CN113469732A - Content understanding-based auditing method and device and electronic equipment - Google Patents

Content understanding-based auditing method and device and electronic equipment Download PDF

Info

Publication number
CN113469732A
CN113469732A CN202110652248.6A CN202110652248A CN113469732A CN 113469732 A CN113469732 A CN 113469732A CN 202110652248 A CN202110652248 A CN 202110652248A CN 113469732 A CN113469732 A CN 113469732A
Authority
CN
China
Prior art keywords
content
audited
auditing
text
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110652248.6A
Other languages
Chinese (zh)
Inventor
张言
邓远达
刘星
梁晓旭
胡旭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202110652248.6A priority Critical patent/CN113469732A/en
Publication of CN113469732A publication Critical patent/CN113469732A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements

Abstract

The disclosure discloses an auditing method and device based on content understanding and electronic equipment, relates to the technical field of computers, and particularly relates to the technical field of information processing. The specific implementation scheme is as follows: determining a management and control requirement; acquiring at least one content tag corresponding to the control demand, and configuring a content auditing system based on the at least one content tag, wherein any one content tag in the at least one content tag corresponds to at least one auditing model; under the condition that the object to be audited is obtained, an auditing model corresponding to the at least one content label is called based on the content auditing system to audit the content of the object to be audited; and outputting an auditing result, wherein the auditing result is used for representing the content of the object to be audited.

Description

Content understanding-based auditing method and device and electronic equipment
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to an auditing method and apparatus based on content understanding, and an electronic device.
Background
With the development of the mobile internet, the content consumption is upgraded, and the content display form covers characters, images, videos and the like. The content needs to be audited before being released and the user obtains information to ensure high quality content pushed to the user. The main purpose of auditing is to filter out the content at risk, and by establishing different risk identification models for different risk categories, when the risk reappears, the risk is identified and filtered through the established risk identification models.
Disclosure of Invention
The disclosure provides an auditing method and device based on content understanding and electronic equipment.
According to a first aspect of the present disclosure, there is provided a content understanding-based auditing method, including:
determining a management and control requirement;
acquiring at least one content tag corresponding to the control demand, and configuring a content auditing system based on the at least one content tag, wherein any one content tag in the at least one content tag corresponds to at least one auditing model;
under the condition that the object to be audited is obtained, an auditing model corresponding to the at least one content label is called based on the content auditing system to audit the content of the object to be audited;
and outputting an auditing result, wherein the auditing result is used for representing the content of the object to be audited.
According to a second aspect of the present disclosure, there is provided a content understanding-based auditing apparatus including:
the determining module is used for determining the management and control requirements;
the configuration module is used for acquiring at least one content tag corresponding to the control demand and configuring a content auditing system based on the at least one content tag, wherein any one of the at least one content tag corresponds to at least one auditing model;
the auditing module is used for invoking an auditing model corresponding to the at least one content tag based on the content auditing system to audit the content of the object to be audited under the condition that the object to be audited is obtained;
and the output module is used for outputting an auditing result, and the auditing result is used for representing the content of the object to be audited.
According to a third aspect of the present disclosure, there is provided 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 the first aspect.
According to a fourth 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 according to the first aspect.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method according to the first aspect.
According to the scheme provided by the disclosure, different auditing systems do not need to be configured for different business parties independently, and the auditing system based on content understanding can be suitable for content auditing of auditing objects of business parties with different management and control requirements, so that the auditing mode of the electronic equipment is more flexible, and the coverage range of the auditing objects is wider.
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
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a flow chart of a content understanding-based auditing method provided according to an embodiment of the present disclosure;
FIG. 2 is a schematic view of a scenario of an auditing method based on content understanding, which is suitable for use in an embodiment of the present disclosure;
fig. 3 is a block diagram of an auditing apparatus based on content understanding provided according to an embodiment of the present disclosure;
FIG. 4 is a block diagram of an electronic device for implementing a content understanding-based auditing method of 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.
The embodiment of the disclosure provides an auditing method based on content understanding.
Referring to fig. 1, fig. 1 is a flowchart of an auditing method based on content understanding according to an embodiment of the present disclosure. As shown in fig. 1, the content understanding-based auditing method includes the following steps:
and step S101, determining a management and control requirement.
In the embodiment of the present disclosure, the management and control requirement may refer to a management and control requirement of a service party, and the service party may refer to a service platform or service software that provides content consumption for a user, for example, search software, a video playing platform, online shopping software, social contact software, and the like.
The management and control requirement of the business party may refer to a control requirement of the business party on the display content on its own platform or software, for example, the display content is not allowed to relate to the content such as the non-civilized term. It will be appreciated that the governing requirements of different business parties may be different.
It should be noted that the method provided by the embodiment of the present disclosure may be applied to an electronic device, and the electronic device may be installed with a service platform or service software of a service party. Furthermore, the electronic device can also obtain the management and control requirements of the installed business side.
And S102, acquiring at least one content tag corresponding to the control requirement, and configuring a content auditing system based on the at least one content tag.
Wherein any one of the at least one content tag corresponds to at least one audit model. For example, if there are three content tags corresponding to regulatory requirements, each of the three content tags may correspond to at least one audit model. The audit model may be a pre-constructed neural network model capable of auditing the object to be audited, the audit model may be obtained by training based on a large number of training samples, the training samples may be training samples related to the content tag, and the training method of the neural network model may refer to the principle and implementation manner in the related art, which is not described in detail in the embodiment of the present disclosure.
In the embodiment of the disclosure, the electronic device is provided with an auditing system based on content understanding, the auditing system based on content understanding can be a pre-constructed auditing system, the auditing system can comprise a requirement layer, a configuration layer and a label layer, the requirement layer is provided with different control requirements, and the configuration layer can configure labels according to the control requirements of a business party; the label layer comprises various preset content labels, the configuration layer configures corresponding labels for the management and control requirements based on the content labels in the label layer, and one content label corresponds to at least one auditing model.
As shown in fig. 2, the requirement layer of the auditing system includes sensitive information management and control, low-quality content management and control, qualification admission management and control, compliance management and control, etc.; the label layer comprises three types of labels of pictures, texts and landing pages respectively, wherein the labels of the picture types comprise household appliances, characters, underwear, wine, flags and underpants, the labels of the text types comprise hints, public opinion descriptions, health care and eight diagrams descriptions, and the labels of the landing pages comprise illegal agents and webpage tampering; if the configuration layer needs to perform tag configuration on the sensitive information management and control, the configuration layer may select corresponding content tags based on three types of tag types, i.e., a picture type tag configured with a character content tag and a flag content tag, a text type tag configured with a public opinion description content tag and an eight trigram description content tag, and a landing page content tag configured with an illegal agent content tag and a webpage tampering content tag. Therefore, based on the management and control requirement of the business party on the sensitive information, the content tags corresponding to the management and control requirement of the sensitive information can be obtained, and further based on the corresponding content tags, a content auditing system of the business party can be configured, and the content auditing system also comprises all auditing models of the corresponding content tags.
And step S103, under the condition that the object to be audited is obtained, based on the content auditing system, invoking an auditing model corresponding to the at least one content tag to audit the content of the object to be audited.
The object to be audited may refer to a business object applied to a business party. For example, the business party is an advertisement delivery platform, and the business object of the business party is the advertisement to be delivered on the platform. The electronic device is provided with the advertisement putting platform, and when the advertisement to be put which needs to be put by the advertisement putting platform is obtained, the advertisement to be put is also an object to be checked, and the content of the advertisement to be put needs to be checked so as to judge whether the content of the advertisement to be put meets the control requirement of the advertisement putting platform.
In the embodiment of the disclosure, after determining the management and control requirement of a service party, an electronic device can obtain at least one content tag corresponding to the management and control requirement of the service party from an auditing system based on content understanding, configure the content auditing system of the service party based on the content tags, and then, when an object to be audited of the service party is obtained, can call an auditing model corresponding to the at least one content tag based on the configured content auditing system to perform content auditing on the object to be audited.
Specifically, if the number of the content tags corresponding to the control requirement of the business side is three, one of the content tags corresponds to one audit model, and the other two content tags correspond to two audit models, the content audit system configured for the business side also corresponds to five audit models; and when the to-be-audited object of the business party is obtained, the five auditing models are called to audit the content of the to-be-audited object.
And S104, outputting an auditing result, wherein the auditing result is used for representing the content of the object to be audited.
In the embodiment of the present disclosure, the electronic device may be a content auditing system configured for a business party, and invoke a corresponding auditing model to perform content auditing on an object to be audited of the business party, so as to output an auditing result, where the auditing result is used to represent the content of the object to be audited, or to describe the content of the object to be audited.
The content auditing method includes the steps that content auditing is conducted on an object to be audited based on an auditing model corresponding to a content auditing system, the object to be audited can be used as input of each auditing model, and the object to be audited is subjected to content auditing based on the auditing model, for example, the object to be audited can be subjected to character extraction or image recognition so as to output auditing results for describing the content of the object to be audited. For example, if the object to be reviewed is an image including "xx building", the output review result may be "xx building", that is, the review result is used to describe the image content in the image.
According to the scheme provided by the embodiment of the disclosure, after the management and control requirements of a business party are determined, the electronic device can obtain at least one content tag corresponding to the management and control requirements of the business party from an auditing system based on content understanding, configure the content auditing system of the business party based on the content tags, and further, when an object to be audited of the business party is obtained, can call a corresponding auditing model based on the configured content auditing system to audit the object to be audited, output an auditing result for representing the content of the object to be audited, and a user can determine whether the object to be audited meets the management and control requirements based on the auditing result. Therefore, the electronic equipment does not need to separately configure different auditing systems for different business parties, and the auditing system based on content understanding can be suitable for content auditing of auditing objects of the business parties with different management and control requirements, so that the auditing mode of the electronic equipment is more flexible, and the coverage range of the auditing objects is wider.
Optionally, the step S103 may include:
under the condition that an object to be audited is obtained, determining the type of the object to be audited, wherein the type comprises at least one of a text and an image;
when the type of the object to be audited comprises a text, invoking a text auditing model in the at least one auditing model to audit the text of the object to be audited so as to judge whether the text of the object to be audited is matched with a preset text;
and under the condition that the type of the object to be audited comprises an image, calling an image auditing model in the at least one auditing model to identify the image of the object to be audited so as to judge whether the image of the object to be audited is matched with a preset image.
For example, the service party is an advertisement delivery platform, the object to be audited is an advertisement to be audited, which needs to be delivered on the platform, and the advertisement includes characters and images, when the electronic device audits the advertisement to be audited, the electronic device can call a text audit model in a corresponding audit model to audit the text of the advertisement to be audited through a configured content audit system, for example, keyword extraction can be performed on the text included in the advertisement to be audited to judge whether the extracted keyword is matched with a preset text; and meanwhile, calling an image auditing model in the corresponding auditing model based on the configured content auditing system to identify the image of the advertisement to be audited so as to judge whether the identified image is matched with a preset image.
In the embodiment of the disclosure, based on the type of the object to be audited, text auditing and/or image auditing are/is performed through the auditing model corresponding to the type, so as to determine whether the text of the object to be audited matches a preset text and/or whether the image of the object to be audited matches a preset image, and output a corresponding auditing result. Therefore, the corresponding auditing model is pertinently called to audit according to the type of the object to be audited, so that the output auditing result can be more appropriate to the type of the object to be audited, and the accuracy of the auditing result is effectively improved.
Further, the step S104 may include:
under the condition that the text of the object to be audited is matched with the preset text, outputting an audit result comprising the preset text;
and under the condition that the image of the object to be audited is matched with the preset image, outputting an audit result comprising text information for describing the preset image.
The text audit model may be obtained by training a large number of text training samples, and the text audit model may include at least one preset text, and the text audit model corresponds to the content tag. For example, the content tag is the description of the eight diagrams, and the preset text included in the text auditing model corresponding to the content tag may include the eight diagrams, the red news, the pop news, the hard news, and the like. If the configured content auditing system comprises a text auditing model corresponding to the eight diagrams description content label, when the text auditing model is called to audit the text of the object to be audited, namely whether the text is matched with the preset texts is judged; if so, outputting an auditing result comprising the preset text; for example, if the text of the object to be audited includes "news-burg", which indicates that the text matches with the preset text "news-burg", the audit result output for the object to be audited also includes the word "news-burg". Furthermore, the user can determine that the object to be audited relates to the description of the eight diagrams based on the auditing result, and more intuitive reference can be provided for the user to determine whether the object to be audited meets the control requirement.
Optionally, the image audit model is also obtained by training a large number of image training samples, and the image audit model may include at least one preset image, and the image audit model corresponds to the content tag. For example, if the configured content auditing system includes an image auditing model corresponding to the flag content tag, when the image auditing model is called to audit the image of the object to be audited, that is, whether the image included in the object to be audited matches with a preset image corresponding to the content tag is judged; and if so, outputting an auditing result comprising text information for describing the preset image. Furthermore, more intuitive reference can be provided for the user to determine whether the object to be audited meets the control requirement. For example, if the service party is an advertisement delivery platform, and if the service party does not meet the requirement of the advertisement law, the user can more intuitively and accurately know that the object to be checked does not meet the control requirement of the service party based on the checking result, and reference can be provided for the user to improve the object to be checked.
In the embodiment of the disclosure, under the condition that the text audit and/or the image audit is performed on the object to be audited through the audit model corresponding to the type based on the type of the object to be audited, the output audit result includes the preset text and/or the text information for describing the preset image, so that the user can more intuitively know the content included in the object to be audited based on the audit result, and provide a more intuitive reference for the user to determine whether the object to be audited meets the control requirement of the business party, and under the condition that the object to be audited does not meet the control requirement, the user can know what the content of the object to be audited does not meet the control requirement, so that a suggestion is provided for the user to improve the object to be audited, and the method is more beneficial for helping the user to obtain the object to be audited meeting the control requirement of the business party.
In this embodiment of the present disclosure, the content understanding-based auditing system may be a preset auditing system that the electronic device has configured a content tag, or a general auditing system; further, the user can also configure the auditing system based on content understanding aiming at the management and control requirements of the business party.
Optionally, in an embodiment of the present disclosure, the method further includes:
under the condition that a service side comprises a target management and control requirement, acquiring a target content label corresponding to the target management and control requirement from a content label database; wherein the at least one content tag comprises the target content tag.
The electronic device may be a preset content tag database, and the content tag database may include content tags corresponding to different regulatory requirements, or may be content tags corresponding to all regulatory requirements of a business party to which the electronic device may be applied.
When the service party includes the target management and control requirement, if the target content tag corresponding to the target management and control requirement is not included in the content understanding-based auditing system or included in a preset auditing system, the electronic device may acquire the target content tag corresponding to the target management and control requirement from a content tag database based on user operation, and then the electronic device may acquire the target content tag corresponding to the target management and control requirement after determining the target management and control requirement of the service party. It should be noted that the number of the target content tags may be at least one, and each target content tag corresponds to at least one audit model. Furthermore, the electronic device can also configure a content auditing system corresponding to the target control requirement of the business party based on the target content tag, and can call an auditing model corresponding to the target content tag to perform content auditing on the object to be audited based on the configured content auditing system under the condition that the object to be audited is obtained.
In the embodiment of the disclosure, under the condition that the service party includes the target management and control requirement, the electronic device can acquire the target content tag corresponding to the target management and control requirement from the content tag database, and then the electronic device can flexibly configure the content tag of the service party management and control requirement according to the management and control requirement of the service party, so as to meet different management and control requirements of different service parties, and thus the application range of the method is wider.
Specifically, the electronic device may configure and generate a Directed Acyclic Graph (DAG) bridge for constructing a business side management and control requirement and a content tag according to a management and control requirement of a business side, and may calculate and obtain a corresponding content tag return according to the management and control requirement through the DAG. Optionally, the DAG may be generated automatically, each operator separately maintains one child DAG, one DAG is equivalent to one content tag, an operator set determined according to the control requirement automatically generates an overall DAG, and the algorithm is as follows:
DAG=(dag0∪dag1…∪dagn);
wherein DAG is the whole DAG, n is the nth operator, DAGnDag for the nth operator. Specifically, reference may be made to related technologies, and details of the present disclosure are not described in detail.
Further, before the obtaining the target content tag corresponding to the target regulatory requirement from the content tag database, the method further includes:
acquiring input information under the condition that the target content tag is not included in the content tag database;
constructing the target content label based on the input information, and constructing at least one auditing model corresponding to the target content label;
adding the target content tag into the content tag database.
In the embodiment of the present disclosure, if the content tag database does not include the target content tag corresponding to the target management and control requirement, the target content tag may be constructed by obtaining input information of a user, constructing at least one audit model corresponding to the target content tag, and adding the constructed target content tag into the content tag database, so that the number and range of the content tags in the content tag database are expanded, and the content tag database can be suitable for more business parties and different management and control requirements. Therefore, for the content labels which are not available, the user only needs to construct the corresponding content labels, and an independent auditing system does not need to be configured for the target management and control requirements of the business party independently.
Optionally, when the management and control requirement of the business party does not meet the current risk management and control requirement, or the management and control requirement of the business party needs to be upgraded, the content tag corresponding to the management and control requirement may be found and upgraded, for example, the content tag may be an audit model of an extended content tag, such as an extended audit model of a preset text or a preset image; or adding a content tag matched with the control requirement and a corresponding auditing model and the like.
For example, if the flag content tag in the picture content tag corresponding to the sensitive information management and control requirement does not meet the current risk management and control requirement, only the flag content tag may be optimized, for example, a preset image in a flag content tag audit model is added, so that the optimized flag content tag can meet the current risk management and control requirement, and it is not necessary to upgrade and optimize all content tags corresponding to the whole sensitive information management and control requirement, so that the upgrade and optimization of the business side management and control requirement can be effectively simplified, and the upgrade cost of the audit system based on content understanding is reduced.
The scheme provided by the embodiment of the disclosure can configure a universal content auditing system for different business parties, and can be suitable for content auditing of auditing objects of business parties with different control requirements, so that different auditing systems do not need to be configured for different business parties separately; or corresponding content tags can be flexibly configured based on the management and control requirements of the business party, so that the business party with different management and control requirements can be met, the auditing of the object to be audited of the business party is met, the expandability of an auditing system is improved, and the auditing method and the auditing device can be suitable for the auditing requirements of different business parties.
The embodiment of the disclosure also provides an auditing device based on content understanding.
Referring to fig. 3, fig. 3 is a structural diagram of an auditing apparatus based on content understanding according to an embodiment of the present disclosure. As shown in fig. 3, the content understanding-based auditing apparatus 300 includes:
a determining module 301, configured to determine a management and control requirement;
a configuration module 302, configured to obtain at least one content tag corresponding to the management and control requirement, and configure a content auditing system based on the at least one content tag, where any one of the at least one content tag corresponds to at least one auditing model;
the auditing module 303 is configured to, when an object to be audited is obtained, invoke an auditing model corresponding to the at least one content tag based on the content auditing system to perform content auditing on the object to be audited;
and an output module 304, configured to output an audit result, where the audit result is used to represent the content of the object to be audited.
Optionally, the content understanding-based auditing apparatus 300 further includes:
the first acquisition module is used for acquiring a target content label corresponding to a target management and control demand from a content label database under the condition that a service party comprises the target management and control demand;
wherein the at least one content tag comprises the target content tag.
Optionally, the content understanding-based auditing apparatus 300 further includes:
a second obtaining module, configured to obtain input information when the content tag database does not include the target content tag;
the construction module is used for constructing the target content label based on the input information and constructing at least one auditing model corresponding to the target content label;
and the adding module is used for adding the target content label into the content label database.
Optionally, the auditing module 303 is further configured to:
under the condition that an object to be audited is obtained, determining the type of the object to be audited, wherein the type comprises at least one of a text and an image;
when the type of the object to be audited comprises a text, invoking a text auditing model in the at least one auditing model to audit the text of the object to be audited so as to judge whether the text of the object to be audited is matched with a preset text;
and under the condition that the type of the object to be audited comprises an image, calling an image auditing model in the at least one auditing model to identify the image of the object to be audited so as to judge whether the image of the object to be audited is matched with a preset image.
Optionally, the output module 304 is further configured to:
under the condition that the text of the object to be audited is matched with the preset text, outputting an audit result comprising the preset text;
and under the condition that the image of the object to be audited is matched with the preset image, outputting an audit result comprising text information for describing the preset image.
The auditing device 300 based on content understanding can configure a universal content auditing system aiming at different business parties, can be suitable for content auditing of auditing objects of business parties with different management and control requirements, and further does not need to configure different auditing systems for different business parties; or corresponding content tags can be flexibly configured based on the management and control requirements of the business party, so that the business party with different management and control requirements can be met, the auditing of the object to be audited of the business party is met, the expandability of an auditing system is improved, and the auditing method and the auditing device can be suitable for the auditing requirements of different business parties.
It should be noted that, the content understanding-based auditing apparatus 300 provided in this embodiment can implement all technical solutions of the content understanding-based auditing method embodiments, so that at least all technical effects can be achieved, and details are not described here.
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. 4 shows a schematic block diagram of an example electronic device 400 that may 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. 4, the electronic device 400 includes a computing unit 401 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)402 or a computer program loaded from a storage unit 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
A number of components in device 400 are connected to I/O interface 405, including: an input unit 406 such as a keyboard, a mouse, or the like; an output unit 407 such as various types of displays, speakers, and the like; a storage unit 408 such as a magnetic disk, optical disk, or the like; and a communication unit 409 such as a network card, modem, wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
Computing unit 401 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing 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 401 executes the respective methods and processes described above, such as the content understanding-based auditing method described above. For example, in some embodiments, the content understanding-based auditing method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 400 via the ROM 402 and/or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the content understanding based auditing method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the content understanding-based auditing 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), 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), 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.
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 the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is 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.

Claims (13)

1. An auditing method based on content understanding, comprising:
determining a management and control requirement;
acquiring at least one content tag corresponding to the control demand, and configuring a content auditing system based on the at least one content tag, wherein any one content tag in the at least one content tag corresponds to at least one auditing model;
under the condition that the object to be audited is obtained, an auditing model corresponding to the at least one content label is called based on the content auditing system to audit the content of the object to be audited;
and outputting an auditing result, wherein the auditing result is used for representing the content of the object to be audited.
2. The method of claim 1, further comprising:
under the condition that a service side comprises a target management and control requirement, acquiring a target content label corresponding to the target management and control requirement from a content label database;
wherein the at least one content tag comprises the target content tag.
3. The method of claim 2, before the obtaining the target content tag corresponding to the target regulatory requirement from the content tag database, further comprising:
acquiring input information under the condition that the target content tag is not included in the content tag database;
constructing the target content label based on the input information, and constructing at least one auditing model corresponding to the target content label;
adding the target content tag into the content tag database.
4. The method according to claim 1, wherein, in a case where the object to be audited is obtained, invoking the at least one audit model based on the content audit system to audit the object to be audited, includes:
under the condition that an object to be audited is obtained, determining the type of the object to be audited, wherein the type comprises at least one of a text and an image;
when the type of the object to be audited comprises a text, invoking a text auditing model in the at least one auditing model to audit the text of the object to be audited so as to judge whether the text of the object to be audited is matched with a preset text;
and under the condition that the type of the object to be audited comprises an image, calling an image auditing model in the at least one auditing model to identify the image of the object to be audited so as to judge whether the image of the object to be audited is matched with a preset image.
5. The method of claim 4, wherein the outputting of the audit result comprises:
under the condition that the text of the object to be audited is matched with the preset text, outputting an audit result comprising the preset text;
and under the condition that the image of the object to be audited is matched with the preset image, outputting an audit result comprising text information for describing the preset image.
6. An auditing apparatus based on content understanding, comprising:
the determining module is used for determining the management and control requirements;
the configuration module is used for acquiring at least one content tag corresponding to the control demand and configuring a content auditing system based on the at least one content tag, wherein any one of the at least one content tag corresponds to at least one auditing model;
the auditing module is used for invoking an auditing model corresponding to the at least one content tag based on the content auditing system to audit the content of the object to be audited under the condition that the object to be audited is obtained;
and the output module is used for outputting an auditing result, and the auditing result is used for representing the content of the object to be audited.
7. The apparatus of claim 6, further comprising:
the first acquisition module is used for acquiring a target content label corresponding to a target management and control demand from a content label database under the condition that a service party comprises the target management and control demand;
wherein the at least one content tag comprises the target content tag.
8. The apparatus of claim 7, further comprising:
a second obtaining module, configured to obtain input information when the content tag database does not include the target content tag;
the construction module is used for constructing the target content label based on the input information and constructing at least one auditing model corresponding to the target content label;
and the adding module is used for adding the target content label into the content label database.
9. The apparatus of claim 6, wherein the audit module is further to:
under the condition that an object to be audited is obtained, determining the type of the object to be audited, wherein the type comprises at least one of a text and an image;
when the type of the object to be audited comprises a text, invoking a text auditing model in the at least one auditing model to audit the text of the object to be audited so as to judge whether the text of the object to be audited is matched with a preset text;
and under the condition that the type of the object to be audited comprises an image, calling an image auditing model in the at least one auditing model to identify the image of the object to be audited so as to judge whether the image of the object to be audited is matched with a preset image.
10. The apparatus of claim 9, wherein the output module is further configured to:
under the condition that the text of the object to be audited is matched with the preset text, outputting an audit result comprising the preset text;
and under the condition that the image of the object to be audited is matched with the preset image, outputting an audit result comprising text information for describing the preset image.
11. 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 1-5.
12. 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 1-5.
13. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-5.
CN202110652248.6A 2021-06-11 2021-06-11 Content understanding-based auditing method and device and electronic equipment Pending CN113469732A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110652248.6A CN113469732A (en) 2021-06-11 2021-06-11 Content understanding-based auditing method and device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110652248.6A CN113469732A (en) 2021-06-11 2021-06-11 Content understanding-based auditing method and device and electronic equipment

Publications (1)

Publication Number Publication Date
CN113469732A true CN113469732A (en) 2021-10-01

Family

ID=77869709

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110652248.6A Pending CN113469732A (en) 2021-06-11 2021-06-11 Content understanding-based auditing method and device and electronic equipment

Country Status (1)

Country Link
CN (1) CN113469732A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114125054A (en) * 2021-11-29 2022-03-01 百果园技术(新加坡)有限公司 Content auditing system, method, device, equipment and medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111274782A (en) * 2020-02-25 2020-06-12 平安科技(深圳)有限公司 Text auditing method and device, computer equipment and readable storage medium
CN111382291A (en) * 2020-03-12 2020-07-07 北京金山云网络技术有限公司 Machine auditing method and device and machine auditing server
CN111985760A (en) * 2020-06-30 2020-11-24 北京百度网讯科技有限公司 Data content evaluation method and device, electronic equipment and storage medium
CN112507936A (en) * 2020-12-16 2021-03-16 平安银行股份有限公司 Image information auditing method and device, electronic equipment and readable storage medium
CN112613501A (en) * 2020-12-21 2021-04-06 深圳壹账通智能科技有限公司 Information auditing classification model construction method and information auditing method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111274782A (en) * 2020-02-25 2020-06-12 平安科技(深圳)有限公司 Text auditing method and device, computer equipment and readable storage medium
CN111382291A (en) * 2020-03-12 2020-07-07 北京金山云网络技术有限公司 Machine auditing method and device and machine auditing server
CN111985760A (en) * 2020-06-30 2020-11-24 北京百度网讯科技有限公司 Data content evaluation method and device, electronic equipment and storage medium
CN112507936A (en) * 2020-12-16 2021-03-16 平安银行股份有限公司 Image information auditing method and device, electronic equipment and readable storage medium
CN112613501A (en) * 2020-12-21 2021-04-06 深圳壹账通智能科技有限公司 Information auditing classification model construction method and information auditing method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114125054A (en) * 2021-11-29 2022-03-01 百果园技术(新加坡)有限公司 Content auditing system, method, device, equipment and medium
CN114125054B (en) * 2021-11-29 2024-03-15 百果园技术(新加坡)有限公司 Content auditing system, method, device, equipment and medium

Similar Documents

Publication Publication Date Title
CN111143505B (en) Document processing method, device, medium and electronic equipment
US9460163B1 (en) Configurable extractions in social media
CN113139816A (en) Information processing method, device, electronic equipment and storage medium
CN113469732A (en) Content understanding-based auditing method and device and electronic equipment
CN113378855A (en) Method for processing multitask, related device and computer program product
CN113407610A (en) Information extraction method and device, electronic equipment and readable storage medium
CN116450723A (en) Data extraction method, device, computer equipment and storage medium
CN109829744A (en) Consultation method, device, electronic equipment and medium based on natural language processing
CN113360672B (en) Method, apparatus, device, medium and product for generating knowledge graph
CN115510508A (en) Page information protection method and device and electronic equipment
CN113850072A (en) Text emotion analysis method, emotion analysis model training method, device, equipment and medium
CN113836462A (en) Page description file generation method, device, equipment and storage medium
CN114329164A (en) Method, apparatus, device, medium and product for processing data
CN113627526A (en) Vehicle identification recognition method and device, electronic equipment and medium
CN113806541A (en) Emotion classification method and emotion classification model training method and device
CN113032251A (en) Method, device and storage medium for determining service quality of application program
CN113449506A (en) Data detection method, device and equipment and readable storage medium
CN113239273A (en) Method, device, equipment and storage medium for generating text
CN112861504A (en) Text interaction method, device, equipment, storage medium and program product
CN112560462B (en) Event extraction service generation method, device, server and medium
CN113239296B (en) Method, device, equipment and medium for displaying small program
CN115965018B (en) Training method of information generation model, information generation method and device
KR20190041821A (en) System and method for managing companion animal related goods
US20220129966A1 (en) Method of transmitting message, electronic device and storage medium
CN107870679B (en) Polyphone processing method and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination