Method and system for determining information sentiment in digital information

Abstract

Automated computer systems and methods for determining information sentiment in digital information or content are disclosed. One aspect includes: deriving, by a processor, the digital information from a source; generating, by the processor, a domain-specific machine learning sentiment score based on the digital information by one of at least two machine learning models; autonomously mapping, by the processor, a non-domain-specific knowledge graph of associations between elements in a set of digital background information; receiving, by the processor, sentiment graphs, each sentiment graph defining a sentiment; generating, by the processor, a graph sentiment score based on the non-domain-specific knowledge graph and the sentiment graphs; generating, by the processor, a final sentiment score based on the graph sentiment score and the domain-specific machine learning sentiment score; and determining, via the final sentiment score, the sentiment of the information in the digital information.

Description

[0001] Cross-referencing related applications

[0002] This application claims the right and priority of U.S. Provisional Application No. 63 / 377,994, filed September 20, 2023, entitled “SEMI-SUPERVISED SYSTEM FOR DOMAIN SPECIFIC SENTIMENT LEARNING,” the contents of which are hereby incorporated herein by reference in their entirety, pursuant to 35 USC § 119(e). Technical Field

[0003] This invention relates to systems and methods for training and enhancing machine learning networks to determine the sentiment or tone of digital information, news items, and other information sources relevant to a specific domain. Specifically, but not as a limitation, this invention relates to systems and methods for semi-supervised domain-specific sentiment learning. Background Technology

[0004] Training machine learning networks using semi-supervised techniques produces outputs with varying degrees of usability and usefulness, particularly in information and news domains and sentiment classification. There is a need to improve the results of semi-supervised training models and enhance their outputs to generate more accurate and consistently usable results. Summary of the Invention

[0005] In various aspects, this disclosure provides a method for determining the sentiment of information in digital information, the method comprising: deriving the digital information from a source by a processor; generating a domain-specific machine learning sentiment score by the processor based on the digital information using one of at least two machine learning models; autonomously drawing a non-domain-specific knowledge graph of associations between elements in a set of digital background information by the processor; receiving the sentiment graph by the processor, each sentiment graph defining a sentiment; generating a graph sentiment score by the processor based on the non-domain-specific knowledge graph and the sentiment graph; generating a final sentiment score by the processor based on the graph sentiment score and the domain-specific machine learning sentiment score; and determining the sentiment of information in the digital information by the processor via the final sentiment score.

[0006] In various aspects, the method may also include automatically updating entity attributes in at least one of a database or server based on the final sentiment score.

[0007] In various aspects, the method includes: training a first machine learning model having a base layer and a second layer for the digital information; incorporating the base layer trained for the digital information into a second machine learning model; and training the second machine learning model, including the base layer and the final layer, to generate a domain-specific machine learning sentiment score. In some aspects, the training of the first machine learning model includes training the first machine learning model to classify topics of the digital information.

[0008] In each respect, the generation of the graph emotion score includes: determining the graph similarity between each emotion graph in the emotion graph and the non-domain-specific knowledge graph; applying the emotion defined by each emotion graph in the emotion graph to the determined graph similarity to generate a graph-specific similarity tone score; and combining the graph-specific similarity tone scores of the emotion graphs.

[0009] In each aspect, the generation of the final sentiment score includes: applying a weight to the graph sentiment score to generate a weighted graph sentiment score; applying another weight to the domain-specific machine learning sentiment score to generate a weighted domain-specific machine learning sentiment score; and combining the weighted graph sentiment score and the weighted domain-specific machine learning sentiment score.

[0010] In the method, the elements may further include at least one of entity, name, location, time, or event. The method may also include at least a portion of the digital information being labeled. In some aspects of the method, the emotion defined in each emotion map is related to a contextually provided digitally.

[0011] In various aspects, this disclosure provides an automated system for defining information sentiment in digital information, the system comprising: at least one of a database or server containing entity attributes; a processor; and a computer-readable medium storing instructions executable by the processor to perform the following operations: deriving the digital information from a source by the processor; generating a domain-specific machine learning sentiment score by the processor based on the digital information using one of at least two machine learning models; autonomously drawing a non-domain-specific knowledge graph of associations between elements in a set of digital contextual information by the processor; receiving a sentiment graph by the processor, each sentiment graph defining a sentiment; generating a graph sentiment score by the processor based on the non-domain-specific knowledge graph and the sentiment graph; generating a final sentiment score by the processor based on the graph sentiment score and the domain-specific machine learning sentiment score; and determining the information sentiment in the digital information by the processor via the final sentiment score. In some aspects, the system may further include methods for automatically updating entity attributes in at least one database or server based on the final sentiment score.

[0012] In various aspects, the automated system includes instructions for: training a first machine learning model having a base layer and a second layer for the digital information; incorporating the base layer trained for the digital information into a second machine learning model; and training the second machine learning model, including the base layer and the final layer, to generate a domain-specific machine learning sentiment score. In other aspects, the instructions for training the first machine learning model include instructions for training it to classify topics from the digital information.

[0013] In various aspects, the automated system includes instructions for generating the graph sentiment scores, including: determining the graph similarity between each sentiment graph in the sentiment graph and the non-domain-specific knowledge graph; applying the sentiment defined by each sentiment graph in the sentiment graph to the determined graph similarity to generate a graph-specific similarity tone score; and combining the graph-specific similarity tone scores of the sentiment graphs.

[0014] In various aspects, the system includes instructions for generating the final sentiment score, including: applying a weight to the graph sentiment score to generate a weighted graph sentiment score; applying another weight to the domain-specific machine learning sentiment score to generate a weighted domain-specific machine learning sentiment score; and combining the weighted graph sentiment score and the weighted domain-specific machine learning sentiment score.

[0015] In various aspects, the elements include at least one of entity, name, location, time, or event. In some aspects, at least a portion of the digital information is labeled. In some aspects, the emotion defined in each emotion map is related to a contextually provided digitally.

[0016] In various respects, this disclosure provides a non-transient computer-readable storage medium having a program embodied thereon, the program being executable by a processor to perform a method for providing sentiment of digital information, the method comprising: deriving the digital information from a source by the processor; generating a domain-specific machine learning sentiment score by the processor based on the digital information using one of at least two machine learning models; autonomously drawing a non-domain-specific knowledge graph of associations between elements in a set of digital contextual information by the processor; receiving the sentiment graph by the processor, each sentiment graph defining a sentiment; generating a graph sentiment score by the processor based on the non-domain-specific knowledge graph and the sentiment graph; generating a final sentiment score by the processor based on the graph sentiment score and the domain-specific machine learning sentiment score; and determining the sentiment of the information in the digital information by the processor via the final sentiment score.

[0017] In various respects, the program that can be executed by a processor to perform the method also includes: automatically updating entity attributes in at least one of a database or a server based on the final emotion score.

[0018] In various aspects, an automated system for updating stored entity attributes based on deterministic information sentiment is disclosed. The system includes a database containing entity attributes, a processor, and a computer-readable medium storing instructions executable by the processor to perform the following operations: inputting domain-specific digital information received from a source into a trained domain-specific machine learning model; outputting a domain-specific sentiment score generated by the domain-specific machine learning model; inputting digital news information into a knowledge graph representing entities; updating the knowledge graph with the digital news information; determining the similarity between the knowledge graph and a defined sentiment graph to generate a graph sentiment score; generating entity sentiment scores based on the domain-specific sentiment scores and the graph sentiment scores; searching for entity sentiment score entries stored in the database; and automatically updating the entity sentiment score entries in the database based on the differences between the entity sentiment scores and the entity sentiment score entries.

[0019] In various aspects, a connectivity system comprising a cluster of nodes for creating and updating entity profiles based on real-time information includes: a plurality of nodes connected within the cluster; a first node among the plurality of nodes communicating with a digital information channel, the first node including instructions executable to receive digital information associated with the entity from the digital information channel, input the digital information into a trained ML network to generate a sentiment classification, and output the sentiment classification to a processing node among the plurality of nodes; and a second node among the plurality of nodes communicating with a news source, the second node including instructions to receive digital news content from the news source and to draw a knowledge graph associated with the entity based on the digital news content. Attached Figure Description

[0020] In this description, specific details, such as particular aspects, procedures, techniques, etc., are set forth for purposes of explanation and not limitation in order to provide a thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention may be practiced in other aspects besides these specific details.

[0021] The accompanying drawings, together with the detailed description below, are incorporated in and form part of the specification, and serve to further illustrate aspects of the concepts included in the claimed disclosure and to explain the various principles and advantages of those aspects. In the drawings, the same reference numerals are used throughout different views to refer to the same or functionally similar elements.

[0022] The methods and systems disclosed herein have been indicated by conventional symbols in the accompanying drawings where appropriate, showing only those specific details relevant to understanding various aspects of this disclosure, so as not to obscure this disclosure with details obvious to those skilled in the art who benefit from the description herein.

[0023] Figure 1 This is a diagram of a method for determining emotion in digital information according to at least one aspect of this disclosure.

[0024] Figure 2 An entity graph representing a knowledge graph or an emotion knowledge graph according to at least one aspect of this disclosure is shown.

[0025] Figure 3 This is a logical flowchart of a method for determining emotion in digital information according to at least one aspect of this disclosure.

[0026] Figure 4 This is a logical flowchart of a method for training a machine learning network according to at least one aspect of the present disclosure.

[0027] Figure 5 This is a flowchart of a method for generating emotion scores based on drawn graphs, according to at least one aspect of this disclosure.

[0028] Figure 6 It is a block diagram of a computer device according to at least one aspect of this disclosure.

[0029] Figure 7 It is a schematic representation of an example system including a host according to at least one aspect of this disclosure, within which a set of instructions is executable for performing any or more of the methods discussed herein. Detailed Implementation

[0030] Before discussing specific aspects and examples, the following provides some descriptions of the terminology used in this article.

[0031] An "application" can include any software module configured to perform one or more specific functions when executed by a computer's processor. For example, a "mobile application" can include a software module configured to operate by a mobile device. Applications can be configured to perform many different functions. For example, a "payment application" can include a software module configured to store and provide account credentials for transactions. A "wallet application" can include a software module having similar functionality to a payment application, which has multiple accounts pre-configured or registered to make it usable through the wallet application. An "application" can be computer code or other data stored on a computer-readable medium (e.g., a memory element or a secure element) that can be executed by a processor to perform a task.

[0032] As used herein, the term "computing device" or "computer apparatus" can refer to one or more electronic devices configured to communicate directly or indirectly with or on one or more networks. A computing device can be a mobile device, a desktop computer, etc. As examples, a mobile device can include a cellular phone (e.g., a smartphone or standard cellular phone), a portable computer, a wearable device (e.g., a watch, glasses, lenses, clothing, etc.), a personal digital assistant (PDA), and / or other similar devices. A computing device can be a mobile device or a non-mobile device, such as a desktop computer. Furthermore, the term "computer" can refer to any computing device that includes the necessary components for sending, receiving, processing, and / or outputting data and typically includes a display device, a processor, memory, an input device, and a network interface, etc.

[0033] As used herein, the term "server" can include one or more computing devices, which may be individual, independent machines located in the same or different locations, owned or operated by the same or different entities, and may also be one or more clusters of distributed computers or "virtual" machines housed in a data center. Those skilled in the art will understand and appreciate that the functionality performed by a single "server" may be distributed across multiple different computing devices for various reasons. As used herein, "server" is intended to refer to all such scenarios and should not be construed as or limited to a particular configuration. Furthermore, a server as described herein may, but does not necessarily, reside in (or be operated by) an agent of a merchant, payment network, financial institution, healthcare provider, social media provider, government agency, or any of the aforementioned entities. The term "server" may also refer to or include one or more processors or computers, storage devices, or similar computer arrangements that facilitate multi-party communication and processing through a network environment such as the Internet, but it should be understood that communication may be facilitated through one or more public or private network environments, and various other arrangements are possible. Furthermore, multiple computers (e.g., servers) or other computerized devices (e.g., point-of-sale devices) communicating directly or indirectly in a network environment can constitute a "system" (e.g., a merchant's point-of-sale system). As used herein, references to “server” or “processor” can refer to the previously stated server and / or processor that performs the preceding steps or functions, different servers and / or processors, and / or combinations of servers and / or processors. The term processor can also mean a distributed processor practice under the control of a single payment network server, encompassing all the methods disclosed herein.

[0034] As used herein, the term “system” can refer to one or more computing devices or a combination of computing devices (e.g., processor, server, client device, software application, components of these computing devices, etc.).

[0035] The terms "client device" and "user device" refer to any electronic device configured to communicate with one or more servers or remote devices and / or systems. Client devices or user devices may include mobile devices, network-enabled devices (e.g., network-enabled televisions, refrigerators, thermostats, and / or the like), computers or computing devices, POS systems, and / or any other devices or systems capable of communicating with a network. Client devices may also include desktop computers, laptop computers, mobile computers (e.g., smartphones), wearable computers (e.g., watches, glasses, lenses, clothing, etc.), cellular phones, network-enabled appliances (e.g., network-enabled televisions, refrigerators, thermostats, etc.), point-of-sale (POS) systems, and / or any other devices, systems, and / or software applications configured to communicate with remote devices or systems. A "user" may include an individual. In some respects, a user may be associated with one or more personal accounts and / or mobile devices. A user may also be referred to as a cardholder, account holder, or consumer.

[0036] Information, current events, data, and news snippets are all factors in assessing the creditworthiness, credit risk, and other status of individuals and entities when building accurate profiles of individuals, entities, and risks to automate decision-making or update systems and / or databases. For example, in the savings, lending, or credit industry, profiles built for individuals, organizations, and other entities are used to design or offer customized products to these entities. Operations teams routinely search for information and news articles about companies or businesses to determine their credit value and risk; however, they may not objectively view or understand what constitutes a negative or positive indicator, tone, or sentiment regarding entities in one or more relevant sectors, nor can they leverage current technology in the field to scale or automate the process.

[0037] One approach to scaling these processes is to attempt to automate them using trained machine learning models that can not only identify the categories and domains of information, news items, and other data, but also classify the sentiment associated with each piece of background information, news item, or entity within the provided information. However, automating such processes or training network models to determine the sentiment associated with one or more entities is challenging. Some of the challenges in training autonomous models include a lack of available data, a shortage of well-labeled information and data, difficulties in classifying information and domains based on this limited information and data, errors and biases in the available data, and the significant costs and investments associated with obtaining well-labeled and consistently high-quality data.

[0038] For example, models trained on generic domain tags, such as eBay tag data, or models derived from customer reviews or other similar publicly available data from merchant websites such as Amazon or Delta airlines, may contain identifiable sentiment, but that sentiment may be irrelevant to the required and used use cases, domains, or topics. For instance, negative customer reviews of Delta seating arrangements or in-flight entertainment may capture general customer sentiment about the ride, but it is unlikely to relate to Delta's creditworthiness or direct bankruptcy risk.

[0039] Another option for improving data relevance is to filter data or available information based on keywords. This filtering or keyword approach aims to select data that is likely more relevant to a specific use case or network training model. However, filtering can be an overly simplistic approach and not a well-tuned option because keywords or tags may employ overly broad or overly limited methods, and the selection or use of specific words or phrases may include inherent biases (and the failure to select or use other words and phrases may also include inherent biases that will affect the data). A more refined approach that considers a more complete perspective and contextual information is needed to accurately assess sentiment towards entities in a specific domain.

[0040] This paper proposes systems and methods to automatically determine sentiment in various news and digital information articles by training, improving, and enhancing machine learning networks using non-domain-specific entity graphs. This sentiment determination is then used to update entity attributes and databases, and to automate changes and decisions based on constructed entity profiles and sentiment information. The presented systems and methods aim to develop automated, accurate, and efficient processes for different use cases to extract, derive, find, and learn sentiment from contextual information across various domains. The presented techniques consist of two main parts: the first part uses auxiliary information to train machine learning models to learn how to classify domains, and then learn how to classify specific sentiments using partially labeled and freely available data; the second part enhances these models with specially tuned non-domain-specific knowledge and sentiment graphs.

[0041] While various machine learning techniques exist for understanding language, such as different natural language processing techniques, machine learning models have consistently failed to accurately derive emotion from input information. This disclosure provides techniques for more accurately deriving emotion from input information, such as, but not limited to, digital text information, via machine learning models, as well as techniques for training such machine learning models to improve their ability, reliability, and accuracy in deriving emotion from information input.

[0042] In various aspects of this disclosure, improved sentiment inference techniques allow the incorporation of machine learning models presented herein into systems such as enterprise systems or networks (referred to herein as "enterprises") to automatically and reliably update information stored in databases or data warehouses, for example, with improved sentiment understanding output based on machine learning models. According to the models proposed herein, automatic data updates based on these machine learning models can only be performed if the machine learning models can be trusted to accurately derive sentiment information from various information sources. For example, real-time deriving of sentiment information about individuals and / or entities can trigger updates to sentiment levels / scores stored in an enterprise database, which in turn can affect various outcomes, such as an entity's credit or risk rating, and thus influence permissions and behavior throughout the system.

[0043] As a non-limiting example, real-time news about a coup in a country can enable the machine learning model proposed in this paper to detect negative sentiment associated with that country. This negative sentiment can be associated with entities doing business in that country or with that country or its related entities, or it can place a certain amount of business activity at risk, thereby increasing their designated risk score. Enterprise systems can use these new scores to update entity / individual credit ratings or reputations, and based on pre-configured or predetermined thresholds, can automatically prevent the granting of loans or loans of a certain size through automated over-control mechanisms on the enterprise network. Conversely, the opposite can also be incorporated into the system described in this paper: when positive sentiment is associated with an entity, such as a company's successful IPO or product launch, the entire enterprise's data, risk scores, and permissions can be automatically updated to allow new permissions, such as granting a larger loan / purchasing additional shares, or additional / increased credit lines to be offered by the enterprise network or users of the enterprise network / system to the relevant company / entity / individual.

[0044] In various embodiments, sentiment scores can be used to provide actionable alert notifications on the user interface of a system, network, or enterprise user / administrator (referred to herein as "user"). In a non-limiting example, new or updated scores may be based on receiving, processing, and deriving new or updated sentiments about an individual / entity, as well as a risk or credit score associated with the sentiments of that individual / entity. For example, a notification could indicate an alert of a sudden overabundance of new sentiments about a particular entity or individual (e.g., a large amount of positive sentiment following a successful product launch by the entity). Users may be provided with options to further investigate the information behind the sentiments or to take additional action against the individual / entity.

[0045] Additionally, actionable notifications may be displayed to certain users, such as those set / permitted to receive such notifications and / or able to approve or reject updates to, for example, scores or attributes in a database, or approve / reject measures such as increasing credit limits or issuing funds or loans to individuals / entities. Notifications may be provided to users, for example, on an interactive graphical user interface on a system or enterprise device, wherein the notification may include any of the following: sentiment information, the reason for categorizing the sentiment information in a certain way, scores affected by the sentiment information, ratings affected by updated scores and / or sentiment information, and selectable actionable options for taking action, such as: allowing database updates, accepting or rejecting incoming sentiment information, scores, or ratings; allowing the incorporation or application / enforcement of new / updated sentiment information, scores, or ratings into or related measures, decisions, rules, or permissions for a specific individual or entity; or adjusting any of the above to increase or decrease, for example, the scope of permissions available to an individual / entity.

[0046] While this technology is susceptible to many different aspects, several specific aspects are shown in the accompanying drawings and will be described in detail herein. It should be understood that this disclosure is to be regarded as an example of the principles of the technology of the invention and is not intended to limit the technology to the aspects shown.

[0047] Figure 1This is a diagram of a method 100 for determining emotion in digital information according to at least one aspect of this disclosure. The method 100 for determining emotion in digital information is based on a combination of two separate parts. The first part of the method 100 includes training a machine learning network. In one aspect, the first part includes two machine learning networks: a first machine learning network 105 (also referred to herein as “M1”) and a second machine learning network 110 (also referred to herein as “M2”). M1 105 defines two separate neural layers: a base layer 115 and a final layer 120 (also referred to herein as “L1”). M1 105 is trained to provide a general topic or domain classification 125 as the output from the data input fed into both the base layer 115 and the final layer L1 120. Once sufficient training has occurred, the base layer 115 is incorporated into M2 110, which is then trained to provide a domain-specific emotion classification 140 having a combination of the trained base layer 115 and the final layer L2 135. The trained base layer 115 and the final layer L2 135 together constitute M2 110. The emotion classification output by M2 110 is represented by a vector or classification score Ys 145. In several aspects of this disclosure, both M1 105 and M2 110 use the same input or input from the same or similar input pools; however, the goals or target outputs of M1 105 and M2 110 differ. In various aspects, for example, M1 105 has a goal of subject classification or categorization of the input, while M2 110 has a goal of emotion classification of the input. This technique allows M1 105 and its base layer to be trained for easier tasks and goals. Right now The topic is categorized into freely available digital information, and then a pre-trained base layer is used as part of an M2 110 to generate different outputs that require further advanced training. Right now Domain-specific emotion classification.

[0048] The second part of method 100 includes determining non-domain-specific sentiment in digital information. This second part of method 100 treats sentiment classification as a graph matching task and includes extracting information or news from at least one source 150. In one aspect, this information is, for example, digital information. Source 150 can be an information source, a database, a news source, and the information can be formatted as audio, video, image, text, or any other suitable digital format. In various aspects, the information extracted, derived, or received from the at least one source 150 can be news or current event information. This information is used to construct a non-domain-specific knowledge graph 160, which includes various components of the derived information or news. For example, knowledge graph 160 can represent, or be constructed on, relationships between entities, events, locations, names, dates, sentiments, topics, etc., depending on what associations knowledge graph 160 intends to present. Knowledge graph 160 can represent or include one or more news snippets or pieces of information from various news sources 150. In every respect, the digital information received or extracted from News Source 150 involves an entity such as a company, individual, institution, state, or government.

[0049] In various aspects, the system may include user 165 defining 170 the sentiment of various news snippets, information, current events, or other forms of digital information from domain users. The system then uses these defined sentiments to create or construct a sentiment knowledge graph 175 (also referred to herein as a “sentiment graph”), which includes various graphs representing different sentiment types. The system may refer to one or more computing devices or combinations of computing devices (e.g., processors, servers, client devices, software applications, components of these computing devices, and / or the like).

[0050] Exemplary emotion types may include, but are not limited to, positive, negative, neutral, slightly negative, moderately negative, highly negative, slightly positive, moderately positive, and highly positive. Then, the knowledge graph 160 is compared with various emotion knowledge graphs 175 via a graph similarity function 180 g(Vec(E), Vec(Ii)), where Vec(E) represents a vector or value of the knowledge graph 160, and Vec(Ii) represents a vector or value (or vectorized value) of the emotion graph 175 compared with the knowledge graph 160. The graph similarity function may be weighted or multiplied by the emotions extracted from or attributed to the relevant emotion graph 175 as defined by the relevant emotion graph to produce a graph emotion score for that particular emotion graph 175. Each graph similarity function 180 utilizes the emotion weights defined by the relevant emotion knowledge graph 175. The graph similarity function 180 is then combined with other graph emotion scores 190 to derive a total graph emotion score Yg 192. The overall graph sentiment score Yg192 is then combined with the machine learning sentiment score Ys145 to produce the final sentiment score Y195 representing the entity's sentiment. Each of the overall graph sentiment score Yg192 and the classification score Ys145 can also be weighted during the combination to produce the final sentiment score Y195.

[0051] Figure 2 An entity graph 200 representing a knowledge graph or sentiment knowledge graph according to at least one aspect of this disclosure is shown. The entity graph 200 includes a plurality of nodes 204. Each of the nodes 204 corresponds to an attribute set (e.g., including attribute 12021, attribute 22022, attribute 32023, attribute 42024, attribute 52025, attribute 62026, attribute 72027, attribute 82028, ... and attribute 202). n The entity graph 200 can define news or information that can be associated with entities, unknown entity graphs, or known entity graphs, as well as sentiment defined by the user or reader of the information. Therefore, attribute 202 can correspond to entities, entity attributes, news stories, names, locations, sentiments, dates, events, and other news information extracted from information sources, news sources, or other databases. Furthermore, the attribute set can include any number of attributes (e.g., any positive integer). Accordingly, the entity graph 200 can include any number of attributes (e.g., any number of positive integers). For example, Node 204 (any positive integer).

[0052] Still referencing Figure 2The structure of the entity graph 200 is determined by the placement of edges 206. Typically, each node 204 is connected to at least one other node 204 via edge 206. Some nodes 204 may be connected to multiple other nodes 204 via multiple edges. For example, the node 204 corresponding to attribute 22022 is only connected to the node 204 corresponding to attribute 12021 via edge 206. Conversely, the node 204 corresponding to attribute 12021 is connected via edge 206 to the nodes corresponding to attributes 22022, 32023, 42024, 72027, 82028, and 92021. n 202 n Node 204. Although in Figure 2 The non-restrictive aspect describes a particular entity graph structure, but entity graph 200 may have any structure, wherein each node 204 is connected to one or more other nodes 204 via an edge 206.

[0053] Figure 3 This is a logic flowchart of a method 300 for determining sentiment in digital information according to at least one aspect of this disclosure. According to method 300, information is first derived from a source. The source may be a news source, an information source, or any other background information source; in all respects, this source is a digital information source. This information is then used by one or more processors to generate a domain-specific machine learning (also referred to herein as “ML”) sentiment score based on the digital information using at least one of at least two machine learning models. The two models... Figure 1 The values ​​are shown as M1 105 and M2 110, and the training of the machine learning model and the generation of domain-specific sentiment scores are described in detail in... Figure 4 middle.

[0054] Still referencing Figure 3 The first part of method 300 provides a domain-specific ML score, while the second part of method 300 treats sentiment classification as a graph matching task. Method 300 then autonomously or automatically draws 315, generates, or constructs at least one knowledge graph describing how various entities are related, associated, or interact with each other. This drawing 315 can be performed based on information derived 305 or from separate information extraction or derivation steps (not shown) and / or from separate information sources. The information sources can be internal or external (e.g., third-party) databases, servers, or digital information sources from systems. The knowledge graph is automatically drawn 315 by the system to show various relationships between several entities in one or more graphs. The types of relationships or entities can be customized within the system. The drawing 315 of the knowledge graph can be used to find or identify one or more entities from digital information sources.

[0055] In some aspects, a knowledge graph is constructed to illustrate entity interactions and relationships; in others, a knowledge graph is created autonomously (315) to illustrate relationships between various elements, including but not limited to entities, events, locations, names, dates, or any other relevant information derived from news sources. The system, database, server, or other processor can then receive (320) other sentiment graphs generated based on information, digital information, or feedback provided by domain users, whereby users define or determine the sentiment in various articles, information snippets, news information, or background information snippets. In each aspect, the graphs are generated internally and use sources separate from those used for autonomously drawing (315) knowledge graphs. These sentiment graphs are used to represent different sentiment scores or sentiment states and can correspond to, for example, positive sentiment or tone, negative sentiment, or neutral sentiment. The autonomously drawn (315) knowledge graph is then compared with the received (320) sentiment graphs via, for example... Figure 1 The graph similarity function 180 shown is compared with other graph similarity functions to generate a non-domain-specific graph sentiment score of 325.

[0056] In some aspects, similarity between graphs is calculated based on graph embeddings, and then the similarity of the embedded vectors is compared with distance measurements. The system then automatically generates a final sentiment score by combining domain-specific machine learning sentiment scores and non-domain-specific graph sentiment scores. Weights can be added to any of these scores; these weights can be products of machine learning network training or assigned based on other factors, observations, trial and error, or other settings. The final generated sentiment score can be used to determine the sentiment of the information source on which the derived or extracted digital information or knowledge and / or sentiment graph is based. In various aspects, the final generated sentiment score is related to specific entities that can be mentioned in the digital information.

[0057] Figure 4 This is a logic flowchart of a method 400 for training a machine learning network according to at least one aspect of this disclosure. Method 400 details one aspect, wherein a machine learning network can be trained... Figure 3 The two machine learning models described in the document and specifically in Figure 3 The method 300 shown in the figure generates a domain-specific machine learning sentiment score at step 310. Now refer to Figure 3 and 4 Extracting 405 or 305 information from the source as background information for at least part of the tagging. The exported 305 can be exported or extracted from any information source, including databases and news sources. Figure 3 ) or extract 405 ( Figure 4The information may be in various formats, including audio, video, images, text, or other suitable digital formats. In some aspects of this disclosure, the information extracted, derived, or received from the information source may be general background information including news or current event information. This information has been tagged or populated with categories or categorized in one or more ways. For example, this information may be tagged with labels such as "stock price." Extraction of this information may include extracting background information that may, for example, describe the subject of a news article, and extracting other information that is generally available and provided by the news source and is at least partially tagged or categorized.

[0058] Now for reference Figure 1 and 4 Because the information is at least partially labeled, extracting or deriving the information from 405 can be used as input to a basic machine learning model, for example, M1 105 ( Figure 1 The system is trained on 410 without requiring any additional domain-specific knowledge. In various aspects, this part of the labeled data and publicly available information is used to train 410 corresponding to the first machine learning model of M1 105. The first machine learning model may include two layers, namely, a base layer and a final layer, and is trained on 410 using a large amount of labeled data to determine the subject or classification of the information derived or extracted in 405.

[0059] Still referencing Figure 1 and 4 In model M1 105 ( Figure 1 After being trained for 410, the trained base layers of the model are copied or merged into 415 to correspond to M2 110 ( Figure 1 In the second machine learning model, because the base layers have been finely tuned in M1 105 to classify topics or categories, or trained to provide outputs on any other suitable target based on training on a large amount of at least partially labeled data, model M2 110, especially its final layer L2 135 ( Figure 1 This can be tuned to train only 420 to determine, output, or generate 425 domain-, category-, or topic-specific sentiment or sentiment scores. For example, this second model M2 110 can generate output scores, values, or vectors that indicate whether an article or other piece of information is negative, positive, or neutral in the category or topic the model has identified. This output is a domain-specific machine learning sentiment score or classification Ys145 (…). Figure 1 Finally, in each respect, the weights to be applied to the output can be learned during training of M1 105 or M2 110, and can also be output by M2 110. These weights can be applied to the generated domain-specific machine learning sentiment score of 425.

[0060] Figure 5This is a logic flowchart of a method 500 for generating non-domain-specific sentiment scores based on drawn graphs, according to at least one aspect of this disclosure. According to method 500, digital information input is first received 505 by a computing device, server, or system, and this digital information can be compared with… Figure 3 and 4 The digital information marked 305 and 405 is identical, or comes from the same source, or may be other digital information received separately from other sources. The system then autonomously draws a non-domain-specific knowledge graph of the relationships between elements in a set of digital background information using a processor, server, or computing device. This autonomous drawing 510 provides a knowledge graph of the relationships between different elements identified in the digital information. The elements may be entities, wherein the drawing associates entities with each other; in other respects, the elements may be various other features or elements, such as names, locations, dates, events, entities, and the knowledge autonomous drawing 510 connects all these various features with each other.

[0061] According to method 500, the processor sentiment graph or sentiment knowledge graph receives 520 each sentiment graph that defines the sentiment or tone of the information. These can be sentiment graphs generated autonomously by a computing device, server, or system, or the graphs can be generated by a domain-specific user who assigns sentiment scores or sentiment attributes to each piece of digital information. Then, the various sentiment scores, attributes, and / or sentiments / tones provided can be autonomously plotted 510 into sentiment graphs representing the tone or sentiment of the digital information. Figure 2 An example of the structure of a knowledge graph or sentiment graph is shown (see Entity Graph 200). The example includes receiving sentiment scores or descriptions from domain users, such as those related to various situations and / or news or current items. Sentiments can be negative, positive, neutral, or somewhere in between.

[0062] Another example could include a domain user or autonomous system generating a score for each information item or digital information, and the sentiment score associated with each item then being autonomously plotted onto a graph, where the graph represents an average sentiment score, which may in turn represent positive, negative, neutral sentiment (or sentiments between these categories). A graph similarity function can be applied to determine the similarity between a knowledge graph plotted by 530 and various sentiment graphs, the graph similarity function being, for example, derived from... Figure 1The graph similarity function shown is 180 g(Vec(E), Vec(Ii)). For each graph similarity function comparing a specific emotion graph and a knowledge graph, an emotion score of 540 for that specific emotion graph is applied. The applied emotion score of 540 is multiplied by the graph similarity function to produce a product between each relevant emotion graph-knowledge graph combination. The product of each emotion score and the graph similarity function is combined with the products of all other emotion scores and graph similarity functions, for example... Figure 1 As seen in equation 190, to generate 550 Figure 1 The tone score of the specific similarity of the Yg192 sentiment graph.

[0063] Figure 6 This is a block diagram of a computer device 1000 according to at least one aspect of this disclosure. The computer device 1000 or its subsystems can be used to perform the methods and functions described herein. Example computer device 1000, also referred to herein as subsystem 1000, is interconnected via system bus 1010. Additional subsystems are shown, such as printer 1018, keyboard 1026, fixed disk 1028 (or other memory including computer-readable media), display screen 1022 coupled to display adapter 1020, etc. Peripheral devices and I / O devices coupled to input / output (I / O) controller 1012 (which may be a processor or other suitable controller) can be connected to the computer system via any number of components known in the art, such as serial port 1024. For example, serial port 1024 or external interface 1030 can be used to connect the computer device to a wide area network, such as the Internet, a mouse input device, or a scanner. The interconnection via system bus 1010 allows central processing unit 1016 to communicate with each subsystem and control the execution of instructions from system memory 1014 or fixed disk 1028, as well as the exchange of information between subsystems. System memory 1014 and / or fixed disk 1028 may embody computer-readable media.

[0064] Figure 7This is a schematic representation of an example system 1 including a host 2000 according to at least one aspect of this disclosure, within which a set of instructions for performing any or more of the methods discussed herein can be executed. In various aspects, the host 2000 operates as a standalone device or can be connected (e.g., networked) to other machines. In a networked deployment, the host 2000 can operate as a server or client machine in a server-client network environment, or as a peer-to-peer (or distributed) network environment. The host 2000 can be a computer or computing device, a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, a portable music player (e.g., a portable hard disk-driven audio device, such as a Mobile Picture Experts Group Audio Layer 3 (MP3) player), a network device, a network router, a switch, or a bridge, or any machine capable of executing a set of instructions (sequentially or otherwise) specifying the actions to be taken by that machine. Furthermore, although only a single machine is described, the term "machine" should also be understood to include any set of machines that individually or collectively execute a set (or more sets) of instructions to perform any one or more of the methods discussed herein.

[0065] Example system 1 includes a host 2000 that runs a host operating system (OS) 2001 on a processor or multiple processors / processor cores 2003 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both) and various memory nodes 2005. The host OS 2001 may include a super manager 2004 capable of control functions and / or communicating with virtual machines (“VMs”) 2010 running on machine-readable media. The VM 2010 may also include a virtual CPU or vCPU 2009. Memory nodes 2005 and 2007 may be linked or pinned to virtual memory nodes or vNodes 2006, respectively. When a memory node 2005 is linked or pinned to a corresponding virtual node 2006, data can then be directly mapped from the memory node 2005 to its corresponding vNode 2006.

[0066] All the various components shown in host 2000 can be connected to and linked to each other, or communicate with each other via a bus (not shown) or via other coupling or communication channels or mechanisms. Host 2000 may also include a video display, audio devices or other peripheral devices 2020 (e.g., liquid crystal display (LCD), alphanumeric input devices including, for example, a keyboard, cursor control devices (e.g., a mouse, voice recognition or biometric authentication unit, external driver, signal generation device, such as a speaker), persistent storage device 2002 (also referred to as a disk drive unit), and network interface device 2025. Host 2000 may also include a data encryption module (not shown) for encrypting data. The components provided in host 2000 are those commonly found in computer systems that are suitable for use with aspects of this disclosure, and are intended to represent a broad category of such computer components known in the art. Thus, system 1 may be a server, a minicomputer, a host computer, or any other computer system. The computer may also include different bus configurations, network platforms, multiprocessor platforms, etc. Various operating systems may be used, including UNIX, LINUX, WINDOWS, QNX ANDROID, IOS, CHROME, TIZEN, and other suitable operating systems.

[0067] The disk drive unit 2002 may also be a solid-state drive (SSD), hard disk drive (HDD), e.MMC, and UFS, or other computer or machine-readable medium storing one or more sets of instructions and data structures (e.g., data or instructions 2015) embodying or utilizing any one or more methods or functions described herein. Instructions 2015 may also reside wholly or at least partially within main memory node 2005 and / or processor 2003 during execution of the instructions by host 2000. Processor 2003 and memory node 2005 may also include machine-readable media.

[0068] Instructions 2015 can also be sent or received via network 2030 through network interface device 2025 using any of several well-known transport protocols (e.g., Hypertext Transfer Protocol (HTTP)). The terms "computer-readable medium" or "machine-readable medium" should be understood to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated cache and server) storing one or more sets of instructions. The term "computer-readable medium" should also be considered to include any medium capable of storing, encoding, or carrying instruction sets for execution by machine 2000 and causing machine 2000 to perform any one or more methods of this application, or capable of storing, encoding, or carrying data structures utilized by or associated with such instruction sets. Therefore, the term "computer-readable medium" should be understood to include, but is not limited to, solid-state storage, optical and magnetic media, and carrier signals. This medium may also include, but is not limited to, hard disks, floppy disks, flash memory cards, digital video optical discs, random access memory (RAM), read-only memory (ROM), etc. The exemplary aspects described herein can be implemented in an operating environment including software installed on a computer, software installed in hardware, or a combination of software and hardware.

[0069] Those skilled in the art will recognize that the Internet service can be configured to provide Internet access to one or more computing devices coupled to the Internet service, and that the computing devices may include one or more processors, buses, memory devices, display devices, input / output devices, etc. Furthermore, those skilled in the art will understand that the Internet service can be coupled to one or more databases, repositories, servers, etc., which can be used to implement any aspect of the present disclosure described herein.

[0070] Computer program instructions may also be loaded onto a computer, server, 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 or other programmable apparatus, provide for implementing the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0071] For example, a suitable network may include any one or more of the following or interface with any one or more of the following: local intranet, PAN (Personal Area Network), LAN (Local Area Network), WAN (Wide Area Network), MAN (Metropolitan Area Network), Virtual Private Network (VPN), Storage Area Network (SAN), Frame Relay connection, Advanced Intelligent Network (AIN) connection, Synchronous Fiber Network (SONET) connection, digital T1, T3, E1 or E3 line, Digital Data Service (DDS) connection, DSL (Digital Subscriber Line) connection, Ethernet connection, ISDN (Integrated Services Digital Network) line, dial-up port (e.g., V.90, V.34 or V.34bis analog modem connection), cable modem, ATM (Asynchronous Transfer Mode) connection, or FDDI (Fiber Distributed Data Interface) or CDDI (Copper Distributed Data Interface) connection. In addition, communications may include links to any of a variety of wireless networks, including WAP (Wireless Application Protocol), GPRS (General Packet Radio Service), GSM (Global System for Mobile Communications), CDMA (Code Division Multiple Access) or TDMA (Time Division Multiple Access), cellular telephone networks, GPS (Global Positioning System), CDPD (Cellular Digital Packet Data), RIM (Dynamic Research Ltd.) full-duplex paging networks, Bluetooth radio, or IEEE 802.11-based radio frequency networks. Network 3030 may also include or interface with any one or more of the following wired or wireless, digital or analog interfaces or connections: RS-232 serial connection, IEEE-1394 (FireWire) connection, Fibre Channel connection, IrDA (Infrared) port, SCSI (Small Computer System Interface) connection, USB (Universal Serial Bus) connection, or other wired or wireless, digital or analog interfaces or connections, mesh or Digi® networks.

[0072] Broadly speaking, a cloud-based computing environment is a resource that typically combines large groups of processors (e.g., within a web server) in computing power and / or large groups of computer memory or storage devices in storage capacity. Systems providing cloud-based resources may be accessible only to their owners, or such systems may be accessible to external users who deploy applications within the computing infrastructure to benefit from large computing or storage resources.

[0073] A cloud can be formed, for example, by a network of network servers comprising multiple computing devices, such as hosts 2000, where each server 2035 (or at least multiple servers) provides processor and / or storage resources. These servers manage workloads provided by multiple users (e.g., cloud resource customers or other users). Typically, each user's workload requirements for the cloud change in real time, and sometimes drastically. The nature and extent of these changes usually depend on the type of business associated with the user.

[0074] It is worth noting that any hardware platform suitable for performing the processing described herein is suitable for use with the technology. As used herein, the terms "computer-readable storage medium" and "computer-readable storage media" refer to any one or more media that participate in providing instructions to the CPU for execution. This medium can take many forms, including (but not limited to) non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical discs or magnetic disks, such as fixed disks. Volatile media include dynamic memory, such as system RAM. Transmission media include coaxial cables, copper wires, and optical fibers, as well as others, which include conductors containing one side of a bus. Transmission media can also take the form of acoustic or optical waves, such as acoustic or optical waves generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media include, for example, floppy disks, hard disks, magnetic tapes, any other magnetic media, CD-ROMs, digital video discs (DVDs), any other optical media, any other physical media with markings or perforations, RAM, PROMs, EPROMs, EEPROMs, FLASH EPROMs, any other memory chips or data exchange adapters, carrier waves, or any other media from which a computer can read.

[0075] Various forms of computer-readable media can participate in loading one or more sequences of one or more instructions to the CPU for execution. A bus carries data to system RAM, from which the CPU fetches and executes instructions. Instructions received from system RAM may optionally be stored on a fixed disk before or after execution by the CPU.

[0076] Computer program code used to perform operations on aspects of this technology can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, or the like, and regular procedural programming languages ​​such as the "C" programming language, Go, Python, or other programming languages, including assembly language. The program code can execute entirely on the user's computer, partially on the user's computer, or as a standalone software package, 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 can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can connect to an external computer (e.g., via the Internet using an Internet service provider).

[0077] Examples of methods according to various aspects of this disclosure are provided below in the numbered clauses. An aspect of the methods may include any one or more of the numbered clauses described below, as well as any combination thereof.

[0078] Clause 1. An automated computer-implemented method for determining information sentiment in digital information, the method comprising: deriving the digital information from a source by a processor; generating a domain-specific machine learning sentiment score by the processor based on the digital information using one of at least two machine learning models; autonomously drawing a non-domain-specific knowledge graph of associations between elements in a set of digital contextual information by the processor; receiving the sentiment graph by the processor, each sentiment graph defining a sentiment; generating a graph sentiment score by the processor based on the non-domain-specific knowledge graph and the sentiment graph; generating a final sentiment score by the processor based on the graph sentiment score and the domain-specific machine learning sentiment score; and determining the information sentiment in the digital information by the processor via the final sentiment score.

[0079] Clause 2. The method described in Clause 1 further includes the processor automatically updating entity attributes in at least one of the database or server based on the final sentiment score.

[0080] Clause 3. The method according to any one of Clauses 1-2 further comprises: training a first machine learning model having a base layer and a second layer for the digital information by the processor; incorporating the base layer trained for the digital information into a second machine learning model by the processor; and training the second machine learning model including the base layer and the final layer by the processor to generate the domain-specific machine learning sentiment score.

[0081] Clause 4. The method according to any one of Clauses 1-3, wherein the training of the first machine learning model comprises training the first machine learning model to classify the topics of the digital information.

[0082] Clause 5. The method according to any one of Clauses 1-4, wherein the generation of the graph sentiment score comprises: the processor determining the graph similarity between each sentiment graph in the sentiment graph and the non-domain-specific knowledge graph; the processor applying the sentiment defined by each sentiment graph in the sentiment graph to the determined graph similarity to generate a graph-specific similarity tone score; and the processor combining the graph-specific similarity tone scores of the sentiment graphs.

[0083] Clause 6. The method according to any one of Clauses 1-5, wherein the generation of the final sentiment score comprises: the processor applying a weight to the graph sentiment score to generate a weighted graph sentiment score; the processor applying another weight to the domain-specific machine learning sentiment score to generate a weighted domain-specific machine learning sentiment score; and the processor combining the weighted graph sentiment score and the weighted domain-specific machine learning sentiment score.

[0084] Clause 7. The method according to any one of Clauses 1-6, wherein the element includes at least one of an entity, name, location, time, or event.

[0085] Clause 8. The method according to any one of Clauses 1-7, wherein at least a portion of the digital information is marked.

[0086] Clause 9. The method according to any one of Clauses 1-8, wherein the emotion defined by each emotion map in the emotion map relates to a contextual situation provided digitally.

[0087] Clause 10. An automated system for updating stored entity attributes based on deterministic information sentiment, the system comprising a database containing entity attributes, a processor, and a computer-readable medium storing instructions executable by the processor to perform the following operations: inputting domain-specific digital information received from a source into a trained domain-specific machine learning model; outputting a domain-specific sentiment score generated by the domain-specific machine learning model; inputting digital news information into a knowledge graph representing entities; updating the knowledge graph with the digital news information; determining a similarity between the knowledge graph and a defined sentiment graph to generate a graph sentiment score; generating entity sentiment scores based on the domain-specific sentiment scores and the graph sentiment scores; searching for entity sentiment score entries stored in the database; and automatically updating the entity sentiment score entries in the database based on the differences between the entity sentiment scores and the entity sentiment score entries.

[0088] Clause 11. The system according to Clause 10, wherein the automatic updating of the entity sentiment score entry includes at least one of the following: deleting, modifying, adding to the entity sentiment score entry in the database, subtracting from the entity sentiment score entry, or applying weight to the entity sentiment score entry.

[0089] Clause 12. A connectivity system comprising a cluster of nodes for creating and updating entity profiles based on real-time information, the system comprising: a plurality of nodes connected within the cluster; a first node among the plurality of nodes communicating with a digital information channel, the first node including instructions executable to receive digital information associated with an entity from the digital information channel, input the digital information into a trained ML network to generate a sentiment classification, and output the sentiment classification to a processing node among the plurality of nodes; and a second node among the plurality of nodes communicating with a news source, the second node including instructions to receive digital news content from the news source and to draw a knowledge graph associated with the entity based on the digital news content.

[0090] Clause 13. The system according to Clause 12, wherein the second node further communicates with the user server to receive a sentiment classification of content from the user server, wherein the sentiment classification is generated by the domain user.

[0091] Clause 14. The system according to any one of Clauses 12-13, wherein the user server includes instructions to receive new emotion categories from domain users; and to update the user emotion database storing the emotion categories with the new emotion categories received from the domain users.

[0092] Clause 15. The system according to any one of Clauses 12-14, wherein the second node includes additional instructions to receive the emotion classification from the domain user server; and to draw emotion graphs based on the emotion classification, wherein each emotion graph contains an emotion tone.

[0093] Clause 16. The system according to any one of Clauses 12-15, wherein the second node includes additional instructions to generate an entity sentiment score based on the similarity between the knowledge graph and at least one of the sentiment graphs, and to output the entity sentiment score to the processing node.

[0094] Clause 17. The system according to any one of Clauses 12-16, wherein the processing node includes instructions to perform the following operations: receiving the emotion classification from a first node; receiving the entity emotion score from a second node; determining a final entity emotion score based on the emotion classification and the entity emotion score; and pushing the final entity emotion score to a database node among a plurality of connected nodes, the database node storing a profile of the entity.

[0095] Clause 18. The system according to any one of Clauses 12-17, wherein the database node includes instructions to: receive the final entity sentiment score from the processing node; and update the profile of the entity stored in the database node with the final entity sentiment score.

[0096] Clause 19. The system according to any one of Clauses 12-18, wherein the first node includes instructions to detect the digital information from the digital information channel.

[0097] Clause 20. The system pursuant to any one of Clauses 12-19, wherein the second node includes instructions to detect the digital news content from the news source.

[0098] The foregoing detailed description includes reference to the accompanying drawings, which form part of the detailed description. The drawings illustrate exemplary aspects. These exemplary aspects, also referred to herein as "examples," are described in sufficient detail to enable those skilled in the art to practice the subject matter of the invention.

[0099] The various aspects described above are presented as examples only and are not intended to be limiting. The description is not intended to limit the scope of the invention to the forms set forth herein. Rather, as those skilled in the art will understand, this specification is intended to cover such alternatives, modifications, and equivalents that may fall within the scope of the invention.

[0100] While specific aspects and examples of the system have been described above for illustrative purposes, various equivalent modifications can be made within the scope of the system, as will be recognized by those skilled in the art. For example, although processes or steps are presented in a given order, alternative aspects may execute routines in a different order, and some processes or steps may be deleted, moved, added, subdivided, combined, and / or modified to provide alternatives or sub-combinations. Each of these processes or steps can be implemented in a variety of different ways. Furthermore, although processes or steps are sometimes shown as being executed sequentially, these processes or steps may be changed to be executed in parallel, or may be executed at different times.

[0101] Without departing from the scope of the claims, aspects may be combined, other aspects may be utilized, or structural, logical, and electrical changes may be made. Those skilled in the art will further understand that any separating words and / or phrases indicating two or more alternative terms, whether in the specification, claims, or drawings, should generally be understood to cover the possibility of including one, any, or both of the stated terms, unless the context otherwise requires. Therefore, the detailed description should not be construed in a limiting sense, and the scope is defined by the appended claims and their equivalents. In this document, as is common in patent documents, the terms “a” or “an” are used to include one or more. In this document, the term “or” is used to refer to a non-exclusive “or”, such that unless otherwise indicated, “A or B” includes “A but not B,” “B but not A,” and “A and B.”

[0102] All patents, patent applications, publications, or other public materials mentioned herein are incorporated herein by reference in their entirety, as if each individual reference were expressly incorporated by reference separately. All references and any material thereof, or portions thereof, referred to herein by reference, are incorporated only to the extent that the incorporated material does not conflict with any existing definitions, statements, or other public materials set forth in this disclosure. Therefore, and to the extent necessary, the disclosure set forth herein supersedes any conflicting material incorporated herein by reference, and the disclosure expressly set forth in this application shall prevail.

[0103] Those skilled in the art will recognize that, in general, the terms used herein and especially in the appended claims (e.g., the body of the appended claims) are intended as “open-ended” terms (e.g., the term “including” should be interpreted as “including but not limited to”, the term “having” should be interpreted as “having at least”, the term “includes” should be interpreted as “including but not limited to”, etc.). Those skilled in the art will further understand that if a particular number of the introduced claim statements are intended, then such intent will be expressly stated in the claims, and where no such statements are present, such intent does not exist. For example, to aid understanding, the appended claims may contain introductory phrases “at least one” and “one or more” used to introduce the claim statements. However, the use of such phrases should not be construed as implying that the introduction of a claim statement by the indefinite article "a(a)" or "an" limits any particular claim containing such an introduced claim statement to a claim containing only one such statement, even when the same claim includes the introductory phrase "one or more" or "at least one" and indefinite articles such as "a(a)" or "an" (e.g., "a(a)" and / or "an" should generally be interpreted as meaning "at least one" or "one or more"); the same applies to the use of definite articles used to introduce a claim statement.

[0104] Furthermore, even if a specific number of claims is explicitly stated, those skilled in the art will recognize that such statements should generally be interpreted as meaning at least the stated number (e.g., simply stating "two statements" without other modifiers generally means at least two statements, or two or more statements). Moreover, in cases where conventions such as "at least one of A, B, and C, etc." are used, such constructions are generally intended to be understood by those skilled in the art in the sense of the convention (e.g., "a system having at least one of A, B, and C" will include, but is not limited to, systems having only A, only B, only C, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). In cases where conventions such as "at least one of A, B, or C, etc." are used, such constructions are generally intended to be understood by those skilled in the art in the sense of the convention (e.g., "a system having at least one of A, B, or C" will include, but is not limited to, systems having only A, only B, only C, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.).

[0105] Regarding the appended claims, those skilled in the art will understand that the operations described herein can generally be performed in any order. Furthermore, although the claims are presented in one or more sequences, it should be understood that various operations may be performed in orders other than those described, or that various operations may be performed simultaneously. Examples of such alternative orderings may include overlapping, interleaving, interruption, reordering, ascending, preparatory, supplementary, simultaneous, inverted, or other varied orderings, unless the context otherwise specifies. Moreover, terms such as “in response to,” “related to,” or other past tense adjectives are generally not intended to exclude such variations, unless the context otherwise specifies.

[0106] It is worth noting that any reference to “an aspect,” “one aspect,” “example,” “an example,” etc., means that a particular feature, structure, or characteristic described in connection with that aspect is included in at least one aspect. Therefore, the phrases “in an aspect,” “in one aspect,” “in an example,” and “in an example” appearing in various places throughout this specification do not necessarily all refer to the same aspect. Furthermore, a particular feature, structure, or characteristic may be combined in one or more aspects in any suitable manner.

[0107] As used herein, unless the context clearly specifies otherwise, the singular forms “a”, “an”, and “the” include the plural referent.

[0108] Directional phrases used herein, such as, but not limited to, top, bottom, left, right, down, up, front, back, and variations thereof, will refer to the orientation of the elements shown in the accompanying drawings and are not limiting to the claims unless otherwise expressly stated.

[0109] Unless otherwise specified, the terms “about” or “approximately” as used in this disclosure mean an acceptable error in a particular value as determined by one of ordinary skill in the art, depending in part on how the value was measured or determined. In some aspects, the terms “about” or “approximately” mean within 1, 2, 3, or 4 standard deviations. In some aspects, the terms “about” or “approximately” mean within 50%, 200%, 105%, 100%, 9%, 8%, 7%, 6%, 5%, 4%, 3%, 2%, 1%, 0.5%, or 0.05% of a given value or range.

[0110] In this specification, unless otherwise indicated, all numerical parameters should be understood to begin and be modified in all cases by the term “about,” whereby the numerical parameters have the inherent variability of the underlying measurement techniques used to determine the values ​​of the parameters. At least, and without attempting to limit the application of the doctrine of equivalence to the scope of the claims, each numerical parameter described herein should be understood at least based on the number of significant figures reported and by applying ordinary rounding techniques.

[0111] Any numerical range listed herein includes all subranges falling within the listed range. For example, the range "1 to 100" includes all subranges between (and inclusive of) the listed minimum value of 1 and the listed maximum value of 100, i.e., a minimum value equal to or greater than 1 and a maximum value equal to or less than 100. Furthermore, all ranges listed herein include the endpoints of the listed range. For example, the range "1 to 100" includes endpoints 1 and 100. Any maximum numerical limit stated in this specification is intended to include all lower numerical limits contained therein, and any minimum numerical limit stated in this specification is intended to include all higher numerical limits contained therein. Therefore, the applicant reserves the right to amend this specification (including the claims) to expressly describe any subranges contained within the range expressly described herein. All such ranges are inherently described in this specification.

[0112] The terms “comprise” (and any form of inclusion, such as “comprises” and “comprising”), “have” (and any form of having, such as “has” and “having”), “include” (and any form of inclusion, such as “includes” and “including”), and “contain” (and any form of containing, such as “contains” and “containing”) are all open-ended linking verbs. Therefore, a system that “comprises,” “has,” “includes,” or “contains” one or more elements possesses, but is not limited to, those one or more elements. Similarly, the elements of a system, apparatus, or device that “comprises,” “has,” “includes,” or “contains” one or more features possess those one or more features, but are not limited to, possessing only those one or more features.

[0113] The corresponding structures, materials, actions, and equivalents of all components or steps plus functional elements in the following claims are intended to include any structure, material, or action for performing a function in combination with other claimed elements as specifically claimed. The description of the invention has been presented for purposes of illustration and description, but this description is not intended to be exhaustive, nor is it limited to the disclosed forms. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the claimed subject matter. Exemplary aspects have been chosen and described to best explain the principles of the invention and its practical application, and to enable those skilled in the art to understand various aspects of this disclosure with modifications suitable for the particular intended use.

Claims

1. An automated computer-implemented method for determining information sentiment in digital information, the method comprising: Digital information is derived from a source by at least one processor; The at least one processor generates a domain-specific machine learning sentiment score based on the digital information using one of at least two machine learning models. The processor autonomously draws a non-domain-specific knowledge graph of the relationships between elements in a set of digital background information. The at least one processor receives an emotion map, where each emotion map defines an emotion. The at least one processor generates a graph sentiment score based on the non-domain-specific knowledge graph and the sentiment graph; The at least one processor generates a final sentiment score based on the graph sentiment score and the domain-specific machine learning sentiment score. as well as The at least one processor determines the sentiment of the information in the digital information based on the final sentiment score. The generation of the graph sentiment score includes: The at least one processor determines the graph similarity between each emotion graph in the emotion graph and the non-domain-specific knowledge graph; The at least one processor applies the emotion defined by each emotion graph in the emotion graph to its determined graph similarity to generate a graph-specific similarity tone score; and The at least one processor combines the graph-specific similarity tone scores of each sentiment graph in the sentiment graph. The generation of the final emotion score includes: The at least one processor applies weights to the graph sentiment score to generate a weighted graph sentiment score; The at least one processor applies another weighting to the domain-specific machine learning sentiment score to generate a weighted domain-specific machine learning sentiment score; and The weighted graph sentiment score and the weighted domain-specific machine learning sentiment score are combined by the at least one processor.

2. The method according to claim 1, further comprising: The at least one processor automatically updates the entity attributes in at least one of the databases or servers based on the final emotion score.

3. The method according to claim 1, further comprising: The at least one processor trains a first machine learning model having a base layer and a second layer on the digital information; The at least one processor incorporates the base layer trained on the digital information into the second machine learning model; as well as The second machine learning model, including the base layer and the final layer, is trained by the at least one processor to generate the domain-specific machine learning sentiment score.

4. The method of claim 3, wherein the training of the first machine learning model comprises training the first machine learning model to classify the topics of the digital information.

5. The method of claim 1, wherein the element comprises at least one of an entity, a name, a location, a time, or an event.

6. The method of claim 1, wherein at least a portion of the digital information is tagged.

7. The method of claim 1, wherein the emotion defined by each emotion map in the emotion map is related to a contextually provided digitally.

8. An automated system for updating stored entity attributes based on deterministic information sentiment, the automated system comprising: A database contains entity attributes; At least one processor; as well as A computer-readable medium storing instructions that can be executed by the processor to perform the following operations: The at least one processor inputs domain-specific digital information received from the source into a trained domain-specific machine learning model; The at least one processor outputs a domain-specific sentiment score generated by the trained domain-specific machine learning model; The at least one processor inputs digital news information into a knowledge graph representing entities; The knowledge graph is updated by the at least one processor using the digital news information; The at least one processor determines the graph similarity between the knowledge graph and each emotion graph in the defined emotion graph; The at least one processor applies the emotions defined by each emotion graph to its determined graph similarity to generate a graph-specific similarity tone score; The at least one processor combines the graph-specific similarity tone scores of each sentiment graph to generate a graph sentiment score. The at least one processor applies weights to the graph sentiment score to generate a weighted graph sentiment score; The at least one processor applies another weight to the domain-specific sentiment score to generate a weighted domain-specific sentiment score; The weighted graph sentiment score and the weighted domain-specific sentiment score are combined by the at least one processor to generate an entity sentiment score; The at least one processor retrieves entity sentiment score entries stored in the database; and Based on the difference between the entity emotion score and the entity emotion score entry, the processor automatically updates the entity emotion score entry in the database.

9. The automated system of claim 8, wherein the automatic update of the entity sentiment score entry in the database comprises at least one of: deleting, modifying, adding to the entity sentiment score entry in the database, subtracting from the entity sentiment score entry, or applying weight to the entity sentiment score entry.

10. A connectivity system comprising a cluster of nodes for creating and updating entity profiles based on real-time information, the connectivity system comprising: Multiple nodes connected within the cluster; The first node among the plurality of nodes, which communicates with the digital information channel, includes instructions executable to perform the following operations: Receive digital information associated with the entity from the digital information channel; The digital information is fed into a trained machine learning (ML) network to generate domain-specific sentiment scores; The domain-specific emotion score is output to the processing node among the multiple nodes; and The second node among the plurality of nodes communicates with the news source, and the second node includes instructions to perform the following operations: Receive digital news content from the news source; A knowledge graph associated with the entity is drawn based on the digital news content; Receive emotion graphs, where each emotion graph defines an emotion; Determine the graph similarity between each emotion graph and the knowledge graph; The emotions defined by each emotion graph are applied to their determined graph similarity to produce a graph-specific similarity tone score; Combine the graph-specific similarity tone scores of each emotion graph to generate a graph emotion score; The sentiment score of the graph is output to the processing node; The processing node includes instructions that can be executed to perform the following operations: Receive the domain-specific sentiment score from the first node; Receive the graph sentiment score from the second node; The weighting is applied to the graph sentiment score to generate a weighted graph sentiment score; Another weighting is applied to the domain-specific sentiment score to generate a weighted domain-specific sentiment score; The weighted graph sentiment score and the weighted domain-specific sentiment score are combined to produce a final sentiment score. as well as The final emotion score is pushed to a database node among the plurality of nodes, and the database node stores a profile of the entity.

11. The connection system of claim 10, wherein the second node further communicates with at least one domain user server to receive a sentiment classification of content from the domain user server, wherein the sentiment classification is generated by a domain user.

12. The connection system of claim 11, wherein the domain user server includes instructions to perform the following operations: Receive new emotion categories from users in at least one domain; and The user emotion database storing the emotion categories is updated with the new emotion categories received from users in the at least one domain.

13. The connection system of claim 11, wherein the second node includes additional instructions to perform the following operations: Receive the emotion classification from the domain user server; and Emotional maps are drawn based on the aforementioned emotion classification, where each emotion map contains an emotional tone.

14. The connection system of claim 10, wherein the database node includes instructions to perform the following operations: Receive the final emotion score from the processing node; and The profile of the entity stored in the database node is updated with the final sentiment score.

15. The connection system of claim 10, wherein the first node includes instructions to perform the following operations: Detect the digital information from the digital information channel.

16. The connection system of claim 10, wherein the second node includes instructions to perform the following operations: Detect the digital news content originating from the news source.

Images