CN113595860B - Data processing method, device, electronic equipment and computer storage medium - Google Patents
Data processing method, device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN113595860B CN113595860B CN202010368121.7A CN202010368121A CN113595860B CN 113595860 B CN113595860 B CN 113595860B CN 202010368121 A CN202010368121 A CN 202010368121A CN 113595860 B CN113595860 B CN 113595860B
- Authority
- CN
- China
- Prior art keywords
- comment
- content
- content object
- candidate
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims description 22
- 238000004891 communication Methods 0.000 claims description 16
- 238000012552 review Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 claims 2
- 238000004364 calculation method Methods 0.000 description 9
- 238000012550 audit Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
- H04L51/10—Multimedia information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
- H04L51/18—Commands or executable codes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention provides a data processing method, a data processing device, electronic equipment and a computer storage medium. The data processing method comprises the following steps: acquiring content quality information and content freshness of the candidate content object; determining a target content object from the candidate content objects according to the content quality information and the content freshness of the candidate content objects; automatically generating comment data for the target content object according to the attribute information of the target content object; and commenting the target content object by using the commentary data. By the embodiment of the invention, the richness of comment modes can be improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a data processing method, a data processing device, electronic equipment and a computer storage medium.
Background
With the development of internet technology, people increasingly share daily life or perform content creation on the internet for other users to watch and comment, so that interaction and social contact are realized. However, the existing comment mode is single, for example, a reviewer performs manual comment under a content object published by an creator. The comment mode has single function and cannot meet different comment requirements.
Disclosure of Invention
In view of the above, an embodiment of the present invention provides a data processing scheme to solve some or all of the above problems.
According to a first aspect of an embodiment of the present invention, there is provided a data processing method, including: acquiring content quality information and content freshness of the candidate content object; determining a target content object from the candidate content objects according to the content quality information and the content freshness of the candidate content objects; automatically generating comment data for the target content object according to the attribute information of the target content object; and commenting the target content object by using the commentary data.
According to a second aspect of an embodiment of the present invention, there is provided a data processing apparatus including: the acquisition module is used for acquiring content quality information and content freshness of the candidate content objects; a first determining module, configured to determine a target content object from the candidate content objects according to content quality information and content freshness of the candidate content objects; the second determining module is used for automatically generating comment data aiming at the target content object according to the attribute information of the target content object; and the comment module is used for commenting the target content object by using the comment data.
According to a third aspect of an embodiment of the present invention, there is provided an electronic apparatus including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform operations corresponding to the data processing method according to the first aspect.
According to a fourth aspect of embodiments of the present invention, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, implements the data processing method according to the first aspect.
According to the data processing scheme provided by the embodiment of the invention, the target content data of the corresponding comment data to be generated is determined according to the content quality information and the content freshness of the candidate content objects, so that the target content objects can be quickly and accurately determined from the candidate content objects, and further comment data is generated according to the attribute information of the target content objects, and the comment is performed by using the comment data object target content objects. Therefore, automatic comments are realized, comment forms are enriched, different comment requirements of users are met, and the comments are high in pertinence and better in relevance with the target content object.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present invention, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1a is a flowchart illustrating steps of a data processing method according to a first embodiment of the present invention;
FIG. 1b is a schematic diagram of a usage scenario according to a first embodiment of the present invention;
FIG. 2 is a flow chart showing steps of a data processing method according to a second embodiment of the present invention;
FIG. 3a is a flowchart illustrating a data processing method according to a third embodiment of the present invention;
FIG. 3b is a schematic diagram of a usage scenario according to a third embodiment of the present invention;
FIG. 4 is a block diagram showing a data processing apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
In order to better understand the technical solutions in the embodiments of the present invention, the following description will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the present invention, shall fall within the scope of protection of the embodiments of the present invention.
The implementation of the embodiments of the present invention will be further described below with reference to the accompanying drawings.
Example 1
Referring to FIG. 1a, a flowchart of the steps of a data processing method according to a first embodiment of the present invention is shown.
In this embodiment, the data processing method is configured at a server (the server includes a server and/or a cloud end), and comment data corresponding to the target content object is automatically generated by the server, so that the comment data is used to comment on the target content object.
The data processing method of the present embodiment includes the steps of:
step S102: content quality information and content freshness of the candidate content object are acquired.
The candidate content object may be content posted by an creator, such as video content, audio content, text content, graphic content, or the like, or may also be comment content posted by a commenter, such as comment content for content posted by an creator, comment content for comment content, or the like, which is not limited by the comparison of the present embodiment.
In this embodiment, the content candidate is described as an example of the content posted by the creator, but in other embodiments, the candidate may be comment content posted by a reviewer.
It should be noted that, the creator and reviewer in this embodiment are different identity roles of users, and each user may have one or more identity roles.
The content quality information is used to indicate the content quality condition of each candidate content object. For example, the content quality information includes one of: high quality content, good content, common content. Of course, the content included in the content quality information may be different as needed, which is not limited in this embodiment.
The content quality information may be obtained in any suitable manner by a person skilled in the art. For example, quality evaluation is performed on each candidate content object in advance by a manual method, and corresponding content quality information is generated.
Content freshness is used to indicate the age and degree of interest of the corresponding candidate content object. The content freshness may be determined according to the posting time of the candidate content object, the number of existing comments, the latest time being reviewed, and the like. This results in a higher number of commented or more fresh content of candidate content objects with newer time to be commented. Of course, in other embodiments, other suitable rules may be used by those skilled in the art to determine the freshness of the content, which is not limited in this embodiment.
Step S104: and determining a target content object from the candidate content objects according to the content quality information and the content freshness of the candidate content objects.
In a particular implementation, the target content object may be a content object having a number of existing reviews that is less than the target number of reviews. Of course, in other embodiments, the target content object may be determined in other ways, which is not limited by the present embodiment.
The target number of comments may be determined from the content quality information and the content freshness. For example, for each candidate content object, a reference value indicating the number of comments when the posting duration reaches a certain duration is determined from its content quality information. And then, adjusting the reference value according to the content freshness of each candidate content object, so as to obtain the target comment number corresponding to each candidate content object.
Since the content freshness can indicate the timeliness and the attention degree of the corresponding candidate content object, the content freshness thereof is considered in determining the target content object, so that the target content object which has proper release time, better timeliness and proper attention degree can be obtained from the candidate content object. Similarly, since the content quality information can indicate the content quality of the candidate content object, the content quality thereof is taken into consideration in determining the target content object, so that a good-quality target content object can be obtained from the candidate content object.
Step S106: and automatically generating comment data for the target content object according to the attribute information of the target content object.
The attribute information includes at least one of: the content classification of the corresponding target content object, the content tag of the corresponding target content object, and the content domain corresponding to the corresponding target content object, but is not limited thereto, and may further include other information, which is not limited thereto in the embodiment.
The target content objects may have different content classifications according to different classification standards, for example, may be classified into han dynasty, tangsheng, ming dynasty, etc. according to the dynasty related to the content, and may be classified into men's wear, women's wear, etc. according to the gender of the person related to the content.
The content tag may be an explanatory tag for which the target content object is set, such as a chinese suit, a quincuncial, or a certain brand, a certain model, etc.
The content domain to which the target content object corresponds may indicate the industry in which it is located.
A person skilled in the art can automatically generate comment data corresponding to the target content object in any appropriate mode, and the comment data are generated according to the attribute information of the target content object, so that on one hand, automation can be realized, comment forms are enriched, on the other hand, the generated comment data are high in association degree with the target content object, and therefore requirements of users can be better met by using the comment data to comment the target content object, and the comment data are closer to real manual comments.
The review data may be automatically generated by one of ordinary skill in the art in any suitable manner, such as by a trained neural network model (e.g., generative model). Or selecting comment data corresponding to the target content object from a preset comment database.
Step S108: and commenting the target content object by using the commentary data.
In a specific implementation, the comment data may be directly sent as a comment on the target content object, or one or more comment data may be sent as comment data of the corresponding target content object at a required time according to needs, which is not limited in this embodiment.
The following describes the data processing method in connection with a specific usage scenario:
as shown in fig. 1b, the server may acquire candidate content objects in the target application at intervals. The candidate content object may be a newly added content object within the interval period, for example, content posted by an creator (such as video content, audio content, text content, graphic content, etc.), or comment content posted by a user (such as comment content for content posted by an creator, comment content for comment content, etc.), and in the present usage scenario, the newly added content object is exemplified as content posted by an creator.
For each candidate content object, the content identification unit of the server determines corresponding content quality information according to at least one of the corresponding browsing data, the auditing state, the recommendation level and the ordering information. For example, the candidate content object a is a good content, the candidate content object B is a good content, the candidate content object C is a normal content, and the like.
The freshness calculating unit determines the content freshness corresponding to the candidate content object according to the release time and the existing comment number of the candidate content object. For example, the number of existing reviews in a unit posting time indicates the freshness of the content. The unit release time may be 1 minute, 10 seconds, 5 minutes, etc.
The comment quantity calculating unit calculates the target comment quantity according to the corresponding content quality information and the content freshness of each candidate content object, and further determines the candidate target object with the existing comment quantity smaller than the target comment quantity as a target content object.
For each target content object, the difference value between the target comment number and the existing comment number is the number of comment data which needs to be automatically generated.
In one manner, when comment data is automatically generated, the comment content production unit may determine, from among a plurality of candidate comment data preset, that the degree of association satisfies a set condition (the set condition may be determined according to a requirement, for example, may be that the degree of association is greater than 70%, etc.) as the determined comment data, based on attribute information of the target content object. N is greater than or equal to the difference between the target number of reviews and the existing number of reviews.
Then, the comment sending task unit comments on each target content object using comment data corresponding thereto.
Because the comment data corresponding to the target content object is automatically generated according to the attribute information of each target content object, the comment data and the target content object are guaranteed to have higher association degree, so that the effect of commenting on the target content object by using the comment data is better, the form of commentary is enriched, the requirement of commenting by users in different modes is met, and the adaptability is improved.
According to the embodiment, the target content data of the comment data to be generated is determined according to the content quality information and the content freshness of the candidate content objects, the target content objects can be rapidly and accurately determined from the candidate content objects, and further the comment data is generated according to the attribute information of the target content objects, so that the comment is performed by using the comment data object target content objects. Therefore, automatic comments are realized, comment forms are enriched, different comment requirements of users are met, and the comments are high in pertinence and better in relevance with the target content object.
The data processing method of the present embodiment may be performed by any suitable electronic device having data processing capabilities, including but not limited to: servers, mobile terminals (such as tablet computers, mobile phones and the like), PCs and the like.
Example two
Referring to fig. 2, a flowchart of steps of a data processing method according to a second embodiment of the present invention is shown.
The data processing method of the present embodiment includes the aforementioned steps S102 to S108.
In a specific implementation of this embodiment, in order to quickly and reliably obtain content quality information and content freshness, so as to improve accuracy of subsequent determination of the target content object, so as to well meet the user requirement, step S102 includes sub-step S1021 and sub-step S1022.
The substep S1021 is used for achieving the purpose of obtaining the content quality information of the candidate content object, and the substep S1022 is used for achieving the purpose of obtaining the content freshness of the candidate content object, but in a specific application, the two steps may be performed in no sequence or may be performed in parallel. Specifically:
substep S1021: and determining content quality information corresponding to the candidate content object according to at least one of browsing data, auditing state, recommendation level and ordering information of the candidate content object.
In the present embodiment, the content quality information includes at least one of: high quality content, good content, and normal content.
The browsing data includes at least one of: number of reviews, number of comments available, and number of shares. The browsing data may be the sum of all the data it includes, or may be determined in any other suitable manner based on the data it includes. By browsing the data, the user's attention and interest level in the candidate content object can be known.
The audit status is used to indicate whether the candidate content object passed the content audit, etc.
The recommendation level may be determined as desired, e.g., recommendation levels 1-5, with higher levels being more likely to be recommended to the user. The ranking information is used to indicate the order of priority of different candidate content objects at the same recommendation level.
Candidate content objects which do not meet the requirements can be screened out through the content quality information, and the content quality of the candidate content objects which meet the requirements can be rated.
In a specific implementation, taking the candidate content object a as an example, the corresponding audit state of the candidate content object a is that the manual audit passes (which may be indicated by using the corresponding quantized data, for example, by using the numeral "3" to indicate that the manual audit passes), the recommendation level is 1, the ranking information is 10, and the weighted summation is performed according to the browse data, the audit state, the recommendation level and the ranking information, so as to determine the content quality information of the candidate content object a according to the weighted summation result, for example, the content quality information of the candidate content object a is used to indicate that the candidate content object a is high-quality content.
The weight values corresponding to the browsing data, the auditing state, the recommendation level and the sorting information in the weighted summation can be determined according to the needs, which is not limited in this embodiment. The correspondence between the weighted sum result and the content quality level may be determined as needed, which is not limited in this embodiment.
Of course, in other embodiments, other ways of determining content quality information for each candidate content object may be employed.
Sub-step S1022: and determining the content freshness corresponding to the candidate content object according to the release time and the existing comment number of the candidate content object.
In one possible manner, for a certain candidate content object, the published time length is determined according to the published time and the current time, the comment number of the unit time length is determined according to the published time length and the existing comment number, and then the comment number of the unit published time is used as the content freshness.
Alternatively, in another possible manner, based on the number of comments per posting time obtained in the previous possible manner, the corresponding content freshness is determined according to a preset correspondence, for example, the content freshness is 90%, or the like.
Alternatively, in yet another possible manner, for a certain candidate content object, the freshness of the content may be obtained by weighting and summing the published time length and the number of existing comments. The weight value in the weighted summation can be determined according to the requirement, and the embodiment is not limited to this. Of course, in other embodiments, one skilled in the art may determine the freshness of the content in other ways, which the present embodiment is not limited to.
According to the embodiment, the target content data of the comment data to be generated is determined according to the content quality information and the content freshness of the candidate content objects, the target content objects can be rapidly and accurately determined from the candidate content objects, and further the comment data is generated according to the attribute information of the target content objects, so that the comment is performed by using the comment data object target content objects. Therefore, automatic comments are realized, comment forms are enriched, different comment requirements of users are met, and the comments are high in pertinence and better in relevance with the target content object.
The data processing method of the present embodiment may be performed by any suitable electronic device having data processing capabilities, including but not limited to: servers, mobile terminals (such as tablet computers, mobile phones and the like), PCs and the like.
Example III
Referring to fig. 3a, a flow chart of steps of a data processing method according to a third embodiment of the present invention is shown.
The data processing method of the present embodiment includes the aforementioned steps S102 to S108. Step S102 may be implemented by any of the foregoing embodiments. In order to be able to determine the target content object more accurately, in this embodiment, step S104 comprises the following sub-steps:
Substep S1041: and determining the target comment number corresponding to each candidate content object according to the content quality information and the content freshness of each candidate content object.
In one embodiment, the content quality information of the candidate content object a is taken as an example of the high-quality content. And determining a corresponding reference value a according to the content quality information of the candidate content object A, and adjusting the reference value a according to the content freshness of the candidate content object A, for example, carrying out weighted summation on the content freshness and the reference value a to obtain the target comment number. The weight value of the weighted sum may be determined as needed, which is not limited in this embodiment.
Of course, in other embodiments, the target number of comments may be obtained in other manners, which is not limited by the present embodiment.
Sub-step S1042: and determining the target content object with the existing comment number smaller than the target comment number according to the target comment number and the existing comment number of each candidate content object.
If the number of existing comments of the candidate content object is smaller than the target number of comments, the candidate content object is determined to be the target content object because comments are required to be made on the candidate content object. Otherwise, if the number of existing comments of the candidate content object is greater than or equal to the target number of comments, the candidate content object is indicated to not need to be commented, and no action can be performed on the candidate content object.
By combining the content quality information and the content freshness information of the candidate content object when the target content object is determined in the mode, the determined target content object is higher in heat degree, the supercooled content object which is too long in release time and lower in heat degree is not processed, and the accuracy of determining the target content object is improved.
Optionally, in this embodiment, when comment data is automatically generated for the determined target content object, in order to ensure that the association degree between the generated comment data and the target content object can meet the requirement, step S106 includes the following substeps:
substep S1061: and for each target content object, respectively determining the content association degree of a plurality of preset candidate comment data and the current target content object according to the attribute information of the current target content object and the content of the existing comment.
In the present embodiment, the attribute information includes at least one of: the content classification of the current target content object, the content label of the current target content object and the content field corresponding to the current target content object.
Of course, in other embodiments, the attribute information may also include other information, which is not limited by the present embodiment.
In a specific implementation manner, a plurality of candidate comment data are preset, and the comment data can be comment content data or comment identification data.
Each comment content data is provided with corresponding comment content attribute information such as corresponding content classification, content labels, corresponding content fields and the like. Similarly, the reviewer identification data may have corresponding reviewer attribute information, such as corresponding content classifications, content tags, and corresponding content fields, among others.
For comment content data, the first content relevance may be calculated according to comment content attribute information thereof, attribute information of the current target content object, and content of which the current target content object has a comment.
For the reviewer identification data, a second content relevance may be calculated based on the reviewer attribute information indicated by the reviewer identification data and attribute information of the current target content object, as well as the content of the existing review of the current target content object.
Those skilled in the art may calculate the content association degree in any suitable manner, for example, in a manner of calculating the euclidean distance or the like, or using a trained neural network model with an association degree calculation function, which is not limited in this embodiment.
Substep S1062: and determining candidate comment data with the content association degree with the current target content object meeting a set threshold value as the comment data of the current target content object.
In a specific implementation, sub-step S1062 may be implemented as: determining candidate comment data of which the content association degree with the current target content object meets a set threshold value; judging whether the determined number of the candidate comment data meets a preset number or not; if yes, selecting the candidate comment data with the preset quantity from the candidate comment data meeting the set threshold value as the comment data of the current target content object; otherwise, determining all the determined candidate comment data as the comment data of the current target content object.
The set threshold may be determined as desired, for example, 70%, 80%, 90%, etc.
When determining candidate comment data, comment content data greater than or equal to a set threshold value may be determined according to a first content association degree corresponding to each comment content data for candidate comment data (referred to as first candidate comment data) containing comment content data, and the first candidate comment data corresponding to these comment content data may be referred to as determined first candidate comment data.
Similarly, for candidate comment data (noted as second candidate comment data) containing comment identification data, comment identification data greater than or equal to a set threshold value may be determined based on the second content association degree corresponding to each of the comment identification data, and the second candidate comment data corresponding to these comment identification data is noted as determined second candidate comment data.
And if the determined first candidate comment data meets the preset quantity, determining the preset quantity of first candidate comment data from the determined first candidate comment data as the comment data of the current target content object. Otherwise, determining all the determined first candidate comment data as the comment data of the current target content object.
Similarly, if the determined second candidate comment data meets the preset number, determining the preset number of second candidate comment data from the determined second candidate comment data as comment data of the current target content object. Otherwise, determining all the determined second candidate comment data as the comment data of the current target content object.
The preset number may be set by those skilled in the art according to actual needs, and may be a difference between the target comment number of the current target content object and the existing comment number.
By the method, comment data with high content association degree with the target content object on the aspects of semantics and content can be obtained, so that the quality of follow-up comments is ensured.
After determining the comment data corresponding to each target content object, step S108 may be implemented as: and generating a corresponding comment task according to comment data corresponding to the target content object and the time to be comment, wherein the comment task is used for publishing the comment data corresponding to the target content object when the time to be comment arrives.
In a specific implementation, the comment tasks corresponding to each target content object may be one or more. Each comment task is provided with at least two corresponding comment data, namely first comment data comprising comment content data and second comment data comprising comment identification data. In addition, each comment task corresponds to one time to be comment.
The implementation manner of determining the first comment data, the second comment data and the time to be comment in the comment task is described below:
in step S106, comment data corresponding to each target content object has been determined, and part of the comment data is first comment data, and the other part of the comment data is second comment data, in this embodiment, for each first comment data, a task combination (i.e. determining comment content and a commenter) formed by the first comment data may be randomly matched with the second comment data, and each task combination corresponds to one comment task.
Of course, in other embodiments, the first comment data and the second comment data in the task combination may be determined in other manners, which is not limited in this embodiment.
The time to be commented corresponding to the commentary task can be determined according to the requirement. For example, a preset corresponding comment period is determined for the target content object, such as 45 minutes, 1 hour, 1 day, etc. after the current time. And randomly matching a time for each comment task in the comment time period to serve as the time to be commented.
And then, generating a comment task according to each task combination and the time to be commented. Each target content object may correspond to one or more comment tasks.
In order to promote automation, the comment task can be sent to a task queue, so that the comment task is automatically executed when the sending time arrives, and comment data corresponding to the corresponding target content object is published.
It should be noted that the task queue may be any suitable queue, for example, in order to reduce the load and ensure the operation reliability, the task queue may be a distributed queue based on a subscription mode.
The implementation process of the method of this embodiment is described below with reference to a specific usage scenario:
As shown in fig. 3b, the server configured with the method periodically triggers a task of acquiring a candidate content object, for example, a task of requesting a candidate content object from a certain target application program through an existing task scheduler.
For each candidate content object, the content identification unit performs quality rating on the candidate content object according to browsing data, auditing state, recommendation level, sorting information and the like, and acquires content quality information. The content quality information includes one of a premium content, a good content, and a normal content. The browsing data is used for indicating the heat of the corresponding candidate target content object.
Further, for each candidate content object, the freshness calculation unit calculates the corresponding content freshness according to the posting time thereof and the number of existing comments.
For each candidate content object, the comment quantity calculation unit calculates through the content quality information and the content freshness, determines whether the current candidate content object needs to automatically generate comment data, and determines the current candidate content object as a target content object if the current candidate content object needs to be generated automatically. In addition, the comment number calculation unit may also determine the number of comment data required for each target content object.
For each target content object, the comment content production unit calculates comment content index values through attribute information (such as content classification, content labels and related industries) of the target content object and contents of existing comments, and matches comment content data and comment identification data from a preset comment content library according to the index values to serve as determined comment data.
The comment sending task unit calculates corresponding sending time for each piece of determined comment data so as to achieve the purpose of sending different pieces of comment data in multiple times. Generating comment tasks according to the comment data and the sending time, sending the comment tasks to a message queue, and sending the comments generated according to the comment data to an application program where a target content object is located by the message queue when the sending time is reached, so that the function of commenting on the target content object is realized.
According to the method, automatic comment according to the needs of the user is achieved, the generated comment data is high in association degree with the target content object, the effect is better, comment time can be freely controlled, multiple comment data can be generated for one target content object at a time, execution efficiency is improved, and an appropriate target content object, such as a target content object with higher heat, can be selected according to the needs of the user to comment.
By the method, the real comment scene can be simulated, and better training effect can be obtained when the comment data of the target content object is used as a training sample for training in the follow-up process.
Alternatively, in another usage scenario, the server configured with the method periodically triggers a task of acquiring the candidate content object, for example, by an existing task scheduler periodically triggers a task of requesting the candidate content object from a certain network address (such as an address of a certain website). The candidate content object may be teletext content posted by the creator in the website.
For each of the obtained candidate content objects, the content identifying unit calculates content quality information of each of the obtained candidate content objects. The calculation may be the same as or different from the calculation of the usage scenario described above. The content quality information includes one of a good content (as indicated by the content quality information being 1), a good content (as indicated by the content quality information being 0.7), and a normal content (as indicated by the content quality information being 0.3).
And determining the corresponding content freshness by a freshness calculation unit according to the posting time, the number of existing comments and the latest comment time so as to indicate the timeliness and the attention degree of the candidate content object by the content freshness. For example, the posting time is determined according to the posting time, the latest comment posting time is determined according to the latest commented time, and the posting time, the number of existing comments and the latest comment posting time are weighted and summed to obtain the freshness of the content.
And determining a corresponding reference value according to the content quality information of the candidate content objects by a comment quantity calculation unit, and determining a target content object which needs to automatically generate comment data in each candidate content object according to the weighted summation result of the content freshness and the reference value. In addition, the comment number calculation unit may also determine the number of comment data required for each target content object.
For each target content object, the comment content production unit calculates comment content index values by passing attribute information (such as content classification, content labels and related industries) of the target content object and contents of existing comments, and matches comment content data and comment identification data from a preset comment content library according to the index values to serve as determined comment data.
The comment sending task unit calculates corresponding sending time for each piece of determined comment data so as to achieve the purpose of sending different pieces of comment data in multiple times. Generating comment tasks according to the comment data and the sending time, sending the comment tasks to a message queue, and sending the comments generated according to the comment data to a website where a target content object is located by the message queue when the sending time is reached, so that the function of commenting on the target content object is realized.
In the use scene, the automatic comment of contents (such as posts posted by users) posted by originators, comments posted by commentators and the like in the website can be realized in this way.
According to the embodiment, the target content data of the comment data to be generated is determined according to the content quality information and the content freshness of the candidate content objects, the target content objects can be rapidly and accurately determined from the candidate content objects, and further the comment data is generated according to the attribute information of the target content objects, so that the comment is performed by using the comment data object target content objects. Therefore, automatic comments are realized, comment forms are enriched, different comment requirements of users are met, and the comments are high in pertinence and better in relevance with the target content object.
The data processing method of the present embodiment may be performed by any suitable electronic device having data processing capabilities, including but not limited to: servers, mobile terminals (such as tablet computers, mobile phones and the like), PCs and the like.
Example IV
Referring to fig. 4, there is shown a block diagram of a data processing apparatus according to a fourth embodiment of the present invention.
The data processing apparatus of the present embodiment includes: an obtaining module 402, configured to obtain content quality information and content freshness of the candidate content object; a first determining module 404, configured to determine a target content object from the candidate content objects according to the content quality information and the content freshness of the candidate content objects; a second determining module 406, configured to automatically generate comment data for the target content object according to attribute information of the target content object; and a comment module 408, configured to comment on the target content object using the comment data.
Optionally, the obtaining module 402 is configured to determine, when obtaining content quality information of a candidate content object, content quality information corresponding to the candidate content object according to at least one of browsing data, an audit state, a recommendation level, and ranking information of the candidate content object, where the browsing data includes at least one of: number of reviews, number of comments available, and number of shares.
Optionally, when acquiring the content freshness of the candidate content object, the acquiring module 402 determines the content freshness corresponding to the candidate content object according to the release time and the existing comment number of the candidate content object.
Optionally, the first determining module 404 is configured to determine, according to content quality information and content freshness of each candidate content object, a target comment number corresponding to each candidate content object; and determining the target content object with the existing comment number smaller than the target comment number according to the target comment number and the existing comment number of each candidate content object.
Optionally, the second determining module 406 is configured to determine, for each of the target content objects, a content association degree between a plurality of preset candidate comment data and the current target content object according to attribute information of the current target content object and content of an existing comment; and determining candidate comment data with the content association degree with the current target content object meeting a set threshold value as the comment data of the current target content object.
Optionally, the second determining module 406 determines, when determining candidate comment data whose content association degree with the current target content object satisfies a set threshold as comment data of the current target content object, candidate comment data whose content association degree with the current target content object satisfies the set threshold; judging whether the determined number of the candidate comment data meets a preset number or not; if yes, selecting the candidate comment data with the preset quantity from the candidate comment data meeting the set threshold value as the comment data of the current target content object; otherwise, determining all the determined candidate comment data as the comment data of the current target content object.
Optionally, the attribute information includes at least one of: the content classification of the current target content object, the content label of the current target content object and the content field corresponding to the current target content object.
Optionally, the comment module 408 is configured to generate a corresponding comment task according to comment data corresponding to the target content object and a time to be comment, where the comment task is configured to post comment data corresponding to the target content object when the time to be comment arrives.
The data processing device of the present embodiment is configured to implement the corresponding data processing method in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again. In addition, the functional implementation of each module in the data processing apparatus of this embodiment may refer to the description of the corresponding portion in the foregoing method embodiment, which is not repeated herein.
Example five
Referring to fig. 5, a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention is shown, and the specific embodiment of the present invention is not limited to the specific implementation of the electronic device.
As shown in fig. 5, the electronic device may include: a processor 502, a communication interface (Communications Interface) 504, a memory 506, and a communication bus 508.
Wherein:
processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508.
A communication interface 504 for communicating with other electronic devices, such as terminal devices or servers.
The processor 502 is configured to execute the program 510, and may specifically perform relevant steps in the above-described data processing method embodiment.
In particular, program 510 may include program code including computer-operating instructions.
The processor 502 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the electronic device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
A memory 506 for storing a program 510. Memory 506 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 510 may be specifically operable to cause the processor 502 to: acquiring content quality information and content freshness of the candidate content object; determining a target content object from the candidate content objects according to the content quality information and the content freshness of the candidate content objects; automatically generating comment data for the target content object according to the attribute information of the target content object; and commenting the target content object by using the commentary data.
In an alternative embodiment, the program 510 is further configured to, when obtaining the content quality information of the candidate content object, cause the processor 502 to determine the content quality information corresponding to the candidate content object according to at least one of browsing data, an audit state, a recommendation level and ranking information of the candidate content object, where the browsing data includes at least one of: number of reviews, number of comments available, and number of shares.
In an alternative embodiment, the program 510 is further configured to, when the processor 502 obtains the content freshness of the candidate content object, determine, according to the release time and the number of existing comments of the candidate content object, the content freshness corresponding to the candidate content object.
In an alternative embodiment, the program 510 is further configured to, when determining a target content object from the candidate content objects according to the content quality information and the content freshness of the candidate content objects, cause the processor 502 to determine, according to the content quality information and the content freshness of each candidate content object, a target comment number corresponding to each candidate content object; and determining the target content object with the existing comment number smaller than the target comment number according to the target comment number and the existing comment number of each candidate content object.
In an optional embodiment, the program 510 is further configured to, when automatically generating comment data for the target content object according to attribute information of the target content object, determine, for each target content object, a content association degree between a plurality of preset candidate comment data and a current target content object according to attribute information of the current target content object and content of an existing comment; and determining candidate comment data with the content association degree with the current target content object meeting a set threshold value as the comment data of the current target content object.
In an alternative embodiment, the program 510 is further configured to cause the processor 502 to determine candidate comment data having a content association with the current target content object that meets a set threshold when determining candidate comment data having a content association with the current target content object that meets a set threshold as comment data of the current target content object; judging whether the determined number of the candidate comment data meets a preset number or not; if yes, selecting the candidate comment data with the preset quantity from the candidate comment data meeting the set threshold value as the comment data of the current target content object; otherwise, determining all the determined candidate comment data as the comment data of the current target content object.
In an alternative embodiment, the attribute information includes at least one of: the content classification of the current target content object, the content label of the current target content object and the content field corresponding to the current target content object.
In an optional embodiment, the program 510 is further configured to cause the processor 502 to generate, when using the comment data to comment on the target content object, a corresponding comment task according to comment data corresponding to the target content object and a time to be comment, where the comment task is configured to post, when the time to be comment arrives, comment data corresponding to the target content object.
The specific implementation of each step in the program 510 may refer to the corresponding steps and corresponding descriptions in the units in the above data processing method embodiment, which are not repeated herein. It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and modules described above may refer to corresponding procedure descriptions in the foregoing method embodiments, which are not repeated herein.
It should be noted that, according to implementation requirements, each component/step described in the embodiments of the present invention may be split into more components/steps, or two or more components/steps or part of operations of the components/steps may be combined into new components/steps, so as to achieve the objects of the embodiments of the present invention.
The above-described methods according to embodiments of the present invention may be implemented in hardware, firmware, or as software or computer code storable in a recording medium such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk, or as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium and to be stored in a local recording medium downloaded through a network, so that the methods described herein may be stored on such software processes on a recording medium using a general purpose computer, special purpose processor, or programmable or special purpose hardware such as an ASIC or FPGA. It is understood that a computer, processor, microprocessor controller, or programmable hardware includes a memory component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the data processing methods described herein. Further, when a general-purpose computer accesses code for implementing the data processing methods illustrated herein, execution of the code converts the general-purpose computer into a special-purpose computer for executing the data processing methods illustrated herein.
Those of ordinary skill in the art will appreciate that the elements and method steps of the examples described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or as a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present invention.
The above embodiments are only for illustrating the embodiments of the present invention, but not for limiting the embodiments of the present invention, and various changes and modifications may be made by one skilled in the relevant art without departing from the spirit and scope of the embodiments of the present invention, so that all equivalent technical solutions also fall within the scope of the embodiments of the present invention, and the scope of the embodiments of the present invention should be defined by the claims.
Claims (8)
1. A data processing method, comprising:
acquiring content quality information and content freshness of a candidate content object, wherein the content freshness is determined according to the release time and the existing comment number of the candidate content object;
Determining a reference value indicating the comment quantity when the posting duration reaches a duration according to the content quality information of the candidate content object;
adjusting the reference value according to the content freshness of the candidate content object to obtain a target comment number corresponding to the candidate content object;
determining target content objects with the existing comment numbers smaller than the target comment numbers according to the target comment numbers and the existing comment numbers of the candidate content objects;
automatically generating comment data aiming at the target content object according to the attribute information of the target content object, wherein the comment data aiming at the target content object is a plurality of comment data generated aiming at one target content object;
and generating a corresponding comment task according to comment data and time to be comment corresponding to the target content object, transmitting the comment task to a message queue, and transmitting the comment generated according to the comment data to an application program where the target content object is located by the message queue when the transmission time is reached.
2. The method of claim 1, wherein obtaining content quality information for the candidate content object comprises:
determining content quality information corresponding to the candidate content object according to at least one of browsing data, auditing state, recommendation level and ordering information of the candidate content object, wherein the browsing data comprises at least one of the following: number of reviews, number of comments available, and number of shares.
3. The method of claim 1, wherein the automatically generating comment data for the target content object from the attribute information of the target content object comprises:
for each target content object, respectively determining the content association degree of a plurality of preset candidate comment data and the current target content object according to the attribute information of the current target content object and the content of the existing comment;
and determining candidate comment data with the content association degree with the current target content object meeting a set threshold value as the comment data of the current target content object.
4. The method of claim 3, wherein the determining candidate comment data that satisfies a set threshold with respect to the content association degree of the current target content object as comment data of the current target content object includes:
determining candidate comment data of which the content association degree with the current target content object meets a set threshold value;
judging whether the determined number of the candidate comment data meets a preset number or not;
if yes, selecting the candidate comment data with the preset quantity from the candidate comment data meeting the set threshold value as the comment data of the current target content object; otherwise, determining all the determined candidate comment data as the comment data of the current target content object.
5. The method of claim 3 or 4, wherein the attribute information includes at least one of: the content classification of the current target content object, the content label of the current target content object and the content field corresponding to the current target content object.
6. A data processing apparatus comprising:
the acquisition module is used for acquiring content quality information and content freshness of the candidate content objects, wherein the content freshness is determined according to the release time and the existing comment number of the candidate content objects;
a first determining module, configured to determine a reference value indicating the number of comments when the posting duration reaches a duration according to content quality information of the candidate content object; adjusting the reference value according to the content freshness of the candidate content object to obtain a target comment number corresponding to the candidate content object; determining target content objects with the existing comment numbers smaller than the target comment numbers according to the target comment numbers and the existing comment numbers of the candidate content objects;
the second determining module is used for automatically generating comment data aiming at the target content object according to the attribute information of the target content object, wherein the comment data aiming at the target content object is a plurality of comment data generated aiming at one target content object;
And the comment module is used for generating a corresponding comment task according to comment data and time to be comment corresponding to the target content object, transmitting the comment task into a message queue, and transmitting the comment generated according to the comment data into an application program where the target content object is located by the message queue when the transmission time arrives.
7. An electronic device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the data processing method according to any one of claims 1 to 5.
8. A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a data processing method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010368121.7A CN113595860B (en) | 2020-04-30 | 2020-04-30 | Data processing method, device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010368121.7A CN113595860B (en) | 2020-04-30 | 2020-04-30 | Data processing method, device, electronic equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113595860A CN113595860A (en) | 2021-11-02 |
| CN113595860B true CN113595860B (en) | 2023-06-13 |
Family
ID=78236918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010368121.7A Active CN113595860B (en) | 2020-04-30 | 2020-04-30 | Data processing method, device, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113595860B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108153856A (en) * | 2017-12-22 | 2018-06-12 | 北京百度网讯科技有限公司 | For the method and apparatus of output information |
| CN108491463A (en) * | 2018-03-05 | 2018-09-04 | 科大讯飞股份有限公司 | Label determination method and device |
| CN110264315A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Recommended information generation method and device |
| CN110737841A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9152675B2 (en) * | 2013-03-15 | 2015-10-06 | Facebook, Inc. | Selection and ranking of comments for presentation to social networking system users |
| US9467744B2 (en) * | 2013-12-30 | 2016-10-11 | Verizon and Redbox Digital Entertainment Services, LLC | Comment-based media classification |
| CN106294373B (en) * | 2015-05-15 | 2020-03-10 | 阿里巴巴集团控股有限公司 | Comment information reply method and device |
| CN107241622A (en) * | 2016-03-29 | 2017-10-10 | 北京三星通信技术研究有限公司 | video location processing method, terminal device and cloud server |
| CN107305549A (en) * | 2016-04-18 | 2017-10-31 | 北京搜狗科技发展有限公司 | Language data processing method, device and the device for language data processing |
| CN107391548B (en) * | 2017-04-06 | 2020-08-04 | 华东师范大学 | Mobile application market examination user group detection method and system |
| CN107832390A (en) * | 2017-10-31 | 2018-03-23 | 广东欧珀移动通信有限公司 | Comment information processing method, device, terminal device and storage medium |
| CN108228794B (en) * | 2017-12-29 | 2020-03-31 | 三角兽（北京）科技有限公司 | Information management apparatus, information processing apparatus, and automatic replying/commenting method |
| CN109408755A (en) * | 2018-09-14 | 2019-03-01 | 广州神马移动信息科技有限公司 | Data processing method, device, terminal device and computer storage medium |
| CN109543068A (en) * | 2018-11-30 | 2019-03-29 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating the comment information of video |
| CN110032623B (en) * | 2018-12-12 | 2023-02-24 | 创新先进技术有限公司 | Method and device for matching question of user with title of knowledge point |
| CN110087118B (en) * | 2019-04-26 | 2022-01-21 | 北京达佳互联信息技术有限公司 | Comment message processing method, comment message processing device, comment message processing terminal, comment message processing server and comment message processing medium |
| CN110310146A (en) * | 2019-05-30 | 2019-10-08 | 北京三快在线科技有限公司 | Method, device, electronic device, and storage medium for determining online celebrity merchants |
| CN110569334A (en) * | 2019-09-11 | 2019-12-13 | 北京搜狐新动力信息技术有限公司 | A method and device for automatically generating comments |
-
2020
- 2020-04-30 CN CN202010368121.7A patent/CN113595860B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108153856A (en) * | 2017-12-22 | 2018-06-12 | 北京百度网讯科技有限公司 | For the method and apparatus of output information |
| CN108491463A (en) * | 2018-03-05 | 2018-09-04 | 科大讯飞股份有限公司 | Label determination method and device |
| CN110737841A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN110264315A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Recommended information generation method and device |
Non-Patent Citations (4)
| Title |
|---|
| Vote-and-Comment: Modeling the Coevolution of User Interactions in Social Voting Web Sites;Alceu Ferraz Costa;《IEEE Xplore》;全文 * |
| 电子商务中的评论挖掘及应用研究;董宇蔚;《CNKI中国知网》;全文 * |
| 网络推荐和在线评论对数字内容商品体验消费的整合影响及实证研究;戴和忠;《CNKI中国知网》;全文 * |
| 评论信息处理的方法及装置;付强;《百度学术》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113595860A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
| EP3873065B1 (en) | Content recommendation method, mobile terminal, and server | |
| US9838743B2 (en) | Techniques for context aware video recommendation | |
| CN106339507B (en) | Streaming Media information push method and device | |
| CN109636487B (en) | Advertisement pushing method, server, computer device and storage medium | |
| CN107870984A (en) | The method and apparatus for identifying the intention of search term | |
| CN107808346B (en) | A kind of evaluation method and evaluation device of potential target object | |
| CN112241327B (en) | Sharing information processing method, device, storage medium and electronic device | |
| CN111651666A (en) | User theme recommendation method, device, computer equipment and storage medium | |
| CN113383362A (en) | User identification method and related product | |
| CN112749327B (en) | Content push method and device | |
| CN109213933B (en) | Content item recommendation method, device, equipment and storage medium | |
| CN108932640B (en) | Method and device for processing orders | |
| CN112182460A (en) | Resource pushing method and device, storage medium and electronic device | |
| WO2022007626A1 (en) | Video content recommendation method and apparatus, and computer device | |
| CN110866040A (en) | User portrait generation method, device and system | |
| CN113743982A (en) | Advertisement putting scheme recommendation method and device, computer equipment and storage medium | |
| CN109284367B (en) | Method and device for processing text | |
| CN112613938A (en) | Model training method and device and computer equipment | |
| CN111126649B (en) | Method and device for generating information | |
| CN117974234A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN110634024A (en) | User attribute marking method and device, electronic equipment and storage medium | |
| CN108647986B (en) | Target user determination method and device and electronic equipment | |
| CN113595860B (en) | Data processing method, device, electronic equipment and computer storage medium | |
| CN113779423A (en) | Model parameter adjusting method and device, electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |