Automatic processing of conferences for confidential content

Abstract

The invention relates to automatic processing of conferences for confidential content. A method, computer system and computer program product for processing digital content are provided. The method can comprise the step of constructing a sensitive statement classification model. The invention may include receiving digital content, wherein the digital content is intended for one or more groups of content consumers. The invention may include processing digital content using a sensitive statement classification model. The invention may include generating consumer-specific digital content for each of one or more groups of content consumers.

Description

Technical Field

[0001] The present invention relates generally to the field of computing, and more particularly to digital content processing. Background Art

[0002] Due in part to the trend toward remote work, many organizations may be conducting many of their most important meetings, public service announcements and lectures, and other discussions, through online software that enables digital content to be replayed by multiple consumers within the organization. Typically, these meetings may be recorded, with portions of the meeting only viewable under certain conditions. Current methods typically require post-processing of the meeting content for each specific group of consumers, require specific encryption equipment to encrypt audio data, require unique authentication with specific equipment, and / or require encoding and / or decoding equipment to encode and / or decode protected data. Current methods may be inefficient, subject to human error, and / or institutional barriers that may reduce the number of consumers who can access digital content playback.

[0003] Therefore, there is a need for a system that automatically generates post-processed conference content through artificial intelligence (AI). More specifically, a system that can identify sensitive data segments in digital content based on the roles of a content producer and a group of content consumers may be beneficial. Summary of the invention

[0004] Embodiments of the present invention disclose a method, computer system, and computer program product for digital content processing. The present invention may include building a sensitive sentence classification model. The present invention may include receiving digital content, wherein the digital content is intended for one or more content consumer groups. The present invention may include processing the digital content using the sensitive sentence classification model. The present invention may include generating consumer-specific digital content for each of one or more content consumer groups.

[0005] In another embodiment, the method may include training a sensitive sentence classification model using a customized training dataset and an existing dataset, wherein the customized training dataset includes keywords and entities derived from organizational information, wherein the existing dataset includes one or more existing sensitive word datasets derived from one or more publicly available resources, and wherein the customized training dataset and the existing dataset are preprocessed using a Word2Vec algorithm.

[0006] In another embodiment, the method may include storing the digital content received in its original form in an original content database, identifying one or more sensitive data segments using a sensitive sentence classification model, and storing the one or more sensitive data segments in a processed content database based on at least one or more of a data type, a timestamp, or a corresponding consumer role, wherein the corresponding consumer role includes at least one of one or more content consumer groups.

[0007] In yet another embodiment, the method may include assigning a plurality of consumers within an organization to one or more content consumer groups according to a hierarchical structure of the organization constructed based on an analysis of organizational information, and displaying consumer-specific digital content to the plurality of consumers, wherein each of the plurality of consumers may access the consumer-specific digital content corresponding to their content consumer group.

[0008] In addition to the method, additional embodiments relate to a computer system and a computer program product for automatically post-processing digital content of sensitive data segments for different groups of content consumers.

[0009] This Summary is provided to introduce some concepts in a simplified form that are further described below in the Detailed Description.This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] These and other objects, features and advantages of the present invention will become apparent from the following detailed description of illustrative embodiments thereof read in conjunction with the accompanying drawings. The various features of the drawings are not to scale, as for the sake of clarity, the illustrations are intended to aid those skilled in the art in understanding the present invention in conjunction with the detailed description. In the drawings:

[0011] Figure 1 A block diagram illustrating an exemplary computing environment in accordance with at least one embodiment is shown;

[0012] Figure 2 is an operational flow diagram illustrating a process for digital content processing according to at least one embodiment; and

[0013] Figure 3 Depicted is a diagram illustrating the use of Figure 2 Block diagram and flow chart of the training process for some of the components discussed in . DETAILED DESCRIPTION

[0014] The exemplary embodiments described below provide a system, method, and program product for digital content processing. Therefore, the present embodiment has the ability to improve the technical field of digital content processing and machine learning by automatically post-processing digital content of sensitive data fragments for different content consumer groups. More specifically, the present invention may include building a sensitive sentence classification model. The present invention may include receiving digital content, wherein the digital content is intended for one or more content consumer groups. The present invention may include processing digital content using a sensitive sentence classification model. The present invention may include generating consumer-specific digital content for each of one or more content consumer groups.

[0015] As previously mentioned, due in part to the teleworking trend, many organizations may be conducting many of their most important meetings, public service announcements, lectures, and other discussions through online software that enables multiple consumers within the organization to replay digital content. Typically, these meetings can be recorded, with portions of the meeting only viewable under certain conditions. Current methods typically require post-processing of the meeting content for each specific group of consumers, require specific encryption equipment to encrypt audio data, require unique authentication with specific equipment, and / or require encoding and / or decoding equipment to encode and / or decode protected data. Current methods may be inefficient, subject to human error, and / or institutional barriers that may reduce the number of consumers who can access digital content replay.

[0016] Therefore, there is a need for a system that automatically generates post-processed conference content through artificial intelligence (AI). More specifically, a system that can identify sensitive data segments in digital content based on the content consumer group and the role of the content producer.

[0017] Thus, it may be advantageous to, among other things, build a sensitive statement classification model and receive digital content, where the digital content is intended for one or more content consumer groups, process the digital content using the sensitive statement classification model, and generate consumer-specific digital content for each of the one or more content consumer groups.

[0018] According to at least one embodiment, the present invention can improve the processing of digital content by providing a system that can specifically identify sensitive data segments in digital content (e.g., video and / or audio of a web conference) based on the roles of content producers and content consumers (e.g., speakers and listeners).

[0019] According to at least one embodiment, the present invention can improve post-processing of conference videos for confidential content by preserving and / or masking identified sensitive data segments in the replayed digital content in a role-based manner.

[0020] In accordance with at least one embodiment, the present invention may improve the monitoring of confidential content in conferences conducted via online software by enabling content providers and / or speakers to optionally and / or manually trigger the marking of sensitive data segments in addition to automatic identification using a sensitive sentence classification model (SSCM).

[0021] According to at least one embodiment, the present invention can improve the efficiency with which multiple consumers can play back digital content, where, as opposed to editing videos separately for each of multiple roles, multiple consumers play different roles within an organization by applying different filtering rules to different roles using a sensitive sentence classification model (SSCM).

[0022] According to at least one embodiment, the present invention can improve the generation of consumer-specific digital content for different consumer groups by training an SSCM model using a customized training dataset and an existing dataset, wherein the customized training dataset includes keywords and entities derived from organizational information, wherein the existing dataset includes one or more existing sensitive word datasets derived from one or more publicly available resources, and wherein the customized training dataset and the existing dataset are pre-processed using a Word2Vec algorithm.

[0023] According to at least one embodiment, the present invention can improve the processing of digital content using the SSCM model by: storing the digital content received in its original form in an original content database; identifying one or more sensitive data fragments using the sensitive statement classification model; and storing the one or more sensitive data fragments in a processed content database based on at least one or more of a data type, a timestamp, or a corresponding consumer role, wherein the corresponding consumer role includes at least one of the one or more content consumer groups.

[0024] According to at least one embodiment, the present invention may improve identifying sensitive data segments by enabling content producers to manually identify sensitive content within a user interface and enabling content consumers to manually tag sensitive content that may be stored in a processed content database and used to retrain the SSCM.

[0025] refer to Figure 1, computing environment 100 comprises an example of an environment for executing at least some of the computer codes involved in performing the methods of the present invention, such as automatically post-processing digital content for sensitive data segments for different content consumer groups using content processing module 150. In addition to block 150, computing environment 100 includes, for example, computer 101, wide area network (WAN) 102, end user device (EUD) 103, remote server 104, public cloud 105, and private cloud 106. In this embodiment, computer 101 includes processor group 110 (including processing circuit 120 and cache 121), communication structure 111, volatile memory 112, permanent storage device 113 (including operating system 122 and block 150, as described above), peripheral device group 114 (including user interface (UI) device group 123, storage device 124, and Internet of Things (IoT) sensor group 125), and network module 115. Remote server 104 includes remote database 130. The public cloud 105 includes a gateway 140 , a cloud coordination module 141 , a host physical machine group 142 , a virtual machine group 143 , and a container group 144 .

[0026] Computer 101 may take the form of a desktop computer, laptop computer, tablet computer, smart phone, smart watch or other wearable computer, mainframe computer, quantum computer, or any other form of computer or mobile device now known or developed in the future that is capable of running programs, accessing a network, or querying a database such as remote database 130. As is well known in the art of computer technology, and depending on the technology, the performance of computer-implemented methods may be distributed among multiple computers and / or among multiple locations. On the other hand, in this presentation of computing environment 100, the detailed discussion focuses on a single computer, particularly computer 101, to keep the presentation as simple as possible. Computer 101 may be located in the cloud, even though it is not yet fully understood. Figure 1 1 is not shown in the cloud, on the other hand, computer 101 need not be in the cloud except to any extent that can be positively indicated.

[0027] Processor group 110 includes one or more computer processors of any type known now or to be developed in the future. Processing circuit 120 can be distributed over multiple packages, such as multiple coordinated integrated circuit chips. Processing circuit 120 can implement multiple processor threads and / or multiple processor cores. Cache 121 is a memory located in the processor chip package, and is generally used for data or code that should be available for rapid access by threads or cores running on processor group 110. Cache memory is generally organized into multiple levels according to relative proximity to the processing circuit. Alternatively, some or all of the caches of the processor group may be located "off chip". In some computing environments, processor group 110 may be designed to work with qubits and perform quantum computing.

[0028] Computer readable program instructions are typically loaded onto computer 101 to cause processor group 110 of computer 101 to perform a series of operating steps to implement a computer-implemented method, such that the instructions so executed will instantiate the method specified in the flow chart and / or the narrative description of the computer-implemented method included in this document (collectively referred to as "the present method"). These computer readable program instructions are stored in various types of computer readable storage media, such as cache 121 and other storage media discussed below. The program instructions and related data are accessed by processor group 110 to control and direct the execution of the present method. In computing environment 100, at least some instructions for executing the present method may be stored in permanent storage device 113 in block block 150.

[0029] Communications fabric 111 is the signaling pathways that allow the various components of computer 101 to communicate with each other. Typically, the fabric is comprised of switches and conductive pathways, such as those that make up a bus, a bridge, physical input / output ports, etc. Other types of signal communication pathways may be used, such as fiber optic communication pathways and / or wireless communication pathways.

[0030] The volatile memory 112 is any type of volatile memory now known or developed in the future. Examples include dynamic random access memory (RAM) or static RAM. Typically, the volatile memory 112 is characterized by random access, but this is not required unless expressly stated. In the computer 101, the volatile memory 112 is located in a single package and is internal to the computer 101, but, alternatively or additionally, the volatile memory can be distributed in multiple packages and / or located externally relative to the computer 101.

[0031] Permanent memory 113 is any form of non-volatile memory for computers known now or developed in the future. The non-volatility of the memory means that the stored data is maintained regardless of whether power is supplied to the computer 101 and / or directly to the permanent memory 113. Permanent memory 113 can be a read-only memory (ROM), but usually at least a portion of the permanent memory allows the writing of data, the deletion of data, and the rewriting of data. Some common forms of persistent storage devices include disks and solid-state storage devices. Operating system 122 can take several forms, such as various known proprietary operating systems or operating systems of the open source portable operating system interface type using a kernel. The code included in block 150 is generally included in at least some of the computer codes involved in executing the method of the present invention.

[0032] The peripheral device group 114 includes a collection of peripheral devices of the computer 101. The data communication connection between the peripheral devices and other components of the computer 101 can be implemented in various ways, such as a Bluetooth connection, a near field communication (NFC) connection, a connection made by a cable (such as a universal serial bus (USB) type cable), a plug-in type connection (e.g., a secure digital (SD) card), a connection made through a local area communication network, and even a connection made through a wide area network such as the Internet. In various embodiments, the UI device group 123 may include components such as a display screen, a speaker, a microphone, a wearable device (such as goggles and smart watches), a keyboard, a mouse, a printer, a touchpad, a game controller, and a tactile device. The storage device 124 is an external storage device, such as an external hard drive, or a pluggable storage device, such as an SD card. The storage device 124 can be permanent and / or volatile. In some embodiments, the storage device 124 can take the form of a quantum computing storage device for storing data in the form of quantum bits. In embodiments where the computer 101 needs to have a large amount of storage (e.g., where the computer 101 locally stores and manages a large database), the storage may be provided by a peripheral storage device designed to store very large amounts of data, such as a storage area network (SAN) shared by multiple geographically distributed computers. The IoT sensor group 125 is composed of sensors that can be used in IoT applications. For example, one sensor may be a thermometer, while another sensor may be a motion detector.

[0033] The network module 115 is a set of computer software, hardware and firmware that allows the computer 101 to communicate with other computers through the WAN 102. The network module 115 may include hardware such as a modem or a Wi-Fi signal transceiver, software for packetizing and / or depacketizing data transmitted over a communication network, and / or web browser software for transmitting data over the Internet. In some embodiments, the network control function and the network forwarding function of the network module 115 are executed on the same physical hardware device. In other embodiments (e.g., embodiments utilizing software defined networks (SDN)), the control function and the forwarding function of the network module 115 are executed on physically separated devices so that the control function manages several different network hardware devices. Computer-readable program instructions for executing the method of the present invention can generally be downloaded to the computer 101 from an external computer or an external storage device via a network adapter card or a network interface included in the network module 115.

[0034] WAN 102 is any wide area network (e.g., the Internet) capable of transmitting computer data over non-local distances by any technology now known or developed in the future for transmitting computer data. In some embodiments, WAN 102 may be replaced and / or supplemented by a local area network (LAN) designed to transmit data between devices located in a local area, such as a Wi-Fi network. WANs and / or LANs typically include computer hardware, such as copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and edge servers.

[0035] End-user device (EUD) 103 is any computer system used and controlled by an end-user (e.g., a customer of an enterprise operating computer 101), and may take any of the forms discussed above in connection with computer 101. EUD 103 typically receives useful and useful data from the operation of computer 101. For example, in the hypothetical case where computer 101 is designed to provide recommendations to an end-user, the recommendations would typically be transmitted from network module 115 of computer 101 to EUD 103 via WAN 102. In this manner, EUD 103 may display or otherwise present the recommendations to the end-user. In some embodiments, EUD 103 may be a client device, such as a thin client, a heavy client, a mainframe computer, a desktop computer, or the like.

[0036] Remote server 104 is any computer system that provides at least some data and / or functionality to computer 101. Remote server 104 may be controlled and used by the same entity that operates computer 101. Remote server 104 represents a machine that collects and stores helpful and useful data for use by other computers, such as computer 101. For example, in the hypothetical case where computer 101 is designed and programmed to provide recommendations based on historical data, then the historical data may be provided to computer 101 from remote database 130 of remote server 104.

[0037] The public cloud 105 is any computer system available for use by multiple entities that provides on-demand availability of computer system resources and / or other computer capabilities, particularly data storage (cloud storage) and computing capabilities, without direct active management by users. Cloud computing typically leverages the sharing of resources to achieve consistency and economy of scale. The direct and active management of the computing resources of the public cloud 105 is performed by computer hardware and / or software of the cloud coordination module 141. The computing resources provided by the public cloud 105 are typically implemented by virtual computing environments running on various computers that constitute the host physical machine set 142, which is the universe of physical computers in the public cloud 105 and / or available for the public cloud. Virtual computing environments (VCEs) typically take the form of virtual machines from a virtual machine group 143 and / or containers from a container group 144. It should be understood that these VCEs can be stored as images and can be transferred between various physical machine hosts as images or after instantiation of the VCEs. The cloud coordination module 141 manages the transmission and storage of images, deploys new instantiations of VCEs, and manages active instantiations of VCE deployments. Gateway 140 is a collection of computer software, hardware, and firmware that allows public cloud 105 to communicate over WAN 102 .

[0038] A further explanation about Virtualized Computing Environments (VCEs) will now be provided. VCEs can be stored as "images". A new active instance of a VCE can be instantiated from an image. Two familiar types of VCEs are virtual machines and containers. A container is a type of VCE that uses operating system-level virtualization. This refers to an operating system feature in which the kernel allows the existence of multiple isolated userspace instances, called containers. These isolated userspace instances typically behave like real computers from the perspective of the programs running inside them. Computer programs running on a normal operating system can utilize all of that computer's resources, such as connected devices, files and folders, network shares, CPU power, and quantifiable hardware capabilities. However, programs running inside a container can only use the contents of the container and the devices assigned to the container, a feature known as containerization.

[0039] The private cloud 106 is similar to the public cloud 105, except that the computing resources are only available to a single enterprise. Although the private cloud 106 is depicted as communicating with the WAN 102, in other embodiments, the private cloud can be completely disconnected from the Internet and can only be accessed through a local / private network. A hybrid cloud is a combination of multiple clouds of different types (e.g., private, community, or public cloud types), typically implemented by different vendors. Each of the multiple clouds remains a separate and discrete entity, but the larger hybrid cloud architecture is bound together by standardized or proprietary technologies that enable coordination, management, and / or data / application portability between the multiple constituent clouds. In this embodiment, the public cloud 105 and the private cloud 106 are both part of a larger hybrid cloud.

[0040] According to this embodiment, the computer environment 100 can use the content processing module 150 to automatically post-process the digital content of the sensitive data segments according to different content consumer groups. Figure 2 and 3 Explain content handling methods in more detail.

[0041] Reference now Figure 2 , describes an operational flow diagram illustrating an exemplary content processing process 200 used by content processing module 150 in accordance with at least one embodiment.

[0042] At 202, the content processing module 150 constructs a sensitive statement classification model (SSCM) (e.g., a classification model). The content processing module 150 may construct the SSCM (e.g., a classification model) to enable identification of sensitive data segments within digital content specifically based on the roles of both speaker and / or consumer groups within an organization. The organization may be a commercial entity, a non-profit organization, an educational institution, or any other organization that may utilize online software to conduct meetings among constituent members. Constituent members may include content producers (e.g., management, organizational leaders, professors, teachers) and content consumers (e.g., employees, volunteers, students), and content producers may be speakers and / or constituent members of the organization presenting within the meeting. Content consumers may be organizational participants for whom digital content may be produced. Content consumers may also include consumers outside the organization, such as clients and / or the public. In Figure 3 The training process that may be involved in building a SSCM (e.g., a classification model) may be described in more detail in .

[0043] The content processing module 150 may utilize one or more language analysis techniques and / or one or more deep learning models with one or more existing sensitive word datasets and / or customized training datasets to identify audio and / or visual content within the organization's digital media content that may contain sensitive words and / or sensitive visual content when building an SSCM (e.g., a classification model). One or more sensitive words may be generally identified using one or more existing sensitive word datasets, and / or may be identified using a customized training dataset used when building an SSCM (e.g., a classification model) to specifically identify one or more sensitive words related to a consumer persona setting. As will be described below and Figure 3 As explained in more detail in , one or more existing sensitive word datasets can be derived from one or more publicly available datasets, and the customized training dataset can be based on at least predefined consumer data, consumer roles, sensitive words, and other data.

[0044] The one or more language analysis techniques may include, but are not limited to, machine learning models including Natural Language Processing (NLP), Latent Dirichlet Allocation (LDA), Speech to Text, Hidden Markov Models (HMM), N-grams, Speaker ID (SD), Semantic Text Similarity (STS), keyword extraction, and other analysis techniques such as those described in IBM (IBM Watson and all Watson-based trademarks are trademarks or registered trademarks of International Business Machines Corporation in the United States and / or other countries), IBM Speech to Text, IBM Tone Analyzer, IBM Natural Language Understanding and IBM Natural Language Classifiers and Other Implementations As will be described in greater detail below, one or more language analysis techniques may be utilized in generating a text transcript of audio content, which may be filtered using a SSCM (eg, a classification model).

[0045] The one or more deep learning models that may be utilized by the content processing module 150 may include, but are not limited to, convolutional neural networks (CNNs) and other image recognition neural network deep learning models for images, objects, and / or other visual content. As will be described in more detail below, one or more deep learning models may be used to identify visual content that may be filtered using an SSCM (e.g., a classification model). CNNs may also be used for processing during the training process of an SSCM (e.g., a classification model), which will be described below and Figure 3 Described in more detail in .

[0046] The content processing module 150 can utilize the above-mentioned one or more language analysis techniques and / or one or more deep learning models when extracting meaning and / or metadata from unstructured text data. Unstructured text data may include organizational information received from an organization. Organizational information may include, but is not limited to, internal documents, organizational directories, management chains, job descriptions, employee titles, user profiles, text files, audio files, and / or video files, as well as other organizational information. The content processing module 150 may not utilize one or more language analysis techniques in performing text analysis on the unstructured text data received from the organization and / or any other data until consent is received from the organization and / or an authorized user within the organization. The content processing module 150 utilizing one or more language analysis techniques may at least extract categories, concepts, classifications, metadata, entities, keywords, emotions, semantic roles, emotions, relationships, and / or syntax.

[0047] The content processing module 150 can additionally utilize multiple manually identified spoken language examples, including sensitive and non-sensitive content that builds a customized training data set. The content processing module 150 can utilize a template (e.g., a base text) and utilize one or more language analysis techniques to identify entities and / or keywords in the template (e.g., a base text). In addition, the content processing module 150 can generate a variation of the template (e.g., a base text) by replacing entities and / or keywords in the base text (e.g., a template) with synonyms and / or antonyms. The content processing module 150 can perform preprocessing of changes in templates (e.g., base text) and sensitive and / or non-sensitive content received from an existing data set. The content processing module 150 can use an NLP model, such as but not limited to a Word2Vec model, to preprocess the input. The NLP model can utilize a text corpus as input and generate an output that can be classified as a sensitive or insensitive sentence by a CNN. For example, the content processing module 150 may utilize a Word2Vec model, which may accept a text corpus as input and output a vector representation of each word of the text corpus as output, which may be classified by a CNN as sensitive or insensitive.

[0048] The content processing module 150 may also utilize consumer role settings when building an SSCM (e.g., a classification model). The consumer role settings may be based on a hierarchical structure of an organization. The hierarchical structure of an organization may be created based on a hierarchical analysis of the organization, which utilizes at least the organizational information described in detail above and other data provided to the content processing module 150 by the organization. The content processing module 150 may not perform a hierarchical analysis of the organization before receiving consent from the organization and / or an authorized user of the organization. The content processing module 150 may utilize one or more tools and / or techniques, such as, but not limited to, the Galton-Watson branching process, the lightweight directory access protocol (LDAP), and other hierarchical analysis techniques to perform a hierarchical analysis of the organization. The hierarchical structure of an organization may be a directory information tree (DIT) showing the positions of multiple users within an organization relative to each other. The hierarchical structure may be used to specify information that may be considered sensitive to a group of multiple consumers based on the role of each group within the organization. For example, compensation information may be considered sensitive to consumers within the sales group of an organization, but not to consumers working within the payroll group of the organization, such that the SSCM (e.g., classification model) may block compensation discussions within digital content for the sales group but not for the payroll group. Another example may involve an organization's goal of maintaining trade secrets, such that information such as formulas, practices, processes, designs, tools, patterns, and / or compilations of information may be considered sensitive to different groups within multiple consumers.

[0049] The SSCM (e.g., classification model) may also be used to block and / or mask visual content identified by the one or more deep learning models described above within the digital content. For example, in an internal meeting within an organization, the content processing module 150 may use one or more deep learning models to identify one or more numbers within a screen sharing overlay. In this example, the SSCM (e.g., classification model) may mask and / or block annual income numbers within one or more numbers that are determined to be sensitive numbers for at least a portion of the content consumers.

[0050] As will be explained in more detail below, consumer role settings may include predefined consumer data, such as roles and sensitive words, which may be used by the SSCM (e.g., classification model) to generate the desired output to the processed content database. For example, the predefined consumer data for the XXX manager may include:

[0051] {

[0052] "Keywords": ["confidential", "contract", "XXX company", "transaction"],

[0053] "Role": ["XXX Manager"]

[0054] }

[0055] In another embodiment, content may be sensitive at one time, but not sensitive at a later time. As will be explained in more detail below, content producers (e.g., administration, organizational leadership, professors, teachers) may specify different blackout times for different groups of content consumers. For example, a professor may produce digital content intended for a teacher's assistant and a group of students before an exam. The digital content may only be partially available to the students before the exam, but may be fully available after the exam.

[0056] At 204, the content processing module 150 receives digital content. The content processing module 150 may receive digital content, which may be produced by a content producer (e.g., an administrator, an organizational leader, a professor, a teacher) for one or more content consumer groups (e.g., employees, volunteers, students). The content processing module 150 may receive the digital content in at least an Internet browser, a dedicated software application, and / or as an integration with a third-party software application. The third-party software application may include web conferencing and / or video recording software used by the organization when conducting meetings, announcements, and / or generating and / or distributing digital content to content consumers (e.g., employees, volunteers, students).

[0057] Digital content can be produced for one or more content consumer groups. A content producer (e.g., management, organizational leadership, professor, teacher) can identify one or more content consumer groups (e.g., employees, volunteers, students) for which digital content is intended in a user interface displayed in at least an Internet browser, a dedicated software application, and / or a third-party software application. The content processing module 150 can also identify one or more content consumer groups for which content is intended based on the hierarchical structure of the organization generated in step 202. As will be explained in more detail below, the content processing module 150 can utilize a content extractor to extract at least audio and / or visual content from the received digital content. Then, an SSCM (e.g., a classification model) can be used to identify sensitive data fragments in the audio and / or visual content corresponding to one or more content consumer groups. As will be explained in more detail below with reference to step 206, a content producer (e.g., management, organizational leadership, professor, teacher) can also manually trigger content shielding and / or blocking in the user interface. A content producer can manually select at least one of the one or more groups in the user interface during the production of digital content for a specific fragment, and the specific fragment can be automatically stored in the processed content database by the content processing module 150.

[0058] At 206, the content processing module 150 processes the digital content. The content processing module 150 may use the SSCM (e.g., classification model) and two or more content databases to process the digital content of each content consumer group. The two or more content databases may include at least an original content database and a processed content database. The two or more content databases may be maintained by the content processing module within the database 130. The original content database may store the digital content in the original form recorded by the content producer. The processed content database may store sensitive data fragments identified by the SSCM (e.g., classification model) and their corresponding consumer roles.

[0059] The digital content may include at least audio and / or video content. The content processing module 150 may utilize one or more language analysis techniques such as speech to text when generating a text transcription of the audio content, which may be filtered using SSCM (e.g., a classification model) when identifying sensitive content. The content processing module 150 may utilize one or more language analysis techniques such as speech to text and / or one or more deep learning models to employ visual analysis techniques such as image and / or object recognition when identifying visual content that may be filtered using SSCM (e.g., a classification model). For example, during a product presentation, when a content producer shares their screen with a customer, sensitive visual content may be detected. The content producer may forget to close one or more internal confidential documents. In this instance, once the content processing module 150 detects that a document contains the keyword "confidential", the content processing module 150 may shield and / or block the one or more internal confidential documents to ensure that sensitive data is not leaked. The content processing module 150 may store the content identified in the audio and / or visual content in a processed content database, which may contain sensitive information based on SSCM (e.g., a classification model).

[0060] The processed content database may store the output of the SSCM (e.g., classification model). The content processing module 150 may store sensitive data segments according to data type, timestamp / location within the digital content, and / or corresponding consumer role. For example, the content processing module 150 may store sensitive audio segments in the processed content database using the following:

[0061] {

[0062] "type": "audio",

[0063] "Start time": "00:01:23",

[0064] "End time": "00:01:59",

[0065] "Keywords": ["profit", "cost"],

[0066] "Applicable roles": ["general public", "non-employee"]

[0067] }

[0068] and sensitive video segments in the processed content database using:

[0069] {

[0070] "type": "video",

[0071] "Start time": "00:10:23",

[0072] "End time": "00:10:44",

[0073] "Keywords": ["confidential", "contract", "XXX company", "transaction"],

[0074] "Applicable roles": ["XXX Manager"]

[0075] }

[0076] The content processing module 150 may also store one or more sensitive data segments manually identified by the producer in the processed content database. In addition, the content processing module 150 may use one or more language analysis techniques described in step 202 to identify additional content segments that may be similar to the one or more data segments identified by the producer. The content processing module 150 may present to the producer in a user interface a list of sensitive data segments that are manually identified and / or identified by the content processing module 150 for each group within the content consumers (e.g., employees, volunteers, students). The content producer (e.g., management, organizational leadership, professor, teacher) may edit and / or approve each of the one or more sensitive data segments for each group.

[0077] As will be explained in more detail below with respect to step 208, the content processing module may utilize digital content stored in the original content database and sensitive data segments stored in the processed content database when generating the consumer-specific digital content.

[0078] In another embodiment, the content processing module 150 may take advantage of the delay in processing digital content so that the digital content can be received in real time and processed using the SSCM (e.g., a classification model) during the intermediate delay, so that the content processing module 150 can be used for digital content intended for replay as well as digital content intended for real-time consumption, such as organizing a meeting.

[0079] At 208, the content processing module 150 generates consumer specific digital content. The content processing module 150 may generate consumer specific digital content for each consumer group according to the consumer role settings.

[0080] The content processing module 150 can generate consumer-specific digital content for each of the one or more consumer groups by retrieving the original form of digital content recorded by the content producer from the original content database and one or more sensitive data segments (including timestamps, corresponding consumer roles and / or associated data) stored in the processed content database. Therefore, the content processing module 150 can determine which video objects and / or audio time periods may need to be masked and / or blocked for each of the one or more consumer groups.

[0081] The content processing module 150 may mask and / or block audio and / or visually sensitive data segments using the output content processor. The output content processor may mask and / or block audio and / or visually sensitive data segments, hide identified keywords in the digital content transcription, mute the sound for a period of time associated with the audio sensitive data segment, remove the entire segment from the digital content, scramble, replace, and otherwise mask and / or block the digital content.

[0082] The content processing module 150 may also utilize the output content processor to send and / or display consumer-specific content to each of the plurality of consumers according to the consumer grouping in the user interface presented by the Internet browser, the dedicated software application, and / or the third-party software application as described in detail above with respect to step 204. The content processing module 150 may also generate a unique download link for each content consumer to download via http, https, and / or ftp. The content processing module 150 may receive approval for each version of the consumer-specific content generated from the content producer (e.g., management, organizational leadership, professor, teacher) and / or another authorized party within the organization before transmitting and / or displaying the consumer-specific content. The content processing module 150 may also require content consumer group verification before enabling the content consumer to view. The content processing module 150 may receive consumer group verification based on a consumer profile associated with the device, a consumer profile associated with the Internet browser, the software application, and / or the third-party application, and / or a manual selection made by the consumer in the user interface.

[0083] The content processing module 150 may also enable content consumers to manually mark sensitive content within consumer-specific content. The content processing module 150 may request additional feedback from the consumer regarding the identified sensitive content and store the sensitive data segments and associated data in a customized training data set. The content processing module 150 may utilize the identified additional sensitive data segments when retraining the SSCM (e.g., a classification model), the training process of which will be described below with reference to Figure 3 Describe in more detail.

[0084] Reference now Figure 3 , provides a method for illustrating the use of at least one embodiment Figure 2 Block diagram and flow chart of the training process of SSCM (e.g., classification model) for some components discussed in .

[0085] As described in detail above at least with respect to step 202, building a sensitive sentence classification model (SSCM) 310 (e.g., a classification model) to enable identification of sensitive data segments within digital content based specifically on the roles of both speakers and / or consumer groups within an organization includes a training process that begins with a customized training dataset 302 and an existing dataset 304.

[0086] The customized training data set 302 can be constructed based on at least predefined consumer data, consumer roles, sensitive words, and other data that can be extracted using one or more language analysis techniques described in detail in step 202. One or more language analysis techniques can extract meaning and / or metadata from unstructured text data received from an organization, such as the organizational information described in step 202. The one or more language analysis techniques can use text analysis to extract meaning and / or metadata to identify entities from the organizational information, such as but not limited to consumers, producers, companies, organizations, cities, geographic features, and / or other entities. In addition, such as IBM Language analysis technology such as IBM and all Watson-based trademarks are trademarks or registered trademarks of International Business Machines Corporation in the United States and / or other countries) can be used to extract keywords associated with each identified entity. The identified entities and keywords can be manually identified as sensitive or insensitive, and are used to generate variations by changing the entities and / or keywords using synonyms or antonyms. The customized training data set 302 includes the identified entities and keywords and the generated variations. The existing data set 304 can be constructed using one or more existing sensitive word data sets derived from one or more publicly available data sets.

[0087] The custom training dataset 302 and the existing dataset 304 can then be provided as input to an NLP model, such as the Word2Vec model 306 described for preprocessing. The preprocessing of the custom training dataset 302 and the existing dataset 304 by the Word2Vec algorithm can utilize a neural network model to learn sensitive or insensitive word associations from the training dataset so that the word embeddings output by the algorithm can achieve vector grouping of similar words. In the case of audio content, the training process may require an additional speech-to-text step, which can be performed using IBM Speech-to-text (IBM Watson and all Watson-based trademarks are trademarks or registered trademarks of International Business Machines Corporation in the United States and / or other countries).

[0088] Then, a convolutional neural network (CNN) 308 can be used for sentence classification. CNN 308 can utilize an n×k representation of a sentence, where n is the number of words and k is the number of vectors for each word. CNN can additionally utilize static and non-static channels, convolutional layers with multiple filter widths and feature maps, maximum time pooling, and fully connected layers with information loss and SoftMax output to determine whether a sentence is a sensitive sentence or a non-sensitive sentence.

[0089] Thus, the digital content for each content consumer group may be automatically processed using the SSCM 310 (eg, a classification model) such that sensitive data segments may be masked and / or blocked according to different content consumer groups.

[0090] Understandably, Figure 2 and 3 Only a description of one embodiment is provided without implying any limitation on how different embodiments may be implemented.Many modifications may be made to the described embodiments based on design and implementation requirements.

[0091] Various aspects of the present disclosure are described by narrative text, flow charts, block diagrams of computer systems, and / or block diagrams of machine logic included in computer program product (CPP) embodiments. With respect to any flow chart, depending on the technology involved, the operations may be performed in an order different from the order shown in a given flow chart. For example, again depending on the technology involved, two operations shown in consecutive flow chart blocks may be performed in reverse order, as a single integrated step, simultaneously, or in a manner that at least partially overlaps in time.

[0092] Computer program product embodiments ("CPP embodiments" or "CPP") are terms used in this disclosure to describe any collection of one or more storage media (also referred to as "media") collectively included in a collection of one or more storage devices that collectively include machine-readable code corresponding to instructions and / or data for performing the computer operations specified in a given CPP claim. A "storage device" is any tangible device that can hold and store instructions for use by a computer processor. Without limitation, a computer-readable storage medium may be an electronic storage medium, a magnetic storage medium, an optical storage medium, an electromagnetic storage medium, a semiconductor storage medium, a mechanical storage medium, or any suitable combination of the foregoing. Some known types of storage devices that include these media include: magnetic disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), static random access memories (SRAM), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), memory sticks, floppy disks, mechanical encoding devices (such as punch cards or pits / land formed in a major surface of a disk), or any suitable combination of the foregoing. Computer-readable storage media, as that term is used in this disclosure, should not be construed as storing in the form of transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides, light pulses through fiber optic cables, electrical signals transmitted through wires, and / or other transmission media. As will be appreciated by those skilled in the art, data is typically moved at certain occasional points in time during normal operation of the storage device, such as during access, defragmentation, or garbage collection, but this does not make the storage device transitory because the data is not transitory while it is stored.

[0093] The description of various embodiments of the present invention has been given for the purpose of illustration, but it is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical application or technical improvement over existing technologies on the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

[0094] This disclosure should not be construed as violating or encouraging the violation of any local, state, federal, or international laws regarding privacy protection.

Claims

1. A method for processing digital content, the method comprising: Build a sensitive sentence classification model; receiving digital content, wherein the digital content is intended for one or more groups of content consumers; Processing the digital content using the sensitive sentence classification model; as well as Consumer-specific digital content is generated for each of the one or more groups of content consumers.

2. The method according to claim 1, wherein: Building the sensitive sentence classification model also includes: The sensitive sentence classification model is trained using a customized training dataset and an existing dataset.

3. The method according to claim 2, wherein: The customized training dataset includes keywords and entities derived from organizational information, and wherein the existing dataset includes one or more existing sensitive word datasets derived from one or more publicly available resources.

4. The method according to claim 2, wherein: The customized training dataset and the existing dataset are preprocessed using the Word2Vec algorithm.

5. The method according to claim 1, wherein: The one or more content consumer groups are identified by a content producer within a user interface.

6. The method according to claim 1, wherein processing the digital content using the sensitive sentence classification model further comprises: storing the digital content received in its original form in an original content database; Identify one or more sensitive data segments using the sensitive sentence classification model; as well as The one or more sensitive data segments are stored in a processed content database according to at least one or more of a data type, a timestamp, or a corresponding consumer role, wherein the corresponding consumer role includes at least one of the one or more content consumer groups.

7. The method of claim 6, wherein identifying the one or more sensitive data segments further comprises: receiving one or more additional sensitive data segments manually identified by a content producer; as well as The one or more additional sensitive data segments are stored in the processed content database.

8. The method according to claim 1, further comprising: allocating a plurality of consumers within the organization to the one or more content consumer groups based on a hierarchical structure of the organization constructed according to an analysis of the organization information; as well as The consumer-specific digital content is displayed to a plurality of consumers, wherein each of the plurality of consumers is able to access the consumer-specific digital content corresponding to their content consumer group.

9. A computer system for processing digital content, comprising: One or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one tangible storage medium of the one or more tangible storage media for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising: Build a sensitive sentence classification model; receiving digital content, wherein the digital content is intended for one or more groups of content consumers; Processing the digital content using the sensitive sentence classification model; and Consumer-specific digital content is generated for each of the one or more groups of content consumers.

10. The computer system according to claim 9, wherein: Building the sensitive sentence classification model also includes: Program instructions stored on at least one of the one or more computer-readable storage media are used to be executed by at least one of the one or more processors via at least one of the one or more memories to train the sensitive sentence classification model using a customized training data set and an existing data set.

11. The computer system according to claim 10, wherein: The customized training dataset includes keywords and entities derived from organizational information, and wherein the existing dataset includes one or more existing sensitive word datasets derived from one or more publicly available resources.

12. The computer system according to claim 10, wherein: The Word2Vec algorithm is used to preprocess the customized training dataset and the existing dataset.

13. The computer system according to claim 9, wherein: The one or more content consumer groups are identified by a content producer within a user interface.

14. The computer system of claim 9, wherein processing the digital content using the sensitive sentence classification model further comprises: program instructions stored on at least one of the one or more computer-readable storage media for execution by at least one of the one or more processors via at least one of the one or more memories to store the digital content received in its original form in an original content database; program instructions stored on at least one of the one or more computer-readable storage media for execution by at least one of the one or more processors via at least one of the one or more memories to identify one or more sensitive data segments using the sensitive sentence classification model; as well as Program instructions stored on at least one of the one or more computer-readable storage media are for execution by at least one of the one or more processors via at least one of the one or more memories to store the one or more sensitive data fragments in a processed content database based on at least one or more of a data type, a timestamp, or a corresponding consumer role, wherein the corresponding consumer role includes at least one of the one or more content consumer groups.

15. The computer system of claim 14, wherein identifying the one or more sensitive data segments further comprises: program instructions stored on at least one of the one or more computer-readable storage media for execution by at least one of the one or more processors via at least one of the one or more memories to receive one or more additional sensitive data segments manually identified by a content producer; as well as Program instructions stored on at least one of the one or more computer-readable storage media are configured to be executed by at least one of the one or more processors via at least one of the one or more memories to store the one or more additional sensitive data segments in the processed content database.

16. A computer program product for processing digital content, comprising: One or more computer-readable storage media, and program instructions stored together on the one or more computer-readable storage media, the program instructions comprising: Build a sensitive sentence classification model; receiving digital content, wherein the digital content is intended for one or more groups of content consumers; Processing the digital content using the sensitive sentence classification model; and Consumer-specific digital content is generated for each of the one or more groups of content consumers.

17. The computer program product according to claim 16, wherein constructing the sensitive sentence classification model further comprises: The program instructions stored on at least one computer-readable storage medium of the one or more computer-readable storage media are used to train the sensitive sentence classification model using a customized training data set and an existing data set.

18. The computer program product of claim 17, wherein: The customized training dataset includes keywords and entities derived from organizational information, and wherein the existing dataset includes one or more existing sensitive word datasets derived from one or more publicly available resources.

19. The computer program product of claim 17, wherein: The customized training dataset and the existing dataset are preprocessed using the Word2Vec algorithm.

20. The computer program product of claim 16, wherein processing the digital content using the sensitive sentence classification model further comprises: program instructions stored on at least one of the one or more computer-readable storage media for storing the digital content received in its original form in an original content database; program instructions stored on at least one of the one or more computer-readable storage media for identifying one or more sensitive data segments using the sensitive sentence classification model; as well as Program instructions stored on at least one of the one or more computer-readable storage media are used to store the one or more sensitive data segments in a processed content database based on at least one or more of a data type, a timestamp, or a corresponding consumer role, wherein the corresponding consumer role includes at least one of the one or more content consumer groups.

Images