CN108280200B

CN108280200B - Method and device for pushing information

Info

Publication number: CN108280200B
Application number: CN201810085111.5A
Authority: CN
Inventors: 岑敏强; 刘勇
Original assignee: Baidu Online Network Technology Beijing Co Ltd
Current assignee: Baidu Online Network Technology Beijing Co Ltd
Priority date: 2018-01-29
Filing date: 2018-01-29
Publication date: 2021-11-09
Anticipated expiration: 2038-01-29
Also published as: CN108280200A

Abstract

The embodiment of the application discloses a method and a device for pushing information. One embodiment of the method comprises: in response to receiving an access request of a user for a target site, determining whether the access request comprises search terms of the user; in response to determining that the access request includes the user's search terms, performing the steps of: inputting the search word into a pre-trained label recognition model to obtain a label for representing the user attribute of the user, wherein the label recognition model is used for representing the corresponding relation between the search word of the user and the label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; and pushing the matched first text. The embodiment improves the diversity of information push.

Description

Method and device for pushing information

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to a method and a device for pushing information.

Background

Information push, namely 'web broadcasting', is a new technology for reducing information overload by periodically transmitting information required by users on the internet through a certain technical standard or protocol. Currently, information for pushing generally includes the following two setting modes: the first is that a technician sets different information according to different sites (pages), and when a user initiates an operation request for a specific page, preset information corresponding to the page is displayed; the second is that the technician sets up uniform information for the website in advance (e.g., your good weather today).

Disclosure of Invention

The embodiment of the application provides a method and a device for pushing information.

In a first aspect, an embodiment of the present application provides a method for pushing information, where the method includes: in response to receiving an access request of a user for a target site, determining whether the access request comprises search terms of the user; in response to determining that the access request includes the user's search terms, performing the steps of: inputting the search word into a pre-trained label recognition model to obtain a label for representing the user attribute of the user, wherein the label recognition model is used for representing the corresponding relation between the search word of the user and the label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; and pushing the matched first text.

In some embodiments, the method further comprises: in response to determining that the access request does not include the user's search terms, performing the steps of: acquiring a pre-stored historical search term set of a user; respectively inputting the historical search words in the historical search word set into a tag identification model to obtain a tag set for representing user attributes of the user; matching a second text from a preset text set based on the obtained labels in the label set and a preset matching relation between the labels and the text; and pushing the matched second text.

In some embodiments, matching a second text from a preset text set based on the obtained tags in the tag set and a preset matching relationship between the tags and the text includes: determining whether at least two label subsets are included in the label set, wherein the label subsets include at least two labels and the included labels are the same; in response to determining that at least two subsets of tags are included in the set of tags, performing the steps of: for each of at least two subsets of tags, determining a quantity value of tags in the subset of tags; determining the label corresponding to the maximum quantity value in the determined quantity values as a target label; and matching a second text from a preset text set based on the determined target label and a preset matching relation between the label and the text.

In some embodiments, the text in the text collection has a preset text priority; and matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text, wherein the matching relation comprises the following steps: matching a target text set from a preset text set based on the obtained label and a preset matching relation between the label and the text; and selecting a first text from the target text set based on the text priority of each text in the target text set.

In some embodiments, the tag recognition model is trained by: obtaining a plurality of sample search terms and a label which is calibrated in advance and corresponds to each sample search term in the plurality of sample search terms; and training to obtain a label recognition model by using a machine learning method and taking each sample search word in the plurality of sample search words as input and taking a label corresponding to each sample search word in the plurality of sample search words, which is calibrated in advance, as output.

In a second aspect, an embodiment of the present application provides an apparatus for pushing information, where the apparatus includes: the determining unit is configured to respond to the received access request of the user for the target site, and determine whether the access request comprises the search word of the user; a first execution unit configured to, in response to determining that the access request includes a search term of the user, perform the steps of: inputting the search word into a pre-trained label recognition model to obtain a label for representing the user attribute of the user, wherein the label recognition model is used for representing the corresponding relation between the search word of the user and the label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; and pushing the matched first text.

In some embodiments, the apparatus further comprises: a second execution unit configured to, in response to determining that the access request does not include the user's search term, perform the steps of: acquiring a pre-stored historical search term set of a user; respectively inputting the historical search words in the historical search word set into a tag identification model to obtain a tag set for representing user attributes of the user; matching a second text from a preset text set based on the obtained labels in the label set and a preset matching relation between the labels and the text; and pushing the matched second text.

In some embodiments, the second execution unit comprises: the system comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining whether at least two label subsets are included in a label set, the label subsets comprise at least two labels, and the included labels are the same; an execution module configured to, in response to determining that the set of tags includes at least two subsets of tags, perform the steps of: for each of at least two subsets of tags, determining a quantity value of tags in the subset of tags; determining the label corresponding to the maximum quantity value in the determined quantity values as a target label; and matching a second text from a preset text set based on the determined target label and a preset matching relation between the label and the text.

In some embodiments, the text in the text collection has a preset text priority; and the first execution unit includes: the matching module is configured to match a target text set from a preset text set based on the obtained tags and a preset matching relationship between the tags and the text; and the selecting module is configured to select a first text from the target text set based on the text priority of each text in the target text set.

In a third aspect, an embodiment of the present application provides a server, 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 one or more processors, the one or more processors implement the method of any embodiment of the method for pushing information.

In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method of any one of the above-mentioned methods for pushing information.

According to the method and the device for pushing the information, whether an access request of a user for a target site comprises a search word of the user is determined by responding to the received access request of the user; in response to determining that the access request includes the user's search terms, performing the steps of: inputting the search terms into a pre-trained label recognition model to obtain a label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; the matched first text is pushed, so that the search word can be identified as the label through a pre-established model in response to the search word obtained by the user, and the text corresponding to the identified label is pushed to the user, so that the diversity of information pushing is improved.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow diagram of one embodiment of a method for pushing information, according to the present application;

FIG. 3 is a schematic diagram of an application scenario of a method for pushing information according to the present application;

FIG. 4 is a flow diagram of yet another embodiment of a method for pushing information according to the present application;

FIG. 5 is a schematic block diagram illustrating one embodiment of an apparatus for pushing information according to the present application;

FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing a server according to embodiments of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

Fig. 1 shows an exemplary system architecture 100 to which embodiments of the present method for pushing information or apparatus for pushing information may be applied.

As shown in fig. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have various client applications installed thereon, such as a web browser application, a shopping-like application, a search-like application, an instant messaging tool, a mailbox client, social platform software, and the like.

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background web server providing support for web pages displayed on the

terminal devices

101, 102, 103. The background web server may analyze and perform other processing on the received data such as the web access request, and feed back a processing result (e.g., the first text) to the terminal device.

It should be noted that the method for pushing information provided by the embodiment of the present application is generally performed by the server 105, and accordingly, the apparatus for pushing information is generally disposed in the server 105.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2, a flow 200 of one embodiment of a method for pushing information in accordance with the present application is shown. The method for pushing the information comprises the following steps:

step 201, in response to receiving an access request of a user for a target site, determining whether the access request includes a search word of the user.

In this embodiment, an electronic device (e.g., a server shown in fig. 1) on which the method for pushing information operates may determine whether an access request includes a search term of a user in response to receiving the access request of the user for a target site through a wired connection manner or a wireless connection manner. The target site may be a website which is established in advance and is used for the user to access, and a text to be pushed to the user is preset for the target site (for example, "hello, wish you to be happy today"). Specifically, the electronic device may receive an access request for a target site sent by a user through a client (e.g.,

terminal devices

101, 102, and 103 shown in fig. 1). The access request may be an inbound request or a search request of the user, etc. The search term may specifically be a word, a sentence, or a voice input by the user, for example, "how much money the mobile phone is. Here, the access request may include a search word input by the user, or may be only an inbound request of the user without including the search word input by the user.

In response to determining that the access request includes the user's search terms, step 202, performing the steps of: inputting the search terms into a pre-trained label recognition model to obtain a label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; and pushing the matched first text.

In this embodiment, the electronic device on which the method for pushing information operates may perform the following steps in response to determining that the access request includes a search term of the user:

step 2021, inputting the search term into a label recognition model trained in advance to obtain a label for representing the user attribute of the user.

The user attributes may include natural attributes such as gender and age of the user, social attributes such as occupation and place of birth, and personal attributes such as interests and hobbies. Tags may include, but are not limited to, at least one of: words, numbers, words, phrases. Illustratively, the label used to characterize the age of the user may include a number, such as "under 18 years old"; tags used to characterize a user's profession may include words, such as "engineers". The resulting label may be one or more. The tag identification model may be used to characterize the correspondence of search terms of the user to tags that characterize user attributes of the user.

Specifically, as an example, the tag identification model may be a correspondence table which is pre-made by a technician based on statistics of a large number of search terms of users and tags for characterizing user attributes of the users and stores correspondence between a plurality of search terms and tags for characterizing user attributes of the users; or a calculation formula obtained by calculating similarity of a plurality of search terms and tags in a preset tag set, which is preset by a technician based on statistics of a large amount of data and stored in the electronic device. The calculation result of the calculation formula may be used to determine a label corresponding to each of the plurality of search terms. Specifically, for each search term in the plurality of search terms, the calculated label with the highest similarity to the search term may be determined as the label corresponding to the search term.

In some optional implementation manners of this embodiment, the label recognition model may be obtained by training through the following steps:

first, the electronic device may obtain a plurality of sample search terms and a label corresponding to each sample search term in the plurality of sample search terms, which is calibrated in advance.

Then, the electronic device may use a machine learning method to input each sample search term in the plurality of sample search terms, and train to obtain a tag identification model by using a tag corresponding to each sample search term in the plurality of sample search terms, which is calibrated in advance, as an output. Specifically, the electronic device may use a Naive Bayesian Model (NBM) or a Support Vector Machine (SVM) for classification, and the like, to input the plurality of sample search terms as a Model, output a label corresponding to each of the plurality of sample search terms calibrated in advance as an output, and train the label to obtain a label recognition Model by using a Machine learning method.

Particularly, when the search word input by the user is a sentence, before the search word is input into the tag recognition model, the electronic device may further perform word segmentation processing on the search word, and input the processed search word into the tag recognition model. As an example, the search term is "how much money a mobile phone is", the search term after the word segmentation process may include "a mobile phone" and "how much money", and further, the identified tag may include "mobile phone" and "money sensitive". It should be noted that the word segmentation is a well-known technology which is widely researched and applied at present, and is not described in detail herein.

Step 2022, matching the first text from the preset text set based on the obtained tag and the preset matching relationship between the tag and the text.

The preset text set may include a text to be pushed, which is input by a technician in advance through the electronic device. The first text may be a text in a preset text set, which is matched by the search term input by the user. The preset matching relationship may be a correspondence relationship between a label preset by a technician and a text in the text set. Specifically, as an example, the matching relationship may be a text in a text set corresponding to a tag; or one label corresponds to a plurality of texts in the text set. For example, the obtained label is "dietician", and the preset text corresponding to the label may be "hello, and the dietician should have the following skills: … … "; or, the obtained label is "movie", and the preset text corresponding to the label may include "hello, a movie is showing" and "hello, recommending the highest-scoring a movie for you". It should be noted that when multiple texts are matched through the tag, the multiple texts may be used as the first text.

In some optional implementations of the embodiment, the texts in the text set have a preset text priority, and the text priority is used to characterize a pushing order of the texts in the text set. Specifically, the text priority may be represented by a number, a letter, a symbol, or the like. For example, the priority level can be characterized by the size of a number, and the smaller the number, the higher the priority level. Here, based on the obtained tag and a preset matching relationship between the tag and the text, the electronic device may match the first text from a preset text set by the following steps:

firstly, based on the obtained tags and the preset matching relationship between the tags and the text, the electronic device may match a target text set from a preset text set. Wherein the target text set may include at least two texts. Here, the resultant tag may be one or more. The matching relationship between the label and the text may be that one label corresponds to a plurality of texts, or one label corresponds to one text. Furthermore, when the obtained tags are multiple or the matching relationship between the tags and the texts is that one tag corresponds to multiple texts, the electronic device may match a target text set including at least two texts from a preset text set.

Then, the electronic device may select the first text from the target text set based on the text priority of each text in the target text set. Specifically, the electronic device may determine a text with the highest text priority in the target text set as the first text.

Step 2023, pushing the matched first text.

Specifically, the electronic device may push the matched first text to a client (e.g.,

terminal devices

101, 102, and 103 shown in fig. 1) where the user is located.

With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the method for pushing information according to the present embodiment. In the application scenario of fig. 3, the server 301 may determine, in response to receiving an access request 302 of a user for a target site (e.g., may be in response to receiving the access request 302 sent by the user through the terminal device 303), whether the access request 302 includes a search term 3021 of the user; server 301 may then, in response to determining that access request 302 includes the user's search term 3021 (e.g., "a movie"), perform the following steps: inputting the search word 3021 into a label recognition model trained in advance, and obtaining a label 304 (e.g., "movie") for representing a user attribute of the user, where the label recognition model may be used to represent a correspondence between the search word of the user and the label for representing the user attribute of the user; matching a first text 305 (for example, "good, showing movie includes: A; B; C") from a preset text set based on the obtained label and a preset matching relationship between the label and the text; finally, the server 301 may push the matched first text 305. Specifically, as shown in fig. 3, the server 301 may push the first text 305 to the terminal device 303.

The method provided by the above embodiment of the application determines whether the access request includes a search word of the user by responding to the received access request of the user for the target site; in response to determining that the access request includes the user's search terms, performing the steps of: inputting the search terms into a pre-trained label recognition model to obtain a label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; the matched first text is pushed, so that the search word can be identified as the label through a pre-established model in response to the search word obtained by the user, and the text corresponding to the identified label is pushed to the user, so that the diversity of information pushing is improved.

With further reference to fig. 4, a flow 400 of yet another embodiment of a method for pushing information is shown. The flow 400 of the method for pushing information comprises the following steps:

in step 401, in response to receiving an access request of a user for a target site, it is determined whether the access request includes a search term of the user.

In this embodiment, an electronic device (e.g., a server shown in fig. 1) on which the method for pushing information operates may determine whether an access request includes a search term of a user in response to receiving the access request of the user for a target site through a wired connection manner or a wireless connection manner. The target site can be a website which is established in advance and used for a user to access, and a text to be pushed to the user is preset for the target site. Specifically, the electronic device may receive an access request for a target site, which is input by a user through a client. The access request may be an inbound request or a search request of the user, etc. The search word may specifically be a word, a sentence, or a voice input by the user. Here, the access request may include a search word input by the user, or may be only an inbound request of the user without including the search word input by the user.

Step 402, in response to determining that the access request does not include the user's search terms, performing the steps of: acquiring a pre-stored historical search term set of a user; respectively inputting the historical search words in the historical search word set into a tag identification model to obtain a tag set for representing user attributes of the user; matching a second text from a preset text set based on the obtained labels in the label set and a preset matching relation between the labels and the text; and pushing the matched second text.

In this embodiment, the electronic device on which the method for pushing information operates may perform the following steps in response to determining that the access request does not include the user's search term:

step 4021, acquiring a pre-stored historical search term set of the user.

The historical search terms may be search terms input by a user through a client (for example,

terminal devices

101, 102, 103 shown in fig. 1) within a preset historical time period. It is to be understood that, within the preset historical time period, the electronic device may receive a search term input by a user and store the search term input by the user.

Step 4022, respectively inputting the historical search words in the historical search word set into the tag identification model, and obtaining a tag set for representing the user attributes of the user.

It should be noted that the same search term may be included in the historical search term set; the same tag may be included in a set of tags. For example, if the user inputs "a movie" at 10:00 and 22:00 within a preset historical time period of "0: 00-24: 00", the historical search term set may include two search terms "a movie", and the tag set may include two tags "movie".

Step 4023, matching a second text from the preset text set based on the obtained tags in the tag set and the preset matching relationship between the tags and the text.

Wherein, the label set can comprise one or more labels. The preset text set may include a text to be pushed, which is previously input by a technician through the electronic device. The second text may be a text in a preset text set matched by the historical search terms of the user. The preset matching relationship may be a correspondence relationship between a label preset by a technician and a text in the text set. It should be noted that when multiple texts are matched through the tag, the multiple texts may be used as the second text.

In some optional implementation manners of this embodiment, based on the obtained tags in the tag set and a preset matching relationship between the tags and the text, the electronic device may match the second text from the preset text set by the following steps:

first, the electronic device may determine whether at least two tag subsets are included in the tag set, where the tag subsets may include at least two tags and the included tags are the same. For example, the set of tags includes tags that are "movies; a movie; a movie; book ", then" movie; a movie; the movie is determined as a label subset, and the label set movie only comprises one book label; a movie; a movie; book "does not include at least two subsets of tags.

Then, the electronic device may perform the following steps in response to determining that the tag set includes at least two tag subsets:

step 40231, determining, for each of at least two subsets of tags, a quantity value for the tags in the subset of tags.

As an example, the set of tags is "movie; a movie; a movie; a book; book ". The label subset is combined into 'movie'; a movie; movies "and" books; book ". The electronic device may determine a tag subset "movie; a movie; the number value of tags in movie "is" 3 "; a subset of tags "books; the number value of the tags in book "is" 2 ".

Step 40232, determining the label corresponding to the maximum quantitative value of the determined quantitative values as the target label.

For example, the "movie" is a subset of tags determined for the electronic device; a movie; the number value of the tags in movie "is" 3 "and the tag subset" book; the number value of the tags in the book is "2", and since the number value "3" is greater than the number value "2", the electronic device may determine the tag "movie" corresponding to the number value "3" as the target tag.

Step 40233, matching a second text from a preset text set based on the determined target label and the preset matching relationship between the label and the text.

The preset matching relationship may be a correspondence relationship between a label preset by a technician and a text in the text set. Specifically, as an example, the matching relationship may be a text in a text set corresponding to a tag; or one label corresponds to a plurality of texts in the text set. For example, the target label is "movie", and the preset text corresponding to the target label may be "hello, the movie being shown includes: a; b; and C', and then carrying out a chemical reaction. It should be noted that when multiple texts are matched through the target tag, the multiple texts may be used as the second text.

And step 4024, pushing the matched second text.

Specifically, the electronic device may push the matched second text to a client (e.g.,

terminal devices

101, 102, and 103 shown in fig. 1) where the user is located.

As can be seen from fig. 4, compared to the corresponding embodiment of fig. 2, the flow 400 of the method for pushing information in the present embodiment highlights the steps performed when the access request does not include the user's search terms. Therefore, the scheme described in the embodiment can introduce the historical search terms of the user, so that the flexibility of information push is improved, and the diversity of information push is further improved.

With further reference to fig. 5, as an implementation of the method shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for pushing information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be applied to various electronic devices.

As shown in fig. 5, the apparatus 500 for pushing information of the present embodiment includes: a determination unit 501 and a first execution unit 502. The determining unit 501 is configured to determine, in response to receiving an access request of a user for a target site, whether the access request includes a search term of the user; the first performing unit 502 is configured to, in response to determining that the access request includes a search term of the user, perform the steps of: inputting the search word into a pre-trained label recognition model to obtain a label for representing the user attribute of the user, wherein the label recognition model can be used for representing the corresponding relation between the search word of the user and the label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; and pushing the matched first text.

In this embodiment, the determining unit 501 may determine whether the access request includes the search term of the user in response to receiving the access request of the user for the target site through a wired connection manner or a wireless connection manner. The target site may be a website which is established in advance and is used for the user to access, and a text to be pushed to the user is preset for the target site (for example, "hello, wish you to be happy today"). Specifically, the determining unit 501 may receive an access request for a target site, which is input by a user through a client (for example, the

terminal devices

101, 102, 103 shown in fig. 1). The access request may be an inbound request or a search request of the user, etc. The search word may specifically be a word, a sentence, or a voice input by the user. Here, the access request may include a search word input by the user, or may be only an inbound request of the user without including the search word input by the user.

In this embodiment, the first execution unit 502 may, in response to determining that the access request includes the search term of the user, perform the following steps:

step 5021, inputting the search words into a label recognition model trained in advance to obtain labels used for representing user attributes of the user.

The user attributes may include natural attributes such as gender and age of the user, social attributes such as occupation and place of birth, and personal attributes such as interests and hobbies. Tags may include, but are not limited to, at least one of: words, numbers, words, phrases. The resulting label may be one or more. The tag identification model may be used to characterize the correspondence of search terms of the user to tags that characterize user attributes of the user.

Step 5022, matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text.

The preset text set may include a text to be pushed, which is input by a technician in advance through the electronic device. The first text may be a text matched by the search word input by the user. The preset matching relationship may be a correspondence relationship between a label preset by a technician and a text in the text set.

Step 5023, pushing the matched first text.

Specifically, the first executing unit 502 may push the matched first text to a client (e.g., the

terminal device

101, 102, 103 shown in fig. 1) where the user is located.

In some optional implementations of this embodiment, the apparatus 500 for pushing information may further include: a second execution unit (not shown in the figures) configured to, in response to determining that the access request does not include the user's search term, perform the steps of: acquiring a pre-stored historical search term set of a user; respectively inputting the historical search words in the historical search word set into a tag identification model to obtain a tag set for representing user attributes of the user; matching a second text from a preset text set based on the obtained labels in the label set and a preset matching relation between the labels and the text; and pushing the matched second text.

In some optional implementations of this embodiment, the second execution unit may include: a determining module (not shown in the figure) configured to determine whether at least two sub-sets of tags are included in the set of tags, wherein the sub-sets of tags may include at least two tags and the included tags are the same; an execution module (not shown in the figures) configured to, in response to determining that at least two subsets of tags are included in the set of tags, perform the steps of: for each of at least two subsets of tags, determining a quantity value of tags in the subset of tags; determining the label corresponding to the maximum quantity value in the determined quantity values as a target label; and matching a second text from a preset text set based on the determined target label and a preset matching relation between the label and the text.

In some optional implementations of this embodiment, the texts in the text set may have a preset text priority; and the first execution unit 502 may include: a matching module (not shown in the figure) configured to match a target text set from a preset text set based on the obtained tags and a preset matching relationship between the tags and the text; and a selecting module (not shown in the figure) configured to select the first text from the target text set based on the text priority of each text in the target text set.

In some optional implementations of this embodiment, the tag recognition model may be obtained by training through the following steps: obtaining a plurality of sample search terms and a label which is calibrated in advance and corresponds to each sample search term in the plurality of sample search terms; and training to obtain a label recognition model by using a machine learning method and taking each sample search word in the plurality of sample search words as input and taking a label corresponding to each sample search word in the plurality of sample search words, which is calibrated in advance, as output.

The apparatus provided by the above embodiment of the present application, through the determining unit 501, in response to receiving an access request of a user for a target site, determines whether the access request includes a search term of the user; the first execution unit 502 then performs the following steps in response to determining that the access request includes the user's search terms: inputting the search terms into a pre-trained label recognition model to obtain a label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; the matched first text is pushed, so that the search word can be identified as the label through a pre-established model in response to the search word obtained by the user, and the text corresponding to the identified label is pushed to the user, so that the diversity of information pushing is improved.

Referring now to FIG. 6, shown is a block diagram of a computer system 600 suitable for use in implementing a server according to embodiments of the present application. The server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 601. It should be noted that the computer readable medium described herein can 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. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a determination unit and a first execution unit. Where the names of these elements do not in some cases constitute a limitation on the elements themselves, for example, a determination element may also be described as an "element that determines whether an access request includes a search term".

As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: in response to receiving an access request of a user for a target site, determining whether the access request comprises search terms of the user; in response to determining that the access request includes the user's search terms, performing the steps of: inputting the search word into a pre-trained label recognition model to obtain a label for representing the user attribute of the user, wherein the label recognition model is used for representing the corresponding relation between the search word of the user and the label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; and pushing the matched first text.

The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

Claims

1. A method for pushing information, comprising:

in response to receiving an access request of a user for a target site, determining whether the access request comprises a search word of the user;

in response to determining that the access request includes the user's search terms, performing the steps of: inputting the search word into a pre-trained label recognition model to obtain a label for representing the user attribute of the user, wherein the label recognition model is used for representing the corresponding relation between the search word of the user and the label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; pushing the matched first text;

in response to determining that the access request does not include the user's search terms, performing the steps of: acquiring a pre-stored historical search term set of the user; respectively inputting the historical search words in the historical search word set into the tag identification model to obtain a tag set for representing the user attribute of the user; matching a second text from a preset text set based on the obtained labels in the label set and a preset matching relation between the labels and the text; and pushing the matched second text.

2. The method of claim 1, wherein the matching out the second text from the preset text set based on the obtained tags in the tag set and a preset matching relationship between the tags and the text comprises:

determining whether at least two label subsets are included in the label set, wherein the label subsets include at least two labels and the included labels are the same;

in response to determining that at least two subsets of tags are included in the set of tags, performing the steps of: for each of the at least two subsets of tags, determining a quantity value of tags in the subset of tags; determining the label corresponding to the maximum quantity value in the determined quantity values as a target label; and matching a second text from a preset text set based on the determined target label and a preset matching relation between the label and the text.

3. The method of claim 1, wherein the text in the set of text has a preset text priority; and

the matching of the first text from the preset text set based on the obtained tag and the preset matching relationship between the tag and the text comprises:

matching a target text set from a preset text set based on the obtained label and a preset matching relation between the label and the text;

and selecting a first text from the target text set based on the text priority of each text in the target text set.

4. The method according to one of claims 1 to 3, wherein the label recognition model is trained by:

obtaining a plurality of sample search terms and a label which is calibrated in advance and corresponds to each sample search term in the plurality of sample search terms;

and training to obtain a label recognition model by using a machine learning method and taking each sample search word in the plurality of sample search words as input and taking a label which is calibrated in advance and corresponds to each sample search word in the plurality of sample search words as output.

5. An apparatus for pushing information, comprising:

the system comprises a determining unit, a searching unit and a searching unit, wherein the determining unit is used for responding to the received access request of a user for a target site, and determining whether the access request comprises a search word of the user;

a first execution unit configured to, in response to determining that the access request includes a search term of the user, perform the steps of: inputting the search word into a pre-trained label recognition model to obtain a label for representing the user attribute of the user, wherein the label recognition model is used for representing the corresponding relation between the search word of the user and the label for representing the user attribute of the user; matching a first text from a preset text set based on the obtained label and a preset matching relation between the label and the text; pushing the matched first text;

a second execution unit configured to, in response to determining that the access request does not include the user's search term, perform the following steps: acquiring a pre-stored historical search term set of the user; respectively inputting the historical search words in the historical search word set into the tag identification model to obtain a tag set for representing the user attribute of the user; matching a second text from a preset text set based on the obtained labels in the label set and a preset matching relation between the labels and the text; and pushing the matched second text.

6. The apparatus of claim 5, wherein the second execution unit comprises:

a determining module configured to determine whether at least two tag subsets are included in the tag set, wherein the tag subsets include at least two tags and the included tags are the same;

an execution module configured to, in response to determining that the labelset comprises at least two labelsets, perform the steps of: for each of the at least two subsets of tags, determining a quantity value of tags in the subset of tags; determining the label corresponding to the maximum quantity value in the determined quantity values as a target label; and matching a second text from a preset text set based on the determined target label and a preset matching relation between the label and the text.

7. The apparatus of claim 5, wherein the text in the set of text has a preset text priority; and

the first execution unit includes:

the matching module is configured to match a target text set from a preset text set based on the obtained tags and a preset matching relationship between the tags and the text;

and the selecting module is configured to select a first text from the target text set based on the text priority of each text in the target text set.

8. The apparatus according to one of claims 5-7, wherein the label recognition model is trained by:

9. A server, 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 1-4.

10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to any one of claims 1-4.