Big data AI evaluation method and system with dynamic emotion correction added
Through data preprocessing and DECM models, the introduction of emotional correction weight factors is solved, and the AI system ignores emotional fluctuations and insufficient generalization in financial risk assessment is achieved, and humanized and dynamic adaptability is achieved, which is suitable for AI evaluation in multiple scenarios.
Patent Information
- Application Number
- CN202510631277.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-16
- Publication Date
- 2025-08-29
AI Technical Summary
The existing AI system ignores investor sentiment fluctuations in financial risk assessment, which leads to risk assessment deviating from actual market behavior, and lacks generalization when processing multi-dimensional data, and cannot adaptively adjust, resulting in a deviation from humanized needs of conclusions.
Data preprocessing, specific data culling and DECM models are used to introduce emotional correction weight factors to generate anthropomorphic judgment results, and exclusive result evaluation criteria are obtained through the DECM model.
It realizes humanized output and dynamic adaptability, and the results are closer to actual decision-making needs, are suitable for multiple scenarios, and can be integrated into existing AI systems without the need to reconstruct the underlying architecture.
Smart Images
Figure CN120561580A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the intersection of artificial intelligence and automation technology, and in particular to a big data AI evaluation method and system with added dynamic emotion correction. Background Art
[0002] With the rapid development of big data and artificial intelligence technologies, automated analysis systems have been widely used in finance, healthcare, customer service, and other fields. Existing technologies are mostly based on static logic algorithms, which generate single results by inputting structured data. However, such single analysis systems have significant limitations when used in complex societies:
[0003] Over-rationalization:
[0004] Traditional AI (such as linear regression models and decision trees) in financial risk assessment often ignores fluctuations in investor sentiment (such as panic or excessive optimism), leading to risk assessments that deviate from actual market behavior. For example, in 2020, a securities AI system, which failed to incorporate sentiment, had a 32% error rate in predicting a market crash, compared to a 12% error rate for human analysts.
[0005] Lack of generalization: When processing continuously changing or ambiguous data, existing systems are unable to adjust adaptively, and are prone to deviations from manual analysis conclusions when dealing with large data or data that changes over time.
[0006] Data fragmentation in integrated scenarios: In scenarios that require the integration of multi-dimensional data (such as public opinion analysis and psychological assessment), pure logical analysis may lead to conclusions that deviate from the user's human needs.
[0007] Therefore, this field urgently needs a technical solution that can solve the problem that AI systems focus on a single parameter and have excessive evaluation standards when processing big data with regional bias or human cognitive bias.
[0008] The information disclosed in this background technology section is only intended to enhance understanding of the overall background of the invention and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the Invention
[0009] The purpose of the present invention is to provide a big data AI evaluation method and system with added dynamic emotion correction.
[0010] To achieve the above object, the present invention provides the following solutions:
[0011] A big data AI evaluation method with dynamic emotion correction, comprising:
[0012] Step 1: Data preprocessing:
[0013] Input any original data set X={x1,x2,……,x n}, through a quantitative analysis value set of a basic AI analysis algorithm f(x), Q1={q1,q2,……,q n};
[0014] Step 2: Eliminate unique data:
[0015] Remove the abnormal data of discreteness, and the screening condition is qi>3σ; after completion, the data set Q2={q1,q2,……,q m}; Based on data set Q2, get the average evaluation value of data set X
[0016] Step 3: Obtain exclusive result evaluation criteria through the DECM model:
[0017] Introducing sentiment correction weight factor:
[0018] N = original data size, e = 2.718, E ranges from 0 to 1; through this factor, the final evaluation value of the data set is obtained
[0019] Step 4: According to the S of this group of data 基 , and finally generate an anthropomorphic judgment result.
[0020] A big data AI evaluation system with dynamic emotion correction, including:
[0021] Data preprocessing module, used for preprocessing data;
[0022] Specific data elimination module, used to eliminate specific data;
[0023] Exclusive result evaluation standard module, used to obtain exclusive result evaluation standards through DECM model;
[0024] The judgment result generation module is used to generate anthropomorphic judgment results.
[0025] Compared with the prior art, the present invention has the following beneficial effects:
[0026] 1. Humanized output: Through emotional correction, the results are made closer to actual decision-making needs.
[0027] 2. Dynamic adaptability: The weight distribution model can automatically adjust according to data patterns and is applicable to multiple scenarios.
[0028] 3. Compatibility: Can be integrated into existing AI systems without reconstructing the underlying architecture. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0030] Figure 1 A flowchart of a big data AI evaluation method with added dynamic emotion correction provided in an embodiment of the present invention.
[0031] Figure 2 A schematic diagram of weighted analysis data provided by an embodiment of the present invention.
[0032] Figure 3 This is a distribution diagram of the four types of pile foundation results automatically determined by an embodiment of the present invention.
[0033] Figure 4 The distribution diagram of the four types of pile foundation results after DECM correction provided by the embodiment of the present invention. DETAILED DESCRIPTION
[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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.
[0035] The purpose of the present invention is to provide a technical solution that can solve the problem that AI systems focus on a single parameter and have excessive evaluation criteria when processing big data with regional bias or human cognitive bias.
[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0037] Example 1:
[0038] This embodiment provides a big data AI evaluation method with dynamic emotion correction, such as Figure 1 As shown, including:
[0039] Step 1: Data preprocessing:
[0040] Input any original data set X={x1,x2,……,x n}, through a quantitative analysis value set of a basic AI analysis algorithm f(x), Q1={q1,q2,……,q n};
[0041] Step 2: Eliminate unique data:
[0042] Remove the abnormal data of discreteness, and the screening condition is qi>3σ; after completion, the data set Q2={q1,q2,……,q m}; Based on data set Q2, get the average evaluation value of data set X
[0043] Step 3: Obtain exclusive result evaluation criteria through the DECM model:
[0044] Introducing sentiment correction weight factor:
[0045] N = original data size, e = 2.718, E ranges from 0 to 1; through this factor, the final evaluation value of the data set is obtained
[0046] Step 4: According to the S of this group of data 基 , and finally generate an anthropomorphic judgment result.
[0047] The following is an example of applying a big data AI evaluation method with added dynamic emotion correction to pile foundation acoustic testing.
[0048] Acoustic testing (sound wave transmission method) of pile foundations is extremely important and accounts for a large proportion of testing in the building structure foundation testing industry. The classification of pile foundation results is primarily based on the relevant provisions of the "Technical Specification for Building Pile Foundation Testing" (JGJ 106-2014). Pile foundation integrity is determined based on the data obtained from the sound wave transmission method (such as sound velocity, amplitude, main frequency, and other parameters). The classification standards are as follows:
[0049] The pile foundation test results are divided into four categories according to their integrity:
[0050] Class I piles: The pile body is complete and of good quality;
[0051] Class II piles: The pile body has slight defects that do not affect normal use;
[0052] Class III piles: The pile body has obvious defects and requires further verification or treatment;
[0053] Class IV piles: The pile body has serious defects and cannot meet the design requirements.
[0054] The specific data relationships are as follows:
[0055] Sound velocity v: relationship between test value and critical value;
[0056] Amplitude attenuation P: the ratio of attenuation not exceeding the average energy;
[0057] Waveform: whether there is distortion, whether it is a sine wave;
[0058] PSD: abnormal slope fluctuations with and without sound;
[0059] However, these indicators lack clear thresholds or boundaries, requiring the final determination by experienced engineers. We set weights for v, P, W, and PSD, referring to regulatory requirements. We then automatically calculated and determined the acoustic data of 100 foundation piles, finding 43 piles classified as Class I, 28 as Class II, 25 as Class III, and 4 as Class IV.
[0060] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.
[0061] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.
Claims
1. A big data AI evaluation method with dynamic emotion correction, characterized in that: include: Step 1: Data preprocessing: Input any original data set X={x1,x2,……,x n }, through a quantitative analysis value set of a basic AI analysis algorithm f(x), Q1={q1,q2,……,q n }; Step 2: Eliminate unique data: Remove the abnormal data of discreteness, and the screening condition is qi>3σ; after completion, the data set Q2={q1,q2,……,q m }; Based on data set Q2, get the average evaluation value of data set X Step 3: Obtain exclusive result evaluation criteria through the DECM model: Introducing sentiment correction weight factor: N = original data size, e = 2.718, E ranges from 0 to 1; through this factor, the final evaluation value of the data set is obtained Step 4: According to the S of this group of data 基 , and finally generate an anthropomorphic judgment result.
2. A big data AI evaluation system with dynamic emotion correction, characterized in that: include: Data preprocessing module, used for preprocessing data; Specific data elimination module, used to eliminate specific data; Exclusive result evaluation standard module, used to obtain exclusive result evaluation standards through DECM model; The judgment result generation module is used to generate anthropomorphic judgment results.