A data processing method, device, electronic equipment and storage medium

Abstract

The application relates to a data processing method and device, electronic equipment and a storage medium, and relates to a data processing method. The method comprises the following steps: acquiring publication times corresponding to a plurality of news respectively displayed on a media platform; dividing the plurality of news based on the publication times to obtain at least one first news and at least one second news; acquiring author information and content information corresponding to each first news; scoring each first news based on the author information and the content information to obtain a reading score corresponding to each first news; when a user operation is detected, acquiring a first account score; sorting the plurality of news based on the first account score, the first reading score, a second reading score and the publication time of each news to obtain a sorting result; and outputting the sorting result to a terminal device corresponding to a user. The application has the effect of improving the adaptation degree between the media platform and the user.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a data processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, more and more people are joining the ranks of those investing. However, due to the weak or nonexistent financial knowledge of novice investors, they often don't know where to start. As a result, novice investors often choose to read financial news through financial media platforms to understand the social and economic situation and learn from it. However, because novice investors have a weak foundation and the news on existing media platforms is geared towards a group that only focuses on financial news, novice investors often find themselves unable to understand the rest of the news after reading half of it. In other words, the current media platforms have a low degree of compatibility with users. Summary of the Invention

[0003] To improve the compatibility between media platforms and users, this application provides a data processing method, apparatus, electronic device, and storage medium.

[0004] Firstly, this application provides a data processing method, employing the following technical solution:

[0005] A data processing method, comprising:

[0006] Obtain the publication time of each of the multiple news items displayed on the media platform;

[0007] Based on the publication time, the multiple news items are divided to obtain at least one first news item and at least one second news item, wherein the first news item is a news item without a reading score and the second news item is a news item with a reading score.

[0008] Obtain the author information and content information for each first news story;

[0009] Each first news item is scored based on the author information and the content information to obtain a reading score for each first news item;

[0010] When a user action is detected, the first account score is obtained, which is the account score corresponding to the user.

[0011] The multiple news items are sorted based on the first account score, the first reading score, the second reading score, and the publication time of each news item to obtain a sorting result. The first reading score is the reading score corresponding to each first news item, and the second reading score is the reading score corresponding to each second news item.

[0012] The sorting results are output to the terminal device corresponding to the user.

[0013] By employing the aforementioned technical solution, the publication times of multiple news items to be displayed on the media platform are obtained. This allows for the segmentation of the news items based on publication time. The first news item is the one without a reading score (i.e., news that has not undergone reading score calculation), while the second news item is the one with a reading score (i.e., news that has undergone reading score calculation). Since the publication time represents the time a news item has been displayed on the media platform, the existence of a reading score for each news item can be determined by the publication time, thus enabling the segmentation of multiple news items into at least one first news item and at least one second news item. Each news item has corresponding author information. Each author has a different writing style and habitual word choice. Therefore, the author information and content information of each first news item can be obtained. This allows for the combination of author information and content information to score each first news item, obtaining a corresponding reading score for each first news item. This, in turn, determines the ease of understanding of each first news item during the analysis process. When a user action is detected, it indicates that a user needs to view news. Therefore, the user's first account score can be obtained. Based on the first account score, first reading score, second reading score, and the publication time of each news item, multiple news items are sorted to obtain a sorting result. The sorting result is then output to the user's corresponding terminal device, allowing the user to view multiple news items based on the sorting result, thereby improving the compatibility between the media platform and the user.

[0014] In another possible implementation, the step of dividing the multiple news items based on the publication time to obtain at least one first news item and at least one second news item includes:

[0015] Get the last acquisition time, where the last acquisition time is the time when the media platform displays the publication time of each of the multiple news items.

[0016] The publication time of each news item is compared with the previous acquisition time to obtain at least one first news item and at least one second news item, wherein the publication time of the first news item is later than the previous acquisition time, and the publication time of the second news item is earlier than the previous acquisition time.

[0017] By adopting the above technical solution, the last acquisition time is the time when the electronic device performed the last acquisition of the publication time corresponding to the multiple news items displayed on the media platform. The publication time of each news item is compared with the last acquisition time. When the publication time is later than the last acquisition time, it means that the news item corresponding to that publication time has not undergone the previous scoring process, thus indicating that the news item corresponding to that publication time has no reading score. Therefore, the news item corresponding to that publication time can be determined as the first news item. When the publication time is earlier than the last acquisition time, it means that the news item corresponding to that publication time has undergone the previous scoring operation, thus indicating that the news item corresponding to that publication time has a reading score. Therefore, the news item corresponding to that publication time can be determined as the second news item. This achieves the effect of dividing multiple news items and obtaining at least one first news item and at least one second news item.

[0018] In another possible implementation, a reading score is obtained by scoring each first news item based on its author information and content information, including:

[0019] Determine whether there is at least one third news item, wherein the third news item is the second news item corresponding to the author information of any first news item;

[0020] If at least one third news item exists, then obtain the comment information for each third news item and the reading score corresponding to each third news item;

[0021] Based on the comment information, the reading score corresponding to each third news item, and the content information corresponding to any first news item, a score is given for each first news item to obtain the reading score corresponding to the first news item.

[0022] If there is no at least one third news item, then obtain the second account score, which is the account score corresponding to the author information of any first news item.

[0023] Based on the score of the second account, predict the reading score corresponding to any of the first news items.

[0024] By employing the aforementioned technical solution, it is determined whether at least one third news item exists, thus clarifying whether the author of the first news item has other news works. If so, it indicates that the author of the first news item has other news works. The comment information and corresponding reading scores reflect the ease of understanding of the news and its suitability for a certain age group. Therefore, the comment information and corresponding reading scores for each third news item can be obtained. Based on the comment information, reading scores, and the content information of the first news item, a score is assigned to the first news item, thus determining its reading score. Conversely, if at least one third news item does not exist, it indicates that the author of the first news item has no other news works, meaning the reading score cannot be determined based on other news works. However, since the account scores of the authors are the same, their financial knowledge is similar, resulting in similar reading scores for their news articles. Therefore, a second account score can be obtained, and the reading score of the first news item can be predicted based on this second account score, thus determining its reading score.

[0025] In another possible implementation, the comment information includes at least one comment, and each comment includes comment content and comment account information;

[0026] The step of scoring any first news item based on the comment information, the reading score corresponding to each third news item, and the content information corresponding to any first news item to obtain the reading score corresponding to the first news item includes:

[0027] Feature recognition is performed on the comment content of the at least one comment to determine at least one target comment from the at least one comment;

[0028] Obtain the third account score, which is the account score of the comment account information corresponding to the at least one target comment;

[0029] Based on the score of the third account, determine the comment score corresponding to the comment information;

[0030] Based on the reading score corresponding to each third news item, the sub-reading score corresponding to any first news item is obtained;

[0031] Perform feature recognition on the content information corresponding to any of the first news items to determine the number of different preset feature words in the content information corresponding to any of the first news items;

[0032] Based on the quantity, determine the content score of the content information corresponding to any of the first news items;

[0033] Based on the comment score, the sub-read score, the content score, and their respective weights, the reading score corresponding to any first news item is obtained.

[0034] By adopting the above technical solution, the comment information includes at least one comment, and each comment includes comment content and comment account information. The target comment is a comment that represents the first news item as easily understandable. Since the comment account information corresponds to different user levels, the target comment can be identified from at least one comment, and the account score corresponding to the comment account information of the target comment, i.e., the third account score, can be obtained. The comment score corresponding to the comment information is determined based on the third account score. Furthermore, since the news reading score can represent the reading score range of the news written by the author of the first news item, the sub-reading score corresponding to the first news item can be obtained based on the reading score corresponding to each third news item. At the same time, the preset feature words are pre-defined feature words, which are specialized terms in financial knowledge. Feature recognition is performed on the content information corresponding to the first news item to determine the number of different preset feature words in the content information corresponding to the first news item. The more preset feature words there are, the more professional the first news item is, and the more users with solid financial knowledge need to understand it. Therefore, the content score of the content information corresponding to the first news item can be determined based on the number of preset feature words. Finally, since the comment score, sub-read score, and content score have different degrees of influence on the reading score, that is, their respective weights are also different. The greater the influence, the greater the weight. Therefore, the reading score of the first news can be obtained based on the comment score, sub-read score, content score, and their respective weights, thus achieving the effect of calculating the reading score of the first news.

[0035] In another possible implementation, predicting the reading score corresponding to any of the first news items based on the second account score includes:

[0036] Obtain at least one second news item from the target author, wherein the target author's account score is the same as the second account score;

[0037] Based on the reading scores corresponding to at least one second news item by the target author, the reading score corresponding to any one of the first news items is determined.

[0038] By adopting the above technical solution, in the embodiments of this application, the target author's account score is the same as the second account score, that is, the same as the account score corresponding to the author information of the first news currently being calculated. Since the scores are the same, it can be said that the authors' writing words are similar. Therefore, by obtaining at least one second news of the target author and determining the reading score corresponding to the first news based on the reading scores corresponding to at least one second news, the effect of predicting the reading score corresponding to the first news based on the second account score can be achieved.

[0039] In another possible implementation, the sorting of the multiple news items based on the first account score, the first reading score, the second reading score, and the publication time of each news item to obtain the sorting result includes:

[0040] Determine the reading score range corresponding to the score of the first account;

[0041] Based on the reading score range, a third reading score and a fourth reading score are determined from the first reading score and the second reading score, wherein the third reading score is the reading score that falls within the reading score range and the fourth reading score is the reading score that does not fall within the reading score range;

[0042] Based on the third reading score and the publication time, the news articles corresponding to the third reading score are sorted to obtain a first sorting result;

[0043] Based on the fourth reading score and the publication time, the news articles corresponding to the fourth reading score are sorted to obtain a second sorting result;

[0044] Based on the first sorting result and the second sorting result, the sorting result of the multiple news items is obtained.

[0045] By adopting the above technical solution, each account score corresponds to a reading score range. The reading score range corresponding to the first account score is determined, allowing for the determination of the third and fourth reading scores from the first and second reading scores based on this range. The third reading score is the reading score within the range, and the news corresponding to the third reading score is news that the user with the first account score can understand. The fourth reading score is the reading score not within the range, and the news corresponding to the fourth reading score is news that the user with the first account score may not understand. Since news is real-time, while facilitating user viewing, it is necessary to sort the news based on its publication time. Preferably, the news corresponding to the third reading score can be sorted based on the third reading score and publication time to obtain a first sorting result. The news corresponding to the fourth reading score can be sorted based on the fourth reading score and publication time to obtain a second sorting result. Based on the first and second sorting results, a sorting result for multiple news items is obtained, thus achieving the effect of sorting multiple news items.

[0046] In another possible implementation, determining the reading score range corresponding to the first account score includes:

[0047] Obtain the reading records of multiple target users, wherein the account score of each target user is the same as the score of the first account.

[0048] Based on the reading records, determine the reading score range for each target user;

[0049] Based on the reading score range corresponding to each target user, the reading score range corresponding to the first account score is determined.

[0050] By adopting the above technical solution, the target user's account score is the same as the first account score, which means that the target user's financial knowledge level is close to that of the current user. Therefore, we can first determine the reading records of each target user and the corresponding reading score range for each target user. By combining the reading score ranges of multiple target users, we can determine the reading score range corresponding to the first account score, thereby achieving the effect of determining the reading range corresponding to the first account score.

[0051] Secondly, this application provides a data processing apparatus, which adopts the following technical solution:

[0052] A data processing apparatus, comprising:

[0053] The first acquisition module is used to acquire the publication time of each of the multiple news items displayed on the media platform;

[0054] The segmentation module is used to segment the multiple news items based on the publication time to obtain at least one first news item and at least one second news item, wherein the first news item is a news item without a reading score and the second news item is a news item with a reading score.

[0055] The second acquisition module is used to acquire author information and content information corresponding to each first news item;

[0056] The scoring module is used to score each first news item based on the author information and the content information, and obtain a reading score for each first news item.

[0057] The third acquisition module is used to acquire a first account score when a user operation is detected, wherein the first account score is the account score corresponding to the user.

[0058] The sorting module is used to sort the multiple news items based on the first account score, the first reading score, the second reading score, and the publication time of each news item to obtain a sorting result. The first reading score is the reading score corresponding to each first news item, and the second reading score is the reading score corresponding to each second news item.

[0059] The output module is used to output the sorting result to the terminal device corresponding to the user.

[0060] By adopting the above technical solution, the first acquisition module obtains the publication times of multiple news items to be displayed on the media platform. This allows the segmentation module to divide the news items based on their publication times. The first news item is the news without a reading score, meaning it has not undergone a reading score calculation. The second news item is the news with a reading score, meaning it has undergone a reading score calculation. Since the publication time represents the time a news item has been displayed on the media platform, the existence of a reading score for each news item can be determined by the publication time, thus enabling the segmentation of multiple news items into at least one first news item and at least one second news item. Each news item has corresponding author information. Each author has a different writing style and habitual word choice. Therefore, the second acquisition module can obtain the author information and content information of each first news item. This allows the scoring module to combine the author information and content information to score each first news item, obtaining a corresponding reading score for each first news item. This, in turn, determines whether each first news item is easy to understand during the analysis process. When a user action is detected, it indicates that a user needs to view news. Therefore, the user's first account score can be obtained through the third acquisition module. The sorting module sorts multiple news items based on the first account score, first reading score, second reading score, and the publication time of each news item, obtaining a sorting result for multiple news items. The sorting result is then output to the user's corresponding terminal device through the output module, so that the user can view multiple news items based on the sorting result, thereby improving the compatibility between the media platform and the user.

[0061] In another possible implementation, when the segmentation module segments the multiple news items based on the publication time to obtain at least one first news item and at least one second news item, it is specifically used for:

[0062] Get the last acquisition time, where the last acquisition time is the time when the media platform displays the publication time of each of the multiple news items.

[0063] The publication time of each news item is compared with the previous acquisition time to obtain at least one first news item and at least one second news item, wherein the publication time of the first news item is later than the previous acquisition time, and the publication time of the second news item is earlier than the previous acquisition time.

[0064] In another possible implementation, when the scoring module scores any first news item based on the author information and content information corresponding to that first news item, and obtains a reading score for that first news item, it is specifically used for:

[0065] Determine whether there is at least one third news item, wherein the third news item is the second news item corresponding to the author information of any first news item;

[0066] If at least one third news item exists, then obtain the comment information for each third news item and the reading score corresponding to each third news item;

[0067] Based on the comment information, the reading score corresponding to each third news item, and the content information corresponding to any first news item, a score is given for each first news item to obtain the reading score corresponding to the first news item.

[0068] If there is no at least one third news item, then obtain the second account score, which is the account score corresponding to the author information of any first news item.

[0069] Based on the score of the second account, predict the reading score corresponding to any of the first news items.

[0070] In another possible implementation, the comment information includes at least one comment, and each comment includes comment content and comment account information;

[0071] When the scoring module scores any first news item based on the comment information, the reading score corresponding to each third news item, and the content information corresponding to any first news item, and obtains the reading score corresponding to any first news item, it is specifically used for:

[0072] Feature recognition is performed on the comment content of the at least one comment to determine at least one target comment from the at least one comment;

[0073] Obtain the third account score, which is the account score of the comment account information corresponding to the at least one target comment;

[0074] Based on the score of the third account, determine the comment score corresponding to the comment information;

[0075] Based on the reading score corresponding to each third news item, the sub-reading score corresponding to any first news item is obtained;

[0076] Perform feature recognition on the content information corresponding to any of the first news items to determine the number of different preset feature words in the content information corresponding to any of the first news items;

[0077] Based on the quantity, determine the content score of the content information corresponding to any of the first news items;

[0078] Based on the comment score, the sub-read score, the content score, and their respective weights, the reading score corresponding to any first news item is obtained.

[0079] In another possible implementation, when the scoring module predicts the reading score corresponding to any of the first news items based on the second account score, it is specifically used for:

[0080] Obtain at least one second news item from the target author, wherein the target author's account score is the same as the second account score;

[0081] Based on the reading scores corresponding to at least one second news item by the target author, the reading score corresponding to any one of the first news items is determined.

[0082] In another possible implementation, when the sorting module sorts the multiple news articles based on the first account score, the first reading score, the second reading score, and the publication time of each news article to obtain the sorting result, it is specifically used for:

[0083] Determine the reading score range corresponding to the score of the first account;

[0084] Based on the reading score range, a third reading score and a fourth reading score are determined from the first reading score and the second reading score, wherein the third reading score is the reading score that falls within the reading score range and the fourth reading score is the reading score that does not fall within the reading score range;

[0085] Based on the third reading score and the publication time, the news articles corresponding to the third reading score are sorted to obtain a first sorting result;

[0086] Based on the fourth reading score and the publication time, the news articles corresponding to the fourth reading score are sorted to obtain a second sorting result;

[0087] Based on the first sorting result and the second sorting result, the sorting result of the multiple news items is obtained.

[0088] In another possible implementation, when determining the reading score range corresponding to the first account score, the sorting module is specifically used for:

[0089] Obtain the reading records of multiple target users, wherein the account score of each target user is the same as the score of the first account.

[0090] Based on the reading records, determine the reading score range for each target user;

[0091] Based on the reading score range corresponding to each target user, the reading score range corresponding to the first account score is determined.

[0092] Thirdly, this application provides an electronic device that adopts the following technical solution:

[0093] An electronic device comprising:

[0094] At least one processor;

[0095] Memory;

[0096] At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform a data processing method as shown in any possible implementation of the first aspect.

[0097] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0098] A computer-readable storage medium that, when the computer program is executed in a computer, causes the computer to perform the data processing method according to any one of the first aspects.

[0099] In summary, this application includes at least one of the following beneficial technical effects:

[0100] 1. Obtain the publication times of multiple news items to be displayed on the media platform. This allows for the segmentation of news items based on publication time. The first news item is the one without a reading score (i.e., it has not undergone a reading score calculation), while the second news item is the one with a reading score (i.e., it has undergone a reading score calculation). Since the publication time represents the time a news item has been displayed on the media platform, the existence of a reading score for each news item can be determined by the publication time, thus segmenting multiple news items into at least one first news item and at least one second news item. Each news item has corresponding author information. Each author has a different writing style and habitual word choice. Therefore, the author information and content information of each first news item can be obtained. This allows for the combination of author and content information to score each first news item, obtaining its corresponding reading score, thereby determining the ease of understanding and analysis of each first news item. When a user action is detected, it means that a user needs to view news. Therefore, the user's first account score can be obtained. Based on the first account score, first reading score, second reading score, and the publication time of each news article, multiple news articles are sorted to obtain a sorting result. The sorting result is then output to the user's corresponding terminal device so that the user can view multiple news articles based on the sorting result, thereby improving the compatibility between the media platform and the user.

[0101] 2. Each account score corresponds to a reading score range. The reading score range corresponding to the first account score is determined so that a third and fourth reading score can be determined from the first and second reading scores based on this range. The third reading score is the reading score within the range, and the news corresponding to the third reading score is news that the user with the first account score can understand. The fourth reading score is the reading score outside the range, and the news corresponding to the fourth reading score is news that the user with the first account score may not understand. Since news is real-time, while facilitating user viewing, news needs to be sorted based on its publication time. Preferably, news corresponding to the third reading score can be sorted based on the third reading score and publication time to obtain a first sorting result. News corresponding to the fourth reading score can be sorted based on the fourth reading score and publication time to obtain a second sorting result. Based on the first and second sorting results, a sorting result for multiple news items is obtained, thus achieving the effect of sorting multiple news items. Attached Figure Description

[0102] Figure 1 This is a flowchart illustrating a data processing method according to an embodiment of this application.

[0103] Figure 2This is a flowchart illustrating a method for scoring any first news item based on the author information and content information corresponding to any first news item, as described in this application, to obtain a reading score for any first news item.

[0104] Figure 3 This is a flowchart illustrating a method for sorting multiple news items based on a first account score, a first reading score, a second reading score, and the publication time of each news item, according to an embodiment of this application, to obtain a sorting result.

[0105] Figure 4 This is a schematic diagram of the structure of a data processing device according to an embodiment of this application.

[0106] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0107] The following is in conjunction with the appendix Figure 1-5 This application will be described in further detail.

[0108] After reading this specification, those skilled in the art may make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0109] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0110] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0111] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0112] This application provides a data processing method executed by an electronic device, which can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this connection. Figure 1 As shown, the method includes steps S101, S102, S103, S104, S105, S106, and S107, wherein,

[0113] Step S101: Obtain the publication time of each of the multiple news items displayed on the media platform.

[0114] In this embodiment of the application, the publication times of multiple news items to be displayed on the media platform are obtained, so as to determine the news items for which reading scores need to be calculated based on the publication times. Assume that the multiple news items to be displayed on media platform A are news A, news B, news C, and news D, and the publication times of news A, news B, news C, and news D are 18:00 on April 7, 2023, 7:00 on April 8, 2023, 8:00 on April 8, 2023, and 8:01 on April 8, 2023, respectively.

[0115] Step S102: Based on the publication time, divide the multiple news items into at least one first news item and at least one second news item.

[0116] The first news item is one without a reading score, while the second news item is one with a reading score.

[0117] In this embodiment of the application, the first news item is news without a reading score, that is, news that has not undergone reading score calculation, and the second news item is news with a reading score, that is, news that has undergone reading score calculation. Since the publication time represents the time that the news has been displayed on the media platform, the publication time can be used to determine whether each news item has a reading score, thereby dividing multiple news items into at least one first news item and at least one second news item. Taking step S101 as an example, assume that the at least one first news item is news C and news D, and the at least one second news item is news A and news B.

[0118] Step S103: Obtain the author information and content information corresponding to each first news item.

[0119] In this embodiment, each news article has corresponding author information. Each author has a different writing style and habitual word choice. Therefore, the author information of each first news article can be obtained to determine whether the first news article is easy to understand. The content information of the news article refers to the specific content stated in the news article. In this embodiment, the carrier of the news article can be text, video, or audio recording, without limitation. For news articles with different carriers, they can all be converted into text form to facilitate subsequent analysis of the news content information. Specifically, for news articles with video and audio recordings, speech recognition can be used to convert the video and audio recordings into text form. Taking step S102 as an example, the author information of news article C is obtained as author C, and the author information of news article D is obtained as author D.

[0120] Step S104: Score each first news item based on author information and content information to obtain a reading score for each first news item.

[0121] In this embodiment of the application, the content information refers to the content stated in the news article. Each author has a different writing style, habitual terminology, and level of financial knowledge required. The reading score of the news article represents its reading difficulty; the higher the score, the more financial knowledge the user needs to acquire during the reading process, and the more difficult it is to understand. Therefore, it is possible to score the first news article based on the author information and content information, thus obtaining the corresponding reading score.

[0122] In this embodiment of the application, only the first news item is scored, avoiding the situation where the second news item that has already been scored is also scored, thus reducing the waste of computer resources.

[0123] Step S105: When a user operation is detected, obtain the first account score.

[0124] The first account score is the score of the user's corresponding account.

[0125] In this embodiment of the application, the first account score is the account score corresponding to the user. In order to facilitate providing users with financial news that is easy to understand, each user has a corresponding account score. This account score can be adjusted according to the user's current comprehension ability. The user's initial comprehension ability can be tested by jumping to a test page when the user registers an account to obtain the user's initial account score. Subsequently, the initial account score is updated according to the user's reading volume and the reading score of the news read, so that the user's account score can reflect the user's comprehension ability of financial news.

[0126] Step S106: Sort multiple news articles based on the first account score, the first reading score, the second reading score, and the publication time of each news article to obtain the sorting result.

[0127] The first reading score is the reading score corresponding to each first news item, and the second reading score is the reading score corresponding to each second news item.

[0128] Step S107: Output the sorting results to the user's corresponding terminal device.

[0129] In this embodiment of the application, for financial news media platforms, even news with existing reading scores still needs to be displayed to users. Due to the real-time nature of news, it is not possible to only show users news that they can understand based on their reading scores. Even if there is news that users may not understand, it is still necessary to display the more difficult-to-understand news. In order to meet the user's reading experience, multiple news items can be sorted according to the user's account score, first reading score, second reading score, and the publication time of each news item. The sorting results are then output so that users can clearly understand the financial news that they can easily understand. This allows users to view financial news in a targeted manner according to their own situation, thereby improving the adaptability between the media platform and the user.

[0130] Furthermore, in this embodiment of the application, the reading score of each news item can be marked next to the news title, so that users can clearly understand whether each news item is easy to understand.

[0131] Furthermore, in this embodiment of the application, the sorting results can be output on the display screen of the user's corresponding terminal device.

[0132] One possible implementation of this application embodiment includes step S102, which involves dividing multiple news items based on their publication time to obtain at least one first news item and at least one second news item, and includes:

[0133] Get the last acquisition time, which is the time when the media platform displays the publication time of each of the multiple news items. Compare the publication time of each news item with the last acquisition time to get at least one first news item and at least one second news item. The publication time of the first news item is later than the last acquisition time, and the publication time of the second news item is earlier than the last acquisition time.

[0134] In this embodiment, the last acquisition time refers to the time when the electronic device acquired the publication time of each of the multiple news items displayed on the media platform. Assuming the last acquisition time was 7:30 AM on April 8, 2023, comparing the publication time of each news item with 7:30 AM on April 8, 2023, if the publication time is later than the last acquisition time, it means that the news item corresponding to that publication time has not undergone the previous scoring process, thus indicating that the news item corresponding to that publication time has no reading score. Therefore, the news item corresponding to that publication time can be identified as the first news item. Conversely, if the publication time is earlier than the last acquisition time, it means that the news item corresponding to that publication time has undergone the previous scoring operation, thus indicating that the news item corresponding to that publication time already has a reading score, and therefore can be identified as the second news item. By dividing multiple news items, the electronic device avoids repeatedly calculating reading scores for news items that already have reading scores, thereby reducing the waste of computing resources.

[0135] Furthermore, in this embodiment of the application, a timestamp can be set for the operation of obtaining the publication time corresponding to multiple news items displayed on the media platform, so as to obtain the effect of the last acquisition through the timestamp.

[0136] One possible implementation of the embodiments of this application is as follows: Figure 2 As shown, step S104 scores any first news item based on its author information and content information, obtaining a reading score for each first news item. This includes steps S1041, S1042, S1043, S1044, and S1045.

[0137] Step S1041: Determine whether there is at least one third news item.

[0138] Among them, the third news item is the second news item corresponding to the author information of any first news item.

[0139] For the embodiments of this application, taking step S102 as an example, assuming that any first news is news C, and the third news is the second news corresponding to author C, that is, the author information of the third news is the same as the author information of news C, it is determined whether there is at least one third news, that is, it is determined whether author C has other news works, so that the writing habits of author C can be determined based on the third news, such as word choice, description, etc., that is, the reading score of news C can be determined based on the third news.

[0140] Step S1042: If there is at least one third news item, obtain the comment information for each third news item and the reading score corresponding to each third news item.

[0141] Step S1043: Based on the comment information, the reading score corresponding to each third news item, and the content information corresponding to any first news item, score any first news item to obtain the reading score corresponding to any first news item.

[0142] In this embodiment of the application, when there is at least one third news item, it indicates that the author of the first news item has other news works. Since the comments section of the news can reflect readers' suggestions and feelings about the news, but due to malicious evaluations and other behaviors, the reading score of the third news item also represents the degree of ease of understanding of the third news item, that is, to a certain extent, it represents whether the news written by author C is easy for readers to understand. Moreover, the content information of the first news item itself can also reflect the ease of understanding of the first news item. Therefore, in order to make the reading score more accurately represent the degree of ease of understanding of the news, the comment information of each third news item and the corresponding reading score of each third news item can be obtained, so that the first news item can be scored based on the comment information, reading score and content information of the first news item in the future.

[0143] Taking step S1041 as an example, assuming that at least one third news item corresponding to author C is news item E and news item F, the comment information of news item E is obtained as comment information E and the reading score is 45 points, and the comment information of news item F is comment information F and the reading score is 40 points.

[0144] Step S1044: If there is no third news item, obtain the second account score, which is the account score corresponding to the author information of any first news item.

[0145] Step S1045: Based on the second account score, predict the reading score corresponding to any first news item.

[0146] In the embodiments of this application, when there is no third news, taking step S1041 as an example, it means that author C does not have other news works, that is, it is not possible to predict the reading score of news C based on author C's news works. However, since author C also needs to log in to the media platform before he can publish news, author C has an account score. The account score of author C represents the degree of author C's understanding of financial knowledge. Therefore, the reading score corresponding to news C can be predicted based on the second account score.

[0147] In this embodiment of the application, for the sake of clarity, a detailed description is given of the calculation of the reading score of at least one first news item based on the calculation of the reading score of a first news item. The calculation method for the reading score of multiple first news items is the same as the calculation method for any one first news item, and will not be repeated here.

[0148] One possible implementation of this application embodiment includes step S1043, which scores any first news item based on comment information, the reading score corresponding to each third news item, and the content information corresponding to any first news item, to obtain the reading score corresponding to any first news item.

[0149] The process involves: identifying features in the content of at least one comment to determine at least one target comment; obtaining a third account score, which is the account score of the comment account information corresponding to each of the at least one target comment; determining the comment score based on the third account score; obtaining the sub-reading score for any first news item based on the reading score for each third news item; identifying features in the content information corresponding to any first news item to determine the number of different preset feature words present in the content information; determining the content score for the content information corresponding to any first news item based on the number of features; and obtaining the reading score for any first news item based on the comment score, sub-reading score, content score, and their respective weights.

[0150] In the embodiments of this application, the comment information includes at least one comment, and each comment includes comment content and comment account information. Taking step S1043 as an example, assume that the comment information E includes comment e1 and comment e2, comment e1 includes comment account e1 and comment content e1, comment e2 includes comment account e2 and comment content e2, and the comment information F includes comment f1 and comment f2, comment f1 includes comment account f1 and comment content f1, and comment f2 includes comment account f2 and comment content f2. When performing feature recognition on the content of at least one comment, the preset feature words in the preset feature word library are positive words, such as "well said," "detailed," and "easy to understand." The target comment is the comment containing the preset feature words. However, due to the different comprehension abilities of the users commenting, the target comment's representation of whether the third news is easy to understand varies. The third account score is the account score of the comment account information corresponding to each of the at least one target comment. Therefore, obtaining the third account score allows electronic devices to determine the comment score corresponding to the intentional influencing factor of the comment information based on the third account score. Assuming that the target comments in comments e1, e2, f1, and f2 are comments e2, f1, and f2, and the account scores corresponding to comment accounts e2, f1, and f2 are 50, 35, and 45 points respectively. Since a lower score indicates that the news is more suitable for people with weak financial knowledge, the third account scores can be sorted, and the lowest third account score can be determined as the comment score. That is, the comment score is determined to be 35 points.

[0151] Furthermore, since the reading scores of news articles E and F represent the overall score range of the news articles written by author C, the sub-reading score for news article C can be obtained based on the reading score for each third news article. In this embodiment, the sub-reading score can be obtained by calculating the average of the reading scores for at least one third news article and determining the average as the sub-reading score. That is, the sub-reading score for news article C is determined to be 42.5 points.

[0152] Preset feature words are pre-defined terms specific to financial knowledge. Feature identification is performed on the content information corresponding to the first news item to determine the number of different preset feature words present. A higher number indicates a more specialized news item, requiring users with solid financial knowledge to understand. Therefore, the content score of the first news item can be determined based on the number of preset feature words. Specifically, the preset number is a pre-defined threshold representing a relatively large number of preset feature words. If the preset number is not reached, it is multiplied by a preset coefficient to obtain the content score. If it is reached, it means that the current news item contains many different preset feature words, making it difficult for most users to understand. Therefore, the highest content score can be directly determined as the content score of the first news item. In this embodiment, a percentage system is used. Assuming the preset number is 20 and the preset coefficient is 5, the current news item C has 8 preset feature words, which does not reach the preset number. Therefore, 8 is multiplied by the preset coefficient 5, resulting in a content score of 40 for news item C.

[0153] Based on the determined comment score of 35 points, sub-read score of 42.5 points, and content score of 40 points, along with their respective weights, the reading score of News C is determined. Since the comment score, sub-read score, and content score have different degrees of influence on the reading score, their respective weights also differ; the greater the influence, the greater the weight. In this embodiment, the weights can be weights set by media platform managers based on their own experience to approximate actual conditions. For example, assuming the weights for the comment score, sub-read score, and content score are 0.2, 0.3, and 0.5 respectively, the calculated reading score for News C is 39.75 points.

[0154] One possible implementation of this application embodiment includes step S1045, which predicts the reading score corresponding to any first news item based on the second account score, including:

[0155] Obtain at least one second news item from the target author, where the target author's account score is the same as the second account score; based on the reading scores corresponding to the at least one second news item from the target author, determine the reading score corresponding to any first news item.

[0156] In this embodiment of the application, the target author's account score is the same as the second account score, that is, the same as the account score corresponding to the author information of the first news article currently being calculated. Since the scores are the same, it can be said that the authors' writing words are similar. Therefore, by obtaining at least one second news article of the target author, assuming the target author is author G, the reading scores of at least one second news article corresponding to author G are 40 points, 35 points and 42 points respectively. Therefore, the average of 40 points, 35 points and 42 points can be calculated, and the average of 39 points is determined as the reading score corresponding to the first news article.

[0157] Furthermore, in this embodiment of the application, there can be multiple target authors. By taking the average of the average values ​​corresponding to the multiple target authors again and determining the final average value as the reading score of the first news article, the reading score of the determined first news article can be more accurate.

[0158] One possible implementation of the embodiments of this application is as follows: Figure 3 As shown, step S106, when sorting multiple news items based on the first account score, the first reading score, the second reading score, and the publication time of each news item to obtain the sorting result, specifically includes steps S1061, S1062, S1063, S1064, and S1065, wherein...

[0159] Step S1061: Determine the reading score range corresponding to the score of the first account.

[0160] Step S1062: Based on the reading score interval, determine the third reading score and the fourth reading score from the first reading score and the second reading score.

[0161] The third reading score is the reading score within the reading score range, and the fourth reading score is the reading score outside the reading score range.

[0162] In this embodiment of the application, each account score corresponds to a reading score range. Assuming the first account score is 50 points, the corresponding reading score range is [0, 59]. The reading score range corresponding to the first account score is determined so that the third and fourth reading scores can be determined from the first and second reading scores based on this range. Assuming the first reading scores are 39.75, 42, and 60 points, and the second reading scores are 35, 40, 70, 75, and 85 points, the third reading score is the reading score within the reading score range. The news corresponding to the third reading score is news that the user can understand, corresponding to the first account score; that is, the third reading scores are 39.75, 42, 35, and 40 points. The fourth reading score is the reading score not within the reading score range; that is, the fourth reading score is 60, 70, 75, and 85 points.

[0163] Step S1063: Based on the third reading score and the publication time, sort the news corresponding to the third reading score to obtain the first sorting result.

[0164] Step S1064: Based on the fourth reading score and the publication time, sort the news corresponding to the fourth reading score to obtain the second sorting result.

[0165] Step S1065: Based on the first sorting result and the second sorting result, obtain the sorting result of multiple news items.

[0166] In this embodiment of the application, news articles corresponding to the third reading score and news articles corresponding to the fourth reading score are sorted based on the distribution of publication time, so that users can not only view the latest news, but also select news to watch based on the ease of reading the news and their own knowledge level.

[0167] In this embodiment of the application, the sorting rule can be that the later the publication time, the higher it appears in the sorting results. Taking step S1062 as an example, assuming that the news corresponding to 39.75 points, 42 points, 35 points, and 40 points are news C, news D, news H, and news I respectively, the first sorting result is determined to be news H, news D, news C, and news I in sequence. The news corresponding to 60 points, 70 points, 75 points, and 85 points are news A, news B, news J, and news K respectively, the second sorting result is determined to be news J, news K, news A, and news B in sequence. That is, the sorting result of multiple news items is determined to be news A, news B, news J, news K, news J, news K, news A, and news B.

[0168] One possible implementation of this application embodiment includes step S1061, which involves determining the reading score range corresponding to the first account score, including:

[0169] Obtain the reading records of multiple target users, whose account scores are the same as the first account score; based on the reading records, determine the reading score range corresponding to each target user; based on the reading score range corresponding to each target user, determine the reading score range corresponding to the first account score.

[0170] In this embodiment of the application, the target user's account score is the same as the first account score, that is, the target user's financial knowledge level is close to that of the current user. Therefore, the reading records of each target user can be determined first to determine the reading score range corresponding to each target user. By combining the reading score ranges of multiple target users, the reading score range corresponding to the first account score can be determined, thereby achieving the effect of determining the reading range corresponding to the first account score.

[0171] Assuming the target users are user B and user C, based on user B's reading history, user B's reading score range is determined to be [0, 65], and based on user C's reading history, user C's reading score range is determined to be [0, 59]. Therefore, it can be determined that news within the range of [0, 59] is understandable to both user B and user C. Thus, [0, 59] can be determined as the reading score range corresponding to the first account's score.

[0172] Furthermore, in this embodiment, since some users attempt to browse news with higher scores, even if they fail to understand them, they still generate reading records, thus raising the user's reading score range, it can be determined whether the user has finished reading the news by combining the user's reading time with the normal reading time for the corresponding news. Specifically, when a user's reading record shows that the reading score of a certain news item is much higher than that of other news items, the user's reading time for that news item is obtained and compared with the preset reading time for that news item. If the preset reading time is exceeded, it means that the user can understand and analyze the news item. If the preset reading time is not reached, it means that the user cannot understand the news item and only briefly viewed it without being able to analyze it. Therefore, it can be determined that the user's reading score range does not include the reading score for that news item, thereby improving the accuracy of the reading score range and making the determined reading score range corresponding to the first account score more closely match the user's actual situation.

[0173] The above embodiments describe a data processing method from the perspective of process flow. The following embodiments describe a data processing apparatus from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.

[0174] This application provides a data processing apparatus 40, such as... Figure 4 As shown, the data processing apparatus 40 may specifically include:

[0175] The first acquisition module 401 is used to acquire the publication time of each of the multiple news items displayed on the media platform;

[0176] The segmentation module 402 is used to segment multiple news items based on their publication time to obtain at least one first news item and at least one second news item. The first news item is a news item that does not have a reading score, and the second news item is a news item that has a reading score.

[0177] The second acquisition module 403 is used to acquire the author information and content information corresponding to each first news item;

[0178] The scoring module 404 is used to score each first news item based on author information and content information, and obtain the reading score corresponding to each first news item.

[0179] The third acquisition module 405 is used to acquire the first account score when a user operation is detected. The first account score is the account score corresponding to the user.

[0180] The sorting module 406 is used to sort multiple news items based on the first account score, the first reading score, the second reading score, and the publication time of each news item, and obtain the sorting result. The first reading score is the reading score corresponding to each first news item, and the second reading score is the reading score corresponding to each second news item.

[0181] Output module 407 is used to output the sorting results to the user's corresponding terminal device.

[0182] By adopting the above technical solution, the first acquisition module 401 acquires the publication times of multiple news items to be displayed on the media platform, so that the segmentation module 402 can segment the multiple news items according to the publication time. The first news item is the news item without a reading score, that is, the news item that has not undergone reading score calculation, and the second news item is the news item with a reading score, that is, the news item that has undergone reading score calculation. Since the publication time represents the time that the news has been displayed on the media platform, it is possible to determine whether each news item has a reading score by using the publication time, thereby achieving the segmentation of multiple news items and obtaining at least one first news item and at least one second news item. Each news item has corresponding author information. Each author has a different writing style and habitual word usage. Therefore, the second acquisition module 403 can acquire the author information and content information of each first news item, so that the scoring module 404 can combine the author information and content information to score each first news item and obtain the corresponding reading score for each first news item, thereby achieving the effect of determining whether each first news item is easy to understand during the understanding and analysis process. When a user operation is detected, it indicates that a user needs to view news. Therefore, the user's first account score can be obtained through the third acquisition module 405. The sorting module sorts multiple news items based on the first account score, first reading score, second reading score, and the publication time of each news item, obtaining a sorting result for multiple news items. The sorting result is then output to the user's corresponding terminal device through the output module 407, so that the user can view multiple news items based on the sorting result, thereby improving the compatibility between the media platform and the user.

[0183] In one possible implementation of this application embodiment, when the segmentation module 402 segments multiple news items based on publication time to obtain at least one first news item and at least one second news item, it is specifically used for:

[0184] Get the last time it was retrieved. The last time it was retrieved is the time when the media platform retrieved the publication time of each of the multiple news items.

[0185] Compare the publication time of each news item with the previous acquisition time to obtain at least one first news item and at least one second news item. The publication time of the first news item is later than the previous acquisition time, and the publication time of the second news item is earlier than the previous acquisition time.

[0186] In one possible implementation of this application embodiment, when the scoring module 404 scores any first news item based on the author information and content information corresponding to any first news item to obtain a reading score for any first news item, it is specifically used for:

[0187] Determine whether there exists at least one third news item, where the third news item is the second news item corresponding to the author information of any first news item;

[0188] If there is at least one third news item, then obtain the comment information for each third news item and the corresponding reading score for each third news item;

[0189] The reading score for each first news item is obtained by scoring the first news item based on the comment information, the reading score for each third news item, and the content information for each first news item.

[0190] If there is no third news item, then obtain the second account score, which is the account score corresponding to the author information of any first news item.

[0191] Based on the second account score, predict the reading score corresponding to any first news item.

[0192] In one possible implementation of this application embodiment, when the scoring module 404 scores any first news item based on comment information, the reading score corresponding to each third news item, and the content information corresponding to any first news item, and obtains the reading score corresponding to any first news item, it is specifically used for:

[0193] Feature recognition is performed on the content of at least one comment to identify at least one target comment from the at least one comment;

[0194] Obtain the third account score, which is the account score corresponding to the comment account information of at least one target comment;

[0195] Determine the comment score corresponding to the comment information based on the third-party account score;

[0196] Based on the reading score corresponding to each third news item, the sub-reading score corresponding to any first news item is obtained;

[0197] Perform feature recognition on the content information corresponding to any first news item to determine the number of different preset feature words in the content information corresponding to any first news item.

[0198] The content score is determined based on the quantity of the content information corresponding to any first news item.

[0199] Based on the comment score, sub-read score, content score, and their respective weights, the reading score for any first news item is obtained.

[0200] In one possible implementation of this application embodiment, when the scoring module 404 predicts the reading score corresponding to any first news item based on the second account score, it is specifically used for:

[0201] Obtain at least one second news item from the target author, where the target author's account score is the same as the second account score;

[0202] Based on the reading scores corresponding to at least one second news item for the target author, determine the reading score corresponding to any first news item.

[0203] In one possible implementation of this application embodiment, when the sorting module 406 sorts multiple news items based on a first account score, a first reading score, a second reading score, and the publication time of each news item, and obtains the sorting result, it is specifically used for:

[0204] Determine the reading score range corresponding to the first account's score;

[0205] Based on the reading score range, the third and fourth reading scores are determined from the first and second reading scores. The third reading score is the reading score that falls within the reading score range, and the fourth reading score is the reading score that does not fall within the reading score range.

[0206] Based on the third reading score and the publication time, the news articles corresponding to the third reading score are sorted to obtain the first sorting result;

[0207] Based on the fourth reading score and the publication time, the news articles corresponding to the fourth reading score are sorted to obtain the second sorting result;

[0208] Based on the first and second sorting results, the sorting results of multiple news items are obtained.

[0209] In one possible implementation of this application embodiment, when the sorting module 406 determines the reading score range corresponding to the first account score, it is specifically used for:

[0210] Obtain the reading records of multiple target users, where the account score of each target user is the same as the score of the first account.

[0211] Based on reading records, determine the reading score range for each target user;

[0212] Based on the reading score range corresponding to each target user, determine the reading score range corresponding to the first account's score.

[0213] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0214] This application provides an electronic device, such as... Figure 5 As shown, Figure 5The illustrated electronic device 50 includes a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, for example, via a bus 502. Optionally, the electronic device 50 may also include a transceiver 504. It should be noted that in practical applications, the transceiver 504 is not limited to one unit, and the structure of this electronic device 50 does not constitute a limitation on the embodiments of this application.

[0215] Processor 501 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 501 may also be a combination that implements computational functions, such as including at least one microprocessor combination, a combination of a DSP and a microprocessor, etc.

[0216] Bus 502 may include a pathway for transmitting information between the aforementioned components. Bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 502 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0217] The memory 503 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0218] The memory 503 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 501. The processor 501 is used to execute the application code stored in the memory 503 to implement the content shown in the foregoing method embodiments.

[0219] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0220] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments. Compared with related technologies, this application provides an embodiment that obtains the publication times of multiple news items to be displayed on a media platform. This facilitates the division of multiple news items based on their publication times. The first news item is one without a reading score, i.e., news that has not undergone reading score calculation. The second news item is one with a reading score, i.e., news that has undergone reading score calculation. Since the publication time represents the time a news item has been displayed on the media platform, the publication time can be used to determine whether each news item has a reading score, thereby dividing multiple news items into at least one first news item and at least one second news item. Each news item has corresponding author information. Each author has a different writing style and habitual word choice. Therefore, the author information and content information of each first news item can be obtained, allowing for the combination of author information and content information to score each first news item and obtain a corresponding reading score. This achieves the effect of determining whether each first news item is easy to understand during the analysis process. When a user action is detected, it indicates that a user needs to view news. Therefore, the user's first account score can be obtained. Based on the first account score, first reading score, second reading score, and the publication time of each news item, multiple news items are sorted to obtain a sorting result. The sorting result is then output to the user's corresponding terminal device, allowing the user to view multiple news items based on the sorting result, thereby improving the compatibility between the media platform and the user.

[0221] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0222] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A data processing method, characterized in that, include: Obtain the publication time of each of the multiple news items displayed on the media platform; Based on the publication time, the multiple news items are divided to obtain at least one first news item and at least one second news item, wherein the first news item is a news item without a reading score and the second news item is a news item with a reading score. Obtain the author information and content information for each first news story; Each first news item is scored based on the author information and the content information to obtain a reading score for each first news item; When a user action is detected, the first account score is obtained, which is the account score corresponding to the user. The multiple news items are sorted based on the first account score, the first reading score, the second reading score, and the publication time of each news item to obtain a sorting result. The first reading score is the reading score corresponding to each first news item, and the second reading score is the reading score corresponding to each second news item. The sorting results are output to the terminal device corresponding to the user.

2. The data processing method according to claim 1, characterized in that, The step of dividing the multiple news items based on the publication time to obtain at least one first news item and at least one second news item includes: Get the last acquisition time, where the last acquisition time is the time when the media platform displays the publication time of each of the multiple news items. The publication time of each news item is compared with the previous acquisition time to obtain at least one first news item and at least one second news item, wherein the publication time of the first news item is later than the previous acquisition time, and the publication time of the second news item is earlier than the previous acquisition time.

3. The data processing method according to claim 1, characterized in that, Based on the author information and content information corresponding to any first news item, a reading score is obtained for each first news item, including: Determine whether there is at least one third news item, wherein the third news item is the second news item corresponding to the author information of any first news item; If at least one third news item exists, then obtain the comment information for each third news item and the reading score corresponding to each third news item; Based on the comment information, the reading score corresponding to each third news item, and the content information corresponding to any first news item, a score is given for each first news item to obtain the reading score corresponding to the first news item. If there is no at least one third news item, then obtain the second account score, which is the account score corresponding to the author information of any first news item. Based on the score of the second account, predict the reading score corresponding to any of the first news items.

4. The data processing method according to claim 3, characterized in that, The comment information includes at least one comment, and each comment includes the comment content and the comment account information; The step of scoring any first news item based on the comment information, the reading score corresponding to each third news item, and the content information corresponding to any first news item to obtain the reading score corresponding to the first news item includes: Feature recognition is performed on the comment content of the at least one comment to determine at least one target comment from the at least one comment; Obtain the third account score, which is the account score of the comment account information corresponding to the at least one target comment; Based on the score of the third account, determine the comment score corresponding to the comment information; Based on the reading score corresponding to each third news item, the sub-reading score corresponding to any first news item is obtained; Perform feature recognition on the content information corresponding to any of the first news items to determine the number of different preset feature words in the content information corresponding to any of the first news items; Based on the quantity, determine the content score of the content information corresponding to any of the first news items; Based on the comment score, the sub-read score, the content score, and their respective weights, the reading score corresponding to any first news item is obtained.

5. The data processing method according to claim 3, characterized in that, The step of predicting the reading score corresponding to any of the first news items based on the second account score includes: Obtain at least one second news item from the target author, wherein the target author's account score is the same as the second account score; Based on the reading scores corresponding to at least one second news item by the target author, the reading score corresponding to any one of the first news items is determined.

6. The data processing method according to claim 1, characterized in that, The process of sorting the multiple news articles based on the first account score, the first reading score, the second reading score, and the publication time of each news article to obtain a sorting result includes: Determine the reading score range corresponding to the score of the first account; Based on the reading score range, a third reading score and a fourth reading score are determined from the first reading score and the second reading score, wherein the third reading score is the reading score that falls within the reading score range and the fourth reading score is the reading score that does not fall within the reading score range; Based on the third reading score and the publication time, the news articles corresponding to the third reading score are sorted to obtain a first sorting result; Based on the fourth reading score and the publication time, the news articles corresponding to the fourth reading score are sorted to obtain a second sorting result; Based on the first sorting result and the second sorting result, the sorting result of the multiple news items is obtained.

7. The data processing method according to claim 6, characterized in that, Determining the reading score range corresponding to the first account score includes: Obtain the reading records of multiple target users, wherein the account score of each target user is the same as the score of the first account. Based on the reading records, determine the reading score range for each target user; Based on the reading score range corresponding to each target user, the reading score range corresponding to the first account score is determined.

8. A data processing apparatus, characterized in that, include: The first acquisition module is used to acquire the publication time of each of the multiple news items displayed on the media platform; The segmentation module is used to segment the multiple news items based on the publication time to obtain at least one first news item and at least one second news item, wherein the first news item is a news item without a reading score and the second news item is a news item with a reading score. The second acquisition module is used to acquire author information and content information corresponding to each first news item; The scoring module is used to score each first news item based on the author information and the content information, and obtain a reading score for each first news item. The third acquisition module is used to acquire a first account score when a user operation is detected, wherein the first account score is the account score corresponding to the user. The sorting module is used to sort the multiple news items based on the first account score, the first reading score, the second reading score, and the publication time of each news item to obtain a sorting result. The first reading score is the reading score corresponding to each first news item, and the second reading score is the reading score corresponding to each second news item. The output module is used to output the sorting result to the terminal device corresponding to the user.

9. An electronic device, characterized in that, It includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, the at least one application being configured to: perform the data processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed in the computer, it causes the computer to perform the data processing method according to any one of claims 1 to 7.

Images