Knowledge information analysis method and system based on ubiquitous computing

Abstract

Embodiments of the present invention provide a knowledge information analysis method and system based on ubiquitous computing. For online behavior extracted knowledge information, based on a single traversal loop, a feature extraction unit in a model unit of a penalty-based feature extraction model generates at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on the behavior extraction features of two of the three ubiquitous computing targets: a first behavior entity, a second behavior entity, and an entity relationship in the online behavior extracted knowledge information. This determines a candidate behavior extraction feature, and ubiquitously computes the online behavior extracted knowledge information based on the obtained target behavior extraction features of each behavior entity or entity relationship in the online behavior knowledge network. This allows for effective ubiquitous computing of online behavior extracted knowledge information, while highlighting entity relationships at different knowledge levels.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a knowledge information analysis method and system based on ubiquitous computing. Background Art

[0002] In the process of ubiquitous computing, how to effectively extract knowledge information from online behaviors for ubiquitous computing and highlight the entity relationships at different knowledge levels is a technical problem that needs to be solved urgently in this field. Summary of the Invention

[0003] In view of this, the purpose of the embodiments of the present invention is to provide a knowledge information analysis method and system based on ubiquitous computing, which can effectively perform ubiquitous computing on knowledge information extracted from online behaviors and highlight the entity relationships at different knowledge levels.

[0004] According to one aspect of an embodiment of the present invention, a method for obtaining a set of online behavior extraction knowledge information is provided, wherein the online behavior extraction knowledge information includes behavior extraction features of a first behavior entity and a second behavior entity that are mutually related in an online behavior knowledge network, and behavior extraction features of an entity relationship between the first behavior entity and the second behavior entity;

[0005] For the online behavior extraction knowledge information, according to a traversal loop, a feature extraction unit in a model unit of a penalty-based feature extraction model generates at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on behavior extraction features of two ubiquitous computing targets among the three ubiquitous computing targets of a first behavior entity, a second behavior entity, and an entity relationship in the online behavior extraction knowledge information;

[0006] Determining a candidate behavior extraction feature from the at least one candidate behavior extraction feature as the corresponding behavior extraction feature of the third ubiquitous computing target in the online behavior knowledge network after this round of traversal cycle;

[0007] The feature extraction unit and the feature decoding unit in the model unit of the penalty-based feature extraction model are updated; accordingly, multiple traversal loops are performed until the traversal loop stop condition is met, the target behavior extraction features of each behavior entity or entity relationship in the online behavior knowledge network are obtained, and the online behavior extraction knowledge information is universally calculated based on the target behavior extraction features.

[0008] Optionally, during one traversal cycle, updating the feature extraction unit and the feature decoding unit in the model unit of the penalty-term-based feature extraction model includes:

[0009] generating at least one universal screening feature based on the behavior extraction features of the two ubiquitous computing targets and at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target, and using the online behavior extraction knowledge information as a universal coding feature;

[0010] performing, according to the feature decoding unit, validity verification on the at least one universal screening feature and the universal coding feature to obtain a validity verification result;

[0011] updating the feature extraction unit according to the validity verification result;

[0012] The feature decoding units are updated according to the validity verification results and the true attributes of the feature decoding units.

[0013] Optionally, the feature extraction unit in the model unit of the penalty-based feature extraction model generates at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on behavior extraction features of two ubiquitous computing targets among the three ubiquitous computing targets of the first behavior entity, the second behavior entity, and the entity relationship in the online behavior extraction knowledge information, including:

[0014] Obtain at least one random behavior extraction feature;

[0015] At least one candidate behavior extraction feature corresponding to the third ubiquitous computing target is obtained by the feature extraction unit based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature.

[0016] Optionally, obtaining, by the feature extraction unit, at least one candidate behavior extraction feature corresponding to the third ubiquitous computing target based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature includes:

[0017] Acquire, by the feature extraction unit, at least one candidate feature corresponding to the third ubiquitous computing target based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature;

[0018] For each candidate feature, the candidate behavior extraction feature is determined based on the online behavior knowledge network.

[0019] Optionally, for each candidate feature, determining the candidate behavior extraction feature based on the online behavior knowledge network includes:

[0020] Determine a behavior extraction feature of a behavior entity or entity relationship that is homogeneous with a third ubiquitous computing target and has a similarity with the candidate feature that meets a preset condition on the online behavior knowledge network;

[0021] The behavior extraction features of the behavior entities or entity relationships that are homogeneous with the third ubiquitous computing target and meet the preset conditions are determined as candidate behavior extraction features.

[0022] According to another aspect of an embodiment of the present invention, a knowledge information analysis system based on ubiquitous computing is provided, which is applied to a server. The system includes:

[0023] an acquisition module, configured to acquire a set of online behavior extraction knowledge information, wherein the online behavior extraction knowledge information includes behavior extraction features of a first behavior entity and a second behavior entity that are mutually associated in an online behavior knowledge network, and behavior extraction features of an entity relationship between the first behavior entity and the second behavior entity;

[0024] a generation module configured to generate, for the online behavior extraction knowledge information, at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on behavior extraction features of two of the three ubiquitous computing targets, namely, a first behavior entity, a second behavior entity, and an entity relationship, in the online behavior extraction knowledge information, based on a traversal loop and using a feature extraction unit in a model unit of a penalty-based feature extraction model;

[0025] a determination module, configured to determine a candidate behavior extraction feature from the at least one candidate behavior extraction feature as the corresponding behavior extraction feature of the third ubiquitous computing target in the online behavior knowledge network after the current traversal cycle;

[0026] An updating module is used to update the feature extraction unit and the feature decoding unit in the model unit of the penalty-based feature extraction model; accordingly, multiple traversal loops are performed until the traversal loop stop condition is met, and the target behavior extraction features of each behavior entity or entity relationship in the online behavior knowledge network are obtained, and the online behavior extraction knowledge information is universally calculated based on the target behavior extraction features.

[0027] Compared to the prior art, the knowledge information analysis method and system based on ubiquitous computing provided by the embodiments of the present invention, for online behavior extraction knowledge information, generates at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on the behavior extraction features of two of the three ubiquitous computing targets, namely, the first behavior entity, the second behavior entity, and the entity relationship, in the online behavior extraction knowledge information, based on a single traversal cycle. This determines a candidate behavior extraction feature as the corresponding behavior extraction feature of the third ubiquitous computing target in the online behavior knowledge network after this traversal cycle, updates the feature extraction unit and feature decoding unit in the model unit of the penalty-based feature extraction model, and then performs ubiquitous computing on the online behavior extraction knowledge information based on the obtained target behavior extraction features of each behavior entity or entity relationship in the online behavior knowledge network. In this way, ubiquitous computing of online behavior extraction knowledge information can be effectively performed, and entity relationships at different knowledge levels can be highlighted.

[0028] In order to make the above-mentioned objects, features and advantages of the embodiments of the present invention more obvious and easy to understand, the embodiments will be described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 A schematic diagram showing components of a server provided by an embodiment of the present invention is shown;

[0031] Figure 2 A schematic diagram showing a flow chart of a knowledge information analysis method based on ubiquitous computing provided by an embodiment of the present invention is shown;

[0032] Figure 3 It shows a functional module block diagram of a knowledge information analysis system based on ubiquitous computing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to help students in this technical field better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0034] The terms "first", "second", "third", etc. (if any) in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the technical project objects used in this way can be interchanged where appropriate, so that the embodiments of the invention described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Figure 1 A schematic diagram of exemplary components of server 100 is shown. Server 100 may include one or more processors 104, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. Server 100 may also include any storage medium 106 for storing any type of information, such as code, settings, data, and the like. For example, and without limitation, storage medium 106 may include any one or more combinations of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, and the like. More generally, any storage medium may use any technology to store information. Furthermore, any storage medium may provide volatile or non-volatile retention of information. Furthermore, any storage medium may represent a fixed or removable component of server 100. In one embodiment, when processor 104 executes associated instructions stored in any storage medium or combination of storage media, server 100 may perform any operation of the associated instructions. Server 100 also includes one or more drive units 108, such as a hard disk drive unit, an optical disk drive unit, and the like, for interacting with any storage medium.

[0036] The server 100 also includes input / output 110 (I / O) for receiving various inputs (via input unit 112) and for providing various outputs (via output unit 114). One specific output mechanism may include a presentation device 116 and an associated graphical user interface (GUI) 118. The server 100 may also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0037] The communication unit 122 can be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 can include any combination of hardwired links, wireless links, routers, gateway functions, name servers 100, etc., governed by any protocol or combination of protocols.

[0038] Figure 2 The flow chart of the knowledge information analysis method based on ubiquitous computing provided by the embodiment of the present invention is shown. The knowledge information analysis method based on ubiquitous computing can be Figure 1 The server 100 shown in FIG is executed, and the detailed steps of the knowledge information analysis method based on ubiquitous computing are introduced as follows.

[0039] Step S110, obtaining a set of online behavior extraction knowledge information, the online behavior extraction knowledge information including the behavior extraction features of the first behavior entity and the second behavior entity that are mutually related in the online behavior knowledge network, and the behavior extraction features of the entity relationship between the first behavior entity and the second behavior entity.

[0040] Step S120, for the online behavior extraction knowledge information, based on a traversal loop, the feature extraction unit in the model unit of the penalty-based feature extraction model generates at least one candidate behavior extraction feature corresponding to the third ubiquitous computing target based on the behavior extraction features of two of the three ubiquitous computing targets, namely, the first behavior entity, the second behavior entity, and the entity relationship in the online behavior extraction knowledge information.

[0041] Step S130 , determining a candidate behavior extraction feature from at least one candidate behavior extraction feature as the corresponding behavior extraction feature of the third ubiquitous computing target in the online behavior knowledge network after this round of traversal loop.

[0042] Step S130 updates the feature extraction unit and feature decoding unit in the model unit of the penalty-based feature extraction model. Repeat this process until the traversal condition is met, obtaining target behavior extraction features for each behavior entity or entity relationship in the online behavior knowledge network. Based on these target behavior extraction features, pervasive computation of online behavior extraction knowledge information is performed.

[0043] Based on the above design, this embodiment extracts online behavior knowledge information. Based on a single traversal cycle, the feature extraction unit in the model unit of the penalty-based feature extraction model generates at least one candidate behavior extraction feature corresponding to the third pervasive computing target based on the behavior extraction features of two of the three pervasive computing targets, namely, the first behavior entity, the second behavior entity, and the entity relationship, in the online behavior extraction knowledge information. This determines a candidate behavior extraction feature as the corresponding behavior extraction feature of the third pervasive computing target in the online behavior knowledge network after this traversal cycle. The feature extraction unit and feature decoding unit in the model unit of the penalty-based feature extraction model are then updated. Then, pervasive computing of the online behavior extraction knowledge information is performed based on the obtained target behavior extraction features of each behavior entity or entity relationship in the online behavior knowledge network. In this way, pervasive computing of online behavior extraction knowledge information can be effectively performed, and entity relationships at different knowledge levels can be highlighted.

[0044] As an example, during a traversal cycle, the specific process of updating the feature extraction unit and the feature decoding unit in the model unit of the penalty-based feature extraction model can be to generate at least one universal screening feature based on the behavior extraction features of two ubiquitous computing targets and at least one candidate behavior extraction feature corresponding to the third ubiquitous computing target, and use the online behavior extraction knowledge information as the universal coding feature, and then verify the validity of the at least one universal screening feature and the universal coding feature based on the feature decoding unit to obtain a validity verification result, update the feature extraction unit based on the validity verification result, and update the feature decoding unit based on the validity verification result and the true attributes of each feature decoding unit.

[0045] As an example, in the process of generating at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on the behavior extraction features of two of the three ubiquitous computing targets, namely, the first behavior entity, the second behavior entity, and the entity relationship in the online behavior extraction knowledge information, by the feature extraction unit in the model unit of the penalty-based feature extraction model, at least one random behavior extraction feature can be obtained, and then at least one candidate behavior extraction feature corresponding to the third ubiquitous computing target can be obtained by the feature extraction unit based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature.

[0046] As an example, in the process of obtaining at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on the behavior extraction features of two ubiquitous computing targets and at least one random behavior extraction feature through a feature extraction unit, at least one candidate feature corresponding to the third ubiquitous computing target can be obtained based on the behavior extraction features of the two ubiquitous computing targets and at least one random behavior extraction feature according to the feature extraction unit, and for each candidate feature, the candidate behavior extraction feature can be determined based on the online behavior knowledge network.

[0047] As an example, for each candidate feature, in the process of determining the candidate behavior extraction features based on the online behavior knowledge network, the behavior extraction features of the behavior entities or entity relationships that are homogeneous with the third ubiquitous computing target and whose similarity with the candidate features meets the preset conditions on the online behavior knowledge network can be determined, and then the behavior extraction features of the behavior entities or entity relationships that are homogeneous with the third ubiquitous computing target that meet the preset conditions are determined as candidate behavior extraction features.

[0048] Figure 3 The functional module diagram of the knowledge information analysis system 200 based on ubiquitous computing provided by an embodiment of the present invention is shown. The functions implemented by the knowledge information analysis system 200 based on ubiquitous computing can correspond to the steps performed by the above method. The knowledge information analysis system 200 based on ubiquitous computing can be understood as the above server 100, or the processor of the server 100, or can be understood as a component independent of the above server 100 or processor that implements the functions of the present invention under the control of the server 100, such as Figure 3 As shown, the functions of each functional module of the knowledge information analysis system 200 based on ubiquitous computing are respectively described in detail below.

[0049] An acquisition module 210 is configured to acquire a set of online behavior extraction knowledge information, the online behavior extraction knowledge information including behavior extraction features of a first behavior entity and a second behavior entity that are mutually associated in an online behavior knowledge network, and behavior extraction features of an entity relationship between the first behavior entity and the second behavior entity;

[0050] A generation module 220 is configured to generate, for the online behavior extraction knowledge information, at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on behavior extraction features of two of the three ubiquitous computing targets, namely, a first behavior entity, a second behavior entity, and an entity relationship, in the online behavior extraction knowledge information, using a feature extraction unit in a model unit of a penalty-based feature extraction model according to a single traversal loop;

[0051] A determination module 230 is configured to determine a candidate behavior extraction feature from at least one candidate behavior extraction feature as the corresponding behavior extraction feature of the third ubiquitous computing target in the online behavior knowledge network after the current traversal cycle.

[0052] The updating module 240 is used to update the feature extraction unit and the feature decoding unit in the model unit of the feature extraction model based on the penalty term; accordingly, multiple traversal loops are performed until the traversal loop stop condition is met, and the target behavior extraction features of each behavior entity or entity relationship in the online behavior knowledge network are obtained, and the online behavior extraction knowledge information is universally calculated based on the target behavior extraction features.

[0053] As an example, during a traversal cycle, updating the feature extraction unit and the feature decoding unit in the model unit of the penalty-based feature extraction model includes:

[0054] generating at least one universal screening feature based on the behavior extraction features of the two ubiquitous computing targets and at least one candidate behavior extraction feature corresponding to the third ubiquitous computing target, and using the online behavior extraction knowledge information as a universal coding feature;

[0055] performing, according to the feature decoding unit, validity verification on at least one universal screening feature and a universal coding feature to obtain a validity verification result;

[0056] Update the feature extraction unit according to the validity verification result;

[0057] The feature decoding units are updated according to the validity verification results and the true attributes of each feature decoding unit.

[0058] As an example, generating at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on behavior extraction features of two ubiquitous computing targets among the three ubiquitous computing targets of the first behavior entity, the second behavior entity, and the entity relationship in the online behavior extraction knowledge information by a feature extraction unit in a model unit of a penalty-based feature extraction model includes:

[0059] Obtain at least one random behavior extraction feature;

[0060] At least one candidate behavior extraction feature corresponding to the third ubiquitous computing target is obtained by a feature extraction unit based on the behavior extraction features of the two ubiquitous computing targets and at least one random behavior extraction feature.

[0061] As an example, obtaining, by a feature extraction unit, at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on the behavior extraction features of the two ubiquitous computing targets and at least one random behavior extraction feature includes:

[0062] Acquire, by a feature extraction unit, at least one candidate feature corresponding to a third ubiquitous computing target based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature;

[0063] For each candidate feature, the candidate behavior extraction feature is determined based on the online behavior knowledge network.

[0064] As an example, for each candidate feature, the candidate behavior extraction feature is determined based on the online behavior knowledge network, including:

[0065] Determine the behavior extraction features of the behavior entities or entity relationships that are homogeneous with the third ubiquitous computing target and have similarities with the candidate features on the online behavior knowledge network that meet preset conditions;

[0066] The behavior extraction features of the behavior entities or entity relationships that are homogeneous with the third ubiquitous computing target and meet the preset conditions are determined as candidate behavior extraction features.

[0067] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0068] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference to any drawing in a claim should not be construed as limiting the claim.

Claims

1. A knowledge information analysis method based on ubiquitous computing, characterized in that: Applied to a server, the method includes: Acquire a set of online behavior extraction knowledge information, the online behavior extraction knowledge information including behavior extraction features of a first behavior entity and a second behavior entity that are mutually related in an online behavior knowledge network, and behavior extraction features of an entity relationship between the first behavior entity and the second behavior entity; For the online behavior extraction knowledge information, according to a traversal loop, a feature extraction unit in a model unit of a penalty-based feature extraction model generates at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on behavior extraction features of two ubiquitous computing targets among the three ubiquitous computing targets of a first behavior entity, a second behavior entity, and an entity relationship in the online behavior extraction knowledge information; Determining a candidate behavior extraction feature from the at least one candidate behavior extraction feature as the corresponding behavior extraction feature of the third ubiquitous computing target in the online behavior knowledge network after this round of traversal cycle; The feature extraction unit and the feature decoding unit in the model unit of the penalty-based feature extraction model are updated; accordingly, multiple traversal loops are performed until the traversal loop stop condition is met, the target behavior extraction features of each behavior entity or entity relationship in the online behavior knowledge network are obtained, and the online behavior extraction knowledge information is universally calculated based on the target behavior extraction features.

2. The method according to claim 1, characterized in that During one traversal cycle, the updating of the feature extraction unit and the feature decoding unit in the model unit of the penalty-based feature extraction model includes: generating at least one universal screening feature based on the behavior extraction features of the two ubiquitous computing targets and at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target, and using the online behavior extraction knowledge information as a universal coding feature; performing, according to the feature decoding unit, validity verification on the at least one universal screening feature and the universal coding feature to obtain a validity verification result; updating the feature extraction unit according to the validity verification result; The feature decoding units are updated according to the validity verification results and the true attributes of the feature decoding units.

3. The method according to claim 1, characterized in that The feature extraction unit in the model unit of the penalty-based feature extraction model generates at least one candidate behavior extraction feature corresponding to the third ubiquitous computing target based on the behavior extraction features of two ubiquitous computing targets among the three ubiquitous computing targets of the first behavior entity, the second behavior entity, and the entity relationship in the online behavior extraction knowledge information, including: Obtain at least one random behavior extraction feature; At least one candidate behavior extraction feature corresponding to a third ubiquitous computing target is obtained by the feature extraction unit based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature.

4. The method according to claim 1, wherein The acquiring, by the feature extraction unit, at least one candidate behavior extraction feature corresponding to the third ubiquitous computing target based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature includes: Acquire, by the feature extraction unit, at least one candidate feature corresponding to the third ubiquitous computing target based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature; For each candidate feature, the candidate behavior extraction feature is determined based on the online behavior knowledge network.

5. The method according to claim 1, wherein For each candidate feature, determining the candidate behavior extraction feature based on the online behavior knowledge network includes: Determine a behavior extraction feature of a behavior entity or entity relationship that is homogeneous with a third ubiquitous computing target and has a similarity with the candidate feature that meets a preset condition on the online behavior knowledge network; The behavior extraction features of the behavior entities or entity relationships that are homogeneous with the third ubiquitous computing target and meet the preset conditions are determined as candidate behavior extraction features.

6. A knowledge information analysis system based on ubiquitous computing, characterized in that: Applied to a server, the system includes: an acquisition module, configured to acquire a set of online behavior extraction knowledge information, wherein the online behavior extraction knowledge information includes behavior extraction features of a first behavior entity and a second behavior entity that are mutually associated in an online behavior knowledge network, and behavior extraction features of an entity relationship between the first behavior entity and the second behavior entity; a generation module configured to generate, for the online behavior extraction knowledge information, at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target based on behavior extraction features of two of the three ubiquitous computing targets, namely, a first behavior entity, a second behavior entity, and an entity relationship, in the online behavior extraction knowledge information, based on a traversal loop and using a feature extraction unit in a model unit of a penalty-based feature extraction model; a determination module, configured to determine a candidate behavior extraction feature from the at least one candidate behavior extraction feature as the corresponding behavior extraction feature of the third ubiquitous computing target in the online behavior knowledge network after the current traversal cycle; An updating module is used to update the feature extraction unit and the feature decoding unit in the model unit of the penalty-based feature extraction model; accordingly, multiple traversal loops are performed until the traversal loop stop condition is met, and the target behavior extraction features of each behavior entity or entity relationship in the online behavior knowledge network are obtained, and the online behavior extraction knowledge information is universally calculated based on the target behavior extraction features.

7. The system according to claim 6, characterized in that During one traversal cycle, the updating of the feature extraction unit and the feature decoding unit in the model unit of the penalty-based feature extraction model includes: generating at least one universal screening feature based on the behavior extraction features of the two ubiquitous computing targets and at least one candidate behavior extraction feature corresponding to a third ubiquitous computing target, and using the online behavior extraction knowledge information as a universal coding feature; performing, according to the feature decoding unit, validity verification on the at least one universal screening feature and the universal coding feature to obtain a validity verification result; updating the feature extraction unit according to the validity verification result; The feature decoding units are updated according to the validity verification results and the true attributes of the feature decoding units.

8. The system according to claim 6, wherein: The feature extraction unit in the model unit of the penalty-based feature extraction model generates at least one candidate behavior extraction feature corresponding to the third ubiquitous computing target based on the behavior extraction features of two ubiquitous computing targets among the three ubiquitous computing targets of the first behavior entity, the second behavior entity, and the entity relationship in the online behavior extraction knowledge information, including: Obtain at least one random behavior extraction feature; At least one candidate behavior extraction feature corresponding to a third ubiquitous computing target is obtained by the feature extraction unit based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature.

9. The system according to claim 8, characterized in that The acquiring, by the feature extraction unit, at least one candidate behavior extraction feature corresponding to the third ubiquitous computing target based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature includes: Acquire, by the feature extraction unit, at least one candidate feature corresponding to the third ubiquitous computing target based on the behavior extraction features of the two ubiquitous computing targets and the at least one random behavior extraction feature; For each candidate feature, the candidate behavior extraction feature is determined based on the online behavior knowledge network.

10. The system according to claim 9, characterized in that For each candidate feature, determining the candidate behavior extraction feature based on the online behavior knowledge network includes: Determine a behavior extraction feature of a behavior entity or entity relationship that is homogeneous with a third ubiquitous computing target and has a similarity with the candidate feature that meets a preset condition on the online behavior knowledge network; The behavior extraction features of the behavior entities or entity relationships that are homogeneous with the third ubiquitous computing target and meet the preset conditions are determined as candidate behavior extraction features.

Images