CN111666522A - Information processing method, device, equipment and storage medium - Google Patents
Information processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111666522A CN111666522A CN202010527041.1A CN202010527041A CN111666522A CN 111666522 A CN111666522 A CN 111666522A CN 202010527041 A CN202010527041 A CN 202010527041A CN 111666522 A CN111666522 A CN 111666522A
- Authority
- CN
- China
- Prior art keywords
- information
- recommended
- historical
- browsing
- content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides an information processing method, an information processing device, information processing equipment and a storage medium, wherein the method comprises the following steps: acquiring a historical browsing record of browsing information of a target user in a past preset time period and an information set to be recommended; identifying historical topic distribution information of the historical browsing records, and identifying topic distribution information to be recommended of the information set to be recommended; and selecting target recommendation information from the information set to be recommended according to the historical theme distribution information and the theme distribution information to be recommended. According to the method and the device, the appropriate target recommendation information is selected from the information set to be recommended according to the historical browsing record of the target user on the information and the theme distribution information of the information set to be recommended, and the effectiveness of information recommendation is improved.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to an information processing method, apparatus, device, and storage medium.
Background
The rapid increase of internet scale and information resources brings the problem of information overload, and how to acquire required information is increasingly difficult. An information recommendation system taking 'information push' as a service mode is a main means for solving the problem of information overload at present. Information Recommendation (Information Recommendation) refers to a system that recommends useful Information to a user that the user may be interested in but cannot acquire, and its implementation relies mainly on a Recommendation system.
With the development of internet information services, users urgently need more accurate information recommendation services, and how to improve the accuracy of information recommendation becomes an urgent problem to be solved.
Disclosure of Invention
An object of an embodiment of the present application is to provide an information processing method, apparatus, device, and storage medium, which are used to select appropriate target recommendation information from an information set to be recommended according to a history browsing record of a target user on information and topic distribution information of the information set to be recommended.
The history aspect of the embodiment of the present application provides an information processing method, including: acquiring a historical browsing record of browsing information of a target user in a past preset time period and an information set to be recommended; identifying historical topic distribution information of the historical browsing records, and identifying topic distribution information to be recommended of the information set to be recommended; and selecting target recommendation information from the information set to be recommended according to the historical theme distribution information and the theme distribution information to be recommended.
In an embodiment, the identifying the historical topic distribution information of the historical browsing record includes: analyzing the historical browsing record to obtain browsing information content and browsing state information of the target user; converting the browsing information content and the browsing state information into texts to generate historical browsing text information; and inputting the historical browsing text information into a preset identification model, and outputting the historical theme distribution information.
In an embodiment, the identifying the distribution information of the to-be-recommended topics of the to-be-recommended information set includes: analyzing the information set to be recommended to obtain each piece of information content and state information when each piece of information content is browsed; converting each piece of information content and the state information of each piece of information content when being browsed into texts, and generating text information to be recommended; and inputting the text information to be recommended to a preset identification model, and outputting the distribution information of the theme to be recommended.
In one embodiment, the step of establishing the predetermined recognition model includes: acquiring browsing record data sets of a plurality of sample information by different users; analyzing the recorded data set, and extracting the content of each sample information and the state information of each sample information when being browsed; converting the content of each sample information and the state information of each sample information when being browsed into texts to generate sample text information; and training a theme model by the sample text information to generate the preset recognition model.
In an embodiment, the selecting target recommendation information from the to-be-recommended information set according to the historical topic distribution information and the to-be-recommended topic distribution information includes: calculating the similarity of the historical theme distribution information and the theme distribution information to be recommended; and sorting each piece of information in the information set to be recommended from large to small according to the similarity, and selecting at least one piece of information with the similarity ranked in the front preset as target recommendation information from the information set to be recommended.
In an embodiment, after the selecting target recommendation information from the to-be-recommended information set according to the historical topic distribution information and the to-be-recommended topic distribution information, the method further includes: and pushing the target recommendation information to a terminal of the target user.
In an embodiment, before the pushing the target recommendation information to the terminal of the target user, the method further includes: and eliminating the information browsed by the target user in the target recommendation information.
An aspect to be recommended in an embodiment of the present application provides an information processing apparatus, including: the acquisition module is used for acquiring a historical browsing record of browsing information of a target user in a past preset time period and an information set to be recommended; the identification module is used for identifying historical theme distribution information of the historical browsing record and identifying to-be-recommended theme distribution information of the to-be-recommended information set; and the selecting module is used for selecting target recommendation information from the information set to be recommended according to the historical theme distribution information and the theme distribution information to be recommended.
In one embodiment, the identification module is configured to: analyzing the historical browsing record to obtain browsing information content and browsing state information of the target user; converting the browsing information content and the browsing state information into texts to generate historical browsing text information; and inputting the historical browsing text information into a preset identification model, and outputting the historical theme distribution information.
In one embodiment, the identification module is configured to: analyzing the information set to be recommended to obtain each piece of information content and state information when each piece of information content is browsed; converting each piece of information content and the state information of each piece of information content when being browsed into texts, and generating text information to be recommended; and inputting the text information to be recommended to a preset identification model, and outputting the distribution information of the theme to be recommended.
In an embodiment, the system further includes a setup module configured to: acquiring browsing record data sets of a plurality of sample information by different users; analyzing the recorded data set, and extracting the content of each sample information and the state information of each sample information when being browsed; converting the content of each sample information and the state information of each sample information when being browsed into texts to generate sample text information; and training a theme model by the sample text information to generate the preset recognition model.
In one embodiment, the selection module is configured to: calculating the similarity of the historical theme distribution information and the theme distribution information to be recommended; and sorting each piece of information in the information set to be recommended from large to small according to the similarity, and selecting at least one piece of information with the similarity ranked in the front preset as target recommendation information from the information set to be recommended.
In one embodiment, the method further comprises: and the pushing module is used for pushing the target recommendation information to the terminal of the target user after selecting the target recommendation information from the information set to be recommended according to the historical theme distribution information and the theme distribution information to be recommended.
In one embodiment, the method further comprises: and the removing module is used for removing the information browsed by the target user in the target recommendation information before the target recommendation information is pushed to the terminal of the target user.
A third aspect of embodiments of the present application provides an electronic device, including: a memory to store a computer program; the processor is used for executing the historical aspects of the embodiment and the method of any embodiment of the embodiment to determine the target recommendation information corresponding to the target user from the information set to be recommended.
A fourth aspect of embodiments of the present application provides a non-transitory electronic device-readable storage medium, including: a program which, when run by an electronic device, causes the electronic device to perform the method of the first aspect of an embodiment of the present application and any embodiment thereof.
According to the information processing method, the device, the equipment and the storage medium, the topic identification is carried out on the historical browsing record of the target user browsing information in the past preset time period to obtain the corresponding historical topic distribution information, the topic identification is carried out on the information set to be recommended to obtain the topic distribution information to be recommended, then the target recommendation information corresponding to the target user is determined from the information set to be recommended according to the historical topic distribution information and the topic distribution information to be recommended, the browsing history of the target user is comprehensively considered, and the more accurate target recommendation information is determined.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
FIG. 2 is a flowchart illustrating an information processing method according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating an information processing method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. In the description of the present application, the terms "history", "to be recommended", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
As shown in fig. 1, the present embodiment provides an electronic apparatus 1 including: at least one processor 11 and a memory 12, one processor being exemplified in fig. 1. The processor 11 and the memory 12 are connected by the bus 10, and the memory 12 stores instructions executable by the processor 11, and the instructions are executed by the processor 11, so that the electronic device 1 can execute all or part of the flow of the method in the embodiments described below, to determine target recommendation information corresponding to a target user from the information set to be recommended.
In an embodiment, the electronic device 1 may be a mobile phone, a notebook computer, a desktop computer, or the like.
Please refer to fig. 2, which is an information processing method according to an embodiment of the present application, and the method may be executed by the electronic device 1 shown in fig. 1 and may be applied in an information pushing scenario to determine target recommendation information corresponding to a target user from an information set to be recommended according to a history browsing record of the target user browsing information and topic division information of the information set to be recommended. The method comprises the following steps:
step 201: and acquiring a historical browsing record of the browsing information of the target user in a past preset time period and an information set to be recommended.
In this step, in the scenario of information pushing, the target user may log in an account of a certain information page through the terminal, and the user may browse the relevant information after logging in. For example, the target user a logs in a news website B and browses news information in the news website B. The preset time period is a time period which has passed relative to the current time, and may be determined based on an actual scene, and assuming that the preset time period is 10 seconds, the historical browsing record is a historical record of browsing information of the target user a in the last 10 seconds. The information browsed may be text, short video, image, etc. The information set to be recommended may be an information set to be pushed to a user by an information platform, and the set may include a plurality of information contents, where the information may be in the form of text, video, image, and the like.
In an embodiment, the historical browsing history may also be a preset number of information records recently browsed by the target user.
Step 202: and identifying historical theme distribution information of the historical browsing records, and identifying to-be-recommended theme distribution information of the to-be-recommended information set.
In this step, in the historical browsing records of the same target user, there may be theme information having the browsing preference of the target user, and the theme distribution information, i.e. the historical theme subsection information, concerned by the target user is obtained from the theme identification performed on the historical browsing records. And simultaneously, performing theme identification on each piece of information in the information set to be recommended to obtain corresponding theme subsection information, namely the theme subsection information to be recommended.
Step 203: and selecting target recommendation information from the information set to be recommended according to the historical theme distribution information and the theme distribution information to be recommended.
In the step, the relevance of the historical theme distribution information and the theme distribution information to be recommended is considered at the same time, and information which is interested by the target user is selected from the information set to be recommended as target recommendation information. Therefore, the accuracy of information pushing is achieved, and resource waste is avoided.
According to the information processing method, the topic identification is carried out on the historical browsing record of the target user browsing information in the past preset time period to obtain the corresponding historical topic distribution information, the topic identification is carried out on the information set to be recommended to obtain the topic distribution information to be recommended, then the target recommendation information corresponding to the target user is determined from the information set to be recommended according to the historical topic distribution information and the topic distribution information to be recommended, the browsing history of the target user is comprehensively considered, and more accurate target recommendation information is determined.
Please refer to fig. 3, which is an information processing method according to an embodiment of the present application, and the method may be executed by the electronic device 1 shown in fig. 1 and may be applied in an information pushing scenario to determine target recommendation information corresponding to a target user from an information set to be recommended according to a history browsing record of the target user browsing information and topic division information of the information set to be recommended. The method comprises the following steps:
step 301: and acquiring browsing record data sets of a plurality of sample information by different users.
In this step, a preset recognition model for topic recognition may be first established based on the big data. Specifically, a large number of records of browsing information of different users can be obtained through big data. Such as a browsing history data set of news information browsed by all users in a certain area. The sample information may be news, movie and television drama, books, etc.
Step 302: the record data set is parsed, and the content of each sample information and the state information of each sample information when viewed are extracted therefrom.
In this step, the recorded data set is history data, such as click history data based on different users on the information platform, including resources such as text titles, short videos, images and the like which are clicked and browsed, and contains the content of sample information browsed by different users and status information of each sample information when browsed. The state information may be time information and/or location information at which the user browses the sample information.
Step 303: and converting the content of each sample information and the state information of each sample information when browsed into texts to generate sample text information.
In this step, the text description may be extracted from the resources such as the clicked and browsed text title, short video, and image, and the text description is segmented, and the state information where the user browses the sample information is converted into text data, for example, the time information may be correspondingly converted into "morning, afternoon, evening, and evening", and the location information may be correspondingly converted into: the names of cities such as Beijing, Shanghai, etc. And then fusing the data after word segmentation and the text data converted from the state information into the same text as sample text information.
Step 304: and training a topic model by sample text information to generate a preset recognition model.
In this step, the sample text information obtained in step 303 is input to a Topic Model (Topic Model, which is a statistical Model for clustering the implicit semantic structures of the corpus in an unsupervised learning manner) to be trained, and finally a preset recognition Model for recognizing the Topic distribution information of the information is generated.
Step 305: and acquiring a historical browsing record of the browsing information of the target user in a past preset time period and an information set to be recommended. See the description of step 201 in the above embodiments for details.
Step 306: and analyzing the historical browsing record to obtain the browsing information content and the browsing state information of the target user.
In this step, data analysis may be performed on the latest preset number (for example, the latest 10) of historical browsing records of the target user, where the historical browsing records include the content of browsing information of the target user and status information of each piece of information when browsed, and the content of the browsing information and the status information of each piece of information when browsed may be extracted from the analysis result. The status information may be time information and/or location information at which the target user browses the information.
Step 307: and converting the browsing information content and the browsing state information into texts to generate historical browsing text information.
In this step, the browsing information content may be in the form of text, short video, image, etc., and the text description part may be extracted from the browsing information content, and then the text description part is subjected to word segmentation processing, and the result data after word segmentation is recorded. And converting the state information where the target user clicks and browses the information content into text data, such as: the time information can be correspondingly converted into the morning, afternoon, evening and evening, and the position information can be correspondingly converted into the following information: the names of cities such as Beijing, Shanghai, etc. And then merging the word segmentation result data of the browsing information content and the text data converted from the state information corresponding to the browsing information into the same text to be used as the historical browsing text information.
Step 308: and inputting the historical browsing text information into a preset identification model, and outputting historical theme distribution information.
In this step, the preset recognition model in step 304 is used to recognize the history browsing text information, so as to obtain a topic distribution vector corresponding to the history browsing record of the target user, and the topic distribution vector is used as the history topic distribution information.
Step 309: and analyzing the information set to be recommended to obtain each piece of information content and state information of each piece of information content when being browsed.
In this step, for the information set to be recommended, each piece of information may have been browsed by a certain user, or may be completely new and unviewed information, the information set to be recommended may record browsed data of each piece of information to be recommended, the data includes content of the browsed information to be recommended and state information of the browsed information to be recommended, and the state information may be time information and/or location information. By performing data analysis on the information set to be recommended, each piece of information content and the state information of each piece of information content when being browsed can be obtained.
Step 310: and converting each piece of information content and the state information of each piece of information content when being browsed into a text to generate text information to be recommended.
In this step, the information content to be recommended may be in the form of text, short video, image, etc., and a text description part may be extracted from the information content to be recommended, and then word segmentation processing is performed on the text description part, and result data after word segmentation is recorded. And converting the state information of the information content to be recommended when being browsed into text data, such as: the time information can be correspondingly converted into the morning, afternoon, evening and evening, and the position information can be correspondingly converted into the following information: the names of cities such as Beijing, Shanghai, etc. And if no user browses the information to be recommended, the state information corresponding to the information to be recommended is null. And finally, fusing word segmentation result data of the information content to be recommended and text data converted from the state information corresponding to the information to be recommended into the same text, and taking the same text as the text information to be recommended.
Step 311: and inputting the text information to be recommended to a preset identification model, and outputting the distribution information of the theme to be recommended.
In this step, the preset identification model in step 304 is used to perform topic identification on the text information to be recommended, so as to obtain a topic distribution vector corresponding to the text information to be recommended, and the topic distribution vector is used as the topic distribution information to be recommended.
In an embodiment, the execution sequence of steps 306 to 308 and 309 to 311 may be changed, that is, the historical topic distribution information may be identified first, the topic distribution information to be recommended may be identified first, or both may be performed simultaneously.
Step 312: and calculating the similarity of the historical theme distribution information and the theme distribution information to be recommended.
In the step, in the information recommendation scene, information which the target user is interested in is selected for purposeful pushing, so that invalid pushing is reduced, and the utilization rate of information resources is improved. The information to be recommended, which is similar to the historical browsing record of the target user, is likely to be information in which the target user is interested, so whether the target user is interested in the information to be recommended can be determined by calculating the similarity between the historical topic distribution information and the topic distribution information to be recommended. In one embodiment, the similarity may be a cosine similarity.
Step 313: and sorting each piece of information in the information set to be recommended according to the similarity from large to small, and selecting at least one piece of information with the similarity ranked at the front preset rank from the information set to be recommended as target recommendation information.
In this step, the information set to be recommended may include a plurality of pieces of information to be recommended, the similarity between the topic subsection information corresponding to each piece of information to be recommended and the historical browsing record of the target user may be different, all pieces of information to be recommended may be sorted according to the similarity from large to small, and a plurality of pieces of information to be recommended with large similarity are selected as the target recommendation information.
Step 314: and eliminating information browsed by the target user in the target recommendation information.
In this step, the selected target recommendation information may include multiple pieces of information, which may include information already viewed by the target user, and in order to further improve the information recommendation accuracy, the information already viewed by the target user is removed from the selected target recommendation information, and the remaining information constitutes the final target recommendation information.
Step 315: and pushing the target recommendation information to a terminal of the target user.
In this step, the final target recommendation information obtained in step 314 is sent to a terminal corresponding to the target user, so that the target user can refer to the target recommendation information through the terminal.
Please refer to fig. 4, which is an information processing apparatus 400 according to an embodiment of the present application, and the apparatus is applicable to the electronic device 1 shown in fig. 1 and is applicable to a scenario of information pushing, so as to determine target recommendation information corresponding to a target user from an information set to be recommended according to a history browsing history of the target user browsing information and topic division information of the information set to be recommended. The device includes: the system comprises an acquisition module 401, an identification module 402 and a selection module 403, wherein the principle relationship of each module is as follows:
the obtaining module 401 is configured to obtain a historical browsing record of browsing information of a target user in a past preset time period, and an information set to be recommended. See the description of step 201 in the above embodiments for details.
The identifying module 402 is configured to identify historical topic distribution information of the historical browsing record, and identify to-be-recommended topic distribution information of the to-be-recommended information set. See the description of step 202 in the above embodiments for details.
The selecting module 403 is configured to select target recommendation information from the to-be-recommended information set according to the historical theme distribution information and the to-be-recommended theme distribution information. See the description of step 203 in the above embodiments for details.
In one embodiment, the identification module 402 is configured to: and analyzing the historical browsing record to obtain the browsing information content and the browsing state information of the target user. And converting the browsing information content and the browsing state information into texts to generate historical browsing text information. And inputting the historical browsing text information into a preset identification model, and outputting historical theme distribution information. See the above embodiments for a detailed description of steps 306-308.
In one embodiment, the identification module 402 is configured to: and analyzing the information set to be recommended to obtain each piece of information content and state information of each piece of information content when being browsed. And converting each piece of information content and the state information of each piece of information content when being browsed into a text to generate text information to be recommended. And inputting the text information to be recommended to a preset identification model, and outputting the distribution information of the theme to be recommended. See the description of steps 309-311 in the above embodiments for details.
In an embodiment, the method further includes a establishing module 404 for: and acquiring browsing record data sets of a plurality of sample information by different users. The record data set is parsed, and the content of each sample information and the state information of each sample information when viewed are extracted therefrom. And converting the content of each sample information and the state information of each sample information when browsed into texts to generate sample text information. And training a topic model by sample text information to generate a preset recognition model. See the description of step 301 to step 304 in the above embodiments in detail.
In one embodiment, the selecting module 403 is configured to: and calculating the similarity of the historical theme distribution information and the theme distribution information to be recommended. And sorting each piece of information in the information set to be recommended according to the similarity from large to small, and selecting at least one piece of information with the similarity ranked at the front preset rank from the information set to be recommended as target recommendation information. See the description of steps 312 to 313 in the above embodiments in detail.
In one embodiment, the method further comprises: the removing module 405 is configured to remove information that has been browsed by the target user from the target recommendation information before the target recommendation information is pushed to the terminal of the target user. See the description of step 314 in the above embodiments for details.
In one embodiment, the method further comprises: and the pushing module 406 is configured to push the target recommendation information to a terminal of a target user after selecting the target recommendation information from the information set to be recommended according to the historical theme distribution information and the theme distribution information to be recommended. See the description of step 315 in the above embodiments for details.
For a detailed description of the information processing apparatus 400, please refer to the description of the related method steps in the above embodiments.
An embodiment of the present invention further provides a non-transitory electronic device readable storage medium, including: a program that, when run on an electronic device, causes the electronic device to perform all or part of the procedures of the methods in the above-described embodiments. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like. The storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (16)
1. An information processing method characterized by comprising:
acquiring a historical browsing record of browsing information of a target user in a past preset time period and an information set to be recommended;
identifying historical topic distribution information of the historical browsing records, and identifying topic distribution information to be recommended of the information set to be recommended;
and selecting target recommendation information from the information set to be recommended according to the historical theme distribution information and the theme distribution information to be recommended.
2. The method of claim 1, wherein the identifying historical topic distribution information for the historical browsing records comprises:
analyzing the historical browsing record to obtain browsing information content and browsing state information of the target user;
converting the browsing information content and the browsing state information into texts to generate historical browsing text information;
and inputting the historical browsing text information into a preset identification model, and outputting the historical theme distribution information.
3. The method according to claim 1, wherein the identifying the distribution information of the to-be-recommended topics of the to-be-recommended information set comprises:
analyzing the information set to be recommended to obtain each piece of information content and state information when each piece of information content is browsed;
converting each piece of information content and the state information of each piece of information content when being browsed into texts, and generating text information to be recommended;
and inputting the text information to be recommended to a preset identification model, and outputting the distribution information of the theme to be recommended.
4. The method according to claim 2 or 3, wherein the step of establishing the preset recognition model comprises:
acquiring browsing record data sets of a plurality of sample information by different users;
analyzing the recorded data set, and extracting the content of each sample information and the state information of each sample information when being browsed;
converting the content of each sample information and the state information of each sample information when being browsed into texts to generate sample text information;
and training a theme model by the sample text information to generate the preset recognition model.
5. The method according to claim 1, wherein the selecting target recommendation information from the information set to be recommended according to the historical topic distribution information and the distribution information of the topics to be recommended comprises:
calculating the similarity of the historical theme distribution information and the theme distribution information to be recommended;
and sorting each piece of information in the information set to be recommended from large to small according to the similarity, and selecting at least one piece of information with the similarity ranked in the front preset as target recommendation information from the information set to be recommended.
6. The method according to claim 1, further comprising, after selecting target recommendation information from the set of information to be recommended according to the historical topic distribution information and the distribution information of the topic to be recommended, the following steps:
and pushing the target recommendation information to a terminal of the target user.
7. The method of claim 6, further comprising, before the pushing the target recommendation information to the terminal of the target user:
and eliminating the information browsed by the target user in the target recommendation information.
8. An information processing apparatus characterized by comprising:
the acquisition module is used for acquiring a historical browsing record of browsing information of a target user in a past preset time period and an information set to be recommended;
the identification module is used for identifying historical theme distribution information of the historical browsing record and identifying to-be-recommended theme distribution information of the to-be-recommended information set;
and the selecting module is used for selecting target recommendation information from the information set to be recommended according to the historical theme distribution information and the theme distribution information to be recommended.
9. The apparatus of claim 8, wherein the identification module is configured to:
analyzing the historical browsing record to obtain browsing information content and browsing state information of the target user;
converting the browsing information content and the browsing state information into texts to generate historical browsing text information;
and inputting the historical browsing text information into a preset identification model, and outputting the historical theme distribution information.
10. The apparatus of claim 8, wherein the identification module is configured to:
analyzing the information set to be recommended to obtain each piece of information content and state information when each piece of information content is browsed;
converting each piece of information content and the state information of each piece of information content when being browsed into texts, and generating text information to be recommended;
and inputting the text information to be recommended to a preset identification model, and outputting the distribution information of the theme to be recommended.
11. The apparatus according to claim 9 or 10, further comprising a setup module configured to:
acquiring browsing record data sets of a plurality of sample information by different users;
analyzing the recorded data set, and extracting the content of each sample information and the state information of each sample information when being browsed;
converting the content of each sample information and the state information of each sample information when being browsed into texts to generate sample text information;
and training a theme model by the sample text information to generate the preset recognition model.
12. The apparatus of claim 8, wherein the selection module is configured to:
calculating the similarity of the historical theme distribution information and the theme distribution information to be recommended;
and sorting each piece of information in the information set to be recommended from large to small according to the similarity, and selecting at least one piece of information with the similarity ranked in the front preset as target recommendation information from the information set to be recommended.
13. The apparatus of claim 8, further comprising:
and the pushing module is used for pushing the target recommendation information to the terminal of the target user after selecting the target recommendation information from the information set to be recommended according to the historical theme distribution information and the theme distribution information to be recommended.
14. The apparatus of claim 13, further comprising:
and the removing module is used for removing the information browsed by the target user in the target recommendation information before the target recommendation information is pushed to the terminal of the target user.
15. An electronic device, comprising:
a memory to store a computer program;
a processor configured to perform the method of any one of claims 1 to 7 to determine target recommendation information corresponding to a target user from the set of information to be recommended.
16. A non-transitory electronic device readable storage medium, comprising: program which, when run by an electronic device, causes the electronic device to perform the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010527041.1A CN111666522A (en) | 2020-06-10 | 2020-06-10 | Information processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010527041.1A CN111666522A (en) | 2020-06-10 | 2020-06-10 | Information processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111666522A true CN111666522A (en) | 2020-09-15 |
Family
ID=72387146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010527041.1A Pending CN111666522A (en) | 2020-06-10 | 2020-06-10 | Information processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111666522A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570411A (en) * | 2021-07-22 | 2021-10-29 | 深圳市雷鸟网络传媒有限公司 | Promotion information display method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
| CN104679743A (en) * | 2013-11-26 | 2015-06-03 | 阿里巴巴集团控股有限公司 | Method and device for determining preference model of user |
| CN104965889A (en) * | 2015-06-17 | 2015-10-07 | 腾讯科技（深圳）有限公司 | Content recommendation method and apparatus |
| CN109460514A (en) * | 2018-11-02 | 2019-03-12 | 北京京东尚科信息技术有限公司 | Method and apparatus for pushed information |
| CN110781391A (en) * | 2019-10-22 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium |
-
2020
- 2020-06-10 CN CN202010527041.1A patent/CN111666522A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104679743A (en) * | 2013-11-26 | 2015-06-03 | 阿里巴巴集团控股有限公司 | Method and device for determining preference model of user |
| CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
| CN104965889A (en) * | 2015-06-17 | 2015-10-07 | 腾讯科技（深圳）有限公司 | Content recommendation method and apparatus |
| CN109460514A (en) * | 2018-11-02 | 2019-03-12 | 北京京东尚科信息技术有限公司 | Method and apparatus for pushed information |
| CN110781391A (en) * | 2019-10-22 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570411A (en) * | 2021-07-22 | 2021-10-29 | 深圳市雷鸟网络传媒有限公司 | Promotion information display method and device, electronic equipment and storage medium |
| CN113570411B (en) * | 2021-07-22 | 2024-06-07 | 深圳市雷鸟网络传媒有限公司 | Popularization information display method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10795939B2 (en) | Query method and apparatus | |
| Jeon et al. | A framework to predict the quality of answers with non-textual features | |
| CN108319630B (en) | Information processing method, information processing device, storage medium and computer equipment | |
| JP5353148B2 (en) | Image information retrieving apparatus, image information retrieving method and computer program therefor | |
| CN106383887B (en) | Method and system for collecting, recommending and displaying environment-friendly news data | |
| US7860878B2 (en) | Prioritizing media assets for publication | |
| CN110888990B (en) | Text recommendation method, device, equipment and medium | |
| US20090319449A1 (en) | Providing context for web articles | |
| CN108334489B (en) | Text core word recognition method and device | |
| US20110246462A1 (en) | Method and System for Prompting Changes of Electronic Document Content | |
| CN108090104B (en) | Method and device for acquiring webpage information | |
| JP2010073114A6 (en) | Image information retrieving apparatus, image information retrieving method and computer program therefor | |
| US11423096B2 (en) | Method and apparatus for outputting information | |
| CN101118560A (en) | Keyword outputting apparatus, keyword outputting method, and keyword outputting computer program product | |
| CN110290199B (en) | Content pushing method, device and equipment | |
| CN111314732A (en) | Method for determining video label, server and storage medium | |
| JP7395377B2 (en) | Content search methods, devices, equipment, and storage media | |
| CN111538903B (en) | Method and device for determining search recommended word, electronic equipment and computer readable medium | |
| CN111708909A (en) | Video tag adding method and device, electronic equipment and computer-readable storage medium | |
| CN114330329A (en) | Service content searching method and device, electronic equipment and storage medium | |
| CN110750707A (en) | Keyword recommendation method and device and electronic equipment | |
| CN110750708A (en) | Keyword recommendation method and device and electronic equipment | |
| CN111666522A (en) | Information processing method, device, equipment and storage medium | |
| WO2019231635A1 (en) | Method and apparatus for generating digest for broadcasting | |
| CN110147488B (en) | Page content processing method, processing device, computing equipment and storage medium |
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 |