A real-time processing and analysis method for AI big data

Through real-time processing and analysis methods of AI big data, including data acquisition, feature extraction and identification, association, screening and analysis, the problem of low efficiency in processing and analysis of AI big data is solved, and more efficient data matching and precise control are achieved.

CN118245680BActive Publication Date: 2024-11-01YIWU CHINA COMMODITIES CITY BIG DATA CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410477684.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-19
Publication Date
2024-11-01
Estimated Expiration
2044-04-19

AI Technical Summary

Technical Problem

The prior art cannot accurately control the processing and analysis process of AI big data, resulting in low processing and analysis efficiency.

Method used

Using AI big data real-time processing and analysis methods, including data acquisition, feature extraction, feature association, feature recognition, data screening and data analysis units, adjust the processing process to improve efficiency through key feature extraction, association, identification, screening and feedback analysis. .

Benefits of technology

It improves the accuracy and efficiency of AI big data processing and analysis, ensures the matching of data with user needs, and improves the accuracy of the processing process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118245680B_ABST
    Figure CN118245680B_ABST
Patent Text Reader

Abstract

The present invention relates to a method for real-time processing and analysis of AI big data, and in particular to the technical field of AI big data processing. The method comprises: obtaining user demand data by using a data acquisition unit, and extracting key features of the user demand data by using a feature extraction unit; associating the user demand data after extracting key features with an AI big data database by using a feature association unit to extract associated data of the user demand data from the AI ​​big data database; performing feature identification on the associated data by using a feature recognition unit and outputting the identification result; screening the identification result by using a data screening unit, sending the screened associated data to a user end by using a data analysis unit, and collecting user feedback data for analysis; and adjusting the processing process by using an adjustment unit based on the analysis result of the data analysis unit. The problem that the prior art cannot accurately control the process of processing and analyzing AI big data is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of AI big data processing technology, and in particular to a method for real-time processing and analysis of AI big data. Background Art

[0002] As an important product of the development of modern information technology, AI has brought many conveniences to people's lives. Realizing business evolution through AI big data services is an important part of today's social business process, especially in mining key data from massive text and image data, thus providing important assistance for people to improve efficiency in work and life. In order to achieve the above goals, accurate processing and analysis of AI data has become a top priority.

[0003] Chinese Patent Publication No.: CN115374186A discloses a data processing method and AI system based on big data, which determines the idea of ​​interest focus decision vector corresponding to each conversation behavior knowledge field according to the factor contribution value, reduces the processing overhead and ensures the timeliness of user interest mining; based on this, the resource consumption in dealing with more complex e-commerce business interaction knowledge chains is reduced, and the time consumption in dealing with more complex e-commerce business interaction knowledge chains is also reduced, thereby ensuring the efficiency of user interest mining for more complex e-commerce business interaction knowledge chains; it can be seen that the prior art has the following problems: in the process of processing big data, the key work is to process the data of the conversation process, but in the process of processing AI big data, not only the accuracy of the front-end conversation process should be considered, but the entire processing process of AI big data should be considered, so as to ensure the precise control of the data processing and analysis process, thereby ensuring the processing and analysis efficiency of AI big data. Summary of the invention

[0004] To this end, the present invention provides a real-time processing and analysis method for AI big data, so as to overcome the problem that the prior art cannot accurately control the process of processing and analyzing AI big data, resulting in low efficiency in processing and analyzing AI big data.

[0005] To achieve the above objectives, the present invention provides an AI big data real-time processing and analysis method, comprising:

[0006] Acquire user demand data using a data acquisition unit, and extract key features of the user demand data using a feature extraction unit;

[0007] Associating the user demand data after extracting key features with the AI ​​big database using a feature association unit to extract associated data of the user demand data from the AI ​​big database;

[0008] Using a feature recognition unit to perform feature recognition on the associated data and output the recognition result;

[0009] The identification results are screened by a data screening unit, and the screened associated data is sent to the user end through a data analysis unit, and user feedback data is collected for analysis;

[0010] The processing procedure is adjusted by the adjustment unit based on the analysis result of the data analysis unit.

[0011] Furthermore, the extracting key features of the user demand data by the feature extraction unit includes obtaining user historical demand data, and determining the similarity between the user demand data and the historical user demand data, and when the similarity is less than or equal to a preset similarity, the feature extraction unit determines to extract only the key features in the user demand data as the final key features.

[0012] Furthermore, the key feature extraction of the user demand data by the feature extraction unit includes obtaining user historical demand data and determining the similarity between the user demand data and the historical user demand data. When the similarity is greater than a preset similarity, the feature extraction unit determines to process the user demand data to associate the associated features of the key features in the user demand data, and uses the key features and the associated features as the final key features.

[0013] Further, the performing feature recognition on the associated data by using the feature recognition unit includes determining a recognition granularity of the associated data when an evaluation value of a degree of association between the key feature and the associated data is less than or equal to a preset evaluation value of a degree of association.

[0014] Further, the performing feature recognition on the associated data by using the feature recognition unit includes determining a recognition ratio of the associated data when an evaluation value of a degree of association between the key feature and the associated data is greater than a preset evaluation value of a degree of association.

[0015] Furthermore, when the feature recognition unit completes the recognition of the associated data, the data screening unit determines to screen the associated data based on a comparison result that the accuracy evaluation value of the recognition results of the associated data of several historical user demand data is less than or equal to a preset accuracy evaluation value.

[0016] Furthermore, the data screening unit screens the associated data by calculating a difference between the accuracy evaluation value and a preset accuracy evaluation value, and determining to remove duplicate data in the associated data based on a comparison result that the difference in the evaluation value is less than or equal to a preset difference.

[0017] 8. The AI ​​big data real-time processing and analysis method according to claim 7 is characterized in that the data screening unit screens the associated data, including determining to perform source tracing detection on the associated data based on the comparison result that the evaluation value difference is less than or equal to a preset difference, and determining the similarity between the source data of the associated data and the user demand data, and eliminating the associated data whose similarity is less than the preset similarity.

[0018] Furthermore, the data analysis unit, under the condition that the screening of the associated data is completed, sends the screened associated data to the user end, and collects user feedback data to determine the supplementary features in the feedback data, so that the adjustment unit determines the adjustment of the identification process of the associated data with the adjustment coefficient according to the comparison result that the data volume ratio of the key feature and the supplementary feature is less than or equal to the preset ratio.

[0019] Furthermore, the adjustment unit determines, based on the comparison result that the ratio is greater than a preset ratio, to adjust the extraction process of the user demand data in a manner of increasing the associated features of the key features.

[0020] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention extracts key features of user demand data and uses a feature association unit to associate the key features with the AI ​​big database, so as to extract associated data of user demand data from the AI ​​big database, and performs feature recognition on the associated data during the process of extracting the associated data, and the recognition results are screened by a data screening unit to ensure that the data fed back to the user can match the user's needs, thereby improving the processing efficiency of AI big data.

[0021] In particular, the present invention analyzes user feedback data through a data analysis unit to determine the accuracy of the recognition results after screening by a data screening unit, and adjusts the data processing process according to the analysis results of the user feedback data by the data analysis unit, thereby further improving the accuracy of matching user needs, thereby further improving the processing efficiency of AI big data.

[0022] In particular, the present invention sets different extraction methods so that when extracting user needs, different extraction methods can be executed according to the actual situation of user needs, and the final key features of the user needs are associated with the AI ​​big data database after extraction, and then different identification methods are determined to identify the associated data according to the degree of association between the identified key features of the user needs and the associated data, thereby further improving the accuracy of matching user needs, thereby further improving the processing efficiency of AI big data. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1This is a flow chart of the AI ​​big data real-time processing and analysis method according to an embodiment of the present invention;

[0024] Figure 2 This is a structural block diagram of each unit in the AI ​​big data real-time processing and analysis method according to an embodiment of the present invention;

[0025] Figure 3 This is a logical block diagram of the process of identifying associated data in the AI ​​big data real-time processing and analysis method described in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0027] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0028] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0029] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] See also Figure 1-Figure 3 As shown, Figure 1 This is a flow chart of the AI ​​big data real-time processing and analysis method according to an embodiment of the present invention; Figure 2 This is a structural block diagram of each unit in the AI ​​big data real-time processing and analysis method according to an embodiment of the present invention; Figure 3 This is a logical block diagram of the process of identifying associated data in the AI ​​big data real-time processing and analysis method described in an embodiment of the present invention.

[0031] The AI ​​big data real-time processing and analysis method according to the embodiment of the present invention includes:

[0032] Step S1, using a data acquisition unit to acquire user demand data, and using a feature extraction unit to extract key features of the user demand data;

[0033] Step S2: using a feature association unit to associate the user demand data after extracting key features with an AI big database to extract associated data of the user demand data from the AI ​​big database;

[0034] Step S3, using a feature recognition unit to perform feature recognition on the associated data and output the recognition result;

[0035] Step S4: Filter the recognition results by using the data filtering unit, send the filtered associated data to the user end through the data analysis unit, and collect user feedback data for analysis;

[0036] Step S5: Using an adjustment unit to adjust the processing process based on the analysis result of the data analysis unit.

[0037] Specifically, in step S1, extracting key features of the user demand data by the feature extraction unit includes acquiring user historical demand data, and determining the similarity between the user demand data and the historical user demand data, so as to determine the extraction method of the key features of the user demand data according to the comparison result of the similarity with the first preset similarity;

[0038] When the similarity is less than or equal to a first preset similarity, the feature extraction unit determines to extract key features from the user demand data in a first extraction manner;

[0039] When the similarity is greater than a first preset similarity, the feature extraction unit determines to extract key features from the user demand data in a second extraction manner.

[0040] In the embodiment of the present invention, in the second extraction mode, the feature extraction unit only extracts key features in the user demand data as final key features;

[0041] In the first extraction mode, the feature extraction unit processes the user demand data to associate associated features of key features in the user demand data, and uses the key features and the associated features as final key features.

[0042] In an embodiment of the present invention, the user demand data includes voice and / or text input by the user, the key features include semantic recognition of the voice and / or text input by the user, and obtaining keywords related to the ultimate purpose of the user demand, and the associated features include keywords that explain and describe the user's ultimate purpose.

[0043] In an embodiment of the present invention, the similarity is the ratio of the user demand data to the same data in the user historical demand data, and the value of the first preset similarity is 0.9, but the value is not limited to this. Those skilled in the art may also adjust the value according to actual needs. For example, when the accuracy requirement for data processing is higher, the value may be adjusted to increase the value; when the accuracy requirement for data processing is low, the value may be reduced.

[0044] Specifically, the present invention sets different extraction methods to perform different keyword extractions on user needs when the comparison results between user needs and historical user needs are at different similarities. When the similarity between user needs and historical user needs is less than or equal to a first preset similarity, a simple extraction method is used to extract, thereby reducing the amount of data processing. When the similarity between user needs and historical needs is greater than a first preset similarity, a complex extraction method is used to ensure the accuracy of the extracted data, thereby improving the accuracy of the data extraction process and further improving processing efficiency.

[0045] Specifically, in step S2, extracting the associated data of the user demand data from the AI ​​big database includes determining the feature data of the key data corresponding to the final key feature to use the feature data of the key data as the associated data of the user demand data.

[0046] Specifically, in step S3, the feature recognition of the associated data using the feature recognition unit includes comparing the association degree evaluation value of the key feature and the associated data with a preset association degree evaluation value to determine an identification method for feature recognition of the associated data;

[0047] When the association degree evaluation value is less than or equal to a preset association degree evaluation value, the feature recognition unit determines to perform feature recognition on the association data in a first recognition manner;

[0048] When the association degree evaluation value is greater than a preset association degree evaluation value, the feature recognition unit determines to perform feature recognition on the association data in a second recognition manner.

[0049] Specifically, the feature recognition unit calculates the association degree evaluation value according to the following formula, setting:

[0050]

[0051] Wherein, R is the amount of data in the associated data that has the same feature as the key feature, and G is the amount of data in the associated data that has a different feature from the key feature.

[0052] Specifically, in an embodiment of the present invention, the preset correlation degree evaluation value is 0.5, which is the average value of several correlation degree evaluation values ​​obtained by extracting several related data and then associating the several related data with key features in several user demand data respectively. However, the value is not limited to this, and technical personnel in this field can also adjust the value according to actual needs.

[0053] Specifically, the feature recognition unit performs feature recognition on the associated data in a first recognition manner, including calculating an absolute value of a difference between the association degree evaluation value and a preset association degree evaluation value, so as to determine a granularity for recognition of the associated data according to a comparison result of the absolute value of the difference with a preset absolute value of the difference;

[0054] When the absolute value of the difference is less than or equal to a preset absolute value of the difference, the feature recognition unit determines to recognize the associated data at a first granularity;

[0055] When the absolute value of the difference is greater than a preset absolute value of the difference, the feature recognition unit determines to recognize the associated data at a second granularity.

[0056] In an embodiment of the present invention, the feature recognition unit, at a first granularity, only recognizes a number of features already stored in the associated data without performing an expansion operation, and at a second granularity, recognizes a number of features in the associated data and determines the approximate features of each feature. The approximate features in this embodiment include synonyms and / or different writing methods of words, and the same color and shape of images.

[0057] In the embodiment of the present invention, the value of the preset absolute value of the difference is 0.2, but the value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0058] Specifically, the feature recognition unit performs feature recognition on the associated data in the second recognition mode, including calculating the absolute value of the difference between the association degree evaluation value and the preset association degree evaluation value, so as to determine the recognition ratio of the associated data according to the comparison result of the absolute value of the difference with the preset absolute value of the difference;

[0059] When the absolute value of the difference is less than or equal to a preset absolute value of the difference, the feature recognition unit determines to recognize the associated data at a first recognition ratio;

[0060] When the absolute value of the difference is greater than a preset absolute value of the difference, the feature recognition unit determines to recognize the associated data at a second recognition ratio.

[0061] In the embodiment of the present invention, the value of the first recognition ratio is 0.6, the value of the second recognition ratio is 0.8, and the recognition ratio is the ratio of the recognized data to the associated data.

[0062] Specifically, when the feature recognition unit completes the recognition of the associated data, the data screening unit determines whether to screen the associated data according to a comparison result of the accuracy evaluation value of the recognition result of the associated data of the historical user demand data with a preset accuracy evaluation value;

[0063] When the accuracy evaluation value is less than or equal to a preset accuracy evaluation value, the data screening unit determines to screen the associated data;

[0064] When the accuracy evaluation value is greater than a preset accuracy evaluation value, the data screening unit determines not to screen the associated data.

[0065] Specifically, the accuracy evaluation value is the ratio of the number of supplementary demands among several users to the total number of supplementary demands.

[0066] In the embodiment of the present invention, the preset accuracy evaluation value is taken as the average value of the sum of the reciprocal of the number of times that users supplement demand data and the reciprocal of the number of key features in the supplemented demand data among several users.

[0067] Specifically, when the data screening unit determines to screen the associated data, the difference between the accuracy evaluation value and the preset accuracy evaluation value is calculated, so as to determine the screening method for the associated data according to the comparison result between the evaluation value difference and the preset difference;

[0068] When the evaluation value difference is less than or equal to a preset difference, the data screening unit determines to screen the data in a first screening manner;

[0069] When the evaluation value difference is greater than a preset difference, the data screening unit determines to screen the data in a second screening manner.

[0070] In the embodiment of the present invention, the preset difference value is 0.3, but the value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0071] Specifically, the data screening unit removes duplicate data from the associated data in the first screening mode;

[0072] In the second screening mode, the data screening unit performs source tracing detection on the associated data, determines the similarity between the source data of the associated data and the user demand data, and removes the associated data whose similarity is less than a second preset similarity.

[0073] In the embodiment of the present invention, the value of the second preset similarity is 0.5, but the value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0074] Specifically, the data analysis unit sends the filtered associated data to the user end under the condition that the associated data is filtered, and collects user feedback data to determine the supplementary features in the feedback data, so as to determine whether to adjust the processing process according to the comparison result of the data volume ratio of the key feature and the supplementary feature with the preset ratio;

[0075] When the ratio is less than or equal to a preset ratio, the data analysis unit determines to adjust the processing process in a first adjustment manner;

[0076] When the ratio is greater than a preset ratio, the data analysis unit determines to adjust the processing process in a second adjustment manner.

[0077] In the embodiment of the present invention, the preset ratio is set to 0.2. In this implementation mode, in order to ensure accuracy requirements, the number of supplementary features allowed by the data analysis unit for the processing process cannot exceed 20% of the original key features.

[0078] Specifically, when the data analysis unit determines to adjust the processing process in a first adjustment manner, the adjustment unit calculates a first relative difference between the ratio and a preset ratio, so as to determine an adjustment to the corresponding identification manner according to a comparison result between the first relative difference and the preset relative difference;

[0079] When the first relative difference is less than or equal to a preset relative difference, the adjustment unit determines to adjust the corresponding identification mode with a first adjustment coefficient;

[0080] When the first relative difference is greater than a preset relative difference, the adjustment unit determines to adjust the corresponding identification mode with a second adjustment coefficient.

[0081] In the embodiment of the present invention, the first relative difference = (first ratio - preset ratio) / preset ratio, and the preset relative difference is 0.2, but the value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0082] Specifically, the adjustment unit sets the adjusted recognition ratio of the first recognition mode to Bw, and sets Bw=Bi×Xj, where Bw is the adjusted recognition ratio, i=1 or 2, B1 is the first recognition ratio, and B2 is the second recognition ratio;

[0083] The adjusting unit sets the adjusted recognition granularity of the second recognition mode to Uw, and sets Uw=Ue×Xj, wherein Uw is the adjusted recognition granularity, e=1 or 2, U1 is the first recognition ratio, and U2 is the second recognition ratio;

[0084] In the embodiment of the present invention, j=1 or 2, X1 is the first adjustment coefficient, X2 is the second adjustment coefficient, the value of X1 is 1.2, and the value of X2 is 1.3.

[0085] Specifically, when the adjustment unit determines to adjust the processing process in a second adjustment manner, the adjustment unit adds associated features of the key features in a corresponding extraction manner.

[0086] In the embodiment of the present invention, when adding the associated features of the key features to the corresponding extraction method, the adjustment unit selects at least two keywords of the associated features and adds them to the key features as the final key features.

[0087] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0088] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for real-time processing and analysis of AI big data, characterized in that: include: Acquire user demand data using a data acquisition unit, and extract key features of the user demand data using a feature extraction unit; Associating the user demand data after extracting key features with the AI ​​big database using a feature association unit to extract associated data of the user demand data from the AI ​​big database; Using a feature recognition unit to perform feature recognition on the associated data and output a recognition result; The feature recognition unit is used to perform feature recognition on the associated data, including calculating the absolute value of the difference between the associated degree evaluation value and the preset associated degree evaluation value when the associated degree evaluation value between the key feature and the associated data is less than or equal to the preset associated degree evaluation value, When the absolute value of the difference is less than or equal to a preset absolute value of the difference, the feature recognition unit determines to recognize the associated data at a first granularity; When the absolute value of the difference is greater than a preset absolute value of the difference, the feature recognition unit determines to recognize the associated data at a second granularity; At a first granularity, only a number of features already stored in the associated data are identified without performing an expansion operation, and at a second granularity, a number of features in the associated data are identified and an approximate feature of each feature is determined; The using the feature recognition unit to perform feature recognition on the associated data includes determining a recognition ratio of the associated data when the evaluation value of the degree of association between the key feature and the associated data is greater than a preset evaluation value of the degree of association, When the absolute value of the difference is less than or equal to a preset absolute value of the difference, the feature recognition unit determines to recognize the associated data at a first recognition ratio; When the absolute value of the difference is greater than a preset absolute value of the difference, the feature recognition unit determines to recognize the associated data at a second recognition ratio; The first recognition ratio is 60 percent, and the second recognition ratio is 80 percent; The identification results are screened by a data screening unit, and the screened associated data is sent to the user end through a data analysis unit, and user feedback data is collected for analysis; The processing procedure is adjusted by the adjustment unit based on the analysis result of the data analysis unit.

2. The AI ​​big data real-time processing and analysis method according to claim 1 is characterized in that: The extracting key features of the user demand data by the feature extraction unit includes obtaining user historical demand data, and determining the similarity between the user demand data and the user historical demand data, and when the similarity is less than or equal to a preset similarity, the feature extraction unit determines to extract only the key features in the user demand data as the final key features.

3. The AI ​​big data real-time processing and analysis method according to claim 2 is characterized in that: The key feature extraction of the user demand data by the feature extraction unit includes obtaining user historical demand data and determining the similarity between the user demand data and the user historical demand data. When the similarity is greater than a preset similarity, the feature extraction unit determines to process the user demand data to associate the associated features of the key features in the user demand data, and uses the key features and the associated features as the final key features.

4. The AI ​​big data real-time processing and analysis method according to claim 1 is characterized in that: When the feature recognition unit completes the recognition of the associated data, the data screening unit determines to screen the associated data according to a comparison result that the accuracy evaluation value of the recognition results of the associated data of several historical user demand data is less than or equal to a preset accuracy evaluation value.

5. The AI ​​big data real-time processing and analysis method according to claim 4 is characterized in that: The data screening unit screens the associated data by calculating the difference between the accuracy evaluation value and a preset accuracy evaluation value, and determining to remove duplicate data in the associated data based on a comparison result that the difference between the evaluation values ​​is less than or equal to the preset difference.

6. The AI ​​big data real-time processing and analysis method according to claim 5 is characterized in that: The data screening unit screens the associated data by determining, based on a comparison result that the evaluation value difference is less than or equal to a preset difference, to perform source tracing detection on the associated data, determining the similarity between the source data of the associated data and the user demand data, and eliminating the associated data whose similarity is less than a preset similarity.

7. The AI ​​big data real-time processing and analysis method according to claim 6 is characterized in that: The data analysis unit sends the filtered associated data to the user end under the condition that the screening of the associated data is completed, and collects user feedback data to determine the supplementary features in the feedback data, so that the adjustment unit determines the adjustment of the identification process of the associated data by the adjustment coefficient according to the comparison result that the data amount ratio of the key feature and the supplementary feature is less than or equal to the preset ratio.

8. The AI ​​big data real-time processing and analysis method according to claim 7 is characterized in that: The adjustment unit determines, according to the comparison result that the ratio is greater than a preset ratio, to adjust the extraction process of the user demand data in a manner of increasing the associated features of the key features.

Citation Information

Cited By

  • AI big data real-time processing and analysis method

    CN119493823A

  • An AI Big Data Real-Time Processing and Analysis Method

    CN119493823B