CN110750708A - Keyword recommendation method and device and electronic equipment - Google Patents
Keyword recommendation method and device and electronic equipment Download PDFInfo
- Publication number
- CN110750708A CN110750708A CN201810810091.3A CN201810810091A CN110750708A CN 110750708 A CN110750708 A CN 110750708A CN 201810810091 A CN201810810091 A CN 201810810091A CN 110750708 A CN110750708 A CN 110750708A
- Authority
- CN
- China
- Prior art keywords
- text
- keywords
- keyword
- determining
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000011218 segmentation Effects 0.000 claims description 53
- 230000004044 response Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000005034 decoration Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a keyword recommendation method, a keyword recommendation device and electronic equipment. One embodiment of the method comprises: acquiring at least two text messages corresponding to preset operations of a user within a preset time period; for each text message, determining candidate recommended keywords corresponding to the text message based on the keywords of the text message; and counting a target recommended keyword from a plurality of candidate recommended keywords corresponding to at least two text messages respectively. The target recommended keywords can be properly adjusted according to the text information corresponding to the preset operation of the user in different preset time periods, so that the interest of the user in different time periods can be met.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a keyword recommendation method and device and electronic equipment.
Background
With the continuous development of internet technology, the amount of internet pushed information is also increasing. When information is pushed to a user, personalized recommendation technology is generally used to select information matching with the interests of the user from a large amount of information and send the information to user terminal equipment.
In the current personalized recommendation technology, a plurality of pieces of information related to information historically browsed by a user are generally recommended to the user according to the information historically browsed by the user.
However, the interests of the user may change in different time periods, and the above-mentioned way of recommending information to the user according to the information historically browsed by the user may cause that the information recommended to the user does not match the current interests of the user.
Disclosure of Invention
The embodiment of the invention provides a keyword recommendation method, a keyword recommendation device and electronic equipment, and aims to solve the technical problems mentioned in the background technology.
In a first aspect, an embodiment of the present invention provides a keyword recommendation method, including: acquiring at least two text messages corresponding to preset operations of a user within a preset time period; for each text message, determining candidate recommended keywords corresponding to the text message based on the text keywords of the text message; and counting a target recommended keyword from a plurality of candidate recommended keywords corresponding to the at least two text messages respectively.
Optionally, for each piece of text information, determining a candidate recommended keyword corresponding to the piece of text information based on the keyword of the piece of text information includes: extracting text keywords of the text information; determining words in a pre-established knowledge graph, which have a preset association relation with the text keywords, as candidate recommended keywords of the text information.
Optionally, for each piece of text information, determining a candidate recommended keyword corresponding to the text information based on the text keyword of the text information includes: extracting text keywords of the text information; determining similarity between the text keywords and each word in a preset word bank; and determining the words with the similarity between the words and the text keywords larger than a preset similarity threshold value as candidate recommended keywords corresponding to the text information.
Optionally, the extracting the text keyword of the text information includes: performing word segmentation operation on text data corresponding to the text information to obtain a plurality of word segmentation results; and determining the text keywords of the text information based on the weight of each word segmentation result and the occurrence frequency of each word segmentation result in the text information.
Optionally, the counting of the target recommended keyword from a plurality of candidate recommended keywords corresponding to the at least two pieces of text information includes: determining the number of text messages corresponding to each candidate recommended keyword; and determining the candidate recommended keywords of which the number of the corresponding text messages is larger than a preset number threshold value as the target recommended keywords.
Optionally, an associated recommended keyword associated with the target recommended keyword is determined.
Optionally, the method further comprises: pushing the target recommendation keywords; and pushing a plurality of pieces of information associated with the target recommendation keywords in response to receiving a triggering operation of the target recommendation keywords by a user.
In a second aspect, an embodiment of the present invention provides a keyword recommendation apparatus, including: the acquisition module is configured to acquire at least two text messages corresponding to preset operations of a user within a preset time period; the determining module is configured to determine candidate recommended keywords corresponding to each piece of text information based on the keywords of the text information; and the statistical module is configured to count the target recommended keywords from a plurality of candidate recommended keywords corresponding to the at least two text messages respectively.
Optionally, the determining module is further configured to: extracting a text keyword of each text message; and determining candidate recommended keywords corresponding to the text information based on a pre-established knowledge graph and the text keywords.
Optionally, the determining module is further configured to: extracting a text keyword of each text message; determining similarity between the text keywords and each word in a preset word bank; and determining the words with the similarity larger than a preset similarity threshold value with the text keywords as candidate recommended keywords corresponding to the text information.
Optionally, the determining module is further configured to: for each text message, performing word segmentation operation on the text data corresponding to the text message to obtain a plurality of word segmentation results; and determining the text keywords of the text information based on the weight of each word segmentation result and the occurrence frequency of each word segmentation result in the text information.
Optionally, the statistics module is further configured to: determining the number of text messages corresponding to each candidate recommended keyword; and determining the candidate recommended keywords of which the number of the corresponding text messages is larger than a preset number threshold value as the target recommended keywords.
Optionally, the apparatus further comprises an associated recommendation keyword determination module configured to: and determining the associated recommended keywords associated with the target recommended keywords.
Optionally, the apparatus further includes a push module configured to: pushing the target recommendation keywords; and pushing a plurality of pieces of information associated with the target recommendation keywords in response to receiving a triggering operation of the target recommendation keywords by a user.
In a third aspect, an embodiment of the present invention provides an electronic device, including: one or more processors; the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the steps of any one of the keyword recommendation methods.
In a fourth aspect, an embodiment of the present invention provides a computer-readable medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of any one of the keyword recommendation methods described above.
According to the keyword recommendation method, the keyword recommendation device and the electronic equipment provided by the embodiment of the invention, the candidate recommendation keywords are determined based on the text keywords corresponding to the at least two text messages corresponding to the preset operation of the user in the preset time period, and then the target recommendation keywords are counted from the candidate recommendation keywords, so that the target recommendation keywords can be properly adjusted according to the text messages corresponding to the preset operation of the user in different preset time periods to match the interests of the user in different time periods. In addition, the target recommendation keywords obtained in each preset time period are displayed for the user, so that the user is guided to browse the associated information associated with the target recommendation keywords. The user experience can be improved.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a flow diagram of one embodiment of a keyword recommendation method in accordance with the present invention;
FIG. 2 is a flow diagram of yet another embodiment of a keyword recommendation method in accordance with the present invention;
FIG. 3 is a schematic diagram illustrating an embodiment of a keyword recommendation apparatus according to the present invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 5 is a schematic diagram of a basic structure of an electronic device provided according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding. They should be considered as merely exemplary. It will therefore be appreciated by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 illustrates a flow of an embodiment of a keyword recommendation method according to the present invention. The keyword recommendation method shown in fig. 1 includes the following steps:
step 101, at least two text messages corresponding to preset operations of a user within a preset time period are obtained.
In this embodiment, the preset time period may be a preset time period before the current time. The preset operation of the user may be an operation performed by the user on information presented on an information presentation page of the terminal device. The preset operation may include, but is not limited to, at least one of the following: clicking, browsing and commenting. Multiple pieces of information can be displayed in the information display page of the terminal equipment. Each piece of information may correspond to a piece of textual information. The text information herein may include, for example, but is not limited to, text data.
The preset time period may be any pre-specified time period, such as 8 hours, 12 hours, 24 hours, etc.
The text information can be obtained locally or from a remote server by web crawler technology.
And 102, for each text message, determining candidate recommended keywords corresponding to the text message based on the text keywords of the text message.
After at least two text messages corresponding to the preset operation of the user within the preset time period are obtained in step 101, each text message may be analyzed and processed by various methods to obtain a text keyword of the text message. And then determining candidate recommended keywords corresponding to the text information according to the text keywords of the text information.
In some embodiments, step 102 may include the following sub-steps:
and extracting text keywords corresponding to the text information.
Further optionally, the text data corresponding to the text information may be obtained first. And then performing word segmentation operation on the text data to obtain a plurality of word segmentation results. And finally, determining the text keywords of the text message based on the weight of each word segmentation result and the occurrence frequency of each word segmentation result in the text message. Specifically, the product of the weight corresponding to a word segmentation result and the number of times that the word segmentation result appears in the text data may be used as the importance value of the word segmentation result. And when the importance value is larger than a preset threshold value, determining the word segmentation result as a text keyword of the text information.
Each word segmentation result can correspond to a name, a dynamic noun, a noun phrase and the like.
The weight of each word segmentation result is related to the position of the word segmentation result appearing in the text data. For example, when a word segmentation result appears in a title, the weight of the word segmentation result is large; when a word segmentation result appears in the summary of the text data, the weight of the word segmentation result is larger. When a word segmentation result appears in the body of text data, the weight of the word segmentation result is smaller.
It should be noted that the word segmentation method used when performing word segmentation operation on text data is a well-known technology widely studied and applied at present, and is not described herein again.
And an optional substep of determining similarity between the text keywords and each word in the preset word bank.
The preset thesaurus may be set in advance in a local or remote server. The preset lexicon may include a plurality of words extracted from the internet data. In addition, the preset word stock can be regularly updated according to mass information of the Internet. The type of the words in the preset word library can be nouns, dynamic noun phrases, noun phrases and the like.
In an optional substep, words with similarity greater than a preset threshold with the text keywords are determined as candidate recommended keywords corresponding to the text information.
In these optional implementation manners, words in the preset word bank, whose similarity to the text keyword is greater than a preset similarity threshold, may be determined as candidate recommended keywords corresponding to the text information.
The number of candidate recommended keywords may be one, two or more.
It should be noted that the method for calculating the similarity between different words is a well-known technology widely studied and applied at present, and is not described herein again.
Step 103, counting a target recommended keyword from a plurality of candidate recommended keywords corresponding to at least two text messages respectively.
In this embodiment, the number of text messages corresponding to each candidate recommended keyword may be determined first. And then determining the candidate recommended keywords of which the number of the corresponding text messages is larger than a preset number threshold value as the target recommended keywords. The text information here refers to text information of at least two text information corresponding to the preset operation of the user in the preset time period.
It should be noted that the number of the objective recommendation keywords may be one, two, or more.
In some embodiments, the keyword recommendation method may further include pushing a target recommendation keyword. For example pushing the destination recommendation keyword to the user's terminal device. The terminal equipment of the user can display the target recommendation keywords in the current display page.
Here, the destination recommendation keyword may be pushed to the terminal device of the user through a network.
In some application scenarios, the recommended keywords may be displayed at the top of the current display page according to settings. In other application scenarios, the recommended keywords may be displayed at the bottom of the current display page according to settings.
For example, when the user browses three text messages a, b and c within 8 hours before the current time. The text keyword corresponding to the text message a is "furniture". The text keyword corresponding to the text message b is "floor". The text keyword corresponding to the text message c is "sleep". Wherein, one candidate recommended keyword corresponding to the text keyword 'furniture' is 'decoration'. One candidate recommended keyword corresponding to the text keyword 'floor' is 'decoration'. The candidate recommended keyword corresponding to the text keyword sleep is rest. The decoration of the target recommended keyword can be counted from the candidate recommended keywords respectively corresponding to the three text messages by the user. That is, the user's point of interest within 8 hours before the current time may be "fit". Thus, the target recommendation keyword 'decoration' can be pushed to the terminal of the user. And browsing more contents related to the target recommendation keywords in a mode of guiding the user to click the target recommendation keywords displayed on the display page.
The method provided by the embodiment of the invention includes the steps of firstly obtaining at least two pieces of text information corresponding to preset operation of a user in a preset time period, then determining candidate recommended keywords corresponding to the text information based on the text keywords of the text information for each piece of text information, and then counting the target recommended keywords from a plurality of candidate recommended keywords corresponding to the at least two pieces of text information. The method provided by the embodiment of the invention can be used for determining the target recommendation keywords corresponding to the user in each preset time period so as to match the interests of the user in different time periods. In addition, the target recommendation keywords obtained through statistics in each preset time period can be pushed to the user, and the user is guided to trigger the target recommendation keywords through triggering operation so as to browse more associated information associated with the target recommendation keywords. Compared with the method for directly pushing the information associated with the target recommendation keyword to the user, the method provided by the embodiment enables the user to selectively trigger the target recommendation keyword according to the current interest of the user, so as to browse more contents associated with the triggered target recommendation keyword, and thus the user experience can be improved.
In some embodiments, the keyword recommendation method may further include: and determining the associated recommendation keywords associated with the target recommendation keywords. For example, the associated recommended word of the target recommended keyword may be determined by the similarity of word senses. Therefore, recommendation keywords recommended to the user can be added for the user to select, and the user experience can be further improved.
In some embodiments, after the target recommendation keyword is pushed to the user, the keyword recommendation method may further include sending a plurality of pieces of information associated with the target recommendation keyword to the terminal device in response to receiving a trigger operation of the user on the target recommendation keyword. The trigger operation may be touch, click, hover, or the like. In this way, when the user performs a trigger operation on the target recommended keyword displayed in the screen of the terminal device, a plurality of pieces of information associated with the recommended keyword are sent to the terminal device for the user to browse. Therefore, the user can obtain a large amount of information matched with the interest of the user at the current moment in a short time. The user experience can be further improved.
With further reference to FIG. 2, a flow diagram of yet another embodiment of a keyword recommendation method is shown. As shown in fig. 2, the flow of the keyword recommendation method includes the following steps:
Step 201 is the same as step 101 in the embodiment shown in fig. 1, and is not described herein again.
For any text message, the text data corresponding to the text message may be acquired first. And then performing word segmentation operation on the text data to obtain a plurality of word segmentation results. And then determining the text keywords of the text message based on the weight of each word segmentation result and the occurrence frequency of each word segmentation result in the text message. The importance value of a word segmentation result can be determined according to the product of the weight corresponding to the word segmentation result and the occurrence frequency of the word segmentation result in the text data. When the importance value of the word segmentation result is greater than a preset threshold, the word segmentation result can be determined as a text keyword of the text information.
Each word segmentation result corresponds to a name, a dynamic noun, a noun phrase and the like. The weight of each word segmentation result is related to the position and the number of times the word segmentation result appears in the text data. For example, when a word segmentation result appears in a title, the weight of the word segmentation result is large; when a word segmentation result appears in the summary of the text data, the weight of the word segmentation result is larger. When a word segmentation result appears in the body of text data, the weight of the word segmentation result is smaller.
The knowledge-graph may be established in advance at a local or remote server. The knowledge graph can be a general knowledge graph or an industry knowledge graph. It should be noted that the above-mentioned knowledge graph and the method for establishing the knowledge graph are well-known technologies which are widely researched and applied at present. And are not described in detail herein.
Multiple entities, as well as relationships between different entities, may be included in a pre-established knowledge-graph. Here, entities are described by words, or nominal phrases.
Candidate key keywords corresponding to the text information may be determined based on the knowledge-graph and the text keywords of the text information. For example, words having a direct connection relationship with text keywords in the knowledge graph are selected as candidate recommendation keywords. Or, determining words having a certain logical relationship with the text keywords in the knowledge graph by using a logical rule reasoning method as candidate recommended keywords corresponding to the text information.
Step 204 is the same as step 103 shown in fig. 1, and is not described herein again.
As can be seen from fig. 2, compared with the embodiment corresponding to fig. 1, the keyword recommendation method in this embodiment highlights the step of determining candidate recommended keywords based on the knowledge graph. Therefore, the scheme described in the embodiment can introduce richer candidate recommended keywords to generate more accurate target recommended keywords, so that the user experience can be further improved.
With further reference to fig. 3, as an implementation of the method shown in the above figures, the present invention provides an embodiment of a keyword recommendation apparatus, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 1, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 3, the keyword recommendation apparatus of the present embodiment includes: an acquisition module 301, a determination module 302 and a statistic module 303. The obtaining module 301 is configured to obtain at least two text messages corresponding to preset operations of a user within a preset time period, where the preset operations include at least one of the following: clicking, browsing and commenting; the determining module 302 is configured to determine, for each text message, a candidate recommended keyword corresponding to the text message based on the keyword of the text message; the statistic module 303 is configured to count a target recommended keyword from a plurality of candidate recommended keywords corresponding to at least two text messages respectively.
In this embodiment, the detailed processing of the obtaining module 301, the determining module 302, and the counting module 303 of the keyword recommendation apparatus and the technical effects thereof can refer to the related descriptions of step 101, step 102, and step 103 in the corresponding embodiment of fig. 1, which are not described herein again.
In some embodiments, the determining module 302 is further configured to: extracting a text keyword of each text message; and determining candidate recommended keywords corresponding to the text information based on a pre-established knowledge graph and the text keywords.
In some embodiments, the determining module 302 is further configured to: for each text message, determining the similarity between the text keywords and each word in a preset word bank; determining words with similarity greater than a preset threshold with the text keywords as candidate recommended keywords corresponding to the text information.
In some embodiments, the determining module 302 is further configured to: for each text message, performing word segmentation operation on the text data corresponding to the text message to obtain a plurality of word segmentation results; and determining the text keywords of the text information based on the weight of each word segmentation result and the occurrence frequency of each word segmentation result in the text information.
In some embodiments, the statistics module 303 is further configured to: determining the number of text messages corresponding to each candidate recommended keyword; and determining the candidate recommended keywords of which the number of the corresponding text messages is larger than a preset number threshold value as the target recommended keywords.
In some embodiments, the keyword recommendation apparatus further includes an associated recommendation keyword determination module (not shown in the figure) configured to determine an associated recommendation keyword associated with the target recommendation keyword.
In some embodiments, the keyword recommendation apparatus further includes a push module (not shown in the figure). The pushing module is configured to push the target recommendation keyword; and pushing a plurality of pieces of information associated with the target recommendation keywords in response to receiving a triggering operation of the target recommendation keywords by the user.
Referring to fig. 4, fig. 4 illustrates an exemplary system architecture to which an embodiment of a keyword recommendation method or a keyword recommendation apparatus of the present invention may be applied.
As shown in fig. 4, the system architecture may include terminal devices 401, 402, 403, a network 404 and a server 405. The network 404 serves as a medium for providing communication links between the terminal devices 401, 402, 403 and the server 405. Network 404 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
A user may use terminal devices 401, 402, 403 to interact with a server 405 over a network 404 to receive or send messages or the like. The terminal devices 401, 402, 403 may have various client applications installed thereon, such as a web browser application, a shopping application, a search application, a news application, etc.
The terminal devices 401, 402, 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 405 may provide various services, such as obtaining historical user operation information from the terminal device, analyzing text information corresponding to the historical user operation, and determining a target recommended word. The server 405 may feed back the determined destination recommended word to the terminal device.
It should be noted that the keyword recommendation method provided in the embodiment of the present invention is generally executed by the server 405, and accordingly, the keyword recommendation apparatus is generally disposed in the server 405.
It should be understood that the number of terminal devices, networks, and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 5, a basic block diagram of an electronic device (server) suitable for use in implementing embodiments of the present invention is shown. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, an electronic device may include one or more processors 501, storage 502. The storage device 502 is used to store one or more programs. One or more programs in storage 502 may be executed by one or more processors 501. The one or more programs, when executed by the one or more processors, enable the one or more processors to implement the above-described functions defined in the method of the present invention.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprises an acquisition module, a determination module and a statistic module. The names of the modules do not form a limitation on the modules themselves under certain circumstances, for example, the acquiring module may also be described as a module that acquires at least two text messages corresponding to preset operations of a user within a preset time period.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium of the present invention may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: acquiring at least two text messages corresponding to preset operations of a user within a preset time period; for each text message, determining candidate recommended keywords corresponding to the text message based on the keywords of the text message; and counting a target recommended keyword from a plurality of candidate recommended keywords corresponding to at least two text messages respectively.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A keyword recommendation method is characterized by comprising the following steps:
acquiring at least two text messages corresponding to preset operations of a user within a preset time period; for each text message, determining candidate recommended keywords corresponding to the text message based on the text keywords of the text message;
and counting a target recommended keyword from a plurality of candidate recommended keywords corresponding to the at least two text messages respectively.
2. The method of claim 1, wherein for each text message, determining the candidate recommended keyword corresponding to the text message based on the text keyword of the text message comprises:
extracting text keywords of the text information;
and determining candidate recommended keywords corresponding to the text information based on a pre-established knowledge graph and the text keywords.
3. The method of claim 1, wherein for each text message, determining the candidate recommended keyword corresponding to the text message based on the text keyword of the text message comprises:
extracting text keywords of the text information;
determining similarity between the text keywords and each word in a preset word bank;
and determining the words with the similarity between the words and the text keywords larger than a preset similarity threshold value as candidate recommended keywords corresponding to the text information.
4. The method according to claim 2 or 3, wherein the extracting the text keyword of the text message comprises:
performing word segmentation operation on text data corresponding to the text information to obtain a plurality of word segmentation results;
and determining the text keywords of the text information based on the weight of each word segmentation result and the occurrence frequency of each word segmentation result in the text information.
5. The method according to any one of claims 1 to 3, wherein the counting of the target recommended keyword from the plurality of candidate recommended keywords corresponding to each of the at least two text messages comprises:
determining the number of text messages corresponding to each candidate recommended keyword;
and determining the candidate recommended keywords of which the number of the corresponding text messages is larger than a preset number threshold value as the target recommended keywords.
6. The method according to any one of claims 1-3, further comprising:
and determining the associated recommended keywords associated with the target recommended keywords.
7. The method according to any one of claims 1-3, further comprising:
pushing the target recommendation keywords; and
and pushing a plurality of pieces of information associated with the target recommendation keywords in response to receiving a triggering operation of the target recommendation keywords by a user.
8. A keyword recommendation apparatus, comprising:
the acquisition module is configured to acquire at least two text messages corresponding to preset operations of a user within a preset time period;
the determining module is configured to determine candidate recommended keywords corresponding to each piece of text information based on the keywords of the text information;
and the statistical module is configured to count the target recommended keywords from a plurality of candidate recommended keywords corresponding to the at least two text messages respectively.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
10. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810810091.3A CN110750708A (en) | 2018-07-23 | 2018-07-23 | Keyword recommendation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810810091.3A CN110750708A (en) | 2018-07-23 | 2018-07-23 | Keyword recommendation method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110750708A true CN110750708A (en) | 2020-02-04 |
Family
ID=69274926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810810091.3A Pending CN110750708A (en) | 2018-07-23 | 2018-07-23 | Keyword recommendation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110750708A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112364155A (en) * | 2020-11-20 | 2021-02-12 | 北京五八信息技术有限公司 | Information processing method and device |
| CN112487765A (en) * | 2020-11-23 | 2021-03-12 | 建信金融科技有限责任公司 | Method and device for generating notification text |
| CN113392637A (en) * | 2021-06-24 | 2021-09-14 | 青岛科技大学 | TF-IDF-based subject term extraction method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866341A (en) * | 2009-04-17 | 2010-10-20 | 华为技术有限公司 | Information push method, device and system |
| CN103955465A (en) * | 2014-03-28 | 2014-07-30 | 百度在线网络技术（北京）有限公司 | Method and device for generating recommended page |
| CN104111941A (en) * | 2013-04-18 | 2014-10-22 | 阿里巴巴集团控股有限公司 | Method and equipment for information display |
| CN105574142A (en) * | 2015-12-15 | 2016-05-11 | 北京奇虎科技有限公司 | Method and system for recommending content to user |
| CN107220386A (en) * | 2017-06-29 | 2017-09-29 | 北京百度网讯科技有限公司 | Information-pushing method and device |
| CN107992563A (en) * | 2017-11-29 | 2018-05-04 | 江苏神州信源系统工程有限公司 | A kind of recommendation method and system of user's browsing content |
| CN108228906A (en) * | 2018-02-08 | 2018-06-29 | 北京百度网讯科技有限公司 | For generating the method and apparatus of information |
| CN108241667A (en) * | 2016-12-26 | 2018-07-03 | 百度在线网络技术（北京）有限公司 | For the method and apparatus of pushed information |
-
2018
- 2018-07-23 CN CN201810810091.3A patent/CN110750708A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866341A (en) * | 2009-04-17 | 2010-10-20 | 华为技术有限公司 | Information push method, device and system |
| CN104111941A (en) * | 2013-04-18 | 2014-10-22 | 阿里巴巴集团控股有限公司 | Method and equipment for information display |
| CN103955465A (en) * | 2014-03-28 | 2014-07-30 | 百度在线网络技术（北京）有限公司 | Method and device for generating recommended page |
| CN105574142A (en) * | 2015-12-15 | 2016-05-11 | 北京奇虎科技有限公司 | Method and system for recommending content to user |
| CN108241667A (en) * | 2016-12-26 | 2018-07-03 | 百度在线网络技术（北京）有限公司 | For the method and apparatus of pushed information |
| CN107220386A (en) * | 2017-06-29 | 2017-09-29 | 北京百度网讯科技有限公司 | Information-pushing method and device |
| CN107992563A (en) * | 2017-11-29 | 2018-05-04 | 江苏神州信源系统工程有限公司 | A kind of recommendation method and system of user's browsing content |
| CN108228906A (en) * | 2018-02-08 | 2018-06-29 | 北京百度网讯科技有限公司 | For generating the method and apparatus of information |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112364155A (en) * | 2020-11-20 | 2021-02-12 | 北京五八信息技术有限公司 | Information processing method and device |
| CN112364155B (en) * | 2020-11-20 | 2024-05-31 | 北京五八信息技术有限公司 | Information processing method and device |
| CN112487765A (en) * | 2020-11-23 | 2021-03-12 | 建信金融科技有限责任公司 | Method and device for generating notification text |
| CN112487765B (en) * | 2020-11-23 | 2022-10-04 | 中国建设银行股份有限公司 | Method and device for generating notification text |
| CN113392637A (en) * | 2021-06-24 | 2021-09-14 | 青岛科技大学 | TF-IDF-based subject term extraction method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11023505B2 (en) | Method and apparatus for pushing information | |
| CN108804450B (en) | Information pushing method and device | |
| CN107679211B (en) | Method and device for pushing information | |
| JP6511487B2 (en) | Method and apparatus for information push | |
| CN107172151B (en) | Method and device for pushing information | |
| CN102890689B (en) | The method for building up and system of a kind of user interest model | |
| CN110069698B (en) | Information pushing method and device | |
| CN104850546B (en) | Display method and system of mobile media information | |
| CN107679119B (en) | Method and device for generating brand derivative words | |
| CN107870984A (en) | The method and apparatus for identifying the intention of search term | |
| US10019419B2 (en) | Method, server, browser, and system for recommending text information | |
| US11423096B2 (en) | Method and apparatus for outputting information | |
| JP2019145093A (en) | Method and apparatus for generating information | |
| CN107908616B (en) | Method and device for predicting trend words | |
| CN108540508B (en) | Method, device and equipment for pushing information | |
| US20180210961A1 (en) | Information search method and apparatus | |
| CN107609192A (en) | The supplement searching method and device of a kind of search engine | |
| CN110750707A (en) | Keyword recommendation method and device and electronic equipment | |
| CN110019948B (en) | Method and apparatus for outputting information | |
| CN110750708A (en) | Keyword recommendation method and device and electronic equipment | |
| CN113806660A (en) | Data evaluation method, training method, device, electronic device and storage medium | |
| CN112926298A (en) | News content identification method, related device and computer program product | |
| CN110347900B (en) | Keyword importance calculation method, device, server and medium | |
| CN110245357B (en) | Main entity identification method and device | |
| CN115098729A (en) | Video processing method, sample generation method, model training method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200204 |
|
| RJ01 | Rejection of invention patent application after publication |