Continuous identity

Abstract

And continuous identity. Systems and methods are provided for determining continuous identities over time and in real time, a request to validate the identity of an individual comprising a plurality of partial identifiers is made to get a quick response by a computing system employing a machine learning algorithm in a manner that is objective, substantially linearly scalable and interpretable due to the application of objective parameters. A request for identification verification may be made with a partial set of identifiers of individuals to be identified. The computing system may access a database of credentials and a database of intensities of relationships between the credentials, and provide information from such credentials to a machine learning algorithm, the machine learning algorithm uses credentials, strengths of relationships, weights, and adjustable risk tolerances to determine whether to validate, or neither to validate, nor to invert an identity.

Description

Technical Field

[0002] The present invention generally relates to using machine learning algorithms to manage and curate sets of credentials for enhancing the trustworthiness of identity determination. Background Art

[0003] In some contexts, humans currently determine identity based on the use of multiple incomplete credentials. For example, if a person refuses or cannot identify himself to an administrative agency, those administrative agencies may collect partial identification information. Alternatively, if a person attempts to identify himself but does not have clear identification credentials, it may be necessary to try to use partial identification information to verify the identity. Alternatively, if someone attempts to identify a deceased person or a person captured in a video or photo, it may be necessary to use partial identification information to find the identity. Typically, if a person or deceased person exists, at least some information can be collected, including fingerprints, one or more photos, and other identification information, such as height, weight, hair color, eye color, apparent age, teeth and other data, such as observable deviations from the usual appearance, including identification or photos of any scars, tattoos, lost appendages, etc. In many cases, not all information is available.

[0004] For example, if a traffic camera captures a photo or video of a person driving through a red light or speeding, only partial identification information may be available. For example, such information may include one or more of the following: partial identification of the make, model, and year of the vehicle, a partial license plate number, a black and white or color photo or video through a car window that may be blurry or low resolution and may only show certain incomplete features of the driver and / or passengers, such as size, skin color, hair color, presence or absence of facial hair, certain clothing details, etc. These details may not be sufficient to identify the driver with certainty alone. Further steps may therefore need to be taken to perform the identification.

[0005] As another example, the body of a deceased person may be found in a state of decay or degradation that makes immediate visual or fingerprint identification difficult or impossible. The body may possess partial fingerprints, partial facial features, some hair, some teeth, or other physical information from which the identity can be determined. In addition, the body may be partially or fully dressed so that the brand, size, pattern, etc. may match a photo or other information. The body may be in possession of or near certain documents such as purchase receipts, a wallet with certain documents, or other types of documents or items. Identification may require more than just observing the body and nearby documents.

[0006] A person seeking a passport may need to provide various types of documentation to prove right to the passport. Such documentation may not be easily obtained or verified by a person. Such documentation may include discrepancies due to typographical errors such as misspelled names or addresses, or differences in photographs taken at different stages of a person's life. Other discrepancies may exist. Therefore, confirming identification may require more than just observing the document.

[0007] In some cases, a person with a changed name may be needed to verify identity. A divorced person (or a child of a divorced person) may have a name change. A person who has been threatened by another person may have obtained a legal name change to feel safer from being tracked by the threatening person, but may otherwise have the same or similar identifying details as they had before the name change. In this case, the photograph or taxpayer identification number may be the same on various documents, while the name, address, or other information may change. Confirming identification may require more than just observing the document.

[0008] A person brought to a medical center in a coma may not have immediately verifiable identification. And the environment may not allow for immediate identification via fingerprints. In such cases, other data points such as tattoos, hair color, eye color, height, weight, skin color, scars, various other features of the body, type or style of clothing, receipts or other documents in pockets or with the person, and other items may provide clues to the person's identity. However, confirming identification may require more than just observing these items.

[0009] In some cases, a person seeking a loan, submitting a job application, applying to college, or seeking to obtain a professional or business investment may submit application information with possible or apparent inconsistencies. In such cases, further identification may be required.

[0010] Various types of identification techniques, such as biometric identification (eg, fingerprints or dental records) and identification through database searches or comparison documents, are known in the art, but are deployed in ways that are not reliably repeatable, objective, and scalable.

[0011] For example, using the collected data, one may initiate multiple searches hoping to verify the identity of an individual based on the available data points. However, different people may proceed in different ways based on their own intelligence, training, biases, or other differences. And as the number of searches increases by orders of magnitude, scaling the search from a single search performed by a person to a hundred searches, thousands, or millions of searches performed by a person results in significant overhead. Such overhead can be in the form of management, human resources, additional desks and additional buildings for workers, travel time to assign tasks, coordination of workers, and the like.

[0012] As deployed in various known systems, biometric authentication can use a process of authenticating an individual by recording their biomarkers (e.g., fingerprints taken from multiple angles, rotations, positions, etc.). Then, when the individual presents their biomarkers to identify themselves, a subset of the measurement points can be used to authenticate the identity of the individual. This allows for a certain amount of inconsistency (also known as "noise") in the process and still make the process work. Systems such as this example of fingerprint measurement produce a two-dimensional database of markers, but do not know to incorporate the time dimension.

[0013] It is known to employ a similar process by using data other than biomarkers. For example, a given first name, last name, or date of birth may be used to search many separate databases. Such databases are often isolated from one another. Furthermore, such databases may not be able to track changes in last names or changes in both last names and first names over time. In the event that such a change may occur, the change may result in a lengthy human verification process at many levels, which may extend the identity verification process to days, weeks, or even months, or it may result in unexplained mismatches.

[0014] In view of the many problems that exist in existing systems, it is desirable to have a reliably repeatable process and system for determining the continuous identity of an entity in real time.

[0015] It would also be desirable to have an objective process and system for determining the continuous identity of an entity in real time that is not affected by differences in bias, education, training, etc. among a person (or persons).

[0016] It would also be desirable to have a scalable process and system for determining the continuous identity of an entity in real time that does not suffer from the many inefficiencies introduced by humans using known systems.

[0017] It would also be desirable to have an explainable process and system for determining the continuous identity of an entity in real time that does not rely on the vagaries of decision making in less logical environments.

[0018] The above-mentioned deficiencies are intended to provide only an overview of some problems of conventional systems and methods, and are not intended to be exhaustive. After reading the following description, other problems of conventional systems and corresponding benefits of various non-limiting embodiments described herein may become more clear. Summary of the invention

[0019] A simplified overview of the specification is given below to provide a basic understanding of some aspects of the specification. This overview is not an extensive review of the specification. It is neither intended to identify the key or important elements of the specification nor to describe any scope specific to any embodiment of the specification or any scope of the claims. Its only purpose is to give some concepts of the specification in a simplified form as a preface to a more detailed description given later. The embodiments set forth below are intended to be non-limiting unless such embodiments describe the only way to implement the system and method of the present invention.

[0020] The purpose of the system and method of the present invention is to provide a reliable and repeatable process and system for determining the continuous identity of an entity in real time. This reliable and repeatable property can be derived in part from using the logical process set forth herein, rather than relying too much on the logically fallible process of the human mind.

[0021] Another object of the system and method of the present invention is to provide an objective process and system for determining the continuous identity of an entity in real time. Such objectivity can be derived from a process and system that is away from over-reliance on human (or many people's) bias, education, training, etc., which can lead to non-objective determinations in the process of evaluating several or many identity queries.

[0022] Another object of the systems and methods of the present invention is to provide a scalable process and system for determining the continuous identity of an entity in real time. Human labor does not scale well and often scales in an asymptotic manner that approaches limits based on the amount of expansion. However, the systems and methods described herein typically scale linearly or substantially linearly in their ability to handle additional identity queries and typically do not approach limits for practical reasons. That is, the ability to scale substantially linearly often appears to be almost unlimited within the amount of queries that may be needed or used. Such systems and methods do not suffer from many of the inefficiencies introduced by humans using known systems. They can scale linearly or substantially linearly over a specific time. That is, if the number of resources and the amount of queries increase at a 1:1 ratio, the systems and methods can scale linearly or substantially linearly over time, as opposed to the asymptotic expansion encountered when humans are heavily involved.

[0023] Another object of the system and method of the present invention is to provide an interpretable process and system for determining the continuous identity of an entity in real time. Such a system and method can provide a set of objective parameters that can be verified for objectivity by using the same parameters for different data. Such an objective and interpretable process and system does not rely on the vagaries of decision making in an environment with poor logic. For example, two people may be asked to write a description of the decision process used in making a complex decision, but it will generally be seen that (even in the case where both make the same decision) the interpretation of the process used will vary from decision to decision. The level of precision with which the decision process of the present invention can be explained is a level that humans do not know can be achieved or approached.

[0024] The inventive concepts set forth herein may be implemented in various forms, including systems, methods, and computer-readable media.

[0025] In an embodiment, a machine learning algorithm may be used to determine continuous identity in real time, wherein a request to verify the identity of an individual is sent or received over a computer network at the first time. Such a request may include one or more partial identifiers. In conjunction with this, a database storing identification credentials of multiple people or entities may be accessed. In the following description, the term "entity" may be considered to refer to a person or other types of living, legal or other entities that may need to be identified, such as a company, a car, etc. Preferably, the database will be large, but it may also be a database storing information of a limited number of entities. Different types of identification credentials may be stored and accessed for different individuals in the entity group within the first database. And certain types of identification credentials may include various types of information that do not overlap for a particular entity or between different entities. It is also expected that the database may include identification credentials that have expired for one or more entities and identification credentials that have not expired for one or more entities. The second database (or a table or organizational structure within the first database) may store information about the strength of the relationship between the various identification credentials stored in the first database. Machine learning algorithms may be applied to partial identifiers, identification credentials, and the strength of the relationship. The machine learning algorithm may determine whether the identity of an entity can be verified, refuted, or neither verified nor refuted. The machine learning algorithm can establish and apply weights to various relationships based on training, feedback, and search. And the machine learning algorithm can apply adjustable risk tolerances to the determination. After making the determination, the system can send a response to the request to verify the identity. In such a system, it is expected that the rate at which the machine learning algorithm processes multiple individuals will scale substantially linearly over time as equal amounts of resources and requests for verification are applied.

[0026] In certain embodiments, it may be desirable to periodically update the first database to store further identification credentials of the individual. After (or concurrently with) that update, it may be desirable to update the second database to add or modify one or more relationship strengths based on the further identification credentials stored during the update. It may also be desirable to again apply the machine learning algorithm to the partial identifiers, identification credentials, and strengths of relationships to update the determination of whether the identity of the individual can be verified, refuted, or neither verified nor refuted.

[0027] In certain embodiments, it is desirable to provide a precise interpretation of the objective parameters used by a machine learning algorithm to determine whether an individual's identity can be verified, refuted, or neither verified nor refuted.

[0028] In some embodiments, a request to verify the identity of an individual may include an indication of a risk tolerance for use by a machine learning algorithm.

[0029] In some embodiments, it may be desirable to receive, over a computer network, another request seeking to verify the identity of a second individual. Such a request may include a second set of partial identifiers and a second indication of a risk tolerance that the machine learning algorithm may use. In this case, it may be desirable for the machine learning algorithm to be able to apply different risk tolerances to different requests. In such embodiments, it may be desirable to apply the machine learning algorithm to the second set of partial identifiers, the identification credentials, the strength of the relationship, and the second indication of the risk tolerance to determine whether the identity of the individual can be verified, refuted, or neither verified nor refuted.

[0030] In other embodiments, a request to verify the identity of an individual desires to include an indication of a desired minimum level of strength of the relationship between identification credentials to be used by the machine learning algorithm.

[0031] In other embodiments, it is desirable to assign an authoritative status to one or more of the plurality of identification credentials stored in the first database.

[0032] Moreover, as further detailed herein, other embodiments are directed to other exemplary methods of facilitating continuous identity authentication and associated systems, devices, and / or other articles of manufacture.

[0033] These and other features of the disclosed subject matter are described in greater detail below. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The devices, assemblies, systems, and methods of the disclosed subject matter are further described with reference to the accompanying drawings, in which:

[0035] Figure 1 is an illustrative process for the management and curation of continuous identities;

[0036] Figure 2 is a block diagram of illustrative components including components of an identity;

[0037] Figure 3 is a block diagram illustrating changing data that may be stored in a database related to management and curation of continuous identities;

[0038] Figure 4 is a block diagram illustrating changing data that may be stored in multiple databases related to the management and curation of continuous identities;

[0039] Figure 5 is a block diagram of an illustrative architecture for the management and curation of continuous identities; and

[0040] Figure 6 is a block diagram of an illustrative architecture of a computer that may be used in a system or method for management and curation of continuous identities. DETAILED DESCRIPTION

[0041] As described above, conventional processes for handling user information and / or solutions for misuse or potential misuse provide some security measures, user control, and / or correction for data breaches, such efforts fail to provide meaningful solutions for increased user control and / or security of user information, and / or suffer further costs or disadvantages, etc., among other deficiencies.

[0042] Figure 1 A simplified flow chart of a method 100 of an embodiment of the present invention is depicted, which is used herein to determine continuous identity in real time. In various applications, it is often necessary and desirable to determine in real time rather than taking hours, days, or weeks to determine. At an airport security checkpoint, it may be necessary to determine identity within seconds. In an online loan application process, it may be necessary to determine identity within minutes. In a passport application process, it may be necessary to determine identity within days. In a job application process, it may be necessary to determine identity within weeks. Each of these is exemplary only, and different processes may have different real-time requirements.

[0043] When the process begins and proceeds to step 110, in step 110, the system of the present invention may receive a request to verify the identity of an individual. The request will include multiple partial identifiers based on which the system is required to make a determination. Such partial identifiers may include name, address, date of birth, ID number, reference, biometric data, or the following Figure 2The request may be sent by a user of an application on a mobile device, a user of a web browser on a computer, an automated process performed by another system, or in many other ways. However, processing the request would be largely impossible without providing some partial identifier, so at least some partial identifier (whether weak or strong) is required.

[0044] In steps 120 and 122, the process accesses two databases. Such databases may be stored on separate servers, stored on the same server, widely distributed, or securely maintained. The databases may be accessed serially or in parallel. It may be necessary to access the databases housed in Figure 2 For ease of reference, the database of step 120 may be considered to be a database (or set of databases) that stores various types of identification credentials for many different individuals. In some cases this may be an employee database, in some cases a prisoner database, in some cases a voter database, in some cases a government identity database, in some cases a customer database for a retail store, etc. The database of step 120 may contain multiple types of identification credentials from a single category of credentials or credentials from multiple categories (e.g., Figure 2 ). The types of data can overlap partially or completely for different people, such as a collection of driver's licenses, social security cards, passports, and birth certificates for many people, or the types of data can not overlap for different people, such as driver's licenses for some people, passports for others, and birth certificates for another group of people. Some such credentials may be old or expired, such as birth certificates or old driver's licenses, while other credentials may be current, such as seasonal ski passes, student ID cards, or current driver's licenses. In some databases, the various types of credentials for a particular person may not overlap, such as a person's social security card with name, signature, and social security number, as opposed to a photo of Mr. Schutte's third grade class showing the school name, year, and a picture that can be used to identify the students. Although the two types of credentials identified in the previous paragraph may not have any overlapping data that allows a direct match, a relationship between the two can be established with a third credential, such as a school yearbook, which shows a list of students in Mr. Schutte's third grade class and contains the names that appear on the social security card, or perhaps a photo from a newspaper article that shows one of the students from the class photo, the student having the name that appears on the social security card. Therefore, it is possible or necessary to track the identity request from one credential to another through one or more additional credentials.As described herein with respect to the example of discussing a severed finger, it may be necessary to track the path through several types of credentials and establish the relationship between the several types of credentials to confirm identity.

[0045] Go to step 122, in which another database storing information about the strength of the relationship between credentials is accessed. The database can be organized in a way that retains the strength of the relationship between various pieces of data in different credentials. Alternatively, it can retain data about the strength of the relationship between different credentials without considering the individual data points within the credentials. Alternatively, it can be maintained as a combination of such information. Preferably, the strength of the relationship is assigned by a machine learning algorithm that operates on the data to be used in step 120 and creates or modifies the strength of the relationship after having been trained with an appropriate set of training data such as represented in database 510. As will be understood by a person of ordinary skill, the training data preferably varies with respect to various types of data that can be retrieved, such as photos, fingerprints, credit reports, account statements, passports, biometric data, and other relevant data. The technician will recognize that a machine learning system 514 trained 530 only for credit reports will likely perform poorly when asked to compare photos to determine identity, a machine learning system 514 trained 530 only for photos will likely perform poorly when asked to compare account statements to determine identity, and so on. Appropriate training (and possible retraining) is necessary to establish the weighting parameters used by the machine learning algorithm. One or more sets of standardized training data and training routines may be prepared and maintained so that they can be audited and reset in a standardized manner. It may be desirable to allow the machine learning system 514 to continue learning from query data received in addition to the training data; however, some systems that place a high priority on accountability, accuracy, and interpretability may wish to only allow training using standardized data sets.

[0046] In step 130, the data retrieved in steps 120 and 122 is provided to the machine learning algorithm 514 along with the identity query received in step 110. If the data is acceptable, the method proceeds to step 140.

[0047] In step 140, the machine learning system 514 uses a parallel computing architecture 540 to apply at least one suitable trained model 530 to evaluate the provided data, including the query, the partial identity identifier, the retrieved identification credentials, and the retrieved relationship strengths to try to determine a response to the query. Preferably, the machine learning system 514 will apply the weights determined by the training in its model and obtain a result indicating whether the identity can be verified, refuted, or neither verified nor refuted. As described above, in some embodiments, the algorithm can continue to be trained even during use. In such an embodiment, it may be desirable to provide a user interface from which a human user can provide whether the obtained result is correct or incorrect, or may be ambiguous in terms of correctness. Alternatively, a separate evaluation (not shown) performed by a different machine learning system may be obtained to evaluate whether the result is correct, incorrect, or ambiguous. Such feedback alone or in combination with internal feedback based on ongoing training can be used to enhance the reliability of the weights within the trained model. The method then proceeds to optional step 150. In some embodiments, it may be desirable to receive an indication of the minimum strength of certain relationships that will be required to verify an identity based on certain types of credentials. Similarly, it may be desirable to allow a querying user or system to assign an authoritative status to one or more credentials. For example, a fingerprint record or passport may be considered an authoritative indicator of identity in some circumstances, while a receipt from a retail store, a photograph, or a library card may be considered a less certain indicator of identity that can aid in determination but is not authoritative.

[0048] In the optional step 150 used in some embodiments of the present method, a risk tolerance may be applied to the determination based on the specific needs of the query that has been made or the specific needs of the user or system making the query. For example, in the case of an identity query to determine whether to make a short-term loan of $50, the risk tolerance may allow less certainty than in the case of an identity query to determine whether the evidence shows that an unidentified body belongs to a specific person. In one of the exemplary cases, the risk of a false positive or false negative is much lower than in other cases. Because various types of users or systems may need to query the method and system of the present invention, it is desirable in some embodiments to provide various risk tolerances that can be adjusted for each query or even within a query. For example, a country's customs agency may give a higher weight to passports from stable countries and a lower weight to passports from unstable countries, while assigning a lower weight to confirmatory evidence in one case than in another case. If another country is allied with an unstable country and conflicts with a stable country, the customs agency of that country may provide the opposite weighting. Therefore, it can be seen that in some embodiments, it is desirable to allow adjustable risk tolerances that can be specific to a specific use case, can focus on certain data, or can be a general overall risk tolerance. It may also be desirable to allow some or all of the risk tolerance to be adjusted for each query, or to allow a single risk tolerance to be stably applied across multiple applications. As an example of this, images captured from a CCTV camera during the day may result in a lower risk of misidentification due to ample lighting, while images captured from a CCTV camera at night may result in a higher risk of misidentification. Thus, it may be desirable to allow a user to adjust the risk at various times of the day, or even to set pre-programmed risk tolerances that may automatically change at certain times, on certain days, or in other preset ways. In some embodiments, it may be desirable to receive risk tolerance information along with the request received in step 110. In such embodiments, it may be desirable to have the ability to receive and apply different risk tolerances with each new query.

[0049] After step 150, the method preferably proceeds to steps 160 and 170. In step 160, a response to the query may be sent to the entity that made the request, such as a user device 502 or an automated system 503. Alternatively, depending on the purpose of the query, the response may be sent to a different system or entity rather than back to the original entity that made the query. If the method is one in which an interpretable result is desired or required, in step 170, the machine learning system 514 may send an accurate interpretation of the objective parameters used to determine whether the identity can be verified, refuted, or neither verified nor refuted. Such an interpretation may be important to avoid claims of bias or discrimination. Alternatively, if the determination is to be used for evidence or as a reason for taking an action, the interpretation may be important. Such an interpretation may be important for an enterprise to maintain documentation of its practices. The level of detail of the precise interpretation may vary depending on the specific application. And it may be desirable to provide a user interface or API in which the desirability of the precise interpretation can be set and the level of detail of the interpretation can be set.

[0050] In use for execution Figure 1 In a system of the method set forth in , it is desirable to construct the system in such a way that the rate at which the machine learning system 514 processes a number of queries can scale substantially linearly over time as new computing resources are added at the same rate as the number of requests being validated. This provides a substantial advantage for systems in which many queries can be processed.

[0051] After step 160 is completed, in some embodiments, it will be desirable to determine (step 180) whether a database update is required or expected. If a database update is not required or expected, the method can be terminated for immediate querying. If a database update is required or expected, the method can proceed to step 190. In step 190, the database of credentials can be updated to include new data or remove data that is no longer considered useful. In conjunction with the update, after or during the update, it may be necessary to update the relationship in the second database accessed in step 122. When updating the relationship, the method can proceed to steps 120 and 122, respectively, through nodes (a) and (b). At this point, the method can continue as described above, while using the updated data to process previously processed queries or new queries. Such updates to the database in steps 190 and 195 can be performed at regular intervals, upon receiving an indication that new data is available, or according to another parameter related to the entity or system using the method to process the query.

[0052] In some embodiments of the invention, it may be desirable to require no less than two minutes to complete step 160 after step 110. In other embodiments, such as validation of Internet forms, it may be desirable to require no less than ten seconds to complete step 160 after step 110. In other embodiments, longer time periods may be acceptable, but will generally remain shorter than a time period in which a human can search for relevant data, assess the strength of the relationship between credentials, and provide an accurately interpretable determination.

[0053] Figure 2 2 is a block diagram 200 of components 203 through 240 including data related to an identity 202 according to certain embodiments of the present disclosure. Identity 202 may include data related to birth certificate 203, credit report 204, passport 206, driver's license 208, billing information 210, banking information 212, location 214, receipts 216, friends (or social network) 218, tendencies 220, coloring 222, size 224, facial features 226, fingerprints 228, clothing 230, and / or many other data sources represented by 240. Some or all of components 203 through 240 may be retrieved locally or over a suitable network connection from one or more data sources (e.g., databases db1 through dbn in data store 508). It will be appreciated that components 203 through 240 are provided for illustrative purposes only and that the identities described herein may include data such as, for example, a plurality of data sources. Figure 4 203 to 240 provided in more or less components. For example, the identity of a young person may include a birth certificate 203, coloring 222, size 224, facial features 226, and fingerprints 228, but may lack other components that may be expected of an older person, such as a driver's license 208, a passport 206, receipts 216, etc. As another example, the identity of a company may include bank information 212, receipts 216, billing information 210, and location 214, but may lack information that a natural person may have, including a driver's license 208, facial features 226, fingerprints 228, clothing 230, etc. The following description of identity data that may be present in certain components is intended to be exemplary and not exhaustive. Those of ordinary skill in the art will recognize that such data may vary from entity to entity, country to country, era to era, etc. For example, passport data varies according to country, passport type, passport issuance year, and other factors that cannot be fully captured in the present disclosure. This is also true for many identity components.

[0054] The birth certificate component 203 may include data such as date of birth, location, time, parents' names, first name, last name, hospital name, length and weight at birth, biological sex, race, etc.

[0055] The credit report component 204 may include first name, last name, tax identification number, current and past addresses when known, various bank and account data including loans, payments, scheduled payments, amounts owed, and various other payment and debt information.

[0056] Passport component 206 may include a photograph, first name, last name, address, signature, passport number, country of origin, country of residence, additional details regarding place of residence, date of birth, issue and expiration dates, biological sex, height at issue, weight at issue, hair color, eye color, and various other details. It is contemplated that it is possible that passport component 206 and birth certificate 203 of a single individual may record the same first name, last name, date of birth, biological sex, and certain other details, but it is likely that weight and height will vary between the two sources, and possibly even between various instances of the same person's passport data.

[0057] Driver's license component 208 may include much of the same type of information as passport component 206, but a driver's license may indicate the issuing province or state rather than the country, one or more types of vehicles the driver is authorized to drive, the date the driver may turn 21, and other data relevant to the driver's license. For a single individual, when passport component 206 and driver's license component 208 are compared, the photo may vary, the height and weight may vary, the hair color may vary, and other details may vary, but it would be expected that the date of birth, biological sex, and name would often (but not always) match.

[0058] The bill information component 210 may include information about bills received, bills paid, bills unpaid, payment amounts, payment dates, whether payments were timely, whether balances are still owed, account numbers, first and last name of the person to whom the bill is sent, mailing address, purpose of the bill, and other relevant information.

[0059] The bank information component 212 may include bank name, account number, withdrawal and deposit information, debit, credit, check information (check number, amount, payee, date, etc.), transfer, taxpayer identification number, mailing address, payee and payee name (and other data), and various other data collected by the bank.

[0060] The location component 214 may include past and current residence information, past and current travel information, location tracking information that ties locations to specific dates and times, frequency of visits to specific locations, travel or visit pattern information, and other location-related information.

[0061] The receipt component 216 may include data associated with receipts for various purchases or sales, including the date, item purchased or sold, time, amount, partial or full account number, partial or full account number associated with the payment method, location of the sale or purchase, information regarding frequency of purchases or rewards account information, purpose of purchase, first and last name of the purchaser and / or seller, tax information, tip information, and / or other information associated with the receipt.

[0062] The friends component 218 may include information collected from the social networking service, the name of the friend, the length of the friendship, the closeness of the friendship, interaction dates (e.g., frequency, date, length, etc.), the type of friendship (e.g., romantic, ideal, professional, etc.), and various other data related to the friendship. Friendships may form, disappear, form again, change in intensity, etc.

[0063] The tendency component 220 may include information about the entity's tendencies, which may vary greatly, such as preferences, habits, exhibited behaviors, and various information related to the tendencies.

[0064] The coloring component 222 may include coloring of skin color, hair color, eye color, or other features. It may be expected that eye color will remain very similar after the first few years of life, but hair color may vary significantly over time. For example, a person may be born blonde, may become brown, may be dyed with dyes at different times, may eventually become gray, may later become white, such that the same person may have extreme variations in hair color over time, but may always have the same eye color.

[0065] The sizing component 224 may include data related to height, weight, shoe size, waist circumference, shirt size, inseam, and many other body measurements. It is expected that some parts of the sizing component 224 will vary significantly, while some components such as height and shoe size generally remain very stable over time during adulthood.

[0066] The facial feature component 226 may include various facial measurements, eye color, lip color, dental records, skin color, layout relationships between eyes, nose, mouth, chin, eyebrows, ears, etc., details about facial hair, and many other facial features.

[0067] Fingerprint component 228 may include fingerprint data for various fingers, handprints, footprints, etc., taken at various times and using various methods. The fingerprint data may be associated with other data, such as a first name, last name, date of birth or age, address information, or other information. The fingerprint data may be expected to undergo certain changes over time if scars form on the fingertips, if a finger is amputated, or as the skin stretches or wrinkles with age.

[0068] The clothing component 230 may include data related to size, clothing type, purchase frequency, preferred brands and styles, and other data reflecting the clothing a person is likely to wear. It can be expected that as young people grow and their styles change, some of their clothing data will change significantly over time, but older people will show less change in data because many people stick to known types and sizes of clothing rather than following fashion and have stopped growing.

[0069] Box 240 generally represents a potentially large amount of other identity data. For example, such data may include tattoo data, affiliation data, family tree data, genealogy data, genetic sequencing data, political and voting data, and many other potential sources of identity data.

[0070] For any given entity, many of the components 203 to 240 of the identity listed above may change significantly over time. Although it is expected that some data points may remain unchanged, it is also expected that other data points may remain static or change slightly. Some data may change gradually, and other data may change suddenly. For example, the height and weight of a person are expected to increase continuously and significantly between the ages of 1 and 18, and then the height is more gently or there is no change in the next 40 years, and the weight may fluctuate up and down with the change of events including pregnancy or exercise plans. In some cultures, it is expected that a man's name will not change in his lifetime, but a woman's name may experience sudden changes with marriage or divorce, and in other cultures, a man's name may change with marriage or divorce. Over time, many other types of changes in identity information can be expected.

[0071] Figure 3 A block diagram representing an exemplary database 300 that may be used in certain embodiments of the invention disclosed herein is shown. The database 300 may include data about various identification credentials 310, 320, 330, 340, and 350. As visually represented, the credentials are given different shapes to represent different types of data. And the shapes within the various credentials are placed in different locations to visually indicate potential different types of data. It should be noted that those of ordinary skill in the art will understand that such data is not typically represented as shapes within a database, but providing examples of such shapes can help understanding.

[0072] Figure 3The present invention includes three rectangular-shaped vouchers 310, 320, and 340, each of which has locations for up to four data subsets. Voucher 310 has data 312 in the first location, data 314 in the second location, no data in the third location, and data 318 in the fourth location. Voucher 320 has data 322 in the first location, no data in the second and third locations, and data 328 in the fourth location. Voucher 340 has data 344 in the second location, and no data in the first, third, and fourth locations. Vouchers 330 and 350 are roughly square to represent a second type of voucher. Voucher 330 has data 328 in its first location, data 333 in its second location, data 335 in its third location, and no data in its fourth location. Voucher 350 has data 353 in its second location, and no data in its first, third, and fourth locations.

[0073] As an example of what this data might represent, vouchers 310, 320, and 340 may represent various government-issued identification cards or licenses, while vouchers 330 and 350 may represent various financial data. In this example, voucher 310 can represent a passport, where data 312 represents a last name, data 314 represents a full government identification number (e.g., a social security number in the United States), and data 318 represents a date of birth. Voucher 320 may represent a driver's license, where data 322 represents a last name and a portion of an identification number, and data 328 represents a date of birth. Voucher 340 may represent a loyalty card, where data 344 represents a full ID number. Voucher 330 may represent a credit report, where data 338 represents a date of birth, data 333 represents a partial identification number (such as the last four digits of a social security number), and data 335 represents a full identification number. Voucher 350 may represent a receipt from a purchase, where data 353 represents a partial identification number; for example, it may contain the last four digits of a social security number.

[0074] Various parts of this data can have relationships with each other, and these relationships can be of varying strengths. Such relationships are determined by Figure 3 The interconnecting lines 362, 364, 366, 368, 370, 372, 374, 376, 378 shown are visual representations. These interconnecting lines are a visual representation of the data that can be stored in a relational database that stores the strength of the relationships. The relational database is in Figure 3, but may be represented as one of the databases db1 to dbn depicted elsewhere in this disclosure. In the event that the relationship is strong or non-contestable, the second database may store data indicating the strong relationship. And in the event that the relationship is weak or contestable, the second database may store data indicating a weak relationship. For each such relationship, the second database may store an indication of each related credential, an indication of the reason for the relationship, and an indication of the strength of the relationship. One of ordinary skill in the art will appreciate that there are many ways to store and index such data that are acceptable for various implementations of the disclosed invention.

[0075] As can be Figure 3 , in the United States, the social security number is intended to be a unique nine-digit number. Therefore, if two data points 314 and 344 contain the same nine-digit social security number, the relationship between the two vouchers 310 and 340 will be very strong. However, there are many social security numbers that may contain the same last four digits. Therefore, although the partial identification number represented as 333 and the complete identification number represented as 344 may appear to match, the relationship will not be as strong as the match of the two complete identification numbers. And many people may have the same last name or even a combination of first and last names. Therefore, although the last name represented as 310 may match the last name represented as part of 320, forming a relationship, the relationship will not be as strong as the match between the two complete identification numbers. In addition, although individual data points within a voucher may form part of a match, the combination of multiple data points can result in a stronger match. For example, credential 310 and credential 320 may have additional strength in their relationship because, in addition to the last name match discussed above, both may have the same date of birth represented as data points 318 and 328, resulting in a closer (or stronger) relationship between 310 and 320 than would be provided by last name alone.

[0076] like Figure 3As described in , lines 362 and 370 can represent the relationship between vouchers 310 and 320, and can be used alone or in combination. It can be expected that these relationships are associated with specific data items such as 312 to 322 and 318 to 328, respectively. Or it can be expected to more generally associate the relationship with the voucher alone. In some implementations, it can be expected to associate the relationship with both the voucher and the specific data point associated with the voucher. As described above, data 312 can represent a surname and can have a strong relationship with data 322 representing a combination of a surname and a portion of an identification number. Similarly, data 333 can represent a partial identification number and have a strong relationship with data 320. However, in this case, data 333 representing a number and data 312 representing a name may not have any direct relationship. Therefore, the evaluation of the relationship may need to be through voucher 320. For example, if it can be determined that both vouchers 310 and 320 are related to the same person, and it can be determined that both vouchers 320 and 330 are related to the same person, it can be logically determined that vouchers 310 and 330 are related to the same person. But if there is any lack of certainty in either or both of relationships 362 and 364, then uncertainty in the relationship between credentials 310 and 330 will also exist.

[0077] Relationships 368, 370, and 372 link credentials 310, 320, and 330 and data 318, 328, and 338. As described above, if each of data 318, 328, and 338 represents a date of birth, a relationship would likely be implied when the dates of birth match. However, because more than one person has been born on each date of birth over the past 200 years, it is not possible to determine a unique identity based on date of birth alone. Therefore, the relationship strength of 368, 370, and 372 may have some intermediate value. Additional information in each credential may need to be considered for a more definitive identity determination.

[0078] Relationships 366, 374, and 376 link vouchers 310, 330, and 340 and data 314, 344, 333, and 335. As described above, data 333 may represent a partial identification number, data 335 may represent a full identification number, and data 314 and data 344 may represent a full identification number. In the case where such a number is unique, relationships 366 and 376 may represent a clear connection between vouchers 310, 330, and 340. However, in the case where the number is not unique, relationships 366 and 376 may have weaker strength. Relationship 374 may represent a relationship between a partial identification number in data 333 and a full identification number in 344. In the case where relationship 376 exists and is clear, relationship 374 may be less useful. But if data 335 is lost or changed, the existence of relationship 374 may gain increased importance as a link between vouchers 330 and 340. Relationship 378 may link vouchers 330 and 350 and data 333 and 353. For example, in an example where voucher 350 represents a receipt for a purchase and requires a person to enter a partial identification number to verify the transaction, voucher 350 may store the partial identification number as data 353 for future verification purposes. In such a case, it is possible to determine a relationship 378 between data 333 and 353. The strength of 378 may be weak; however, if other relationships are discovered between data in voucher 378 and other vouchers, such discovery may provide a stronger relationship link between voucher 378 or data 353 and other vouchers or data.

[0079] Figure 4 Built on Figure 3 , and depicts a block diagram representing a second exemplary database 400 that can be used in certain embodiments of the invention disclosed herein. Database 400 may include data about two additional types of identification credentials labeled 410, 420, 430, and 440. As visually represented, the credentials are given different shapes to represent different types of data internally and between databases 300 and 400. And the shapes within the various credentials are placed in different locations to visually indicate potential different types of data. It should also be noted that those of ordinary skill in the art will understand that such data is typically not represented as shapes within a database, but providing examples of such shapes can help understanding.

[0080] Figure 4Two triangular vouchers 410 and 420 are included, each of which has locations for up to four data subsets. Voucher 410 has data 413 at the upper location, data 416 at the lower left location, no data at the center location, and data 419 at the lower right location. Voucher 420 has data 423 at the upper location and no data at the other three locations. Vouchers 430 and 440 are generally circular to represent a fourth type of voucher. Voucher 430 has data 432 and 438 at its upper and lower locations, respectively, and no data at the left or right locations. Voucher 440 has data 442 at its upper location, data 444 and 446 at its left and right locations, respectively, and no data at its lower location.

[0081] As an example of what this data might represent, 410 and 420 may represent various personal identification credentials, while credentials 430 and 440 may represent educational credentials. In this example, credential 410 may represent an elementary school identification card, where data 413 represents age, data 416 represents the name of the school, and data 419 represents grade level. Credential 420 may represent a fingerprint record, where data 423 represents date of birth. Credential 430 may represent a high school graduation credential (such as a transcript or diploma), where data 432 represents the graduation date, and data 438 represents an identification number. Credential 440 may represent a college graduation credential, where data 442 represents the graduation date, data 444 represents a partial identification number, and data 446 represents an email address that may incorporate a portion of the identification number.

[0082] Various portions of this data may be related to each other and / or to data in database 300, and these relationships may be of varying strengths. Such relationships are determined by Figure 4 The interconnecting lines 462, 464, 466, 468, 470, 472, 474, 476, 478, 480, and 482 shown are visual representations of data that may be stored in a relational database that stores the strength of the relationships. Figure 4 , but may be represented as one of the databases db1 to dbn depicted elsewhere in the present disclosure. In the event that the relationship is strong or non-contestable, the second database may store data indicating the strong relationship. And in the event that the relationship is weak or contestable, the second database may store data indicating a weak relationship. For each such relationship, the second database may store an indication of each related credential, an indication of the reason for the relationship, and an indication of the strength of the relationship. One of ordinary skill in the art will appreciate that there are many ways to store and index such data that are acceptable for various implementations of the disclosed invention.

[0083] As can be Figure 4, various educational documents may be related to each other over time, so that a person who completes freshman year in a certain year may be predicted to graduate from high school eleven years later and graduate from college approximately four years later. Therefore, if three data points 419, 432, and 442 all contain data related to grades or graduation ceremonies in various years, they may be related to the same person. For example, the grade at a certain time stored in data 419 may be related to the high school graduation year stored in data 432 and the college graduation stored in data 442. Because the length of time required to complete a college course of study often varies more than the length of time required to complete high school, relationship 474 may be stronger than relationship 478 or relationship 476. However, each of these relationships may be considered relatively weak unless combined with other identity data in the credential, which is due to the fact that many people graduate each year, making the graduation year a relatively weak identifier. However, the combination of graduation year with photo, name, and email address can provide a stronger possibility of identity confirmation or rejection.

[0084] As part of this example, the age represented as data 413 may have a strong relationship with the birth date provided as data 423 and data 328, which means that relationships 462, 464, and 482 may be stronger than relationships 474, 476, and 478. Even within this hierarchy, relationship 462 may be the strongest because the birth date matches exactly, while relationships 464 and 482 both match the birth date to the age, but the relationship is not as strong. The birth date in data 423 may also be matched to the school grade in data 419 as shown by relationship 480, although such a match will be relatively weak due to the fact that many children with a particular birth date are found within a particular grade.

[0085] In this example, relationships 466 and 468 depict the ability to establish relationships between data across databases, such as identification numbers in data 438, 314, and 344. Because these three data points represent complete identification numbers, they can be used to determine the existence of a strong or unambiguous relationship between credentials 310, 430, and 340. If the identification numbers are unique, then an unambiguous relationship can be established. If the identification numbers are not unique, then relationships 466 and 468 will be strong, but not unambiguous. Similarly, relationships 470 and 472 represent potential relationships between a partial identification number in data 444, an email address in data 446 containing a partial identification number, and a partial identification number in data 353. In this case, different portions of the partial identification number in data 353 can be matched to each of the individual numbers in data 444 and 446.

[0086] As will be appreciated, the above description and Figure 3 and 4The examples depicted in are simplified to facilitate understanding and avoid overly cluttered diagrams. It will be appreciated that any of the credentials identified above may have many more pieces of data, some of which may form explicit relationships with other credentials, and some of which may form weaker relationships individually but may form strong relationships in pairs, triplets, or collectively. In some instances, it may be necessary for relationships to span multiple credentials to establish a relationship between a data point and a person's identity. As an example, a severed finger found by police in Montana may match a 30-year-old fingerprint record of Suzy Smith in Tucson, Arizona; the fingerprint record may match a graduation record of Suzy Smith from Tucson High School; the record may match a newspaper article reporting that Suzy Smith was admitted to the University of Toledo; the article may match a marriage license of Suzy Smith and John Jones in Toledo, Ohio; the marriage license may match a record showing that Suzy Jones attended New York University School of Medicine; and the name may match a police report indicating that Dr. S. Jones of Battle Creek, Michigan was the subject of a missing persons report shortly before the severed finger was found. This may result in a relationship of strong or weak strength between Dr. Suzy Jones and the severed finger. As will be appreciated by one of ordinary skill, there may be many other paths that may be followed that may suggest additional links to the same person, or may also suggest links to different persons of varying strengths. Thus, relationships of varying strengths may need to be considered or ranked in order to determine identity.

[0087] Figure 5 A functional block diagram illustrating an exemplary environment 500 suitable for use with aspects of the disclosed subject matter is depicted. For example, it depicts an exemplary collection of devices, parties, or participants that are communicatively coupled to each other and that participate in the provision, collection, use, and distribution of identity information. For example, a user device 502 can provide information to and receive information from other devices that are communicatively coupled to the communication network 504 over a communication network 504.

[0088] The user device 502 may be a hardware device and may include a computer application. Although only one user device 502 is depicted, it should be understood that in many networks, multiple user devices 502 may be connected and communicated with. The user device 502 may be communicatively coupled to the network 504 via a wired, wireless, or combined connection. As non-limiting examples, the user device 502 may be a mobile or fixed computer, a mobile phone, an augmented reality device, or other such hardware that may become available and allow such communications.

[0089] Automated system 503 may also provide information to and receive information from other devices communicatively coupled to network 504 over network 504. Automated system 503 may be a system controlled primarily or entirely by an artificial intelligence (“AI”) or machine learning (“ML”) algorithm, or system 503 may be primarily or entirely controlled by humans or other non-learning computer systems.

[0090] Similar to user device 502, automation system 503 may be a hardware device and may include a computer application. Although only one automation system 503 is depicted, it should be understood that in many networks, multiple automation systems 503 may be connected and communicated with. Automation system 503 may be communicatively coupled to network 504 via a wired, wireless, or combination connection. As non-limiting examples, automation system 503 may be a mobile or fixed computer, a mobile phone, an augmented reality device, or other such hardware that may become available and allow implementation of such a system with communications.

[0091] The control server 506 may include a suitable computer server, which may include a web server, a file server, or other server and a suitable control mechanism. The control server 506 may be configured to receive data including control requests or commands from the user device 502 and / or the automation system 503. Such requests or commands may be transmitted via the network 504.

[0092] Data store 508 may be communicatively connected to control server 506, network 504, and / or machine learning system 514. Training data store 510 is preferably communicatively coupled to at least machine learning system 514.

[0093] The machine learning system 514 may be implemented using a variety of frameworks. Preferably, a parallel processing framework 540 is employed. It is also desirable to implement a training model 530. In order to determine the identity of an entity in real time, it is desirable to implement a risk analysis module 520 within the machine learning system 514 to allow for the identification and implementation of various risk models depending on the risk tolerance desired or allowed for the particular identification task being performed.

[0094] The communication network 504 may include wired and / or wireless network components, such as the Internet, cellular or local area wireless networks. The communication network 504 may also include networks such as Bluetooth and infrared networks. Communications on the communication network 504 may be encrypted or protected using any appropriate security or encryption protocol.

[0095] The control server 506, which may include any network server or virtual server (such as a file or web server), can access the data sources db1...dbn in the data store 508 locally or through an appropriate network connection (such as the network 504). The control server 506 may also include processing circuitry (e.g., one or more computer processors or microprocessors), memory (e.g., RAM, ROM, and / or mixed types of memory), and one or more storage devices (e.g., hard disk drives, optical drives, flash drives, etc.). The processing circuitry included in the control server 506 may execute a processor capable of performing various processes in parallel. The server 506 may be capable of receiving, processing, and distributing information generated by an application executed on a user device 502, such as a computer or a mobile device (e.g., a cellular phone, a wearable mobile device such as an augmented reality device, etc.). The processing circuitry included in the control server 506 may also perform a large number of calculations and operations that may be required when managing and determining continuous identities. In some embodiments, a computer-readable medium having computer program logic recorded thereon is included within the control server 506. The computer program logic may perform the various steps described herein with respect to identity determination.

[0096] The control server 506 can access the data sources in the data store 508 through the Internet, a secure private LAN, or other communication network. The data sources in the data store 508 may include one or more third-party data sources, such as from Figure 2 , or other relevant sources. For example, the data sources in data store 508 may include identity-related data from one or more of a social network, a government identity database, a biometric identity database, a credit bureau, a bank, a retailer, or various information services. The data sources in data store 508 may also include data stores and databases local to control server 506 that contain identity-related information (e.g., databases of addresses, legal records, transportation passenger lists, political and / or charitable donations, political affiliations, vehicle license plates or identification numbers, universal product codes, news articles, business registries, and hospital or university affiliations).

[0097] The control server 506 can communicate with the machine learning system 514. The machine learning system 514, which can include any parallel or distributed computing framework or cluster, can be configured to divide the computing job into smaller jobs to be executed simultaneously, in a distributed manner, or in both ways. For example, the machine learning system 514 can support data-intensive distributed applications by implementing a map / reduce computing paradigm, where the application can be divided into multiple small work fragments, each of which can be executed or re-executed on any core processor in a cluster of cores. Suitable examples of machine learning systems 514 include Apache Hadoop clusters.

[0098] The machine learning system 514 can be interfaced with the training data store 510 and / or the data store 508, which can also take the form of a cluster of cores. For example, the machine learning system 514 can express large-scale distributed computing as a sequence of distributed operations on a data set by dividing the operations into jobs. Such jobs can be executed across multiple nodes in a cluster of parallel computing frameworks 540. The processing and computing described herein can be performed at least in part by any type of processor or combination of processors. For example, various types of quantum processors (e.g., solid-state quantum processors and light-based quantum processors), artificial neural networks, etc. can be used to perform large-scale parallel computing and processing.

[0099] The machine learning system 514 may distribute many tasks across a cluster of nodes and provide the appropriate piece of intermediate data to each task.

[0100] The tasks in each stage can be executed in a fault-tolerant manner, such that if one or more nodes fail during computation, the tasks assigned to such failed nodes can be redistributed to the remaining nodes. This behavior can allow load balancing and re-execution of failed tasks with low runtime overhead.

[0101] The data sources in data storage 508 and training data storage 510 may implement any distributed file system that can reliably store large files. For example, they may implement Hadoop's own distributed file system (DFS) or a more scalable column-oriented distributed database such as HBase, or other data storage and analysis systems such as Google BigQuery, Apache Spark, Snowflake, etc. Such file systems or databases may include BigTable-like capabilities, such as supporting an arbitrary number of table columns.

[0102] although Figure 5 In order to avoid making the figure too complicated, only a single instance of user device 502, automation system 503, communication network 504, control server 506, data storage 508, training data 510, and machine learning system 514 is shown, but in fact, architecture 500 may include multiple instances of one or more of the aforementioned components. In addition, in some embodiments, certain elements may also be removed.

[0103] To provide additional context for the various embodiments described herein, Figure 6The following discussion is intended to provide a brief, general description of a suitable computing environment 600 in which various embodiments described herein may be implemented. Although the embodiments are described above in the general context of computer-executable instructions that may be executed on one or more computers, those skilled in the art will appreciate that the embodiments may also be implemented in conjunction with other program modules and / or as a combination of hardware and software.

[0104] Generally, program modules include routines, programs, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In addition, those skilled in the art will appreciate that parts of the method of the present invention can be implemented with other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, distributed computing systems, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc., each of which can be operatively coupled to one or more associated devices.

[0105] The illustrated embodiments of the embodiments herein may also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0106] Computing devices typically include various media, which may include computer-readable storage media, machine-readable storage media, and / or communication media, the two terms being used differently from each other herein as follows. Computer-readable storage media or machine-readable storage media can be any available storage media that can be accessed by a computer, and include volatile and non-volatile media, removable and non-removable media. By way of example and not limitation, computer-readable storage media or machine-readable storage media can be implemented in conjunction with any method or technology for storing information such as computer-readable or machine-readable instructions, program modules, structured data, or unstructured data.

[0107] Computer-readable storage media may include, but are not limited to, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD), Blu-ray disk (BD) or other optical disk storage, magnetic disk storage or other magnetic storage devices, solid-state drives or other solid-state storage devices, or other tangible and / or non-transitory media that can be used to store the desired information. In this regard, the terms "tangible" or "non-transitory" herein as applied to storage devices, memories, or computer-readable media will be understood to exclude only the propagation of transient signals per se as a modifier, and do not disclaim rights to all standard storage devices, memories, or computer-readable media that propagate more than just transient signals per se.

[0108] Computer-readable storage media may be accessed by one or more local or remote computing devices, such as via access requests, queries, or other data retrieval protocols, to perform various operations with respect to information stored by the media.

[0109] Communication media typically embodies computer readable instructions, data structures, program modules, or other structured or unstructured data in a data signal such as a modulated data signal (e.g., a carrier wave) or other transport mechanism, and includes any information delivery or transmission media. The term "modulated data signal" or signal refers to a signal that has one or more of its characteristics set or changed in such a manner as to encode information in one or more signals. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection and wireless media such as acoustic, RF, infrared and other wireless media.

[0110] Reference again Figure 6 , an example environment 600 for implementing various embodiments of various aspects described herein includes a computer 602, which includes a processing unit 604, a system memory 606, and a system bus 608. The system bus 608 couples system components including, but not limited to, the system memory 606 to the processing unit 604. The processing unit 604 can be any of a variety of commercially available processors. Dual microprocessors and other multi-processor architectures can also be used as the processing unit 604.

[0111] The system bus 608 may be any of several bus structures that may also interconnect to a memory bus (with or without a memory controller), a peripheral bus, and a local bus using any of a variety of commercially available bus architectures. The system memory 606 includes ROM 610 and RAM 612. A basic input / output system (BIOS) containing the basic routines that help transfer information between elements within the computer 602, such as during startup, may be stored in a nonvolatile memory such as a ROM, an erasable programmable read-only memory (EPROM), an EEPROM, or the like. RAM 612 may also include a high-speed RAM, such as a static RAM for caching data.

[0112] The computer 602 also includes an internal hard disk drive (HDD) 614 (e.g., EIDE, SATA), one or more external storage devices 616 (e.g., magnetic floppy disk drive (FDD), memory stick or flash drive reader, memory card reader, etc.), and an optical drive 620 (e.g., it can read or write from a CD-ROM disk, DVD, BD, etc.). Although the internal HDD 614 is shown as being located within the computer 602, the internal HDD 614 can also be configured to be used externally in a suitable chassis (not shown). In addition, although not shown in the environment 600, a solid state drive (SSD) can be used in addition to or instead of the HDD 614. The HDD 614, the external storage device 616, and the optical drive 620 can be connected to the system bus 608 via a HDD interface 624, an external storage interface 626, and an optical drive interface 628, respectively. The interface 624 for external drive implementation can include at least one or both of a universal serial bus (USB) and an Institute of Electrical and Electronics Engineers (IEEE) 694 interface technology. Other external drive connection technologies are within the contemplation of the embodiments described herein.

[0113] The drives and their associated computer-readable storage media provide non-volatile storage of data, data structures, computer-executable instructions, etc. For the computer 602, the drives and storage media accommodate the storage of any data in an appropriate digital format. Although the above description of computer-readable storage media refers to corresponding types of storage devices, it should be understood by those skilled in the art that other types of computer-readable storage media, whether currently existing or developed in the future, may also be used in the example operating environment, and further, any such storage media may contain computer-executable instructions for performing the methods described herein.

[0114] A number of program modules may be stored in the drives and RAM 612, including an operating system 630, one or more application programs 632, other program modules 634, and program data 636. All or portions of the operating system, applications, modules, and / or data may also be cached in RAM 612. The systems and methods described herein may be implemented using various commercially available operating systems or combinations of operating systems.

[0115] Computer 602 may optionally include emulation technology. For example, a hypervisor (not shown) or other intermediary may emulate the hardware environment of operating system 630, and the emulated hardware may optionally be different from the hardware of the operating system 630. Figure 6The hardware shown. In such an embodiment, the operating system 630 may include one of a plurality of virtual machines (VMs) hosted at the computer 602. In addition, the operating system 630 may provide a runtime environment such as a Java runtime environment or a .NET framework for the application 632. The runtime environment is a consistent execution environment that allows the application 632 to run on any operating system that includes a runtime environment. Similarly, the operating system 630 may support containers, and the application 632 may be in the form of a container, which is a lightweight, independent, executable software package that includes, for example, code, runtime, system tools, system libraries, and settings for the application.

[0116] The user may preferably enter commands and information into the computer 602 through one or more wired / wireless input devices such as a keyboard 638, a touch screen 640, and a pointing device such as a mouse 642. Other input devices (not shown) may include a microphone, an infrared (IR) remote control, a radio frequency (RF) remote control or other remote control, a joystick, a virtual reality controller and / or a virtual reality headset, a game pad, a stylus, an image input device (e.g., a camera), a gesture sensor input device, a visual movement sensor input device, an emotion or facial detection device, a biometric input device (e.g., a fingerprint or iris scanner), etc. These and other input devices are typically connected to the processing unit 604 through an input device interface 644, which may be coupled to the system bus 608, but may also be connected through other interfaces, such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, a Bluetooth® interface, etc.

[0117] A monitor 646 or other type of display device may also be connected to the system bus 608 via an interface, such as a video adapter 648. In addition to the monitor 646, computers typically include other peripheral output devices (not shown) such as speakers, printers, and the like.

[0118] The computer 602 can operate in a networked environment using logical connections to one or more remote computers, such as a remote computer 650, via wired and / or wireless communications. The remote computer 650 can be a workstation, a server computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other common network node, and typically includes many or all of the elements described for the computer 602, but only a memory / storage device 652 is shown for simplicity. The depicted logical connections include wired / wireless connections to a local area network (LAN) 654 and / or a larger network such as a wide area network (WAN) 656. Such LAN and WAN networking environments are common in offices and companies, and facilitate enterprise-wide computer networks such as intranets, all of which can be connected to global communication networks such as the Internet.

[0119] When used in a LAN networking environment, the computer 602 can be connected to a local network 654 through a wired and / or wireless communication network interface or adapter 658. The adapter 658 can facilitate wired or wireless communication with the LAN 654, which can also include a wireless access point (AP) deployed thereon for communicating with the adapter 658 in a wireless mode.

[0120] When used in a WAN networking environment, the computer 602 may include a modem 660, or may be connected to a communication server on the WAN 656 via other means for establishing communications on the WAN 656, such as through the Internet. The modem 660 may be internal or external and may be a wired or wireless device, which may be connected to the system bus 608 via the input device interface 644. In a networked environment, program modules described for the computer 602 or portions thereof may be stored in the remote memory / storage device 652. It will be appreciated that the network connections shown are examples and other means of establishing a communications link between the computers may be used.

[0121] When used in a LAN or WAN networking environment, the computer 602 can access a cloud storage system or other network-based storage system in addition to or in lieu of the external storage device 616 described above. Typically, the connection between the computer 602 and the cloud storage system can be established through the LAN 654 or WAN 656, for example, by an adapter 658 or a modem 660, respectively. When the computer 602 is connected to the associated cloud storage system, the external storage interface 626 can manage the storage provided by the cloud storage system with the help of the adapter 658 and / or the modem 660, just as it would manage other types of external storage. For example, the external storage interface 626 can be configured to provide access to cloud storage sources as if those sources were physically connected to the computer 602.

[0122] Computer 602 may be operable to communicate with any wireless device or entity operatively deployed in wireless communications, such as printers, scanners, desktop and / or portable computers, portable data assistants, communication satellites, any device or location associated with a wirelessly detectable tag (e.g., a public telephone booth, a kiosk, a store shelf, etc.), and a telephone. This may include Wireless Fidelity (Wi-Fi) and Bluetooth® wireless technologies. Thus, the communication may be a predefined structure such as utilizing a conventional network, or simply an ad hoc communication between at least two devices.

[0123] It will be further appreciated that, although a brief overview of exemplary systems, methods, scenarios, and / or devices has been provided, the disclosed subject matter is not limited thereto. It will be further appreciated, therefore, that various modifications, changes, additions, and / or deletions may be made without departing from the scope of the embodiments described herein. Thus, similar non-limiting implementations may be used, or modifications and additions may be made to the described embodiments to perform the same or equivalent functions of the corresponding embodiments without departing therefrom.

[0124] It will be appreciated by those skilled in the art that the various embodiments and related systems, devices and / or methods of the disclosed subject matter described herein can be implemented in conjunction with various computers or other client or server devices, which can be deployed as part of a communication system, a computer network and / or deployed in a distributed computing environment, and can be connected to any kind of data storage. In this regard, the various embodiments described herein can be implemented in several types of computer systems or environments, which have any number of memories or storage units and many applications and processes that occur across any number of storage units or capacities, which can be used in conjunction with a communication system using the technology, system and method according to the disclosed subject matter. The disclosed subject matter can be applied to environments with remote or local storage having server computers and client computers deployed in a network environment or a distributed computing environment. The disclosed subject matter can also be applied to independent computing devices having programming language functions, interpretation and execution capabilities for generating, receiving, storing and / or sending information in conjunction with remote or local services and processes.

[0125] Distributed computing provides sharing of computer resources and services through communication exchanges between computing devices and systems. These resources and services may include exchange of information, cache storage and disk storage for objects such as files. These resources and services may also include sharing of processing power on multiple processing units for load balancing, resource expansion, processing specialization, etc. Distributed computing utilizes network connections, allowing clients to leverage their collective power to benefit the entire enterprise. In this regard, various devices may have applications, objects, or resources that may utilize the disclosed and related systems, devices, and / or methods as described for various embodiments of the present disclosure.

[0126] Those skilled in the art will recognize that it is common in the art to describe devices and / or processes in the manner set forth herein and thereafter use engineering practices to integrate such described devices and / or processes into a system. That is, at least a portion of the devices and / or processes described herein can be integrated into a system by a reasonable amount of experimentation. Those skilled in the art will recognize that a typical system may include a system unit housing, a video display device, a memory such as volatile and non-volatile memory, a processor such as a microprocessor and a digital signal processor, a computing entity such as an operating system, a driver, a graphical user interface, and an application, one or more interactive devices such as a touch pad or a touch screen, and / or one or more of a control system including a feedback loop and a control device (e.g., feedback for sensing position and / or velocity; a control device for moving and / or adjusting parameters). A typical system may be implemented using any suitable commercially available components, such as those commonly found in data computing / communication and / or network computing / communication systems.

[0127] Various embodiments of the disclosed subject matter sometimes show different components that are contained in or connected to other components.It should be understood that the architecture described in this way is merely exemplary, and in fact, many other architectures can be implemented, which implement the same and / or equivalent functions.In a conceptual sense, any arrangement of components that implement the same and / or equivalent functions is effectively "associated" to achieve the desired function.Therefore, any two components combined to achieve a specific function herein can be regarded as "associated" with each other to achieve the desired function, regardless of the architecture or intermediate components.Similarly, any two components so associated can also be regarded as "operably connected", "operably coupled", "communicatively connected" and / or "communicatively coupled" to achieve the desired function, and any two components that can be so associated can also be regarded as "operably couplable" or "communicatively couplable" to achieve the desired function.Specific examples of operably couplable or communicatively couplable can include, but are not limited to, physically pairable and / or physically interactive components, wirelessly interactive and / or wirelessly interactive components, and / or logically interactive and / or logically interactive components.

[0128] With respect to substantially any plural and / or singular terms used herein, those skilled in the art can appropriately convert from plural to singular and / or from singular to plural according to context and / or application. For clarity, various singular / plural permutations can be clearly set forth herein without limitation.

[0129] Those skilled in the art will understand that, in general, the terms used herein and particularly in the appended claims (e.g., the bodies of the appended claims) are generally intended as "open" 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 "comprising" should be interpreted as "including but not limited to," etc.). Those skilled in the art will also understand that if a specific number of an introduced claim recitation is intended, such intent will be explicitly recited in the claim, and in the absence of such recitation, no such intent is present. For example, to aid understanding, the following appended claims may contain the use of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be interpreted as implying that a claim feature introduced by the indefinite article "a" or "an" will limit any particular claim containing such introduced claim feature to an embodiment containing only one such feature, even when the same claim includes the introductory phrase "one or more" or "at least one" and an indefinite article such as "a" or "an" (e.g., "a" and / or "an" should be interpreted as meaning "at least one" or "one or more"); the same applies to the use of definite articles to introduce claim recitations. In addition, even if a specific number of introduced claim recitations is explicitly recited, a person skilled in the art will recognize that such recitation should be interpreted as meaning at least the recited number (e.g., the unmodified recitation of "two recitations" means at least two recitations, or two or more recitations, in the absence of other modifiers). Furthermore, in those instances where a convention similar to “at least one of A, B, and C, etc.” is used, generally such construction is intended in the sense that one skilled in the art would understand the convention (e.g., “a system having at least one of A, B, and C” would include, but is not limited to, systems having only A, only B, only C, A and B, A and C, B and C, and / or A, B, and C, etc.). In those instances where a convention similar to “at least one of A, B, or C, etc.” is used, generally such construction is intended in the sense that one skilled in the art would understand the convention (e.g., “a system having at least one of A, B, or C” would include, but is not limited to, systems having only A, only B, only C, A and B, A and C, B and C, and / or A, B, and C, etc.). One skilled in the art would also understand that any disjunctive conjunctions and / or phrases that actually present two or more alternative terms, whether in the specification, claims, or drawings, should be understood to contemplate the possibility of including one of the terms, either of the terms, or both of the terms. For example, the phrase "A or B" will be understood to include the possibilities of "A" or "B" or "A and B."

[0130] In addition, where features or aspects of the disclosure are described in terms of Markush groups, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual member or subgroup of members of the Markush group.

[0131] As will be understood by those skilled in the art, for any and all purposes, such as in terms of providing a written description, all ranges disclosed herein also encompass any and all possible sub-ranges and combinations of sub-ranges thereof. Any listed range can be easily considered to fully describe and enable the same range to be decomposed into at least equal half, one-third, one-quarter, one-fifth, one-tenth, etc. As a non-limiting example, each range discussed herein can be easily decomposed into a lower third, a middle third, and an upper third, etc. It will also be understood by those skilled in the art that all languages ​​such as "up to", "at least", etc. include the numbers listed, and refer to the ranges that can be subsequently decomposed into sub-ranges as described above. Finally, as will be understood by those skilled in the art, a range includes each individual member. Therefore, for example, a group with 1-3 units refers to a group with 1, 2 or 3 units. Similarly, a group with 1-5 units refers to a group with 1, 2, 3, 4 or 5 units, etc.

[0132] From the above, it should be noted that various embodiments of the disclosed subject matter are described herein for illustrative purposes, and various modifications may be made without departing from the scope and spirit of the invention. Therefore, the various embodiments disclosed herein are not restrictive, and the true scope and spirit are indicated by the appended claims.

[0133] In addition, the words "exemplary" and "non-limiting" are used herein to indicate use as examples, instances, or illustrations. For the avoidance of doubt, the subject matter disclosed herein is not limited by these examples. In addition, any aspect or design described herein as "example", "illustration", "exemplary" and / or "non-limiting" is not necessarily to be interpreted as being preferred or advantageous over other aspects or designs, nor is it meant to exclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. In addition, with respect to the use of the terms "including", "having", "comprising" and other similar words in the detailed description or claims, for the avoidance of doubt, these terms are intended to be inclusive as open transition words in a manner similar to the term "comprising", without excluding any additional or other elements as described above.

[0134] As mentioned above, the various techniques described herein can be implemented in combination with hardware or software, or in combination with a combination of the two in appropriate circumstances. As used herein, the terms "component", "system", etc. are equally intended to represent computer-related entities, or hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process, a processor, an object, an executable file, a thread of execution, a program and / or a computer running on a processor. As an illustration, both the application program and the computer running on the computer can be a component. In addition, one or more components can reside in a process and / or a thread of execution, and a component can be located on a computer and / or be distributed between two or more computers.

[0135] The system described herein can be described with respect to the interaction between several components. It is understood that such systems and components can include those components or specified subcomponents, certain specified components or subcomponents or parts thereof, and / or additional components, and various permutations and combinations of the foregoing. Subcomponents can also be implemented as communicatively coupled to other components rather than being included in a parent component (layered). In addition, it should be noted that one or more components can be combined into a single component that provides cluster functionality, or divided into several separate subcomponents, and any one or more intermediate component layers such as a management layer can be provided to communicatively couple to such subcomponents, so as to provide integrated functionality, as mentioned. Any component described herein can also interact with one or more other components that are not specifically described herein but are generally known to those skilled in the art.

[0136] As described above, in view of the exemplary systems described herein, the methods that can be implemented according to the described subject matter can be better understood with reference to the flowcharts of the accompanying drawings, and vice versa. Although the method can be shown and described as a series of frames for simplicity of description, it should be understood and appreciated that the claimed subject matter is not limited by the order of the frames, because some frames can occur in a different order than that depicted and described herein and / or occur simultaneously with other frames. In the case of non-sequential or branched processes shown by flowcharts, it can be understood that various other branches, process paths, and orders of frames that can achieve the same or similar results. In addition, not all of the frames shown are necessary to implement the methods described herein.

[0137] Although the disclosed subject matter has been described in conjunction with the disclosed embodiments and the various figures, it should be understood that other similar embodiments may be used, or the described embodiments may be modified and added to perform the same functions of the disclosed subject matter without departing therefrom. In addition, multiple processing chips or multiple devices may share the performance of one or more functions described herein, and similarly, storage may be implemented across multiple devices. In other cases, changes in process parameters (e.g., configuration, number of components, set of components, timing and sequence of process steps, addition and / or deletion of process steps, addition of pre-processing and / or post-processing steps, etc.) may be made to further optimize the provided structures, devices, and methods, as shown and described herein. In any case, the systems, structures, and / or devices described herein and the associated methods have many applications in various aspects of the disclosed subject matter, etc. Therefore, the present invention should not be limited to any single embodiment, but should be interpreted according to the breadth, spirit, and scope of the appended claims.

Claims

1. A system for determining continuous identity in real time, comprising: a computer network connection for first receiving a request to verify the identity of an individual, the request including a plurality of partial identifiers provided with the request; a first database on a first server storing a plurality of identification credentials for each of a plurality of individuals, wherein different types of identification credentials can be stored and accessed in the first database for different individuals of the plurality of individuals, wherein the plurality of different types of identification credentials for any of the plurality of individuals include non-overlapping types of information, wherein one or more of the different types of identification credentials of any of the plurality of individuals may be expired, wherein one or more of the different types of identification credentials of any individual of the plurality of individuals may be unexpired; a second database on the first server for storing information regarding the strength of the relationship between the plurality of identification credentials stored in the first database; a parallel processing system for applying a machine learning algorithm to the plurality of partial identifiers, the plurality of identification credentials, and the strength of the relationship to determine whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted, wherein the machine learning algorithm establishes and applies weights to various relationships based on training and feedback, wherein the machine learning algorithm applies an adjustable risk tolerance to the determination; and a memory comprising computer executable instructions for sending, at a second time, a response to said request to verify said identity, The system can be scaled by adding further parallel processing resources so that the rate at which the machine learning algorithm processes multiple individuals scales substantially linearly over time as an equal number of parallel processing resources and verified requests are applied.

2. The system according to claim 1, wherein: The memory also includes computer executable instructions for: periodically updating the first database to store further identification credentials of one or more individuals of the plurality of individuals; after updating the first database, updating the second database to add or modify one or more relationship strengths based on said further identification credentials stored during said updating; as well as The machine learning algorithm is applied to the plurality of partial identifiers, the plurality of identification credentials, and the strength of the relationship to update the determination of whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted.

3. The system according to claim 1, wherein: The memory also includes computer-executable instructions for providing a refined interpretation of objective parameters used by the machine learning algorithm to determine whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted.

4. The system according to claim 1, wherein: The request to verify the identity of an individual also includes a first indication of a risk tolerance for use by the machine learning algorithm.

5. The system according to claim 1, wherein: The memory also includes computer executable instructions for: receiving, at a third time via the computer network connection, a second request to verify the identity of a second individual, the second request including a second plurality of partial identifiers provided with the request and a second indication of a risk tolerance for use by the machine learning algorithm, wherein the second indication of risk tolerance is different from the first indication of risk tolerance; as well as Applying the machine learning algorithm to the second plurality of partial identifiers, the plurality of identification credentials, the strength of the relationship, and the second indication of risk tolerance to determine whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted.

6. The system according to claim 1, wherein: The request to verify the identity of an individual also includes a first indication of a required minimum level of strength of a relationship between the plurality of identification credentials stored in the first database for use by the machine learning algorithm.

7. The system according to claim 1, wherein: The memory also includes computer executable instructions for: An authoritative status is assigned to one or more of the plurality of identification credentials stored in the first database.

8. A method for determining continuous identity in real time, comprising: receiving, at a first time, via a computer network, a request to verify an identity of an individual, the request including a plurality of partial identifiers provided with the request; accessing a first database storing a plurality of identification credentials for each of a plurality of individuals, wherein different types of identification credentials can be stored and accessed in the first database for different individuals of the plurality of individuals, wherein the plurality of different types of identification credentials for any of the plurality of individuals include non-overlapping types of information, wherein one or more of the different types of identification credentials of any of the plurality of individuals may be expired, wherein one or more of the different types of identification credentials of any individual of the plurality of individuals may be unexpired; accessing a second database storing information regarding the strength of the relationship between the plurality of identification credentials stored in the first database; applying a machine learning algorithm to the plurality of partial identifiers, the plurality of identification credentials, and the strength of the relationship to determine whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted, wherein the machine learning algorithm establishes and applies weights to various relationships based on training and feedback, wherein the machine learning algorithm applies an adjustable risk tolerance to the determination; as well as sending, at a second time, a response to the request to verify the identity, Wherein the rate at which the machine learning algorithm processes multiple individuals scales substantially linearly over time as equal numbers of resources and authenticated requests are applied.

9. The method according to claim 8, further comprising: periodically updating the first database to store further identification credentials of one or more individuals of the plurality of individuals; after updating the first database, updating the second database to add or modify one or more relationship strengths based on said further identification credentials stored during said updating; as well as The machine learning algorithm is applied to the plurality of partial identifiers, the plurality of identification credentials, and the strength of the relationship to update the determination of whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted.

10. The method according to claim 8, further comprising: Providing a precise interpretation of the objective parameters used by the machine learning algorithm to determine whether the individual's identity can be verified, refuted, or neither verified nor refuted.

11. The method according to claim 8, wherein: The request to verify the identity of an individual also includes a first indication of a risk tolerance for use by the machine learning algorithm.

12. The method according to claim 11, further comprising: receiving, at a third time via the computer network, a second request to verify the identity of a second individual, the second request including a second plurality of partial identifiers provided with the request and a second indication of a risk tolerance for use by the machine learning algorithm, wherein the second indication of risk tolerance is different from the first indication of risk tolerance; as well as Applying the machine learning algorithm to the second plurality of partial identifiers, the plurality of identification credentials, the strength of the relationship, and the second indication of risk tolerance to determine whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted.

13. The method according to claim 8, wherein: The request to verify the identity of an individual also includes a first indication of a required minimum level of strength of a relationship between the plurality of identification credentials stored in the first database for use by the machine learning algorithm.

14. The method according to claim 8, further comprising An authoritative status is assigned to one or more of the plurality of identification credentials stored in the first database.

15. A non-transitory computer-readable storage medium comprising: Instructions that, when executed by a device comprising a processor, facilitate performance of operations comprising: receiving, at a first time, via a computer network, a request to verify an identity of an individual, the request including a plurality of partial identifiers provided with the request; accessing a first database storing a plurality of identification credentials for each of a plurality of individuals, wherein different types of identification credentials can be stored and accessed in the first database for different individuals of the plurality of individuals, wherein the plurality of different types of identification credentials for any of the plurality of individuals include non-overlapping types of information, wherein one or more of the different types of identification credentials of any of the plurality of individuals may be expired, wherein one or more of the different types of identification credentials of any individual of the plurality of individuals may be unexpired; accessing a second database storing information regarding the strength of the relationship between the plurality of identification credentials stored in the first database; applying a machine learning algorithm to the plurality of partial identifiers, the plurality of identification credentials, and the strength of the relationship to determine whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted, wherein the machine learning algorithm establishes and applies weights to various relationships based on training and feedback, wherein the machine learning algorithm applies an adjustable risk tolerance to the determination; and sending, at a second time, a response to the request to verify the identity, Wherein, when the instructions are executed, the rate at which the machine learning algorithm processes multiple individuals scales substantially linearly over time as an equal number of resources and authenticated requests are applied.

16. The medium of claim 15, further comprising instructions that, when executed by a device comprising a processor, facilitate performance of operations comprising: periodically updating the first database to store further identification credentials of one or more individuals of the plurality of individuals; After updating the first database, updating the second database to add or modify one or more relationship strengths based on the further identification credentials stored during the updating; and The machine learning algorithm is applied to the plurality of partial identifiers, the plurality of identification credentials, and the strength of the relationship to update the determination of whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted.

17. The medium according to claim 15, wherein The instructions facilitate performance of operations further including: Providing a precise interpretation of the objective parameters used by the machine learning algorithm to determine whether the individual's identity can be verified, refuted, or neither verified nor refuted.

18. The medium according to claim 15, wherein The request to verify the identity of an individual also includes a first indication of a risk tolerance for use by the machine learning algorithm.

19. The medium of claim 15, further comprising instructions that, when executed by a device comprising a processor, facilitate performance of operations comprising: receiving, at a third time via the computer network, a second request to verify the identity of a second individual, the second request including a second plurality of partial identifiers provided with the request and a second indication of a risk tolerance for use by the machine learning algorithm, wherein the second indication of risk tolerance is different from the first indication of risk tolerance; and Applying the machine learning algorithm to the second plurality of partial identifiers, the plurality of identification credentials, the strength of the relationship, and the second indication of risk tolerance to determine whether the identity of the individual can be verified, rebutted, or neither verified nor rebutted.

20. The medium of claim 15, wherein: The request to verify the identity of an individual also includes a first indication of a required minimum level of strength of a relationship between the plurality of identification credentials stored in the first database for use by the machine learning algorithm.

Images