CN110413875B - Text information pushing method and related device - Google Patents
Text information pushing method and related device Download PDFInfo
- Publication number
- CN110413875B CN110413875B CN201910564424.3A CN201910564424A CN110413875B CN 110413875 B CN110413875 B CN 110413875B CN 201910564424 A CN201910564424 A CN 201910564424A CN 110413875 B CN110413875 B CN 110413875B
- Authority
- CN
- China
- Prior art keywords
- topic
- keyword
- keywords
- target
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000013598 vector Substances 0.000 claims description 124
- 238000012545 processing Methods 0.000 claims description 43
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000009825 accumulation Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 13
- 230000010365 information processing Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 12
- 238000000605 extraction Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 210000000744 eyelid Anatomy 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a text information pushing method and a related device, which are used for establishing a corresponding relation between text information and a proper topic, and then covering the content actually expressed by an article through topic keywords of the topic, filling in keywords which are closely connected with the article but are not appeared in the article, carrying out user matching through the topic keywords, and enabling the matched keywords to be closer to the content actually expressed by the article, so that a better pushing effect can be achieved. The method of the embodiment of the application comprises the following steps: acquiring text information; according to a preset topic matching relationship, determining a target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword; determining a user to be pushed according to the at least one topic keyword in the target topics through matching of the at least one topic keyword and a user keyword; and pushing the text information to the user to be pushed.
Description
Technical Field
The application relates to the technical field of Internet, in particular to a text information pushing method and a related device.
Background
With the development of modern society, people need to browse a large amount of information every day to meet the increasing information demands of people. The user can search for the information wanted by the user on the internet, and can also passively receive the pushed information, for example, when the user clicks on the news website top page, news pushed by the website will be shown on the news website top page, for example, when the user refreshes the information top page, new hot spot information will be obtained, for example, when the user opens a certain classification interface, articles corresponding to the classification are displayed.
If the user can push the article interested by the user when receiving the push message, the reading experience of the user is greatly improved. Therefore, at present, one or more keywords contained in the articles are usually matched with the labels of the users, and when the keywords are the same as the labels of the users, the articles corresponding to the keywords are matched with the users, and then the articles corresponding to the keywords are pushed to the users.
However, the pushing method relies on the extraction capability of the keywords of the article, and the keywords extracted from the article are words appearing in the article, so that the keywords which can be closely connected with the article but are not appearing in the article are missed, the keywords corresponding to the article cannot completely cover the content actually expressed by the article, and the pushing effect is poor.
Disclosure of Invention
The embodiment of the application provides a text information pushing method and a related device, which are used for determining a user to be pushed by adopting topic keywords of a target topic by determining the target topic corresponding to the text information, and determining the user to be pushed by using topic keywords which are closer to the actual expression content of an article, so that the technical problem of poor pushing effect at present is solved.
In view of this, a first aspect of the present application provides a method for pushing text information, including:
acquiring text information, wherein the text information comprises target text keywords;
Determining a target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword according to a preset topic matching relationship, wherein the preset topic matching relationship comprises an association relationship between the topic keyword and the topic, and the target topic comprises at least one topic keyword;
determining a user to be pushed according to the at least one topic keyword in the target topics through matching of the at least one topic keyword and a user keyword, wherein the user to be pushed corresponds to the user keyword, and the user keyword is used for determining topic keywords associated with the user to be pushed;
And pushing the text information to the user to be pushed.
A second aspect of an embodiment of the present application provides a text information pushing device, including:
The system comprises an acquisition module, a search module and a search module, wherein the acquisition module is used for acquiring text information, and the text information comprises target text keywords;
The processing module is used for determining a target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword according to a preset topic matching relation, wherein the preset topic matching relation comprises an association relation between the topic keyword and the topic, and the target topic comprises at least one topic keyword;
the processing module is further configured to determine a user to be pushed according to the at least one topic keyword in the target topic, through matching of the at least one topic keyword and a user keyword, where the user to be pushed corresponds to the user keyword, and the user keyword is used to determine a topic keyword associated with the user to be pushed;
And the pushing module is used for pushing the text information to the user to be pushed.
In a possible design, in a first implementation manner of the second aspect of the embodiments of the present application, the processing module is further configured to:
Generating word vectors of the target text keywords through a word vector model;
performing accumulation processing and normalization processing on word vectors of the target text keywords to obtain accumulated word vectors of the text information;
generating word vectors of the topic keywords through a word vector model;
performing accumulation processing and normalization processing on word vectors of the topic keywords to obtain accumulated word vectors of the topics;
calculating a first cosine similarity score between the accumulated word vector of the text information and the accumulated word vector of the topic;
Selecting the target topics from M topics according to the first cosine similarity score, wherein the target topics are the first N topics with the first cosine similarity score ordered from large to small, M is an integer greater than or equal to 1, and N is an integer greater than or equal to 1 and less than or equal to M.
In a second implementation manner of the second aspect of the embodiment of the present application, the processing module is further configured to: and if the user keywords are the same as the at least one topic keyword in the target topics, determining the user to be pushed according to the user keywords.
In a possible design, in a third implementation manner of the second aspect of the embodiment of the present application, the text information pushing device further includes a text information processing module, where the text information processing module is configured to select Y pieces of text information from X pieces of text information according to the topic keyword to push, if the user keyword is the same as the at least one topic keyword in the target topic, where at least one topic keyword of the Y pieces of text information is the same as the user keyword, and X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1 and less than or equal to X.
In a possible design, in a fourth implementation manner of the second aspect of the embodiment of the present application, the text information pushing device further includes a preset topic matching relationship module, where the preset topic matching relationship module is used to obtain sample text information, and the sample text information includes a sample text keyword;
clustering the sample text keywords by a clustering algorithm;
Selecting the topic from the sample text keywords in the cluster;
Selecting the topic keywords from a preset word stock according to the topics, wherein the topic keywords have association relation with the topics;
and establishing the preset topic matching relation according to the topics and the topic keywords.
In a fifth implementation manner of the second aspect of the embodiment of the present application, the preset topic matching relation module is further configured to: generating word vectors of the topics and word vectors of candidate topic keywords in the preset word stock through a word vector model;
calculating a second cosine similarity score between the word vector of the topic and the word vector of the candidate topic keyword;
And selecting the topic keywords from the preset word stock, wherein the topic keywords are the first L candidate topic keywords with the second similarity scores ordered from big to small, and L is an integer greater than or equal to 1.
A third aspect of an embodiment of the present application provides a server, including: memory, transceiver, processor, and bus system;
Wherein the memory is used for storing programs;
the processor is used for executing the program in the memory, and comprises the following steps:
acquiring text information, wherein the text information comprises target text keywords;
Determining a target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword according to a preset topic matching relationship, wherein the preset topic matching relationship comprises an association relationship between the topic keyword and the topic, and the target topic comprises at least one topic keyword;
determining a user to be pushed according to the at least one topic keyword in the target topics through matching of the at least one topic keyword and a user keyword, wherein the user to be pushed corresponds to the user keyword, and the user keyword is used for determining topic keywords associated with the user to be pushed;
Pushing the text information to the user to be pushed;
the bus system is used for connecting the memory and the processor so as to enable the memory and the processor to communicate.
A fourth aspect of an embodiment of the application provides a computer readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the method of the first aspect described above.
A fifth aspect of an embodiment of the application provides a computer program product comprising instructions which, when run on a computer or processor, cause the computer or processor to perform the method of the first aspect described above.
From the above technical solutions, the embodiment of the present application has the following advantages:
According to the embodiment of the application, after the corresponding relation between the text information and the proper topics is established, the content actually expressed by the articles can be covered by the topic keywords of the topics, so that the keywords closely related to the articles but not appearing in the articles are filled, the user matching is carried out by the topic keywords, and the matched keywords are closer to the content actually expressed by the articles, so that a better pushing effect can be achieved.
Drawings
FIG. 1 is a schematic diagram of a system for pushing text messages according to an embodiment of the present application;
FIG. 2 is a flow chart of one embodiment of a method for text message pushing in accordance with an embodiment of the present application;
FIG. 3 is a schematic diagram of matching topics with text information in an embodiment of the present application;
FIG. 4 is a schematic diagram of matching text information with a user according to an embodiment of the present application;
FIG. 5 is a schematic diagram of an embodiment of a text message pushing device according to an embodiment of the present application;
FIG. 6 is a schematic diagram of an alternative embodiment of a text message pushing device according to an embodiment of the present application;
FIG. 7 is a schematic diagram of an alternative embodiment of a text message pushing device according to an embodiment of the present application;
fig. 8 is a schematic diagram of a server structure according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a text information pushing method and a related device, which are used for determining a user to be pushed by adopting topic keywords of a target topic by determining the target topic corresponding to the text information, and determining the user to be pushed by using topic keywords which are closer to the actual expression content of an article, so that the technical problem of poor pushing effect at present is solved.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "includes" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that with the development of modern society, people have entered a big data age and are browsing a large amount of information every day, wherein the main information is text information. Text information is usually a collection of texts, such as articles, short texts, news, information, microblogs, short messages and messages, the language adopted can be any language such as Chinese, english, japanese and the like, and the file format stored and transmitted in a computer can be any format such as doc, txt and the like. The text information is stored in a server, when a user prepares to browse the text information, the server pushes the text information to a client of the user, for example, when the user opens a client home page, refreshes the client home page, opens a page under a certain category and opens an Application (APP), or when the user client stands by, a short message, a notification or a message sent by the server is received, for example, when the user subscribes to an a-anchor's play message, and when the a-anchor plays, the server pushes a background message to the user client even if the user client does not open a live client. It can be seen that text messages are typically users that select a push by keyword matching, such as the "a-anchor" keywords described above. However, these keywords do not necessarily completely cover the scope of the text message, for example, if a text message describes a financial fraud on the a e-commerce website, the text message will be pushed to the user whose user keyword is "a e-commerce website" or "financial fraud" through the keywords "a e-commerce website" and "financial fraud", but will not be pushed to the user whose user keyword is "B e-commerce website". However, in practice, the user with the user keyword "B e-commerce website" is also likely to be interested in the "a e-commerce website", that is, the text message describing the financial fraud on the a e-commerce website, so if the server pushes the text message to the user with the user keyword "B e-commerce website", the reading experience of the user can be actually improved, and a better pushing effect is achieved.
The embodiment of the application provides a text information pushing method and a related device, which can say that text information describing financial fraud cases on an E-commerce website A is pushed to a user with a keyword of 'B E-commerce website', improve the reading experience of the user and realize a better pushing effect. Embodiments of the present application will be described in detail below.
It should be understood that pushing through a server is a common technical means, in practical application, in order to reduce the burden of the server, a text message may also be downloaded to a client entirely, and then the client performs pushing of the text message by analyzing keywords, and the execution subject is not specifically limited in the embodiment of the present application.
Fig. 1 is a schematic diagram of an architecture of a text message pushing system in an embodiment of the present application, where, as shown in fig. 1, a server establishes a communication connection with a terminal device through a network, after a text message is selected by the server, the text message is pushed to the terminal device, and the text message is displayed through a client on the terminal device. The terminal device shown in fig. 1 is only one illustration, and in practical applications, the terminal device includes, but is not limited to, a mobile phone, a desktop computer, a tablet computer, a notebook computer, and a palm computer.
It may be understood that, in the embodiment of the present application, the server pushes the text information to the terminal device, and displays the text information through the client on the terminal device, where the client on the terminal device may be an application program or an applet in the application program, or may be a subscription number, a service number, an enterprise number, a microblog, a friend circle, a video website, and other portal websites, and the present application is not limited specifically herein.
In the following, a method for pushing text information in the embodiment of the present application will be described in detail from the perspective of a server, referring to fig. 2, and one embodiment of the method for pushing text information in the embodiment of the present application includes:
201. Acquiring text information, wherein the text information comprises target text keywords;
in the embodiment of the application, the text information can be stored in a database, a network or a specific server. The server may acquire the text information, and push the text information to the user terminal device after selecting the user to be pushed.
In the embodiment of the application, the target text keywords in the text information are keywords extracted from the text information, and the keywords can be extracted by a keyword extraction algorithm. The amount of text information may be one or more.
202. Determining a target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword according to a preset topic matching relation, wherein the preset topic matching relation comprises an association relation between the topic keyword and the topic, and the target topic comprises at least one topic keyword;
It may be understood that the target text keyword in the text information may be matched with a topic keyword in a preset topic matching relationship, and the matching method between the target text keyword and the topic keyword (between two groups of words) may be a method of searching for a word commonly occurring in the two groups of words, or a method of calculating cosine similarity between word vectors, or a method of neural network similarity matching, which is not limited specifically herein.
In the embodiment of the application, the topic and the topic keyword have an association relationship, and the association relationship can be preset. The topic keywords can be topic labels, the association relation between the topics and the topic keywords is realized in a label form, and after the corresponding relation between the text information and the target topics is determined, the topic labels can be matched with the user keywords.
After the target text keywords in the text information are matched with topic keywords in a preset topic matching relation, target topics corresponding to the target text keywords in the text information can be determined, wherein the number of the target topics corresponding to the text information is variable, as shown in table 1, the target text keywords of the text information 1 are E-commerce websites A and financial fraud cases (the financial fraud cases are not written in table 1), and the topic keywords of the E-commerce websites are E-commerce websites A, E-commerce websites B and E-commerce websites C. In the embodiment of the application, the text information 1 corresponds to the E-commerce website (target text keyword) and the A-commerce website (topic keyword) corresponds to the E-commerce website (topic), namely, the A-commerce website keyword in the text information 1 is matched with the A-commerce website keyword in the E-commerce website topic, so that the target topic corresponding to the target text keyword in the text information 1 can be determined to be the E-commerce website topic. Referring to table 1, table 1 is one illustration of topic determination based on a preset topic matching relationship.
TABLE 1
203. Determining a user to be pushed according to at least one topic keyword in the target topics through matching of the at least one topic keyword and a user keyword, wherein the user to be pushed corresponds to the user keyword, and the user keyword is used for determining topic keywords associated with the user to be pushed;
it can be understood that after the target topic corresponding to the text information is determined, the user to be pushed can be determined by matching the topic keyword of the target topic with the user keyword of the user to be pushed. The matching method between the topic keyword and the user keyword (between two groups of words) may be a method of searching for a word co-occurring in the two groups of words, or a method of calculating cosine similarity between word vectors, or a method of neural network similarity matching, which is not limited herein.
In the embodiment of the application, the user keywords and the user have an association relationship, and the association relationship can be preset. The user keyword may be a user portrait, namely a user portrait tag (image tag), the text information also has a corresponding text information portrait, namely an article portrait tag (article image tag), the text information portrait includes topic keywords under a target topic corresponding to the text information, so that matching the text information portrait with the user portrait may mean that the topic keywords of the target topic are matched with the user keywords of the user, so as to determine the association relationship between the text information and the user, namely, determine to which users to be pushed the text information should be pushed.
After topic keywords of the target topics are matched with user keywords of the user to be pushed, the user to be pushed can be determined, as shown in table 2, the target topics corresponding to the text information 1 are e-commerce websites and fraud cases, wherein the e-commerce websites topics are provided with topic keywords of the e-commerce websites B, and the topic keywords are matched with the e-commerce websites of the user keywords B, so that the text information 1 can be determined to be pushed to the user 1to be pushed. From the above examples, it can be seen that, even if the user 1to be pushed does not have the target text keyword "a e-commerce website" of the text information 1, the embodiment of the present application can obtain the pushing of the text information 1, and the text information 1 page is interested in the user 1to be pushed, so that the reading experience of the user 1to be pushed can be improved, and a better pushing effect is achieved. Referring to table 2, table 2 is a schematic illustration of user pushing situations based on a preset topic matching relationship.
TABLE 2
204. And pushing the text information to the user to be pushed.
It should be understood that the server may push text information to the terminal device of the user to be pushed through the network, so that the terminal device of the user to be pushed displays the text information, or may store the text information in a storage module of the terminal device, and display the text information when the user to be pushed needs to view the related text information, or may embed the text information as a data code into a code library of the terminal device. The text information may be displayed as a background notification or may be displayed in an application.
In the embodiment of the application, the content actually expressed by the article can be covered by the topic keywords of the topic by determining the target topic of the text information and then matching according to the topic keywords of the target topic, so that the keywords closely related to the article but not appearing in the article are filled, the user matching is performed by the topic keywords, and the matched keywords are closer to the content actually expressed by the article, so that a better pushing effect can be achieved.
Optionally, in an optional embodiment of the method for pushing text information provided by the embodiment of the present application on the basis of the respective embodiments corresponding to fig. 2, determining, according to a preset topic matching relationship, a target topic corresponding to the target text keyword in the text information by matching the target text keyword with the topic keyword includes:
generating word vectors of the target text keywords through a word vector model;
performing accumulation processing and normalization processing on word vectors of the target text keywords to obtain accumulated word vectors of the text information;
generating word vectors of topic keywords through a word vector model;
the word vectors of the topic keywords are subjected to accumulation processing and normalization processing, so that accumulated word vectors of topics are obtained;
Calculating a first cosine similarity score between the accumulated word vectors of the text information and the accumulated word vectors of the topics;
Selecting a target topic from M topics according to the first cosine similarity score, wherein the target topic is the first N topics with the first cosine similarity score ordered from big to small, M is an integer greater than or equal to 1, N is an integer greater than or equal to 1 and less than or equal to M.
In an embodiment Of the present application, the Word vector Model may be each Model in Word2vec, such as a Word Bag Model, skip-gram Model, or Continuous Word Bag Model (CBOW Model). The word vector model may be trained by gensim tools, and the trained word vector model may generate a word vector of the target text keyword or generate a word vector of the topic keyword. The generation of the word vector by the word vector model is one of the vectorization processing methods, and the word vector may also be generated by other vectorization processing methods, which are not particularly limited herein.
The word vectors are accumulated and normalized to form a plurality of vectors, and in the embodiment of the application, the text information comprises one or more target text keywords, so that the word vectors of the one or more target text keywords are also corresponding, and the word vectors of the target text keywords are accumulated and normalized to obtain an accumulated word vector, namely the accumulated word vector corresponding to the text information. The topics comprise one or more topic keywords, each topic keyword generates a word vector, and the word vectors of the topics are subjected to accumulation processing and normalization processing to obtain an accumulated word vector, namely the accumulated word vector of the topics.
It is appreciated that calculating a first cosine similarity score between the accumulated word vector of text information and the accumulated word vector of topics may be calculated by a formula. The similarity of the two vectors is evaluated by calculating the cosine value of the included angle of the two vectors, and the description is omitted here.
In the embodiment of the application, one text message can be matched with a plurality of topics, so that a plurality of cosine similarities can be calculated, the cosine similarities are arranged from large to small, topics corresponding to the first N cosine similarities are taken as target topics, namely the first N topics with the highest similarity with one text message are selected as target topics. These top N topics may also be further screened by human, without limitation.
In the embodiment of the application, a plurality of text messages can be matched with one topic, as shown in fig. 3, a plurality of cosine similarities can be calculated, the cosine similarities are arranged from large to small, and the text messages corresponding to the previous cosine similarities are taken as the text messages recovered from the text message database by the server. After the server acquires the text information from the text information database, the text information can be processed and pushed, and all the text information in the text information database is not required to be processed and pushed, so that the burden of the server is greatly reduced, and the text information matched with the topic can be directly displayed in an interface corresponding to the topic. For example, if there are 30 text messages under the topic of the e-commerce web site, the text messages may be displayed in the interface of the topic of the e-commerce web site.
Fig. 3 shows a schematic diagram of matching topics with text information, and in the embodiment of the present application, vectorization processing is performed on a topic keyword set corresponding to each topic to generate word vectors of topic keywords, and then the word vectors of each topic keyword are accumulated and normalized to obtain accumulated word vectors (topic vector) of topics. Meanwhile, extracting keywords of the text information through a keyword extraction technology, vectorizing the keywords of the text information to generate word vectors of the keywords (target text keywords) of the text information, accumulating the word vectors and normalizing the word vectors to obtain text information vectors, calculating cosine similarity (cos similarity) between topic vectors and the text information vectors, and finally taking the text information corresponding to the cosine similarity as the text information recovered from the text information database by the server. After the recovery, topic keywords are included in the keywords of the text information.
In the embodiment of the application, a plurality of text messages can be matched with a plurality of topics, a plurality of cosine similarities can be calculated, the cosine similarities are arranged from large to small, each cosine similarity corresponds to a text message and topic combination, for example, a first cosine similarity corresponds to the text message 1 and the topic 1, a second cosine similarity corresponds to the text message 1 and the topic 2, a plurality of cosine similarities are taken, and a plurality of most similar combinations can be obtained. And then the topic with the highest similarity with a certain text message can be selected as a target topic through statistics.
Optionally, in an optional embodiment of the method for pushing text information provided by the embodiment of the present application on the basis of the respective embodiments corresponding to fig. 2, determining, by matching at least one topic keyword in the target topics with the user keyword, the user to be pushed includes:
If the user keywords are the same as at least one topic keyword in the target topics, determining the user to be pushed according to the user keywords.
In the embodiment of the present application, the matching method between the topic keyword and the user keyword (between two groups of words) may be searching for a word commonly occurring in the two groups of words, that is, the user keyword is the same as at least one topic keyword in the target topic, for example, the topic keyword of the text information 1 in table 2 has six words of a e-commerce website, B e-commerce website, C e-commerce website, financial fraud, telephone fraud and phishing case, and the user keyword of the user 1 to be pushed has three words of stock, B e-commerce website and fund, and the topic keyword "B e-commerce website" is the same as the user keyword "B e-commerce website", so that the user 1 to be pushed may be determined according to the user keyword "B e-commerce website", and the text information 1 may be pushed to the user 1 to be pushed next.
It may be understood that, in the embodiment of the present application, the server may search the user keywords first, that is, first, find whether the user keywords are the same as the first topic keywords, and then find whether the user keywords are the same as the second topic keywords, until whether the user keywords are the same as the last topic keywords are found, for example, in table 2, first, find whether the user keywords are the same as the "a e-commerce website", and then find whether the user keywords are the same as the "B e-commerce website", until find whether the user keywords are the same as the "phishing website", in this process, find the user keywords to be pushed corresponding to the user keywords, and then determine the user 1 to be pushed according to the user keywords B e-commerce website, and then push the text information 1 to the user 1 to be pushed. If the user 2 to be pushed also has the user keyword 'B e-commerce website', the user 2 to be pushed is determined to be the target of pushing the text information 1.
Fig. 4 shows a schematic diagram of matching text information with a user in the embodiment of the present application, and it can be seen that the target topics corresponding to the text information in fig. 4 are: the method comprises the steps of television dramas, face-lifting and variety shows, wherein topic keywords corresponding to the television dramas have even dramas, the user keywords of the user above the figure 4 are found to have even dramas, the user above the figure 4 is determined to be the user to be pushed, the text information is immediately pushed to the user above the figure 4, or the topic keywords corresponding to the face-lifting are provided with double-fold eyelid cutting, the user keywords of the user above the figure 4 are also provided with double-fold eyelid cutting, the user above the figure 4 is determined to be the user to be pushed, and the text information is immediately pushed to the user above the figure 4. And the topic keywords corresponding to the variety program comprise XX guard and talk show, and if the user keywords of the user below the figure 4 are found to comprise XX guard and talk show, the user below the figure 4 is determined to be the user to be pushed, and then the text information is pushed to the user below the figure 4.
Optionally, in an optional embodiment of the method for pushing text information according to the embodiment of the present application based on the respective embodiments corresponding to fig. 2, after determining, by matching the target text keyword with the topic keyword, a target topic corresponding to the target text keyword in the text information, the method further includes:
If the user keyword is the same as at least one topic keyword in the target topics, Y text messages are selected from the X text messages according to the topic keyword for pushing, the at least one topic keyword of the Y text messages is the same as the user keyword, X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1 and less than or equal to X.
In the embodiment of the application, X pieces of text information can be processed at the same time. When the X text messages are processed at the same time, if the user keywords are the same as at least one topic keyword in the target topics, Y text messages can be determined according to the same topic keywords, namely, the topic keywords of the X text messages can be searched in the X text messages, if the same topic keywords exist in the text messages, the text messages can be extracted, and Y text messages are finally obtained, wherein the same topic keywords exist in the Y text messages, namely, at least one topic keyword of the Y text messages is the same as the user keywords.
For example, if the same topic keyword in table 2 is a B e-commerce website, text information of the B e-commerce website in the topic keyword corresponding to the text information may be searched, and Y text information may be obtained by extracting the text information, where the B e-commerce website is included in the Y text information.
It will be appreciated that after Y text messages are selected, the Y text messages may be pushed to users to be pushed having the same user keywords as required.
According to the method for selecting Y text messages, text messages with other same topic keywords can be selected, so that all text messages which can be matched with users are obtained, and a text message database is formed.
Optionally, in an optional embodiment of the method for pushing text information provided by the embodiment of the present application on the basis of the respective embodiments corresponding to fig. 2, before determining, according to a preset topic matching relationship, a target topic corresponding to the target text keyword in the text information by matching the target text keyword with the topic keyword, the method further includes:
acquiring sample text information, wherein the sample text information comprises sample text keywords;
Clustering the sample text keywords by a clustering algorithm;
selecting topics from sample text keywords in the clusters;
Selecting topic keywords from a preset word stock according to topics, wherein the topic keywords have association relation with the topics;
And establishing a preset topic matching relation according to the topics and the topic keywords.
In the embodiment of the present application, the sample text keywords in the sample text information may be extracted by a keyword extraction technique, which is not described herein. The clustering algorithm in the embodiment of the application can be a kmeans algorithm. Clustering the sample text keywords through a clustering algorithm to form at least one cluster, and selecting topics from the sample text keywords in the cluster, for example, if the sample text keywords in a certain cluster include an e-commerce website, an a-commerce website, a B-commerce website and a C-commerce website, the e-commerce website can be selected as topics, the selecting process can be selected manually, the clustering center can be calculated through an algorithm for calculating the clustering center, the sample text keywords in the clustering center are selected as topics, or one sample text keyword is selected from the sample text keywords through other algorithms as topics, and the selecting process is not limited herein. After the topic is selected, topic keywords related to the topic can be selected from a preset word stock, and then a preset topic matching relationship is established, wherein the preset topic matching relationship comprises topics and topic keywords, and the topics and the topic keywords have an association relationship as shown in table 3. Referring to table 3, table 3 is an illustration of the correspondence between topics and topic keywords.
TABLE 3 Table 3
It is understood that words in the topic may or may not appear repeatedly in the topic keywords. Topics and topic keywords in table 3 are only used as examples, and other preset topic matching relationships can be established according to the method provided by the embodiment of the present application, and are not described herein.
Optionally, in an optional embodiment of the method for pushing text information provided by the embodiment of the present application based on the respective embodiments corresponding to fig. 2, selecting, according to a topic, a topic keyword from a preset word stock includes:
Generating word vectors of topics and word vectors of candidate topic keywords in a preset word bank through a word vector model;
Calculating a second cosine similarity score between the word vector of the topic and the word vector of the candidate topic keyword;
Selecting topic keywords from a preset word stock, wherein the topic keywords are the first L candidate topic keywords with second similarity scores ordered from large to small, and L is an integer greater than or equal to 1.
The topic keywords are selected from a preset word stock according to topics, can be selected manually, and can also be extracted through an algorithm. Firstly, generating Word vectors of topics and Word vectors of candidate topic keywords in a preset Word stock through a Word vector model, wherein the Word vector model can be any model in Word2vec, and the number of the candidate topic keywords in the preset Word stock is one or more. After the word vector is generated, a second cosine similarity score can be obtained through calculation of a cosine similarity algorithm, the second cosine similarity score can describe the similarity degree between the topic and the candidate topic keywords, and the higher the second cosine similarity score is, the higher the similarity degree is. The second cosine similarity scores can be ranked according to the big-small order, if the second cosine similarity score of the candidate topic keywords is high, the candidate topic keywords are ranked in front, and then the first L candidate topic keywords are taken as topic keywords corresponding to the topic.
Among the first L candidate topic keywords, a manual screening may be performed, and then the candidate topic keywords after the manual screening may be used as topic keywords corresponding to the topic. Of course, the screening may be performed without manual screening or by other algorithms, and is not particularly limited herein. It should be noted that, the information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
Referring to fig. 5, fig. 5 is a schematic diagram of an embodiment of a text information pushing device according to an embodiment of the present application, and the text information pushing device 500 includes:
An obtaining module 501, configured to obtain text information, where the text information includes a target text keyword;
The processing module 502 is configured to determine, according to a preset topic matching relationship, a target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword, where the preset topic matching relationship includes an association relationship between the topic keyword and the topic, and the target topic includes at least one topic keyword;
The processing module 502 is further configured to determine, according to at least one topic keyword in the target topic, a user to be pushed through matching of the at least one topic keyword with a user keyword, where the user to be pushed corresponds to the user keyword, and the user keyword is used to determine a topic keyword associated with the user to be pushed;
A pushing module 503, configured to push text information to a user to be pushed.
Optionally, on the basis of the foregoing respective embodiments corresponding to fig. 5, in an optional embodiment of the text information pushing device 500 provided by the embodiment of the present application, the processing module 502 is further configured to:
generating word vectors of the target text keywords through a word vector model;
performing accumulation processing and normalization processing on word vectors of the target text keywords to obtain accumulated word vectors of the text information;
generating word vectors of topic keywords through a word vector model;
the word vectors of the topic keywords are subjected to accumulation processing and normalization processing, so that accumulated word vectors of topics are obtained;
Calculating a first cosine similarity score between the accumulated word vectors of the text information and the accumulated word vectors of the topics;
Selecting a target topic from M topics according to the first cosine similarity score, wherein the target topic is the first N topics with the first cosine similarity score ordered from big to small, M is an integer greater than or equal to 1, N is an integer greater than or equal to 1 and less than or equal to M.
Optionally, on the basis of the foregoing respective embodiments corresponding to fig. 5, in an optional embodiment of the text information pushing device 500 provided by the embodiment of the present application, the processing module 502 is further configured to: if the user keywords are the same as at least one topic keyword in the target topics, determining the user to be pushed according to the user keywords.
Optionally, in an alternative embodiment of the text information pushing device 500 provided by the embodiment of the present application based on the embodiments corresponding to fig. 5, referring to fig. 6, the text information pushing device 500 further includes a text information processing module 504, where the text information processing module 504 is configured to select Y text information from X text information to push according to the topic keyword if the user keyword is the same as at least one topic keyword in the target topic, the at least one topic keyword of the Y text information is the same as the user keyword, X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1 and less than or equal to X.
Optionally, in an optional embodiment of the text information pushing device 500 provided by the embodiment of the present application, referring to fig. 7, on the basis of the respective embodiments corresponding to fig. 5, the text information pushing device 500 further includes a preset topic matching relationship module 505, where the preset topic matching relationship module is configured to obtain sample text information, and the sample text information includes a sample text keyword;
Clustering the sample text keywords by a clustering algorithm;
selecting topics from sample text keywords in the clusters;
Selecting topic keywords from a preset word stock according to topics, wherein the topic keywords have association relation with the topics;
And establishing a preset topic matching relation according to the topics and the topic keywords.
Optionally, on the basis of the foregoing respective embodiments corresponding to fig. 5, in an optional embodiment of the text information pushing device 500 provided by the embodiment of the present application, the preset topic matching relationship module 505 is further configured to: generating word vectors of topics and word vectors of candidate topic keywords in a preset word bank through a word vector model;
Calculating a second cosine similarity score between the word vector of the topic and the word vector of the candidate topic keyword;
Selecting topic keywords from a preset word stock, wherein the topic keywords are the first L candidate topic keywords with second similarity scores ordered from large to small, and L is an integer greater than or equal to 1.
Fig. 8 is a schematic diagram of a server structure provided by an embodiment of the present invention, where the server 800 may vary considerably in configuration or performance, and may include one or more central processing units (central processing units, CPUs) 822 (e.g., one or more processors) and memory 832, one or more storage mediums 830 (e.g., one or more mass storage devices) storing applications 842 or data 844. Wherein the memory 832 and the storage medium 830 may be transitory or persistent. The program stored in the storage medium 830 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 822 may be configured to communicate with the storage medium 830 to execute a series of instruction operations in the storage medium 830 on the server 800.
The server 800 may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input/output interfaces 858, and/or one or more operating systems 841, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like.
The steps performed by the server 800 in the above embodiments may be based on the server structure shown in fig. 8.
In an embodiment of the present application, the central processor 822 included in the server 800 further has the following functions:
acquiring text information, wherein the text information comprises target text keywords;
determining a target topic corresponding to the target text keyword in the text information through the matching of the target text keyword and the topic keyword according to a preset topic matching relation, wherein the preset topic matching relation comprises an association relation between the topic keyword and the topic, and the target topic comprises at least one topic keyword;
Determining a user to be pushed according to at least one topic keyword in the target topics through matching of the at least one topic keyword and a user keyword, wherein the user to be pushed corresponds to the user keyword, and the user keyword is used for determining the topic keyword associated with the user to be pushed;
And pushing the text information to the user to be pushed.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Claims (11)
1. A method of text messaging pushing, comprising:
acquiring text information, wherein the text information comprises target text keywords;
determining a target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword according to a preset topic matching relation, wherein the preset topic matching relation comprises an association relation between the topic keyword and the topic, and the target topic comprises at least one topic keyword, and cosine similarity between the target text keyword corresponding to the target topic and the topic keyword meets a preset condition;
Determining a user to be pushed according to the at least one topic keyword in the target topics through matching of the at least one topic keyword and a user keyword, wherein the user to be pushed corresponds to the user keyword, and the user keyword is used for determining topic keywords associated with the user to be pushed;
Pushing the text information to the user to be pushed;
According to a preset topic matching relationship, determining the target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword comprises:
Generating word vectors of the target text keywords through a word vector model;
performing accumulation processing and normalization processing on word vectors of the target text keywords to obtain accumulated word vectors of the text information;
generating word vectors of the topic keywords through the word vector model;
performing accumulation processing and normalization processing on word vectors of the topic keywords to obtain accumulated word vectors of the topics;
calculating a first cosine similarity score between the accumulated word vector of the text information and the accumulated word vector of the topic;
Selecting the target topics from M topics according to the first cosine similarity score, wherein the target topics are the first N topics with the first cosine similarity score ordered from large to small, M is an integer greater than or equal to 1, N is an integer greater than or equal to 1 and less than or equal to M;
Before determining the target topic corresponding to the target text keyword in the text information through the matching of the target text keyword and the topic keyword according to the preset topic matching relation, the method further comprises:
Acquiring sample text information, wherein the sample text information comprises sample text keywords;
clustering the sample text keywords by a clustering algorithm;
Selecting the topic from the sample text keywords in the cluster;
Selecting the topic keywords from a preset word stock according to the topics, wherein the topic keywords have association relation with the topics;
and establishing the preset topic matching relation according to the topics and the topic keywords.
2. The method of claim 1, wherein the determining, from the at least one topic keyword in the target topic, the user to be pushed by matching the at least one topic keyword with a user keyword comprises:
And if the user keywords are the same as the at least one topic keyword in the target topics, determining the user to be pushed according to the user keywords.
3. The method according to claim 1, wherein after determining the target topic corresponding to the target text keyword in the text information by matching the target text keyword with the topic keyword according to the preset topic matching relationship, the method further comprises:
And if the user keyword is the same as the at least one topic keyword in the target topic, selecting Y pieces of text information from X pieces of text information according to the topic keyword to push, wherein at least one topic keyword of the Y pieces of text information is the same as the user keyword, X is an integer greater than or equal to 1, Y is an integer greater than or equal to 1 and less than or equal to X.
4. The method of claim 1, wherein the selecting topic keywords from a preset word stock according to the topics comprises:
generating word vectors of the topics and word vectors of candidate topic keywords in the preset word stock through a word vector model;
calculating a second cosine similarity score between the word vector of the topic and the word vector of the candidate topic keyword;
selecting the topic keywords from the preset word stock, wherein the topic keywords are the first L candidate topic keywords with the second cosine similarity scores ordered from large to small, and L is an integer greater than or equal to 1.
5. A text information pushing device, characterized by comprising:
The system comprises an acquisition module, a search module and a search module, wherein the acquisition module is used for acquiring text information, and the text information comprises target text keywords;
the processing module is used for determining a target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword according to a preset topic matching relation, wherein the preset topic matching relation comprises an association relation between the topic keyword and the topic, the target topic comprises at least one topic keyword, and cosine similarity between the target text keyword corresponding to the target topic and the topic keyword meets a preset condition;
the processing module is further configured to determine a user to be pushed according to the at least one topic keyword in the target topic, through matching of the at least one topic keyword and a user keyword, where the user to be pushed corresponds to the user keyword, and the user keyword is used to determine a topic keyword associated with the user to be pushed;
the pushing module is used for pushing the text information to the user to be pushed;
the processing module is also used for:
generating word vectors of the target text keywords through a word vector model;
Performing accumulation processing and normalization processing on word vectors of the target text keywords to obtain accumulated word vectors of text information;
Generating word vectors of topic keywords through the word vector model;
Performing accumulation processing and normalization processing on word vectors of the topic keywords to obtain accumulated word vectors of topics;
calculating a first cosine similarity score between the accumulated word vector of the text information and the accumulated word vector of the topic;
selecting a target topic from M topics according to the first cosine similarity score, wherein the target topic is the first N topics with the first cosine similarity score ordered from large to small, M is an integer greater than or equal to 1, N is an integer greater than or equal to 1 and less than or equal to M;
The device further comprises a preset topic matching relation module, wherein the preset topic matching relation module is used for acquiring sample text information, and the sample text information comprises sample text keywords;
Clustering the sample text keywords by a clustering algorithm;
selecting topics from sample text keywords in the clusters;
Selecting topic keywords from a preset word stock according to topics, wherein the topic keywords have association relation with the topics;
And establishing a preset topic matching relation according to the topics and the topic keywords.
6. The apparatus of claim 5, wherein the processing module is further configured to: if the user keywords are the same as at least one topic keyword in the target topics, determining the user to be pushed according to the user keywords.
7. The apparatus of claim 5, further comprising a text information processing module, wherein the text information processing module is configured to select Y text information from the X text information to push according to the topic keyword if the user keyword is the same as at least one topic keyword of the target topic, the at least one topic keyword of the Y text information is the same as the user keyword, X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1 and less than or equal to X.
8. The apparatus of claim 5, wherein the preset topic matching relationship module is further configured to: generating word vectors of topics and word vectors of candidate topic keywords in a preset word bank through a word vector model;
Calculating a second cosine similarity score between the word vector of the topic and the word vector of the candidate topic keyword;
And selecting topic keywords from a preset word stock, wherein the topic keywords are the first L candidate topic keywords with the second cosine similarity scores ordered from large to small, and L is an integer greater than or equal to 1.
9. A server, comprising: memory, transceiver, processor, and bus system;
Wherein the memory is used for storing programs;
the processor is used for executing the program in the memory, and comprises the following steps:
acquiring text information, wherein the text information comprises target text keywords;
Determining a target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword according to a preset topic matching relation, wherein the preset topic matching relation comprises an incidence relation between the topic keyword and the topic, and the target topic comprises at least one topic keyword, and cosine similarity between the target text keyword corresponding to the target topic and the topic keyword meets a preset condition;
determining a user to be pushed according to the at least one topic keyword in the target topics through matching of the at least one topic keyword and a user keyword, wherein the user to be pushed corresponds to the user keyword, and the user keyword is used for determining topic keywords associated with the user to be pushed;
Pushing the text information to the user to be pushed;
the bus system is used for connecting the memory and the processor so as to enable the memory and the processor to communicate;
According to a preset topic matching relationship, determining the target topic corresponding to the target text keyword in the text information through matching of the target text keyword and the topic keyword comprises:
Generating word vectors of the target text keywords through a word vector model;
performing accumulation processing and normalization processing on word vectors of the target text keywords to obtain accumulated word vectors of the text information;
generating word vectors of the topic keywords through a word vector model;
performing accumulation processing and normalization processing on word vectors of the topic keywords to obtain accumulated word vectors of the topics;
calculating a first cosine similarity score between the accumulated word vector of the text information and the accumulated word vector of the topic;
Selecting the target topics from M topics according to the first cosine similarity score, wherein the target topics are the first N topics with the first cosine similarity score ordered from large to small, M is an integer greater than or equal to 1, N is an integer greater than or equal to 1 and less than or equal to M;
Before determining the target topic corresponding to the target text keyword in the text information by matching the target text keyword with the topic keyword according to the preset topic matching relationship, the method further comprises:
Acquiring sample text information, wherein the sample text information comprises sample text keywords;
clustering the sample text keywords by a clustering algorithm;
Selecting the topic from the sample text keywords in the cluster;
Selecting the topic keywords from a preset word stock according to the topics, wherein the topic keywords have association relation with the topics;
and establishing the preset topic matching relation according to the topics and the topic keywords.
10. A computer readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 4.
11. A computer program product comprising instructions which, when run on a computer or processor, cause the computer or processor to perform the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910564424.3A CN110413875B (en) | 2019-06-26 | 2019-06-26 | Text information pushing method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910564424.3A CN110413875B (en) | 2019-06-26 | 2019-06-26 | Text information pushing method and related device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110413875A CN110413875A (en) | 2019-11-05 |
| CN110413875B true CN110413875B (en) | 2024-06-07 |
Family
ID=68358382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910564424.3A Active CN110413875B (en) | 2019-06-26 | 2019-06-26 | Text information pushing method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110413875B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021092803A1 (en) * | 2019-11-13 | 2021-05-20 | 深圳市欢太科技有限公司 | Push user determination method and apparatus, server, and storage medium |
| CN110888990B (en) * | 2019-11-22 | 2024-04-12 | 深圳前海微众银行股份有限公司 | Text recommendation method, device, equipment and medium |
| CN111143506B (en) * | 2019-12-27 | 2023-11-03 | 汉海信息技术(上海)有限公司 | Topic content ordering method, topic content ordering device, server and storage medium |
| CN111159566A (en) * | 2019-12-31 | 2020-05-15 | 中国银行股份有限公司 | Information pushing method and device for financial market products |
| CN111368063B (en) * | 2020-03-06 | 2023-03-17 | 腾讯科技（深圳）有限公司 | Information pushing method based on machine learning and related device |
| CN111914079A (en) * | 2020-08-07 | 2020-11-10 | 上海梅斯医药科技有限公司 | Topic recommendation method and system based on user tags |
| CN114357278B (en) * | 2020-09-28 | 2024-03-19 | 腾讯科技（深圳）有限公司 | Topic recommendation method, device and equipment |
| CN114818706A (en) * | 2021-01-29 | 2022-07-29 | 阿里巴巴集团控股有限公司 | Text matching method and device and government affair service text matching method |
| CN113379481A (en) * | 2021-05-25 | 2021-09-10 | 北京大米科技有限公司 | Data processing method and device |
| CN113505293B (en) * | 2021-06-15 | 2024-03-19 | 深圳追一科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN115150462B (en) * | 2022-05-25 | 2023-10-31 | 东风柳州汽车有限公司 | Driving topic pushing method, device, equipment and storage medium |
| CN116992111B (en) * | 2023-09-28 | 2023-12-26 | 中国科学技术信息研究所 | Data processing method, device, electronic equipment and computer storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014110005A (en) * | 2012-12-04 | 2014-06-12 | Nec Software Tohoku Ltd | Information search device and information search method |
| 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 |
| CN107767172A (en) * | 2017-10-12 | 2018-03-06 | 百度在线网络技术（北京）有限公司 | Information-pushing method, device, server and medium |
| CN107944033A (en) * | 2017-12-13 | 2018-04-20 | 北京百度网讯科技有限公司 | Associate topic and recommend method and apparatus |
| CN107943895A (en) * | 2017-11-16 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
| CN108153824A (en) * | 2017-12-06 | 2018-06-12 | 阿里巴巴集团控股有限公司 | The determining method and device of targeted user population |
| CN108920675A (en) * | 2018-07-09 | 2018-11-30 | 北京百悟科技有限公司 | A kind of method, apparatus of information processing, computer storage medium and terminal |
-
2019
- 2019-06-26 CN CN201910564424.3A patent/CN110413875B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014110005A (en) * | 2012-12-04 | 2014-06-12 | Nec Software Tohoku Ltd | Information search device and information search method |
| 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 |
| CN107767172A (en) * | 2017-10-12 | 2018-03-06 | 百度在线网络技术（北京）有限公司 | Information-pushing method, device, server and medium |
| CN107943895A (en) * | 2017-11-16 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
| CN108153824A (en) * | 2017-12-06 | 2018-06-12 | 阿里巴巴集团控股有限公司 | The determining method and device of targeted user population |
| CN107944033A (en) * | 2017-12-13 | 2018-04-20 | 北京百度网讯科技有限公司 | Associate topic and recommend method and apparatus |
| CN108920675A (en) * | 2018-07-09 | 2018-11-30 | 北京百悟科技有限公司 | A kind of method, apparatus of information processing, computer storage medium and terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110413875A (en) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110413875B (en) | Text information pushing method and related device | |
| CN108334533B (en) | Keyword extraction method and device, storage medium and electronic device | |
| US11334635B2 (en) | Domain specific natural language understanding of customer intent in self-help | |
| CN109145280B (en) | Information pushing method and device | |
| CA3083723C (en) | Method and apparatus for providing personalized self-help experience | |
| CN110147425B (en) | Keyword extraction method and device, computer equipment and storage medium | |
| US20160189047A1 (en) | Method and System for Entity Linking | |
| CN109885773A (en) | A kind of article personalized recommendation method, system, medium and equipment | |
| CN110413872B (en) | Method and device for displaying information | |
| WO2015135110A1 (en) | Systems and methods for keyword suggestion | |
| CN111447575B (en) | Short message pushing method, device, equipment and storage medium | |
| US20220358552A1 (en) | Methods and systems for hair-service based digital image searching and ranking | |
| CN114330329A (en) | Service content searching method and device, electronic equipment and storage medium | |
| CN108280081B (en) | Method and device for generating webpage | |
| CN110750707A (en) | Keyword recommendation method and device and electronic equipment | |
| CN110245357B (en) | Main entity identification method and device | |
| CN107153697A (en) | Product search method and device in a kind of commodity transaction website | |
| CN111737607B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN108470289A (en) | Virtual objects distribution method and equipment based on electric business shopping platform | |
| CN110351183B (en) | Resource collection method and device in instant messaging | |
| CN108509449B (en) | Information processing method and server | |
| CN115982503A (en) | Website information acquisition method and system based on cloud platform | |
| US20180276294A1 (en) | Information processing apparatus, information processing system, and information processing method | |
| CN115048504A (en) | Information pushing method and device, computer equipment and computer readable storage medium | |
| JP2020042545A (en) | Information processing device, information processing method, and program |
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 |