A data storage method based on artificial intelligence learning

Abstract

The application relates to the technical field of data storage, in particular to a data storage method based on artificial intelligence learning, which comprises the following steps: acquiring a plurality of to-be-stored data and calling information of each to-be-stored data; determining a storage area corresponding to each to-be-stored data according to the calling information; acquiring data categories and data attributes corresponding to each to-be-stored data, and dividing the storage area into a plurality of sub-storage areas according to the data categories; and storing all the to-be-stored data based on the data attributes and all the sub-storage areas. The application effectively improves the subsequent data query efficiency through dynamic hierarchical storage.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data storage, and particularly relates to a data storage method based on artificial intelligence learning. BACKGROUND

[0002] With the rapid progress of current information technology and the development of big data technology, various industries are faced with the demand of large data storage and query. For example, in the enterprise digital system, a large amount of employee data, enterprise confidential data and enterprise financial data are stored, and when the enterprise makes a major decision, a large amount of data may need to be stored in a short time, at which time the enterprise needs to store and manage a large amount of data uniformly in order to facilitate data application in the later period.

[0003] In the related art, data is directly stored in a database, and when data in the database needs to be queried, all data in the database is directly traversed; however, when a user has an emergency data query requirement, i.e., the user needs to query in a short time, it may take a long time to query by traversing the database, and it can be seen that the storage of data in the related art may cause the problem of low data query efficiency. SUMMARY

[0004] In order to solve the above technical problems, the present application provides a data storage method based on artificial intelligence learning.

[0005] In a first aspect, the present application provides a data storage method based on artificial intelligence learning, comprising:

[0006] obtaining a plurality of to-be-stored data and calling information of each to-be-stored data;

[0007] determining a storage area corresponding to each to-be-stored data according to the calling information;

[0008] obtaining a data type and a data attribute corresponding to each to-be-stored data, and dividing each storage area into a plurality of sub-storage areas according to the data type;

[0009] storing all to-be-stored data based on the data attribute and all sub-storage areas.

[0010] In a preferred example, the present application can be further configured to: the calling information includes a plurality of calling time periods and a calling frequency corresponding to each calling time period, and the determination of the storage area corresponding to each to-be-stored data according to the calling information comprises:

[0011] for each to-be-stored data, determining a calling frequency mean based on all calling time periods and a calling frequency corresponding to each calling time period;

[0012] obtain a collection of frequencies of retrieval corresponding to each of the storage areas;

[0013] determine the storage area corresponding to each of the to-be-stored data according to the mean of the frequencies of retrieval of each of the to-be-stored data and the collection of frequencies of retrieval corresponding to each of the storage areas.

[0014] In a preferred example, the application can be further configured to store all the to-be-stored data based on the data attribute and all the sub-storage areas, including:

[0015] For each of the sub-storage areas, obtain the storable amount corresponding to each of the sub-storage areas;

[0016] calculate the correlation between the to-be-stored data, and determine a plurality of associated data of each of the to-be-stored data according to the correlation;

[0017] generate a to-be-stored data item according to all the associated data of each of the to-be-stored data;

[0018] obtain the data amount of all the to-be-stored data items, and determine whether the data amount is less than the storable amount;

[0019] If yes, store the to-be-stored data item into the corresponding sub-storage area;

[0020] If no, correct the storable amount of each of the sub-storage areas according to the storable amount and the data attribute to obtain a corrected sub-storage area;

[0021] store the to-be-stored data item into the corrected sub-storage area.

[0022] In a preferred example, the application can be further configured to calculate the correlation between the to-be-stored data, including:

[0023] generate a plurality of data tags corresponding to each of the to-be-stored data, the data tags being used to identify the to-be-stored data;

[0024] determine a first correlation of each of the to-be-stored data based on the data tags corresponding to each of the to-be-stored data;

[0025] obtain the retrieval time of the to-be-stored data, and determine a second correlation of each of the to-be-stored data based on the retrieval time of each of the to-be-stored data and a preset corresponding relationship;

[0026] determine a comprehensive correlation based on the first correlation and the second correlation, and determine the comprehensive correlation as the correlation between the to-be-stored data.

[0027] In a preferred example, the application can be further configured to determine the first correlation degree of each of the to-be-stored data based on the data tags corresponding to each of the to-be-stored data, including:

[0028] Obtaining application information of each of the to-be-stored data, and determining a weight value of each of the data tags according to the application information and all the data tags of each of the to-be-stored data;

[0029] Determining a plurality of target data tags based on the weight value of each of the data tags and a preset weight value threshold;

[0030] For each pair of the to-be-stored data, determining a same data tag from all the target data tags;

[0031] Obtaining a first label quantity of the target data tag of each of the to-be-stored data and a second label quantity corresponding to the same data tag;

[0032] Determining a data similarity according to the first label quantity, the second label quantity, and all the same data tags;

[0033] Determining the data similarity as the first correlation degree of each of the to-be-stored data.

[0034] In a preferred example, the application can be further configured to determine the data similarity according to the first label quantity, the second label quantity, and all the same data tags, including:

[0035] For each of the same data tags, determining an occurrence frequency of the same data tag based on the first label quantity and the second label quantity;

[0036] Obtaining a data quantity of the to-be-stored data, and determining an inverse document frequency of the same data tag according to the occurrence frequency, the data quantity of the to-be-stored data, and a preset similarity calculation formula, the inverse document frequency representing a universality of the same data tag;

[0037] Determining a vector value based on the occurrence frequency and the inverse document frequency;

[0038] Determining a data distance between the to-be-stored data based on the vector value;

[0039] Determining the data similarity according to the data distance and a target corresponding relationship, the target corresponding relationship being a corresponding relationship between the data distance and the data similarity.

[0040] In summary, the application has the following beneficial technical effects:

[0041] When the call frequency of the to-be-stored data is higher, the to-be-stored data is used more frequently, indicating that the to-be-stored data is more important, and thus the to-be-stored data and the respective call frequency need to be obtained; the storage area of each to-be-stored data is determined according to the call frequency, and the to-be-stored data of different importance levels is stored in different areas for subsequent data calling; the data type and data attribute of each to-be-stored data are obtained, and the storage area is divided into a plurality of sub-storage areas according to the data type, so as to further subdivide the data storage area on the basis of the storage of data of the same importance level; the storage area is divided into a plurality of sub-storage areas according to the data type for classified storage; on the basis of the classified storage, the storage is further refined according to the data attribute; compared with the related art, the to-be-stored data is divided into a plurality of levels according to the call frequency, the data type and the data attribute, and the to-be-stored data of different levels is stored in different areas to realize dynamic hierarchical storage of the to-be-stored data, which facilitates subsequent user hierarchical data query, and effectively improves the data query efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 A scene schematic diagram of a data storage method based on artificial intelligence learning provided by an embodiment of the present application;

[0043] Figure 2 A flowchart of a data storage method based on artificial intelligence learning provided by an embodiment of the present application;

[0044] Figure 3 A structure schematic diagram of a data storage device based on artificial intelligence learning provided by an embodiment of the present application;

[0045] Figure 4 A structure schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will be described in detail with reference to the accompanying drawings. Figure 1 to the accompanying drawings Figure 4 The present application will be further described in detail.

[0047] Those skilled in the art can make modifications to the embodiments of the present application without creative contribution after reading the present specification, but as long as the modifications are within the scope of the claims of the present application, they are protected by the patent law.

[0048] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0049] In addition, the term "and / or" in this document is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects unless otherwise specified.

[0050] The embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings of the specification. As shown in the drawings, a data storage scenario schematic diagram provided by the embodiments of the present application is shown, a user generates a storage request and inputs to-be-stored data at a user-side device, the electronic device receives the storage request and the to-be-stored data, and then comprehensively analyzes the calling information, data type and data attribute of the to-be-stored data, and dynamically classifies and stores the to-be-stored data. Figure 1

[0051] The embodiments of the present application provide a data storage method based on artificial intelligence learning, which is executed by an electronic device. The electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server providing cloud computing services. The terminal device can be a smartphone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected through wired or wireless communication, and the embodiments of the present application do not limit this. As shown in the drawings, the method comprises steps S101, S102, S103 and S104, wherein: Figure 2

[0052] Step S101, obtaining a plurality of to-be-stored data and calling information of each to-be-stored data.

[0053] Specifically, a monitoring program is pre-integrated in the electronic device, which is used to monitor the triggering behavior of the acquisition request. Once the acquisition request is triggered, the acquisition operation is performed. Specifically, the user can generate an acquisition request by clicking or voice. The to-be-stored data and the calling information are pre-input by the user into the to-be-stored database. The to-be-stored data can be enterprise data or government data, etc., and the embodiments of the present application do not limit the specific to-be-stored data. The calling information includes a plurality of calling time periods of the to-be-stored data and a calling frequency corresponding to each calling time period.

[0054] Step S102, determining a storage area corresponding to each to-be-stored data according to the calling information.

[0055] ​​Specifically, the calling information includes a plurality of calling time periods and a calling frequency corresponding to each calling time period, and each calling time period is composed of a plurality of calling times.

[0056] In step S103, the data category and the data attribute corresponding to each to-be-stored data are obtained, and each storage area is divided into a plurality of sub-storage areas according to the data category.

[0057] Specifically, the data category of the to-be-stored data can be determined by a data category identification tool. In the embodiments of the present application, the data category of the to-be-stored data can be continuous data, discrete data, ordered data, time series data, text data, etc., which is not limited in the embodiments of the present application. The data attribute is used to describe the characteristics of the data, such as enterprise customer data and enterprise product data, etc., and the specific data attribute is not limited in the embodiments of the present application. The number of sub-storage areas is a plurality; each sub-area corresponds to a data attribute.

[0058] In step S104, all to-be-stored data are stored based on the data attribute and all sub-storage areas.

[0059] Specifically, the specific process of storing all to-be-stored data based on the data attribute and all sub-storage areas can be referred to in the following embodiments. It can be understood that storing the to-be-stored data into the corresponding sub-storage area according to the data attribute can realize further refined storage and dynamic storage of the to-be-stored data, and then realize fast calling of the data in the subsequent calling process.

[0060] Based on the above embodiments, when the calling frequency of the to-be-stored data is higher, the to-be-stored data is applied more frequently, indicating that the to-be-stored data is more important, and thus the to-be-stored data and the corresponding calling information need to be obtained; then the storage area of each to-be-stored data is determined according to the calling information, and the to-be-stored data of different importance levels are stored in different areas to facilitate subsequent data calling; the data category and the data attribute of each to-be-stored data are obtained, and the storage area is divided into a plurality of sub-storage areas according to the data category, so as to further subdivide the data storage area on the basis of the same importance level data storage; then the storage area is divided into a plurality of sub-storage areas according to the data category for classified storage; on the basis of classified storage, the data is further refined according to the data characteristics; compared with the related art, the present application divides the to-be-stored data into multiple levels according to the calling information, the data category and the data attribute of the data, and stores the data in different areas according to different levels to realize dynamic hierarchical storage of the to-be-stored data, which facilitates subsequent user hierarchical data query, and effectively improves the data query efficiency.

[0061] Further, the calling information includes a plurality of calling time periods and calling frequencies corresponding to the calling time periods, and the storage area corresponding to each to-be-stored data is determined according to the calling information, including:

[0062] For each to-be-stored data, the average calling frequency is determined based on all calling time periods and the calling frequencies corresponding to the calling time periods.

[0063] A set of calling frequencies corresponding to each storage area is obtained.

[0064] The storage area corresponding to each to-be-stored data is determined according to the average calling frequency of each to-be-stored data and the set of calling frequencies corresponding to each storage area.

[0065] Specifically, the number of calling time periods and the total calling frequency of the calling time period are determined, and the average calling frequency is determined according to the calculation formula,

[0066] In the embodiments of the present application, the storage area includes a first storage area, a second storage area and a third storage area; the storage priorities of different storage areas are different, and the area priorities of the storage areas are pre-set by technical personnel; wherein the area priority of the first storage area is higher than the storage priority of the second storage area, and the area priority of the second storage area is higher than the area priority of the third storage area. Wherein the storage data corresponding to the first storage area are all high-frequency calling data, the storage data corresponding to the second storage area are all medium-frequency calling data, and the storage data corresponding to the third storage area are all low-frequency calling data, that is, the calling frequency of the storage data in the first storage area is greater than the calling frequency of the storage data in the second storage area, the calling frequency of the storage data in the second storage area is greater than the calling frequency of the storage data in the third storage area, and the set of calling frequencies corresponding to each storage area is pre-set by technical personnel, and the set of calling frequencies is composed of a plurality of calling frequency values. The average calling frequency and the set of calling frequencies are matched one by one to obtain the storage area corresponding to the to-be-stored data. It can be understood that when the calling frequency of the to-be-stored data is high, it indicates that the to-be-stored data is more important, and in the later use, important data is preferentially scheduled from the storage area, compared with traversing all storage areas, the present application can effectively improve the calling efficiency.

[0067] Based on the above embodiments, the average calling frequency is determined according to the calling time period and the corresponding calling frequency, so as to represent the overall calling frequency of the to-be-stored data through the average calling frequency; then the set of calling frequencies of each storage area is obtained, and the storage area corresponding to each to-be-stored data is determined according to the average calling frequency and the set of calling frequencies, so as to effectively improve the accuracy of the to-be-stored area division.

[0068] Further, all to-be-stored data are stored based on the data attribute and all sub-storage areas, including:

[0069] For each sub-storage area, obtain the storable amount corresponding to each sub-storage area;

[0070] Calculate the correlation between the to-be-stored data, and determine the associated data of each to-be-stored data according to the correlation;

[0071] Generate a to-be-stored data item according to all the associated data of each to-be-stored data;

[0072] Obtain the data amount of all to-be-stored data items, and determine whether the data amount is less than the storable amount;

[0073] If yes, store the to-be-stored data item into the corresponding sub-storage area;

[0074] If no, modify the storable amount of each sub-storage area according to the storable amount and the data attribute to obtain a modified sub-storage area;

[0075] Store the to-be-stored data item into the modified sub-storage area.

[0076] Specifically, the storable amount of each sub-storage area is pre-set by a technician, and the present application does not limit the storable amount. The specific process of calculating the correlation between two to-be-stored data can refer to the following embodiments. The correlation is compared with a pre-set correlation threshold value, and if the correlation is greater than the pre-set correlation threshold value, the to-be-stored data is determined as the associated data of another to-be-stored data, and the to-be-stored data that are associated with each other are generated into a data item (including at least two to-be-stored data) for storage. It can be understood that storing the to-be-stored data in the form of a data item during storage helps to maintain the consistency and integrity of the to-be-stored data, and when subsequent queries and access are needed, the user only needs to perform one operation to access all related data, effectively improving the data query efficiency. The data amount of the to-be-stored data item is input by the user. If the data amount is less than the storable amount of the sub-storage area, the to-be-stored data can be directly stored; if not, the storable amount of the sub-storage area is modified, and the specific process of modifying the storage capacity of each sub-storage area includes: obtaining the attribute weight value of the pre-set data attribute, and modifying the storage capacity of the sub-storage area according to the attribute weight value and the corresponding relationship between the modified storage capacity to obtain the modified storable capacity, and then storing the modified to-be-stored data item into the corresponding sub-storage area. The corresponding relationship between the attribute weight value and the modified storage capacity is pre-set by a technician. It can be understood that the attribute weight value is used to describe the importance of the data attribute, and with the increase of the attribute weight value, the corresponding to-be-stored data is more important, and the data amount of the important to-be-stored data will also increase, so the storage capacity needs to be appropriately expanded to avoid the occurrence of data loss problems due to insufficient storage capacity.

[0077] Based on the above embodiments, the storability of each sub-storage area is obtained, and the storage capacity of the sub-storage area is corrected according to the storability and the data attribute. The importance levels of data with different characteristics are also different. In order to avoid data loss caused by storage failure of more important data, it is necessary to correct the storage capacity in order to store complete to-be-stored data. The correlation between to-be-stored data is calculated, and the associated data of the to-be-stored data is determined according to the correlation. Then, the to-be-stored data item is generated according to all the associated data of all the to-be-stored data, and the associated storage between data is realized. When the data is queried subsequently, only one query is required to realize the query of all the related data, and the query efficiency is effectively improved.

[0078] Further, the correlation between to-be-stored data is calculated, including:

[0079] A plurality of data tags corresponding to each to-be-stored data are generated, and the data tags are used to identify the to-be-stored data.

[0080] Based on the data tags corresponding to each to-be-stored data, the first correlation of each to-be-stored data is determined.

[0081] The retrieval time of the to-be-stored data is obtained, and based on the retrieval time of each to-be-stored data and a preset corresponding relationship, the second correlation of each to-be-stored data is determined.

[0082] The comprehensive correlation is determined based on the first correlation and the second correlation, and the comprehensive correlation is determined as the correlation between the to-be-stored data.

[0083] Specifically, the data label is used to identify the data to be stored, such as when the data to be stored is enterprise product data, then the corresponding data label can be product sales status, popularity, etc. The data label can be generated by a preset data label labeling model. The data to be stored is input into the data label labeling model, and the data label labeling model outputs the above-mentioned data to be stored and its corresponding data label. The data label of each data to be stored can be one or more. The data label labeling model is obtained by training a plurality of training data. The training process of the data label labeling model includes: inputting a plurality of training storage data and their respective sample data labels into a time sequence neural network model, the time sequence neural network model outputs the training data label corresponding to each training storage data, calculates the loss value between the training data label and the sample data label according to the training data, the sample data label and the loss value function, and determines whether the loss value is greater than a preset loss value threshold. If the loss value is not greater than the preset loss value threshold, continue to train the time sequence neural network model using the training storage data and the corresponding sample data label until the loss value is greater than the preset loss value threshold. If the loss value is greater than the preset loss value threshold, continue to train the time sequence neural network model for a preset number of times, and calculate the average loss value after the loss value is greater than the preset loss value threshold. Then, calculate the loss value variance according to the average loss value, and compare the loss value variance with the variance threshold. If the loss value variance is less than the variance threshold, stop training, and determine the time sequence neural network model as the data label labeling model. Otherwise, continue to train the time sequence neural network model until the loss value variance is less than the variance threshold. The above-mentioned loss value function can be mean square error loss function, binary cross entropy loss function, etc. The preset loss value threshold and the variance threshold are both preset by the technical personnel. It can be understood that when the loss value variance is less than the variance threshold, it indicates that the change amplitude of the loss value is small at this time, that is, the time sequence neural network model can output data labels with high accuracy. The specific process of determining the first correlation degree between the data to be stored according to the data label of the data to be stored can be referred to in the following embodiments. The retrieval time of the data to be stored is the time value sent by the user to the electronic device; the preset correspondence is set by the technical personnel according to the working experience. The specific process of determining the comprehensive correlation degree according to the first correlation degree and the second correlation degree includes: obtaining the first weight value corresponding to the first correlation degree and the second weight value corresponding to the second correlation degree, and obtaining the comprehensive correlation degree according to the first weight value, the first correlation degree, the second weight value and the second correlation degree, that is, comprehensive correlation degree = first weight value * first correlation degree + second weight value * second correlation degree. In the embodiments of the present application, the first weight value is greater than the second weight value. It can be understood that different weight values are given to the first correlation degree and the second correlation degree to calculate the comprehensive correlation degree and obtain a more accurate comprehensive correlation degree. The comprehensive correlation degree is determined as the correlation degree between the two data to be stored.

[0084] Based on the above embodiments, the data tags help to further refine and distinguish the to-be-stored data, so it is necessary to generate the data tags of the to-be-stored data to analyze the correlation between the to-be-stored data from a micro perspective, and then determine the first correlation degree according to the data tags of the to-be-stored data to effectively improve the accuracy of the first correlation degree; then determine the second correlation degree according to the retrieval time and the corresponding relationship, and determine the comprehensive correlation degree according to the first correlation degree and the second correlation degree, which realizes comprehensive analysis of the correlation between the to-be-stored data from different dimensions, and further improves the accuracy of determining the correlation between the to-be-stored data.

[0085] Further, based on the data tags corresponding to each to-be-stored data, the first correlation degree of each to-be-stored data is determined, including:

[0086] Obtaining application information of each to-be-stored data, and determining a weight value of each data tag according to the application information and all data tags corresponding to each to-be-stored data;

[0087] Based on the weight value of each data tag and the preset weight value threshold, a plurality of target data tags are determined;

[0088] For each pair of to-be-stored data, the same data tag is determined from all target data tags;

[0089] Obtaining the first label quantity of the target data tag of each to-be-stored data and the second label quantity corresponding to the same data tag;

[0090] Determining the data similarity according to the first label quantity, the second label quantity and all same data tags;

[0091] The data similarity is determined as the first correlation degree of each to-be-stored data.

[0092] Specifically, the application information of the to-be-stored data represents an application scenario identifier of the to-be-stored data, for example, when the to-be-stored data is enterprise product data, the corresponding application scenario can be an enterprise annual display or product revenue accounting application scenario, and the application information can be sent by the user to the electronic device at the same time as the to-be-stored data. The specific process of determining the weight value of the data tag according to the application information and the data tag includes: obtaining a preset weight value corresponding to each application scenario identifier, matching the data tag with all application scenario identifiers through a semantic matching algorithm, and determining the weight value of the application scenario identifier corresponding to the data tag as the weight value of the data tag. The weight value of each data tag is compared with the preset weight value threshold, and the data tag with a weight value greater than the preset weight value threshold is determined as a target data tag, and then the first correlation degree of the to-be-stored data is determined according to the representative data tag, so as to improve the accuracy of the first correlation degree calculation. In addition, the data tag is screened through the weight value, which can further improve the accuracy of the first correlation degree by reducing the interference of irrelevant data tags. The first label quantity and the second label quantity can be obtained from the data tag statistical library. The specific process of determining the data similarity according to the first label quantity, the second label quantity, and the same data tag can refer to the following embodiments, and the data similarity is determined as the first correlation degree between the to-be-stored data.

[0093] Based on the above embodiments, when the application scenarios are different, the same data tag intuitively reflects the degree of to-be-stored data, and thus different data tags have different importance degrees for to-be-stored data. Therefore, the weight value of each data tag needs to be determined according to the application information. Then, the target data tag is determined according to the weight value of the data tag and the preset weight value threshold, that is, the data tag that is more important and can more intuitively reflect the to-be-stored data is taken as a reference. For each two to-be-stored data, the same data tag is determined from all target data tags. When the number of the same data tags between the to-be-stored data is more, it indicates that the correlation degree between the to-be-stored data is higher. Then, the first label quantity of the target data tag and the second label quantity of the same data tag are obtained, and the data similarity is determined according to the first label quantity, the second label data, and the same data tag. Then, the data similarity is determined as the first correlation degree between the to-be-stored data.

[0094] Further, the data similarity is determined according to the first label quantity, the second label quantity, and all the same data tags, including:

[0095] For each same data tag, based on the first label quantity and the second label quantity, the occurrence frequency of the same data tag is determined.

[0096] The data amount of the to-be-stored data is acquired, and the inverse document frequency of the same data label is determined according to the occurrence frequency, the data amount of the to-be-stored data, and a preset similarity calculation formula, where the inverse document frequency represents the universality of the same data label;

[0097] The vector value is determined based on the occurrence frequency and the inverse document frequency;

[0098] The data distance between the to-be-stored data is determined based on the vector value;

[0099] The data similarity is determined according to the data distance and a target correspondence relationship, where the target correspondence relationship is the correspondence relationship between the data distance and the data similarity.

[0100] Specifically, the occurrence frequency of the same data label can be determined according to a calculation formula, where the occurrence frequency represents the occurrence frequency of the same data label in the target data label in the embodiment of the present application; and the calculation formula is as follows: The preset similarity calculation formula in the embodiment of the present application is as follows: where the preset value is a positive integer greater than 0, and the embodiment of the present application does not limit the specific preset value, which can be 1 or 2, etc. It can be understood that, in order to avoid the denominator being 0 in the above formula and resulting in a negative value, the preset value needs to be considered.

[0101] The inverse document frequency represents the universality of the data label between the two to-be-stored data, and the higher the universality of the data label, the stronger the correlation between the two to-be-stored data. The vector value can be obtained according to a vector value calculation formula, where the calculation formula is as follows: vector value = occurrence frequency * inverse document frequency, that is, the vector value is the distance between the to-be-stored data determined from the same data label dimension. For the same data label of the to-be-stored data, the Euclidean algorithm can be used to calculate the sub-data distance corresponding to the two to-be-stored data, and the embodiment of the present application does not limit the specific calculation process. In an implementable manner, the average sub-data distance is calculated according to the sub-data distance corresponding to all same data labels, and the average sub-data distance is determined as the data distance between the to-be-stored data. It can be understood that the average value can more accurately reflect the degree of change between the data, and thus the average sub-data distance can be selected as the data distance between the to-be-stored data. The data distance and the target correspondence relationship are matched one by one, and thus the data similarity corresponding to the data distance can be obtained. In the embodiment of the present application, the smaller the data distance, the greater the data similarity; and the target correspondence relationship is input into the electronic device by the technician in advance.

[0102] Based on the above embodiment, the occurrence frequency of the same data label in the target data label is determined according to the first label quantity and the second label quantity; the data quantity of the to-be-stored data is obtained, and the universality of the same data label is determined according to the occurrence frequency, the to-be-stored data and the preset similarity calculation formula; then the vector value corresponding to the same data label is determined according to the occurrence frequency and the inverse document frequency, and the data distance between the to-be-stored data is determined according to the vector value; when the correlation between two to-be-stored data is higher, the data distance between the to-be-stored data is closer, so it is necessary to determine the data distance between the to-be-stored data; then the data similarity is determined according to the data distance and the target corresponding relationship; the same data label and the to-be-stored data are quantified in the form of a vector, and the data distance is determined according to the vector value, and the data similarity is reflected by the data distance, so as to effectively improve the accuracy of the data similarity.

[0103] The above embodiment introduces a data storage method based on artificial intelligence learning from the perspective of method flow. The following embodiment introduces a data storage device based on artificial intelligence learning from the perspective of virtual modules or virtual units. For details, see the following embodiments.

[0104] The embodiment of the present application provides a data storage device based on artificial intelligence learning, as shown in the Figure 3 The data storage device based on artificial intelligence learning can specifically include:

[0105] The acquisition module 201 is configured to acquire a plurality of to-be-stored data and calling information of each to-be-stored data.

[0106] The storage area determination module 202 is configured to determine a storage area corresponding to each to-be-stored data according to the calling information.

[0107] The sub-storage area determination module 203 is configured to acquire a data category and a data attribute corresponding to each to-be-stored data, and divide each storage area into a plurality of sub-storage areas according to the data category.

[0108] The storage module 204 is configured to store all to-be-stored data based on the data attribute and all sub-storage areas.

[0109] When the higher the frequency of the to-be-stored data is called, the higher the number of times the to-be-stored data is applied, indicating that the to-be-stored data is more important, and thus the to-be-stored data and the respective corresponding call frequency need to be obtained; then the storage area of each to-be-stored data is determined according to the call frequency, and the to-be-stored data of different importance levels is stored in different areas for subsequent data calling; the data type and data attribute of each to-be-stored data are obtained, and the storage area is divided into a plurality of sub-storage areas according to the data type, so as to further subdivide the data storage area on the basis of the storage of data of the same importance level; then the storage area is divided into a plurality of sub-storage areas according to the data type for classified storage; on the basis of classified storage, the storage is further refined according to the data characteristics; compared with the related art, the to-be-stored data is divided into multiple levels according to the call frequency, data type and data attribute of the data, and the to-be-stored data is stored in different areas for different levels to realize dynamic hierarchical storage of the to-be-stored data, which facilitates subsequent user hierarchical data query, and effectively improves the data query efficiency.

[0110] In a possible implementation of the embodiment of the present application, the calling information includes a plurality of call time periods and a call frequency corresponding to each call time period, and the storage area determination module 202, when determining the storage area corresponding to each to-be-stored data according to the calling information, is specifically configured to:

[0111] For each to-be-stored data, based on all call time periods and the call frequency corresponding to each call time period, determine the average call frequency;

[0112] Obtain a call frequency set corresponding to each storage area;

[0113] According to the average call frequency of each to-be-stored data and the call frequency set corresponding to each storage area, determine the storage area corresponding to each to-be-stored data.

[0114] In a possible implementation of the embodiment of the present application, the storage module 204, when storing all to-be-stored data based on the data attribute and all sub-storage areas, is specifically configured to:

[0115] For each sub-storage area, obtain the storable amount corresponding to each sub-storage area;

[0116] Calculate the correlation between to-be-stored data, and determine a plurality of associated data of each to-be-stored data according to the correlation;

[0117] Generate a to-be-stored data item according to all associated data of each to-be-stored data;

[0118] Obtain the data amount of all to-be-stored data items, and determine whether the data amount is less than the storable amount;

[0119] If yes, store the to-be-stored data item into the corresponding sub-storage area.

[0120] If no, the storability of each sub-storage area is corrected according to the storability and the data attribute, and a corrected sub-storage area is obtained;

[0121] The data item to be stored is stored in the corrected sub-storage area.

[0122] In a possible implementation of the embodiment, when the storage module 204 performs the calculation of the correlation between the data to be stored, the storage module 204 is specifically configured to:

[0123] Generate a plurality of data tags corresponding to each data to be stored, the data tag being used to identify the data to be stored;

[0124] Determine the first correlation of each data to be stored based on the data tag corresponding to each data to be stored;

[0125] Obtain the retrieval time of the data to be stored, and determine the second correlation of each data to be stored based on the retrieval time of the data to be stored and a preset corresponding relationship;

[0126] Determine the comprehensive correlation based on the first correlation and the second correlation, and determine the comprehensive correlation as the correlation between the data to be stored.

[0127] In a possible implementation of the embodiment, when the storage module 204 determines the first correlation of each data to be stored based on the data tag corresponding to each data to be stored, the storage module 204 is specifically configured to:

[0128] Obtain the application information of each data to be stored, and determine the weight value of each data tag according to the application information and all data tags of each data to be stored;

[0129] Determine a plurality of target data tags based on the weight value of each data tag and a preset weight value threshold;

[0130] For each pair of data to be stored, determine the same data tag from all target data tags;

[0131] Obtain the first label quantity of the target data tag of each data to be stored and the second label quantity corresponding to the same data tag;

[0132] Determine the data similarity according to the first label quantity, the second label quantity, and all same data tags;

[0133] Determine the data similarity as the first correlation of each data to be stored.

[0134] In a possible implementation of the embodiment, when the storage module 204 determines the data similarity according to the first label quantity, the second label quantity, and all same data tags, the storage module 204 is specifically configured to:

[0135] For each same data label, based on the first label quantity and the second label quantity, determine the occurrence frequency of the same data label;

[0136] Obtain the data quantity of the to-be-stored data, and determine the inverse document frequency of the same data label according to the occurrence frequency, the data quantity of the to-be-stored data, and a preset similarity calculation formula. The inverse document frequency represents the universality of the same data label.

[0137] Based on the occurrence frequency and the inverse document frequency, determine the vector value.

[0138] Based on the vector value, determine the data distance between the to-be-stored data.

[0139] According to the data distance and the target corresponding relationship, determine the data similarity. The target corresponding relationship is the corresponding relationship between the data distance and the data similarity.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described data storage device based on artificial intelligence learning can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0141] In the embodiments of the present application, an electronic device is provided, as shown in Figure 4 As shown in Figure 4 The electronic device shown in comprises a processor 301 and a memory 303. Wherein, the processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device can also include a transceiver 304. It should be noted that in actual application, the transceiver 304 is not limited to one, and the structure of the electronic device does not constitute a limitation on the embodiments of the present application.

[0142] The processor 301 can be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure content. The processor 301 can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc.

[0143] The bus 302 can include a path that transmits information between the above-described components. The bus 302 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 4 Only one thick line is used in the middle, but it does not mean that there is only one bus or one type of bus.

[0144] The memory 303 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0145] The memory 303 is used to store application program codes for implementing the scheme of the present application, and is controlled by the processor 301 to perform. The processor 301 is used to execute the application program codes stored in the memory 303 to realize the content shown in the foregoing method embodiments.

[0146] The electronic device includes, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a car terminal (for example, a car navigation terminal), etc., and a fixed terminal such as a digital TV, a desktop computer, etc. It can also be a server, etc. Figure 4 The electronic device shown is only an example, and should not bring any limitation to the function and use range of the embodiments of the present application.

[0147] The embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program is run on a computer, the computer can execute the corresponding content in the foregoing method embodiment. Compared with the related art, the embodiment of the present application is used more frequently when the to-be-stored data is to be stored, and the to-be-stored data is used more frequently, which indicates that the to-be-stored data is more important, and thus the to-be-stored data and the respective corresponding frequency of access need to be acquired; the storage area of each to-be-stored data is determined according to the frequency of access, and the to-be-stored data of different importance degrees is stored in different areas for subsequent data access; the data type and data attribute of each to-be-stored data are acquired, and the storage area is divided into a plurality of sub-storage areas according to the data type, so as to further subdivide the data storage area on the basis of the data storage of the same importance degree; the storage area is divided into a plurality of sub-storage areas according to the data type for classified storage; the storage is further refined according to the data attribute on the basis of the classified storage; compared with the related art, the to-be-stored data is divided into a plurality of levels according to the frequency of access, the data type and the data attribute, and the to-be-stored data is stored in different areas according to different levels to realize dynamic hierarchical storage of the to-be-stored data, so that the user can perform hierarchical data query, and the data query efficiency is effectively improved.

[0148] It should be understood that, although each step in the flowchart of the accompanying drawings is shown in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include a plurality of sub-steps or a plurality of stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or sub-steps or stages of other steps.

[0149] The above only describes some embodiments of the present application, and it should be pointed out that, for ordinary skilled in the art, without departing from the principles of the present application, some improvements and refinements can be made, and these improvements and refinements should be regarded as the protection scope of the present application.

Claims

1. A data storage method based on artificial intelligence learning, characterized by, The method comprises the following steps: acquiring a plurality of to-be-stored data and calling information of each of the to-be-stored data; determining a storage area corresponding to each of the to-be-stored data according to the calling information; acquiring a data type and a data attribute corresponding to each of the to-be-stored data, and dividing each of the storage areas into a plurality of sub-storage areas according to the data type; storing all of the to-be-stored data based on the data attribute and all of the sub-storage areas; the storing all of the to-be-stored data based on the data attribute and all of the sub-storage areas comprises: for each of the sub-storage areas, acquiring a storable amount corresponding to each of the sub-storage areas; calculating a correlation degree between the to-be-stored data, and determining a plurality of associated data of each of the to-be-stored data according to the correlation degree; generating a to-be-stored data item according to all of the associated data of each of the to-be-stored data; acquiring a data amount of all of the to-be-stored data items, and judging whether the data amount is less than the storable amount; if yes, storing the to-be-stored data item into the corresponding sub-storage area; if no, correcting the storable amount of each of the sub-storage areas according to the storable amount and the data attribute to obtain a corrected sub-storage area; storing the to-be-stored data item into the corrected sub-storage area; the calculating the correlation degree between the to-be-stored data comprises: generating a plurality of data tags corresponding to each of the to-be-stored data, the data tags being used for identifying the to-be-stored data; determining a first correlation degree of each of the to-be-stored data based on the data tags corresponding to each of the to-be-stored data; acquiring a calling time of the to-be-stored data, and determining a second correlation degree of each of the to-be-stored data based on the calling time of each of the to-be-stored data and a preset corresponding relationship; determining a comprehensive correlation degree based on the first correlation degree and the second correlation degree, and determining the comprehensive correlation degree as the correlation degree between the to-be-stored data. 2.The data storage method based on artificial intelligence learning according to claim 1, characterized in that, The calling information comprises a plurality of calling time periods and a calling frequency corresponding to each of the calling time periods, and the determining the storage area corresponding to each of the to-be-stored data according to the calling information comprises: for each of the to-be-stored data, determining a calling frequency average based on all of the calling time periods and the calling frequency corresponding to each of the calling time periods; acquiring a calling frequency set corresponding to each of the storage areas; determining the storage area corresponding to each of the to-be-stored data according to the calling frequency average of each of the to-be-stored data and the calling frequency set corresponding to each of the storage areas. 3.The data storage method based on artificial intelligence learning according to claim 1, characterized in that, The determining the first correlation degree of each of the to-be-stored data based on the data tags corresponding to each of the to-be-stored data comprises: acquiring application information of each of the to-be-stored data, and determining a weight value of each of the data tags according to the application information and all of the data tags of each of the to-be-stored data; determining a plurality of target data tags based on the weight value of each of the data tags and a preset weight value threshold; for each pair of the to-be-stored data, determining a same data tag from all of the target data tags; acquiring a first label quantity of the target data tag of each of the to-be-stored data and a second label quantity corresponding to the same data tag; determine a data similarity according to the first label quantity, the second label quantity and all the same data labels; determine the data similarity as a first correlation degree of each of the to-be-stored data. 4.The data storage method based on artificial intelligence learning according to claim 3, characterized in that, The determining the data similarity according to the first label quantity, the second label quantity and all the same data labels comprises: for each of the same data labels, determining an occurrence frequency of the same data label based on the first label quantity and the second label quantity; obtain a data quantity of the to-be-stored data, and determine an inverse document frequency of the same data label according to the occurrence frequency, the data quantity of the to-be-stored data and a preset similarity calculation formula, the inverse document frequency representing a universality of the same data label; determine a vector value based on the occurrence frequency and the inverse document frequency; determine a data distance between the to-be-stored data based on the vector value; determine the data similarity according to the data distance and a target corresponding relationship, the target corresponding relationship being a corresponding relationship between the data distance and the data similarity.

Images