Abstract: A soil modeling and mapping framework for use in precision agriculture analyzes remotely-sensed data pertaining to characteristics of one or more agricultural fields, and determines optimal sampling locations from information in remotely-sensed information, terrain derivatives and satellite imagery, to develop a customized sampling design for modeling soil properties in such agricultural fields that optimized for the particular landscape in such fields. The soil modeling and mapping framework then analyzes soil samples collected based on the customized sampling design in machine learning-based models that predict soil properties in sampled, semi-sampled, and unsampled target fields. The predicted soil properties are used to develop highly-accurate maps of soil properties such as fertility maps, which may further be used for defining and creating one or more management zones with recommendations for applying the right amount of nutrients at variable rates in the correct areas.

Abstract: An iterative attention-based neural network training and processing method and system iteratively applies a focus of attention of a trained neural network on syntactical elements and generates probabilities associated with representations of the syntactical elements, which in turn inform a subsequent focus of attention of the neural network, resulting in updated probabilities. The updated probabilities are then applied to generate syntactical elements for delivery to a user. The user may respond to the delivered syntactical elements, providing additional training information to the trained neural network.

Abstract: A text classification command line interface tool assists a user label a dataset. The command line interface tool comprises a plurality of top-level modules programmed and operable to assist a user to obtain the dataset from a file location, semi-automatically search and label select datapoints of the dataset, train a first label-assist model, compute confidence scores for each of the datapoints of the dataset, and review metrics. The command line interface tool is operable to assist a user to retrain the first label-assist model via reinforcement learning until accuracy is sufficient. The CLI tool can save and export the pre-processed labeled dataset. In embodiments, a production classifier is trained using the preprocessed dataset and operable to classify new datapoints in real time. Examples of datapoints to classify include without limitation entity websites. Examples of categories include, without limitation, SHAFT and cannabis-related categories. Related computer-implemented methods are also described.

Abstract: Embodiments are described herein for training machine learning models using digital twin outputs, including for purposes of pain quantification and estimation. In various embodiments, simulation parameter(s) may be applied to a digital twin created for a subject. The digital twin may simulate an anatomical structure of the subject, and the simulation parameter(s) may cause the digital twin to generate digital twin output that simulates behavior of the anatomical structure in response to the one or more simulation parameters. Data indicative of the digital twin output may be applied as input across a pain estimation machine learning model to generate pain estimation output. Based on the pain estimation output, a quantification of pain, e.g., an estimated pain score, may be rendered using an output device and/or used to select a treatment plan.

Abstract: A method implemented in an electronic device, the electronic device and a corresponding computer program product and medium. The method includes: at least partial playback, on a user interface of the electronic device, of items obtained from computing applications and associated with at least a first class of a plurality of item classes; acquiring at least a first command to be executed, wherein the first command relates to at least one of the items that has been at least partially played back.

Abstract: A system may generate a prompt based in part on a search query from a customer client device. The prompt instructs a machine learned model to provide item predictions. And the model was trained by: converting structured data describing items of an online catalog to annotated text data (unstructured data), generating training examples based in part on the annotated text data, and training the model using the training examples. The system may receive item predictions generated by the prompt being applied to the machine learned model, the item predictions may have corresponding item identifiers. The item predictions are processed to identify a recommended item from the item predictions. The processing includes determining item information for the recommended item using an item identifier associated with the recommended item. The item information is provided to the customer client device.

Abstract: Aspects of the disclosure relate to a cloud-based parallel processing and cognitive learning computing platform. A computing platform may receive query data comprising a plurality of requested metrics. The computing platform may select a secondary node to process the query request from a plurality of secondary nodes of the computing platform. The computing platform may send the query request to the secondary node. The computing platform may send a request to generate a metric mapping table for a first requested metric to a cognitive learning module of the computing platform. The cognitive learning module may generate the metric mapping table for the first requested metric using neuron clusters that comprise a plurality of unique programmable quadratic function neurons. The computing platform may calculate a value for the first requested metric based on the metric mapping table.

Abstract: A method for controlling a serving robot is provided. The method includes the steps of: generating at least one character on the basis of at least one property related to a voice, and determining a character to be applied to a serving robot from among the at least one generated character; and generating at least one piece of visual information corresponding to the determined character, and determining a piece of visual information to be applied to the serving robot from among the at least one generated piece of visual information.

Abstract: Systems and methods for providing recommendations to users while maintaining privacy and information security for those users. In particular, user demographic information and/or geographic/environmental information can be represented as hashes, or fingerprints, which in turn can define a dimension of a recommendation matrix having another dimension defined by attributes of products, services, routines, and so on that may be associated with recommendations to the user. The values of the recommendation matrix can correspond to normalized customer review data and/or other data.

Abstract: A computer-implemented method can include: an audio input device of a portable electronic device receiving verbal speech input from a user and converting the received verbal speech input into an audio input signal; an online processing module of the portable electronic device performing at least one speech recognition operation on the audio input signal; an offline processing module of the portable electronic device performing at least one speech recognition operation on the audio input signal; an interactive game module of the portable electronic device generating user feedback based on results from the at least one speech recognition operation performed by the online processing module and the at least one speech recognition operation by the offline processing module; and a user interface of the portable electronic device providing the user feedback to the user.

Abstract: Methods and systems for generating training data for sequential conversational responses to alleviate the collection burden are disclosed herein. More specifically, the methods and systems describe generating determining dynamic conversational responses to generate training data for sequential conversation responses. For example, the system creates a special form of a random treatment control experiment to reduce the data collection while at the same time generating effectively adequate learning data for intents for the sequenced machine learning.

Abstract: A system and method for electronic health record permissioning and monetization that can grant or deny access to patient data and pay one or more entities for access to the data is presented. The present disclosure provides for a system configured to provide a patient the ability to: ‘grant,’ ‘deny,’ ‘update,’ and ‘revoke’ the permission to read data for a specific entity, and specific properties within that entity, from their personal data records (e.g., an electronic health record, a Global Patient Record (GPR), pharmaceutical records, demographic records, financial records, criminal records, or other suitable personal information). A Data-Read-Permission request can be a ‘Property Collection’ (PC) containing specific properties that describe the read permission rights and an amount the Data-Client is willing to offer for the Data-Read-Permission rights. This PC can be written as part of a blockchain transaction (TX1), which can be issued by the Data-Client.

Abstract: Embodiments in the present disclosure relate to computer network architectures and methods for predictive analysis using lookup tables as prediction models. The predictive analysis, including the generation of the lookup tables, performed by a predictive system of the present disclosure is driven entirely by a query language, such as Structured Query Language, in various embodiments. The predictive analysis, including the generation of the lookup tables, is performed without machine learning or generative artificial intelligence, in various embodiments.

Abstract: An apparatus and method for analysis of preservation requirements using a dual-predictor architecture, wherein the apparatus includes a processor and memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor receive a sustainment profile, identify at least a preservation need as a function of a deterioration predictor, wherein the deterioration predictor is configured to output a plurality of rates corresponding to a plurality of physical process variables, determine at least a relative advantage of a maintenance program as a function of an advantage predictor, wherein the advantage predictor is configured to receive the preservation need as input and output the maintenance program and the relative advantage, and display, through a graphical user interface, the at least a preservation need and relative advantage.

Abstract: A machine learning system executed by a processor may generate predictions for a variety of natural language processing (NLP) tasks. The machine learning system may include a single deployment implementing a parameter efficient transfer learning architecture. The machine learning system may use adapter layers to dynamically modify a base model to generate a plurality of fine-tuned models. Each fine-tuned model may generate predictions for a specific NLP task. By transferring knowledge from the base model to each fine-tuned model, the ML system achieves a significant reduction in the number of tunable parameters required to generate a fine-tuned NLP model and decreases the fine-tuned model artifact size. Additionally, the ML system reduces training times for fine-tuned NLP models, promotes transfer learning across NLP tasks with lower labeled data volumes, and enables easier and more computationally efficient deployments for multi-task NLP.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sharing learned information among robots. In some implementations, a robot obtains sensor data indicating characteristics of an object. The robot determines a classification for the object and generates an embedding for the object using a machine learning model stored by the robot. The robot stores the generated embedding and data indicating the classification for the object. The robot sends the generated embedding and the data indicating the classification to a server system. The robot receives, from the server system, an embedding generated by a second robot and a corresponding classification. The robot stores the received embedding and the corresponding classification in the local cache of the robot. The robot may then use the information in the cache to identify objects.

Abstract: A smart communication system including a stream processor, a plurality of inputs that are time stamped with times from a chip scaled atomic clock, and a plurality of functional blocks implemented in non-transitory computer-readable mediums. The plurality of functional blocks include an encrypted private distributed ledger block, a fusion engine block, a hashing block, and a predictive analytics block. The plurality of inputs are hashed by the hashing block to produce hashed inputs and the hashed inputs are posted into the encrypted private distributed ledger block as a hash table. The predictive analytics block processes the hash table based upon a predetermined criteria for a particular user or based upon a predictive analytics determined criteria of the particular user to produce a data subset for the particular user. The fusion engine block organizes the data subset for the particular user into an organized data subset.

Abstract: Embodiments are disclosed for machine learning-based generation of recommended layouts. The method includes receiving a set of design elements for performing generative layout recommendation. A number of each type of design element from the set of design elements is determined. A set of recommended layouts are generated using a trained generative layout model and the number and type of design elements. The set of recommended layouts are output.

Abstract: Decision tables can be automatically validated on a computer according to some examples. In one example, a system can determine a first set of values associated with a first column of a decision table and a second set of values associated with a second column of the decision table. The system can then determine that each respective value in the first set of values has a one-to-one relationship with a corresponding value in the second set of values. Based on determining that each respective value in the first set of values has the one-to-one relationship, the system determines that the first column and second column violate a third normal form (3NF) constraint. The system may then automatically rearrange the first and second columns into separate decision tables that comply with the 3NF constraint.

Abstract: A method and device for analysis of sampled physiological parameters according to at least a second-order process over time, e.g., second-order differential equation or model, for use in therapeutic, diagnostic, or predictive health applications. The system may generate an alert regarding a present or predicted health abnormality. The biometric device may be implantable, wearable, contact or non-contact, and may communicate through a network, to send an alert. The system may further comprise an actuator or therapeutic device to perform an action based on the at least second-order process.

Abstract: To support appropriate selection of a configuration of a cloud system. A computer system includes a processor 111, a storage apparatus 112 and an input/output apparatus 141, the storage apparatus 112 stores at least configuration condition information 132 indicating evaluation values for system configurations that can be constructed on cloud, the input/output apparatus 141 accepts a configuration request indicating a condition for a system configuration to be constructed on the cloud, the processor 111 obtains an evaluation value corresponding to the configuration request, compares the evaluation value corresponding to the configuration request with the evaluation values of the configuration condition information and determines a candidate for a system configuration to be proposed on the basis of a result of the comparison, and the input/output apparatus 141 outputs the candidate for the system configuration to be proposed.

Abstract: System receives request from user for decision making options, and provide gameplan document that suggests accessing first and second data source to collect options. System extracts first data records set from content copied by user from first data source, and inserts first data records set in first table in gameplan document. System extracts second data records set from content copied by user from second data source, and inserts second data records set in second table in gameplan document. System inserts combined data records set, based on first data records set joined with second data records set, in combined data table in gameplan document. System enables user to identify candidates, for options, in combined data records set in response to user commands. System determines overall scores corresponding to candidates, based on applying criteria, scored by user, to each candidate. System outputs candidates, ranked based on corresponding scores, as decision making options.

Abstract: This disclosure provides systems, methods, and devices for wireless communication that support AI model-based enhancements for RRC IDLE and INACTIVE state operations. In a first aspect, a method of wireless communication includes receiving, by a wireless communication device, artificial intelligence (AI) model configuration information for IDLE/INACTIVE state procedures; retrieving, by the wireless communication device, an AI model for IDLE/INACTIVE state procedures based on the AI model configuration information; and performing, by the wireless communication device, one or more IDLE/INACTIVE state procedures based on the AI model. Other aspects and features are also claimed and described.

Abstract: A system with graph-based Natural Language Processing (NLP) for querying, analyzing, and visualizing complex data structures is described. Such a system executes a generalized AI language model; defines and migrates a training dataset into a graph database by exposing data sources to an executing AI language model that self-defines a structure and self-writes an executable script to query the original data sources and self-writes code to load the extracted data into a graph database in the form of new nodes and new relationships with directionality between the nodes. The system further includes means for loading the extracted data into the graph database; condensing the information stored within the graph database into a condensed data structure representing the full architecture of the data in a natural language format; and responding to human language inquiries with responsive text, speech, and visualizations using the data loaded into the graph database.

Abstract: A system and method for electronic health record permissioning and monetization that can grant or deny access to patient data and pay one or more entities for access to the data is presented. The present disclosure provides for a system configured to provide a patient the ability to: ‘grant,’ ‘deny,’ ‘update,’ and ‘revoke’ the permission to read data for a specific entity, and specific properties within that entity, from their personal data records (e.g., an electronic health record, a Global Patient Record (GPR), pharmaceutical records, demographic records, financial records, criminal records, or other suitable personal information). A Data-Read-Permission request can be a ‘Property Collection’ (PC) containing specific properties that describe the read permission rights and an amount the Data-Client is willing to offer for the Data-Read-Permission rights. This PC can be written as part of a blockchain transaction (TX1), which can be issued by the Data-Client.

Abstract: A method including a user who has brand affinities about a product brand or a product brand category. The method can include analyzing whether the user has brand affinities for the product brand or the brand category with two binary classification models that can include (a) a model one to determine an affinity to a particular product brand and (b) a model two to determine an affinity to a particular product brand category. The method also can include analyzing whether the user has affinities for a similar product brand or a similar product brand category by a model three neural network. The method can include displaying recommendations and the promotions for a product brand, a product brand category, a similar product brand, or a similar product brand category to the user. Other embodiments are disclosed.

Abstract: Embodiments of the present disclosure provide a method and a device for music play. The method comprises receiving a first operation instruction in a target application for playing music; in response to the first operation instruction, presenting a first interface of the target application, the first interface including an operation control for enhancing a play effect of the music through at least one processing, the processing being used for representing music content in a way more than sound; receiving a second operation instruction for the operation control; processing the music based on the second operation instruction during a process of playing the music.

Abstract: Certain aspects of the present disclosure provide techniques for sharing machine learning models and an indication of transmission and reception points (TRPs) for which the machine learning models are applicable between wireless nodes such as user equipments (UEs) and base stations (BSs). For example, a UE receives an indication of one or more machine learning models associated with at least one TRP of one or more TRPs from a BS. The UE then uses the at least one of the one or more machine learning models for applications related to the at least one TRP. The applications may include a channel state information (CSI) compression, a cross frequency channel prediction, and a beam selection.

Abstract: A component of the technical system, a component designation and a characteristic parameter designation for a characteristic parameter of relevance to the design of the components are read and a search engine is queried with same is provided. The documents found by the search engine are read and component information, e.g. product information concerning a specific component, is extracted from said documents. The extracted component information is supplied to a machine learning routine which has been trained, using a plurality of predefined training component information and training characteristic parameter values, to reproduce predefined training characteristic parameter values using predefined training component information. Output data from the machine learning routine is selected as characteristic parameter values and inserted into a planning data record. The planning data record is then output to design the technical system.

Abstract: An iterative attention-based neural network training and processing method and system iteratively applies a focus of attention of a trained neural network on syntactical elements and generates probabilities associated with representations of the syntactical elements, which in turn inform a subsequent focus of attention of the neural network, resulting in updated probabilities. The updated probabilities are then applied to generate syntactical elements for delivery to a user. The user may respond to the delivered syntactical elements, providing additional training information to the trained neural network.

Abstract: A system receives feature parameters, each identifying possible values for one of a set of features. The system receives outcomes corresponding to the feature parameters. The system generates a simulated patient population dataset with multiple simulated patient datasets, each simulated patient dataset associated with the outcomes and including feature values falling within the possible values identified by the feature parameters. The system may train a machine learning engine based on the simulated patient population dataset and optionally additional simulated patient population datasets. The machine learning engine generates predicted outcomes based on the training in response to queries identifying feature values.

Abstract: A label switching router for a switching network configured for source routing can be configured to modify one or more reported properties of a link associated with that router based on one or more link quality metrics. For example, a router can include a link with available bandwidth of 10 Gbps, a value that can be used by a headend when evaluating nodes of the network against a set of constraints required by a particular requested connection or tunnel. A link of that router may exhibit an increased bit error rate which can be used by the label switching router to artificially deflate available bandwidth, thereby reducing the number of label switching paths including the router are selected by the headend.

Abstract: Artificial Intelligence (AI) based systems and methods are disclosed for implementing patient-specific medical adherence intervention. An AI model is trained on a first set of data comprising (1) patient data defining a plurality of medical patients having respective prescribed medications and (2) intervention communication data. During a first iteration of a medication adherence session, a second set of data comprising patient data of a new or existing medical patient is received and input by the AI model to generate a medical adherence intervention prediction defining at least a preferred intervention channel specific to the new or existing medical patient. An electronic medical adherence intervention communication, is generated, and related correspondence is sent, to the new or existing medical patient based on (1) the medical adherence intervention prediction and (2) an intervention template corresponding to the preferred intervention channel.

Abstract: A method for dynamically allocating server resources includes receiving a request from a client system, wherein the request comprises a request for a first set of streaming data, providing from the server to the client system a first portion of streaming data from the first set of streaming data, wherein the first portion is associated with a first quality of service level, receiving user activity data from the client system for the first portion of the streaming data, determining a second quality of service level for a second portion of the streaming data from the first set of streaming data, providing from the server to the client system the second portion of streaming data from the first set of streaming data, wherein the second portion provided with the second quality of service level, and wherein the first quality of service level is different from the second quality of service level.

Abstract: In some implementations, a language proficiency of a user of a client device is determined by one or more computers. The one or more computers then determines a text segment for output by a text-to-speech module based on the determined language proficiency of the user. After determining the text segment for output, the one or more computers generates audio data including a synthesized utterance of the text segment. The audio data including the synthesized utterance of the text segment is then provided to the client device for output.

Abstract: A computer-implemented system is provided that includes at least one processor that is adapted to analyze a plurality of frames from a real-time video to identify frames during which an operator is interacting with an image device to examine areas of a patient. The at least one processor is further configured to generate, from the identified frames, data representations of a first area examined by the operator interacting with the image device and further generate data representations of one or more further areas examined by the operator interacting with the image device.

Abstract: A method, computer program product, and computer system identifying intent relating to a query associated with an object. A plurality of informational items associated with the object may be identified. At least a first informational item associated with the object for which a first portion of information is already known may be identified. At least a second informational item associated with the object for which a second portion of information is unknown may be identified. A question may be generated to determine the second portion of information based upon the second portion of information being unknown. An answer may be received to determine the second portion of information. A response to the intent relating to the query may be provided based upon the first informational item for which the first portion of information is already known and the answer for the question generated to determine the second portion of information.

Abstract: Methods for building and training a network of chatbots are provided. Methods may perform data analysis on a first chatbot in the network. The first chatbot may include a first domain of intents. The data analysis may identify and rank the intents in the first domain. The first domain may represent answers to a first domain of user queries. Methods may select a predetermined number of highest-ranking intents from the first domain based on the data analysis. Methods may input the selected intents into a second chatbot in the network. The second chatbot may include a second domain of intents. The second domain may represent answers to a second domain of user queries. Methods may input a hook into the second chatbot. The hook may include a trigger word and may correspond to the first domain. When the hook is triggered, the second chatbot may invoke the first chatbot.

Abstract: An ethical AI development platform operates by: facilitating the development of a training dataset; providing access to auto machine learning tools to facilitate the development of an AI model; providing access to machine learning analysis tools to facilitate the evaluation of the AI model, wherein the machine learning analysis tools include an AI moral insight model that generates predicted moral score data associated with the AI model, wherein the AI moral insight model is trained based on at least one-hundred thousand sets of training data, wherein the training data includes reviewed media content and moral score data associated with moral indices, wherein the moral indices include: a degree of immorality/morality, a degree of betrayal/loyalty, a degree of degradation/sanctity, a degree of harm/care a degree of cheating/fairness and a degree of subversion/authority; and providing access to a version control repository for storing versions of the training dataset and the AI model.

Abstract: Disclosed systems and methods convert user-supplied textual content into animated videos. Textual input is received and processed to identify narrative elements such as characters, settings, and events. These elements are then transformed into visual scene components. Still images generated based on these components are subsequently animated in line with the narrative context. The system can automatically implement storytelling techniques adapted to incorporate neuroscience principles. The system also synthesizes speech for dialogues or narrations using voice synthesis technology that considers emotional markers, tone, and pace. Generated media and metadata are stored in a data storage system that maintains data integrity and enables efficient retrieval. Users can interact with an export interface to choose video resolution, format, and sharing options. A feedback system employing machine learning algorithms collects and analyzes user feedback for real-time adjustments to the generated animated video.

Abstract: A technology is described for correlating application performance to external event types. An example method may include obtaining electronic content from a content server associated with an electronic content provider and extracting a potential reference to an external event from the electronic content, where the external event may impact performance of an application hosted on a computing resources. The reference may be identified as being associated with an external event type using a categorization technique that associates the reference in the electronic content to one or more external event types, and an external event log may be generated to include event data for the external event type to allow correlation of the external event type to performance of the application hosted on the computing resources.

Abstract: An insight comprising a fact about a portion of data in a dataset is detected in the dataset. A context is determined by analyzing a natural language input, the context identifying an intent and an entity referenced by the natural language input. A relevance score is computed for the insight, the relevance score comprising a measure of similarity between a vector representation of the insight and a vector representation of the context, the vector representation of the insight comprising an encoding of the insight in multidimensional numerical form, the vector representation of the context comprising an encoding of the context in multidimensional numerical form. A selected insight is presented, the selected insight selected from a set of insights including the insight, the selected insight selected based on the relevance score.

Abstract: Methods, apparatus, and processor-readable storage media for automatically processing user request data using artificial intelligence techniques are provided herein. An example computer-implemented method includes generating, using a chatbot during a communication session with a user, answers to user requests by processing the user requests using a first set of artificial intelligence techniques associated with the chatbot; generating knowledge base-related predictions associated with the user requests by processing the user requests using a second set of artificial intelligence techniques associated with a knowledge base; calculating at least one score associated with at least a portion of the answers and the user requests based on qualifying values computed in connection with at least one of generating the answers and generating the knowledge base-related predictions; and performing one or more automated actions based on the at least one calculated score.

Abstract: Embodiments of the present disclosure provide an information processing method, apparatus, electronic device, and computer readable storage medium, and relate to the field of natural language processing technologies. The method includes: obtaining attribute information currently corresponding to an information responding party based on current input of a user, and then determining the information to be responded corresponding to the current input of the user, and then generating and outputting a target response based on the attribute information currently corresponding to the information responding party and the information to be responded corresponding to the current input of the user. The embodiments of the present disclosure realize that the target response is outputted more accurately when an information responding party (for example, an intelligent chatbot) interacts with the user, so as to implement the dialogue with the user.

Abstract: A system may port a data model into a strict schema system, translate the data model into a transformation rule definition, fit the transformation rule definition to a transform action, receive strict schema data, perform the transform action on the strict schema data based on the transformation rule definition to form rough data, and execute filtering and enriching operations on the rough data to form loose schema data.

Abstract: Provided is an information processing device to activate communication between an autonomous operation body and a user. The information processing device includes an application control unit that controls operation of an application relating to communication between an autonomous operation body and a user and a reflection unit that causes the autonomous operation body to reflect an operation performed by the user in the application. In the information processing device, the application control unit controls operation of an avatar imitating the autonomous operation body, and the reflection unit causes the autonomous operation body to reflect a reward obtained by the avatar on the basis of the operation performed by the user.

Abstract: Methods, systems, and computer program products for generating context-aware process-based model determinations for greenhouse gas emissions from agricultural fields are provided herein.

Abstract: A method is provided for operating a multi-channel messaging system. The method may provide automated conversation across multiple communication channels associated with a user by: selecting a first communication channel from the multiple communication channels, wherein the first communication channel is hosted by a first communication server; receiving, via an existing user interface of the first communication channel, a first user input via as part of a conversation with a chatbot, wherein the chatbot comprises a communication data structure comprising a plurality of communication paths; selecting a communication path based on the first user input; and generating a first feedback in response to the first user input according to the selected communication path.

Abstract: Systems and methods for controlling traffic flow for software experimentation are disclosed. An example method includes receiving a first traffic from a first plurality of users to receive an existing feature or a new feature, determining, from the first traffic, a first portion of the first plurality of users to receive the existing feature (with the first portion bounded by a first lower threshold and/or a first upper threshold) and a second portion of the first plurality of users to receive a new feature (with the second portion bounded by a second lower threshold and/or a second upper threshold). The method also includes providing the existing feature to the first portion, providing the new feature to the second portion, receiving feedback from the first plurality of users, and adjusting the first portion and/or the second portion based on the feedback and based on the bounds.

Abstract: Based on one metadata template determined from among a plurality of metadata templates, a screen including a scan image, a plurality of keys defined in the one determined metadata template, and value input fields each corresponding to a different one of the plurality of keys is displayed, and in a case where a user selects any one of the plurality of keys displayed in the screen, character string areas determined to match a data format of a value corresponding to the key are displayed in such a manner that the character string areas are recognizable as value candidates on the scan image.