Mapping method and system based on user state and structured situation tag

Abstract

The invention discloses a user state and structured situation tag mapping method and system, and belongs to the technical field of artificial intelligence and data modeling. The method comprises the following steps: providing a structured analysis model and abstracting a potential state of the structured analysis model into a plurality of predefined situation tags; obtaining a user state data sample set containing user behavior data, subjective report data and derivative state indexes; based on a mapping model (realized by adopting a rule engine or a machine learning model), mapping the user state data to the situation tag to establish an association relationship between the user state data and the situation tag; and outputting a mapping relation library for query. According to the method, the multi-source user state data is converted into the structured situation tag with clear business semantics, and a standardized understanding interface is provided for an upper-layer decision-making system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, cognitive computing and data modeling, and particularly relates to a method and system for mapping multi-source user state data to a set of pre-defined structured situation label systems. BACKGROUND

[0002] In the fields of personalized services and group ecological governance, deep understanding of user state is the premise for effective interaction and accurate intervention. However, the existing technology has the following problems: the representation of user state is mainly dependent on simple, isolated labels or single-dimensional indicators, especially it fails to integrate and utilize the dynamic interaction relationship between users and space-time environment (for example, the relative phase value calculated based on space-time relative phase mapping) from upstream perception systems, making it difficult to deeply describe from a holistic and correlated perspective; there is a lack of automatic mapping layer between complex analysis models and unstructured user data collected by real-time systems, relying on expert manual interpretation, which is difficult to meet the real-time and large-scale business needs; the decision support generated based on shallow state understanding lacks pertinence and systematicness.

[0003] As a technical foundation that can realize the whole-link connection from perception to governance, first of all, a unified, machine-understandable structured definition of the user data is needed: Environmental data: refers to external environmental information such as the space-time coordinates of the user.

[0004] User native data: refers to data directly generated or reported by the user, including subjective report data (such as emotion index) and native behavior data (such as interaction sequence, task record).

[0005] User derived data: refers to quantitative indicators obtained by calculating user native data, such as behavior regularity, state intensity value, etc.

[0006] User-generated content: refers to structured or unstructured content created by the user using system tools.

[0007] System interaction data: refers to the record of the user's behavior in the system, such as resource operation, permission use, token transaction, etc.

[0008] Although the above data system provides a rich data basis for deep description of user state, existing technical solutions can usually only process one or a few types of data, and lack a unified semantic framework, resulting in data islands. More importantly, even if these multi-source, heterogeneous low-dimensional data are obtained, there is a lack of an effective mechanism to automatically enhance and normalize them into high-dimensional cognitive expressions with clear and consistent business semantics (i.e., structured situation labels).

[0009] Therefore, there is an urgent need in this field for a technical solution that can automatically, accurately and reliably map the aforementioned multi-source, heterogeneous low-dimensional data into high-dimensional, structured situational labels, in order to establish a standardized bridge from data to cognition and bridge the semantic gap between low-level perception and high-level decision-making. Summary of the Invention

[0010] (a) Purpose of the invention The purpose of this invention is to provide a method and system for mapping user status to structured situational labels, so as to solve the semantic gap between multi-source user status data and high-level business cognition, and provide standardized cognitive input for subsequent decision-making and intervention systems.

[0011] (II) Technical Solution To achieve the above-mentioned objectives, the present invention adopts the following technical solution: A method for mapping user status to structured situation labels includes: providing a structured analysis model and abstracting the potential states of the model into multiple predefined situation labels; obtaining a set of user status data samples; mapping the user status data samples to the situation labels based on a mapping rule to establish an association between user status data and situation labels; and outputting a mapping relationship library, which is used to query the corresponding situation labels based on the input user status data.

[0012] A mapping system between user status and structured situational tags, comprising: a tag definition module, a data acquisition module, a mapping training module, and a relational database output module.

[0013] (III) Beneficial Effects Compared with the prior art, the present invention has the following beneficial effects: It enables in-depth, structured interpretation of user status, transforming shallow, isolated data into situational labels with clear business semantics.

[0014] By establishing an automated mapping mechanism, the process of transforming data into cognition has been scaled up.

[0015] The standardized situation labels output provide a clear and consistent interface for the upper-level decision-making system. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the system module composition provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the method flow provided in an embodiment of the present invention; Figure 3 A flowchart (dual path) is provided for establishing the mapping relationship in the embodiments of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in further detail below with reference to the accompanying drawings and embodiments.

[0018] Example 1: Basic Flow and Implementation of the Method See Figure 2 The mapping method provided in this embodiment includes the following steps: Step S201: Define the situation label set.

[0019] Based on the selected structured analysis model, an abstract and defined set of machine-understandable situation labels is created.

[0020] Step S202: Collect multi-source user status data.

[0021] User status data is collected through various channels such as application programming interfaces (APIs) and sensors. The user status data sample set systematically covers native user data (such as subjective report data and behavioral sequences) and key user-derived data (such as relative phase values ​​calculated through spatiotemporal relative phase mapping), thereby providing a comprehensive and in-depth feature foundation for situation label mapping.

[0022] Step S203: Establish and train the mapping relationship.

[0023] A mapping relationship between user status data and situation labels can be established by using a matching method based on predefined rules or a classification model training method based on machine learning.

[0024] Step S204: Output and deploy the mapping relationship library.

[0025] The obtained mapping model is encapsulated into a mapping relationship library, which provides a standardized application programming interface that receives user state data as input and returns the corresponding situation label and its confidence level.

[0026] Example 2: System Performance Verification To verify the system's ability to transform data into effective cognition, a comparative experiment was designed.

[0027] 1. Experimental setup: Task: Identify whether the user is in a "work-focused state".

[0028] Grouping: The experimental group used the method described in this invention, while the control group used a simple threshold rule.

[0029] 2. Experimental Results: The test set verified that the experimental group had an accuracy rate of 89.2% in recognizing "work focus" and an F1 score of 0.87; the control group had an accuracy rate of 71.5% and an F1 score of 0.68.

[0030] 3. Experimental conclusions: Experiments show that by fusing multi-source data and establishing an automated mapping model, this invention can significantly improve the accuracy and robustness of identifying complex user states.

[0031] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for mapping user status to structured situational tags, characterized in that, include: Step S201: Provide a structured analysis model and abstract the potential states of the model into multiple predefined situation labels; Step S202: Obtain a sample set of user status data; Step S203: Based on a mapping rule, map the user state data sample to the situation label to establish the association between user state and situation label; Step S204: Output a mapping database, which is used to query the corresponding situation tag based on the input user status data.

2. The method according to claim 1, characterized in that, The user status data mentioned in step S202 includes native user data and derived user data; the native user data includes the emotion index actively reported by the user, the user selection behavior captured through the human-computer interaction interface, and / or the user behavior data collected non-intrusively by sensors; the derived user data includes quantitative indicators that characterize the temporal regularity of user behavior calculated from the user behavior sequence.

3. The method according to claim 2, characterized in that, The user-derived data further includes relative phase values ​​calculated through spatiotemporal relative phase mapping, which are used to characterize the dynamic interaction relationship between the user and the spatiotemporal environment.

4. The method according to claim 1, characterized in that, The mapping rules established in step S203 are implemented using a matching method based on predefined rules or a classification model based on machine learning.

5. The method according to claim 1, characterized in that, The mapping database also stores the confidence level of each mapping relationship.

6. The method according to claim 1, characterized in that, The situation labels are used as input to a higher-level state prediction system or decision-making system to generate targeted intervention strategies.

7. A mapping system between user status and structured situational tags, used to implement the method as described in any one of claims 1 to 6, characterized in that, include: The label definition module is used to execute step S201; The data acquisition module is used to execute step S202; The mapping training module is used to execute step S203; The relational database output module is used to execute step S204.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 6.

Images