Dynamic determination of digital content retention period

Abstract

Provided are computer program products, systems, and methods for dynamically determining a retention period for digital content. Metadata is generated for an instance of digital content including access patterns of the digital content by a user of a computing device, attributes of the digital content, and a retention period for which the stored digital content is to be retained in storage. A machine learning module is trained with inputs including the metadata for the instance of digital content to generate a retention period for the digital content. Inputs received after training of the machine learning module including the determined metadata from the digital content are provided to the machine learning module to generate an output retention period for the received digital content after training. The output retention period is used to determine when to remove the received digital content from storage after training.

Description

Technical Field

[0001] The present invention relates to a computer program product, a system, and a method for dynamically determining the retention period of digital content.

Background Art

[0002] Portable computing devices such as smartphones and tablets have limited storage capacity. Portable computing devices often have file-sharing applications, chat applications, social media applications, etc. installed, and receive and transmit messages with digital content such as photos, videos, web pages, etc. attached. If the number of attached files received with messages increases rapidly, the storage of the portable computing device may be used to its maximum. Furthermore, when digital media files are added, the capacity of the attached cloud storage may also reach its limit. A user who notices that the storage has reached the limit level may need to manually delete files to free up space, but this takes a very long time and can result in an overall unpleasant user experience.

[0003] There is a need in the art for an improved technique for managing the retention of files in storage, such as digital media files received through messages and file-sharing applications.

Summary of the Invention

[0004] The provided offerings are a computer program product, system, and method for dynamically determining the retention period of digital content. Metadata is generated for instances of digital content stored on a computing device, including user access patterns of the digital content, attributes of the digital content, and the retention period for which the stored digital content is retained in storage. A machine learning module is trained using input containing the metadata of the digital content instance to generate the retention period of the digital content. Input containing the metadata determined from the digital content, received after the training of the machine learning module, is provided to the machine learning module to generate an output retention period for the digital content received after training. The output retention period is used to determine when to delete the digital content received after training from storage. [Brief explanation of the drawing]

[0005] [Figure 1] This figure shows one embodiment of a computing device in which digital content is managed. [Figure 2] This figure shows one embodiment of data content metadata. [Figure 3] This figure shows one embodiment of an instance of the retention period for digital content. [Figure 4] This figure shows one embodiment of the operation for determining the retention period of received digital content. [Figure 5] This diagram shows one embodiment of an operation for managing digital content with respect to quarantine and deletion periods. [Figure 6] This figure shows one embodiment of an operation that handles user access to digital content, including requests for reviewing digital content and removing digital content from quarantine. [Figure 7] This figure shows one embodiment of the process of training a retention machine learning module (MLM). [Figure 8]This figure shows one embodiment of an operation for processing user deletion of digital media content. [Figure 9] This figure shows a computing environment in which the components shown in Figure 1 can be implemented. [Modes for carrying out the invention]

[0006] The described embodiments provide an improvement in computer technology for managing the retention of digital content received by computing devices, such as portable computing devices, in the storage of those computing devices. As file sharing becomes more widespread through messaging and file-sharing applications, local and cloud storage used by portable computing devices receiving communications may reach its storage capacity limits. The described embodiments provide an improved technique for assigning retention periods to digital content, including multiple instances of digital content attached to a message, based on the access patterns and attributes of the digital content. In the described embodiments, a retention machine learning module is trained on inputs that include metadata of digital content in a training set of digital content, and generates retention periods for digital content as output. Subsequently, when digital content is received through messaging, file sharing, etc., the retention machine learning module may be used to determine the retention period of the digital content based on the metadata and classification of the digital content. The determined retention period can then be used to determine when to expire and delete the digital content. In this way, because retention periods can be assigned to received digital content using a retention machine learning module based on the metadata and classification of digital content, users do not need to periodically manually delete files received in communications.

[0007] Figure 1 shows a computing device 100 in which an embodiment is implemented. The computing device 100 includes a processor 102 and main memory 104. The main memory 104 includes various program components and data structures, including an operating system 108 that manages the operation of the system 100 and the flow of operations between components, and a retention manager 110 that manages the overall flow of operations for determining the retention period for holding and storing received digital content 112 in digital content storage 114. The retention manager 110 provides the received digital content 112 to a content parser 116, and the segment 118 in which the digital content has been parsed i If such, the analyzed segments 1181, 1182...118 include different files or parts of the digital content 112. n The content is then analyzed. For example, if digital content 112 contains a message, the message may have one or more attachments of different files in different media formats. The message and attachments are analyzed into segments 1181, 1182...118. n This includes. Furthermore, the digital content 112 may include a compressed file having multiple segments 118 or different files.

[0008] The analyzed segment 118 or single digital content 112 file can be annotated and classified by ML analysis tools 1201, 1202...120 m The selection of machine learning (ML) analysis tools is provided to the selection module 120. For example, segment 118 i Alternatively, if the digital content 112 consists of text, the ML analysis tool 1201 will analyze the input segment 118 iOr it may include a natural language processor (NLP), such as the Watson (trademark) Natural Language Processor program, for determining the classification of digital content 112. In the case of other types of media formats, different ML analysis tools 1202... 120 and classification programs are used to classify digital content 112 or segment 118 i from different media formats (such as still images, videos, audio, etc.) into one or more classifiers such as image and video analysis, deep learning. The result of the ML analysis tool selection 120 is the analyzed segments 1181, 1182... 118 n or one or more segment classifications 1221, 1222... 122 that provide machine learning classifications of the content of digital content 112 n The segment classification 122 includes. Classifications 1221, 1222... 122 n may include hashtags, text, or other classification codes. (Watson is a trademark of International Business Machines Corporation worldwide).

[0009] The digital content 112 is further provided to the metadata manager 124, and for each of the analyzed segments 118 i a single digital content 112 or a metadata instance 200 i of the digital content metadata 200 (Figure 2) is generated. Segment classifications 1221, 1222... 122 n , and for each segment 118 i one digital content metadata 200 is provided as an input to a retention machine learning module (MLM) 126 that generates, as an output, the retention period 300 of the digital content 112 or one retention period for each segment 118 i

[0010] ​The retention period 300 (Figure 3) may consist of the components of an isolation period 304 and a deletion period 306. The isolation period 304 refers to the period from when the digital content 112 was received, and after the expiration of the isolation period 304, the digital content 112 / segment 118 i The isolated digital content 112 / segment 118 is shown separately. The deletion period 306 refers to the period from when the digital content 112 was isolated, and after the expiration of the deletion period 306, the isolated digital content 112 / segment 118 i It is deleted and removed from storage 114. Isolated digital content 112 / segment 118 i This is presented to the user of the computing device 100 in an isolated view 117 including a graphical user interface (GUI), and the user can access the digital content 112 / segment 118. i You may have the option to either remove it from storage 114 or remove it from quarantine to keep it on storage 114.

[0011] The digital content manager 128 determines when to update the metadata 200 and retrains the retention MLM 126 based on the training set of the digital content metadata 200, using the digital content 112 / segment 118. i Manage access to this.

[0012] Memory 104 may include non-volatile memory types or volatile memory types, or both, such as flash memory (NAND dies of flash memory cells), non-volatile dual in-line memory modules (NVDIMMs), DIMMs, static random access memory (SRAM), ferroelectric random access memory (FeTRAM), random access memory (RAM) drives, dynamic RAM (DRAM), storage class memory (SCM), phase change memory (PCM), resistive random access memory (RRAM), spin-transition torque memory (STM-RAM), conductive bridging RAM (CBRAM), nanowire non-volatile memory, magnetoresistive random access memory (MRAM), and other electrically erasable programmable read-only memory (EEPROM) type devices, hard disk drives, removable memory / storage devices, etc. Storage 114 may include appropriate non-volatile storage or memory devices, including those non-volatile memory devices described above.

[0013] In an alternative embodiment, storage 114 may include cloud storage with a maximum capacity so that the user may want to limit the retention of digital content to avoid the cloud storage account reaching its maximum storage capacity.

[0014] The user computing device 100 may include personal computing devices such as laptops, desktop computers, tablets, smartphones, and wearable computers, or other types of computing devices such as servers.

[0015] Generally, program components 108, 110, 116, 120, 1201, 1202...120 mProgram modules such as 124, 126, and 128 may contain routines, programs, objects, components, logic, and data structures that perform specific tasks or implement specific abstract data types. Program components and hardware devices of computing equipment may be implemented in one or more computer systems, and if implemented in multiple computer systems, the computer systems may communicate over a network.

[0016] Program components 108, 110, 116, 120, 1201, 1202...120 m , 124, 126, and 128 can be accessed and executed by processor 102 from memory 104. Alternatively, program components 108, 110, 116, 120, 1201, 1202, 120 m Some or all of 124, 126, and 128 may be implemented in other hardware devices, such as application-specific integrated circuit (ASIC) hardware devices.

[0017] Program components 108, 110, 116, 120, 1201, 1202...120 m The functions described as being performed by 124, 126, and 128 may be implemented as program code in fewer program modules than shown, or they may be implemented as program code across more program modules than shown.

[0018] Machine learning modules 126, 1202...120 mCertain components, such as the natural language processor 1201, may utilize machine learning and deep learning algorithms such as decision tree learning, association rule learning, neural networks, inductive programming logic, support vector machines, and Bayesian networks. In the case of an implementation of an artificial neural network program, each neural network may be trained using backpropagation to adjust the weights and biases at the nodes of the hidden layer to produce a computed output. In backpropagation used to train a neural network machine learning module, the biases at the nodes of the hidden layer are adjusted as appropriate to produce a desired output retention period of 300 based on a given confidence level. Backpropagation may include supervised learning algorithms for artificial neural networks that use gradient descent. Given an artificial neural network and an error function, the method may compute the gradient of the error function with respect to the weights and biases of the neural network.

[0019] In the backpropagation used to train neural network machine learning modules such as the retention machine learning module 126, the margin of error is determined based on the difference between the calculated retention period 300 and the actual time the digital content 112 remained in storage 114 before being deleted by the user, and an adjusted retention period is generated. Biases in the hidden layer nodes are adjusted as appropriate to reduce the margin of error in the output retention period 300.

[0020] The arrows between the components shown in Figure 1 and the objects in memory 104 represent the data flow between the components.

[0021] The term "user" can refer to a person or a computer process such as a bot.

[0022] Figure 2 shows digital content 112 / segment 118 i Data center metadata 200 maintained for iThe embodiment shows data content / segment ID 202, media format of the content 204 (e.g., text, audio, video, still image, etc.), containing data content 206 that includes segment 202 (e.g., message with segment 202 attached, compressed container, etc.), sender creating the content, sender of the transmission containing content 202, classification 122, 1221, 1222...122 n Attributes 208-1221, 1222...122 of content 202, including one or more data content classifications 210 such as n This includes information generated by the ML analysis tool selection 120 for the content 202, providing access counts 212 and viewing patterns indicating the number of times a user has accessed the digital content / segment 202, reception time 214 when the digital content / segment 202 was received, deletion time 216 when the digital content / segment 202 was deleted by a user or automatically, and a quarantine flag 218 that occurs after the quarantine period 304 for the digital content / segment 202 has expired, indicating whether the digital content / segment 202 is quarantined.

[0023] Metadata attribute 208 may include user priority ratings provided to digital content, additional identifying factors for determining content revisit and viewing patterns, and identifying factors for determining user content deletion patterns. Attribute 208 may indicate related messages and digital content to which a particular digital content is part, such as part of a group of messages that form a thread of messages based on an initial message.

[0024] Figure 3 shows digital content 112 / segment 118 i The retention period generated by the retaining MLM126 is 300. i This is a diagram showing an embodiment, with a retention period of 300. i The generated digital content 112 / segment 118 iIncludes the digital content / segment identifier 302, the generated isolation period 304, and the generated deletion period 306. Digital content 112 / segment 118 i The total retention period may include the sum of the isolation period 304 and the deletion period 306.

[0025] Segments 1181...118 within the same contained data content 206 n It is accessed and deleted at different times and has a different retention period of 300. i It can have a retention period of 300. i This may indicate archiving specific digital content so that it is never deleted. In a further embodiment, the retention period is 300. i This may include a single period indicating when the digital content will be deleted after it has been retained for the duration of its retention period.

[0026] Figure 4 shows the retention period 300 for the received digital content 112. i This figure shows an embodiment of the operations performed by the Digital Content Manager 128, Retention Manager, Content Parser 116, Metadata Manager 124, and Retention MLM 126 in order to determine the digital content 112 (block 400). When digital content 112 such as a message transmitted over the Internet or a network is received (block 400), the Metadata Manager 124 determines the attributes 208 of the digital content (e.g., sender, sender, embedded metadata in the content, sender group, relationship with other digital content, related calendar events (e.g., personal calendar events such as holidays and birthdays, social events, etc.)) (block 402), and the metadata 200 for the received digital content 112 i It is added as part of attribute 208. The content parser 116 determines whether the digital content 112 has multiple segments of different or the same media format (block 404). If not, the ML parsing tool selection 120 selects an ML parsing tool 120 related to the media format 204 of the received digital content 112.i Determine (block 406). Determined ML analysis tool 120 i This process (block 408) the digital content 112, determines one or more classifications of the content of the digital content 112, and assigns the determined classification 210 to metadata 200. i Save to (block 410).

[0027] (In block 404) Digital content 112 consists of multiple segments 1181...118 n If present, the content parser 116 processes the received digital content 112 into segments 1181...118 n Analyze (block 412). Each segment 118 i Regarding this, metadata manager 124 is segment 118 i Segment metadata 200 includes indicating contained digital content 206 (e.g., messages) i Generate (block 414). Each segment 118 i Regarding this, the operation of blocks 416-418 is as follows: segment 118 i Segment classification 122 i This is executed to determine (block 416).

[0028] If digital content 112 (in block 418) is not received from block 410 or 416 during the training period when data is being collected to form a training set for training the retention MLM 126, the retention manager 110 will not receive the digital content 112 / segment 118. i Generated metadata for 200 i The classification 210 is provided as input to MLM126 (block 420), and the retention period 300 is calculated. i The retention manager 110 outputs the retention period 300 output by the retention MLM 126 in response to the metadata 210 input. iThe data can be saved (block 422) and may include a quarantine period 304 and a deletion period 306. The quarantine period timer 302 is started to move the digital content to quarantine after it expires (block 424). If digital content is received during the training period (in block 418), control ends.

[0029] In the embodiment shown in Figure 4, a machine learning module and artificial intelligence are used to classify digital content and any segments within the digital content, and metadata about the digital content / segments is provided to the retention MLM126 to determine the retention period for the digital content. The retention MLM126 is trained on a dataset of the retention period of files and their MLM classification and metadata, so the MLM126 is configured to output a retention period that optimizes how long the digital content is retained based on observed user access and deletion patterns.

[0030] Figure 5 shows the digital content 112 and segment 118 held in storage 114. i Manage (Block 500) This figure shows one embodiment of an operation performed by the digital content manager 128 for the purpose of digital content 112 / segment 118 (in block 502). i When the isolation period 304 expires, the isolation flag 218 is set (in block 504), and the digital content 112 / segment 118 i It is indicated that it is quarantined until deletion. The deletion period timer 504 is started (in block 506), and after the deletion period timer 504 expires, the digital content 112 / segment 118 i Ensure that the data is deleted from storage 114. (At block 508) If the deletion period 306 expires, the digital content 112 / segment 118 i metadata 200 i The entry is updated to show deletion time 216, and the content is subsequently deleted from storage 114. (Block 510) .

[0031] In the embodiment shown in Figure 5, digital content is added to quarantine after the quarantine period has expired following the file's receipt. From quarantine, the file is deleted after the deletion period 306 has expired. While the file is in quarantine, the user can access the file to avoid deletion, allowing the user to prevent the deletion of digital content they wish to retain for a longer period.

[0032] Figure 6 shows digital content 112 / segment 118 i This figure shows one embodiment of the operations performed by the digital content manager 128 and retention MLM 126 to process user requests to access the digital content 112 / segment 118, such as a read request or a request to remove the digital content from quarantine. i When user access is received (block 600), the accessed digital content 112 / segment 118 i metadata 200 i In this case, the number of accesses 212 that may be accessed within or outside the isolation zone is incremented (block 602). (In block 604) Accessed digital content 112 / segment 118 i However, if the device is in isolation as indicated by the isolation flag 218, the isolation flag 218 is set to indicate that it is not in isolation. (Block 606) Because the user chose to remove the digital content from quarantine for retention for a longer period, the digital content manager 128 then determined the previously determined retention period 300 i Digital content 112 / segment 118 including longer quarantine period 304 and deletion period 306 i New retention period of 300 i This can be determined (block 608). For example, there may be a predetermined number of retention period levels having isolation periods and deletion periods, and a new retention period may follow a previously determined retention period in a given set of retention period levels. Accessed digital content 112 / segment 118 imetadata 200 i And classification 210 determines new retention period 300 i To generate the output, it is provided to the holding MLM 126 (block 610). (In block 604) Digital content 112 / segment 118 i If it is not isolated, control will terminate.

[0033] In the embodiment shown in Figure 6, when digital content is accessed, the access count 212 is incremented, and if the digital content is isolated, a new, longer retention period is determined. The retention MLM 126 is then retrained and adjusted to output a longer retention period for digital content that has the attributes 208 and classification 210 of the isolated accessed digital content. The accessed digital content may then be retained for the new, longer retention period.

[0034] Figure 7 shows one embodiment of the operations performed by the Retention Manager 110 and the Retention MLM 126 Manager to initiate training of the Retention MLM 126 based on a training dataset collected over a certain period. During the construction of the training dataset, digital content metadata 200 is generated for the received digital content, indicating the deletion time to build the training set. When training is started (in block 700), the digital content 112 / segment 118 deleted during the period for which data is collected for the training set is identified. i For each instance, the retention manager 110 determines the actual retention period based on the deletion time 216 minus the reception time 214 (block 702). Digital content 112 / segment 118 deleted during the training period. i For each instance, the retention manager 110 is trained to generate the actual retention period, or quarantine period and deletion period, as output, by inputting digital content 112 / segment 118 to the retention MLM 126. i metadata 200 i And provides classification 210 (block 704).

[0035] In the embodiment shown in Figure 7, a training set of collected information about deleted digital content / segments is provided to the retention MLM 126 for use in outputting the actual retention period. In this way, the retention MLM 126 outputs the digital content 112 / segment 118 i Based on attribute 208 and the determined classification 210 of the actual user access and deletion patterns of the received digital content, the retention period is trained to output. This allows the retention MLM 126 to be optimized to retain content for the period during which it is likely to be accessed. Content that is no longer likely to be accessed may be deleted from storage 114 to save space in storage 114, which may have limited space.

[0036] Figure 8 shows digital content 112 / segment 118 i This shows one embodiment of the operation performed by the digital content manager 128 and the retention MLM 126 to process a user request to delete digital content 112 / segment 118. i In response to a request to delete (block 800), the digital content manager 128 deletes the digital content 112 / segment 118. i metadata 200 i The deletion time 216 is shown (block 802), and the actual retention period is calculated by subtracting the reception time 214 from the deletion time 216. (In block 804) The actual retention period is the retention period 300 determined by the machine, such as the isolation period 304 and the deletion period 306. i If different, metadata 200 will be used to generate the actual retention period as output. i The classification 210 is provided as input to retrain the retention MLM 126 (block 806). The retention period 300 determined by the machine i If there is no substantial difference between the actual retention period and the generated retention period, the control is terminated without relearning the retention MLM126 because the correct retention period has been generated.

[0037] In an alternative embodiment, the operation shown in Figure 8 may be performed periodically to build a retraining dataset of recently deleted digital content in order to periodically retrain the retention MLM126.

[0038] In the embodiment of Figure 8, information on the actual retention period determined when a file is deleted can be used to determine whether to retrain the retention MLM 126 to adjust the output retention period to the actual retention period, based on the metadata and classification of the deleted digital content. The embodiment of Figure 8 allows the retention MLM 126 to self-adjust during normal digital content management operations to reflect actual user deletion and access patterns for digital content with digital content metadata.

[0039] The present invention may be a system, a method, a computer program product, or a combination thereof. The computer program product may include a computer-readable storage medium storing computer-readable program instructions for causing a processor to execute an aspect of the present invention.

[0040] A computer-readable storage medium can be a tangible device capable of holding and storing instructions used by an instruction execution device. A computer-readable storage medium may, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or a suitable combination thereof. More specific examples of computer-readable storage media include portable computer diskettes, hard disks, RAM, ROM, EPROM (or flash memory), SRAM, CD-ROM, DVD, memory stick, floppy disk, punch cards, or grooved raised structures, and mechanically encoded devices on which instructions are recorded, and suitable combinations thereof. The computer-readable storage medium as used herein should not be interpreted as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through optical fiber cables), or electrical signals transmitted through wires.

[0041] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, or a wireless network, or a combination thereof). The network consists of copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, or edge servers, or a combination thereof. The network adapter card or network interface of each computing / processing device receives computer-readable program instructions from the network and transfers the computer-readable program instructions for storage on the computer-readable storage medium within each computing / processing device.

[0042] The computer-readable program instructions for performing the operation of the present invention may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and procedural programming languages ​​such as the C programming language or similar programming languages. The computer-readable program instructions are executable as a standalone software package, either entirely on the user's computer or partially on the user's computer. Alternatively, they may be executable partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or to an external computer (for example, via the Internet using an Internet service provider). In some embodiments, for example, an electronic circuit including a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA) can execute computer-readable program instructions by personalizing them using state information of computer-readable program instructions in order to perform aspects of the present invention.

[0043] Aspects of the present invention are described herein with reference to flowcharts or block diagrams, or both, of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It will be understood that each block in a flowchart or block diagram, or both, and any combination of blocks in a flowchart or block diagram, or both, can be implemented by computer-readable program instructions.

[0044] These computer-readable program instructions can be provided to a general-purpose computer, a dedicated computer processor, or other programmable data processing device to generate a machine, such that instructions executed via the processor of a computer or other programmable data processing device generate means for implementing functions / operations specified in one or more blocks of a flowchart or block diagram or both. These computer-readable program instructions can also be stored in a computer-readable storage medium that can be connected to a computer, a programmable data processing device, or other device or combination of devices that function in a particular way, such that the computer-readable storage medium on which the instructions are stored constitutes one of the outputs containing instructions that implement the modes of functions / operations specified in one or more blocks of a flowchart or block diagram or both.

[0045] Computer-readable program instructions, like instructions that perform a function / action specified in one or more blocks of a flowchart or block diagram or both on a computer, other programmable device, or other device, can also be loaded into a computer, other programmable data processing device, or other device and perform a series of operational steps on the computer, other programmable device, or other device to produce a computer-implemented process.

[0046] The flowcharts and block diagrams in the figures illustrate the configuration, functions, and operation of executable implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or part of an instruction, which constitutes one or more executable instructions for implementing a specified logical function. In some alternative embodiments, the functions shown in the blocks may differ from the order shown in the figures. For example, two blocks shown consecutively may actually be executed substantially simultaneously, or the blocks may be executed in reverse order depending on the functions they relate to. It should also be noted that each block in a block diagram or flowchart diagram, or both, and any combination of blocks in a block diagram or flowchart diagram, or both, can be implemented by a special-purpose hardware-based system that performs a specified function or operation, or a combination of special-purpose hardware and computer instructions.

[0047] The computing components of the computing device 100 in Figure 1 may be implemented in one or more computer systems, such as the computer system 902 shown in Figure 9. The computer system / server 902 may be described in the general context of computer system executable instructions, such as program modules, being executed by the computer system. Generally, program modules may include routines, programs, objects, components, logic, and data structures that perform a specific task or implement a specific abstract data type. The computer system / server 902 may be implemented in a distributed cloud computing environment where tasks are executed by remote processing devices linked over a communication network. In a distributed cloud computing environment, program modules may reside on both local and remote computer system storage media, including memory storage devices.

[0048] As shown in Figure 9, the computer system / server 902 is shown in the form of a general-purpose computing device. The components of the computer system / server 902 may include, but are not limited to, one or more processors or processing units 904, system memory 906, and a bus 908 that connects various system components, including the system memory 906, to the processor 904. The bus 908 represents one or more of several types of bus structures, including a memory bus or memory controller using any of the various bus architectures, peripheral buses, accelerated graphics ports, and processor or local buses. Examples of such architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, Microchannel Architecture (MCA) bus, Extended ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0049] The computer system / server 902 generally includes various computer system-readable media. Such media may be any available media accessible by the computer system / server 902 and may include both volatile and non-volatile media, as well as both removable and non-removable media.

[0050] The system memory 906 may include computer system-readable media in the form of volatile memory, such as random access memory (RAM) 910 or cache memory 912 or both. The computer system / server 902 may also include other removable / non-removable computer system-readable media and volatile / non-volatile computer system-readable media. For example, the storage system 913 may be provided for reading and writing to a non-removable non-volatile magnetic medium (not shown; commonly referred to as a “hard drive”). Also, although not shown, a magnetic disk drive for reading and writing to removable non-volatile magnetic disks (e.g., floppy disks) and an optical disk drive for reading and writing to removable non-volatile optical disks (such as CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these examples, each may be connected to the bus 908 by one or more data medium interfaces. As further illustrated and described below, the memory 906 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of embodiments of the present invention.

[0051] A program / utility 914 having a set (at least one) of program modules 916 can be stored in memory 906 in an illustrative and non-limiting manner, as can an operating system, one or more application programs, other program modules, and program data. Each of the operating system, one or more application programs, other program modules, and program data, or any combination thereof, may include an implementation of a network environment. Components of computer 902 may be implemented as program modules 916 that generally perform the functions or methodologies, or both, of the embodiments of the present invention described herein. The system of Figure 1 may be implemented in one or more computer systems 902, and if implemented in multiple computer systems 902, the computer systems may communicate over a network.

[0052] The computer system / server 902 can communicate with one or more external devices 918 such as a keyboard, pointing device, or display 920, one or more devices that enable interaction between the user and the computer system / server 902, or any device that enables communication between the computer system / server 902 and one or more other computer devices (e.g., a network card or modem), or a combination thereof. Such communication can be performed via the input / output (I / O) interface 922. Furthermore, the computer system / server 902 can communicate with one or more networks (such as a local area network (LAN), a general-purpose wide area network (WAN), or a public network (e.g., the Internet), or a combination thereof) via the network adapter 924. As shown in the figure, the network adapter 924 can communicate with other components of the computer system / server 902 via the bus 908. Although not shown in the figure, other hardware components, software components, or both can be used in combination with the computer system / server 902. Examples of these include microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archive storage systems.

[0053] Letter notations such as i, m, and n are used to specify the number of instances of an element, but when used with the same or different elements, they may indicate that the number of instances of that element is variable.

[0054] In this specification, "an embodiment," "embodiment," "embodiments," "the embodiment," "the embodiments," "in one or more embodiments," "some embodiments," and "one embodiment" mean "one or more (but not all) embodiments of the present invention" unless expressly specified.

[0055] The terms "inducing," "comprising," and "having," and their variations, mean "including but not limited to," unless explicitly stated otherwise.

[0056] Furthermore, unless explicitly stated otherwise, the listed items do not imply that any or all of them are mutually exclusive.

[0057] The terms "a," "an," and "the" mean "one or more" unless explicitly stated otherwise.

[0058] Devices communicating with each other do not need to communicate continuously unless explicitly specified otherwise. Furthermore, devices communicating with each other may communicate directly or indirectly through one or more intermediaries.

[0059] The description of embodiments having multiple components that communicate with each other does not mean that all such components are necessary. Rather, various optional components are described in order to illustrate the diverse possible embodiments of the present invention.

[0060] Where a single device or article is described herein, it will be readily apparent that multiple devices / articles (whether they work together or not) may be used in place of the single device / article. Similarly, where two or more devices or articles (whether they work together or not) are described herein, it will be readily apparent that a single device / article may be used in place of the two or more devices or articles, or that a different number of devices / articles may be used in place of the number of devices or programs indicated. The functionality or features, or both, of a device may be implemented by one or more other devices not expressly described as having such functionality / features. Therefore, other embodiments of the present invention do not necessarily have to include the device itself.

[0061] The foregoing description relating to various embodiments of the present invention is presented for illustrative and explanatory purposes only. It is not intended to be exhaustive or to limit the invention to the exact forms disclosed. Many modifications and variations are possible in light of the above teachings. The scope of the present invention is intended to be limited not by this detailed description, but rather by the claims appended herein. The above specification, examples, and data provide a complete description relating to the manufacture and use of the compositions of the present invention. Since many embodiments of the present invention can be made without departing from the scope of the present invention, the present invention resides within the claims appended herein.

Claims

1. A computer program for managing digital content in storage used by a computing device, wherein the computer program includes program instructions that, when executed, cause an action, and the action is To generate metadata for an instance of digital content, wherein the metadata includes the access patterns of the digital content by the user of the computing device and the attributes of the digital content. The actual retention period of an instance of the digital content is determined based on the time the digital content is in the storage. Training a machine learning module to generate the determined actual retention period of the digital content using an input that includes the metadata of the instance of the digital content, After training the machine learning module, the machine learning module is provided with input including metadata of the received digital content to generate an output retention period, which is the output retention period of the received digital content. The timing for deleting the received digital content from the storage is determined using the output retention period, A computer program that includes [this].

2. The computer program according to claim 1, wherein the attributes of the digital content include at least one of the sender of the digital content, the sender who sent the digital content to the computing device in a message, metadata embedded in the digital content when it was sent to the computing device, the classification of the digital content as determined by a classification program, the group to which the sender belongs, the relationship of the digital content to previously received digital content, and associated calendar events.

3. The aforementioned operation is, In response to receiving digital content, The process involves determining whether the received digital content includes a segment of the digital content that constitutes a separate instance of the digital content. In response to determining that the received digital content includes the segment, the received digital content is analyzed into the segment of the digital content, wherein metadata is generated for the segment, and the machine learning module is separately trained for the segment of the digital content with inputs including the metadata generated for the segment, in order to generate an output retention period for the segment. The computer program according to claim 1, further comprising:

4. The computer program according to claim 3, wherein at least one instance of the digital content includes a message having attachments, the segment includes the message and the attachments, and the machine learning module generates different retention periods for the segment.

5. The aforementioned operation is, To determine a message classification based on natural language processing (NLP) of the content of the message, the NLP of the content of the message is performed, the message classification is provided as input to train a machine learning module to generate the output retention period of the segment containing the message, and the execution of this process further includes: The computer program according to claim 4.

6. The aforementioned operation is, With respect to the digital content segment, the machine learning analysis tool determines to generate a segment classification of the content within the segment based on the media format of the content within the segment, further comprising determining that the metadata generated for the segment and input into the machine learning module includes the segment classification determined by the machine learning analysis tool determined for the segment. The computer program according to claim 3.

7. The computer program according to claim 1, wherein the output retention period includes an isolation period and a deletion period for the digital content over the retention period, the digital content is shown isolated after the expiration of the isolation period, and the isolated digital content is deleted from the storage in response to the expiration of the deletion period which was initiated when the digital content was shown isolated, and training the machine learning module includes training the machine learning module to generate the isolation period and the deletion period as outputs based on the input to the digital content.

8. The aforementioned operation is, Receiving a user selection to delete digital content from the aforementioned isolation in order to retain it in storage, The digital content to be removed from the quarantine is not currently in the quarantine, To determine a new retention period that is longer than the retention period determined for the digital content in order to remove it from the aforementioned isolation, In order to retrain the machine learning module that generates the new retention period as an output, the machine learning module is provided with an input that includes metadata determined from the digital content to be deleted from isolation, The computer program according to claim 7, further comprising:

9. The aforementioned operation is, The machine learning module receives a selection to delete the digital content whose retention period has been determined, To determine whether the actual retention period of the deleted digital content, based on the time the digital content was deleted, differs from the output retention period, In order to generate the actual retention period as output, the machine learning module is retrained using the metadata of the deleted digital content as input, The computer program according to claim 1, further comprising:

10. A system coupled to storage for managing digital content within storage, wherein the system is Processor and A computer-readable storage medium having program instructions that, when executed by the aforementioned processor, cause an action, wherein the action is To generate metadata for instances of digital content stored in a computing device, wherein the metadata includes the access patterns of the digital content by the user of the computing device and the attributes of the digital content. The actual retention period of an instance of the digital content is determined based on the time the digital content is in the storage. Training a machine learning module to generate the determined actual retention period of the digital content using an input that includes the metadata of the instance of the digital content, After training the machine learning module, the machine learning module is provided with input including metadata of the received digital content to generate an output retention period, which is the output retention period of the received digital content. The timing for deleting the received digital content from the storage is determined using the output retention period, A system that includes this.

11. The aforementioned operation is, In response to receiving digital content, The process involves determining whether the received digital content includes a segment of the digital content that constitutes a separate instance of the digital content. In response to determining that the received digital content includes the segment, the received digital content is analyzed into the segment of the digital content, wherein metadata is generated for the segment, and the machine learning module is separately trained for the segment of the digital content with inputs including the metadata generated for the segment, in order to generate an output retention period for the segment. The system according to claim 10, further comprising:

12. The system according to claim 11, wherein at least one instance of the digital content includes a message having attachments, the segment includes the message and the attachments, and the machine learning module generates different retention periods for the segment.

13. The aforementioned operation is, With respect to the digital content segment, the machine learning analysis tool determines to generate a segment classification of the content within the segment based on the media format of the content within the segment, further comprising determining that the metadata generated for the segment and input into the machine learning module includes the segment classification determined by the machine learning analysis tool determined for the segment. The system according to claim 11.

14. The system according to claim 10, wherein the output retention period includes an isolation period and a deletion period for the digital content over the retention period, the digital content is shown isolated after the expiration of the isolation period, the isolated digital content is deleted from the storage in response to the expiration of the deletion period which was initiated when the digital content was shown isolated, and training the machine learning module includes training the machine learning module to generate the isolation period and the deletion period as outputs based on the input to the digital content.

15. The aforementioned operation is, The machine learning module receives a selection to delete the digital content whose retention period has been determined, To determine whether the actual retention period of the deleted digital content, based on the time the digital content was deleted, differs from the output retention period, In order to generate the actual retention period as output, the machine learning module is retrained using the metadata of the deleted digital content as input, The system according to claim 10, further comprising:

16. A method performed by a computing device for managing digital content in storage used by the computing device, The computing device generates metadata for an instance of digital content, wherein the metadata includes the access patterns of the digital content by the user of the computing device and the attributes of the digital content. The computing device determines the actual retention period of an instance of the digital content based on the time the digital content is in the storage, The computing device trains a machine learning module to generate the determined actual retention period of the digital content using an input that includes the metadata of the instance of the digital content. The computing device, after training the machine learning module, provides the machine learning module with input including metadata of the received digital content to generate an output retention period, which is the output retention period of the received digital content. The computing device determines the timing for deleting the received digital content from the storage using the output retention period. Methods that include...

17. In response to receiving digital content, The computing device performs the task of determining whether the received digital content includes a segment of the digital content that constitutes a separate instance of the digital content. In response to the computing device determining that the received digital content includes the segment, the received digital content is analyzed into the segment of the digital content, wherein metadata is generated for the segment, and the machine learning module is separately trained on the segment of the digital content with inputs including the metadata generated for the segment in order to generate an output retention period for the segment. The method according to claim 16, further comprising:

18. The method according to claim 17, wherein at least one instance of the digital content includes a message having attachments, the segment includes the message and the attachments, and the machine learning module generates different retention periods for the segment.

19. The computing device determines a machine learning analysis tool for a segment of digital content to generate a segment classification of the content within the segment based on the media format of the content within the segment, further comprising determining that the metadata generated for the segment and input into the machine learning module includes the segment classification determined by the machine learning analysis tool determined for the segment. The method according to claim 17.

20. The method according to claim 16, wherein the output retention period includes an isolation period and a deletion period for the digital content over the retention period, the digital content is shown isolated after the expiration of the isolation period, and the isolated digital content is deleted from the storage in response to the expiration of the deletion period which was initiated when the digital content was shown isolated, and training the machine learning module includes training the machine learning module to generate the isolation period and the deletion period as outputs based on the input to the digital content.

Images