Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F40/00—Handling natural language data
  • G06F40/30—Semantic analysis
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/04—Architecture, e.g. interconnection topology
  • G06N3/0499—Feedforward networks
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/08—Learning methods
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/08—Learning methods
  • G06N3/09—Supervised learning
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N5/00—Computing arrangements using knowledge-based models
  • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F2207/00—Indexing scheme relating to methods or arrangements for processing data by operating upon the order or content of the data handled
  • G06F2207/38—Indexing scheme relating to groups G06F7/38 - G06F7/575
  • G06F2207/48—Indexing scheme relating to groups G06F7/48 - G06F7/575
  • G06F2207/4802—Special implementations
  • G06F2207/4818—Threshold devices
  • G06F2207/4824—Neural networks
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F40/00—Handling natural language data
  • G06F40/20—Natural language analysis
  • G06F40/205—Parsing
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/04—Architecture, e.g. interconnection topology
  • G06N3/048—Activation functions

Definitions

• the present invention generally relates to the field of hypernym induction, and more specifically, to a method and system for neural network-based hypernym induction.
• One embodiment of the present invention provides a method comprising receiving a text corpus, and generating a first list of triples based on the text corpus.
• Each triple of the first list comprises a first term representing a candidate hyponym, a second term representing a candidate hypernym, and a frequency value indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in the text corpus.
• the method further comprises training a neural network for hypernym induction based on the first list.
• the trained neural network is a strict partial order network (SPON) model.
• Another embodiment of the present invention provides a system comprising at least one processor and a non-transitory processor-readable memory device storing instructions that when executed by the at least one processor causes the at least one processor to perform operations.
• the operations include receiving a text corpus, and generating a first list of triples based on the text corpus. Each triple of the first list comprises a first term representing a candidate hyponym, a second term representing a candidate hypernym, and a frequency value indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in the text corpus.
• the operations further include training a neural network for hypernym induction based on the first list.
• the trained neural network is a SPON model.
• One embodiment of the present invention provides a computer program product comprising a computer readable storage medium having program instructions embodied therewith.
• the program instructions are executable by a processor to cause the processor to receive a text corpus, and generate a first list of triples based on the text corpus.
• Each triple of the first list comprises a first term representing a candidate hyponym, a second term representing a candidate hypernym, and a frequency value indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in the text corpus.
• the program instructions are further executable by the processor to cause the processor to train a neural network for hypernym induction based on the first list.
• the trained neural network is a SPON model.
• FIG. 1 illustrates an example computing architecture for implementing neural network-based hypernym induction, in accordance with an embodiment of the invention
• FIG. 2 illustrates an example neural network-based hypernym induction system, in accordance with an embodiment of the invention
• FIG. 3 illustrates an example strict partial order network (SPON) model, in accordance with an embodiment of the invention
• FIG. 4 is a flowchart for an example process for neural network-based hypernym induction, in accordance with an embodiment of the invention.
• FIG. 5 is a high level block diagram showing an information processing system useful for implementing an embodiment of the present invention.
• the present invention generally relates to the field of hypernym induction, and more specifically, to a method and system for neural network-based hypernym induction.
• One embodiment of the present invention provides a method comprising receiving a text corpus, and generating a first list of triples based on the text corpus.
• Each triple of the first list comprises a first term representing a candidate hyponym, a second term representing a candidate hypernym, and a frequency value indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in the text corpus.
• the method further comprises training a neural network for hypernym induction based on the first list.
• the trained neural network is a strict partial order network (SPON) model.
• Another embodiment of the present invention provides a system comprising at least one processor and a non-transitory processor-readable memory device storing instructions that when executed by the at least one processor causes the at least one processor to perform operations.
• the operations include receiving a text corpus, and generating a first list of triples based on the text corpus. Each triple of the first list comprises a first term representing a candidate hyponym, a second term representing a candidate hypernym, and a frequency value indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in the text corpus.
• the operations further include training a neural network for hypernym induction based on the first list.
• the trained neural network is a SPON model.
• One embodiment of the present invention provides a computer program product comprising a computer readable storage medium having program instructions embodied therewith.
• the program instructions are executable by a processor to cause the processor to receive a text corpus, and generate a first list of triples based on the text corpus.
• Each triple of the first list comprises a first term representing a candidate hyponym, a second term representing a candidate hypernym, and a frequency value indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in the text corpus.
• the program instructions are further executable by the processor to cause the processor to train a neural network for hypernym induction based on the first list.
• the trained neural network is a SPON model.
• a hyponym is a term representing an abstraction, such as a type or class.
• a hypernym is a term representing an abstraction, such as a type or class, that is more generic than a hyponym.
• NE A named entity is a proper noun. Available NE types are limited and pre-defined, ranging from dozens to hundreds at most. By comparison, hypernyms are broader than NE types.
• Hypernyms are building blocks for taxonomy construction.
• a hypernymy relation (i.e., relationship) comprises of an is-a (i.e., is a) relation between a hyponym and a hypernym.
• potato pancake is-a pancake is a hypernymy relation between the hyponym potato pancake and the hypernym pancake.
• Hypernymy relations within a taxonomy satisfy the following properties: reflexivity, transitivity, and asymmetry (i.e., not symmetric). For example, if Wittgenstein is-a philosopher and philosopher is-a person, it follows that Wittgenstein is-a person by the transitive property. It also follows that philosopher is not Wittgenstein and person is not philosopher by the asymmetry property.
• hypoonym-hypernym pair generally refers to a pair of terms comprising a hyponym and a hypernym that exhibits a hypernymy relation.
• hypernym detection generally refers to a task of classifying or predicting whether a given pair of terms (x, y) (e.g, (robin, passerine)) are in a hypernymy relation.
• hypernym direction generally refers to a task of identifying or predicting which term in a given pair of terms (x, y) is the hypernym (i.e., which of (x, y) or (y, x) is in a hypernymy relation).
• hypernym discovery generally refers to a task of predicting, for a given hyponym x, ranked predictions of hypernymsfor the given hyponym x.
• supervised machine learning systems can be trained to predict hypernyms if there is sufficient training data.
• training data may not be available equally across all domains.
• Embodiments of the invention provide a method and system for automatic extraction of hyponym- hypernym pairs from unstructured free text using a deep neural network model that learns how to encode hypernymy relationships.
• Embodiments of the invention can be used to perform tasks such as, but not limited to, hypernym detection, hypernym direction, and hypernym discovery. Each task can be performed in either in an unsupervised or supervised manner.
• a strict partial order is a binary relation that is transitive, irreflexive, and asymmetric. Strict partial order relations correspond more directly to directed acyclic graphs (DAGs).
• Embodiments of the invention provide a SPON designed to learn and model hyponym-hypernym pairs representing hypernymy relationships within a taxonomy.
• a SPON is a neural network architecture comprising non negative activations and residual connections designed to enforce the asymmetry and transitivity requirements of strict partial order relations as soft constraints.
• One embodiment provides a SPON model trained to enforce the asymmetry and transitivity requirements of strict partial order relations as soft constraints. During a learning process, the SPON model is trained with hyponym-hypernym pairs.
• an augmented variant of the SPON model can generalize type information learned for in-vocabulary terms to previously unseen ones to identify/predict hypernyms for out-of-vocabulary (OOV) terms (i.e., terms that are not observed/seen by the SPON model during the learning process); the augmented variant does this using normalized distributional similarity values as weights within a probabilistic model.
• OOV out-of-vocabulary
• FIG. 1 illustrates an example computing architecture 100 for implementing neural network-based hypernym induction, in accordance with an embodiment of the invention.
• the computing architecture 100 is a centralized computing architecture.
• the computing architecture 100 is a distributed computing architecture.
• the computing architecture 100 comprises computation resources such as, but not limited to, one or more processor units 110 and one or more storage units 120.
• One or more applications execute/operate on the computing architecture 100 utilizing the computation resources of the computing architecture 100.
• the applications on the computing architecture 100 include, but are not limited to, a neural network-based hypernym induction system 200 configured for automatic extraction of hyponym- hypernym pairs from a text corpus (e.g., unstructured free text) utilizing a deep neural network that learns to encode hypernymy relationships.
• the neural network-based hypernym induction system 200 is used to automatically extract hyponym-hypernym pairs from an unannotated large text corpus.
• the neural network utilized by the neural network-based hypernym induction system 200 is a SPON model 250 (FIG. 2) trained to enforce the asymmetry and transitivity requirements of strict partial order relations as soft constraints in the context of hypernym induction.
• the neural network-based hypernym induction system 200 is configured to exchange data with one or more electronic devices 400 and/or one or more remote server devices 20 over a connection (e.g., a wireless connection such as a Wi-Fi connection or a cellular data connection, a wired connection, or a combination of the two).
• a connection e.g., a wireless connection such as a Wi-Fi connection or a cellular data connection, a wired connection, or a combination of the two).
• an electronic device 400 comprises one or more computation resources such as, but not limited to, one or more processor units 410 and one or more storage units 420.
• One or more applications execute/operate on an electronic device 400 utilizing the one or more computation resources of the electronic device 400 such as, but not limited to, one or more software applications 450 loaded onto or downloaded to the electronic device 400.
• software applications 450 include, but are not limited to, artificial intelligence (Al) applications, NLP applications.
• Examples of an electronic device 400 include, but are not limited to, a desktop computer, a mobile electronic device (e.g., a tablet, a smart phone, a laptop, etc.), a wearable device (e.g., a smart watch, etc.), an Internet of Things (loT) device, a smart appliance such as a smart television, etc.
• a desktop computer e.g., a desktop computer
• a mobile electronic device e.g., a tablet, a smart phone, a laptop, etc.
• a wearable device e.g., a smart watch, etc.
• an Internet of Things (loT) device e.g., a smart appliance such as a smart television, etc.
• an electronic device 400 comprises one or more input/output (I/O) units 430 integrated in or coupled to the electronic device 400, such as a keyboard, a keypad, a touch interface, a display screen, etc.
• I/O input/output
• a user utilizes an I/O module 430 of an electronic device 400 to configure one or more user preferences, configure one or more parameters (e.g., hyper-parameters for the SPON model 250, etc.), provide input (e.g., manually labeled training data, such as a list of manually validated is-a relationships), etc.
• an electronic device 400 and/or a remote server device 20 is a source of training data and/or a text corpus.
• the neural network-based hypernym induction system 200 is accessed or utilized by one or more online services (e.g., Al services, NLP services) hosted on a remote server device 20 and/or one or more software applications 450 (e.g., Al applications, NLP applications) operating on an electronic device 400.
• a virtual assistant, a search engine, or another type of software application 450 operating on an electronic device 400 invokes the system 200 to perform hypernym detection, hypernym direction, and/or hypernym discovery to generate broader or narrower search terms, answer questions by finding more general categories, build taxonomies and knowledge bases, etc.
• FIG. 2 illustrates an example neural network-based hypernym induction system 200, in accordance with an embodiment of the invention.
• the system 200 comprises a linguistic pattern-based unit 210 configured to: (1) receive, as an input, a text corpus (e.g., unstructured free text), and (2) generate, based on the text corpus, a list of candidate hyponym-hypernym pairs.
• a text corpus e.g., unstructured free text
• C generally denote a text corpus received as an input.
• the linguistic pattern-based unit 210 is configured to generate a list of candidate hyponym-hypernym pairs by applying one or more linguistic patterns to a text corpus C to extract one or more candidate hyponym-hypernym pairs, wherein the list comprises of one or more extracted candidate hyponym- hypernym pairs.
• the one or more linguistic patterns applied comprises Hearst-like patterns.
• the linguistic pattern-based unit 210 is configured to generate a list of candidate hyponym-hypernym pairs based on a manually labeled training set (e.g., a list of manually validated is-a relationships) provided to the system 200.
• the linguistic pattern-based unit 210 is configured to remove a candidate hyponym-hypernym pair that is likely erroneous (i.e., incorrect or spurious), if any, from a list of candidate hyponym- hypernym pairs based on one or more statistical significance and circumstantial evidences.
• the linguistic pattern-based unit 210 flags/identifies the candidate hypernym and the several other candidate hypernyms as likely erroneous for removal.
• the system 200 comprises a filtering and expansion unit 220 configured to: (1) receive a list of candidate hyponym-hypernym pairs (e.g., from the linguistic pattern-based unit 210), and (2) improve quality of the received list by applying one or more filtering and/or expansion techniques to the received list to filter and/or expand the received list.
• a filtering and expansion unit 220 configured to: (1) receive a list of candidate hyponym-hypernym pairs (e.g., from the linguistic pattern-based unit 210), and (2) improve quality of the received list by applying one or more filtering and/or expansion techniques to the received list to filter and/or expand the received list.
• the filtering and expansion unit 220 automatically filters a list of candidate hyponym-hypernym pairs to remove one or more candidate hyponym-hypernym pairs that are likely erroneous, if any, based on heuristics. For example, in one embodiment, the filtering and expansion unit 220 filters the list based on a heuristic defined as follows: if a candidate hypernym of a candidate hyponym-hypernym pair included in the list is a proper noun, filter out (i.e., remove) the pair from the list as the pair is erroneous (e.g., a candidate hyponym- hypernym pair (x, North America) is filtered out).
• a heuristic defined as follows: if a candidate hypernym of a candidate hyponym-hypernym pair included in the list is a proper noun, filter out (i.e., remove) the pair from the list as the pair is erroneous (e.
• the filtering and expansion unit 220 filters the list based on a heuristic defined as follows: if there exists a sequence of terms i, 2, and 3 such that (xi, 2), (X2, X3) and (x 3 ⁇ 4 i) are candidate hyponym-hypernym pairs of the list, filter out one of these pairs from the list to break a cycle formed between the terms.
• the filtering and expansion unit 220 automatically expands a list of candidate hyponym-hypernym pairs to include one or more additional candidate hyponym-hypernym pairs by exploiting super terms and sub-terms.
• the one or more additional candidate hyponym-hypernym pairs are not extracted from a text corpus C and not included in a manually labeled training set. For example, ( Bank of Riverdale, Bank) is a candidate hyponym-hypernym pair resulting from exploiting the terms Bank of Riverdale and Bank, wherein Bank of Riverdale is a super-term of Bank, and Bank is a sub-term of Bank of Riverdale.
• the system 200 comprises an initialization unit 230 configured to control how a SPON model 250 is initialized.
• the initialization unit 230 is configured to: (1) receive a list of candidate hyponym- hypernym pairs (e.g., from the filtering and expansion unit 220 or the linguistic-pattern based unit 210), and (2) generate a list of candidate hyponym-hypernym-count triples, wherein each triple comprises a candidate hyponym, a candidate hypernym, and a frequency (i.e., count) indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in a text corpus C.
• a frequency i.e., count
• the initialization unit 230 is configured to encode each term (i.e., candidate hyponym, candidate hypernym) of a list of candidate hyponym-hypernym-count triples based on a either a pre initialized word/character embedding or a word/character embedding trained from a text corpus C, such that the resulting list includes initial (i.e., initialization) vectors for each term of the list. For example, if each term of the list is encoded based on a pre-initialized word/character embedding, the SPON model 250 is initialized using external pre-trained vectors.
• the SPON model 250 is initialized using embeddings from the text corpus C.
• the system 200 is configured to train a SPON model 250 based on training data comprising is-a relations.
• T generally denote training data used to train the SPON model 250.
• the training data T comprises candidate hyponym-hypernym pairs.
• the system 200 feeds a list of candidate hyponym-hypernym-count triples (e.g., from the initialization unit 230) to the SPON model 250 as the training data T.
• the SPON model 250 is trained against a loss function that satisfies the asymmetry and transitivity requirements of strict partial order relations as soft constraints.
• a trained SPON model 250 resulting from the learning process is configured to induce hypernymy relations.
• the trained SPON model 250 in a deployment phase/stage, is used to perform tasks such as, but not limited to, hypernym detection, hypernym direction, and hypernym discovery.
• the trained SPON model 250 is applied to classify/predict whether an unseen pair of terms (i.e., a pair of terms not seen in the training data) are in a hypernymy relation.
• FIG. 3 illustrates an example SPON model 250, in accordance with an embodiment of the invention.
• the SPON model 250 is a neural network architecture trained to enforce the asymmetry and transitivity requirements of strict partial order relations as soft constraints.
• the SPON model 250 is trained using positive examples (i.e., positive instances) and negative examples (i.e., negative instances) derived from the training data T.
• Positive examples i.e., positive instances
• negative examples i.e., negative instances
• !H generally denote a set of all hypernyms observed/seen in the training data T .
• Each positive instance comprises a pair of terms (x, ⁇ c ), wherein ⁇ c is a set of candidate hypernyms for a given candidate hyponym x in the training data T.
• Each negative instance comprises a pair of terms (x, W x ), wherein !H X is a set of negative hypernym samples (i.e., false hypernyms) for a given candidate hyponym x in the training data T.
• the system 200 is configured to generate negative instances for a given candidate hyponym x using random negative sampling (i.e., selecting terms uniformly at random from M ⁇ H C , wherein the selected terms behave as hypernyms but are not hypernyms for a given candidate hyponym x).
• the SPON model 250 comprises a multiplication unit 260 configured to perform an element-wise multiplication of the input vector x with a weight vector w t to obtain a weighted vector w t ® x, wherein ® is element-wise multiplication.
• the SPON model 250 comprises an addition unit 265 configured to add the weighted vector w t ® x to a bias vector b t to obtain a biased and weighted vector w t ® x + b t .
• / and g denote functions, wherein /: M d ® M d , and g: M d ® M d .
• the functions / and g satisfy two constraints: First, the functions / and g satisfy the constraint that the function g is a non-linear non-negative activation function.
• the SPON model 250 comprises an addition unit 280 configured to add g(x) from the ReLU layer 270 to the input vector x to obtain fix) in accordance with equation (2).
• z generally denote an input vector, wherein z e M d , and each term z e £ is represented via the input vector z. If the model parameters Q are learned in such a way that "x is-a y" implies fix) ⁇ y component wise (and vice versa), (i.e., violations to this inequality is zero), then the SPON model 250 satisfies the asymmetry and transitivity requirements of strict partial order relations.
• the SPON model 250 comprises of a loss layer 290 configured to compute a loss value xp(x, y) in accordance with equation (3) provided below: wherein the sum is taken over all components of participating dimensions d, and e is a scalar hyper parameter.
• the SPON model 250 is configured to compute and minimize a cross entropy loss for each candidate hyponym-hypernym pair (x,y), wherein the cross entropy loss is weighted, and weights factored in the cross-entropy loss are computed as a function of a frequency parameter.
• the system 200 fulfills this requirement via hypernym discovery, thereby allowing creation of hypernymy relations from a text corpus C and avoiding the problem of sparsity that often characterizes most knowledge bases.
• the system 200 implements hypernym discovery by leveraging distributional similarity metrics between words in the same text corpus C.
• the SPON model 250 is trained, during the learning process, to learn embedding for words/characters (i.e., terms) appearing in the training data T.
• O test generally denote OOV input test hyponyms.
• the SPON model 250 is configured to generate top -k ranked hypernyms for each hyponym within o test , wherein k is a positive integer.
• Y x generally denote a random variable denoting an assignment of a hypernym for an OOV hyponym x that is not seen in the training data T, wherein Y x takes a value within a set of known hypernyms in the training data T(denoted by ⁇ ).
• the SPON model 250 is configured to compute a probability of a random variable Y x taking on a value c e OP in accordance with equation (4) provided below:
• Y x 1 x ⁇ h i.e., Y x is independent of x given h
• m is a scoring function that provides a score between [0, 1] (i.e., m is a (normalized) similarity function, wherein m: M d x M d ® [0, 1])
• S x contains p-terms from 8 that provide top -p largest values for the scoring function m
• p is a hyper-parameter.
• the SPON model 250 first normalizes the values of m(7i
• Table 1 below provides examples of ranked predictions (from left-to-right) of hypernyms resulting from the SPON model 250 performing hypernym discovery on a set of eight randomly selected test queries from an English dataset.
• the top four query terms are OOV hyponym terms, while the bottom four query terms are in-vocabulary hyponym terms.
• Predicted hypernyms that match expected hypernyms are in bold, and predicted hypernyms that are not included in expected hypernyms are underlined.
• FIG. 4 is a flowchart for an example process 500 for neural network-based hypernym induction, in accordance with an embodiment of the invention.
• Process block 501 includes receiving a text corpus.
• Process block 502 includes generating a first list of triples based on the text corpus, wherein each triple of the first list comprises a first term representing a candidate hyponym, a second term representing a candidate hypernym, and a frequency value indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in the text corpus.
• Process block 503 includes training a neural network for hypernym induction based on the first list, where the trained neural network is a strict partial order network (SPON) model.
• Process block 504 includes applying the SPON model to perform a task (e.g., hypernym detection, hypernym direction, or hypernym discovery).
• a task e.g., hypernym detection, hyperny
• process blocks 501-504 are performed by one or more components of the system 200
• FIG. 5 is a high level block diagram showing an information processing system 300 useful for implementing one embodiment of the invention.
• the computer system includes one or more processors, such as processor 302.
• the processor 302 is connected to a communication infrastructure 304 (e.g., a communications bus, cross-over bar, or network).
• the computer system can include a display interface 306 that forwards graphics, text, and other data from the voice communication infrastructure 304 (or from a frame buffer not shown) for display on a display unit 308.
• the computer system also includes a main memory 310, preferably random access memory (RAM), and also includes a secondary memory 312.
• main memory 310 preferably random access memory (RAM)
• the secondary memory 312 includes, for example, a hard disk drive 314 and/or a removable storage drive 316, representing, for example, a floppy disk drive, a magnetic tape drive, or an optical disk drive.
• the removable storage drive 316 reads from and/or writes to a removable storage unit 318 in a manner well known to those having ordinary skill in the art.
• Removable storage unit 318 represents, for example, a floppy disk, a compact disc, a magnetic tape, or an optical disk, etc. which is read by and written to by removable storage drive 316.
• the removable storage unit 318 includes a computer readable medium having stored therein computer software and/or data.
• the secondary memory 312 includes other similar means for allowing computer programs or other instructions to be loaded into the computer system.
• Such means include, for example, a removable storage unit 320 and an interface 322.
• Examples of such means include a program package and package interface (such as that found in video game devices), a removable memory chip (such as an EPROM, or PROM) and associated socket, and other removable storage units 320 and interfaces 322, which allows software and data to be transferred from the removable storage unit 320 to the computer system.
• the computer system also includes a communication interface 324.
• Communication interface 324 allows software and data to be transferred between the computer system and external devices.
• examples of communication interface 324 include a modem, a network interface (such as an Ethernet card), a communication port, or a PCMCIA slot and card, etc.
• software and data transferred via communication interface 324 are in the form of signals which are, for example, electronic, electromagnetic, optical, or other signals capable of being received by communication interface 324. These signals are provided to communication interface 324 via a communication path (i.e., channel) 326.
• this communication path 326 carries signals and is implemented using wire or cable, fiber optics, a phone line, a cellular phone link, an RF link, and/or other communication channels.
• the present invention may be a system, a method, and/or a computer program product at any possible technical detail level of integration
• the computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention
• the computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device.
• the computer readable storage medium may be, for example, 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 any suitable combination of the foregoing.
• a non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing.
• RAM random access memory
• ROM read-only memory
• EPROM or Flash memory erasable programmable read-only memory
• SRAM static random access memory
• CD-ROM compact disc read-only memory
• DVD digital versatile disk
• memory stick a floppy disk
• a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon
• a computer readable storage medium is not to be construed as being transitory signals perse, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.
• Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network.
• the network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers.
• a network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.
• Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the "C" programming language or similar programming languages.
• the computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
• the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).
• electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.
• These computer readable program instructions may be provided to a processor of a computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
• These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.
• the computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
• each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s).
• the functions noted in the blocks may occur out of the order noted in the Figures.
• two blocks shown in succession may, in fact, be accomplished as one step, executed concurrently, substantially concurrently, in a partially or wholly temporally overlapping manner, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
• embodiments of the present invention provide a system, computer program product, and method for implementing the embodiments of the invention.
• Embodiments of the present invention further provide a non-transitory computer-useable storage medium for implementing the embodiments of the invention.
• the non-transitory computer-useable storage medium has a computer-readable program, wherein the program upon being processed on a computer causes the computer to implement the steps of embodiments of the present invention described herein.

Landscapes

• Engineering & Computer Science (AREA)
• Theoretical Computer Science (AREA)
• Physics & Mathematics (AREA)
• Artificial Intelligence (AREA)
• Computational Linguistics (AREA)
• General Engineering & Computer Science (AREA)
• General Physics & Mathematics (AREA)
• General Health & Medical Sciences (AREA)
• Health & Medical Sciences (AREA)
• Software Systems (AREA)
• Mathematical Physics (AREA)
• Computing Systems (AREA)
• Evolutionary Computation (AREA)
• Data Mining & Analysis (AREA)
• Life Sciences & Earth Sciences (AREA)
• Biomedical Technology (AREA)
• Biophysics (AREA)
• Molecular Biology (AREA)
• Audiology, Speech & Language Pathology (AREA)
• Machine Translation (AREA)
• Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
• Character Discrimination (AREA)

Priority Applications (3)

Applications Claiming Priority (2)

Publications (1)

Family

ID=74868969

Family Applications (1)

Country Status (5)

Families Citing this family (7)

Citations (5)

Family Cites Families (27)

• 2019
  • 2019-09-18 US US16/575,107 patent/US11068665B2/en not_active Expired - Fee Related
• 2020
  • 2020-09-15 CN CN202080065379.8A patent/CN114402330B/zh active Active
  • 2020-09-15 WO PCT/IB2020/058575 patent/WO2021053511A1/en not_active Ceased
  • 2020-09-15 GB GB2204770.8A patent/GB2602762A/en not_active Withdrawn
  • 2020-09-15 JP JP2022515915A patent/JP2022549077A/ja active Pending
• 2021
  • 2021-06-09 US US17/343,643 patent/US11694035B2/en active Active

Patent Citations (5)

Also Published As

Similar Documents

Legal Events