Systems and methods for hybrid content provisioning with dual recommendation engines

• US 10,355,924 B1
• Filed: 08/25/2016
• Issued: 07/16/2019
• Est. Priority Date: 04/08/2016
• Status: Active Grant

• Current Assignee: Pearson Education Incorporated (Pearson plc)
• Original Assignee: Pearson Education Incorporated (Pearson plc)
• Inventors: McAllister, Angie, Moriarty, Brian, McFall, Greg
• Primary Examiner(s): Zhen, Li B.
• Assistant Examiner(s): Buss, Benjamin J
• Application Number:
  US15/247,623
• Time in Patent Office: 1,055 Days
• Field of Search: None
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/322 Trees
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/338 Presentation of query results
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/123 Storage facilities
• CPC Class Codes: G06F 40/131 Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/226 Validation
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 : Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/04 : Inference or reasoning models
• CPC Class Codes: G06N 7/01 : Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 30/02 : Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0224 : based on user history
• CPC Class Codes: G06Q 30/0269 : based on user profile or attribute
• CPC Class Codes: G06Q 50/20 : Education
• CPC Class Codes: G09B 5/00 : Electrically-operated educational appliances working with questions and answers G09B7/00; simulators G09B9/00; advertising or displaying in general G09F
• CPC Class Codes: G09B 7/02 : of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
• CPC Class Codes: H04L 12/407 : with decentralised control
• CPC Class Codes: H04L 12/4641 : Virtual LANs, VLANs, e.g. virtual private networks [VPN] LAN interconnection over a bridge based backbone H04L12/462; encapsulation techniques H04L12/4633; routing of packets H04L45/00; packet switches H04L49/00; virtual private networks for security H04L63/0272
• CPC Class Codes: H04L 41/0806 : for initial configuration or provisioning, e.g. plug-and-play
• CPC Class Codes: H04L 41/142 : using statistical or mathematical methods
• CPC Class Codes: H04L 41/145 : involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 41/5051 : Service on demand, e.g. definition and deployment of services in real time
• CPC Class Codes: H04L 43/16 : Threshold monitoring
• CPC Class Codes: H04L 45/74591 : using content-addressable memories [CAM]
• CPC Class Codes: H04L 47/10 : Flow control; Congestion control
• CPC Class Codes: H04L 65/1069 : Session establishment or de-establishment
• CPC Class Codes: H04L 67/02 : based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/06 : specially adapted for file transfer, e.g. file transfer protocol [FTP]
• CPC Class Codes: H04L 67/10 : in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1095 : Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/1097 : for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/146 : Markers for unambiguous identification of a particular session, e.g. session cookie or URL-encoding
• CPC Class Codes: H04L 67/306 : User profiles
• CPC Class Codes: H04L 67/52 : specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/535 : Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 67/567 : Integrating service provisioning from a plurality of service providers
• CPC Class Codes: H04L 67/61 : taking into account QoS or priority requirements
• CPC Class Codes: H04W 88/02 : Terminal devices

Abstract

Systems and methods for content selection with first and second recommendation engines are disclosed herein. The system can include a memory include a content library database and a model database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include one or more servers that can include a packet selection system and a presentation system. These one or more servers can: receive response data from the user device; provide received response data to a first recommendation engine; alert a second recommendation engine when a selected next node is a placeholder node; retrieve at least one statistical model relevant to selection of next node content; and select next node content based on an output of the at least one statistical model.

Claims

1. A system for hybrid content provisioning, the system comprising:

memory comprising;

a user profile database comprising information relating to a plurality of users, wherein the information relating to the plurality of users comprises unique user history data associated with each of the users in the plurality of users; and

a content library database comprising a plurality of nodes linked in a sequential relationship in a content network, wherein some of the plurality of nodes are associated with guard conditions, wherein each guard condition identifies a condition for entrance into the node associated with that guard condition;

a user device comprising;

a first network interface configured to exchange data via a communication network; and

a first I/O subsystem configured to convert electrical signals to user interpretable outputs via a user interface; and

one or more servers configured to selectively use a rule-based recommendation engine and an adaptive recommendation engine of a dual recommendation engine configuration to perform state-based traversal of at least some of the plurality of nodes and to perform adaptive generation and presentation of node content based at least in part on;

receiving user identification information, wherein the user identification information identifies a user;

determining a location of the user identified by the received user identification information in the content network;

identifying potential next nodes based on the location of the user in the content network according to the rule-based recommendation engine;

determining a next node from the identified potential next nodes;

determining that the next node is a placeholder node;

consequent to the determining that the next node is the placeholder node, causing the adaptive recommendation engine to generate an output corresponding to next node content is based on a predictive model from a model database, wherein the predictive model is trained to select content based on inputs corresponding to at least a user skill level, and the next node content is based at least in part on;

retrieving potential placeholder content associated with the next node; and

identifying content from the retrieved potential placeholder content;

transmitting the output corresponding to the next node content to cause presentation of the next node content via the user device; and

after the output is transmitted, when a subsequent node is determined to not be a placeholder node, generating additional output based at least in part on the rule-based recommendation engine and subsequent content is directly linked to the subsequent node, and transmitting the additional output corresponding to subsequent node content to cause presentation of the subsequent node content via the user device.

2. The system of claim 1, wherein the next content is provided to the user via a presenter module.

3. The system of claim 2, wherein the presenter module resides in the one or more servers.

4. The system of claim 1, wherein the location of the user comprises a first node.

5. The system of claim 4, wherein identifying potential next nodes comprises:

identifying nodes directly linked to the first node by an edge; and

identifying a subset of the nodes directly linked to the first node by an edge that are non-prerequisite nodes to the first node.

6. The system of claim 5, wherein the one or more servers are further configured to:

retrieve guard conditions for the potential next nodes from the content library database; and

retrieve the unique user history data for the user.

7. The system of claim 6, wherein the next node is determined by application of the retrieved unique user history data to the retrieved guard conditions.

8. The system of claim 7, wherein the one or more servers are further configured to determine that the next node is a placeholder node.

9. The system of claim 8, further comprising the model database stored in the memory, wherein the model database comprises a plurality of predictive models.

10. The system of claim 9, wherein the predictive model comprises a mathematically based statistical model.

11. The system of claim 10, wherein the mathematically based statistical model is based on Item Response Theory (IRT).

12. The system of claim 7, wherein the one or more servers are further configured to determine that the next node is not a placeholder node.

13. A method of hybrid content provisioning, the method comprising:

selectively use a rule-based recommendation engine and an adaptive recommendation engine of a dual recommendation engine configuration to perform state-based traversal of at least some of a plurality of nodes and to perform adaptive generation and presentation of node content based at least in part on;

receiving user identification information, wherein the user identification information identifies a user;

determining a location of the user in a content network comprising the plurality of nodes linked in a sequential relationship, wherein some of the plurality of nodes are each associated with at least one guard condition, wherein each of the at least one guard condition identifies a condition for entrance into the node associated with that at least one guard condition;

identifying potential next nodes according to the rule-based recommendation engine based on the location of the user in the content network;

determining a next node from the potential next nodes;

determining that the next node is a placeholder node;

consequent to the determining that the next node is the placeholder node, causing the adaptive recommendation engine to generate an output corresponding to next node content based on a predictive model from a model database, wherein the predictive model is trained to select content based on inputs corresponding to at least a user skill level, and the next node content is based at least in part on;

retrieving potential placeholder content associated with the next node; and

identifying the next content from the retrieved potential placeholder content;

transmitting the output corresponding to the next node content to cause presentation of the next node content via user device; and

after the output is transmitted, when a subsequent node is determined to not be a placeholder node, generating additional output based at least in part on the rule-based recommendation engine and subsequent content is directly linked to the subsequent node, and transmitting the additional output corresponding to subsequent node content to cause presentation of the subsequent node content via the user device.

14. The method of claim 13, wherein the location of the user comprises a first node.

15. The method of claim 14, wherein identifying potential next nodes comprises:

identifying nodes directly linked to the first node by an edge;

and identifying a subset of the nodes that are directly linked to the first node by an edge and that are non-prerequisite nodes to the first node.

16. The method of claim 15, further comprising:

retrieving guard conditions for the potential next nodes from a content library database; and

retrieving user history data for the user.

17. The method of claim 16, wherein the next node is determined by application of the retrieved user history data to the retrieved guard conditions.

18. The method of claim 17, wherein the predictive model comprises a mathematically based statistical model.