A database segmentation management method and system based on artificial intelligence

Abstract

The present invention provides a database segmentation management method and system based on artificial intelligence. The method includes: obtaining the user's operation history data for each application, analyzing the user's operation habit data based on the operation history data, and determining multiple data groups corresponding to each application based on the operation habit data and the AI ​​analysis model; dividing at least a part of the database into specific areas, segmenting the specific areas to obtain multiple sub-databases, and storing each data group in a corresponding sub-database; wherein the sub-database corresponds to the application one-to-one. The present invention can improve the data interaction efficiency between the application and the database.

Description

Technical Field

[0001] The present invention relates to the technical field of database management, and in particular to an artificial intelligence-based database segmentation management method and system. Background Art

[0002] A database refers to a collection of data that is stored together in a certain way, can be shared by multiple users, has as little redundancy as possible, and is independent of applications. It is holistic and shared. In a computer terminal device, multiple applications will call and use the data in the database at the same time, so that multiple threads will execute SQL queries at the same time, and the database's response capacity to simultaneous calls has an upper limit. Even if the number of calling threads is within the capacity of the database management system, it is easy to reduce the response efficiency, and then reduce the rate at which the application calls the database data, which is not conducive to the user's smooth use of the application. The present invention aims to solve this technical problem. Summary of the invention

[0003] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a database segmentation management method and system based on artificial intelligence.

[0004] A first aspect of the present invention provides a database segmentation management method based on artificial intelligence, comprising the following steps:

[0005] Acquire the user's operation history data for each application, analyze the user's operation habit data based on the operation history data, and determine multiple data groups corresponding to each application based on the operation habit data and the AI ​​analysis model;

[0006] At least a part of the database is divided into a specific area, a plurality of sub-databases are obtained by segmentation in the specific area, and each of the data groups is stored in a corresponding sub-database; wherein the sub-databases correspond to the application programs one by one.

[0007] In some embodiments, obtaining the user's operation history data for each application includes:

[0008] Acquire first operation history data of the user on each application within a first period, and extract high-intensity operation data corresponding to each application from the first operation history data;

[0009] Performing correlation analysis and calculation on all the high-intensity operation data to obtain a first expansion coefficient;

[0010] The first period is expanded and adjusted to a second period according to the first expansion coefficient, and second operation history data of the user for each application in the second period is obtained, where the second operation history data is the operation history data.

[0011] In some embodiments, performing correlation analysis and calculation on all the high-intensity operation data to obtain a first expansion coefficient includes:

[0012] Sorting the high-intensity operation data corresponding to each application program in chronological order and fitting the high-intensity operation data into a first operation intensity curve;

[0013] Mapping all the first operation intensity curves according to the same time axis, performing fitting processing on all the mapped operation intensity curves to obtain a first equivalent operation intensity curve;

[0014] The number of peaks in the first equivalent operation intensity curve that are higher than an intensity threshold is counted, and the first expansion coefficient is determined according to the number.

[0015] In some embodiments, the obtaining the user's operation habit data according to the operation history data analysis includes:

[0016] Determine a second operation intensity curve corresponding to each application according to the second operation history data, and map all the second operation intensity curves according to the same time axis;

[0017] Constructing a plurality of first closed graphs with the time axis as the base for each of the second operation intensity curves, and performing intersection calculation on all of the first closed graphs to obtain a second closed graph;

[0018] Dividing the second closed figure into a plurality of sub-closed figures according to the trough nodes of the upper boundary curve of the second closed figure, calculating the integral value of the upper boundary curve of each of the sub-closed figures, and obtaining a second equivalent operation intensity curve by fitting according to the integral value;

[0019] Synchronously compare each of the second operation intensity curves with the second equivalent operation intensity curve to determine the application corresponding to each of the integral values, and thereby determine the operation association intensity data set corresponding to each application, that is, analyze and obtain the user's operation habit data; wherein the operation association intensity data set includes a plurality of operation association intensity data representing the application and any other application, and the operation association intensity data is determined based on the integral value.

[0020] In some embodiments, the determining of multiple data groups corresponding to each application program based on the operation habit data and the AI ​​analysis model includes:

[0021] Acquire first attribute data of the main application, and obtain a first data group according to the first attribute data;

[0022] Based on the synchronous comparison result of the second operation intensity curves of the main application and each associated application, determine and obtain each second data group corresponding to each associated application;

[0023] Determine each of the operation association strength data corresponding to the main application in the operation association strength data set, and filter and process each of the second data groups according to the operation association strength data corresponding to the associated application and the AI ​​analysis model to obtain each third data group;

[0024] fusing the first data group and each of the third data groups to obtain the data group;

[0025] The above process is repeated to obtain the data group corresponding to each main application.

[0026] In some embodiments, the second data group is screened and processed according to the operation association strength data corresponding to the associated application and the AI ​​analysis model to obtain the third data group, including:

[0027] Inputting the second data group into the AI ​​analysis model to obtain a fourth data group;

[0028] Determine a second expansion coefficient according to the operation association strength data corresponding to the associated application;

[0029] The fourth data group is expanded and adjusted according to the second expansion coefficient to obtain the third data group.

[0030] In some embodiments, the step of performing expansion adjustment on the fourth data set according to the second expansion coefficient to obtain the third data set includes:

[0031] Obtaining version change data of the main application, determining a version change frequency according to the version change data, and determining a third expansion coefficient according to the version change frequency;

[0032] The fourth data group is expanded and adjusted according to the second expansion coefficient and the third expansion coefficient to obtain the third data group.

[0033] The second aspect of the present invention provides a database segmentation management system based on artificial intelligence, comprising an acquisition module, a processing module, and a storage module, wherein the processing module is connected to the storage module and the acquisition module; wherein:

[0034] The acquisition module is at least used to acquire the user's operation history data for each application program and transmit it to the processing module;

[0035] The storage module is used to store executable computer program code;

[0036] The processing module is used to execute the method as described in any of the preceding items by calling the executable computer program code in the storage module to achieve segmentation of a specific area of ​​the database.

[0037] The present invention collects the user's operation history data for each application, analyzes their operation habits based on this, and then uses an AI analysis model to determine the data group corresponding to the operation habit, which is the data that the user can use when using the application; then, separate storage areas are divided in the database to store the above-mentioned data groups separately. Therefore, in the scheme of the present invention, when a user uses a specific application, the application can specify to the database management system to retrieve the data in the corresponding sub-database, and each application only needs to perform operations such as retrieval and storage of data in its own sub-database. At this time, the database management system does not need to index and retrieve data in the entire database according to the data retrieval instruction, which can effectively improve the management efficiency of the database management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0039] Figure 1 It is a flowchart of a database segmentation management method based on artificial intelligence disclosed in an embodiment of the present invention;

[0040] Figure 2 It is a structural diagram of an artificial intelligence-based database segmentation management system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0042] See also Figure 1 The embodiment of the present invention discloses a database segmentation management method based on artificial intelligence, comprising the following steps:

[0043] Acquire the user's operation history data for each application, analyze the user's operation habit data based on the operation history data, and determine multiple data groups corresponding to each application based on the operation habit data and the AI ​​analysis model;

[0044] At least a part of the database is divided into a specific area, a plurality of sub-databases are obtained by segmentation in the specific area, and each of the data groups is stored in a corresponding sub-database; wherein the sub-databases correspond to the application programs one by one.

[0045] The present invention collects the user's operation history data for each application, analyzes their operation habits based on this, and then uses an AI analysis model to determine the data group corresponding to the operation habit, which is the data that the user can use when using the application; then, separate storage areas are divided in the database to store the above-mentioned data groups separately. Therefore, in the scheme of the present invention, when a user uses a specific application, the application can specify to the database management system to retrieve the data in the corresponding sub-database, and each application only needs to perform operations such as retrieval and storage of data in its own sub-database. At this time, the database management system does not need to index and retrieve data in the entire database according to the data retrieval instruction, which can effectively improve the management efficiency of the database management system.

[0046] In addition, the database management system can also configure a corresponding management module for each sub-database, so that when the database management system receives the data retrieval instruction sent by the application, it can directly forward the data retrieval instruction to the corresponding management module based on the corresponding relationship between the application and the sub-database, and the management module is responsible for indexing and retrieving data in the corresponding sub-database, thereby further improving the database management efficiency. Of course, when the management module does not find the data that the application needs to call in the sub-database, it can feed back the data retrieval instruction to the database management system, so that it can perform data interaction in the conventional database area outside the specific area in a conventional manner.

[0047] It should be noted that the database in the present invention can be a database configured in various terminal devices, or a database located at the network end. Also, the above-mentioned application programs involved in the present invention can be designated applications, such as those applications that are statistically found to cause a significant slowdown in the database interactive response speed, and other applications can be interactively responded by the database management system in a conventional manner.

[0048] In some embodiments, obtaining the user's operation history data for each application includes:

[0049] Acquire first operation history data of the user on each application within a first period, and extract high-intensity operation data corresponding to each application from the first operation history data;

[0050] Performing correlation analysis and calculation on all the high-intensity operation data to obtain a first expansion coefficient;

[0051] The first period is expanded and adjusted to a second period according to the first expansion coefficient, and second operation history data of the user for each application in the second period is obtained, where the second operation history data is the operation history data.

[0052] In this embodiment, the first period is set to a fixed value, such as one week or one month, and the user's operation history data for each application within the first period is obtained to identify the high-intensity operation data therein. Each application has a corresponding set of high-intensity operation data. Then, a correlation analysis is performed on the high-intensity operation data corresponding to each application. According to the result of the correlation analysis, a suitable first expansion coefficient can be determined. The first period can be appropriately expanded to a second period using the first expansion coefficient, so that the user's operation habit data can be obtained and analyzed based on the operation history data within the second period. Since the time span of the second period is longer, such as a quarter, half a year, or a year, the basic data volume of the obtained operation history data is larger, and the credibility of the obtained operation habit data is higher.

[0053] Among them, high-intensity operation data refers to the intensity of data interaction between the application and the database, such as the amount of data interaction per unit time, the frequency of interaction, etc., and can also include the number of interaction data types. Obviously, the higher the amount of data interaction per unit time, the more frequent the interaction, and the more interactive data types, the greater the intensity of data interaction between the application and the database. When the interaction intensity reaches a certain threshold, the operation history data in the period can be determined as high-intensity operation data. The above intensity can be a weighted integrated value of the normalized values ​​of the above-mentioned factor parameters.

[0054] In some embodiments, performing correlation analysis and calculation on all the high-intensity operation data to obtain a first expansion coefficient includes:

[0055] Sorting the high-intensity operation data corresponding to each application program in chronological order and fitting the high-intensity operation data into a first operation intensity curve;

[0056] Mapping all the first operation intensity curves according to the same time axis, performing fitting processing on all the mapped operation intensity curves to obtain a first equivalent operation intensity curve;

[0057] The number of peaks in the first equivalent operation intensity curve that are higher than an intensity threshold is counted, and the first expansion coefficient is determined according to the number.

[0058] In this embodiment, the high-intensity operation data extracted from each application is sorted and fitted in chronological order to obtain the corresponding operation intensity curve; then, the operation intensity curves corresponding to all applications are placed on the same time axis, and then these operation intensity curves are fitted into the first equivalent operation intensity curve. Each peak value in the first equivalent operation intensity curve represents the correlation of all applications in terms of operation intensity. The larger the peak value, the more multiple applications interact with the database at the same time in the corresponding period, and the greater the overall interaction intensity. Obviously, the greater the interaction pressure on the database during this period.

[0059] At the same time, the present invention counts the number of these peak values. The more peak values ​​there are, the more fully the operation history data in the first period has characterized the operation correlation between the applications. In this case, the first expansion coefficient is set to be smaller, that is, there is no need to frame more operation history data to analyze and mine this correlation. On the contrary, it means that the operation history data in the first period has not sufficiently characterized the operation correlation between the applications. In this case, the first expansion coefficient is set to be larger, that is, more operation history data is framed to analyze and mine this correlation between the applications.

[0060] The intensity threshold is a fixed value determined based on a statistical value or an empirical value, and the present invention will not elaborate on it here.

[0061] In some embodiments, the obtaining the user's operation habit data according to the operation history data analysis includes:

[0062] Determine a second operation intensity curve corresponding to each application according to the second operation history data, and map all the second operation intensity curves according to the same time axis;

[0063] Constructing a plurality of first closed graphs with the time axis as the base for each of the second operation intensity curves, and performing intersection calculation on all of the first closed graphs to obtain a second closed graph;

[0064] Dividing the second closed figure into a plurality of sub-closed figures according to the trough nodes of the upper boundary curve of the second closed figure, calculating the integral value of the upper boundary curve of each of the sub-closed figures, and obtaining a second equivalent operation intensity curve by fitting according to the integral value;

[0065] Synchronously compare each of the second operation intensity curves with the second equivalent operation intensity curve to determine the application corresponding to each of the integral values, and thereby determine the operation association intensity data set corresponding to each application, that is, analyze and obtain the user's operation habit data; wherein the operation association intensity data set includes a plurality of operation association intensity data representing the application and any other application, and the operation association intensity data is determined based on the integral value.

[0066] In this embodiment, after obtaining the second operation intensity curve of the user for each application in the second period, mapping is performed according to the method of the above embodiment, and multiple second operation intensity curves located in the same coordinate system are obtained. The intersection of these second operation intensity curves reflects the relationship between multiple applications interacting with the database at the same time. For the convenience of calculation, the present invention constructs multiple first closed graphs with the time axis as the bottom and each second operation intensity curve as the top, and then calculates the intersection of these first closed graphs to obtain a second closed graph, whose upper boundary curve is the intersection of each second operation intensity curve, and the integral value of each segment (divided by trough) of the upper boundary curve of the second closed graph can be easily calculated. According to multiple integral values, a second equivalent operation intensity curve can be fitted. At this time, the second equivalent operation intensity curve is coaxially compared with all the second operation intensity curves to determine the segment of the second operation intensity curve matched by each curve segment, and then based on the overlap relationship between the curves (the overlap is higher than the set value), the multiple applications involved in each segment are further determined. Obviously, these applications have the characteristics of simultaneous interaction with the database, that is, they belong to associated applications.

[0067] It should be noted that, since it is difficult to directly calculate the intersection between curves, the present invention first processes the second operation history curve into a closed graph, then performs intersection processing, and then restores it to a curve form, namely, the second equivalent operation intensity curve.

[0068] In addition, the operation association strength data is determined according to the integral value. For example, the integral value may be directly determined as the operation association strength data, or a preset coefficient may be used to multiply the integral value to obtain the operation association strength data.

[0069] In some embodiments, the determining of multiple data groups corresponding to each application program based on the operation habit data and the AI ​​analysis model includes:

[0070] Acquire first attribute data of the main application, and obtain a first data group according to the first attribute data;

[0071] Based on the synchronous comparison result of the second operation intensity curves of the main application and each associated application, determine and obtain each second data group corresponding to each associated application;

[0072] Determine each of the operation association strength data corresponding to the main application in the operation association strength data set, and filter and process each of the second data groups according to the operation association strength data corresponding to the associated application and the AI ​​analysis model to obtain each third data group;

[0073] fusing the first data group and each of the third data groups to obtain the data group;

[0074] The above process is repeated to obtain the data group corresponding to each main application.

[0075] In this embodiment, multiple associated applications with the above-mentioned association with the main application are determined in the aforementioned manner. In order to improve the interaction efficiency between multiple applications and the database, in addition to dividing each application into a sub-database, the present invention further determines the main application and its associated applications as an application combination, and divides a sub-database for the application combination. Therefore, when the main application needs to associate and start or call other associated applications, other associated applications can also retrieve corresponding data in the sub-database. In this way, the data interaction between the main application and each associated application on the database can be achieved through the management module of the sub-database, which can reduce the processing load of the database management system. After the above processing, sub-databases supporting multiple main applications can be obtained. These sub-databases contain data that the main application may need to use, as well as data that the associated application may need to use when interacting with the main application (such as calling, jumping, etc.).

[0076] Specifically, first obtain the first attribute data of the main application, the first attribute data of the application includes information such as required permissions and external data interfaces, and all the data that may be used by the main application can be analyzed based on these first attribute data, including photos, address books, authorization passwords, user preference data, etc. Then, compare the second operation intensity curves of the main application and the associated application obtained above, and then determine the synchronization data of the main application and the associated application according to the time period corresponding to the highly overlapping part of the two curves. The synchronization data refers to the data of the interaction between the main application and the associated application and the database, which meets the overlap higher than the overlap threshold and the similarity of the data volume trend is also higher than the similarity threshold (indicating that the probability of these data being the data of the interaction period between the main application and the associated application is relatively high), and determine it as the above-mentioned second data group. Then, according to the operation association intensity data of the main application and each associated application and the AI ​​analysis model, select part of the data from the second data group to form a third data group, and then merge the first data group with all the third data groups to obtain the data group corresponding to each main application. The fusion here can be a union calculation.

[0077] It should be noted that although the data in the second data group belongs to the interactive period, it may not be data related to the interaction. This data does not need to be placed in the sub-database of the main application. Therefore, the present invention uses an AI analysis model to identify and filter out non-interactive data in the second data group.

[0078] In some embodiments, the second data group is screened and processed according to the operation association strength data corresponding to the associated application and the AI ​​analysis model to obtain the third data group, including:

[0079] Inputting the second data group into the AI ​​analysis model to obtain a fourth data group;

[0080] Determine a second expansion coefficient according to the operation association strength data corresponding to the associated application;

[0081] The fourth data group is expanded and adjusted according to the second expansion coefficient to obtain the third data group.

[0082] In this embodiment, the data that each application interacts with the database when interacting has characteristics in terms of data volume trend, trend synchronization, etc., and the AI ​​analysis model can be trained accordingly to accurately identify these characteristics. Therefore, the present invention uses the AI ​​analysis model to implement preliminary screening of the second data group and obtain the fourth data group. At the same time, the operational association strength data between the main application and the associated application represents the association strength between the two applications. When the association strength is higher, it means that the probability that the main application and the associated application have "interacted" is greater, that is, the probability that the second data group contains more interactive data is greater; conversely, the probability that the second data group contains more interactive data is smaller. Therefore, the present invention determines the probability of "interaction" between the main application and the associated application based on the operational association strength data, and determines the above-mentioned second expansion coefficient accordingly. Using the second expansion coefficient, a part of the data can be further screened out from the remaining data in the second data group except the data in the fourth data group, and added to the fourth data group, thereby obtaining the target third data group. Obviously, the second expansion coefficient is positively correlated with the operational association strength data.

[0083] Therefore, the third data group predicted by the present invention contains more data that is more likely to be generated when the main application interacts with the associated application. Moreover, since the expansion is based on the conservative fourth data group, the amount of data in the third data group obtained after the expansion is controllable and will not occupy too much storage space in a specific area of ​​the database unnecessarily.

[0084] In some embodiments, the step of performing expansion adjustment on the fourth data set according to the second expansion coefficient to obtain the third data set includes:

[0085] Obtaining version change data of the main application, determining a version change frequency according to the version change data, and determining a third expansion coefficient according to the version change frequency;

[0086] The fourth data group is expanded and adjusted according to the second expansion coefficient and the third expansion coefficient to obtain the third data group.

[0087] In this embodiment, the main application program is continuously updated, and each update may bring new functions, which will in turn affect the data interaction intensity with the associated application program. For example, in the old version, the main application program calls the associated application program due to a certain function A, but because the experience of this function A is poor, few users generally use it. However, in the new version, this function A is optimized, and the frequency of users using this function A increases. Another example is that in the old version, the main application program does not configure a certain function B, but this function B is newly added in the new version, and the usage data of this function B by users starts to exist and gradually increases. In the above examples, the update of the main application program affects the data interaction intensity between it and the associated application program. In response to this, the present invention determines the third expansion coefficient according to the version change frequency of the main application program, and then simultaneously uses the second expansion coefficient and the third expansion coefficient to perform expansion adjustment on the fourth data group, so as to obtain a more accurate third data group.

[0088] It should be noted that the version change frequency is determined by the version change time interval and the version change intensity. Specifically, it has a negative correlation with the version change time interval between the two, and a positive correlation with the version change intensity. Among them, the version change time interval refers to the time interval between two adjacent versions. By statistically calculating the above time intervals for all versions (or versions within a specific time period), the equivalent time interval can be determined. The smaller the equivalent time interval, the higher the version change frequency. The version change intensity refers to the evaluation value of the degree of version change, which is mainly determined based on the version numbers of历次 changes of the main application program. The version numbers can be 12.1.3, 12.1.4, 12.1.5, 13.0.0. It can be set that the change from 12.1.3 to 12.1.5 is a normal degree change, and the change to 13.0.0 is a generational change. Set the value of the normal degree change to a and the value of the generational change to b, where a < b. Then, by calculating the average value of the above values for all versions (or versions within a specific time period), the above evaluation value is obtained. Obviously, the higher the version change frequency, the larger the third expansion coefficient, that is, more remaining data is filled into the fourth data group.

[0089] Please refer to Figure 2 , an embodiment of the present invention discloses an artificial intelligence-based database segmentation management system, including an acquisition module, a processing module, and a storage module. The processing module is connected to the storage module and the acquisition module; among them,

[0090] The acquisition module is at least used to acquire the operation history data of users for each application program and transmit it to the processing module;

[0091] The storage module is used to store executable computer program code;

[0092] It is characterized in that: the processing module is used to execute the method as described in any of the preceding items by calling the executable computer program code in the storage module to achieve segmentation of a specific area of ​​the database.

[0093] An embodiment of the present invention further discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method as described in any of the preceding items.

[0094] The embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any of the above items is executed.

[0095] The embodiment of the present invention further discloses a computer program product, and when the computer program is executed by a processor, any of the above methods is executed.

[0096] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0098] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0100] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0101] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0102] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.

[0103] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A database segmentation management method based on artificial intelligence, characterized in that: The steps include: Obtaining the user's operation history data for each application, analyzing the user's operation habit data based on the operation history data, and determining multiple data groups corresponding to each application based on the operation habit data and the AI ​​analysis model; Dividing at least a portion of the database into a specific area, dividing the specific area to obtain a plurality of sub-databases, and storing each of the data groups in a corresponding sub-database; wherein the sub-databases correspond to the application programs one by one; The obtaining of the user's operation history data for each application program includes: Acquire first operation history data of the user on each application within a first period, and extract high-intensity operation data corresponding to each application from the first operation history data; Performing correlation analysis and calculation on all the high-intensity operation data to obtain a first expansion coefficient; The first period is expanded and adjusted to a second period according to the first expansion coefficient, and second operation history data of the user for each application in the second period is obtained, where the second operation history data is the operation history data; The obtaining of the user's operation habit data according to the analysis of the operation history data includes: Determine a second operation intensity curve corresponding to each application according to the second operation history data, and map all the second operation intensity curves according to the same time axis; Constructing a plurality of first closed graphs with the time axis as the base for each of the second operation intensity curves, and performing intersection calculation on all of the first closed graphs to obtain a second closed graph; Dividing the second closed figure into a plurality of sub-closed figures according to the trough nodes of the upper boundary curve of the second closed figure, calculating the integral value of the upper boundary curve of each of the sub-closed figures, and obtaining a second equivalent operation intensity curve by fitting according to the integral value; Synchronously comparing each of the second operation intensity curves with the second equivalent operation intensity curve, determining the application corresponding to each of the integral values, and determining the operation association intensity data set corresponding to each of the application programs, that is, analyzing and obtaining the user's operation habit data; wherein the operation association intensity data set includes a plurality of operation association intensity data representing the application program and any other application program, and the operation association intensity data is determined according to the integral value; The determining of a plurality of data groups corresponding to each application program according to the operation habit data and the AI ​​analysis model includes: Acquire first attribute data of the main application, and obtain a first data group according to the first attribute data; Based on the synchronous comparison result of the second operation intensity curves of the main application and each associated application, determine and obtain each second data group corresponding to each associated application; Determine each of the operation association strength data corresponding to the main application in the operation association strength data set, and filter and process each of the second data groups according to the operation association strength data corresponding to the associated application and the AI ​​analysis model to obtain each third data group; fusing the first data group and each of the third data groups to obtain the data group; The above process is repeated to obtain the data group corresponding to each main application.

2. The method for database segmentation management based on artificial intelligence according to claim 1, characterized in that: The performing correlation analysis and calculation on all the high-intensity operation data to obtain a first expansion coefficient includes: Sorting the high-intensity operation data corresponding to each application program in chronological order and fitting the high-intensity operation data into a first operation intensity curve; Mapping all the first operation intensity curves according to the same time axis, performing fitting processing on all the mapped operation intensity curves to obtain a first equivalent operation intensity curve; The number of peaks in the first equivalent operation intensity curve that are higher than an intensity threshold is counted, and the first expansion coefficient is determined according to the number.

3. The method for database segmentation management based on artificial intelligence according to claim 2, characterized in that: The second data group is screened and processed according to the operation association strength data corresponding to the associated application and the AI ​​analysis model to obtain a third data group, including: Inputting the second data group into the AI ​​analysis model to obtain a fourth data group; Determine a second expansion coefficient according to the operation association strength data corresponding to the associated application; The fourth data group is expanded and adjusted according to the second expansion coefficient to obtain the third data group.

4. The method for database segmentation management based on artificial intelligence according to claim 3, characterized in that: The step of expanding and adjusting the fourth data set according to the second expansion coefficient to obtain the third data set includes: Obtaining version change data of the main application, determining a version change frequency according to the version change data, and determining a third expansion coefficient according to the version change frequency; The fourth data group is expanded and adjusted according to the second expansion coefficient and the third expansion coefficient to obtain the third data group.

5. A database segmentation management system based on artificial intelligence, comprising an acquisition module, a processing module, and a storage module, wherein the processing module is connected to the storage module and the acquisition module; wherein: The acquisition module is at least used to acquire the user's operation history data for each application program and transmit it to the processing module; The storage module is used to store executable computer program code; It is characterized in that: the processing module is used to execute the method according to any one of claims 1 to 4 by calling the executable computer program code in the storage module to achieve segmentation of a specific area of ​​the database.

Images