阅读说明：本技术 一种信息提取方法、装置、设备、及介质 (Information extraction method, device, equipment and medium ) 是由 丁超 张晓晴 蒲伟 陈天明 李硕 于 2021-08-31 设计创作，主要内容包括：本公开提供了一种信息提取方法、装置、设备、及介质,涉及计算机技术领域,尤其涉及云计算技术领域,包括：获取与信息提取需求相对应的目标任务,目标任务用于提取目标移动应用中至少一项公开信息；目标任务中包括用户操作行为模拟指令序列；将目标任务调度至安装目标移动应用的目标云设备中,并触发目标云设备在目标移动应用内执行目标任务中的各用户操作行为模拟指令；实时根据目标移动应用针对各用户操作行为模拟指令触发生成的应用内展示信息,获取与信息提取需求匹配的公开信息提取结果。本公开实施例的技术方案可以实现对富媒体信息的监管处理,为用户针对移动应用提供有效的信息服务。(The present disclosure provides an information extraction method, apparatus, device, and medium, which relate to the field of computer technology, in particular to the field of cloud computing technology, and include: acquiring a target task corresponding to an information extraction requirement, wherein the target task is used for extracting at least one item of public information in a target mobile application; the target task comprises a user operation behavior simulation instruction sequence; scheduling the target task to target cloud equipment for installing the target mobile application, and triggering the target cloud equipment to execute each user operation behavior simulation instruction in the target task in the target mobile application; and acquiring a public information extraction result matched with the information extraction requirement according to the in-application display information generated by the target mobile application aiming at the user operation behavior simulation instruction in real time. The technical scheme of the embodiment of the disclosure can realize supervision processing of rich media information and provide effective information service for users aiming at mobile application.)

1. An information extraction method, wherein the method comprises:

acquiring a target task corresponding to an information extraction requirement, wherein the target task is used for extracting at least one item of public information in a target mobile application; the target task comprises a user operation behavior simulation instruction sequence;

scheduling the target task to target cloud equipment for installing the target mobile application, and triggering the target cloud equipment to execute each user operation behavior simulation instruction in the target task in the target mobile application;

and acquiring a public information extraction result matched with the information extraction requirement according to the in-application display information generated by the target mobile application aiming at the user operation behavior simulation instruction in real time.

2. The method of claim 1, wherein scheduling a target task into a target cloud device that installs a target mobile application comprises:

acquiring all alternative cloud equipment for installing the target mobile application in a cloud service platform;

judging whether the target task needs to be executed after logging in the target mobile application by using an account;

if yes, detecting the quantity value of a target account used in the historical execution task of each alternative cloud device, wherein the target account is used for logging in the target mobile application; selecting target cloud equipment from the candidate cloud equipment of which the quantity value of the target account is smaller than or equal to a preset quantity threshold, and scheduling a target task to the target cloud equipment.

3. The method of claim 1, further comprising:

acquiring at least one real person operation simulation instruction in a real person operation simulation instruction library;

and dynamically adding each real person operation simulation instruction into a user operation behavior simulation instruction sequence corresponding to the target task.

4. The method of claim 1, further comprising:

according to the information type of each public information included in the public information extraction result, performing information processing and/or information summarization on each public information to obtain a processing summarization result;

and displaying the processing and summarizing result in a visual and/or data report form mode.

5. The method of claim 1, further comprising:

acquiring a plurality of pieces of in-application display information extracted aiming at different tasks;

and analyzing the video content and/or text content included in the display information in each application by using at least one public opinion monitoring service to obtain public opinion monitoring results respectively corresponding to each public opinion monitoring service.

6. The method of claim 5, wherein the public opinion monitoring service comprises at least one of:

video content identification, image detection of a target attention object, text detection of a target keyword, trend analysis of a set event, character relation combing, comment analysis and evidence collection.

7. An information extraction apparatus, the apparatus comprising:

the task acquisition module is used for acquiring a target task corresponding to the information extraction requirement, and the target task is used for extracting at least one item of public information in the target mobile application; the target task comprises a user operation behavior simulation instruction sequence;

the task scheduling module is used for scheduling the target task to target cloud equipment provided with the target mobile application and triggering the target cloud equipment to execute each user operation behavior simulation instruction in the target task in the target mobile application;

and the result acquisition module is used for acquiring a public information extraction result matched with the information extraction requirement according to the in-application display information generated by the target mobile application aiming at the simulation instruction of the operation behavior of each user in real time.

8. The apparatus of claim 7, wherein the task scheduling module further comprises:

the cloud equipment acquisition unit is used for acquiring all alternative cloud equipment for installing the target mobile application in a cloud service platform;

the task judging unit is used for judging whether the target task needs to be executed after logging in the target mobile application by using the account;

the quantity detection unit is used for detecting the quantity value of a target account used in the historical execution task of each alternative cloud device when the target task needs to be executed after logging in the target mobile application by using the account, and the target account is used for logging in the target mobile application;

and the device selecting unit is used for selecting target cloud devices from the candidate cloud devices of which the number value of the target account is smaller than or equal to a preset number threshold, and scheduling the target tasks to the target cloud devices.

9. The apparatus of claim 7, wherein the task acquisition module further comprises:

the simulation instruction acquisition unit is used for acquiring at least one real person operation simulation instruction in a real person operation simulation instruction library;

and the simulation instruction adding unit is used for dynamically adding each real person operation simulation instruction into the user operation behavior simulation instruction sequence corresponding to the target task.

10. The apparatus of claim 7, wherein the apparatus further comprises:

the information processing module is used for carrying out information processing and/or information summarization on each public information according to the information type of each public information included in the public information extraction result to obtain a processing and summarizing result;

and the result display module is used for displaying the processing and summarizing results in a visual and/or data report form mode.

11. The apparatus of claim 7, wherein the apparatus further comprises:

the information acquisition module is used for acquiring a plurality of pieces of in-application display information extracted aiming at different tasks;

and the monitoring module is used for analyzing and processing video content and/or text content included in the display information in each application by using at least one public opinion monitoring service to obtain public opinion monitoring results respectively corresponding to each public opinion monitoring service.

12. The apparatus of claim 11, wherein the public opinion monitoring service comprises at least one of: video content identification, image detection of a target attention object, text detection of a target keyword, trend analysis of a set event, character relation combing, comment analysis and evidence collection.

13. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-6.

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for extracting information.

Background

Currently, mobile devices (such as mobile phones, tablet computers, etc.) have become a main mode of social information production, browsing, interaction and propagation, and Application programs (APPs) in mobile ecology form information islands respectively; meanwhile, with the advent of the fifth Generation Mobile Communication Technology (5th Generation Mobile Communication Technology, 5G), the information sources, information forms, and information levels in the Mobile internet have changed dramatically. Pictures, text and link information in traditional web pages are beginning to be transformed into rich media information, such as video, audio and live information. The social activities of users are greatly transferred to the online, and typically, rich media information with information such as short video live broadcast as the leading is rapidly spread.

However, the related art has the following drawbacks: real-time supervision on mobile internet information (especially rich media information which is rapidly spread) is just needed, but because the existing information supervision technology still takes webpage information or picture and text link information as the main part, and the supervision on the mobile rich media information is almost blank, the traditional supervision system cannot effectively support the security supervision on the whole network information.

Disclosure of Invention

The present disclosure provides an information extraction method, apparatus, device, and medium.

According to an aspect of the present disclosure, there is provided an information extraction method, the method including:

acquiring a target task corresponding to an information extraction requirement, wherein the target task is used for extracting at least one item of public information in a target mobile application; the target task comprises a user operation behavior simulation instruction sequence;

scheduling the target task to target cloud equipment for installing the target mobile application, and triggering the target cloud equipment to execute each user operation behavior simulation instruction in the target task in the target mobile application;

and acquiring a public information extraction result matched with the information extraction requirement according to the in-application display information generated by the target mobile application aiming at the user operation behavior simulation instruction in real time.

According to another aspect of the present disclosure, there is provided an information extraction apparatus, the apparatus including:

the task acquisition module is used for acquiring a target task corresponding to the information extraction requirement, and the target task is used for extracting at least one item of public information in the target mobile application; the target task comprises a user operation behavior simulation instruction sequence;

the task scheduling module is used for scheduling the target task to target cloud equipment provided with the target mobile application and triggering the target cloud equipment to execute each user operation behavior simulation instruction in the target task in the target mobile application;

and the result acquisition module is used for acquiring a public information extraction result matched with the information extraction requirement according to the in-application display information generated by the target mobile application aiming at the simulation instruction of the operation behavior of each user in real time.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to cause the at least one processor to perform a method according to any one of the embodiments of the disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of any of the embodiments of the present disclosure.

The technical scheme of the embodiment of the disclosure can realize supervision processing of rich media information and provide effective information service for users aiming at mobile application.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

FIG. 1 is a schematic flow chart diagram of a method of information extraction according to an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart diagram of yet another information extraction method according to an embodiment of the present disclosure;

FIG. 3 is a schematic flow chart diagram of yet another information extraction method according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an information extraction apparatus according to an embodiment of the present disclosure;

fig. 5 is a block diagram of an electronic device of an information extraction method according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a flowchart of an information extraction method according to an embodiment of the present disclosure, where the present embodiment is suitable for a situation where public information in a mobile application is extracted, and the method may be performed by an information extraction device, and the device may be implemented by software and/or hardware, and may be generally integrated in a terminal or a server having a data processing function. Specifically, referring to fig. 1, the method specifically includes the following steps:

step 110, acquiring a target task corresponding to an information extraction requirement, wherein the target task is used for extracting at least one item of public information in a target mobile application; the target task comprises a user operation behavior simulation instruction sequence.

In this embodiment, a user may input an information extraction requirement through a cloud service platform, where the information extraction requirement may include a target mobile application and an information tag of public information that the user wants to extract from the target mobile application.

In a specific embodiment, assuming that a user wants to collect all the praise amounts of content published by the user in a certain content publishing platform, the content publishing platform may be selected in the cloud service platform, and "all the praise amounts of content published by the user" may be selected in an option of an information tag provided by the cloud service platform. After detecting that the user selects the content publishing platform, the content publishing platform may be used as a target mobile application, and "the total praise number of the content published by the user" may be used as an information tag of the public information extracted from the target mobile application.

In this step, after receiving an information extraction requirement input by a user, a target task corresponding to the information extraction requirement may be obtained according to a target mobile application specified in the information extraction requirement and an information tag. The target task comprises a user operation behavior simulation instruction sequence formed by a plurality of user operation behavior simulation instructions. The user operation behavior simulation instruction sequence may be a simulation instruction corresponding to the actual operation behavior of the user. The actual operation behavior of the user can be understood as a behavior which needs to be actually operated in the target mobile application when the user realizes the information extraction requirement.

In this embodiment, optionally, the target task may be screened from the pre-stored extraction tasks corresponding to the multiple mobile applications according to the target mobile application and the information tag. Each extraction task comprises a corresponding mobile application and an information tag. The plurality of extraction tasks can be pre-constructed by developers for different mobile applications and different information labels.

In a specific embodiment, it is assumed that a target mobile application specified in an information extraction requirement is a certain content publishing platform, an information tag is "total praise amount of content published by a user", and a target task corresponding to the information extraction requirement may include user operation behavior simulation instructions such as "clicking a user personal home page in the content publishing platform", "clicking all content published by the user", and a plurality of user operation behavior simulation instructions jointly form a user operation behavior simulation instruction sequence.

And step 120, scheduling the target task to target cloud equipment for installing the target mobile application, and triggering the target cloud equipment to execute each user operation behavior simulation instruction in the target task in the target mobile application.

In this embodiment, optionally, a cloud device whose working state is an idle state may be selected from a plurality of cloud devices in which the target mobile application is installed as the target cloud device, and the target task is scheduled to the target cloud device. Optionally, after the target task is scheduled to the target cloud device, a task execution instruction may be sent to the target cloud device, so that after the target cloud device receives the task execution instruction, each user operation behavior simulation instruction in the target task is executed in the target mobile application.

And step 130, acquiring a public information extraction result matched with the information extraction requirement according to the in-application display information generated by the target mobile application aiming at the user operation behavior simulation instruction in real time.

In this embodiment, after the target cloud device executes each user operation behavior simulation instruction in the target mobile application, the display information in the target mobile application page may be fed back to the cloud service platform, and the cloud service platform may obtain or generate the public information extraction result matched with the information extraction requirement according to the display information in the target mobile application page.

In a specific embodiment, it is assumed that the target mobile application specified in the information extraction requirement is a certain content publishing platform, the information tag is "total praise number of content published by the user", and after the target cloud device executes each user operation behavior simulation instruction in the content publishing platform, the display information in the content publishing platform page may include the praise number corresponding to each piece of published content of the user. After the cloud service platform obtains the praise number corresponding to each piece of release content, the praise numbers corresponding to each piece of release content can be superposed to obtain a public information extraction result matched with the information extraction requirement.

In another specific embodiment, it is assumed that the target mobile application specified in the information extraction requirement is a certain video playing platform, the information tag is "a concert held by a certain singer at a certain place", and after the target cloud device executes each user operation behavior simulation instruction in the video playing platform, the display information in the page of the video playing platform may include all the concert videos held by the singer. After the cloud service platform acquires the display information, all concert videos can be screened according to the appointed place in the information tag, and a public information extraction result matched with the information extraction requirement is obtained.

In this embodiment, after the public information extraction result matching the information extraction requirement is obtained, the monitoring personnel can monitor the information in the mobile application according to the public information extraction result. On one hand, the embodiment can realize the supervision processing of the rich media information; on the other hand, when the user has the requirement of analyzing and processing the public information in the mobile application, the effective information service can be provided for the user.

According to the technical scheme of the embodiment, the target task corresponding to the information extraction requirement is obtained, the target task is dispatched to the target cloud equipment provided with the target mobile application, the target cloud equipment is triggered to execute each user operation behavior simulation instruction in the target task in the target mobile application, the generated in-application display information is triggered according to the target mobile application aiming at each user operation behavior simulation instruction in real time, and the public information extraction result matched with the information extraction requirement is obtained.

Fig. 2 is a schematic flow chart of another information extraction method according to an embodiment of the present disclosure, which is a further refinement of the foregoing technical solution, and the technical solution in this embodiment may be combined with one or more of the foregoing implementations. Specifically, referring to fig. 2, the method specifically includes the following steps:

step 210, obtaining a target task corresponding to an information extraction requirement, wherein the target task is used for extracting at least one item of public information in a target mobile application; the target task comprises a user operation behavior simulation instruction sequence.

And step 220, acquiring at least one real person operation simulation instruction from the real person operation simulation instruction library.

It can be understood that, in the actual operation process of the mobile application, in order to reduce the probability of occurrence of the risk event, the server of the mobile application will often set a corresponding wind control policy. For example, when the server detects that an operation behavior in the mobile application satisfies a certain rule, it considers that the operation behavior may be automatically executed by the machine, in which case, the server usually performs a forced shutdown process on the mobile application or performs a number sealing process on a current login account used by the mobile application.

In order to avoid that the target mobile application cannot normally run in the process that the target cloud device executes the target task in the target mobile application, the embodiment provides an implementation manner in which an irregular real-person operation simulation instruction is added to the target task, so that the operation executed by the target cloud device on the target mobile application is closer to the operation of a real person.

In this step, at least one real person operation simulation instruction may be acquired from a real person operation simulation instruction library established in advance, where the real person operation simulation instruction may be a simulation instruction corresponding to an operation behavior personalized by a user, and the personalized operation behavior may be an operation of irregularly sliding, browsing, or waiting an application page.

And step 230, dynamically adding each real person operation simulation instruction into a user operation behavior simulation instruction sequence corresponding to the target task.

In this step, optionally, each real-person operation simulation instruction may be added to one end of the user operation behavior simulation instruction sequence (for example, each real-person operation simulation instruction is added before or after all the user operation behavior simulation instructions), or each real-person operation simulation instruction may be randomly added between each user operation behavior simulation instruction.

Therefore, by acquiring the real-person operation simulation instruction and dynamically adding the real-person operation simulation instruction into the user operation behavior simulation instruction sequence corresponding to the target task, the execution process of the target cloud equipment on the target task can be closer to the execution process of the real user, and the situation that the target mobile application cannot normally run in the process that the target cloud equipment executes the target task in the target mobile application can be avoided.

And 240, scheduling the target task to target cloud equipment for installing the target mobile application, and triggering the target cloud equipment to execute each user operation behavior simulation instruction in the target task in the target mobile application.

In an implementation manner of this embodiment, scheduling a target task to a target cloud device that installs a target mobile application includes:

241, acquiring all alternative cloud equipment for installing the target mobile application in a cloud service platform;

step 242, judging whether the target task needs to be executed after logging in the target mobile application by using the account, if yes, executing step 243; if not, selecting cloud equipment with an idle working state from the plurality of cloud equipment provided with the target mobile application as target cloud equipment, and scheduling the target task to the target cloud equipment.

In this embodiment, optionally, whether the target task needs to be executed after logging in the target mobile application by using the account may be determined according to an information tag specified in the information extraction requirement. For example, assuming that the information tag specified in the information extraction requirement is associated with the user, it may be confirmed that the target task needs to be executed after logging in the target mobile application by using the account.

In a specific embodiment, it is assumed that the target mobile application specified in the information extraction requirement is a certain content publishing platform, and the information tag is "the total number of praise for the content published by the user", and since the information tag is associated with the user, the target task corresponding to the information extraction requirement can be confirmed, and needs to be executed after logging in the target mobile application by using an account.

In another specific embodiment, it is assumed that the target mobile application specified in the information extraction requirement is a certain video playing platform, and the information tag is "a concert video of a singer", and since the information tag is not associated with the user, the target task corresponding to the information extraction requirement can be confirmed, and the target mobile application is not required to be logged in by using an account and then executed.

Step 243, detecting the quantity value of a target account used in the historical execution task of each alternative cloud device, wherein the target account is used for logging in the target mobile application; selecting target cloud equipment from the candidate cloud equipment of which the quantity value of the target account is smaller than or equal to a preset quantity threshold, and scheduling a target task to the target cloud equipment.

It can be understood that, during the actual running process of the mobile application, the server of the mobile application often sets an upper limit value of the login account to reduce the occurrence of risk events. For example, when the server detects that the number of login accounts used by the mobile application is greater than the upper limit, the server typically performs a number sealing process on the current login account used by the mobile application.

In order to avoid that the target mobile application cannot normally operate in the process that the target cloud device executes the target task in the target mobile application, the embodiment provides that the cloud device with the smaller login account number value used by the target mobile application is selected from the plurality of cloud devices to serve as the target cloud device so as to ensure that the target mobile application normally operates.

In this step, a task may be executed according to the history of each candidate cloud device, the number value of the target account used by the target mobile application in each candidate cloud device is detected, then, in each candidate cloud device in which the number value of the target account is less than or equal to a preset number threshold, the candidate cloud device in the idle state is selected as the target cloud device, and the target task is scheduled to the target cloud device.

The method has the advantages that the situation that the current login account number used by the target mobile in the target cloud equipment is signed can be avoided, and therefore the normal operation of the target mobile application can be guaranteed.

And 250, acquiring a public information extraction result matched with the information extraction requirement according to the in-application display information generated by the target mobile application aiming at each user operation behavior simulation instruction in real time.

And step 260, performing information processing and/or information summarization on each public information according to the information type of each public information included in the public information extraction result to obtain a processing and summarizing result.

In this embodiment, after the public information extraction result matching the information extraction requirement is obtained, each piece of public information included in the public information extraction result may be processed according to a corresponding information type. The information type of each public information in the public information extraction result may include video, picture, document, and the like.

In a specific embodiment, assuming that the public information extraction result includes video information, the video information processing result may be obtained by performing sharpness processing or editing processing on each video included in the video information; if the public information extraction result includes the information of the picture class, each picture included in the information can be processed according to a uniform picture format, for example, the resolution of each picture is changed into a preset resolution, and the like, so that a picture information processing result is obtained; if the public information extraction result includes information of a document type, the characters in each document included in the information can be processed according to a uniform font format, or each document can be converted into a uniform document format, so that a document information processing result is obtained.

The method has the advantages that the public information in the public information extraction result can be more standardized, and the reading experience of the user on the public information is improved.

In this embodiment, after the public information extraction result matching the information extraction requirement is obtained, the public information included in the public information extraction result may be summarized according to the corresponding information type.

In a specific embodiment, assuming that the public information extraction result includes video information, the videos included in the information can be merged to obtain a video information summarization result; if the public information extraction result includes the information of the picture class, all pictures included in the information can be spliced to obtain a picture information summarizing result; if the public information extraction result includes the information of the document class, all documents included in the information can be merged into the same document to obtain a document information summarizing result.

The method has the advantages that the reading time of the user for the public information can be saved and the reading efficiency can be improved by summarizing the public information included in the public information extraction result.

In this step, optionally, the video information processing result, the picture information processing result, the document information processing result, the video information summarizing result, the picture information summarizing result, and the document information summarizing result together constitute the processing summarizing result.

And 270, displaying the processing and summarizing result in a visual and/or data report form mode.

In this embodiment, the processing summary result may be directly presented to the user through a visualization page; or generating a data report corresponding to the processing and summarizing result according to the quantity value of the corresponding processing result under different information types in the processing and summarizing result, and displaying the data report to a user. For example, assuming that the number value of the video information processing results in the processing summary results is 10, the number value of the picture information processing results is 5, and the number value of the document information processing results is 15, a histogram corresponding to the processing summary results may be generated to reflect the number of corresponding processing results in different information types.

The technical scheme of the embodiment of the disclosure includes that a target task corresponding to an information extraction requirement is obtained, at least one real-person operation simulation instruction is obtained from a real-person operation simulation instruction library, each real-person operation simulation instruction is dynamically added into a user operation behavior simulation instruction sequence corresponding to the target task, then the target task is dispatched to a target cloud device provided with a target mobile application, the target cloud device is triggered to execute each user operation behavior simulation instruction in the target mobile application, in-application display information generated by the target mobile application according to each user operation behavior simulation instruction is triggered in real time, finally a public information extraction result matched with the information extraction requirement is obtained, information processing and/or information gathering are carried out on each public information according to the information type of each public information included in the public information extraction result, the technical means of obtaining the processing and summarizing results and displaying the processing and summarizing results in a visual and/or data report form mode can provide a mode for extracting public information in the mobile internet, realize supervision and processing of rich media information and provide effective information service for users aiming at mobile application.

The embodiment of the present disclosure is further detailed in the above embodiment, and the same or corresponding terms as those of the embodiment are explained, and the embodiment of the present disclosure is not repeated. Fig. 3 is a flowchart of an information extraction method provided in the embodiment of the present disclosure, where the method of the embodiment specifically includes the following steps:

step 310, acquiring a target task corresponding to an information extraction requirement, wherein the target task is used for extracting at least one item of public information in a target mobile application; the target task comprises a user operation behavior simulation instruction sequence.

And step 320, scheduling the target task to target cloud equipment for installing the target mobile application, and triggering the target cloud equipment to execute each user operation behavior simulation instruction in the target task in the target mobile application.

And 330, acquiring a public information extraction result matched with the information extraction requirement according to the in-application display information generated by the target mobile application aiming at the user operation behavior simulation instruction in real time.

And 340, acquiring a plurality of pieces of in-application display information extracted aiming at different tasks.

Step 350, using at least one item of public opinion monitoring service, analyzing and processing the video content and/or text content included in the display information in each application to obtain public opinion monitoring results respectively corresponding to each public opinion monitoring service.

In this embodiment, the public opinion monitoring service may be a service module developed in advance by a developer according to different monitoring requirements, and each public opinion monitoring service corresponds to one monitoring requirement. Each public opinion monitoring service is used for analyzing and processing video content and/or text content included in display information in the application according to a pre-integrated information analysis algorithm to obtain a corresponding public opinion monitoring result.

In a specific embodiment, assuming that the monitoring requirement is to monitor a preset sensitive word, the public opinion monitoring service corresponding to the monitoring requirement may be a sensitive word monitoring service, where the sensitive word monitoring service is configured to perform sensitive word recognition on video content and text content included in presentation information in an application according to a pre-integrated speech recognition and text recognition algorithm, and use the recognized sensitive word as a corresponding public opinion monitoring result.

The method has the advantages that the public opinion monitoring service is used, the video content and/or the text content included in the display information in each application are analyzed, the automation of the rich media information supervision process can be realized, and the supervision efficiency of the rich media information is improved.

In this embodiment, optionally, the public opinion monitoring service includes at least one of the following: video content identification, image detection of a target attention object, text detection of a target keyword, trend analysis of a set event, character relation combing, comment analysis and evidence collection.

In a specific embodiment, optionally, the video content identification is configured to identify the video content included in the in-application presentation information, so as to determine whether the video content included in the in-application presentation information meets the relevant specification; detecting an image of the target attention object, wherein the image is used for detecting whether the display information in the application comprises the target attention object; text detection of the target keywords is used for detecting video content included in the display information in the application and whether the text content includes the target keywords or not; setting trend analysis of the event, and judging the view trend of the masses aiming at a certain hot event according to the video content and the text content included in the display information in the application; the character relation combing is used for carrying out relation combing on characters appearing in the video content and the text content included in the display information in the application to obtain a corresponding character relation map; comment analysis, which is used for analyzing comments of the masses aiming at a certain event according to the video content and the text content included in the display information in the application; and evidence collection and evidence obtaining, which is used for saving or collecting evidence related to certain event according to the video content and the text content included in the display information in the application.

The method has the advantages that comprehensive supervision on rich media information can be realized by integrating public sentiment monitoring services such as video content identification, image detection of target attention objects, text detection of target keywords, trend analysis of set events, character relation combing, comment analysis and evidence collection.

The disclosed embodiment can provide a technical means for extracting public information in the mobile internet by obtaining a target task corresponding to an information extraction requirement, scheduling the target task to a target cloud device installed with a target mobile application, triggering the target cloud device to execute each user operation behavior simulation instruction in the target mobile application, triggering generated in-application display information aiming at each user operation behavior simulation instruction according to the target mobile application in real time, then obtaining a public information extraction result matched with the information extraction requirement, obtaining a plurality of in-application display information extracted aiming at different tasks, analyzing and processing video content and/or text content included in each in-application display information by using at least one public opinion monitoring service, and obtaining the public opinion monitoring result corresponding to each public opinion monitoring service respectively, the method and the device realize supervision processing on the rich media information and provide effective information service for the user aiming at the mobile application.

The embodiment of the disclosure also provides an information extraction device, which is used for executing the information extraction method.

Fig. 4 is a block diagram of an information extraction apparatus 400 according to an embodiment of the present disclosure, where the apparatus includes: a task obtaining module 410, a task scheduling module 420, and a result obtaining module 430.

The task obtaining module 410 is configured to obtain a target task corresponding to an information extraction requirement, where the target task is used to extract at least one item of public information in a target mobile application; the target task comprises a user operation behavior simulation instruction sequence;

the task scheduling module 420 is configured to schedule the target task to a target cloud device where the target mobile application is installed, and trigger the target cloud device to execute each user operation behavior simulation instruction in the target task in the target mobile application;

and the result obtaining module 430 is configured to obtain a public information extraction result matched with the information extraction requirement according to in-application display information generated by triggering the target mobile application for each user operation behavior simulation instruction in real time.

According to the technical scheme of the embodiment, the target task corresponding to the information extraction requirement is obtained, the target task is dispatched to the target cloud equipment provided with the target mobile application, the target cloud equipment is triggered to execute each user operation behavior simulation instruction in the target task in the target mobile application, the generated in-application display information is triggered according to the target mobile application aiming at each user operation behavior simulation instruction in real time, and the public information extraction result matched with the information extraction requirement is obtained.

On the basis of the foregoing embodiments, the task scheduling module 420 further includes:

the cloud equipment acquisition unit is used for acquiring all alternative cloud equipment for installing the target mobile application in a cloud service platform;

the task judging unit is used for judging whether the target task needs to be executed after logging in the target mobile application by using the account;

the quantity detection unit is used for detecting the quantity value of a target account used in the historical execution task of each alternative cloud device when the target task needs to be executed after logging in the target mobile application by using the account, and the target account is used for logging in the target mobile application;

and the device selecting unit is used for selecting target cloud devices from the candidate cloud devices of which the number value of the target account is smaller than or equal to a preset number threshold, and scheduling the target tasks to the target cloud devices.

The task obtaining module 410 further includes:

the simulation instruction acquisition unit is used for acquiring at least one real person operation simulation instruction in a real person operation simulation instruction library;

and the simulation instruction adding unit is used for dynamically adding each real person operation simulation instruction into the user operation behavior simulation instruction sequence corresponding to the target task.

The device further comprises:

the information processing module is used for carrying out information processing and/or information summarization on each public information according to the information type of each public information included in the public information extraction result to obtain a processing and summarizing result;

the result display module is used for displaying the processing and summarizing results in a visual and/or data report form mode;

the information acquisition module is used for acquiring a plurality of pieces of in-application display information extracted aiming at different tasks;

the monitoring module is used for analyzing and processing video content and/or text content included in display information in each application by using at least one public opinion monitoring service to obtain public opinion monitoring results respectively corresponding to each public opinion monitoring service;

the public opinion monitoring service comprises at least one of: video content identification, image detection of a target attention object, text detection of a target keyword, trend analysis of a set event, character relation combing, comment analysis and evidence collection.

The information extraction device provided by the embodiment of the disclosure can execute the information extraction method provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects of the execution method.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 5 illustrates a schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 5, the apparatus 500 comprises a computing unit 501 which may perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The calculation unit 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

A number of components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing AI chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 501 performs the respective methods and processes described above, such as the information extraction method. For example, in some embodiments, the information extraction method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the information extraction method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the information extraction method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), AI system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in this disclosure may be performed in parallel or sequentially or in a different order, as long as the desired results of the technical solutions provided by this disclosure can be achieved, and are not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.