', so that the links among the two nodes mark the upper and lower positions, namely, the two words are in the upper and lower relationship;
the construction method of the preset semantic tree comprises the following steps: selecting target words and determining the relation between every two target words, wherein the relation between the words comprises the relation between upper and lower positions, semantic similarity and the like, linking all the words according to the relation between every two words, for example, as shown in fig. 2, fig. 2 is a flow diagram of a preset semantic tree construction method provided by the embodiment of the application, node a corresponds to "sports", node B corresponds to "basketball", node D corresponds to "football", firstly, determining the relation between the words corresponding to the 4 nodes, namely, the relation between the "sports" and the "basketball" is similar to the semantic of the "sports", the relation between the "sports" and the "football" is the relation between the upper and lower positions, the relation between the "sports" and the "basketball" is the relation between the upper and lower positions, and then linking the node according to the relation between the words, namely, linking the node a and the node B, linking the node a and the node C, linking the node B and the node C, and the node B and the node D, so as to obtain the preset semantic tree.
S103: and selecting at least one second keyword according to the node position corresponding to the first keyword and a preset semantic tree.
In the semantic tree, the fewer the number of links required for links between nodes, the greater the word association degree corresponding to the two nodes is, and at least one second keyword is selected according to the node position corresponding to the first keyword and a preset semantic tree.
S104: and recommending the text to the target object according to the at least one second keyword.
Firstly, constructing a keyword set according to the first keywords and the at least one second keyword, then matching to obtain texts with the times of occurrence of keywords in the keyword set in the texts being larger than a fourth preset threshold value, and finally recommending the matched texts to a target object.
In this embodiment, a personalized recommendation method is provided, including: extracting keywords from a target object text browsing record, taking the keywords as first keywords, determining the corresponding node positions of the first keywords in a preset semantic tree, wherein the preset semantic tree consists of a plurality of nodes and links among the nodes, one node corresponds to one word, the links among the nodes mark the relation among the words, selecting at least one second keyword according to the node positions corresponding to the first keywords and the preset semantic tree, recommending the text to the target object according to the at least one second keyword, expanding the keywords in a semantic manner, and recommending the user in a personalized manner according to the original keywords and the words obtained after semantic expansion, wherein the recommended content can more easily meet user preference, and the satisfaction degree of the user on personalized recommendation is improved.
Referring to fig. 3, fig. 3 is a flow chart of another personalized recommendation method provided in an embodiment of the present application, including:
the S301 embodiment corresponds to the S101 embodiment, the S302 embodiment corresponds to the S102 embodiment, and the S307 embodiment corresponds to the S104 embodiment, which will not be described here.
S303: and recording the frequency of the first keyword in the text browsing record.
And recording the occurrence times of the first keyword in the text browsing record, wherein the more the occurrence times are, the more interested the target object is in the text in which the first keyword is generated, and the more the occurrence times can show the interest degree of the target object most intuitively.
S304: and determining the activation value of the first keyword according to the occurrence times of the first keyword in the text browsing record.
And determining an activation value of the first keyword according to the occurrence times of the first keyword in the text browsing record, wherein the activation value of the first keyword is positively correlated with the occurrence times of the first keyword in the text browsing record, namely the larger the occurrence times of the first keyword in the text browsing record is, the larger the activation value of the first keyword is, and the specific relation between the occurrence times of the first keyword in the text browsing record and the activation value of the first keyword is determined according to specific situations.
S305: and determining the number of the target links according to the activation value of the first keyword.
If the activation value of the first keyword is smaller than a first preset threshold value, determining the number of target links according to the activation value of the first keyword; if the activation value of the first keyword is greater than or equal to the first preset threshold, determining the number of target links according to the first preset threshold, wherein the first preset threshold is used for limiting the maximum value of the activation value of the first keyword, and if the activation value of the first keyword is too large, selecting a second keyword which is irrelevant to the first keyword in the process of selecting the second keyword.
When the condition that the activation value of the first keyword is larger than or equal to a second preset threshold is met, determining the number of target links according to the activation value of the first keyword, wherein the second preset threshold is smaller than the first preset threshold, and when the activation value of the first keyword is smaller than the second preset threshold, the target object is not interested in the first keyword, and the second keyword is not needed to be selected.
For example, the first preset threshold is 5, the second preset threshold is 2, the number of target links is determined to be 3 when the activation value of the first keyword is 3, the number of target links is determined to be 5 when the activation value of the first keyword is 8, and the operation of determining the number of target links is not performed when the activation value of the first keyword is 1.
S306: and selecting words corresponding to nodes with the number of links smaller than or equal to the number of target links required by linking the nodes corresponding to the first keywords as second keywords.
The words corresponding to the nodes, the number of which is smaller than or equal to the number of the target links, required for linking the nodes corresponding to the first keywords are selected as the second keywords, so that the universality and the relevance of the selection of the second keywords can be ensured.
The embodiments of the present application provide some specific implementations of a personalized recommendation method, and based on this, the present application further provides a corresponding apparatus. The apparatus provided in the embodiments of the present application will be described from the viewpoint of functional modularization.
Referring to a schematic structural diagram of a personalized recommendation device shown in fig. 4, the personalized recommendation device 400 includes:
a keyword extraction unit 410, configured to extract a keyword from a target object text browsing record, and use the keyword as a first keyword;
a first determining unit 420, configured to determine a node position corresponding to the first keyword in a preset semantic tree, where the preset semantic tree is composed of a plurality of nodes and links between nodes, one of the nodes corresponds to a word, and the links between the nodes identify a relationship between the words;
a selecting unit 430, configured to select at least one second keyword according to the node position corresponding to the first keyword and the preset semantic tree;
and a recommending unit 440, configured to recommend text to the target object according to the at least one second keyword.
Optionally, the apparatus 400 further includes:
a recording unit, configured to record the number of occurrences of the first keyword in the text browsing record;
a second determining unit, configured to determine an activation value of the first keyword according to a number of occurrences of the first keyword in the text browsing record, where the activation value of the first keyword is positively correlated with the number of occurrences of the first keyword in the text browsing record;
the selecting unit 430 is specifically configured to determine the number of target links according to the activation value of the first keyword; and selecting words corresponding to nodes with the number of the links smaller than or equal to the number of the target links, which are required by linking the nodes corresponding to the first keywords, as second keywords.
Optionally, the selecting unit 430 is specifically configured to determine, if the activation value of the first keyword is smaller than the first preset threshold, the number of target links according to the activation value of the first keyword; if the activation value of the first keyword is greater than or equal to the first preset threshold, determining the number of target links according to the first preset threshold.
Optionally, the selecting unit 430 is specifically configured to determine the number of target links according to the activation value of the first keyword when the condition that the activation value of the first keyword is greater than or equal to the second preset threshold is satisfied.
Optionally, the recommending unit 440 is specifically configured to construct a keyword set according to the first keyword and the at least one second keyword; matching to obtain texts with the times of occurrence of the keywords in the keyword set in the texts being greater than a fourth preset threshold value; and recommending the matched text to the target object.
The device comprises a memory for storing instructions or code and a processor for executing the instructions or code to cause the device to perform the method according to any of the embodiments of the present application.
The computer storage medium has code stored therein that, when executed, causes an apparatus for executing the code to perform the method described in any of the embodiments of the present application.
From the above description of embodiments, it will be apparent to those skilled in the art that all or part of the steps of the above described example methods may be implemented in software plus general hardware platforms. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which may be stored in a storage medium, such as a read-only memory (ROM)/RAM, a magnetic disk, an optical disk, or the like, including several instructions for causing a computer device (which may be a personal computer, a server, or a network communication device such as a router) to perform the methods described in the embodiments or some parts of the embodiments of the present application.
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 the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. 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 invention without undue burden.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
It should be further noted that, in the present 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 the apparatus and device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The apparatus and device embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements presented 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 invention without undue burden.
The foregoing is merely one specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A personalized recommendation method, comprising:
extracting keywords from a target object text browsing record, and taking the keywords as first keywords;
determining the corresponding node position of the first keyword in a preset semantic tree, wherein the preset semantic tree consists of a plurality of nodes and links among the nodes, one node corresponds to one word, and the links among the nodes mark the relationship among the words;
selecting at least one second keyword according to the node position corresponding to the first keyword and the preset semantic tree;
and recommending text to the target object according to the at least one second keyword.
2. The method according to claim 1, wherein the method further comprises:
recording the number of times the first keyword appears in the text browsing record;
determining an activation value of the first keyword according to the occurrence times of the first keyword in the text browsing record, wherein the activation value of the first keyword is positively correlated with the occurrence times of the first keyword in the text browsing record;
the selecting at least one second keyword according to the node position corresponding to the first keyword and the preset semantic tree includes:
determining the number of target link bars according to the activation value of the first keyword;
and selecting words corresponding to nodes with the number of the links smaller than or equal to the number of the target links, which are required by linking the nodes corresponding to the first keywords, as second keywords.
3. The method of claim 2, wherein the determining the number of target links according to the activation value of the first keyword comprises:
if the activation value of the first keyword is smaller than the first preset threshold, determining the number of target links according to the activation value of the first keyword;
if the activation value of the first keyword is greater than or equal to the first preset threshold, determining the number of target links according to the first preset threshold.
4. The method of claim 2, wherein the determining the number of target links according to the activation value of the first keyword comprises:
and when the condition that the activation value of the first keyword is larger than or equal to the second preset threshold value is met, determining the number of target link bars according to the activation value of the first keyword.
5. The method of claim 1, wherein recommending text to the target object based on the at least one second keyword comprises:
constructing a keyword set according to the first keyword and the at least one second keyword;
matching to obtain texts with the times of occurrence of the keywords in the keyword set in the texts being greater than a fourth preset threshold value;
and recommending the matched text to the target object.
6. A personalized recommendation device, comprising:
the keyword extraction unit is used for extracting keywords from the target object text browsing record, and taking the keywords as first keywords;
the first determining unit is used for determining the node position corresponding to the first keyword in a preset semantic tree, the preset semantic tree consists of a plurality of nodes and links among the nodes, one node corresponds to one word, and the links among the nodes mark the relationship among the words;
the selecting unit is used for selecting at least one second keyword according to the node position corresponding to the first keyword and the preset semantic tree;
and the recommending unit is used for recommending the text to the target object according to the at least one second keyword.
7. The apparatus of claim 6, wherein the apparatus further comprises:
a recording unit, configured to record the number of occurrences of the first keyword in the text browsing record;
a second determining unit, configured to determine an activation value of the first keyword according to a number of occurrences of the first keyword in the text browsing record, where the activation value of the first keyword is positively correlated with the number of occurrences of the first keyword in the text browsing record;
the selecting unit is specifically configured to determine the number of target links according to the activation value of the first keyword; and selecting words corresponding to nodes with the number of the links smaller than or equal to the number of the target links, which are required by linking the nodes corresponding to the first keywords, as second keywords.
8. The apparatus of claim 7, wherein the selecting unit is specifically configured to determine, if the activation value of the first keyword is smaller than the first preset threshold, a target number of links according to the activation value of the first keyword; and the second link number determining subunit is configured to determine, if the activation value of the first keyword is greater than or equal to the first preset threshold, the target link number according to the first preset threshold.
9. The apparatus according to claim 4, wherein the selecting unit is specifically configured to determine the number of target links according to the activation value of the first keyword when a condition that the activation value of the first keyword is greater than or equal to the second preset threshold is satisfied.
10. The apparatus according to claim 1, wherein the recommending unit is specifically configured to construct a keyword set according to the first keyword and the at least one second keyword; matching to obtain texts with the times of occurrence of the keywords in the keyword set in the texts being greater than a fourth preset threshold value; and recommending the matched text to the target object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211478596.7A CN116089701A (en) | 2022-11-17 | 2022-11-17 | Personalized recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211478596.7A CN116089701A (en) | 2022-11-17 | 2022-11-17 | Personalized recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116089701A true CN116089701A (en) | 2023-05-09 |
Family
ID=86198177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211478596.7A Pending CN116089701A (en) | 2022-11-17 | 2022-11-17 | Personalized recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116089701A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117648909A (en) * | 2024-01-29 | 2024-03-05 | 国网湖北省电力有限公司信息通信公司 | Electric power system document data management system and method based on artificial intelligence |
-
2022
- 2022-11-17 CN CN202211478596.7A patent/CN116089701A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117648909A (en) * | 2024-01-29 | 2024-03-05 | 国网湖北省电力有限公司信息通信公司 | Electric power system document data management system and method based on artificial intelligence |
| CN117648909B (en) * | 2024-01-29 | 2024-04-12 | 国网湖北省电力有限公司信息通信公司 | Electric power system document data management system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220020056A1 (en) | Systems and methods for targeted advertising | |
| US8352396B2 (en) | Systems and methods for improving web site user experience | |
| CN1934569B (en) | Search systems and methods with integration of user annotations | |
| US8204878B2 (en) | System and method for finding unexpected, but relevant content in an information retrieval system | |
| CN101124576B (en) | Search system and methods with integration of user annotations from a trust network | |
| US9864951B1 (en) | Randomized latent feature learning | |
| US8219579B2 (en) | Expansion of search queries using information categorization | |
| US7693904B2 (en) | Method and system for determining relation between search terms in the internet search system | |
| JP5431727B2 (en) | Relevance determination method, information collection method, object organization method, and search system | |
| US9444907B2 (en) | Prediction of user response to invitations in a social network system based on keywords in the user's profile | |
| US9449078B2 (en) | Evaluating the ranking quality of a ranked list | |
| US20170154116A1 (en) | Method and system for recommending contents based on social network | |
| US9276974B2 (en) | Topical activity monitor and identity collector system and method | |
| CN109325182B (en) | Information pushing method and device based on session, computer equipment and storage medium | |
| Cleger-Tamayo et al. | Top-N news recommendations in digital newspapers | |
| KR20160057475A (en) | System and method for actively obtaining social data | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| US20130173568A1 (en) | Method or system for identifying website link suggestions | |
| KR101925950B1 (en) | Method and device for recommending contents based on inflow keyword and relevant keyword for contents | |
| US20130110594A1 (en) | Ad copy determination | |
| CN110175264A (en) | Construction method, server and the computer readable storage medium of video user portrait | |
| KR101450453B1 (en) | Method and apparatus for recommending contents | |
| CN116089701A (en) | Personalized recommendation method and device | |
| US20100145965A1 (en) | Presentation of websites to a computer user | |
| CN116701791B (en) | Course recommendation method and system based on artificial intelligence |
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 |