CN106934006B - Page recommendation method and device based on multi-branch tree model - Google Patents
Page recommendation method and device based on multi-branch tree model Download PDFInfo
- Publication number
- CN106934006B CN106934006B CN201710135272.6A CN201710135272A CN106934006B CN 106934006 B CN106934006 B CN 106934006B CN 201710135272 A CN201710135272 A CN 201710135272A CN 106934006 B CN106934006 B CN 106934006B
- Authority
- CN
- China
- Prior art keywords
- page
- tree model
- pages
- node
- branch tree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
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 Transfer Between Computers (AREA)
Abstract
The invention provides a page recommendation method and device based on a multi-way tree model, wherein the method comprises the following steps: analyzing all pages of a service website to generate a multi-branch tree model, wherein a root node of the multi-branch tree model corresponds to a main menu page, a middle node of the multi-branch tree model corresponds to a pull-down menu page, and a leaf node of the multi-branch tree model corresponds to a function page; performing word segmentation on natural language input by a user by using a word segmentation tool to obtain characteristic words; and searching one or more functional pages matched with the characteristic words in the multi-branch tree model. The page recommendation method and the page recommendation device provided by the invention can quickly and accurately position the functional web page to be accessed by the user through the simple natural language.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a method for recommending a webpage to a user through deep analysis of natural language, in particular to a webpage recommending method and device based on a multi-way tree model.
Background
At present, existing portal sites (e.g., internet banking, internet business hall, etc.) basically show contents of web pages (pages) to customers on the basis of vertical search engines, but as interactive interface functions are increasingly diversified, people gradually find inconvenience of the vertical search engines, for example, the contents of search results are too much, and customers cannot accurately and quickly identify the contents; the webpage layout of the search result is disordered, and the user cannot accurately and quickly identify and select the webpage without primary and secondary points; the function classification is mutually crossed, the menu classification is disordered, and the phenomenon of multiple entries of the same function often appears, so that misunderstanding is caused to a client.
In order to solve the problems and improve user experience, a plurality of service websites provide a function of total-station search, firstly, the natural language input by a client is segmented, then, a crawler in the website is used for fuzzily searching all web pages related to the segmentation in the website according to the segmentation result, and the web pages are displayed to the user to be selected by the user.
The whole-station searching function can show all relevant web pages of a website for a user to select, the searching content is relatively less, and the menu classification is clear. However, the total-station search function only uses some participles after the natural language participles of the client to perform fuzzy matching, which is equivalent to segmenting the participle result into independent modules, the total-station search function does not fully use semantic relation between the natural language words, so as to search the really required functional web page for the user, the search result still has no primary and secondary scores, and the user cannot quickly and accurately identify and select the really required functional web page from a plurality of candidate functional web pages.
Therefore, it is highly desirable for those skilled in the art to develop a web page (page) search method so as to recommend a web page really needed by a user to the user according to a natural language input by the user, so that the user can accurately and quickly enter a target web page.
Disclosure of Invention
In view of the above, the invention provides a page recommendation method and device based on a multi-way tree model, which are used for solving the problems that in the prior art, a function page meeting the user requirements cannot be accurately recommended to a user, and the user experience is poor.
In order to solve the above technical problem, a technical solution of the present invention is to provide a page recommendation method based on a multi-way tree model, including: analyzing all pages of a service website to generate a multi-branch tree model, wherein a root node of the multi-branch tree model corresponds to a main menu page, a middle node of the multi-branch tree model corresponds to a pull-down menu page, and a leaf node of the multi-branch tree model corresponds to a function page; performing word segmentation on natural language input by a user by using a word segmentation tool to obtain characteristic words; searching out one or more functional pages matched with the feature words in the multi-branch tree model, wherein the searching out comprises the following steps: finding out a root node according to the characteristic words; locating one or more child nodes of the root node according to the feature words; judging whether the child node is a leaf node; if the child node is not a leaf node, continuing to locate one or more next level child nodes of the child node; and if the child node is a leaf node, searching out a functional page corresponding to the leaf node. Another technical solution of the present invention is to provide a page recommendation apparatus based on a multi-way tree model, including: the system comprises an analysis unit, a function page generation unit and a function page generation unit, wherein the analysis unit is used for analyzing all pages of a service website to generate a multi-branch tree model, a root node of the multi-branch tree model corresponds to a main menu page, a middle node of the multi-branch tree model corresponds to a pull-down menu page, and a leaf node of the multi-branch tree model corresponds to a function page; the word segmentation unit is used for segmenting the natural language input by the user by using a word segmentation tool to obtain characteristic words; the searching unit is used for searching one or more functional pages matched with the characteristic words in the multi-branch tree model; the search unit specifically includes: the searching module is used for searching out the root node according to the characteristic words; the positioning module is used for positioning one or more child nodes of the root node according to the feature words; and the judging module is used for judging whether the child nodes are leaf nodes, if the child nodes are not the leaf nodes, one or more next-level child nodes of the child nodes are continuously positioned, and if not, the functional pages corresponding to the leaf nodes are searched out.
The page recommendation method and device based on the multi-way tree model provided by the specific embodiment of the invention at least have the following characteristics: taking a main menu page of a service website as one or more root nodes of a multi-branch tree, taking a pull-down menu (thinning menu) page as one or more middle nodes of the multi-branch tree, and taking a function page as one or more leaf nodes of the multi-branch tree, thereby creating a multi-branch tree model; the method comprises the steps that a word segmentation tool is used for carrying out word segmentation processing on natural language input by a user, one or more functional pages are searched in a multi-branch tree model based on word segmentation results according to semantic relation between words, the searched functional pages are recommended to the user according to weighted value sequences, the method can be integrated in mobile terminal application or vehicle-mounted application, and the user can quickly and accurately position a desired functional webpage through simple natural language; in addition, partial word segmentation results can be automatically and additionally recorded in a target function webpage, manual input of a user is not needed, the user is helped to quickly realize related functions, and the customer experience is further improved while business expansion is guaranteed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a first embodiment of a page recommendation method based on a multi-way tree model according to an embodiment of the present invention;
fig. 2 is a flowchart of a second embodiment of a page recommendation method based on a multi-way tree model according to a specific embodiment of the present invention;
fig. 3 is a flowchart of a third embodiment of a page recommendation method based on a multi-way tree model according to a specific embodiment of the present invention;
fig. 4 is a flowchart of a fourth embodiment of a page recommendation method based on a multi-way tree model according to a specific embodiment of the present invention;
FIG. 5 is a schematic block diagram of a first embodiment of a page recommendation apparatus based on a multi-way tree model according to an embodiment of the present invention;
fig. 6 is a schematic block diagram of a second embodiment of a page recommendation device based on a multi-way tree model according to a specific embodiment of the present invention;
fig. 7 is a schematic block diagram of a third embodiment of a page recommendation device based on a multi-way tree model according to a specific embodiment of the present invention;
fig. 8 is a schematic block diagram of a fourth embodiment of a page recommendation device based on a multi-way tree model according to a specific embodiment of the present invention.
Detailed Description
In order to make the technical features and effects of the invention more obvious, the technical solution of the invention is further described below with reference to the accompanying drawings, the invention can also be described or implemented by other different specific examples, and any equivalent changes made by those skilled in the art within the scope of the claims are within the scope of the invention.
Fig. 1 is a flowchart of a first embodiment of a page recommendation method based on a multi-way tree model according to an embodiment of the present invention, and as shown in fig. 1, a main menu page of a service website is used as one or more root nodes of a multi-way tree, a pull-down menu (detailed menu) page is used as one or more middle nodes of the multi-way tree, and a function page is used as one or more leaf nodes of the multi-way tree, so as to create the multi-way tree model; and performing word segmentation processing on the natural language input by the user by using a word segmentation tool, and searching one or more functional pages in the multi-branch tree model based on word segmentation results according to semantic relation between words.
In the specific embodiment shown in the figure, the page recommendation method based on the multi-way tree model includes:
step 101: analyzing all pages of a service website to generate a multi-branch tree model, wherein a root node of the multi-branch tree model corresponds to a main menu page, a middle node of the multi-branch tree model corresponds to a pull-down menu page, and a leaf node of the multi-branch tree model corresponds to a function page. In an embodiment of the present invention, the service website is an internet bank or an internet business hall. The multi-branch tree model is provided with one or more root nodes, and the root nodes are functional nodes, such as money transfer, financing, mobile service, broadband service and the like; the multi-branch tree model is provided with one or more intermediate nodes, and the intermediate nodes are control nodes, such as transfer accounts, fund purchases, package transaction, service sales promotion and the like; the multi-branch tree model has one or more leaf nodes, and the leaf nodes are page nodes, such as in-line transfer, historical balance inquiry, current remaining flow inquiry, mobile phone recharging and the like. The main menu page is usually a webpage corresponding to a large class of services on a main page of a service website, such as a transfer page, a financing page, a mobile service page, a broadband service page and the like; the pull-down menu page is generally a page corresponding to a subclass contained in a business major class, such as a transfer page, a fund purchase page, a package transaction page and a business promotion page; the functional page is generally a page for realizing the final target of the user, such as an inline transfer page, a historical balance inquiry page, a current remaining flow inquiry page, a mobile phone recharging page and the like.
In the specific embodiment of the invention, the natural language is Chinese, English and other sentences, and the word segmentation tool is a Stanford N L P segmentation tool.
Step 103: and searching one or more functional pages matched with the characteristic words in the multi-branch tree model. According to the characteristic words, a plurality of functional pages are searched in the multi-branch tree model.
Referring to fig. 1, semantic relations among feature words are fully utilized, and a user can quickly and accurately locate a desired functional webpage through a simple natural language, so that the user experience is improved.
Fig. 2 is a flowchart of a second embodiment of a page recommendation method based on a multi-way tree model according to a specific embodiment of the present invention, as shown in fig. 2, a matched function page is recommended to a user according to an access amount, and the user can quickly identify a target page to be accessed; and related feature words are automatically supplemented into the matched function pages, so that the manual data input amount of a user is reduced.
In the embodiment shown in the figure, after step 103, the method for recommending a page based on the multi-way tree model further includes:
step 104: and recommending one or more functional pages matched with the characteristic words to the user according to the weight values. In a specific embodiment of the present invention, the weight value is an access amount of the function page.
Step 105: and automatically supplementing the characteristic words into the matched functional pages.
Referring to fig. 2, the function page is recommended to the user according to the access amount of the matched function page, and the user can quickly identify a target page to be accessed; the related feature words are automatically supplemented into the matched function pages, so that the manual data input amount of a user is reduced, the operation time of the user is saved, and the user experience is improved.
Fig. 3 is a flowchart of a third embodiment of a page recommendation method based on a multi-way tree model according to a specific embodiment of the present invention, and as shown in fig. 3, tags of all pages of a service website are analyzed, so that the pages are divided into a main menu page, a pull-down menu page, and a function page, and then the multi-way tree model is created according to a logical relationship between the pages.
In the embodiment shown in the drawing, step 101 specifically includes:
step 1011: and analyzing the label of the page so as to divide the page into a main menu page, a pull-down menu page and a function page. In a specific embodiment of the present invention, the tag comprises: hypertext markup language tags and field tags. For example, the parsing page finds that the page is entitled "transfer remittance", and the page may be taken as a main menu page; analyzing the page to find the page title as 'in-line transfer', and taking the page as a pull-down menu page; when the fields of 'amount' and 'payee' are found in the field tags of the page by analyzing the page, the page can be used as a functional page.
Step 1012: and generating a multi-branch tree model according to the logical relationship among the main menu page, the pull-down menu page and the function page. The logical relationship mainly refers to the jump sequence among a main menu page, a pull-down menu page and a function page when a specific service is realized.
Referring to fig. 3, all pages of a service website are classified to create a multi-way tree model, and different pages of the service website correspond to different nodes of the multi-way tree model.
Fig. 4 is a flowchart of a fourth embodiment of a page recommendation method based on a multi-way tree model according to the specific embodiment of the present invention, as shown in fig. 4, a root node is first found according to a feature word, a child node (first-level child node) is selected from a plurality of child nodes (first-level child nodes) of the root node according to the feature word, and a child node (second-level child node) is selected from a plurality of child nodes (second-level child nodes) of the child node according to the feature word until the selected child node is a leaf node.
In the embodiment shown in the drawing, step 103 specifically includes:
step 1031: and finding out the root node according to the characteristic words.
Step 1032: and positioning one or more child nodes of the root node according to the characteristic words.
Step 1033: and judging whether the child node is a leaf node.
Step 1034: if the child node is not a leaf node, one or more next level child nodes of the child node are located.
Step 1035: and if the child node is a leaf node, searching out a functional page corresponding to the leaf node. In the embodiment of the invention, the leaf nodes correspond to the function pages one by one.
Referring to fig. 4, the root node, one or more intermediate nodes, and the leaf node are sequentially found out according to the feature words, so that the functional page corresponding to the leaf node is found out, a user can conveniently and rapidly and accurately locate a target page, and the user experience is greatly improved.
Fig. 5 is a schematic block diagram of a first embodiment of a page recommendation apparatus based on a multi-way tree model according to an embodiment of the present invention, and the apparatus shown in fig. 5 may be applied to the methods shown in fig. 1 to fig. 4, where a main menu page of a service website is used as one or more root nodes of the multi-way tree, a pull-down menu (refined menu) page is used as one or more middle nodes of the multi-way tree, and a function page is used as one or more leaf nodes of the multi-way tree, so as to create the multi-way tree model; and performing word segmentation processing on the natural language input by the user by using a word segmentation tool, and searching one or more functional pages in the multi-branch tree model based on word segmentation results according to semantic relation between words.
In the embodiment shown in the figure, the page recommendation device based on the multi-way tree model comprises: the system comprises an analysis unit 1, a word segmentation unit 2 and a search unit 3, wherein the analysis unit 1 is used for analyzing all pages of a service website to generate a multi-branch tree model, a root node of the multi-branch tree model corresponds to a main menu page, a middle node of the multi-branch tree model corresponds to a pull-down menu page, and a leaf node of the multi-branch tree model corresponds to a function page; the word segmentation unit 2 is used for performing word segmentation on the natural language input by the user by using a word segmentation tool to obtain feature words; the searching unit 3 is used for searching out one or more functional pages matched with the characteristic words in the multi-branch tree model.
Referring to fig. 5, semantic relations among feature words are fully utilized, and a user can quickly and accurately locate a desired functional webpage through a simple natural language, so that the user experience is improved.
Fig. 6 is a schematic block diagram of a second embodiment of a page recommendation apparatus based on a multi-way tree model according to a specific embodiment of the present invention, as shown in fig. 6, a matched function page is recommended to a user according to an access amount, and the user can quickly identify a target page to be accessed; and related feature words are automatically supplemented into the matched function pages, so that the manual data input amount of a user is reduced.
In the specific embodiment shown in the figure, the page recommendation device based on the multi-branch tree model further includes a recommendation unit 4 and a supplement unit 5, wherein the recommendation unit 4 is configured to recommend one or more functional pages matched with the feature words to a user according to weight values; and the adding unit 5 is used for automatically adding the characteristic words into the matched functional pages.
Referring to fig. 6, the function page is recommended to the user according to the access amount of the matched function page, and the user can quickly identify a target page to be accessed; the related feature words are automatically supplemented into the matched function pages, so that the manual data input amount of a user is reduced, the operation time of the user is saved, and the user experience is improved.
Fig. 7 is a schematic block diagram of a third embodiment of a page recommendation device based on a multi-way tree model according to a specific embodiment of the present invention, and as shown in fig. 7, tags of all pages of a service website are analyzed, so that the pages are divided into a main menu page, a pull-down menu page, and a function page, and then the multi-way tree model is created according to a logical relationship between the pages.
In the specific embodiment shown in the figure, the parsing unit 1 specifically includes a parsing module 11 and a generating module 12, where the parsing module 11 is configured to parse a tag of a page so as to divide the page into a main menu page, a pull-down menu page, and a function page; the generating module 12 is configured to generate a multi-branch tree model according to a jump relationship among the main menu page, the pull-down menu page, and the function page.
Referring to fig. 7, all pages of a service website are classified to create a multi-way tree model, and different pages of the service website correspond to different nodes of the multi-way tree model.
Fig. 8 is a schematic block diagram of a fourth embodiment of a page recommendation apparatus based on a multi-way tree model according to the present invention, as shown in fig. 8, a root node is first found according to a feature word, one or more child nodes (primary child nodes) are selected from a plurality of child nodes (primary child nodes) of the root node according to the feature word, and then one or more child nodes (secondary child nodes) are selected from a plurality of child nodes (secondary child nodes) of the child node according to the feature word until the selected child nodes are leaf nodes.
In the embodiment shown in the drawing, the search unit 3 specifically includes: a search module 31, a location module 32 and a judgment module 33. The searching module 31 is configured to search for a root node according to the feature word; a positioning module 32, configured to position one or more child nodes of the root node according to the feature words; a determining module 33, configured to determine whether the child node is a leaf node, if the child node is not a leaf node, continue to locate one or more next-level child nodes of the child node, and otherwise, search out a functional page corresponding to the leaf node.
Referring to fig. 8, the root node, one or more intermediate nodes, and the leaf node are sequentially found out according to the feature words, so that the functional page corresponding to the leaf node is found out, a user can conveniently and rapidly and accurately locate a target page, and the user experience is greatly improved.
In an embodiment of the present invention, the parsing unit 1 parses all pages of the internet banking website of the chinese bank to generate the multi-branch tree model. If a customer of a certain China bank wants to transfer three accounts through the China bank internet bank, if the natural language input by the customer is 'I wants to transfer 1000 yuan for three bank cards', firstly, the word segmentation unit 2 performs word segmentation on the natural language to obtain characteristic words of 'three accounts', 'bank cards', 'account transfer', '1000', 'and yuan'. The searching unit 3 searches a function page matched with the characteristic words in the multi-branch tree model, firstly, the searching unit 3 searches root nodes which can be matched according to the characteristic words of 'transfer', and determines 'transfer remittance' as the most matched root node; then finding sub-nodes (middle nodes) corresponding to the root node 'transfer remittance' as 'transfer' and 'remittance', and determining the sub-nodes matched with the sub-node 'transfer' party according to the characteristic word 'transfer'; the next-level sub-node (middle node) corresponding to the sub-node 'transfer' is 'intra-row ordinary transfer', 'cross-row ordinary transfer', 'intra-row real-time transfer', 'cross-border transfer'; determining the matched next-level sub-nodes as 'cross-bank common transfer' and 'cross-bank real-time transfer' according to the characteristic words 'work bank card' and 'element', judging the next-level sub-nodes as leaf nodes, and searching out a functional page corresponding to the next-level sub-nodes 'cross-bank common transfer' and 'cross-bank real-time transfer' by the searching unit 3; the recommending unit 4 recommends the searched functional page to the client according to the access amount, and since the access amount of the cross-bank common transfer page is far larger than that of the cross-bank real-time transfer page, the cross-bank common transfer page is recommended to the client at first, and then the cross-bank real-time transfer page is recommended to the client. The supplementing unit 5 automatically supplements the matched functional pages with the characteristic words of Zhang III and 1000, so that the client does not need to input transfer objects and transfer money, the input amount of client data is saved, and the experience of the client is improved.
The specific implementation mode of the invention provides a page recommendation method and a device based on a multi-branch tree model, wherein a main menu page of a service website is used as one or more root nodes of the multi-branch tree, a pull-down menu (thinning menu) page is used as one or more middle nodes of the multi-branch tree, and a function page is used as one or more leaf nodes of the multi-branch tree, so that the multi-branch tree model is created; the method comprises the steps that a word segmentation tool is used for carrying out word segmentation processing on natural language input by a user, one or more functional pages are searched in a multi-branch tree model based on word segmentation results according to semantic relation between words, the searched functional pages are recommended to the user according to weighted value sequences, the method can be integrated in mobile terminal application or vehicle-mounted application, and the user can quickly and accurately position a desired functional webpage through simple natural language; in addition, partial word segmentation results can be automatically and additionally recorded in a target function webpage, manual input of a user is not needed, the user is helped to quickly realize related functions, and the customer experience is further improved while business expansion is guaranteed.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the purpose of illustrating the present invention, and any person skilled in the art can modify and change the above embodiments without departing from the spirit and scope of the present invention. Therefore, the scope of the claims should be accorded the full scope of the claims.
Claims (11)
1. A page recommendation method based on a multi-branch tree model is characterized by comprising the following steps:
analyzing all pages of a service website to generate a multi-branch tree model, wherein a root node of the multi-branch tree model corresponds to a main menu page, a middle node of the multi-branch tree model corresponds to a pull-down menu page, and a leaf node of the multi-branch tree model corresponds to a function page;
performing word segmentation on natural language input by a user by using a word segmentation tool to obtain characteristic words; and
searching out one or more functional pages matched with the feature words in the multi-branch tree model, wherein the searching out comprises the following steps:
finding out a root node according to the characteristic words;
locating one or more child nodes of the root node according to the feature words;
judging whether the child node is a leaf node;
if the child node is not a leaf node, continuing to locate one or more next level child nodes of the child node; and
and if the child node is a leaf node, searching out a functional page corresponding to the leaf node.
2. The method for page recommendation based on the multi-way tree model of claim 1, wherein after the step of searching the multi-way tree model for one or more functional pages matching the feature words, the method further comprises:
and recommending one or more functional pages matched with the characteristic words to the user according to the weight values.
3. The method of claim 2, wherein the weight value is an access amount of the function page.
4. The method for page recommendation based on the multi-way tree model of claim 1, wherein after the step of searching the multi-way tree model for one or more functional pages matching the feature words, the method further comprises:
and automatically supplementing the characteristic words into the matched functional pages.
5. The method for recommending pages based on the multi-way tree model as claimed in claim 1, wherein the step of parsing all pages of the service website to generate the multi-way tree model specifically comprises:
analyzing the label of the page so as to divide the page into a main menu page, a pull-down menu page and a function page; and
and generating a multi-branch tree model according to the logical relationship among the main menu page, the pull-down menu page and the function page.
6. The method of claim 5, wherein the tag comprises: hypertext markup language tags and field tags.
7. The method for recommending pages based on the multi-way tree model of claim 1, wherein said service website is an online bank or an online business hall.
8. A page recommendation device based on a multi-way tree model is characterized by comprising:
the system comprises an analysis unit, a function page generation unit and a function page generation unit, wherein the analysis unit is used for analyzing all pages of a service website to generate a multi-branch tree model, a root node of the multi-branch tree model corresponds to a main menu page, a middle node of the multi-branch tree model corresponds to a pull-down menu page, and a leaf node of the multi-branch tree model corresponds to a function page;
the word segmentation unit is used for segmenting the natural language input by the user by using a word segmentation tool to obtain characteristic words; and
the searching unit is used for searching one or more functional pages matched with the characteristic words in the multi-branch tree model;
the search unit specifically includes:
the searching module is used for searching out the root node according to the characteristic words;
the positioning module is used for positioning one or more child nodes of the root node according to the feature words; and
and the judging module is used for judging whether the child node is a leaf node, if the child node is not a leaf node, continuously positioning one or more next-level child nodes of the child node, and otherwise, searching out a functional page corresponding to the leaf node.
9. The apparatus for page recommendation based on the multi-way tree model of claim 8, further comprising:
and the recommending unit is used for recommending one or more functional pages matched with the characteristic words to the user according to the weight values.
10. The apparatus for page recommendation based on the multi-way tree model of claim 8, further comprising:
and the adding unit is used for automatically adding the characteristic words into the matched functional pages.
11. The apparatus for recommending pages based on the multi-way tree model according to claim 8, wherein said parsing unit specifically comprises:
the analysis module is used for analyzing the label of the page so as to divide the page into a main menu page, a pull-down menu page and a function page; and
and the generating module is used for generating a multi-branch tree model according to the logical relationship among the main menu page, the pull-down menu page and the function page.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710135272.6A CN106934006B (en) | 2017-03-08 | 2017-03-08 | Page recommendation method and device based on multi-branch tree model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710135272.6A CN106934006B (en) | 2017-03-08 | 2017-03-08 | Page recommendation method and device based on multi-branch tree model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106934006A CN106934006A (en) | 2017-07-07 |
| CN106934006B true CN106934006B (en) | 2020-07-10 |
Family
ID=59431964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710135272.6A Active CN106934006B (en) | 2017-03-08 | 2017-03-08 | Page recommendation method and device based on multi-branch tree model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106934006B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107818163B (en) * | 2017-11-01 | 2019-03-29 | 平安科技（深圳）有限公司 | Page display method, device, computer equipment and storage medium |
| WO2021227059A1 (en) | 2020-05-15 | 2021-11-18 | 深圳市世强元件网络有限公司 | Multi-way tree-based search word recommendation method and system |
| CN111737986A (en) * | 2020-05-15 | 2020-10-02 | 深圳市世强元件网络有限公司 | A method and system for search word recommendation based on multi-fork tree |
| CN114579009A (en) * | 2020-11-30 | 2022-06-03 | 中移(苏州)软件技术有限公司 | Method, device, equipment and storage medium for triggering menu items |
| CN115098050A (en) * | 2022-05-25 | 2022-09-23 | 杭州脸脸会网络技术有限公司 | Multi-screen linkage method and device, electronic device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102968469A (en) * | 2012-11-09 | 2013-03-13 | 北京小米科技有限责任公司 | Method and system for building application index, and method and system for application indexes |
| CN103455492A (en) * | 2012-05-29 | 2013-12-18 | 腾讯科技（深圳）有限公司 | Method and device for searching web pages |
| CN105740417A (en) * | 2016-01-29 | 2016-07-06 | 青岛海信移动通信技术股份有限公司 | Webpage based target data search method and module, browser and terminal |
-
2017
- 2017-03-08 CN CN201710135272.6A patent/CN106934006B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455492A (en) * | 2012-05-29 | 2013-12-18 | 腾讯科技（深圳）有限公司 | Method and device for searching web pages |
| CN102968469A (en) * | 2012-11-09 | 2013-03-13 | 北京小米科技有限责任公司 | Method and system for building application index, and method and system for application indexes |
| CN105740417A (en) * | 2016-01-29 | 2016-07-06 | 青岛海信移动通信技术股份有限公司 | Webpage based target data search method and module, browser and terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106934006A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12032905B2 (en) | Methods and systems for summarization of multiple documents using a machine learning approach | |
| KR102472572B1 (en) | Method for profiling user's intention and apparatus therefor | |
| CN103870973B (en) | Information push, searching method and the device of keyword extraction based on electronic information | |
| US20170213157A1 (en) | Method and system to provide related data | |
| CN106934006B (en) | Page recommendation method and device based on multi-branch tree model | |
| CN109190049B (en) | Keyword recommendation method, system, electronic device and computer readable medium | |
| US20210390609A1 (en) | System and method for e-commerce recommendations | |
| CN107704512A (en) | Financial product based on social data recommends method, electronic installation and medium | |
| CN105302810A (en) | Information search method and apparatus | |
| CN108346075A (en) | Information recommendation method and device | |
| CN111680165B (en) | Information matching method and device, readable storage medium and electronic equipment | |
| Petz et al. | On text preprocessing for opinion mining outside of laboratory environments | |
| CN118193806B (en) | Target retrieval method, target retrieval device, electronic equipment and storage medium | |
| US20250190470A1 (en) | Intelligent natural language queries via large language model and user interface element metadata | |
| CN107368489A (en) | A kind of information data processing method and device | |
| CN113988057A (en) | Title generation method, device, device and medium based on concept extraction | |
| CN110363206B (en) | Clustering of data objects, data processing and data identification methods | |
| KR20160103470A (en) | System and method for providing response informations of prior users on goods through network | |
| CN119127019A (en) | Agent-based human-computer interaction method, device, electronic equipment and medium | |
| CN118228713A (en) | Method and device for generating demand document, electronic equipment and storage medium | |
| CN107315831B (en) | A kind of method and device of the unknown incidence relation of mining rule correlation model | |
| CN108509571B (en) | General method for webpage information data mining | |
| CN111144122B (en) | Evaluation processing method, device, computer system and medium | |
| CN118608295A (en) | Product name identification method, device, electronic device and medium | |
| CN117909560A (en) | Search method, training device, training equipment, training medium and training program product |
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 |