System and method for intelligently providing supporting information using machine learning
阅读说明：本技术 使用机器学习智能地提供支持信息的系统和方法 (System and method for intelligently providing supporting information using machine learning ) 是由 李立 彭晓宇 潘柯华 于 2017-03-28 设计创作，主要内容包括：用于基于对数据集的大数据分析向用户智能地提供支持信息的系统和方法。可以使用数据集来执行机器学习算法,以识别数据集的数据对象之间的相关性。可以使用相关性向用户推荐支持信息。可以提供用户界面以使用户能够发起与事件相关联的处理。响应于接收到输入,系统可以识别与请求相关联的变量。基于这些变量,系统可以检索机器学习算法的输出数据,以识别用户的支持信息。(Systems and methods for intelligently providing support information to a user based on big data analysis of a data set. A machine learning algorithm may be performed using the data set to identify correlations between data objects of the data set. The relevance may be used to recommend supporting information to the user. A user interface may be provided to enable a user to initiate processing associated with an event. In response to receiving the input, the system may identify a variable associated with the request. Based on these variables, the system may retrieve the output data of the machine learning algorithm to identify the user's supporting information.)
1, a computer-implemented method, comprising:
collecting, at a fare tracking system, a data set for generating a machine learning model using or more machine learning algorithms, the data set including or more events that have previously occurred, each of the or more events corresponding to or more event parameters that identify characteristics of the event;
defining or more evaluation metrics using the or more event parameters, each evaluation metric classifying the or more events as an event type;
evaluating the one or more evaluation metrics and the dataset, the evaluating including executing the or more machine learning algorithms to generate the machine learning model, the executing the or more machine learning algorithms generating or more correlations between a plurality of nodes and at least two of the plurality of nodes, and each node representing a value associated with an event and corresponding to a weight;
detecting an th communication from a computing device, the th communication being associated with a user and corresponding to a request to initiate processing associated with a particular event, the th request being associated with an actual or expected cost, and the th communication being received at the cost tracking system;
in response to detecting the communication, determining one or more variables from the request, each variable of the one or more variables representing a characteristic of the particular event;
mapping the or more variables to the plurality of nodes of the machine learning model;
based at least in part on the mapping, identifying or more nodes for each of the or more variables, the or more nodes being included in the plurality of nodes of the machine learning model, and the or more correlations being used to identify the or more nodes;
retrieving or more values associated with each of the or more nodes, and
sending a second communication to the computing device, the second communication being responsive to the th communication and including at least of the retrieved or more values.
2. The computer-implemented method of claim 1, further comprising:
identifying a client variable from the request, the client variable being of the variables determined from the request;
in response to identifying the client variable, accessing one or more rules associated with the client variable;
restricting sets of nodes identified using the one or more dependencies, the sets of nodes being restricted to a subset of nodes, the restricting based on the one or more rules;
retrieving a value for each node in the subset of nodes; and
sending the second communication to the computing device, the second communication including the retrieved value.
3. The computer-implemented method of claim 1, wherein the collecting of the data set is performed continuously such that when a new event occurs, the new event is included in the data set.
4. The computer-implemented method of claim 3, further comprising:
updating the machine learning model when the new event is included in the dataset such that at least weights corresponding to nodes of the plurality of nodes are updated.
5. The computer-implemented method of claim 1, wherein the particular event corresponds to a future event, and wherein the retrieved or more values correspond to or more recommended values provided as recommendations associated with the particular event.
6. The computer-implemented method of claim 1, further comprising:
detecting a third communication from an additional computing device, wherein the third communication corresponds to another requests to initiate another processes associated with the particular event, wherein the third communication is received after the communication is received and before the particular event occurs;
identifying that the th communication and the third communication each correspond to the particular event, and
sending an alert message to the additional computing device, the alert message including a notification that a user associated with the communication is also associated with the particular event.
7. The computer-implemented method of claim 6, further comprising:
sending a fourth communication to the additional computing device, the fourth communication being responsive to the third communication and including at least of the retrieved or more values.
8. The computer-implemented method of claim 6, wherein the user associated with the th communication and a different user associated with the third communication are each associated with the same entity.
9. The computer-implemented method of claim 1, further comprising:
detecting that a particular node of the one or more nodes is associated with a predicted occurrence that corresponds to an event parameter exceeding a defined threshold, and
accessing a workflow associated with the predicted occurrence, the workflow comprising an identification of or more documents associated with the predicted occurrence, the or more documents identifying a process for obtaining compensation associated with the particular node.
10. The computer-implemented method of claim 1, wherein the particular event is an event that has previously occurred, and at least of the or more nodes correspond to a workflow for identifying or more documents, the or more documents identifying a process for obtaining compensation associated with the particular event.
A system of , comprising:
or a plurality of data processors, and
a non-transitory computer-readable storage medium containing instructions that, when executed on the data processors, cause the data processors to:
collecting a data set for generating a machine learning model using or more machine learning algorithms, the data set comprising or more events that have previously occurred, each of the or more events corresponding to or more event parameters that identify characteristics of the event;
defining or more evaluation metrics using the or more event parameters, each evaluation metric classifying the or more events as an event type;
evaluating the one or more evaluation metrics and the dataset, the evaluating including executing the or more machine learning algorithms to generate the machine learning model, the executing the or more machine learning algorithms generating or more correlations between a plurality of nodes and at least two of the plurality of nodes, and each node representing a value associated with an event and corresponding to a weight;
detecting an th communication from the computing device, the th communication being associated with a user and corresponding to a request to initiate processing associated with a particular event, the th request being associated with an actual or expected cost, and the th communication being received at a cost tracking system;
in response to detecting the communication, determining one or more variables from the request, each variable of the one or more variables representing a characteristic of the particular event;
mapping the or more variables to the plurality of nodes of the machine learning model;
based at least in part on the mapping, identifying or more nodes for each of the or more variables, the or more nodes being included in the plurality of nodes of the machine learning model, and the or more correlations being used to identify the or more nodes;
retrieving or more values associated with each of the or more nodes, and
sending a second communication to the computing device, the second communication being responsive to the th communication and including at least of the retrieved or more values.
12. The system of claim 11, wherein the operations further comprise:
identifying a client variable from the request, the client variable being of the variables determined from the request;
in response to identifying the client variable, accessing one or more rules associated with the client variable;
restricting sets of nodes identified using the one or more dependencies, the sets of nodes being restricted to a subset of nodes, the restricting based on the one or more rules;
retrieving a value for each node in the subset of nodes; and
sending the second communication to the computing device, the second communication including the retrieved value.
13. The system of claim 11, wherein the collection of the data set is performed continuously such that when a new event occurs, the new event is included in the data set.
14. The system of claim 13, wherein the operations further comprise:
updating the machine learning model when the new event is included in the dataset such that at least weights corresponding to nodes of the plurality of nodes are updated.
15. The system of claim 11, wherein the particular event corresponds to a future event, and wherein the retrieved or more values correspond to or more recommended values provided as recommendations associated with the particular event.
16. The system of claim 11, wherein the operations further comprise:
detecting a third communication from an additional computing device, wherein the third communication corresponds to another requests to initiate another processes associated with the particular event, wherein the third communication is received after the communication is received and before the particular event occurs;
identifying that the th communication and the third communication each correspond to the particular event, and
sending an alert message to the additional computing device, the alert message including a notification that a user associated with the communication is also associated with the particular event.
17. The system of claim 16, wherein the operations further comprise:
sending a fourth communication to the additional computing device, the fourth communication being responsive to the third communication and including at least of the retrieved or more values.
18. The system of claim 16, wherein the user associated with the th communication and a different user associated with the third communication are each associated with the same entity.
19. The system of claim 11, wherein the operations further comprise:
detecting that a particular node of the one or more nodes is associated with a predicted occurrence that corresponds to an event parameter exceeding a defined threshold, and
accessing a workflow associated with the predicted occurrence, the workflow comprising an identification of or more documents associated with the predicted occurrence, the or more documents identifying a process for obtaining compensation associated with the particular node.
20. The system of claim 11, wherein the particular event is an event that has previously occurred, and at least of the or more nodes correspond to a workflow for identifying or more documents, the or more documents identifying a process for obtaining compensation associated with the particular event.
Technical Field
More particularly, the present disclosure relates to systems and methods for applying machine learning techniques to historical expense data to intelligently provide support information.
Background
Employees often travel on business for their employers. During business trips, costs may be incurred. Systems that request reimbursement (reimbursement) are often cumbersome and inefficient. For example, the employer-defined agreement may be unknown or difficult to access to the user. Additionally, determining aspects of the discrepancy (e.g., a schedule) may be time consuming.
Disclosure of Invention
In embodiments, a user interface may be provided to enable a user to initiate processing associated with an event (e.g., a business trip event). examples of initiating processing associated with an event may include defining an event (e.g., a scheduled flight), requesting compensation (offset) (e.g., reimbursement), requesting documents related to obtaining compensation, etc. the event may have occurred before or may be set to a future time.
In another embodiments, the centralized repository may store data objects (e.g., fare reports) received from various user devices, e.g., the th user device may send th data object (e.g., a booked flight to a particular city) to the centralized repository at th time, and the second user device may send a second data object (e.g., a request to book a flight to a particular city) to the centralized repository at a second time (after th time), when the system receives the second data object, the system may detect a correlation between the second data object and the th data object, e.g., when each of the th and second data objects corresponds to an event in a particular location (e.g., a flight to the same city), may detect a correlation, after detecting a correlation, the system may notify a notification message (e.g., via a pop-up window, push message in native application, information toolkit, text message, web user interface (e.g., a) to send a second user device indicating that the second user device has taken a previous reservation action, e.g., a number of flights, e.g., a number of previous reservation actions, e.g., a number of flights, indicating that the second user devices may be a previous reservation action, e.g., a number of additional user devices, e.g., a number of previous reservation actions, a number of additional user devices, e.g., a number of additional information indicating that a reservation actions may be performed in a number of previous reservation actions, e.g., a number of alert 9635, a number of previous reservation actions, a number of alert, e.g., a reservation actions, a reservation of alert, a.
In some embodiments , methods computer-implemented methods are provided, the methods may include collecting a data set for generating a machine learning model using 0 or more machine learning algorithms, the data set may include 1 or more previously occurring events, or more events each of which may correspond to or more event parameters identifying characteristics of the event, the methods may further include defining 5 or more evaluation metrics using or more event parameters, each evaluation metric may be used to classify or more events as an event type, additionally, the methods may include evaluating or more evaluation metrics and a data set, the evaluating may include executing or more machine learning algorithms to generate a machine learning model, the execution of or more machine learning algorithms may generate a plurality of nodes and the plurality of nodes between which may be associated with a plurality of nodes, and the plurality of nodes may be associated with a plurality of communication parameters, such as a number of communication parameters, a number of which may be associated with a number of communication nodes , and a number of which may be associated with a number of communication parameters corresponding communication parameters, such as a number of communication parameters , a number of communication between each of the number of nodes and a number of which may be associated with a number of communication device, a number of communication request, a number of which may be associated with at least one of a number of communication node , a number of communication device , and a number of which may be associated with a number of communication node , or a number of communication node , and which may be associated with a number of communication request, a number of communication node , and which may be associated with a number of communication node , or a number of communication node may be associated with a number of communication node , and which may be associated with a number of communication node, a number of communication device may be associated with a number of communication, or a number of communication request may be associated with a number of communication, a number of communication node , a number of communication, a number of.
In embodiments, computer program products are provided that are tangibly embodied in a non-transitory machine-readable storage medium, the computer program products may include instructions configured to cause or more data processors to perform part or all of the methods disclosed herein in embodiments, systems are provided that may include or more data processors and a non-transitory computer-readable storage medium containing instructions that, when executed on or more data processors, cause or more data processors to perform part or all of the methods disclosed herein.
Advantageously, embodiments of the present disclosure relate to training or generating machine learning models using or more machine learning algorithms using stored data objects previously submitted by various user devices (e.g., stored, previously received data objects) as a data set.
The following detailed description and the accompanying drawings will provide a better understanding of the nature and advantages of the present disclosure.
Drawings
Illustrative embodiments of the invention are described in detail below with reference to the following drawings:
FIG. 1 illustrates an example network for controlling resource access and operation across subsystems and/or systems.
Fig. 2 shows a simplified block diagram of a machine learning network environment.
FIG. 3 is a flow chart illustrating a process for determining correlations within a data set using a machine learning algorithm.
FIG. 4 depicts a simplified diagram of a distributed system for implementing of an embodiment.
Fig. 5 is a simplified block diagram of components of a system environment through which services provided by components of an embodiment system may be provisioned as cloud services, according to an embodiment of the present disclosure.
FIG. 6 illustrates an exemplary computer system in which various embodiments of the invention may be implemented.
Detailed Description
In the following description, for purposes of explanation, specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, that various embodiments may be practiced without these specific details. The drawings and description are not intended to be limiting.
FIG. 1 shows an example network 100 for controlling resource access and operation across subsystems and/or systems, network 100 includes a system corresponding to a plurality of clients and a plurality of locations, more specifically, each of on-site client 1 system 102, virtual client system 106, and client 2 system 104 may correspond to sets of devices and/or other components, such as or more servers (e.g., and/or a server farm or server cluster), user devices (e.g., desktop computers, laptops, tablets, or smartphones), data storage devices (e.g., network attached storage), and/or equipment, in cases (e.g., for on-site client 1 systems), the sets of devices and/or other components may be co-located , such as within or more buildings or geographic areas associated with the clients.
Each of the plurality of subsystems may, for example, be configured to perform different types of operations, use different resources (and/or different types of resources), generate different types of output, be located in different geographic locations, correspond to (e.g., grant access to) different agents or users (e.g., different portions of an organization), etc. for example, the on-site client system 102 may include an -th subsystem 110 and a second subsystem 112. the 0-th subsystem 110 may be configured to receive and respond to content requests from user devices, and the second subsystem 112 may be configured to dynamically monitor and reconfigure network resources. the -th and second subsystems 112 may communicate via the WiFi network 108 or the local area network 114. each of the -th and second subsystems 110, 112 may also communicate with the subsystem coordination resource 116. the subsystem coordination resource 116 may process data from each of the -or multiple subsystems to, for example, determine whether operations at the subsystem are associated with operations at the 352-level or how the multiple subsystems 82923 and/493 are assigned to the subsystem.
The implementation depicted in FIG. 1 illustrates various types of resources of a system. It will be appreciated that these resources are illustrative. Resources represented by separate blocks may, but need not, correspond to separate devices or groups of devices.
In the depicted example, the th subsystem 110 includes a content management resource 118 configured to query one or more data stores for content in response to content requests and send responses to the content requests, for example, the content management resource 118 may be configured to receive HTTP requests from user devices 119 and respond with web page data, the th subsystem 110 may also include a security resource 120 configured to determine what data various users are authorized to receive and/or what types of actions various agents are authorized to perform, for example, the security resource 120 may receive or intercept requests from the agent device 122 to add or modify data in the content data store (e.g., stored locally at the th subsystem 110 or remotely), and determine whether to allow such additions or modifications (e.g., based on authentication of the agent device 122 and/or information associated with the request).
The th subsystem 110 also includes processing resources 124 that may be configured to perform data processing, such as processing retrieved content (e.g., to convert it from a th format to a second format or to identify particular content objects to retrieve in response to a request). the th subsystem 110 also includes scheduling resources 126 that may monitor incoming requests and identify when each request is to be processed (e.g., by managing a queue of requests).
The second subsystem 112 includes a performance monitoring resource 128 that may evaluate data logs corresponding to requests processed by the th subsystem 110. evaluation may include monitoring speed and error rate of processing requests. the results of the evaluation may be sent to another proxy devices 130. the network configuration resource 132 may initiate various reconfigurations that may affect performance, such as server allocation.
The client 2 system 104 includes equipment resources 134 that may be configured to generate outputs, for example, the equipment resources 134 may, for example, process inputs (e.g., parts, materials, and/or input data) to generate tangible products (e.g., manufactured or assembled parts) or intangible results (e.g., quantitative characterizations of samples or parts, biometrics, environmental data, wireless signal characteristics, etc.). the sensor resources 136 may be configured to generate readings corresponding to the operation of the equipment resources 134, such as operating temperatures and/or energies used.
For example, the operational parameters may include or at least partially define portion of a workflow that will occur as part of processing of the request (e.g., at least partially via equipment resource 134). in cases, the local or remote security resource verifies that a particular agent device or corresponding agent is authorized to provide such parameters and/or gain access.
In some cases, the virtual client system 106 may be identified as a local subsystem (e.g., the first subsystem 110 and/or the second subsystem 112) or as a local subsystem or as being used by a local subsystem.
In the depicted example, virtual client system 106 includes data storage resources 142, which may include databases and/or data repositories of clients, the databases and/or data repositories may be configured to facilitate periodic updates and/or retrieval of data in response to queries generated and coordinated by query resources 144, for example, the data repositories may include content objects managed by content management resources 118, and query resources 144 may be configured to generate queries for content objects from external sources (e.g., source system 146).
The usage monitoring resource 148 may generate data logs corresponding to, for example, incoming communications, internal system performance (e.g., of content retrieval or equipment operations) and/or system communications the usage monitor 148 may generate and maintain data logs evaluated by the performance monitoring resource 128 based on monitoring of requests and request responses processed by the content management resource 118, as another examples, the usage monitor 148 may generate and maintain data logs of quality metrics and/or maintenance events corresponding to the equipment resources 134, as yet another examples, the usage monitor 148 may generate and maintain data logs of sensor measurements collected by the sensor resources 136.
For example, the frequency, source, and/or requested content of content object requests may be evaluated data logs are evaluated to determine if any pattern, trend, and/or log element frequency is indicative of a security threat. As yet another example, the security resource 150 may monitor equipment operations or proxy instructions to determine if any operations or instructions are atypical or correspond to satisfaction of an alarm indication as compared to or more characteristics of previous instructions.when a potential threat decision is detected by the security resource 150, it may trigger an alarm to be sent to a proxy device such as proxy device 122, proxy device 140, or external proxy device 152.
Allocation resources 152 may control which cloud resources are allocated to a given client, client subsystem, task execution, and the like. For example, allocation resources 152 may control allocation of memory, data stores (e.g., network attached storage), processors, and/or virtual machines.
FIG. 2 shows a simplified block diagram of a machine learning network environment, as shown in the example of FIG. 2, network environment 200 includes user devices 205, 210, and 215, although the illustration of FIG. 2 shows user device 205 as a smartphone and user devices 210 and 215 as desktop computers, it should be appreciated that any number of any type of user devices may be included in network environment 200. in the case of , the user devices may be operated by users (e.g., employees) associated with an entity (e.g., an employer). additionally, user devices 205, 210, and 215 may be configured to connect to a network (e.g., network 235 and/or 240) to send or more data objects to a centralized repository 220. in the case of , the user devices may communicate with the centralized repository 220 using or more interfaces (e.g., interfaces 245, 250, and 255. in the case of , 250, 255 are the same interfaces that facilitate connection to the repository 220, in the case of other interfaces 245, 255 and 250 may operate at a higher level than if the user devices operate at a higher security level than the centralized repository 250, , the user devices 205, , and operate according to the user devices.
The centralized repository 220 may include or more servers in communication (wired or wireless) with or more data repositories, additionally, the centralized repository 220 may be a network location that stores all of the various data objects received from the user devices (via an interface, such as an interface managed by an entity). In some cases, if 10,000 users are associated with an entity, or all of the 10,000 users may submit the various data objects using or more interfaces. , once a data object is sent from a user device, the data object may be sent over or more networks to be stored at the centralized repository 220. in the cases of , a data stream may be sent to the centralized repository 220. for example, a data stream may include a plurality of data objects.
The machine learning system 225 may include or more servers and/or computing devices configured to execute or more machine learning algorithms using a data set stored in the centralized repository 220. or more machine learning algorithms, decision trees, workflows, and/or models may be stored in the data repository 230. the data repository 230 may also store data generated by or for an entity (e.g., usernames, parts , projects, jobs, etc.) non-limiting examples of machine learning algorithms or techniques may include artificial neural networks (including back propagation, Boltzmann (Boltzmann) machines, etc.), bayesian (baysian) statistics (e.g., bayesian networks or knowledge bases), logistic trees, support vector machines, information fuzzy networks, hidden markov models, hierarchical clustering (unsupervised), self-organizing maps, clustering techniques, and other suitable machine learning techniques (supervised or unsupervised), for example, the machine learning system 225 may retrieve 56 or hidden markov models stored in the data repository to generate a relevant clustering (unsupervised or unsupervised) data models, and may be used as an example for identifying relevant data set of a relevant learning algorithms, or as a relevant data set for use in a predictive model, or as an example, a predictive model for identifying relevant data set of a relevant data set, or for use in a relevant learning algorithm, a relevant data set, or for use as an example, a predictive model, or for an example, a predictive model for identifying a relevant data set, a data set, or for use, a data set, or a, a data set, a, or a data set, a system.
As yet another example, , machine learning system 225 may include a tree learning model in which observations are mapped to determine which future state is most likely to be linked to the current state based on information included in the data objects.1) the tree learning model may be configured with two assumptions 1) that a user who has initiated processing associated with a particular event (e.g., a business trip plan, a cost of occurrence, a hotel reservation, a cost of eating in a restaurant, etc.) will send at least data objects and, if so, which values may be included in the data objects, and/or 2) that a user will submit data objects that include events in each of a plurality of classified event types (e.g., business trip, lodging, eating, etc.) and, if so, which values were submitted by the previous user for each event type.
In , the data object may not include a fare report, but rather include a request defining an event having an expected fare, the event may have or more event parameters (e.g., a location of a hotel, a price of a dinner, a price of a flight, a destination city of a flight, etc.) in addition, the event parameters for various events may be classified as or more event parameters (e.g., a location of a hotel, a price of a dinner, a price of a flight, a destination city of a flight, etc.) and may be stored in a travel data collection device, a travel data collection device.
The interface may provide the user with information about other user experiences, such as a particular destination, when the user device sends a data object, as another examples, by applying machine learning techniques to data objects previously received from the user, the user may be provided with a ranked list of most popular hotels in the destination city and feedback from users (who have previously lived in these hotels) using the machine learning model.
In examples, a machine learning model may be used to identify supporting documents or information associated with an event, for example, if the event corresponds to a hotel reservation, or more documents that outline the entity's policy and/or processes that require compensation may be identified using the machine learning model.
In examples, when a user device sends a particular data object, or more variables (e.g., data fields within the data object) may be associated with the group of stored data objects support information associated with the group of stored data objects may be used to identify support information specific to the particular data object in cases output data may be retrieved from a machine learning model in real-time, for example, if the user device 205 is on the go, the current location of the user device may be identified and support information associated with the current location (e.g., the nearest cheapest restaurant) may be retrieved.
In examples, a machine learning model may be used and applied in a social network context, as an example, a user device operated by a user may send a 1 data object indicating a particular event (e.g., a reservation for a future flight), in addition, a second user device operated by a second user may send a second data object indicating the same particular event, a machine learning model and/or 2 or more rules may be used to identify data objects of particular events sent by a 583 user and the second user, in addition, each of the user device and the second user device may receive an alert message indicating that another user sent a data object of a particular event, a user and the second user may or may not be associated with the same entity as the event 9, in examples, the user may send data objects and the data objects may be used to generate data objects that may be associated with the same entity as the user coordination with another user (e.g., a table may be used to infer that the user may be able to use these data objects to generate data objects as inferred data objects from the data objects of the second user database 72, and/or may be used to generate data objects from the same user devices may be associated with the same entity as inferred data objects 3614, and/or inferred from the second data objects 365 in proximity to generate data repository 845, and/or from the same data objects 3614, the inferred data objects 3614, and/or from the inferred data repository 365 user devices may be associated with the inferred data objects of the same user data objects of the inferred data objects , and/or other user identified by the inferred data objects , and/or other user devices may be associated with the inferred data objects 3614 user devices may be used to generate data objects in the inferred by the system under the inferred by the inferred under the inferred system under the inferred data repository 3614 example, 3614, , 3614, 367 user data repository 367 user data object may be associated with the inferred data object, , 367 user data object may be associated with the inferred data object under the inferred data object under the inferred data.
In another example, the user may upload documents to the data repository during or after the occurrence of the event.
In examples, the system may append metadata to the identified support information to provide additional information and/or to provide supplemental information to the support information.
For example, the process 300 may include requesting compensation for an event (e.g., when the event has previously occurred) or requesting support information associated with the event (e.g., when the event may have occurred at a future time.) the process 300 begins at block 305, wherein a data set used to generate the machine learning model is collected. the machine learning model may be generated using or more machine learning algorithms.
In this example, event parameters of a difference distance may be used to classify the event as a flight.
At block 315, the data set and evaluation metrics may be evaluated, hi cases, evaluating the data set and evaluation metrics includes determining or identifying correlations between data objects within the data set.e., evaluating the data set and evaluation metrics may include executing or more machine learning algorithms to generate a machine learning model. or more machine learning algorithms may be related to unsupervised learning techniques, although the disclosure is not so limited.
If the classified event type is a hotel, then the various nodes of the hotel event type may include different hotels included within the collected data set. in some cases, the nodes may be represented by a hierarchical tree structure including a root node, non-leaf nodes, and leaf nodes. node may correspond to a hotel (e.g., the value of the node), and a second node may correspond to a second hotel (e.g., the value of the second node). additionally, for example, each node may be assigned a weight corresponding to the frequency of occurrence of a particular hotel.
At block 320, a th communication may be detected at a system (e.g., a centralized repository and/or a server in communication with the centralized repository). The th communication may be initially sent by a user device (e.g., user device 205) operated by a user.it will be appreciated that any th communication may be sent from any computing device by any individual on behalf of the user. th communication may be associated with a user operating the user device.A user device may display an interface (e.g., interface 245) and the interface may be configured to receive input from the user.an input received at the interface may correspond to a request to initiate a process associated with a particular event.an example of a request to initiate a process associated with an event may include a request to define an event (e.g., book a flight, book a room, book a seat, etc.), a request to compensate for an event (e.g., at a restaurant), a request to an entity document related to an event (e.g., an entity's reimbursement policy and/or process file), etc. a request to initiate a specific event (e.g., a restaurant), a restaurant, a cost may be a cost of a given by a hotel, a restaurant, a system may include a cost of a given for a given event (e.g., a given event).
At block 325, one or more variables may be determined from the request, in cases, the variables may represent characteristics of the particular event, for example, if the particular event is a hotel reservation on a future date, the requested variables associated with the particular event may include the location of the hotel, the date of the requested stay at the hotel, the name of the hotel, the type of event (e.g., hotel and flight), etc. in cases, the requested variables may include a process indicating whether the request initiated a previously occurring event or a future event.
For example, if a particular event represents a flight to san francisco, the mapping may include identifying whether there is a node in the plurality of nodes that represents san francisco as a destination city.
At block 335, or more nodes may be identified from among the plurality of nodes or more nodes may be associated with each of 1 or more variables determined from the request, based at least in part on the mapping at block 330. additionally, the identified 0 or more nodes may be associated with or more correlations determined from a machine learning algorithm performed using the data set may be used to identify or more nodes, for example, the identified or more nodes will be nodes associated with a node representing a particular event.
In 1, the weights may correspond to a number of users previously associated with the event (e.g., how many users were previously parked at a particular hotel, how many users have flown to san francisco, etc.), in , the weights may be generated based at least in part on user feedback (e.g., if a user associated with an entity provides negative feedback for a particular restaurant, the weight representing the node of the restaurant may be low, such that the restaurant is not recommended to employees who will be traveling to a region near the restaurant, the weight representing the restaurant may be selected or identified at block 335 when restaurant 2 or more nodes each have a weight above a defined threshold, the system may select or identify the one or more hotel nodes as having a higher weight than the weight of a restaurant routine at block , alternatively, the weight representing the restaurant may be selected as a more frequent dining node than the restaurant routine learning algorithm at block 49335, or the weight representing the restaurant may be selected as a more frequent dining node than the restaurant routine learning algorithm at block 7335.
In cases, where a group of nodes is identified , metadata identified based on information included in the request (e.g., information indicating a purpose of the event) may be used to limit the group of nodes to a subset of nodes.
Using the example above, if or more nodes include a th node, a second node, and a third node, values representing each node may be retrieved.A value may identify information about the node, for example, a value representing a th node may include a name of a restaurant, a value representing a second node may represent a name of a taxi company, and a value representing a third node may include links to or more entity documents.
In addition, the second communication may include at least of the or more values retrieved.
FIG. 4 depicts a simplified diagram of a distributed system 400 for implementing of the embodiments, hi the illustrated embodiment, the distributed system 400 includes or more client computing devices 402, 404, 406, and 408 configured to execute and operate client applications, such as web browsers, proprietary clients (e.g., Oracle Forms), etc., over a network 410 ( or more). Server 412 may be communicatively coupled with remote client computing devices 402, 404, 406, and 408 via network 410.
In various embodiments, server 412 may be adapted to run or more services or software applications provided by or more components of the system in embodiments, these services may be provided as web-based services or cloud services, or provided to users of client computing devices 402, 404, 406, and/or 408 under a software as a service (SaaS) model.
In the configuration depicted in the figure, software components 418, 420, and 422 of system 400 are shown as being implemented on server 412. in other embodiments, or more components of system 400 and/or services provided by these components may also be implemented by or more of client computing devices 402, 404, 406, and/or 408. then, a user operating a client computing device may utilize services provided by these components with one or more client applications.these components may be implemented in hardware, firmware, software, or a combination thereof.
Client computing devices 402, 404, 406, and/or 408 may be portable handheld devices (e.g.,
Although the exemplary distributed system 400 is shown with four client computing devices, any number of client computing devices may be supported. Other devices (such as devices with sensors, etc.) may interact with the server 412.
Network(s) 410 in distributed system 400 may be any type of network familiar to those skilled in the art that may support data communications using any of a variety of commercially available protocols, including, but not limited to, TCP/IP (Transmission control protocol/Internet protocol), SNA (System network architecture), IPX (Internet message exchange), AppleTalk, etc. by way of example only, network(s) 410 may be a Local Area Network (LAN), such as an Ethernet, token Ring, etc., network(s) 410 may be a domain network and the Internet, which may include virtual networks, including but not limited to a Virtual Private Network (VPN), an intranet, an extranet, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (e.g., in accordance with the institute of Electrical and electronics (IEEE)802.11 protocol suite, a network,
The server 412 may be comprised of or more general purpose computers, special purpose server computers (including, by way of example, PC (personal computer) servers, and the like,
Server 412 can run an operating system comprising any of the operating systems discussed above, as well as any commercially available server operating system Server 412 can also run any of a variety of additional server applications and/or intermediate layer applications, including HTTP (HyperText transfer protocol) servers, FTP (File transfer protocol) servers, CGI (common gateway interface) servers, Windows,
In implementations, the server 412 may include or more applications to analyze and integrate data feeds and/or event updates received from users of the client computing devices 402, 404, 406, and 408.Feeding,
Distributed system 400 may also include or more databases 414 and 416 the databases 414 and 416 may reside in various locations of the databases 414 and 416 may reside on non-transitory storage media local to the server 412 (and/or resident in the server 412), as an example, alternatively, the databases 414 and 416 may be remote from the server 412 and communicate with the server 412 via a network-based connection or a dedicated connection group embodiment, the databases 414 and 416 may reside in a Storage Area Network (SAN) familiar to those skilled in the art.
FIG. 5 is a simplified block diagram of or more components of a system environment 500 through which system environment 500 services provided by or more components of an embodiment system may be provided as cloud services, hi the illustrated embodiment, system environment 500 includes or more client computing devices 504, 506, and 508 that may be used by a user to interact with cloud infrastructure system 502 that provides cloud services.
In addition, the embodiments shown in the figures are merely examples of cloud infrastructure systems that may incorporate embodiments of the invention, in some other embodiments, cloud infrastructure system 502 may have more or fewer components than shown in the figures, may combine two or more components, or may have a different configuration or arrangement of components.
Client computing devices 504, 506, and 508 may be similar devices to those described above for 402, 404, 406, and 408.
Although the exemplary system environment 500 is shown with three client computing devices, any number of client computing devices may be supported. Other devices, such as devices with sensors, may interact with cloud infrastructure system 502.
Network(s) 510 may facilitate data communication and exchange between clients 504, 506, and 508 and cloud infrastructure system 502. each network may be any type of network familiar to those skilled in the art that may support data communication using any of the various commercially available protocols, including those described above for network(s) 410 ().
Cloud infrastructure system 502 may include or more computers and/or servers, which may include those described above for server 412.
In some embodiments, the services provided by the cloud infrastructure system may include many services available on demand to users of the cloud infrastructure system, such as online data storage and backup solutions, Web-based email services, hosted office (office) suites and document collaboration services, database processing, managed technical support services, and the like.
In examples, services in a computer network cloud infrastructure may include protected computer network access to storage, hosted databases, hosted Web servers, software applications, or other services provided to users by a cloud provider, or as otherwise known in the art.
In certain embodiments, cloud infrastructure system 502 may include a suite of applications, middleware, and database services products delivered to customers in a self-service, subscription-based, elastically extensible, reliable, highly available, and secure manner. An example of such a cloud infrastructure system is the Oracle public cloud provided by the present assignee.
In various embodiments, cloud infrastructure system 502 may be adapted to automatically provision, manage, and track customer subscriptions to services offered by cloud infrastructure system 502. cloud infrastructure system 502 may provide cloud services via different deployment models.A service may be provided in accordance with a public cloud model, where cloud infrastructure system 502 is owned by an organization that sells cloud services (e.g., owned by Oracle), and is available to enterprises of the same public or different industries.As another examples, a service may be provided in accordance with a cloud private model, where cloud infrastructure system 502 operates only for a single organization, and may provide services to or more entities within the organization.
In embodiments, the services provided by cloud infrastructure system 502 may include or more services offered under a software as a service (SaaS) category, a platform as a service (PaaS) category, an infrastructure as a service (IaaS) category, or other service categories including hybrid services.
In some embodiments , the services provided by the cloud infrastructure system 502 can include, but are not limited to, application services, platform services, and infrastructure services. , in some examples, application services can be provided by the cloud infrastructure system via a SaaS platform.
In embodiments, platform services may be provided by a cloud infrastructure system via a PaaS platform that may be configured to provide cloud services that fall into PaaS categories examples of platform services may include, but are not limited to, services that enable an organization (such as Oracle) to integrate existing applications on a shared public architecture and leverage the ability of the platform-provided shared services to build new applications.
embodiments, the platform services provided by the cloud infrastructure system can include database cloud services, middleware cloud services (e.g., Oracle fusion middleware services), and Java cloud services in embodiments, the database cloud services can support a shared services deployment model that enables organizations to aggregate database resources and provision database-as-a-service to customers in the form of a database cloud.
Various infrastructure services may be provided by the IaaS platform in the cloud infrastructure system. Infrastructure services facilitate management and control of underlying computing resources, such as storage, networks, and other underlying computing resources, for customers to utilize services provided by SaaS platforms and PaaS platforms.
In embodiments, the infrastructure resources 530 may include a combination of pre-integrated and optimized hardware (such as servers, storage, and networking resources) to perform the services provided by the PaaS platform and the SaaS platform.
For example, cloud infrastructure system 530 may enable a group of users in time zone to utilize the resources of the cloud infrastructure system for a specified number of hours, and then enable the same resources to be reallocated to another group of users located in a different time zone, thereby maximizing utilization of the resources.
In certain embodiments, multiple internal shared services 532 may be provided that are shared by different components or modules of cloud infrastructure system 502 as well as services provided by cloud infrastructure system 502. These internal sharing services may include, but are not limited to: security and identity services, integration services, enterprise repository services, enterprise manager services, virus scanning and whitelisting services, high availability, backup and restore services, cloud support enabled services, email services, notification services, file transfer services, and the like.
In embodiments, cloud management functions may include capabilities for provisioning, managing, and tracking customer subscriptions, etc. received by cloud infrastructure system 502.
In embodiments, as depicted in the figure, cloud management functionality may be provided by or more modules, such as order management module 520, order orchestration module 522, order provisioning module 524, order management and monitoring module 526, and identity management module 528.
In an example operation 534, a customer using a client device (such as client device 504, 506, or 508) may interact with cloud infrastructure system 502 by requesting or more services provided by cloud infrastructure system 502 and placing an order to subscribe to or more services offered by cloud infrastructure system 502.
After the customer places the order, order information is received via cloud UI 512, 514, and/or 516.
At operation 536, the order is stored in an order database 518 the order database 518 may be one of several databases operated by the cloud infrastructure system 518 and operated with other system elements .
At operation 538, the order information is forwarded to the order management module 520 in cases, the order management module 520 may be configured to perform billing and accounting functions related to the order, such as validating the order and ordering the order after validation.
At operation 540, information regarding the order is communicated to the order orchestration module 522 may orchestrate the provision of services and resources for the order placed by the customer using the order information at in some cases, the order orchestration module 522 may orchestrate the provision of resources using the services of the order provision module 524 to support the subscribed services.
In certain embodiments, order orchestration module 522 enables management of business processes associated with each order and application of business logic to determine whether the order should proceed to provisioning. At operation 542, upon receiving a newly subscribed order, the order orchestration module 522 sends a request to the order provisioning module 524 to allocate resources and configure those resources needed to fulfill the subscribed order. The order provisioning module 524 enables allocation of resources for the services ordered by the customer. Order provisioning module 524 provides an abstraction layer between the cloud services provided by cloud infrastructure system 500 and the physical implementation layer for provisioning resources for providing the requested services. Thus, the order orchestration module 522 may be isolated from implementation details (such as whether services and resources are actually provisioned immediately or pre-provisioned and only allocated/assigned after a request).
At operation 544, , upon provisioning of the services and resources, may send a notification of the services provided to the customer on client devices 504, 506, and/or 508 through order provisioning module 524 of cloud infrastructure system 502.
At operation 546, the order management and monitoring module 526 may manage and track the customer's subscription orders in some cases, the order management and monitoring module 526 may be configured to collect usage statistics for the services in the subscription order, such as the amount of memory used, the amount of data transferred, the number of users, and the amount of system run time and system downtime time.
In , the identity management module 528 may control information about customers who wish to utilize services provided by the cloud infrastructure system 502. such information may include information that authenticates the identities of these customers and information that describes which actions these customers are authorized to perform with respect to various system resources (e.g., files, directories, applications, communication ports, memory segments, etc.).
FIG. 6 illustrates an exemplary computer system 600 in which various embodiments of the invention may be implemented. System 600 may be used to implement any of the computer systems described above. As shown, computer system 600 includes a processing unit 604 that communicates with a number of peripheral subsystems via a bus subsystem 602. These peripheral subsystems may include a processing acceleration unit 606, an I/O subsystem 608, a storage subsystem 618, and a communication subsystem 624. Storage subsystem 618 includes tangible computer-readable storage media 622 and system memory 610.
Bus subsystem 602 provides a mechanism for letting the various components and subsystems of computer system 600 communicate with each other as intended, although bus subsystem 602 is shown schematically as a single bus, an alternative embodiment of a bus subsystem may utilize multiple buses, bus subsystem 602 may be any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures.
Processing unit 604, which may be implemented as or more integrated circuits (e.g., a conventional microprocessor or microcontroller), controls the operation of computer system 600. or more processors may be included in processing unit 604.
In various embodiments, processing unit 604 may execute various programs in response to program code and may maintain multiple concurrently executing programs or processes at any given time, or all of the program code to be executed may reside in processor(s) 604 and/or storage subsystem 618.
The I/O subsystem 608 may include user interface input devices and user interface output devices. The user interface input devices may include a keyboard, a pointing device such as a mouse or trackball, a touchpad or touch screen incorporated into the display, a scroll wheel, a click wheel, a dial, a button, a switch, a keyboard, an audio input device with voice command recognition systemA microphone, and other types of input devices. The user interface input device may include, for example, a motion sensing and/or gesture recognition device, such as Microsoft Windows
User interface input devices may also include, but are not limited to, three-dimensional (3D) mice, joysticks or pointing sticks, game pads and graphics tablets, and audio/video devices such as speakers, digital cameras, digital video cameras, portable media players, web cameras, image scanners, fingerprint scanners, barcode readers, 3D scanners, 3D printers, laser rangefinders, and gaze tracking devices. Further, the user interface input device may comprise, for example, a medical imaging input device, such as a computed tomography scan, magnetic resonance imaging, positron emission tomography, medical ultrasound device. The user interface input devices may also include, for example, audio input devices such as MIDI keyboards, digital musical instruments, and the like.
generally, use of the term "output device" is intended to include all possible types of devices and mechanisms for outputting information from computer system 600 to a user or other computer.
Computer system 600 may include a storage subsystem 618, shown as currently located in system memory 610, containing software elements. System memory 610 may store program instructions that are loadable and executable on processing unit 604, and data generated during the execution of these programs.
Depending on the configuration and type of computer system 600, system memory 610 may be volatile (such as Random Access Memory (RAM)) and/or non-volatile (such as Read Only Memory (ROM), flash memory, and the like.) RAM typically contains data and/or program modules that are immediately accessible to and/or presently being operated on and executed by processing unit 604. in implementations, system memory 610 may include a variety of different types of memory, such as Static Random Access Memory (SRAM) or dynamic random access memory (DRAM.) in implementations, such as a basic input/output system (BIOS) containing the basic routines that help to transfer information between elements of computer system 600 during startup, which may typically be stored in ROM. by way of example and not limitation, system memory 610 also shows application programs 612, program data 614, and operating system 616. By way of example, the operating system 616 may include various versions of Microsoft Windows
Storage subsystem 618 may also provide a tangible computer-readable storage medium for storing the basic programming and data structures that provide the functionality of the embodiments.
Storage subsystem 600 may also include a computer-readable storage media reader 620, which may be further connected to a computer-readable storage medium 622, along with system memory 610 and, optionally, in conjunction therewith, computer-readable storage medium 622 may represent a remote, local, fixed, and/or removable storage device plus storage media for temporarily and/or more permanently containing, storing, transmitting, and retrieving computer-readable information.
Computer-readable storage media 622 containing the code or portions of code may also include any suitable media known or used in the art, including storage media and communication media, such as, but not limited to, volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage and/or transmission of information. This may include tangible computer-readable storage media such as RAM, ROM, electrically erasable programmable ROM (eeprom), flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or other tangible computer-readable media. This can also include non-tangible computer-readable media, such as data signals, data transmissions, or any other medium that can be used to transmit desired information and that can be accessed by the computing system 600.
By way of example, the computer-readable storage media 622 may include a hard disk drive that reads from or writes to non-removable, nonvolatile magnetic media, a magnetic disk drive that reads from or writes to a removable, nonvolatile magnetic disk, and removable, nonvolatile optical disks (such as CD ROMs, DVDs, and the like)
The communications subsystem 624 provides an interface to other computer systems and networks the communications subsystem 624 serves as an interface for receiving data from other systems and sending data from the computer system 600 to other systems the communications subsystem 624 may, for example, enable the computer system 600 to connect to or more devices via the Internet in embodiments the communications subsystem 624 may include a Radio Frequency (RF) transceiver component for accessing a wireless voice and/or data network (e.g., an advanced data networking technology using cellular telephone technology such as 3G, 4G, or EDGE (enhanced data rates for global evolution), WiFi (IEEE802.11 series of standards), or other mobile communications technologies, or any combination thereof), a Global Positioning System (GPS) receiver component, and/or other components the communications subsystem 624 may, in embodiments, provide a wired network connection (e.g., Ethernet) in addition to or in place of the wireless interface.
In embodiments, the communications subsystem 624 may also receive input communications in the form of structured and/or unstructured data feeds 626, event streams 628, event updates 630, etc. on behalf of or multiple users that may use the computer system 600.
As an example, the communication subsystem 624 may be configured to receive data feeds 626 from users of social networks and/or other communication services in real-time, such as
Further, the communication subsystem 624 may also be configured to receive data in the form of a continuous data stream, which may include an event stream 628 and/or event updates 630 that may be continuous or unbounded in nature with real-time events not explicitly terminated. Examples of applications that generate continuous data may include, for example, sensor data applications, financial tickers, network performance measurement tools (e.g., network monitoring and traffic management applications), clickstream analysis tools, automotive traffic monitoring, and so forth.
The communication subsystem 624 may also be configured to output structured and/or unstructured data feeds 626, event streams 628, event updates 630, and the like, which or more databases may communicate with or more streaming data source computers coupled to the computer system 600.
The computer system 600 may be of various types , including hand-held portable devices (e.g.,
Due to the ever-changing nature of computers and networks, the description of computer system 600 depicted in the figures is intended only as a specific example. Many other configurations are possible with more or fewer components than the system depicted in the figures. For example, custom hardware may also be used and/or particular elements may be implemented in hardware, firmware, software (including applets), or combinations thereof. In addition, connections to other computing devices, such as network input/output devices, may also be employed. Based on the disclosure and teachings provided herein, a person of ordinary skill in the art will recognize other ways and/or methods to implement the various embodiments.
In the foregoing specification, aspects of the present invention have been described with reference to specific embodiments thereof, but it will be recognized by those skilled in the art that the invention is not limited thereto.
- 上一篇：一种医用注射器针头装配设备
- 下一篇：广义量子通道