Artificial intelligence-based collective asset data categorization method and system

Abstract

The artificial intelligence-based collective asset data classification method and system provided in the application compares the business user data sample category corresponding to the target interaction event with the above-mentioned search category, and obtains the matching result of the target interaction event in the search category, classifies the user information data according to the matching result, so as to accurately classify the data. Especially in the case that the target interaction event category is multiple or the quality of the collected business user data is poor, the target verification of a single business user data may appear abnormal analysis or analysis error, the application can analyze more comprehensively, so as to overcome the problem of inaccurate data category analysis, thereby causing data classification error, and when the user queries the data, the corresponding file cannot be accurately and quickly queried.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a method and system for classifying collective asset data based on artificial intelligence. Background Technology

[0002] Artificial intelligence (AI) is a branch of computer science that attempts to understand the essence of intelligence and produce new intelligent machines that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. Since its inception, AI has matured in both theory and technology, and its applications have expanded continuously. It is conceivable that future AI-driven technological products will serve as "containers" of human wisdom. AI can simulate the information processes of human consciousness and thought. While AI is not human intelligence, it can think like a human and may even surpass human intelligence.

[0003] With the continuous development of information technology, a large amount of new data is generated daily at all levels of administrative regions, including villages, townships, districts, counties, provinces, and cities. This necessitates effective processing of this data. The current data processing method involves starting data collection at the village level and then reporting it upwards layer by layer. By the time the data reaches the provincial level, the volume is enormous, making data classification a tedious and cumbersome process. This can easily lead to data classification anomalies or errors, resulting in poor query performance, slow query speeds, and a significantly negative impact on user experience. Therefore, a technical solution is urgently needed to improve these technical problems. Summary of the Invention

[0004] To address the technical problems existing in related technologies, this application provides a method and system for classifying collective asset data based on artificial intelligence.

[0005] Firstly, an artificial intelligence-based method and system for classifying collective asset data is provided. The method includes at least: obtaining a first business user data category corresponding to a target interaction event in first business user data and a business user data sample category corresponding to the target interaction event; matching the first business user data category with a business user data lookup directory corresponding to the target interaction event in second business user data, where the second business user data is business user data following the first business user data; comparing the business user data sample category with the business user data lookup directory to obtain a matching result for the target interaction event in the business user data lookup directory; and classifying user information data based on the matching result.

[0006] In one independently implemented embodiment, the business user data lookup directory includes at least two category distribution subsets. The step of comparing the business user data sample categories with the business user data lookup directory to obtain a matching result corresponding to the target interaction event in the business user data lookup directory, and classifying user information data based on the matching result, includes: performing difference analysis processing on the at least two category distribution subsets according to the business user data sample categories to obtain difference analysis values ​​corresponding to each of the at least two category distribution subsets, where the difference analysis value corresponding to each category distribution subset represents a common factor between the category of business user data corresponding to the category distribution subset and the business user data sample categories; combining the difference analysis values ​​corresponding to each of the at least two category distribution subsets to find a target category distribution subset corresponding to the business user data sample categories in the at least two category distribution subsets; based on finding the target category distribution subset, determining a second business user data category corresponding to the target interaction event in the business user data lookup directory, where the second business user data category is the matching result.

[0007] In one independently implemented embodiment, the step of performing difference analysis processing on the not less than two category distribution subsets based on the business user data sample types to obtain the difference analysis values ​​corresponding to each of the not less than two category distribution subsets includes: performing descriptive knowledge extraction processing on the business user data sample types and the business user data search directory to obtain first business user data descriptive knowledge corresponding to the business user data sample types and second business user data descriptive knowledge corresponding to the business user data search directory; determining the first business user data descriptive knowledge as a key descriptive knowledge set; performing descriptive knowledge extraction processing on the second business user data descriptive knowledge to obtain a descriptive knowledge network, wherein the descriptive knowledge network includes data segments corresponding to each of the not less than two category distribution subsets, and the feature value corresponding to each data segment is the difference analysis value corresponding to the corresponding category distribution subset.

[0008] In one standalone embodiment, the step of matching the target interaction event with the business user data search directory corresponding to the first business user data type in the second business user data includes: determining a matching window in the second business user data corresponding to the first business user data type; and enlarging the matching window to obtain the business user data search directory.

[0009] In one independently implemented embodiment, obtaining the first business user data type corresponding to the target interaction event in the first business user data and the business user data sample type corresponding to the target interaction event includes: performing interaction event verification processing on the first business user data to obtain the first business user data type; extracting the type business user data corresponding to the first business user data type from the first business user data; and determining the type business user data as the business user data sample type.

[0010] In one independently implemented embodiment, the step of performing interaction event verification processing on the first business user data to obtain the first business user data type includes: performing descriptive knowledge extraction processing on the first business user data to obtain business user data descriptive knowledge corresponding to the first business user data; performing candidate window determination processing based on the business user data descriptive knowledge to obtain candidate windows corresponding to the first business user data; and performing target verification processing on the candidate windows to obtain a positioning window corresponding to the target interaction event, wherein the positioning window represents the first business user data type.

[0011] In one standalone embodiment, the matching result is the second business user data category corresponding to the target interaction event in the business user data lookup directory. The method further includes: determining the business user data sequence corresponding to the second business user data; extracting category business user data corresponding to the second business user data category from the second business user data based on the business user data sequence meeting the sample debugging requirements; and debugging the business user data sample category based on the category business user data corresponding to the second business user data category to obtain the debugged business user data sample category.

[0012] In one standalone embodiment, the method further includes: obtaining interaction event information corresponding to the target interaction event and an attention layer corresponding to the second business user data, wherein the attention layer represents the spatial location where the second business user data is collected; and generating three-dimensional spatial distribution data based on the interaction event information and the attention layer.

[0013] Secondly, an artificial intelligence-based user information data classification system is provided, including a processor and a memory that communicate with each other. The processor is used to read a computer program from the memory and execute it to implement the above-mentioned method.

[0014] The AI-based collective asset data classification method and system provided in this application obtains the business user data category corresponding to a target interaction event in the first business user data. It then matches the target interaction event with the search category in the second business user data following the first. By comparing the business user data sample category corresponding to the target interaction event with the aforementioned search category, the matching result for the target interaction event in that search category is obtained. Based on the matching result, user information data is classified, thereby enabling accurate data classification. Especially when there are many target interaction event categories or the quality of collected business user data is poor, target verification for individual business user data may result in analysis anomalies or errors. This application provides a more comprehensive analysis, thus overcoming the problem of inaccurate data category analysis, which can lead to data classification errors and prevent users from accurately and quickly finding the corresponding files when querying data. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating an artificial intelligence-based method and system for classifying collective asset data, provided in an embodiment of this application.

[0017] Figure 2 This is a block diagram of a user information data classification device based on artificial intelligence, provided as an embodiment of this application.

[0018] Figure 3 This is an architecture diagram of an artificial intelligence-based user information data classification system provided in an embodiment of this application. Detailed Implementation

[0019] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0020] Please see Figure 1This paper presents a method and system for classifying collective asset data based on artificial intelligence. The method may include the technical solutions described in steps 210-230.

[0021] Step 210: Obtain the type of first business user data corresponding to the target interaction event in the first business user data and the type of business user data sample corresponding to the target interaction event.

[0022] Furthermore, the aforementioned target interaction events are interaction events verified from the first business user data.

[0023] Furthermore, the first business user data is located in the business user data sequence.

[0024] There can be multiple ways to verify the aforementioned target interaction event, and this application embodiment does not limit this. In one possible embodiment, the aforementioned first service user data can be the first frame of service user data in the service user data sequence from which the target interaction event is verified. Accordingly, the above method includes the following steps (205-207).

[0025] Step 205: Perform interactive event verification processing on the first business user data to obtain the first business user data type.

[0026] The aforementioned first business user data type refers to the type in which the target interaction event is located within the first business user data.

[0027] Furthermore, an artificial intelligence model is used to extract descriptive knowledge from the business user data (such as the third business user data mentioned above) in the business user data sequence, resulting in descriptive knowledge of the business user data. Based on this descriptive knowledge, target interaction events appearing in the business user data are verified, and the boundary corresponding to each target interaction event is given. The above boundary can represent the type of first business user data corresponding to the target interaction event in the first business user data.

[0028] In one possible implementation, step 205 may include the following steps (a to c).

[0029] Step a: Perform descriptive knowledge extraction processing on the first business user data to obtain the business user data descriptive knowledge corresponding to the first business user data.

[0030] Furthermore, the first business user data is subjected to descriptive knowledge extraction processing to obtain the descriptive knowledge extracted from the first business user data; the descriptive knowledge extracted from the first business user data is subjected to dimensionless simplification processing to obtain dimensionless simplified descriptive knowledge; the dimensionless simplified descriptive knowledge is subjected to projection processing to obtain the business user data descriptive knowledge corresponding to the first business user data mentioned above.

[0031] Furthermore, the aforementioned business user data description knowledge is the description knowledge network corresponding to the first business user data.

[0032] In one possible implementation, the aforementioned third-party user data is input into a pre-trained machine learning model. The machine learning model comprises a descriptive knowledge extraction unit, a dimensionless simplification unit, and a triggering unit. The descriptive knowledge extraction unit is responsible for extracting basic descriptive knowledge such as boundary features. The dimensionless simplification unit performs dimensionless simplification on the descriptive knowledge extracted by the descriptive knowledge extraction layer according to a normal distribution, thus cleaning up interfering descriptive knowledge and accelerating model training convergence. The triggering unit projects the descriptive knowledge extracted by the descriptive knowledge extraction layer, enhancing the model's generalization ability.

[0033] Step b involves determining the candidate window based on the knowledge of the business user data description, thereby obtaining the candidate window corresponding to the first business user data.

[0034] Furthermore, the aforementioned business user data description knowledge is a description knowledge network, which includes at least one description knowledge point.

[0035] In one example, for the extracted business user data description knowledge, based on the determination of each description knowledge point, some or all of the preset units can be selected from the preset units mentioned above to determine the candidate window corresponding to the description knowledge point.

[0036] Step c: Perform target validation on the selected window to obtain the positioning window corresponding to the target interaction event.

[0037] Furthermore, the aforementioned positioning window indicates the type of user data for the first business.

[0038] In one possible implementation, the category description knowledge corresponding to the candidate windows is determined; based on the category description knowledge, interaction event verification processing is performed to obtain a first probability that the candidate window corresponds to a preset interaction event category. The first probability represents the probability that the business user data category corresponding to the candidate window belongs to the target interaction event of the preset interaction event category; according to the first probability corresponding to each candidate window, the target interaction event and the positioning window corresponding to the target interaction event are determined.

[0039] Specifically, a candidate window with a probability value greater than a preset probability setting can be identified as a target candidate window; the maximum probability value corresponding to the target candidate window can be determined; and then the interaction event category corresponding to the maximum probability value can be determined as the target interaction event category corresponding to the target candidate window. Thus, it can be determined that the target candidate window is the positioning window corresponding to the target interaction event of the target interaction event category. Alternatively, based on this candidate window, a positioning window corresponding to the target interaction event of the target interaction event category can be further matched.

[0040] In an alternative embodiment, after performing the interaction event verification processing based on the aforementioned category description knowledge, the output is a second probability value corresponding to the candidate window. This probability value represents the probability that the target interaction event exists in the business user data category corresponding to the candidate window, without distinguishing between interaction event categories. Based on the second probability value, the candidate window corresponding to the existence of the target interaction event can be determined, that is, the location of the target interaction event in the business user data has been verified; thus improving the accuracy and reliability of the verification.

[0041] Step 206: Extract the category-specific business user data corresponding to the category of the first business user data from the first business user data.

[0042] Since the target interaction event is detected in the first business user data, when detecting subsequent business user data, it is necessary to determine whether the target interaction event exists in the subsequent business user data to be verified. Thus, the target interaction event detected in the already verified business user data can be identified as the interaction event to be processed corresponding to the subsequent business user data to be verified, and the corresponding type of business user data of the target interaction event in the first business user data can be extracted to assist in the target processing in the subsequent business user data.

[0043] Step 207: Determine the types of business user data as the types of business user data samples.

[0044] After determining the location type of the target interaction event in the first business user data (e.g., locating a window), a type of business user data can be extracted from the first business user data based on this location type to determine the business user data sample type corresponding to the target interaction event, i.e., the processing sample. This aforementioned business user data sample type serves as a reference sample for difference analysis, used for processing and matching the target interaction event in subsequent business user data; that is, it involves searching for the reference sample of the target interaction event in the subsequently determined business user data search directory.

[0045] The aforementioned business user data sample types can be selected from the corresponding types of business user data in each verified business user data for the target interaction event.

[0046] Based on the first frame of business user data of the target interaction event verified in the first business user data sequence, the type of business user data corresponding to the first business user data type is the original business user data sample type corresponding to the target interaction event.

[0047] On another basis, the first business user data is not the first frame of business user data in the business user data sequence that verifies the above-mentioned target interaction event, but the above-mentioned target interaction event is processed in the first business user data. In this case, the type of business user data corresponding to the type of the first business user data is not necessarily determined as the type of business user data sample.

[0048] When obtaining the above-mentioned business user data sample types, the obtained data is the latest business user data sample type.

[0049] In the technical solution provided in this application embodiment, once a new target interaction event is detected in the business user data, a processing sample for difference analysis can be extracted based on the verification and positioning type of the target interaction event, thereby improving the accuracy and real-time performance of the difference analysis.

[0050] Step 220: Match the target interaction event in the second business user data search directory according to the type of the first business user data.

[0051] Furthermore, the aforementioned second business user data is business user data following the first business user data, and the second business user data can be understood as real-time data.

[0052] In one possible implementation, the first business user data is the business user data of the previous frame of the second business user data. In this way, when matching the business user data search directory, the basis used is the type of business user data of the target interaction event in the previous frame of business user data, which has high real-time performance.

[0053] In an exemplary embodiment, step 220 above may include the following steps (221 to 222).

[0054] Step 221: Determine the matching window in the second business user data that corresponds to the type of the first business user data.

[0055] The aforementioned first type of user data can be represented by its corresponding matching window.

[0056] Step 222: Zoom in on the matching window to obtain the business user data search directory.

[0057] Furthermore, the matching window is enlarged according to the pre-set weights to obtain the business user data search directory.

[0058] Furthermore, during the zoom-in process, the matching method corresponding to the target interaction event is obtained, and the matching window is zoomed in according to the above matching method to obtain the above business user data search directory.

[0059] It is understandable that determining the matching window by first identifying the type of business user data, and then determining the business user data search directory by enlarging the matching window, helps to reduce the difficulty of determining the business user data search directory and the difficulty of difference analysis, thereby improving the efficiency of difference analysis processing.

[0060] Step 230: Compare the types of business user data samples with the business user data search directory to obtain the matching results of the target interaction event in the business user data search directory, and classify the user information data according to the matching results.

[0061] In one possible implementation, the business user data lookup directory includes at least two category distribution subsets. The business user data sample categories are compared with the business user data lookup directory to obtain a matching result for the target interaction event in the business user data lookup directory. Based on the matching result, the user information data is categorized, including the following steps: performing difference analysis on at least two category distribution subsets according to the business user data sample categories to obtain difference analysis values ​​for each of the at least two category distribution subsets. Each difference analysis value represents a common factor between the category of business user data and the category of business user data sample categories corresponding to the category distribution subset. Combining the difference analysis values ​​for each of the at least two category distribution subsets, a target category distribution subset corresponding to the business user data sample categories is searched within the at least two category distribution subsets. Based on the found target category distribution subset, a second business user data category corresponding to the target interaction event in the business user data lookup directory is determined, and the second business user data category is the matching result.

[0062] Understandably, performing difference analysis on multiple datasets can reduce the risk of data errors or anomalies.

[0063] Using the aforementioned business user data sample categories as a reference, they can be compared with the business user data content in the business user data search directory. For example, the search directory can be used to find similar categories to the aforementioned business user data sample categories. If a similar category exists in the business user data search directory, the target interaction event is considered to have appeared in that category, thus achieving the matching of the target interaction event in the second business user data. If no similar category exists in the business user data search directory, the target interaction event is considered not to have appeared in the aforementioned business user data search directory. Since the business user data search directory represents the largest reasonable category for the target interaction event to appear in the second business user data, if the target interaction event is not found in the business user data search directory, it can be determined that the target interaction event has been removed from the business user data.

[0064] The aforementioned similarity categories refer to categories within the business user data search directory whose common factor with the business user data sample categories is greater than the set value of the common factor.

[0065] It is understandable that the types of business user data samples obtained above are independent of each other and may be consistent with each other.

[0066] In this embodiment, the above-mentioned business user data search directory includes no less than two category distribution subsets; correspondingly, the above-mentioned step 230 may include the following steps (231-233).

[0067] Step 231: Perform differential analysis on at least two subsets of the business user data sample to obtain differential analysis values ​​for each of the at least two subsets of the data sample.

[0068] If a subset of categories similar to the categories of the business user data sample is found in the business user data search directory, the target interaction event mentioned above can be matched in the business user data search directory, and that category can be the matching result mentioned above.

[0069] Among them, the difference analysis value corresponding to each category distribution subset represents the common factor between the category business user data and the category business user data sample categories corresponding to the category distribution subset.

[0070] Furthermore, the aforementioned difference analysis values ​​are common descriptive knowledge factors between the business user data descriptive knowledge corresponding to the business user data sample types and the business user data descriptive knowledge corresponding to the category distribution subsets.

[0071] In one possible implementation, step 231 above includes the following steps (231a to 231b).

[0072] Step 231a: Perform descriptive knowledge extraction processing on the business user data sample types and business user data search directory to obtain the first business user data descriptive knowledge corresponding to the business user data sample types and the second business user data descriptive knowledge corresponding to the business user data search directory.

[0073] Furthermore, the business user data sample types and the business user data search directory are processed through the same descriptive knowledge extraction neural network layer to extract descriptive knowledge, resulting in a first descriptive knowledge network corresponding to the business user data sample types and a second descriptive knowledge network corresponding to the business user data search directory. The aforementioned first business user data descriptive knowledge can be derived from the aforementioned first descriptive knowledge network, and the aforementioned second business user data descriptive knowledge can be derived from the aforementioned second descriptive knowledge network.

[0074] Step 231b: Determine the first business user data description knowledge as the key description knowledge set, and perform description knowledge extraction processing on the second business user data description knowledge to obtain the description knowledge network.

[0075] The knowledge network described above includes data segments corresponding to at least two category distribution subsets, and the feature value corresponding to each data segment is the difference analysis value corresponding to the corresponding category distribution subset.

[0076] Accordingly, the aforementioned subsets of categories are determined based on the different moving positions of the key descriptive knowledge set during descriptive knowledge extraction. The larger the feature value corresponding to a data segment in the descriptive knowledge network, i.e., the larger the difference analysis value, the higher the commonality factor between the subset of categories corresponding to that data segment and the categories of business user data samples. When it exceeds a set value, it can be considered that the target interaction event has been processed, and the subset of categories is the category to which the target interaction event belongs.

[0077] Step 232: Based on the difference analysis values ​​corresponding to at least two category distribution subsets, find the target category distribution subset corresponding to the category of business user data samples in at least two category distribution subsets.

[0078] Furthermore, the difference analysis values ​​corresponding to at least two category distribution subsets are compared with the pre-set calculated value settings, and category distribution subsets with difference analysis values ​​greater than or equal to the above calculated value settings are selected; the category distribution subsets with difference analysis values ​​greater than or equal to the above calculated value settings are determined as the target category distribution subsets corresponding to the business user data sample categories.

[0079] Step 233: Based on finding the target type distribution subset, determine the second business user data type corresponding to the target interaction event in the business user data search directory according to the target type distribution subset.

[0080] The second type of user data mentioned above is the matching result.

[0081] In an exemplary embodiment, the matching result is the second type of business user data corresponding to the target interaction event in the business user data lookup directory; accordingly, the above method also includes the following steps (1 to 3).

[0082] Step 1: Determine the business user data sequence corresponding to the second business user data.

[0083] Furthermore, the aforementioned business user data sequence can be the sequence number of the second business user data within the business user data sequence.

[0084] Step 2: Based on the fact that the business user data sequence meets the sample debugging requirements, extract the category business user data corresponding to the second business user data category from the second business user data.

[0085] Step 3: Adjust the business user data sample types based on the type of business user data corresponding to the second type of business user data to obtain the adjusted business user data sample types.

[0086] Furthermore, the type of business user data corresponding to the second type of business user data is determined as the type of business user data sample.

[0087] The target processing module based on difference analysis first matches the business user data search directory in the subsequent business user data according to the position of the target interaction event in the previous business user data. Then, it performs difference analysis on the business user data search directory based on the types of business user data samples, thereby verifying the location of the target interaction event in the subsequent business user data and outputting business user data marked with the location of the interaction event.

[0088] In summary, the technical solution provided in this application, by obtaining the business user data type corresponding to the target interaction event in the first business user data, can match the target interaction event to the search type corresponding to the target interaction event in the second business user data following the first business user data. By comparing the business user data sample type corresponding to the target interaction event with the aforementioned search type, the matching result corresponding to the target interaction event in that search type can be obtained. Based on the matching result, user information data is categorized, thereby enabling accurate data classification. Especially when there are many types of target interaction events or the quality of collected business user data is poor, the target verification for a single business user data may result in analysis anomalies or errors. This application can perform a more comprehensive analysis, thus overcoming the problem of inaccurate data type analysis, which can lead to data classification errors and prevent users from accurately and quickly finding the corresponding files when querying data.

[0089] Based on the above, please refer to the following: Figure 2 A user information data classification device 500 based on artificial intelligence is provided, the device comprising:

[0090] The category acquisition module 510 is used to obtain the first business user data category corresponding to the target interaction event in the first business user data and the business user data sample category corresponding to the target interaction event.

[0091] The directory query module 520 is used to match the target interactive event in the second business user data with the first business user data type to find the business user data search directory corresponding to the second business user data, where the second business user data is the business user data following the first business user data.

[0092] The data classification module 530 is used to compare the types of the business user data samples with the business user data search directory, obtain the matching result of the target interaction event in the business user data search directory, and classify the user information data according to the matching result.

[0093] Based on the above, please refer to the following: Figure 3 The present invention illustrates a user information data classification system 300 based on artificial intelligence, including a processor 310 and a memory 320 that communicate with each other. The processor 310 is used to read computer programs from the memory 320 and execute them to implement the above-described method.

[0094] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method during runtime.

[0095] In summary, based on the above scheme, by obtaining the business user data category corresponding to the target interaction event in the first business user data, the search category corresponding to the target interaction event in the second business user data following the first business user data can be matched. By comparing the business user data sample category corresponding to the target interaction event with the above search category, the matching result of the target interaction event in that search category can be obtained. Based on the matching result, user information data is classified, thereby enabling accurate data classification. Especially when there are many types of target interaction events or the quality of collected business user data is poor, the target verification for individual business user data may result in analysis anomalies or errors. This application can perform a more comprehensive analysis, thus overcoming the problem of inaccurate data category analysis, which leads to data classification errors and prevents users from accurately and quickly finding the corresponding files when querying data.

[0096] It should be understood that the systems and modules described above can be implemented in various ways. For example, in some embodiments, the systems and modules can be implemented by hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the methods and systems described above can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The systems and modules of this application can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, or by a combination of the aforementioned hardware circuits and software (e.g., firmware).

[0097] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.

[0098] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0099] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0100] Furthermore, those skilled in the art will understand that aspects of this application can be described and illustrated through several patentable types or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, aspects of this application can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software may be referred to as a “data block,” “module,” “engine,” “unit,” “component,” or “system.” Furthermore, aspects of this application may manifest as a computer product located on one or more computer-readable media, the product including computer-readable program code.

[0101] Computer storage media may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and suitable combinations thereof. Computer storage media can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0102] The computer program code required for the operation of each part of this application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby, and Groovy, or other programming languages. This program code can run entirely on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as Software as a Service (SaaS).

[0103] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this application are not intended to limit the order of the processes and methods of this application. Although the foregoing disclosure has discussed some currently considered useful embodiments of the invention through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the substance and scope of the embodiments of this application. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely through software solutions, such as installing the described system on existing servers or mobile devices.

[0104] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

[0105] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are open to adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters are taken into account a specified number of significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of application in some embodiments of this application are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0106] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this application, the entire contents of that patent are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this application, as well as documents that limit the broadest scope of the claims in this application (currently or subsequently appended to this application). It should be noted that if there are any inconsistencies or conflicts between the descriptions, definitions, and / or terminology used in the supplementary materials of this application and the content of this application, the descriptions, definitions, and / or terminology used in this application shall prevail.

[0107] Finally, it should be understood that the embodiments described in this application are merely illustrative of the principles of the embodiments of this application. Other modifications may also fall within the scope of this application. Therefore, alternative configurations of the embodiments of this application are considered as examples and not limitations, and are regarded as consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly described and illustrated in this application.

[0108] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for classifying collective asset data based on artificial intelligence, characterized in that, The method includes at least: Obtain the type of first business user data corresponding to the target interaction event in the first business user data and the type of business user data sample corresponding to the target interaction event; The target interactive event is matched with the business user data search directory in the second business user data based on the first business user data type. The second business user data is the business user data following the first business user data. The types of business user data samples are compared with the business user data search directory to obtain the matching result of the target interaction event in the business user data search directory. The user information data is then classified according to the matching result. The acquisition of the first business user data type corresponding to the target interaction event in the first business user data and the business user data sample type corresponding to the target interaction event includes: Perform interactive event verification processing on the first business user data to obtain the type of the first business user data; Extract the category of business user data corresponding to the category of the first business user data from the first business user data; The aforementioned types of business user data are identified as the business user data sample types; The step of performing interaction event verification processing on the first service user data to obtain the types of the first service user data includes: The first business user data is subjected to descriptive knowledge extraction processing to obtain the business user data descriptive knowledge corresponding to the first business user data. Based on the business user data description knowledge, a candidate window determination process is performed to obtain the candidate window corresponding to the first business user data. The candidate window is subjected to target verification processing to obtain the positioning window corresponding to the target interaction event, and the positioning window represents the type of the first business user data; The business user data lookup directory includes at least two category distribution subsets. The process involves comparing the categories of the business user data samples with the business user data lookup directory to obtain the matching result of the target interaction event in the business user data lookup directory. Based on the matching result, the user information data is categorized, including: Based on the types of business user data samples, differential analysis is performed on the not less than two type distribution subsets to obtain the differential analysis values ​​corresponding to each of the not less than two type distribution subsets. The differential analysis value corresponding to each type distribution subset represents the common factor between the type of business user data corresponding to the type distribution subset and the type of business user data samples. Based on the difference analysis values ​​corresponding to each of the not less than two category distribution subsets, find the target category distribution subset corresponding to the category of the business user data sample in the not less than two category distribution subsets; Based on finding the target type distribution subset, the second business user data type corresponding to the target interaction event in the business user data search directory is determined by combining the target type distribution subset, and the second business user data type is the matching result; The step of matching the target interaction event with the corresponding business user data search directory in the second business user data based on the first business user data type includes: Determine the matching window in the second service user data that corresponds to the type of the first service user data; The matching window is magnified to obtain the business user data search directory.

2. The method according to claim 1, characterized in that, The step of performing difference analysis on at least two subsets of the business user data samples based on the types of data to obtain the difference analysis values ​​corresponding to each of the at least two subsets of the data samples includes: Descriptive knowledge extraction processing is performed on the business user data sample types and the business user data search directory to obtain the first business user data description knowledge corresponding to the business user data sample types and the second business user data description knowledge corresponding to the business user data search directory. The first business user data description knowledge is determined as the key description knowledge set, and the second business user data description knowledge is subjected to description knowledge extraction processing to obtain a description knowledge network. The description knowledge network includes data segments corresponding to each of the not less than two category distribution subsets, and the feature value corresponding to each data segment is the difference analysis value corresponding to the corresponding category distribution subset.

3. The method according to claim 1, characterized in that, The matching result is the second business user data category corresponding to the target interaction event in the business user data lookup directory, and the method further includes: Determine the business user data sequence corresponding to the second business user data; Based on the fact that the business user data sequence meets the sample debugging requirements, extract the category business user data corresponding to the second business user data category from the second business user data; The business user data sample types are adjusted based on the type of business user data corresponding to the second type of business user data to obtain the adjusted type of business user data sample types.

4. The method according to claim 3, characterized in that, The method further includes: Obtain the interaction event information corresponding to the target interaction event and the attention layer corresponding to the second business user data, wherein the attention layer represents the spatial location for collecting the second business user data; Based on the interaction event information and the attention level, three-dimensional spatial distribution data is generated.

5. A user information data classification system based on artificial intelligence, characterized in that, The method includes a processor and a memory that communicate with each other, the processor being configured to read a computer program from the memory and execute it to implement the method of any one of claims 1-4.

Images