Financial Investment and Financing Management Platform Based on Artificial Intelligence and Big Data

Abstract

The present invention discloses a financial investment and financing management platform based on artificial intelligence big data. The present invention relates to the technical field of financial data management, and solves the problem that the method of using a full database engine search not only overly relies on the computing power resources of the search engine, but also causes slow data output. The present invention improves the input efficiency through the multi-threaded input control terminal that inputs according to the data type using preset threads; by real-time monitoring the input rate and the standard input rate, dynamically allocating computing power resources to ensure thread load balancing, avoiding thread memory contention and packet loss, and ensuring the input effect and data integrity; the index vector construction terminal generates a feature vector circle and a node index vector according to the storage node path, and generates an index table in combination with the classification data header to achieve fast data indexing, converting complex hierarchical paths into intuitive index vectors, and improving the index accuracy and speed.

Description

Technical Field

[0001] The present invention relates to the technical field of financial data management, and specifically to a financial investment and financing management platform based on artificial intelligence big data. Background Art

[0002] In the context of the rapid development of the financial industry and the deep integration of technology, it is crucial to build a financial investment and financing management platform based on artificial intelligence big data. This platform relies on advanced artificial intelligence algorithms and a vast amount of financial data to provide comprehensive, efficient, and intelligent services for financial institutions, investors, and financiers. Its aim is to break down information barriers, improve the efficiency of financial resource allocation, enhance risk management capabilities, and promote the innovative development of the financial market.

[0003] The application with the publication number CN110210962A discloses a one-stop investment and financing information service platform for small and medium-sized enterprises, which adopts the B / S mode and includes a WEB application server, a load balancing server, an investment and financing information service system, a database system, a management terminal, a user terminal, a network firewall, and a communication network. The investment and financing information service system is used to provide one-stop investment and financing information services for small and medium-sized enterprises, including a user-side system and a management-side system. The user-side system is used to provide debt financing, equity financing, financial intermediation, policy declaration, enterprise credit investigation, and other related services for small and medium-sized enterprises, and establish a reliable and fast investment and financing channel between small and medium-sized enterprises and financial and investment institutions. The management-side system is used to provide online user identity management, debt and equity investment and financing management, business review management, intermediary information management, and other related management services for the management party of the investment and financing information service system.

[0004] During the data management process of the financial data associated with its financial investment and financing, generally based on the input time of the corresponding financial data, the corresponding financial data is stored in a specified storage area, and subsequently, based on the headers of the corresponding data, the relevant financial data is indexed. However, this indexing method has a slow indexing rate. Due to the huge volume of the input financial data, using the full database engine search method not only overly relies on the computing power resources of the search engine but also causes slow data output. The indexing method in its original data management process needs to be improved. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides a financial investment and financing management platform based on artificial intelligence big data, which solves the problem that using the full database engine search method not only overly relies on the computing power resources of the search engine but also causes slow data output.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A financial investment and financing management platform based on artificial intelligence big data, including:

[0007] A financial data acquisition terminal collects financial data generated by different data sources within a specified period, where the specified period is a preset period;

[0008] A multi-threaded input control terminal inputs the collected financial data of this batch based on a preset number of threads. According to the inputtable types associated with the corresponding threads, it inputs the financial data of the specified data type, and adjusts the computing power resources associated with a single thread based on the input characteristics generated in real time, so that multiple threads are in a load-balanced state during synchronous input. The specific method is as follows:

[0009] Based on the financial data collected in this batch, classify data of different data types are identified from it, and each group of classified data corresponds to one data type;

[0010] According to a preset number of threads and the inputtable types input by the corresponding threads, where the inputtable types are preset types corresponding to the data types, classify data with the same corresponding thread type are matched and input;

[0011] The input rate associated with each thread is recorded in real time and labeled as V i , where i represents different threads, and the preset standard input rate of each thread is labeled as B i , where the standard input rate is a preset rate, and it is confirmed in real time whether there is: (B i -V i ) > Y1 for a thread. If so, this thread is labeled as a thread to be adjusted, where Y1 is a preset fluctuation value. If not, no labeling is performed;

[0012] Based on the labeled threads to be adjusted and other threads actually running, the computing power resources associated with each thread are confirmed, and the computing power resources associated with other threads are allocated to the threads to be adjusted. Each time the computing power resources associated with the allocation process of other threads is one unit, and the unit is a preset unit, that is, 1 FLOPS. The thread load balance associated with each allocation process is confirmed:

[0013] Based on the input rate V i monitored in real time and the standard input rate B i , the input characteristic ratio associated with the corresponding thread is confirmed: TB i =V i ÷B i , and multiple groups of input characteristic ratios TB iPerform variance processing, confirm the standard variance, and confirm whether the standard variance meets the condition: standard variance ≤ Y2, where Y2 is a preset value. If it meets the condition, end the computing power resource allocation process. If it does not meet the condition, continue the allocation and continuously confirm the threads to be adjusted in real time until the load of multiple threads is balanced and then stop;

[0014] The cloud database stores the financial data entered in the current batch. The storage node paths associated with each different classification data in the financial data are different, and the financial data entered in different batches are stored in different classification intervals;

[0015] The index vector construction end confirms the storage node paths of each different classification data in the current batch, generates a corresponding number of hierarchical circles according to the hierarchical classification of multiple groups of different storage node paths, then confirms the equal division points of the hierarchical circles of the specified level according to the total number of storage node paths, and locks the node index vectors associated with the corresponding classification data for multiple groups of equal division points associated with a single group of classification data. The specific method is as follows:

[0016] Based on the storage node paths of each different classification data, using the first group of hierarchical paths as the initial path, sequentially confirm the subsequent continuously appearing other node paths. Taking the initial path as the center, generate the hierarchical circle associated with the second group of hierarchical paths, and based on the multiple groups of storage node paths included in the second group of hierarchical paths, identify the total number G of different storage node paths from the multiple groups of storage node paths, then confirm the number of equal division points on the hierarchical circle associated with the second group of hierarchical paths, and the number of equal division points is also G, and record the storage node paths associated with each different equal division point;

[0017] Then generate the hierarchical circle associated with the third group of hierarchical paths. The latter group of hierarchical circles is located outside the previous group of hierarchical circles, and the same determination method as the hierarchical circle of the second group of hierarchical paths is used to confirm the equal division points on the circumference of the third group of hierarchical circles;

[0018] And so on, until the confirmation of the hierarchical circles and the internal equal division points associated with the last group of hierarchical paths is completed. Record the multiple groups of generated hierarchical circles as the characteristic vector circles associated with the financial data in this batch;

[0019] According to the storage node paths of the classification data associated with the corresponding classification data, sequentially select the associated equal division points on the corresponding hierarchical circles, and connect the line segments sequentially from the center of the characteristic vector circle outwards to generate the node index vectors belonging to this classification data. The node index vectors of all the classification data in this batch are confirmed within the characteristic vector circle, and match the confirmed classification data headers with the corresponding node index vectors one by one to generate an index table, and transmit the generated index table and the characteristic vector circles associated with the current batch to the storage unit for storage;

[0020] The index output terminal receives the externally input index instruction, confirms the associated node index vector from the storage unit based on the index instruction, then directly determines the storage location of the corresponding classified data in the cloud database based on the associated storage node path, and directly performs index output. The specific method is as follows:

[0021] Based on the received index instruction, confirm the classified data header associated with this index instruction in the storage unit index table, and then confirm the node index vector associated with the classified data header;

[0022] Based on the node index vector and the associated feature vector circle, quickly lock the storage location of this classified data. If a single index instruction corresponds to multiple different classified data headers, confirm the node index vectors associated with each different classified data header, and based on the node index vector and the associated feature vector circle, quickly lock the storage location of the classified data;

[0023] If there is only single classified data, directly perform index output;

[0024] If there are multiple different classified data, confirm the byte amounts associated with the different classified data based on the attributes of the corresponding classified data and label them as Z k where k represents different classified data, and based on the byte amount Z k in the ascending sorting method, sort the multiple different classified data, and sequentially index and output the sorted classified data.

[0025] The present invention provides a financial investment and financing management platform based on artificial intelligence big data. Compared with the prior art, it has the following beneficial effects:

[0026] The present invention uses a multi-threaded input control terminal to input according to the data type using preset threads, improving the input efficiency; by real-time monitoring the input rate and the standard input rate, dynamically allocating computing power resources to ensure thread load balance, avoiding thread memory contention and packet loss, and ensuring the input effect and data integrity;

[0027] The index vector construction terminal generates a feature vector circle and a node index vector according to the storage node path, combines with the classified data header to generate an index table, realizes fast data indexing, converts complex hierarchical paths into intuitive index vectors, and improves the index accuracy and speed;

[0028] The index output terminal receives the index instruction and quickly locates the data storage location according to the index table and the feature vector circle. For multi-data indexing, output sequentially according to the byte amount, which not only ensures the index output efficiency but also ensures the orderly output of the data, avoids chaos, optimizes the user retrieval experience, and improves the data usage value. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a schematic diagram of the principle framework of the present invention;

[0030] Figure 2 This is a schematic diagram for determining the eigenvector circle of the present invention. Specific Embodiments

[0031] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0032] First Embodiment: Please refer to Figure 1 , this application provides a financial investment and financing management platform based on artificial intelligence big data, including a financial data acquisition end, a multi-threaded input and regulation end, a cloud database, an index vector construction end, a storage unit, and an index output end. Among them, the financial data acquisition end, the multi-threaded input and regulation end, and the cloud database are electrically connected in sequence from the output node to the input node, and the cloud database is electrically connected to the input nodes of the index vector construction end and the index output end respectively, and the index vector construction end, the storage unit, and the index output end are electrically connected in sequence from the output node to the input node;

[0033] Among them, the financial data acquisition end collects the financial data generated by different data source parties within a specified period, and enters the financial data collected in this batch through the multi-threaded input and regulation end. The specified period is a preset period, generally taking the value of 24h, that is, collecting once a day. During the simulation training process of artificial intelligence, a large amount of data is required for training. Therefore, the financial data generated by different source parties each time needs to be batch-collected. The different data source parties include, but are not limited to, financial investment and financing data such as stock exchanges, banking systems, and corporate financial reports. Moreover, the volume of financial data collected in each batch is huge, and there are a large number of relevant financial data of different data types. The data formats include, but are not limited to, PDF format, text format, audio format, video files, etc.;

[0034] Among them, the multi-threaded input and regulation end enters the financial data collected in this batch based on a preset number of threads, enters the financial data of the specified data type according to the inputtable type associated with the corresponding thread, and adjusts the computing power resources associated with a single thread based on the input characteristics generated in real time, so that multiple threads are in a load-balanced state during synchronous input. The specific method for real-time adjustment of computing power resources is as follows:

[0035] Based on the financial data collected in this batch, classify the data of different types and confirm the classified data for each type; each group of classified data corresponds to one data type.

[0036] According to a preset number of threads and the input types entered for the corresponding threads, where the input types are preset types corresponding to the data types, match the classified data with the same type as the corresponding thread type (the type is the input type and the data type), and enter this classified data.

[0037] Record the input rate associated with each thread in real time and label it as V i , where i represents different threads, and label the preset standard input rate of each thread as B i , where the standard input rate is a preset rate, determined in advance by relevant operators based on experience, and confirm in real time whether there is: (B i - V i ) > Y1 for a thread. If so, label this thread as a thread to be adjusted, where Y1 is a preset fluctuation value, determined in advance by relevant personnel based on experience. If not, no labeling is performed.

[0038] Based on the labeled threads to be adjusted and other threads actually running, confirm the computing power resources associated with each thread (the computing power resources have been preset in advance and can be understood as computing power values), and allocate the computing power resources associated with other threads to the threads to be adjusted. Each time the computing power resources associated with the allocation process of other threads is one unit, and the unit is a preset unit, that is, 1 FLOPS. Confirm the thread load balance associated with each allocation process:

[0039] Based on the input rate V monitored in real time i and the standard input rate B i , confirm the input characteristic ratio associated with the corresponding thread: TB i = V i ÷B i , and perform variance processing on multiple groups of input characteristic ratios TB i associated with multiple threads, confirm the standard variance, and confirm whether the standard variance meets: standard variance ≤ Y2, where Y2 is a preset value, and its specific value is determined by the operator based on experience. If it meets, end the computing power resource allocation process. If not, continue the allocation and confirm the threads to be adjusted in real time until the load balance of multiple threads is achieved and stop.

[0040] Example: There are multiple groups of threads respectively. In this batch of financial data, there are only four types of classified data. Therefore, the corresponding classified data is entered through the corresponding threads. During the input process, confirm the real-time input rate V associated with each thread in real time i, and then, based on the preset relevant criteria, evaluate whether the corresponding thread is in the normal input state. When it belongs to the normal input state, no calibration is required. When it does not belong to the normal input state, allocate computing power resources. Each time, allocate a unit of computing power resources from other threads. During the actual process of successive computing power resource allocation, confirm whether the rate ratios of each thread are sufficiently balanced. When the computing power resources associated with multiple threads are synchronously in a balanced state, then it can effectively ensure that multiple threads are in the same type of load state, and there will be no situation where threads compete for memory, ensuring the input effect during input and preventing packet loss.

[0041] Among them, the cloud database stores the financial data entered in the current batch. The storage node paths associated with each different classification data in the financial data are different. The financial data entered in different batches is stored in different classification intervals. In order to achieve the corresponding time differentiation effect, the financial data for different time periods is stored separately. The system will store different classification data in the specified storage node paths according to the preset storage program. For example, when downloading data from a specified website or port, the computer will automatically select a group of paths for data storage. Such self-selected paths are the paths associated with this classification data.

[0042] Among them, the index vector construction end confirms the storage node paths of each different classification data in the current batch, generates the corresponding number of hierarchical circles according to the hierarchical classification of multiple different storage node paths, then confirms the equal division points of the specified hierarchical circle according to the total number of storage node paths, and locks the node index vectors associated with the corresponding classification data for the multiple equal division points associated with a single group of classification data, facilitating subsequent fast indexing. The storage node path associated with a set of classification data is set as: 2024.02.19 / users / financial_archive / derivative_data / 202502_derivative_batch_2 / option_data / 20250219_1120. This is just an example here. Among them, 2024.02.19 is the time interval. In order to ensure that the financial data of each different batch is stored in different classification intervals, the initial path of each classification data associated with this batch is 2024.02.19. Here, "2024.02.19" is the name of the corresponding initial storage path.

[0043] Based on the storage node paths of each different classification data, with the first group of hierarchical paths as the initial paths, successively confirm the subsequent continuously appearing other node paths. Taking the initial paths as the center, generate hierarchical circles associated with the second group of hierarchical paths. And based on the multiple groups of storage node paths included in the second group of hierarchical paths, identify the total number G of different storage node paths from the multiple groups of storage node paths. Then, confirm the number of evenly divided points on the hierarchical circles associated with the second group of hierarchical paths, and the number of evenly divided points is also G. Record the storage node paths associated with each different evenly divided point (random allocation can be used here, as long as each evenly divided point is in one-to-one correspondence with the storage node paths associated with the second group of hierarchical paths);

[0044] Then generate the hierarchical circles associated with the third group of hierarchical paths. The latter group of hierarchical circles is located outside the previous group of hierarchical circles (there is no need to limit the radius of the hierarchical circles, as long as the evenly divided points can be determined), and use the same determination method as the hierarchical circles of the second group of hierarchical paths to confirm the evenly divided points on the circumference of the third group of hierarchical circles;

[0045] And so on, until the confirmation of the hierarchical circles and the internal evenly divided points associated with the last group of hierarchical paths is completed. Denote the multiple groups of generated hierarchical circles as the feature vector circles associated with this batch of financial data;

[0046] According to the storage node paths of the classification data associated with the corresponding classification data, successively select the associated evenly divided points on the corresponding hierarchical circles, and connect line segments successively from the center of the feature vector circle outwards to generate the node index vectors belonging to this classification data. Confirm all the node index vectors of the classification data within this batch within the feature vector circle, and match the confirmed classification data headers (that is, data titles) with the corresponding node index vectors one by one to generate an index table. Then, transmit the generated index table and the feature vector circles associated with the current batch to the storage unit for storage;

[0047] Combined with Figure 2: It is determined that there are nine groups of classification data associated currently. The storage node paths associated with each group of classification data are divided into five levels successively. The first level is the same for all, which is the storage range associated with the corresponding batch. There are six groups (Q1, Q2, ……, Q6) of different storage paths in its second level. Therefore, six equal division points are confirmed within the first group of level circles. Then, the confirmation of the third level is carried out. There are three groups of different storage paths in the third level, so three equal division points (QQ1, QQ2, QQ3) are confirmed within the second group of level circles. The confirmation is carried out successively backward. The equal division points of the third group of level circles are 4 groups (QQQ1, ……, QQQ4), and the equal division points of the fourth group of level circles are 9 groups (QQQQ1, QQQQ2, ……, QQQQ9). Since each different equal division point is associated with a different storage node path, and then based on the storage node path associated with a single group of classification data, the node index vector is confirmed within the feature vector circle. The classification data with the storage node path of 2024.02.19 / users / financial_archive / derivative_data / 202502_derivative_batch_2 is in Figure 2 The node vector path confirmed in it is: center - Q1 - QQ2 - QQQ2 - QQQQ2. Therefore, the node index vectors associated with each different classification data are all different.

[0048] Second Embodiment: In the specific implementation process of this embodiment, compared with the above embodiment, in the indexing of this embodiment, there are multiple synchronous output processes of index data, and the index output is carried out by the relevant index output terminals;

[0049] Among them, the index output terminal receives the index instructions input from the outside, and based on the index instructions, confirms the associated node index vector from the storage unit, and then directly determines the storage location of the corresponding classification data from the cloud database based on the associated storage node path, and directly carries out the index output. The specific way of its specific operation is:

[0050] Based on the received index instructions, confirm the classification data header associated with this index instruction in the storage unit index table, and then confirm the node index vector associated with the classification data header;

[0051] Based on the node index vector and the associated feature vector circle, quickly lock the storage location of this classification data. If a single index instruction corresponds to multiple different classification data headers, then confirm the node index vectors associated with each different classification data header, and based on the node index vectors and the associated feature vector circle, quickly lock the storage location of the classification data;

[0052] If there is only single classification data, directly carry out the index output;

[0053] If there are multiple different classification data, the byte amounts associated with the different classification data are confirmed based on the attributes of the corresponding classification data and labeled as Z k , where k represents different classification data, and based on the byte amount Z k , in the ascending order of sorting, the multiple different classification data are sorted, and the sorted classification data are indexed and output in sequence;

[0054] Specifically, this way of indexing and outputting in sequence can effectively guarantee the indexing and output efficiency, and at the same time guarantee the sequentiality of data indexing, without the situation of data chaos, and guarantee the overall effect of the data indexing process.

[0055] Some of the data in the above formula are numerically calculated after removing their dimensions, and the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0056] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A financial investment and financing management platform based on artificial intelligence big data, characterized in that, Including: A financial data acquisition terminal that collects financial data generated by different data sources within a specified period, where the specified period is a preset period; A multi-threaded input control terminal that inputs the collected financial data in this batch based on a preset number of threads, inputs the financial data of the specified data type according to the inputtable types associated with the corresponding threads, and adjusts the computing power resources associated with a single thread based on the input characteristics generated in real time, so that the multiple threads are in a load-balanced state during synchronous input; A cloud database that stores the financial data input in the current batch, where the storage node paths associated with each different classification data in the financial data are different; An index vector construction terminal that confirms the storage node paths of each different classification data in the current batch, generates a corresponding number of hierarchical circles according to the hierarchical classification of multiple groups of different storage node paths, then confirms the evenly divided points of the hierarchical circles at the specified level according to the total number of storage node paths, and then locks the node index vectors associated with the corresponding classification data based on the multiple groups of evenly divided points associated with a single group of classification data. The specific method is as follows: Based on the storage node paths of each different classification data, using the first group of hierarchical paths as the initial path, sequentially confirm the subsequent continuously appearing other node paths, generate a hierarchical circle associated with the second group of hierarchical paths with the initial path as the center, and based on the multiple groups of storage node paths included in the second group of hierarchical paths, identify the total number G of different storage node paths from the multiple groups of storage node paths, then confirm the number of evenly divided points of the hierarchical circle associated with the second group of hierarchical paths, and the number of evenly divided points is also G, and record the storage node paths associated with each different evenly divided point; Then generate a hierarchical circle associated with the third group of hierarchical paths, with the latter group of hierarchical circles located outside the former group of hierarchical circles, and use the same determination method as the hierarchical circle of the second group of hierarchical paths to confirm the evenly divided points on the circumference of the third group of hierarchical circles; And so on, until the hierarchical circles and the internal evenly divided points associated with the last group of hierarchical paths are confirmed. Record the multiple groups of generated hierarchical circles as the feature vector circles associated with the financial data in this batch; According to the storage node paths of the classification data associated with the corresponding classification data, sequentially select the associated evenly divided points on the corresponding hierarchical circles, and connect the line segments sequentially from the center of the feature vector circle outward to generate the node index vector belonging to this classification data; An index output terminal that receives the externally input index instruction, confirms the associated node index vector from the storage unit based on the index instruction, then directly determines the storage location of the corresponding classification data in the cloud database based on the associated storage node path, and directly performs index output.

2. The financial investment and financing management platform based on artificial intelligence big data according to claim 1, characterized in that The specific method for the multi-threaded input control terminal to adjust the computing power resources in real time is as follows: Based on the financial data collected in this batch, confirm the classification data of different data types from it, and each group of classification data corresponds to one data type; According to a plurality of preset threads and the inputtable types input by the corresponding threads, where the inputtable types are preset types corresponding to data types, classify the data that matches the corresponding thread type and input this classified data; Record the input rate associated with each thread in real time and calibrate it as V i , where i represents different threads, and calibrate the preset standard input rate of each thread as B i , where the standard input rate is a preset rate, and confirm in real time whether there is: (B i -V i ) > Y1 for a thread. If so, calibrate this thread as a thread to be adjusted, where Y1 is a preset fluctuation value; Based on the calibrated thread to be adjusted and other actually running threads, confirm the computing power resources associated with each thread, and allocate the computing power resources associated with other threads to the thread to be adjusted. Each time the computing power resources associated with the allocation process of other threads is one unit, and the unit is a preset unit, that is, 1 FLOPS. Confirm the thread load balancing associated with each allocation process: Input rate V based on real-time monitoring i and standard input rate B i , confirm the input feature ratio associated with the corresponding thread: TB i =V i ÷B i , and perform variance processing on multiple groups of input feature ratios TB associated with multiple threads i , confirm the standard variance, and confirm whether the standard variance meets: standard variance ≤ Y2, where Y2 is a preset value. If it meets, end the computing power resource allocation process. If it does not meet, continue to allocate and confirm the threads to be adjusted in real time until the multiple threads are load-balanced and then stop.

3. The financial investment and financing management platform based on artificial intelligence big data according to claim 2, wherein If there is no thread where (B i -V i ) > Y1, no calibration is performed.

4. The financial investment and financing management platform based on artificial intelligence big data according to claim 1, characterized in that, In the cloud database, the financial data input in different batches is stored in different classification intervals.

5. The financial investment and financing management platform based on artificial intelligence big data according to claim 1, characterized in that, The node index vectors of all the classified data in this batch are confirmed within the feature vector circle, and the confirmed classified data headers are matched one by one with the corresponding node index vectors to generate an index table, and the generated index table and the feature vector circle associated with the current batch are transmitted to the storage unit for storage.

6. The financial investment and financing management platform based on artificial intelligence big data according to claim 5, characterized in that, The specific method of index output at the index output end is as follows: Based on the received index instruction, confirm the classified data header associated with this index instruction in the storage unit index table, and then confirm the node index vector associated with the classified data header; Based on the node index vector and the associated feature vector circle, quickly lock the storage location of this classified data. If a single index instruction corresponds to multiple different classified data headers, confirm the node index vectors associated with each different classified data header, and based on the node index vectors and the associated feature vector circles, quickly lock the storage locations of the classified data; If there is only single classified data, directly perform index output.

7. The financial investment and financing management platform based on artificial intelligence big data according to claim 6, characterized in that, If there are multiple different classification data, confirm the byte amounts associated with the different classification data based on the attributes of the corresponding classification data and label them as Z k , where k represents different classification data, and according to the byte amount Z k , sort the multiple different classification data in ascending order, index the sorted classification data in sequence, and output them

Images