Method, device and equipment for determining public opinion information collection entrance and storage medium

Abstract

Embodiments of the present application provide a method, device and storage medium for determining an opinion information collection portal. In the embodiments of the present application, the method comprises: obtaining target information that is hit in social media based on a search condition; the target information comprises opinion information and / or social information associated with the opinion information; determining a collection portal mining strategy that matches an information type of the target information according to a pre-set correspondence between different information types and collection portal mining strategies and the information type of the target information; and performing information mining on the target information using the collection portal mining strategy to obtain a social media account associated with the target information as an opinion information collection portal.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for determining a public opinion information collection entry point. Background Technology

[0002] From a technical perspective, public opinion monitoring refers to the integration of internet information collection technology and intelligent information processing technology. By automatically capturing, classifying and clustering, detecting themes, and focusing on topics from massive amounts of internet information, it enables users to meet their information needs such as monitoring online public opinion and tracking news topics, and generates analytical results such as briefings, reports, and charts.

[0003] In the process of implementing the above technologies, "automatic capture of massive amounts of information on the Internet" is a crucial step in obtaining the data foundation for public opinion monitoring. Theoretically, when conducting public opinion monitoring, the more Internet information (public opinion information) used for public opinion analysis and the wider its sources, the higher the accuracy of the public opinion analysis conclusions will be.

[0004] Currently, social media is a significant source of internet information. Social media refers to online platforms for content production and exchange based on user relationships. These platforms currently include social networking sites / software, microblogs, WeChat, blogs, forums, short video platforms, and more, and the information they disseminate has become an important part of people's internet browsing experience.

[0005] In existing technologies, public opinion information can be obtained by using users' social media accounts as the entry point for collecting relevant information (including collecting posts, comments, etc.). However, because social media accounts are constantly changing—new or deleted accounts may be added every minute—how to achieve sustainable collection of public opinion information from social media accounts in this scenario is a problem that existing technologies urgently need to solve. Summary of the Invention

[0006] This application provides a method, apparatus, electronic device, and storage medium for determining the entry point for public opinion information collection, in order to solve the problem of how to achieve sustainable collection of public opinion information from social media accounts in the prior art.

[0007] This application embodiment also provides a method for determining the entry point for public opinion information collection, including: acquiring target information hit in social media based on search conditions; the target information includes: public opinion information and / or social information associated with the public opinion information; determining an entry point mining strategy that matches the information type of the target information according to a pre-set correspondence between different information types and entry point mining strategies, and the information type of the target information; and using the entry point mining strategy to perform information mining on the target information to obtain social media accounts associated with the target information, which serve as entry points for public opinion information collection.

[0008] This application embodiment also provides a device for determining a public opinion information collection entry point, including: an information acquisition module, used to acquire target information hit in social media based on search conditions; the target information includes: public opinion information and / or social information associated with the public opinion information; a strategy determination module, used to determine a collection entry mining strategy that matches the information type of the target information according to a pre-set correspondence between different information types and collection entry mining strategies, and the information type of the target information; and an information mining module, used to perform information mining on the target information using the collection entry mining strategy to obtain social media accounts associated with the target information as public opinion information collection entry points.

[0009] This application embodiment also provides an electronic device, including: a memory and a processor; the memory is used to store a computer program; the processor, coupled to the memory, is used to execute the computer program for: acquiring target information hit in social media based on search conditions; the target information includes: public opinion information and / or social information associated with the public opinion information; determining a collection entry mining strategy that matches the information type of the target information according to a pre-set correspondence between different information types and collection entry mining strategies, and the information type of the target information; and using the collection entry mining strategy to perform information mining on the target information to obtain social media accounts associated with the target information as public opinion information collection entry points.

[0010] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to implement the steps of the method for determining the public opinion information collection entry point provided in this application.

[0011] Through at least one of the above embodiments, since it is possible to obtain target information such as public opinion information and / or social information associated with public opinion information in social media based on search conditions, and then determine the collection entry mining strategy that matches the information type of the target information according to the pre-set correspondence between different information types and collection entry mining strategies, this allows for the use of collection entry mining strategies that match the real-time hit public opinion information and / or social information associated with public opinion information, regardless of changes in social media accounts. Information mining can then be performed on the hit public opinion information and / or social information associated with public opinion information to obtain social media accounts associated with the hit target information, serving as the public opinion information collection entry point, thus achieving sustainable collection of public opinion information from social media accounts. Furthermore, after hitting the public opinion information and / or social information associated with public opinion information, this solution further mines the associated accounts based on the hit information, which can increase the number of accounts covered by the hit public opinion information and / or social information associated with public opinion information. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0013] Figure 1 A schematic diagram illustrating the implementation process of a method for determining a public opinion information collection entry point, provided as an exemplary embodiment of this application;

[0014] Figure 2 A schematic diagram illustrating the correspondence between different information types and the mining strategy of the collection entry point in the method for determining the public opinion information collection entry point provided in the exemplary embodiment of this application;

[0015] Figure 3 A flowchart illustrating the method for determining the public opinion information collection entry point provided in the exemplary embodiments of this application, applied in a real-world scenario;

[0016] Figure 4 A schematic diagram of the structure of a device for determining a public opinion information collection entry point, provided as an exemplary embodiment of this application;

[0017] Figure 5 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application. Detailed Implementation

[0018] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0019] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a,” “the,” and “the” used in one or more embodiments of this application and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.

[0020] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this application, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0021] First, the terms and concepts involved in one or more embodiments of this application will be explained.

[0022] To address the aforementioned problems in existing technologies, this application provides a method for determining the entry point for public opinion information collection. This method acquires target information such as public opinion information and / or related social information found on social media based on search criteria. Then, according to a pre-set correspondence between different information types and entry point mining strategies, and the information type of the target information, a mining strategy matching the information type of the target information is determined. Thus, regardless of changes in social media accounts, a mining strategy matching the real-time found public opinion information and / or related social information can be used to mine the found public opinion information and / or related social information, thereby obtaining social media accounts associated with the found target information as entry points for public opinion information collection, achieving sustainable collection of public opinion information from social media accounts. Specifically, this application provides a method for determining the entry point for public opinion information collection. This application also relates to a device, electronic device, and computer-readable storage medium for determining the entry point for public opinion information collection, which will be described in detail in the following embodiments.

[0023] Figure 1This is a flowchart illustrating a method for determining a public opinion information collection entry point, provided as an exemplary embodiment of this application. Figure 1 As shown, the method includes:

[0024] Step 110: Obtain target information in social media based on search criteria; the target information includes: public opinion information and / or social information associated with public opinion information.

[0025] The search criteria can consist of one or more search keywords and a specified search category. Social media can include platforms such as Weibo, Facebook, Twitter, and Instagram that allow users to post their opinions. Because public opinion on social media is often rapidly changing—for example, a piece of public opinion information may only remain in a trending area for a very limited time before being overshadowed by new trending information—and because the posting and dissemination of each piece of public opinion information relies on a social media account, and users' social media accounts typically do not change, the information posted by users on social media can be analyzed more deeply based on their social media accounts. Therefore, to achieve sustainable collection of public opinion data in a specific area, this application uses users' social media accounts as the entry point for public opinion information collection. To improve the coverage of the ultimately identified user's social media accounts, the corresponding collection entry point mining strategy can be determined based on the different types of target information hit by the search criteria on social media, in order to fully explore social media accounts associated with the target information.

[0026] Optionally, to obtain social media accounts associated with public opinion information in a specified field and improve the efficiency of social media account mining, the search conditions in this application embodiment may include search keywords and search categories. Specifically, obtaining target information hit in social media based on search conditions includes:

[0027] Obtain search criteria, which include at least one search keyword and a search category, including at least one of the following: post list, user list, group list, page list, activity list, image list, and video list;

[0028] Retrieve target information based on at least one search keyword in the search criteria that matches a specified search category on social media.

[0029] The search criteria can include a single keyword or a combination of keywords. To improve the efficiency of discovering social media accounts, search categories can be specified when defining search criteria. For example, search categories such as user location are not relevant to obtaining social media accounts associated with public opinion information in a specific field, so these categories can be excluded. Specifically, search categories such as post lists, user lists, group lists, page lists, activity lists, image lists, and video lists can be specified as search criteria. After the search keywords and search categories are determined, target information can be retrieved from social media based on these keywords and categories. This target information can include search results for the search keywords in the specified post lists, user lists, group lists, page lists, activity lists, image lists, and video lists. As an example, assuming the search keyword includes "xx event", the target information that is hit could include a list of posts about "xx event", a list of users who have given feedback on "xx event", a list of groups that have discussed "xx event", a list of pages related to "xx event", a list of activities related to "xx event", a list of pictures and videos related to "xx event", etc.

[0030] Step 120: Based on the pre-set correspondence between different information types and data collection entry mining strategies, and the information type of the target information, determine the data collection entry mining strategy that matches the information type of the target information.

[0031] Optionally, to improve the efficiency of mining social media accounts associated with target information, a pre-set correspondence between different information types and data collection entry mining strategies can be established. After determining the type of target information, information mining can be performed directly based on the data collection entry mining strategy corresponding to the type of target information. Specifically, based on the pre-set correspondence between different information types and data collection entry mining strategies, and the information type of the target information, a data collection entry mining strategy matching the information type of the target information is determined, including:

[0032] The information type of the target information is determined, which includes information types used to characterize the public opinion information and information types used to characterize social information associated with the public opinion information; wherein, the pre-set correspondence between different information types and collection entry mining strategies includes: the correspondence between information types used to characterize public opinion information and content collection entry mining strategies, and the correspondence between information types used to characterize social information associated with public opinion information and account collection entry mining strategies.

[0033] If the information type of the target information is the information type used to represent public opinion information, then according to the pre-set correspondence between different information types and the collection entry mining strategy, the collection entry mining strategy that matches the information type of the target information is determined as the content collection entry mining strategy.

[0034] If the target information is a type of social information used to represent information related to public opinion, then based on the pre-set correspondence between different information types and data collection entry mining strategies, the data collection entry mining strategy that matches the target information is determined to be the account data collection entry mining strategy.

[0035] like Figure 2 The diagram illustrates the correspondence between different information types and data collection entry point mining strategies in the method for determining public opinion information collection entry points provided in an exemplary embodiment of this application. The specified search categories can be broadly divided into two categories: Category 1, an account list, and Category 2, a list of posts / pages, videos / images, and groups / activities. Mining for Category 1 can be termed an account mining task, which can employ an account data collection entry point mining strategy. Mining for Category 2 can be termed a content mining task, which can employ a content data collection entry point mining strategy.

[0036] Step 130: Use the data collection entry mining strategy to mine the target information to obtain social media accounts associated with the target information, which will serve as the data collection entry points for public opinion information.

[0037] Optionally, when the target information is public opinion information, in order to fully explore the social media accounts associated with the public opinion information, a content collection entry mining strategy can be first applied to the target information, and then the mined social media account information can be further mined using an account collection entry mining strategy. Specifically, the collection entry mining strategy is used to mine the target information to obtain social media accounts associated with the target information, which serve as the public opinion information collection entry points, including:

[0038] If the target information is of the type used to represent public opinion information, then a content collection entry mining strategy is adopted to mine the account-related information of the user who published the target information and the publishing address of the target information. The account-related information includes the user name, user homepage link, user avatar link and user identifier.

[0039] Based on the publishing address of the target information, a content collection entry mining strategy is adopted to mine account-related information of users who interact with the target information.

[0040] Based on the account information of the users who published and interacted with the target information, identify the account information of related users who have social relationships with the users who published and interacted with the target information;

[0041] The account information of the users who publish and interact with the target information, as well as the account information of related users who have social relationships with the users who publish and interact with the target information, will be used as the entry point for collecting public opinion information.

[0042] In one example, the information types used to characterize public opinion information may include lists of posts / pages, lists of videos / images, and lists of groups / activities displaying public opinion information. Figure 2 In Category 2, for the list of posts / pages, you can directly search for posts / pages containing the search keywords. Based on this list, you can obtain the poster's / page publisher's name, homepage link, and avatar information. Then, you can browse the comment list, repost list, and like list related to the post / page. Based on the comment list, repost list, and like list, you can obtain the social media account names, social media homepage links, and social media avatar information of the users publicly disclosed in the comment list, repost list, and like list. Finally, you can further mine the user follower list and user following list of the obtained user social media accounts to obtain more social media account information such as user social media account names, social media homepage links, and social media avatar information.

[0043] For Category 2, the video / image list, the search keywords can be used to directly retrieve the searched video / image list. From this list, further analysis can be conducted on comments, shares, and likes. Based on these, the social media account names, social media homepage links, and social media profile pictures of the users in these lists can be obtained. Finally, further analysis of the user follower and following lists of these users can yield more information about their social media accounts, including their names, homepage links, and profile pictures. Similarly, for Category 2, the group / activity list, the search keywords can be used to retrieve the searched groups and activities. Some groups / activities can be joined, while others can be viewed directly. By collecting posts and related comments, likes, and shares from these groups and activities, information about the users' social media accounts can be obtained. Finally, further analysis of the user follower and following lists can yield more information about their social media accounts, including their names, homepage links, and profile pictures.

[0044] Optionally, when the target information is social information related to public opinion information, in order to fully explore the social media accounts associated with this social information, the minable social media account information can be further mined using an account collection entry mining strategy. Specifically, an entry mining strategy is used to mine the target information to obtain social media accounts associated with the target information, which serve as entry points for public opinion information collection, including:

[0045] If the target information is social information used to characterize the association of public opinion information, then an account collection entry mining strategy is adopted to mine the account-related information of users associated with the target information.

[0046] Based on the account information of the users associated with the target information, identify the account information of related users who have social relationships with the users associated with the target information;

[0047] The account information of users associated with the target information, as well as the account information of related users who have social relationships with the users associated with the target information, are used as the entry point for collecting public opinion information.

[0048] In one example, the information type used to characterize the social information associated with public opinion information may include an account list, in which the social media accounts are user social media accounts that participated in the discussion and dissemination of public opinion information related to the search keywords. For the account list in category 1, the user social media accounts that participated in the discussion and dissemination of public opinion information related to the search keywords can be directly obtained based on the search keywords. Then, the user follower list and user following list of these user social media accounts can be further mined to obtain more social media account information such as user social media account names, social media homepage links, and social media profile picture information.

[0049] in, Figure 2 The content mining task, as shown, after uncovering information about the social media accounts of users who shared, commented, and liked posts, then activates an account mining task to further mine the follower lists and following lists of each user's social media account, until the number of mined social media accounts meets the mining requirements. Clearly, by continuously accumulating the mined social media accounts using this method, the monitoring coverage of public opinion information related to search keywords can be effectively improved.

[0050] Optionally, after obtaining the social media accounts associated with the target information, to reduce the workload of the public opinion information collection program and avoid duplicate information collection from the same social media account, this embodiment of the application can perform deduplication processing on these account information after obtaining the social media accounts associated with the target information. Specifically, after using a collection entry point mining strategy to mine the target information to obtain the social media accounts associated with the target information as the public opinion information collection entry point, the method further includes:

[0051] Store the public opinion information collection portal in the social media account database;

[0052] Based on social media platforms, social media account identifiers, and social media account homepage links, the account information in the social media account database is deduplicated to obtain a deduplicated social media account database.

[0053] As an example, after information enters the account database, incremental account database information can be read and transferred to the social media account database through scheduled task control. Deduplication is performed using a combination of social media platform, social media account identifier, and social media account homepage link. For example, deduplication can be performed based on Redis components combined with Bloom filter algorithm before being stored in the social media account database for use by public opinion information collection programs.

[0054] Optionally, after obtaining the deduplicated social media account database, in order to avoid some accounts being canceled or having their account information changed, causing the public opinion information collection program to fail to collect information multiple times, this application embodiment can also call the account collection program to collect information based on the account information in the social media account database, so as to determine the invalid account information in the social media account database;

[0055] Remove invalid account information from the deduplicated social media account database to obtain a usable social media account database;

[0056] The public opinion information collection program is invoked to collect public opinion information based on the available social media account database.

[0057] As an example, it can be combined with an account collection program to periodically identify tasks that fail to collect and parse data. If the access still fails after multiple retries, it can be automatically marked in the user database to avoid the public opinion information collection program wasting request resources.

[0058] Figure 3 A flowchart illustrating the method for determining the public opinion information collection entry point provided in the exemplary embodiments of this application, applied in a real-world scenario, may include:

[0059] S31, Enter search criteria, including search keywords and search categories.

[0060] S32, Obtain target information in social media based on search criteria.

[0061] S33, determine whether the target information is a type of public opinion information.

[0062] If the target information is of the public opinion information type, then execute S34; otherwise, execute S35.

[0063] S34. A content collection entry mining strategy is used to mine the target information to obtain the account information of the user who published the target information and the account information of the user who interacted with the target information.

[0064] Specifically, for post and page lists, the poster's name, homepage link, avatar link, and user identifier are directly stored in the account mining task library, while the relevant main post URLs are stored in the content mining task library. For group and activity lists, the post links from groups and activities are stored in the content mining task library. For image and video lists, the collected main post URLs need to be stored in the content mining task library. The information stored in this content mining task library can be summarized as account-related information of the user who published the target information and account-related information of the user who interacted with the target information.

[0065] S35 employs an account collection entry mining strategy to mine account-related information of users who publish target information and account-related information of users who interact with target information.

[0066] Specifically, for user lists, user names, homepage links, avatar links, and user identifiers can be directly stored in the account mining task library. Then, by expanding the account's relationship list through pagination, further data can be collected to uncover the public avatars, names, homepage links, etc., of the accounts followed and followed by each account in the account mining task library. These further discovered social media accounts are then stored in a social media account library. Using this method, a social media account library for a specific search criterion can ultimately be formed.

[0067] S36 performs deduplication on the discovered account-related information.

[0068] S37, periodically call the account collection program to collect information based on the account information in the social media account database, in order to remove invalid account information and obtain a usable social media account database.

[0069] S38, invoke the public opinion information collection program to collect public opinion information based on the available social media account database.

[0070] In this embodiment, since it is possible to obtain target information such as public opinion information and / or social information associated with public opinion information in social media based on search conditions, and then determine the collection entry mining strategy that matches the information type of the target information according to the pre-set correspondence between different information types and collection entry mining strategies, this allows for the use of collection entry mining strategies that match the real-time hit public opinion information and / or social information associated with public opinion information, regardless of changes in social media accounts. Information mining is then performed on the hit public opinion information and / or social information associated with public opinion information to obtain social media accounts associated with the hit target information, serving as the public opinion information collection entry point and enabling the sustainable collection of public opinion information from social media accounts. Furthermore, after hitting the public opinion information and / or social information associated with public opinion information, this solution further mines the associated accounts based on the hit information, which can increase the number of accounts covered by the hit public opinion information and / or social information associated with public opinion information.

[0071] It should be noted that the execution subject of each step of the method provided in the above embodiments can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 110 to 130 can be device A; or the execution subject of steps 110 to 120 can be device A, and the execution subject of step 130 can be device B; and so on.

[0072] Furthermore, some processes described in the above embodiments and accompanying drawings include multiple operations that appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or they may be executed in parallel. The operation numbers, such as 110, 120, etc., are merely used to distinguish different operations and do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel.

[0073] Figure 4 This is a schematic diagram of a device for determining a public opinion information collection entry point, provided as an exemplary embodiment of this application. Figure 4 As shown, the device 400 includes: an information acquisition module 410, a strategy determination module 420, and an information mining module 430, wherein:

[0074] The information acquisition module 410 is used to acquire target information that is hit in social media based on search conditions; the target information includes: public opinion information and / or social information associated with the public opinion information;

[0075] The strategy determination module 420 is used to determine the acquisition entry mining strategy that matches the information type of the target information based on the pre-set correspondence between different information types and acquisition entry mining strategies, as well as the information type of the target information.

[0076] The information mining module 430 is used to perform information mining on the target information using the collection entry mining strategy to obtain social media accounts associated with the target information, which serve as the entry point for collecting public opinion information.

[0077] Optionally, when the information acquisition module 410 acquires target information matched in social media based on search criteria, it is specifically used for:

[0078] Obtain search criteria, which include at least one search keyword and a specified search category, wherein the search category includes at least one of the following: post list, user list, group list, page list, activity list, image list, and video list;

[0079] Obtain target information that matches at least one search keyword in the search criteria within a specified search category on social media.

[0080] Optionally, when the strategy determination module 420 determines the acquisition entry mining strategy that matches the information type of the target information based on the pre-set correspondence between different information types and acquisition entry mining strategies, and the information type of the target information, it is specifically used for:

[0081] The information type of the target information is determined, including information types used to characterize the public opinion information and information types used to characterize social information associated with the public opinion information; wherein, the pre-set correspondence between different information types and data collection entry mining strategies includes: the correspondence between information types used to characterize the public opinion information and content data collection entry mining strategies, and the correspondence between information types used to characterize social information associated with the public opinion information and account data collection entry mining strategies;

[0082] If the information type of the target information is an information type used to characterize the public opinion information, then according to the pre-set correspondence between different information types and the collection entry mining strategy, the collection entry mining strategy that matches the information type of the target information is determined as the content collection entry mining strategy.

[0083] If the information type of the target information is a social information type used to characterize the public opinion information, then according to the pre-set correspondence between different information types and collection entry mining strategies, the collection entry mining strategy that matches the information type of the target information is determined to be the account collection entry mining strategy.

[0084] Optionally, the information mining module 430 uses the acquisition entry mining strategy to perform information mining on the target information to obtain social media accounts associated with the target information. When used as an entry point for collecting public opinion information, it is specifically used for:

[0085] If the information type of the target information is the information type used to characterize the public opinion information, then a content collection entry mining strategy is adopted to mine the account-related information of the user who published the target information and the publishing address of the target information. The account-related information includes user name, user homepage link, user avatar link and user identifier.

[0086] Based on the publishing address of the target information, a content collection entry mining strategy is adopted to mine the account-related information of the users who interacted with the target information.

[0087] Based on the account information of the users who published and interacted with the target information, the account information of associated users who have social relationships with the users who published and interacted with the target information is determined.

[0088] The account information of the users who published the target information and the users who interacted with it, as well as the account information of related users who have social relationships with the users who published the target information and the users who interacted with it, are used as the entry point for collecting public opinion information.

[0089] Optionally, the information mining module 430 uses the acquisition entry mining strategy to perform information mining on the target information to obtain social media accounts associated with the target information. When used as an entry point for collecting public opinion information, it is specifically used for:

[0090] If the information type of the target information is social information used to characterize the association of the public opinion information, then an account collection entry mining strategy is adopted to mine the account-related information of the users associated with the target information.

[0091] Based on the account information of the users associated with the target information, determine the account information of related users who have social relationships with the users associated with the target information;

[0092] The account information of users associated with the target information, as well as the account information of related users who have social relationships with the users associated with the target information, are used as the entry point for collecting public opinion information.

[0093] Optionally, the device further includes an account deduplication module, used for:

[0094] The aforementioned public opinion information collection portal is stored in a social media account database;

[0095] Based on social media platforms, social media account identifiers, and social media account homepage links, the account information in the social media account database is deduplicated to obtain a deduplicated social media account database.

[0096] Optionally, the device further includes a public opinion collection module, used for:

[0097] The account collection program is invoked to collect information based on the account information in the social media account database in order to identify invalid account information in the social media account database.

[0098] The invalid account information is removed from the deduplicated social media account database to obtain a usable social media account database;

[0099] The public opinion information collection program is invoked to collect public opinion information based on the available social media account database.

[0100] The device 400 for determining the entry point for public opinion information collection can achieve... Figures 1-2 For details of the method implementation examples, please refer to [link / reference]. Figures 1-2 The method for determining the public opinion information collection entry point in the illustrated embodiment will not be described again.

[0101] Figure 5 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application. For example... Figure 5 As shown, the device includes a memory 51 and a processor 52.

[0102] Memory 51 is used to store computer programs and can be configured to store various other data to support operation on the computing device. Examples of this data include instructions for any application or method used to operate on the computing device, contact data, phone book data, messages, pictures, videos, etc.

[0103] Processor 52, coupled to memory 51, is used to execute computer programs in memory 51 for: acquiring target information hit in social media based on search criteria; the target information includes: public opinion information and / or social information associated with the public opinion information; determining a collection entry mining strategy that matches the information type of the target information according to a pre-set correspondence between different information types and collection entry mining strategies, and the information type of the target information; and using the collection entry mining strategy to perform information mining on the target information to obtain social media accounts associated with the target information as public opinion information collection entry points.

[0104] The electronic device provided in this application can acquire target information such as public opinion information and / or social information associated with public opinion information in social media based on search conditions. Then, according to the pre-set correspondence between different information types and data collection entry mining strategies, and the information type of the target information, it determines a data collection entry mining strategy that matches the information type of the target information. Thus, regardless of changes in social media accounts, it can use a data collection entry mining strategy that matches the real-time hit public opinion information and / or social information associated with it to mine the hit public opinion information and / or social information associated with it, thereby obtaining social media accounts associated with the hit target information as public opinion information collection entry points, achieving sustainable collection of public opinion information from social media accounts. Furthermore, after hitting the public opinion information and / or social information associated with it, this solution further mines the associated accounts based on the hit information, which can increase the number of accounts covered by the hit public opinion information and / or social information associated with it.

[0105] Furthermore, such as Figure 5 As shown, the electronic device also includes other components such as a communication component 53, a display 54, a power supply component 55, and an audio component 56. Figure 5 The diagram only shows some components and does not mean that the electronic device includes only these components. Figure 5 The components shown. Additionally, depending on the implementation of the traffic playback device, Figure 5 The components within the dashed box are optional, not mandatory. For example, when an electronic device is implemented as a terminal device such as a smartphone, tablet, or desktop computer, it may include... Figure 5 The components within the dashed box; when the electronic device is implemented as a server-side device such as a conventional server, cloud server, data center, or server array, it may be excluded. Figure 5 The component within the dashed box.

[0106] Accordingly, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to implement the steps in the above-described method for determining the public opinion information collection entry point.

[0107] Accordingly, this application also provides a computer program product, including a computer program / instructions, which, when executed, can implement the steps that can be executed by an electronic device in the above-described processing method embodiment of the design drawing. Optionally, this computer program product, in addition to executing the steps in the above-described method for determining the public opinion information collection entry point, can also perform other steps.

[0108] The above Figure 5The communication component is configured to facilitate wired or wireless communication between the device containing the communication component and other devices. The device containing the communication component can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, the communication component receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component may further include a Near Field Communication (NFC) module, Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, etc.

[0109] The above Figure 5 The memory in the memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0110] The above Figure 5 The display includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of the touch or swipe action, but also the duration and pressure associated with the touch or swipe operation.

[0111] The above Figure 5 The power supply component provides power to the various components of the device in which it resides. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which it resides.

[0112] The above Figure 5 The audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC) configured to receive external audio signals when the device containing the audio component is in an operating mode, such as call mode, recording mode, or voice recognition mode. The received audio signals can be further stored in memory or transmitted via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0113] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0115] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0118] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0119] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0120] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0122] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining the entry point for collecting public opinion information, characterized in that, include: Obtain target information based on search criteria in social media; The target information includes: public opinion information and / or social information associated with the public opinion information; Based on the pre-set correspondence between different information types and data collection entry mining strategies, and the information type of the target information, determine the data collection entry mining strategy that matches the information type of the target information; The aforementioned data collection entry mining strategy is used to mine the target information to obtain social media accounts associated with the target information, which serve as data collection entry points for public opinion information. The step of determining the acquisition entry mining strategy that matches the information type of the target information based on the pre-set correspondence between different information types and acquisition entry mining strategies, and the information type of the target information, includes: The information type of the target information is determined, including information types used to characterize the public opinion information and information types used to characterize social information associated with the public opinion information; wherein, the pre-set correspondence between different information types and data collection entry mining strategies includes: the correspondence between information types used to characterize the public opinion information and content data collection entry mining strategies, and the correspondence between information types used to characterize social information associated with the public opinion information and account data collection entry mining strategies; If the information type of the target information is an information type used to characterize the public opinion information, then according to the pre-set correspondence between different information types and the collection entry mining strategy, the collection entry mining strategy that matches the information type of the target information is determined as the content collection entry mining strategy. If the information type of the target information is a social information type used to characterize the public opinion information, then according to the pre-set correspondence between different information types and collection entry mining strategies, the collection entry mining strategy that matches the information type of the target information is determined to be the account collection entry mining strategy.

2. The method as described in claim 1, characterized in that, The process of using the aforementioned data collection entry mining strategy to mine the target information to obtain social media accounts associated with the target information, serving as data collection entry points for public opinion information, includes: If the information type of the target information is the information type used to characterize the public opinion information, then a content collection entry mining strategy is adopted to mine the account-related information of the user who published the target information and the publishing address of the target information. The account-related information includes user name, user homepage link, user avatar link and user identifier. Based on the publishing address of the target information, a content collection entry mining strategy is adopted to mine the account-related information of the users who interacted with the target information. Based on the account information of the users who published and interacted with the target information, the account information of associated users who have social relationships with the users who published and interacted with the target information is determined. The account information of the users who published the target information and the users who interacted with it, as well as the account information of related users who have social relationships with the users who published the target information and the users who interacted with it, are used as the entry point for collecting public opinion information.

3. The method as described in claim 1, characterized in that, The aforementioned data collection entry point mining strategy is used to mine information from the target information to obtain social media accounts associated with the target information, which serve as entry points for collecting public opinion information, including: If the information type of the target information is social information used to characterize the association of the public opinion information, then an account collection entry mining strategy is adopted to mine the account-related information of the users associated with the target information. Based on the account information of the users associated with the target information, determine the account information of related users who have social relationships with the users associated with the target information; The account information of users associated with the target information, as well as the account information of related users who have social relationships with the users associated with the target information, are used as the entry point for collecting public opinion information.

4. The method as described in claim 1, characterized in that, The acquisition of target information in social media based on search criteria includes: Obtain search criteria, which include at least one search keyword and a search category, wherein the search category includes at least one of the following: post list, user list, group list, page list, activity list, image list, and video list; Obtain target information that matches at least one search keyword in the search criteria within a specified search category on social media.

5. The method according to any one of claims 1 to 4, characterized in that, After employing the aforementioned data collection entry mining strategy to perform information mining on the target information to obtain social media accounts associated with the target information, which serve as data collection entry points for public opinion information, the method further includes: The aforementioned public opinion information collection portal is stored in a social media account database; Based on social media platforms, social media account identifiers, and social media account homepage links, the account information in the social media account database is deduplicated to obtain a deduplicated social media account database.

6. The method as described in claim 5, characterized in that, The method further includes: The account collection program is invoked to collect information based on the account information in the social media account database in order to identify invalid account information in the social media account database. The invalid account information is removed from the deduplicated social media account database to obtain a usable social media account database; The public opinion information collection program is invoked to collect public opinion information based on the available social media account database.

7. A device for determining the entry point for collecting public opinion information, characterized in that, include: The information acquisition module is used to acquire target information found in social media based on search criteria; The target information includes: public opinion information and / or social information associated with the public opinion information; The strategy determination module is used to determine the acquisition entry mining strategy that matches the information type of the target information based on the pre-set correspondence between different information types and acquisition entry mining strategies, as well as the information type of the target information. The information mining module is used to perform information mining on the target information using the collection entry mining strategy, so as to obtain social media accounts associated with the target information as the entry point for collecting public opinion information; Specifically, when the strategy determination module determines the acquisition entry mining strategy that matches the information type of the target information based on the pre-set correspondence between different information types and acquisition entry mining strategies, and the information type of the target information, it is used for: The information type of the target information is determined, including information types used to characterize the public opinion information and information types used to characterize social information associated with the public opinion information; wherein, the pre-set correspondence between different information types and data collection entry mining strategies includes: the correspondence between information types used to characterize the public opinion information and content data collection entry mining strategies, and the correspondence between information types used to characterize social information associated with the public opinion information and account data collection entry mining strategies; If the information type of the target information is an information type used to characterize the public opinion information, then according to the pre-set correspondence between different information types and the collection entry mining strategy, the collection entry mining strategy that matches the information type of the target information is determined as the content collection entry mining strategy. If the information type of the target information is a social information type used to characterize the public opinion information, then according to the pre-set correspondence between different information types and collection entry mining strategies, the collection entry mining strategy that matches the information type of the target information is determined to be the account collection entry mining strategy.

8. An electronic device, characterized in that, include: Memory and processor; The memory is used to store computer programs; The processor, coupled to the memory, is used to execute the computer program for implementing the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it causes the processor to perform the steps of the method according to any one of claims 1 to 6.

Images