Cloud architecture intelligent terminal operation backtracking method and system

Abstract

The invention discloses a cloud architecture intelligent terminal operation backtracking method and system. According to the method, multi-dimensional behavior data processing and event cluster division are carried out on collected operation data, a double-engine backtracking architecture of a reverse-order backtracking engine and a synchronous backtracking engine is designed, an existing data collection system is fully and rapidly utilized, and a backtracking method of a user operation behavior track is mined and constructed; the user of the intelligent television terminal can realize the operation backtracking function. And finally, on the basis of the dynamic segmentation of the user behavior track and the key event points, realizing the construction of a scientific and reasonable event reverse-order backtracking function and a synchronous backtracking function.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent terminal control, and more particularly, to a cloud architecture intelligent terminal operation backtracking method and system. BACKGROUND

[0002] With the continuous development and wide popularization of Internet smart display screen technology, more and more users choose to equip their homes with Internet smart televisions with multiple functions, and can enjoy the viewing experience by only operating on the smart television system. However, in actual use, user misoperation or accidental touch is common, especially for the elderly, who are often affected in use due to the problem of being unable to recover from accidental touch.

[0003] The current backtracking function of the smart television mainly relies on a physical back button scheme, that is, the switching backtracking of adjacent content / channels is realized through the physical button on the remote controller, but there are defects such as short backtracking distance (only two-level jump is supported) and inability to record historical tracks for a long time. For example, if a user needs to backtrack to a specific content watched three days ago, the traditional scheme cannot achieve this. The backtracking logic is single, only supporting the reverse backtracking of individual operations, and lacks the dynamic modeling capability of operation behavior, and cannot build a multi-dimensional track table containing time stamp, viewing content and function logic, resulting in difficulty in realizing complex backtracking requirements. SUMMARY

[0004] The present application overcomes the deficiency of single logic in operation record backtracking in the prior art, and provides a cloud architecture intelligent terminal operation backtracking method and system, so as to solve the problems existing in the prior art.

[0005] To solve the above technical problems, one aspect of the present application provides a cloud architecture intelligent terminal operation backtracking method:

[0006] A cloud architecture intelligent terminal operation backtracking method, comprising the following steps:

[0007] S1: Real-time collection of user operation tracks;

[0008] S2: Multi-dimensional behavior data processing and storage of the collected user operation tracks;

[0009] S3: Dynamic segmentation of multi-dimensional operation track data based on target operation behavior tracks and user intentions;

[0010] S4: Designing backtracking engines and strategies according to different scenarios, and providing generation results of different backtracking engines;

[0011] S5: When a customer performs a backtracking operation, providing an interactive page according to the backtracking engine result, and executing the corresponding backtracking result according to the customer's operation.

[0012] Further technical solutions are that the S1 comprises the following steps:

[0013] S11 collects user operation behaviors, splits events and event attributes;

[0014] S12 defines existing events and event attribute descriptions.

[0015] Further technical solutions are that the S2 comprises the following steps:

[0016] S21: the system records multi-dimensional interaction events and sends the records to the cloud;

[0017] S22: the cloud receives and performs protocol conversion and semantic analysis after receiving, and identifies operation records;

[0018] S23: a multi-dimensional attribute track database containing time stamps, event identifiers, and operation types is constructed synchronously.

[0019] Further technical solutions are that the S3 specifically comprises the following steps:

[0020] S31: dynamically segmenting operation tracks;

[0021] S32: constructing a user behavior path model, extracting key operation points based on a dynamic event clustering algorithm, and clustering user operation behaviors with similar characteristics and in the same time domain into interactive event clusters;

[0022] S33: forming a traceable behavior analysis graph.

[0023] Further technical solutions are that the S4 specifically comprises the following steps:

[0024] S41: designing a reverse backtracking engine according to operation timing and key event clusters;

[0025] S42: designing a same-period backtracking engine according to a user behavior analysis model and historical data in the same period;

[0026] S43: constructing an event cluster-based backtracking flow using the reverse backtracking or same-period backtracking engine;

[0027] S44: providing generated results of different backtracking engines.

[0028] Further technical solutions are that the S44 specifically comprises:

[0029] directly giving reverse backtracking and same-period backtracking results, and / or performing cloud collaborative calculation and analysis on the reverse backtracking and same-period backtracking results to form intelligent backtracking recommendation results of double-engine collaboration.

[0030] Further technical solutions are that the S5 specifically comprises:

[0031] When the customer performs the backtracking operation, based on the three key elements of the event cluster, the time axis and the intelligent backtracking recommendation result, an interactive operation backtracking track is quickly constructed, and a user operation backtracking interface is provided.

[0032] Further technical solutions are that the terminal operation backtracking method further comprises the following steps:

[0033] In each step of S1-S5, a check mechanism is added, and abnormal values are removed;

[0034] In S5, the spatiotemporal consistency is detected, and abnormal event interference useless for backtracking is removed.

[0035] Another aspect of the application also provides a cloud architecture intelligent terminal operation backtracking system, comprising a data acquisition module, a cloud analysis and processing module, a dynamic segmentation module, a backtracking execution module and a backtracking interaction module.

[0036] The data acquisition module is used for real-time acquisition of user operation tracks.

[0037] The cloud analysis and processing module is used for multi-dimensional behavior data processing and storage of the acquired user operation tracks.

[0038] The dynamic segmentation module is used for dynamic segmentation of multi-dimensional operation track data.

[0039] The backtracking execution module is used for designing a backtracking engine and a strategy, and providing generation results of different backtracking engines.

[0040] The backtracking interaction module is used for providing an interactive page according to the backtracking engine result.

[0041] Further technical solutions are that the dynamic segmentation module is also used for constructing a user behavior path model, extracting key operation points based on a dynamic event clustering algorithm, clustering user operation behaviors with similar features and in the same time domain into interactive event clusters, and forming a traceable behavior analysis graph.

[0042] Compared with the prior art, the application has at least the following beneficial effects:

[0043] The application performs multi-dimensional behavior data processing on the collected operation data, defines a set of protocols for converting and analyzing user behavior tracks for real-time acquisition of multi-dimensional user behavior interaction events of the intelligent terminal, and adopts a columnar storage structure to facilitate reverse deduction based on the time axis.

[0044] And through event cluster division, a set of key operation point event extraction mechanism based on dynamic time clustering algorithm is designed for the operation trajectory of multi-behavior event, a real-time session cutting-clustering dual-mode analysis framework is adopted to realize dynamic segmentation of user behavior trajectory and definition of key event points.

[0045] Further, the application adopts a dual-engine backtracking architecture of reverse backtracking engine and synchronous backtracking engine, and provides multi-dimensional and high-precision operation trajectory restoration and intelligent recommendation services for intelligent terminal users through cloud collaborative computing and intelligent analysis technology. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 The flowchart of the embodiment one of the application is shown in the figure.

[0047] Figure 2 The event attribute structure diagram of the collected event is shown in the figure.

[0048] Figure 3 The event cluster division diagram is shown in the figure.

[0049] Figure 4 The user backtracking interaction diagram is shown in the figure. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical scheme and advantages of the application clearer, the application is further described in detail below in combination with embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

[0051] Embodiment one

[0052] A cloud architecture intelligent terminal operation backtracking method, referring to Figure 1 , includes the following steps:

[0053] It should be noted that the method is applicable to any intelligent terminal that can be operated, and in this embodiment, the intelligent television terminal is taken as an example.

[0054] S1: Real-time collection of user operation trajectory;

[0055] The existing intelligent terminal data collection collects real-time data according to user event serialization records, which can realize full-link recording of user operation behavior, and can subsequently perform session division. The user operation event behavior records are encapsulated through a standardized protocol and then uploaded to a cloud server.

[0056] In the preferred embodiment, the S1 includes the following steps:

[0057] S11: Collecting user operation behavior and splitting events and event attributes;

[0058] S12 defines the existing event and event attribute description.

[0059] Taking the opening and exiting of an application by a user at a television terminal as an example, the definition of an event and an event attribute example is as follows:

[0060]

[0061] Figure 2 The event attribute structure provided by the embodiment for collecting events can be applied to various types of events, and finally serves as part of a collection device.

[0062] S2: multi-dimensional behavior data processing and storage of the collected user operation trajectory;

[0063] In a preferred embodiment, the S2 includes the following steps:

[0064] S21: the system records multi-dimensional interaction events and sends the records to the cloud;

[0065] S22: protocol conversion and semantic analysis are performed after the cloud receives, and the operation records are identified;

[0066] For example, according to the reported events and their attributes, the events and their attribute descriptions are standardized / normative records according to the agreed protocol.

[0067] S23: a multi-dimensional attribute trajectory database containing a timestamp, an event identifier, and an operation type is synchronously constructed.

[0068] The above steps model the trajectory. Specifically, the events after conversion and analysis are stored in HBASE according to device ID for hierarchical trajectory data storage, supporting queries according to time, application, function, and other dimensions.

[0069] S3: dynamic segmentation of multi-dimensional operation trajectory data based on target operation behavior trajectory and user intent;

[0070] In a preferred embodiment, the S3 specifically includes the following steps:

[0071] S31: dynamic segmentation of the operation trajectory;

[0072] S32: construction of a user behavior path model, extraction of key operation points using a dynamic event clustering algorithm, and clustering of user operation behaviors with similar characteristics and in the same time domain into an interactive event cluster;

[0073] Exemplary, the event cluster division specific steps are, for single user trajectory data based on dynamic time clustering algorithm to extract user key behavior operation event, while using real-time session cutting-cluster dual mode analysis architecture, dynamic segmentation of single user behavior trajectory, extraction to key event point definition; finally, the single user behavior trajectory is divided into a cluster of event clusters, and finally the event clustering grouping is realized. The event cluster division result is shown in Figure 3 .

[0074] S33: Forming a traceable behavior analysis atlas.

[0075] S4: Designing a backtracking engine and strategy according to different scenes, and providing generation results of different backtracking engines;

[0076] For users, the backtracking of operation behavior needs to follow the established logic, and the time reverse backtracking engine and the same period backtracking engine are designed according to product planning, which meets the backtracking needs of users in different scenes.

[0077] In a preferred embodiment, the S4 specifically includes the following steps:

[0078] S41: Designing a reverse backtracking engine according to operation timing and key event cluster;

[0079] S42: Designing a same period backtracking engine according to user behavior analysis model and historical data in the same period;

[0080] S43: Using the reverse backtracking or same period backtracking engine to construct a backtracking flow based on event cluster;

[0081] S44: Providing generation results of different backtracking engines.

[0082] The time reverse backtracking engine is specifically to backtrack the operation behavior trajectory of the user from the current time point after the start of the whole machine. From the technical layer design, that is, traversing the trajectory table in reverse from the current time point, supporting jumping to the position of the last N operations to quickly realize the backtracking of the user in the operation sequence of the current television terminal.

[0083] The same period backtracking engine is specifically to recommend the event cluster with the highest operation frequency on the same day or in the same period according to the user's historical operation behavior, so as to realize the memory of user operation and avoid repeated operation.

[0084] The S44 is specifically to directly give the reverse backtracking and same period backtracking results, and / or to perform cloud collaborative calculation and analysis on the reverse backtracking and same period backtracking results, forming intelligent backtracking recommendation results of double-engine cooperation.

[0085] Using the above double-engine backtracking architecture, multi-dimensional and high-precision operation trajectory restoration and intelligent recommendation service can be realized.

[0086] S5: When the customer performs a backtracking operation, an interactive page is provided according to the backtracking engine result, and a corresponding backtracking result is executed according to the operation of the customer.

[0087] In a preferred embodiment, when the customer performs a backtracking operation, based on the three key elements of event cluster, time axis and intelligent backtracking recommendation result, an interactive operation backtracking track is quickly constructed to provide a user operation backtracking interface.

[0088] For example, in order to facilitate user interaction, different display interaction strategies are adopted in the following scenarios.

[0089] For reverse backtracking scenarios: event clusters are classified and displayed according to whole point time, and the key operation event points containing time and space characteristics of each event cluster are used as key points of the axis. The key points can be quickly positioned to the final user behavior operation step of the event cluster. The events in the event cluster can also be individually focused and quickly backtracked to the position.

[0090] For synchronous backtracking scenarios: independent operation event clusters are recommended according to user historical same-day or same-period operation behavior, and the time axis logic is removed. The interaction logic is the same as that of the "reverse backtracking scenario".

[0091] Figure 4 The backtracking interaction principle schematic diagram is shown.

[0092] In a preferred embodiment, a verification mechanism is added in each step of S1-S5, and abnormal values are removed.

[0093] In S5, the spatio-temporal consistency is detected, and abnormal events that are useless for backtracking are removed.

[0094] Embodiment two

[0095] A cloud architecture intelligent terminal operation backtracking system, comprising a data acquisition module, a cloud analysis and processing module, a dynamic segmentation module, a backtracking execution module and a backtracking interaction module.

[0096] The data acquisition module is used to acquire user operation tracks in real time.

[0097] The cloud analysis and processing module is used to process and store the acquired user operation tracks in multiple dimensions.

[0098] The dynamic segmentation module is used to dynamically segment the multi-dimensional operation track data.

[0099] The dynamic segmentation module is also used to construct a user behavior path model, extract key operation points based on a dynamic event clustering algorithm, cluster user operation behaviors with similar characteristics and in the same time domain into interactive event clusters, and form a traceable behavior analysis graph.

[0100] The backtracking execution module is used for designing a backtracking engine and a strategy, and providing generated results of different backtracking engines;

[0101] The backtracking interaction module is used for providing an interaction page according to the backtracking engine result.

[0102] Although the application has been described with reference to the explanatory embodiments thereof, it is to be understood that many other modifications and implementations will be apparent to those skilled in the art without departing from the principles and spirit of the application disclosed herein. More specifically, many variations and modifications will be possible in the subject combination layout, both to the components of the layout and / or the layout itself. In addition to variations and modifications to the components of the layout and / or the layout itself, other uses will also be apparent to those skilled in the art.

Claims

1. A cloud-based intelligent terminal operation backtracking method, characterized in that: The following steps are involved: S1: Real-time collection of user operation trajectories; S2: Process and store the collected user operation traces into multi-dimensional behavioral data; S3: Dynamically segment multi-dimensional operation trajectory data based on the target operation behavior trajectory and user intention; S4: Design backtracking engines and strategies according to different scenarios, and provide the generation results of different backtracking engines; S5: When the customer performs a backtracking operation, an interactive page is provided according to the backtracking engine result, and the corresponding backtracking result is executed according to the customer's operation.

2. The cloud-based intelligent terminal operation backtracking method according to claim 1, characterized in that: Said S1 comprises the following steps: S11 collects user operation behaviors and splits events and event attributes; S12 unifies the descriptions of various events, defines existing events and describes event attributes.

3. The cloud-based intelligent terminal operation backtracking method according to claim 1, characterized in that: The S2 comprises the following steps: S21: The system records multi-dimensional interaction events and sends the records to the cloud; S22: After receiving the data, the cloud performs protocol conversion and semantic analysis to identify the operation records. S23: Synchronously build a multi-dimensional attribute trajectory database containing timestamps, event identifiers, and operation types.

4. The cloud-based intelligent terminal operation backtracking method according to claim 1, characterized in that: The S3 specifically includes the following steps: S31: Dynamically segment the operation trajectory; S32: Build a user behavior path model, extract key operation points using a dynamic event clustering algorithm, and cluster user operation behaviors with similar characteristics and within the same time domain into interactive event clusters; S33: Form a traceable behavioral analysis map.

5. The cloud-based intelligent terminal operation backtracking method according to claim 1, characterized in that: The S4 specifically includes the following steps: S41: Design a reverse order backtracking engine based on the operation sequence and key event clusters; S42: Design a concurrent backtracking engine based on user behavior analysis models and historical concurrent data; S43: Use the reverse order backtracking or the same period backtracking engine to build a backtracking flow based on event clusters; S44: Providing generation results of different backtracking engines.

6. The cloud-based intelligent terminal operation backtracking method according to claim 5, characterized in that: The S44 is specifically: Directly provide reverse chronological backtracking and concurrent backtracking results, and / or perform cloud-based collaborative calculation and analysis on reverse chronological backtracking and concurrent backtracking results to form dual-engine collaborative intelligent backtracking recommendation results.

7. The cloud-based intelligent terminal operation backtracking method according to claim 5, characterized in that: The S5 is specifically: When a customer performs a backtracking operation, an interactive operation backtracking trajectory is quickly constructed based on the three key elements of event cluster, timeline and the intelligent backtracking recommendation results, providing a user operation backtracking interface.

8. The cloud-based intelligent terminal operation backtracking method according to claim 1, characterized in that: The following steps are also included: In each step S1-S5, a verification mechanism is added and outliers are eliminated; In S5, the spatiotemporal consistency is detected to eliminate the interference of abnormal events that are useless for retrospection.

9. A cloud-based intelligent terminal operation backtracking system, characterized in that: Including, including, Data acquisition module, cloud parsing and processing module, dynamic segmentation module, backtracking execution module and backtracking interaction module; The data acquisition module is used to collect user operation tracks in real time; The cloud parsing and processing module is used to process and store the collected user operation traces into multi-dimensional behavior data; The dynamic segmentation module is used to dynamically segment the multi-dimensional operation trajectory data; The backtracking execution module is used to design backtracking engines and strategies and provide generation results of different backtracking engines; The backtracking interaction module is used to provide an interactive page according to the backtracking engine result.

10. A cloud-based intelligent terminal operation backtracking system as claimed in claim 9, characterized in that: The dynamic segmentation module is also used to construct a user behavior path model, extract key operation points using a dynamic event clustering algorithm, cluster user operation behaviors with similar characteristics and in the same time domain into interactive event clusters, and form a traceable behavior analysis map.

Images