CN118018330B - Data analysis method and system based on artificial intelligence - Google Patents
Data analysis method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN118018330B CN118018330B CN202410413347.2A CN202410413347A CN118018330B CN 118018330 B CN118018330 B CN 118018330B CN 202410413347 A CN202410413347 A CN 202410413347A CN 118018330 B CN118018330 B CN 118018330B
- Authority
- CN
- China
- Prior art keywords
- data
- user
- storage
- node
- reliability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 37
- 238000007405 data analysis Methods 0.000 title claims abstract description 33
- 238000012795 verification Methods 0.000 claims abstract description 127
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000005540 biological transmission Effects 0.000 claims description 39
- 238000004080 punching Methods 0.000 claims description 24
- 238000005265 energy consumption Methods 0.000 claims description 22
- 238000004458 analytical method Methods 0.000 claims description 14
- 231100000279 safety data Toxicity 0.000 claims description 9
- 238000013500 data storage Methods 0.000 abstract description 9
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Landscapes
- Storage Device Security (AREA)
Abstract
The application discloses a data analysis method and a system based on artificial intelligence, and relates to the field of data analysis, wherein the data analysis method based on artificial intelligence comprises the following steps: s1: receiving a storage request of a user node; s2: performing reliability verification according to the storage request to obtain a reliability verification result, and if the reliability verification result is reliable, receiving data to be stored and executing S3; if the reliability verification result is unreliable, ending the flow and generating alarm information; s3: automatically analyzing data to be stored according to a pre-constructed storage frame to obtain a storage strategy; s4: and processing the data to be stored according to the storage strategy to obtain a plurality of storage sub-data, and storing the plurality of storage sub-data. The application can improve the accuracy and the safety of data analysis and data storage.
Description
Technical Field
The application relates to the technical field of data analysis, in particular to a data analysis method and system based on artificial intelligence.
Background
With rapid development of technology, artificial intelligence technology has gradually penetrated into various fields including: data analysis field and data storage field. Conventional data analysis methods and conventional data storage methods often rely on manual operations, have subjectivity and limitations, and are difficult to process large amounts of complex data.
Enterprise information refers to data about enterprise operations, administration, activities, events, etc., which is generally divided into: regular data and non-regular data, the regular data being stored data with a fixed template, the non-regular data being stored data without a fixed template. In enterprises, different positions have different corresponding authorities, the data which can be transmitted, received and stored are different, and the confidentiality of different data is different. When a user needs to utilize equipment inside an enterprise to store data of the enterprise in a distributed mode, the traditional data analysis method and the traditional data storage method both need the user to manually select one or more storage objects according to the uploaded data to be stored, under the conditions of various data types and complex user rights, analysis errors and storage errors are easy to occur, and the risk of data leakage is increased.
Therefore, an artificial intelligence-based data analysis method and system thereof are urgently needed to solve the problems of low analysis, storage accuracy and security of data of enterprises with various data types and complex user rights.
Disclosure of Invention
The application aims to provide a data analysis method and a system based on artificial intelligence, which can automatically analyze and automatically store data to be stored through a constructed storage frame, so that the condition of data leakage caused by analysis errors and storage errors is avoided, and the accuracy and the safety of data analysis and data storage are improved.
In order to achieve the above object, the present application provides an artificial intelligence based data analysis method, comprising the steps of: s1: receiving a storage request of a user node, wherein the storage request at least comprises: request time, request number, user name, user password, and device ID; s2: performing reliability verification according to the storage request to obtain a reliability verification result, wherein the reliability verification result is reliable or unreliable; if the reliability verification result is reliable, receiving data to be stored, and executing S3; if the reliability verification result is unreliable, ending the flow and generating alarm information; s3: automatically analyzing data to be stored according to a pre-constructed storage frame to obtain a storage strategy; wherein, the storage frame includes at least: a plurality of user nodes; a user node corresponds to a template data packet, each template data packet comprises a plurality of template data, and one template data corresponds to one or a plurality of transmission objects; a user node corresponds to a node name and a node ID; one template data corresponds to a plurality of template features; s4: processing data to be stored according to a storage strategy to obtain a plurality of storage sub-data, and storing the plurality of storage sub-data; wherein, the storage strategy at least comprises: the storage system comprises a plurality of storage nodes, a storage sequence number of each storage node and a number of segments to be segmented.
As above, the sub-steps of performing the reliability verification according to the storage request, and obtaining the reliability verification result are as follows: s21: performing user reliability verification according to the storage request to obtain a user reliability result, wherein the user reliability result is reliable or unreliable; if the user reliability result is reliable, executing S22; if the user reliability result is unreliable, generating a reliability verification result, wherein the generated reliability verification result is unreliable; s22: verifying the reliability of the equipment according to the storage request to obtain an equipment reliability result, wherein the equipment reliability result is reliable or unreliable; if the equipment reliability result is reliable, generating a reliability verification result, wherein the generated reliability verification result is reliable; if the equipment reliability result is unreliable, generating a reliability verification result, and generating the reliability verification result to be unreliable.
As above, the sub-steps of performing the device reliability verification according to the storage request and obtaining the device reliability result are as follows: s221: generating an acquisition instruction according to the equipment ID, and sending the acquisition instruction to a corresponding user node and a corresponding acquisition subsystem, wherein the acquisition instruction at least comprises: executing an object, collecting the object and collecting a target; s222: receiving equipment data obtained after executing an acquisition instruction, wherein the equipment data at least comprises: energy consumption data and various safety data; s223: analyzing the equipment data to obtain an equipment safety value; s224: analyzing the equipment safety value according to the equipment safety threshold value to generate an equipment reliability result, and if the equipment safety value is greater than or equal to the equipment safety threshold value, generating the equipment reliability result to be reliable; if the device security value is less than the device security threshold, the generated device reliability result is unreliable.
As above, the expression of the device security value is as follows:；
Wherein, Is a device security value; /(I)For/>The impact weight corresponding to the seed safety data; /(I)For/>Secure data,/>，/>Is the total number of security data; /(I)Is energy consumption data; /(I)The energy consumption time for generating the energy consumption data for the user node; /(I)The actual unit energy consumption of the user node; /(I)The unit energy consumption of the preset user node in the normal operation state is obtained.
As above, the sub-steps of automatically analyzing the data to be stored according to the pre-constructed storage frame to obtain the storage policy are as follows: s31: traversing a plurality of user nodes in the storage frame according to the user names and the equipment IDs, determining that the node names are the same as the user names, and taking the user nodes with the same node IDs as the equipment IDs as request nodes; s32: analyzing the data to be stored by using a template data packet of the request node, and determining a plurality of transmission nodes; s33: carrying out node security analysis on each transmission node to obtain node fault probability, analyzing the node fault probability according to a preset fault probability threshold, and taking the transmission node with the node fault probability smaller than or equal to the fault probability threshold as a storage node; s34: generating a storage sequence number for each storage node according to the random sequence, and sequentially increasing the storage sequence numbers according to the random sequence; s35: and generating the number of the segments to be segmented according to the storage sequence numbers, and taking the storage sequence numbers of the storage nodes and each storage node and the number of the segments to be segmented as a storage strategy.
As above, the sub-steps of analyzing the data to be stored using the template packet of the requesting node, and determining the plurality of transmitting nodes are as follows: s321: extracting features of data to be stored to obtain a plurality of main features; s322: analyzing the plurality of main features with a plurality of template features of each template data in the template data packet respectively to obtain a similarity value; s323: judging each similarity value according to a preset similarity threshold, and if the similarity value which is larger than or equal to the similarity threshold is not available in the plurality of similarity values, executing S324; if one or more similarity values larger than or equal to a similarity threshold exist in the similarity values, template data corresponding to the maximum value in all the similarity values are used as a target template, and one or more transmission objects corresponding to the target template are used as transmission nodes; s324: generating a selection request according to a plurality of user nodes of the storage framework, sending the selection request to a request node, receiving a selection result sent by the request node after executing the selection request, and taking one or more user nodes in the selection result as transmission nodes.
As above, the expression of the number of segments to be segmented is: ; wherein/> The number of the segments to be segmented; Is a positive integer; /(I) To store the total number of sequence numbers.
As above, the sub-steps of performing the user reliability verification according to the storage request and obtaining the user reliability result are as follows: s211: traversing the user database according to the equipment ID, and taking the user data packet with the registered equipment ID identical to the equipment ID as pre-verification user data; s212: analyzing the user name and the user password according to the pre-verification user data to generate a first pre-verification result, wherein the first pre-verification result is reliable or unreliable; if the user name is consistent with the registered name in the pre-verification user data, the user password is consistent with the registered password in the pre-verification user data, the generated first pre-verification result is reliable, and S213 is executed; if the user name and/or the user password are inconsistent with the registration name and/or the registration password in the pre-verification user data, the generated first pre-verification result is unreliable, and S215 is executed; s213: judging the request times according to the pre-verification user data to generate a second pre-verification result, wherein the second pre-verification result is reliable or unreliable; if the number of requests is equal to the preset number of requests in the pre-verification user data, zeroing the sequence number of the number of requests and executing S215; if the number of requests is smaller than the preset number of requests in the pre-verification user data, executing S214; s214: acquiring a card punching time range according to a user name, analyzing the request time according to the card punching time range, and directly generating a user reliability result if the request time belongs to the card punching time range, wherein the user reliability result is reliable; if the request time does not belong to the time range of punching, executing S215; s215: randomly selecting one or more biological verification methods as a current biological verification method, collecting real-time biological data according to the current biological verification method, and extracting features of the real-time biological data to obtain biological features to be verified; s216: analyzing the biological characteristics to be verified by utilizing the biological characteristics in the user data packet, and if the biological characteristics are the same as the biological characteristics to be verified, generating a user reliability result to be reliable; if the biological characteristics are different from the biological characteristics to be verified, the generated user reliability result is unreliable.
As above, the biological verification method at least comprises: iris verification method, video verification method, audio verification method, and fingerprint verification method.
The application also provides a data analysis system based on artificial intelligence, which at least comprises: a plurality of user nodes, a plurality of acquisition subsystems and an artificial intelligence analysis center; one user node corresponds to one acquisition subsystem; wherein, the user node: for sending a storage request; and an acquisition subsystem: the system comprises an artificial intelligent analysis center, a user node, a device data acquisition module and a data acquisition module, wherein the artificial intelligent analysis center is used for receiving and executing an acquisition instruction sent by the artificial intelligent analysis center, acquiring the data of the user node, and sending the device data to the artificial intelligent analysis center; artificial intelligence analysis center: for performing the artificial intelligence based data analysis method described above.
According to the application, the data to be stored can be automatically analyzed and stored through the constructed storage frame, so that the condition of data leakage caused by analysis errors and storage errors is avoided, and the accuracy and safety of data analysis and data storage are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a schematic diagram of an embodiment of an artificial intelligence based data analysis system;
FIG. 2 is a flow chart of one embodiment of an artificial intelligence based data analysis method.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the present application provides an artificial intelligence based data analysis system, at least comprising: a plurality of user nodes 110, a plurality of acquisition subsystems 120, and an artificial intelligence analysis center 130; one user node 110 corresponds to one acquisition subsystem 120.
Wherein the user node 110: for sending a storage request.
The acquisition subsystem 120: the system is used for receiving and executing the acquisition instruction sent by the artificial intelligence analysis center 130, acquiring data of the user node 110, obtaining device data, and sending the device data to the artificial intelligence analysis center 120.
Artificial intelligence analysis center 130: for performing the artificial intelligence based data analysis method described below.
Further, the artificial intelligence analysis center 130 includes at least: the device comprises a receiving and transmitting unit, a verification unit, an analysis unit and a storage unit.
Wherein, the receiving and transmitting unit: receiving a storage request of a user node and sending the storage request to a verification unit; and sending alarm information to the user node.
And a verification unit: performing reliability verification according to the storage request to obtain a reliability verification result, and if the reliability verification result is reliable, receiving data to be stored and sending the data to be stored to an analysis unit; if the reliability verification result is unreliable, ending the flow, generating alarm information and sending the alarm information to the receiving and transmitting unit.
Analysis unit: automatically analyzing data to be stored according to a pre-constructed storage frame to obtain a storage strategy; and processing the data to be stored according to the storage strategy to obtain a plurality of storage sub-data, and storing the plurality of storage sub-data.
And a storage unit: for storing a user database comprising a plurality of user data packages, each user data package comprising at least: the registration name, the registration password, the preset request times and a plurality of biological characteristics, wherein the plurality of biological characteristics at least comprise: iris features, voiceprint features, head portrait features, and fingerprint features; a user data packet corresponds to a registered device ID; for storing a plurality of storage frames.
In particular, an enterprise corresponds to at least one storage frame, and the application is preferably one.
As shown in fig. 2, the present application provides a data analysis method based on artificial intelligence, comprising the steps of:
s1: receiving a storage request of a user node, wherein the storage request at least comprises: request time, number of requests, user name, user password, and device ID.
Specifically, the request time is a time node at which the user node sends a storage request.
User name: and a user node corresponds to a user name for the name of the user corresponding to the user node.
User password: for a user password corresponding to a user name, one user name corresponds to one user password.
Device ID: is the ID of the device of the user node.
Number of requests: the number of the storage requests is sent out for the user node this time, and the number of the requests of this time=the number of the last requests+1.
S2: performing reliability verification according to the storage request to obtain a reliability verification result, wherein the reliability verification result is reliable or unreliable; if the reliability verification result is reliable, receiving data to be stored, and executing S3; if the result of the reliability verification is unreliable, ending the flow and generating alarm information.
Further, the sub-steps of performing reliability verification according to the storage request and obtaining the reliability verification result are as follows:
S21: performing user reliability verification according to the storage request to obtain a user reliability result, wherein the user reliability result is reliable or unreliable; if the user reliability result is reliable, executing S22; if the user reliability result is unreliable, generating a reliability verification result, and generating the reliability verification result to be unreliable.
Specifically, the alarm information includes at least: alert time and reliability verification results.
Further, the sub-steps of performing user reliability verification according to the storage request and obtaining the user reliability result are as follows:
S211: traversing the user database according to the equipment ID, and taking the user data packet with the registered equipment ID identical to the equipment ID as pre-verification user data.
S212: analyzing the user name and the user password according to the pre-verification user data to generate a first pre-verification result, wherein the first pre-verification result is reliable or unreliable; if the user name is consistent with the registered name in the pre-verification user data, the user password is consistent with the registered password in the pre-verification user data, the generated first pre-verification result is reliable, and S213 is executed; if the user name and/or user password are not consistent with the registration name and/or registration password in the pre-verification user data, the generated first pre-verification result is unreliable, and S215 is executed.
S213: judging the request times according to the pre-verification user data to generate a second pre-verification result, wherein the second pre-verification result is reliable or unreliable; if the number of requests is equal to the preset number of requests in the pre-verification user data, zeroing the sequence number of the number of requests and executing S215; if the number of requests is smaller than the preset number of requests in the pre-verification user data, S214 is executed.
Specifically, the specific value of the preset request times is determined according to the actual situation, when the request times in the current storage request is equal to the preset request times, the preset nodes needing to be subjected to biological verification are indicated to be reached, and the biological verification is performed according to the preset request times, so that the user safety can be effectively improved. Zeroing the sequence number of requests refers to: the number of requests for next transmission of a storage request=0+1.
S214: acquiring a card punching time range according to a user name, analyzing the request time according to the card punching time range, and directly generating a user reliability result if the request time belongs to the card punching time range, wherein the user reliability result is reliable; if the request time does not belong to the punch time range, S215 is performed.
Further, the expression of the time range of punching card is:；
Wherein, For/>The working time of the standard time range of checking card of the job position of the nature; /(I)Is the firstThe off-duty card punching time of the standard card punching time range of the job position with the nature; /(I)To shift the card-punching time forward/>User node/>, obtained after a time periodAn actual start value of the punch time range; /(I)To shift the off duty card punching time backward/>User node/>, obtained after a time periodIs the actual end value of the punch time range.
Wherein,
；
；
Wherein,For user node/>First/>The time length of the day is earlier than the working card punching time; /(I)For user node/>First/>The time period is later than the off-duty card punching time; /(I)，/>Total days for punching.
Specifically, in enterprises, the time of the regular daily time punch corresponding to the positions with different properties is different, so that each position with different properties corresponds to a standard punch time range.
Different users in the same-nature job position also have the condition that the time of daily card punching is different, so that the actual card punching time range of the user corresponding to each user name is collected as the card punching time range, and the card punching time range is larger than or equal to the standard card punching time range. One user corresponds to one user node and one user name.
S215: randomly selecting one or more biological verification methods as a current biological verification method, collecting real-time biological data according to the current biological verification method, and extracting features of the real-time biological data to obtain biological features to be verified.
Further, the biological verification method at least comprises: iris verification method, video verification method, audio verification method, and fingerprint verification method.
Specifically, feature extraction of the real-time biological data can be completed through the existing feature extraction model or the existing artificial intelligence technology, so that the biological feature to be verified is obtained.
S216: analyzing the biological characteristics to be verified by utilizing the biological characteristics in the user data packet, and if the biological characteristics are the same as the biological characteristics to be verified, generating a user reliability result to be reliable; if the biological characteristics are different from the biological characteristics to be verified, the generated user reliability result is unreliable.
Specifically, analysis of the biological characteristics and the biological characteristics to be verified can be realized through a pre-constructed neural network or artificial intelligent analysis model, so that whether the biological characteristics and the biological characteristics to be verified are identical is judged.
S22: verifying the reliability of the equipment according to the storage request to obtain an equipment reliability result, wherein the equipment reliability result is reliable or unreliable; if the equipment reliability result is reliable, generating a reliability verification result, wherein the generated reliability verification result is reliable; if the equipment reliability result is unreliable, generating a reliability verification result, and generating the reliability verification result to be unreliable.
Further, the device reliability verification is performed according to the storage request, and the sub-steps of obtaining the device reliability result are as follows:
s221: generating an acquisition instruction according to the equipment ID, and sending the acquisition instruction to a corresponding user node and a corresponding acquisition subsystem, wherein the acquisition instruction at least comprises: executing an object, collecting the object and collecting the target.
Specifically, the artificial intelligence analysis center generates an acquisition instruction according to the equipment ID, and sends the acquisition instruction to the corresponding user node and the corresponding acquisition subsystem. One device ID corresponds to one user node and one user node corresponds to one acquisition subsystem.
The execution object is an acquisition subsystem for acquiring equipment data of the acquisition object.
The acquisition object is a user node needing to acquire equipment data, namely: the device ID corresponds to the device.
The acquisition target is specific content of equipment data to be acquired, and at least comprises the following steps: energy consumption data and various safety data.
S222: receiving equipment data obtained after executing an acquisition instruction, wherein the equipment data at least comprises: energy consumption data and various safety data.
Wherein the security data comprises at least: hardware security data, software security data, and network security data.
Specifically, the hardware security data is a security value of equipment hardware of the user node, which is acquired in real time according to the acquisition instruction, and is used for indicating the current hardware security of the user node. The hardware security data can be obtained through the existing acquisition mode.
The software security data is the security value of the software of the user node acquired in real time according to the acquisition instruction and is used for representing the current software security of the user node. The value of the software security data can be obtained through the existing acquisition mode.
The network security data is a network security value of the management user terminal, which is acquired in real time according to the acquisition instruction, and is used for representing the current network security of the user node. The value of the network security data can be obtained through the existing acquisition mode.
The energy consumption data is the actual power consumption of the user node acquired in real time according to the acquisition instruction.
S223: and analyzing the equipment data to obtain an equipment safety value.
Further, the expression of the device security value is as follows:
；
In particular, the method comprises the steps of, Is a device security value; /(I)For/>The impact weight corresponding to the seed safety data; /(I)Is the firstSecure data,/>，/>Is the total number of security data; /(I)Is energy consumption data; /(I)The energy consumption time for generating the energy consumption data for the user node; /(I)The actual unit energy consumption of the user node; /(I)The unit energy consumption of the preset user node in the normal operation state is obtained.
Specifically, the specific value of the unit energy consumption of the preset user node in the normal running state is set according to the actual equipment model. The corresponding influence weight of each kind of safety data is preset, and the specific value of the influence weight is determined according to the actual situation and is used for indicating the influence degree of the safety data on the user node. By considering the value of the security data of the user node and the energy consumption difference value at the same time, the accuracy of the analyzed security condition of the equipment can be further ensured.
S224: analyzing the equipment safety value according to the equipment safety threshold value to generate an equipment reliability result, and if the equipment safety value is greater than or equal to the equipment safety threshold value, generating the equipment reliability result to be reliable; if the device security value is less than the device security threshold, the generated device reliability result is unreliable.
Specifically, the specific value of the device safety threshold is set according to the actual situation.
S3: automatically analyzing data to be stored according to a pre-constructed storage frame to obtain a storage strategy, wherein the storage frame at least comprises: a plurality of user nodes; a user node corresponds to a template data packet, each template data packet comprises a plurality of template data, and one template data corresponds to one or a plurality of transmission objects; a user node corresponds to a node name and a node ID; one template data corresponds to a plurality of template features.
Specifically, the transmission object is: user nodes that receive and/or store stored data.
Further, according to the pre-constructed storage frame, the data to be stored is automatically analyzed, and the sub-steps of obtaining the storage strategy are as follows:
S31: traversing the plurality of user nodes in the storage frame according to the user names and the equipment IDs, determining that the node names are the same as the user names, and taking the user nodes with the same node IDs as the equipment IDs as request nodes.
S32: and analyzing the data to be stored by using the template data packet of the request node, and determining a plurality of transmission nodes.
Further, the sub-steps of analyzing the data to be stored by using the template data packet of the requesting node and determining the plurality of transmission nodes are as follows:
s321: and extracting the characteristics of the data to be stored to obtain a plurality of main characteristics.
Further, feature extraction is performed on the data to be stored through a pre-trained feature extraction model or an existing artificial intelligence technology, and a plurality of main features are obtained.
Specifically, the main feature is a feature of an editing template capable of indicating data to be stored, for example: format features and title features.
S322: and analyzing the plurality of main features with a plurality of template features of each template data in the template data packet respectively to obtain a similarity value.
Specifically, the similarity value between a plurality of main features and a plurality of template features of each template data is obtained by the existing feature similarity calculation method, and the larger the similarity value is, the higher the similarity between the data to be stored and the template data is, namely: the template data with the largest similarity value with the data to be stored is the text template used by the data to be stored.
S323: judging each similarity value according to a preset similarity threshold, and if the similarity value which is larger than or equal to the similarity threshold is not available in the plurality of similarity values, executing S324; if one or more similarity values larger than or equal to the similarity threshold exist in the similarity values, template data corresponding to the maximum value in all the similarity values is used as a target template, and one or more transmission objects corresponding to the target template are used as transmission nodes.
Specifically, if one or more similar values greater than or equal to the similar threshold value exist in the plurality of similar values, the data to be stored is conventional data written by adopting a fixed template.
If the plurality of similarity values have no similarity value which is larger than or equal to the similarity threshold value, the data to be stored is the non-conventional data written by adopting the non-fixed template.
S324: generating a selection request according to a plurality of user nodes of the storage framework, sending the selection request to a request node, receiving a selection result sent by the request node after executing the selection request, and taking one or more user nodes in the selection result as transmission nodes.
Specifically, the selection request includes at least: a plurality of user nodes in a storage framework.
The selection result at least comprises: one or more user nodes are custom selected from a plurality of user nodes of the storage framework.
S33: and carrying out node security analysis on each transmission node to obtain node fault probability, analyzing the node fault probability according to a preset fault probability threshold, and taking the transmission node with the node fault probability smaller than or equal to the fault probability threshold as a storage node.
Further, the expression of the node failure probability is as follows:
；
Wherein, For/>Node failure probabilities of the individual transmission nodes; /(I)Storing impact weights for the data; /(I)Influencing the weight for data transmission; /(I)To request node to send the/>Total number of stored sub-data of the individual transmission nodes; for/> The total number of the stored sub-data successfully completed by the transmission nodes; /(I)Transmits for the requesting node the firstTotal amount of transmission data of the transmission nodes; /(I)For/>The total number of transmission data successfully received by each transmission node.
In particular, the transmission data includes storage sub data and other kinds of data other than the storage sub data, for example: public announcement information and group files.
Data storage impact weightThe specific value of (2) is determined according to the actual situation, and is used for representing the influence degree of the probability of failure when the transmission node performs data storage.
Data transmission impact weightThe specific value of (2) is determined according to the actual situation, and is used for representing the influence degree of the probability of failure when the transmission node receives the data.
The specific value of the failure probability threshold value depends on the actual situation. If the node fault probability is smaller than or equal to the fault probability threshold, the transmission node corresponding to the node fault probability is used as a storage node, and if the node fault probability is larger than the fault probability threshold, the transmission node corresponding to the node fault probability is removed, and a fault warning is sent, so that equipment of the transmission node can be overhauled and/or replaced conveniently.
S34: a storage sequence number is generated for each storage node in a random order, and the storage sequence numbers are sequentially incremented in the random order.
Specifically, one storage node corresponds to one storage sequence number. The storage sequence number of the storage node with the random sequence of the first is 1, the storage sequence number of the storage node with the random sequence of the second is 2, … …, and the storage sequence number of the storage node with the random sequence of the Mth is M.
S35: and generating the number of the segments to be segmented according to the storage sequence numbers, and taking the storage sequence numbers of the storage nodes and each storage node and the number of the segments to be segmented as a storage strategy.
Further, the expression of the number of segments to be segmented is:
；
Wherein, The number of the segments to be segmented; /(I)Is a positive integer; /(I)To store the total number of sequence numbers.
Further, the method comprises the steps of,The specific value of (2) is determined according to the actual situation, and the application is preferably/>。
S4: processing data to be stored according to a storage strategy to obtain a plurality of storage sub-data, and storing the plurality of storage sub-data, wherein the storage strategy at least comprises: the storage system comprises a plurality of storage nodes, a storage sequence number of each storage node and a number of segments to be segmented.
Further, the sub-steps of processing the data to be stored according to the storage policy to obtain a plurality of storage sub-data and storing the plurality of storage sub-data are as follows:
S41: dividing and numbering the data to be stored according to the number of the segments to be divided in the storage strategy to obtain a plurality of storage sub-data, wherein one storage sub-data corresponds to one data number, and the data numbers are sequentially increased according to the dividing sequence.
Specifically, the dividing sequence is a sequence in which one piece of data to be stored is read from top to bottom in sequence normally after the data to be stored is opened. The data number of the storage sub data of the first division order is 1, the data number of the storage sub data of the second division order is 2, … …, and the data number of the storage sub data of the division order is W.
S42: dividing the storage sub data into a plurality of groups of storage data according to the sequence from small data numbers to large data numbers, wherein the total number of the storage sub data included in one group of storage data is equal to the total number of the storage nodes.
S43: and respectively transmitting the plurality of storage sub-data in each group of storage data to a plurality of storage nodes for storage, and enabling the data numbers of the storage sub-data to be respectively in one-to-one correspondence with the storage sequence numbers of the storage nodes from small to large according to the sequence from small to large.
Specifically, the data numbers of the storage sub data are respectively corresponding to the storage sequence numbers of the storage nodes from small to large one by one according to the sequence from small to large, namely: the storage sub-data with the smallest data number in each group of storage data is stored in the storage node with the smallest storage sequence number, and the storage sub-data with the largest data number in each group of storage data is stored in the storage node with the largest storage sequence number.
Further, the sub-steps of processing the data to be stored according to the storage policy to obtain a plurality of storage sub-data, and storing the plurality of storage sub-data further include: s44: after all the storage sub-data are stored, search information is generated according to a storage strategy, the search information is sent to a request node, and the request node directly sends the search information to a corresponding search node through an internal channel, so that the search node can acquire the storage sub-data according to the search information.
Specifically, the retrieval node is one or more of the storage nodes.
The search information includes at least: the splitting order and the fetch address of the storage sub-data.
After the retrieval node obtains the corresponding storage sub-data according to the obtaining address of the storage sub-data, the retrieval node can obtain complete and accurate retrieval data (namely, the data to be stored uploaded by the request node) according to the segmentation sequence.
Furthermore, the internal channel of the enterprise is not connected with the external channel and/or the external network, so that the security of transmitting the search information can be improved.
According to the application, the data to be stored can be automatically analyzed and stored through the constructed storage frame, so that the condition of data leakage caused by analysis errors and storage errors is avoided, and the accuracy and safety of data analysis and data storage are improved.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the scope of the application be interpreted as including the preferred embodiments and all alterations and modifications that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the technical equivalents thereof, the present application is also intended to include such modifications and variations.
Claims (8)
1. The data analysis method based on artificial intelligence is characterized by comprising the following steps:
S1: receiving a storage request of a user node, wherein the storage request at least comprises: request time, request number, user name, user password, and device ID;
S2: performing reliability verification according to the storage request to obtain a reliability verification result, wherein the reliability verification result is reliable or unreliable; if the reliability verification result is reliable, receiving data to be stored, and executing S3; if the reliability verification result is unreliable, ending the flow and generating alarm information;
S3: automatically analyzing data to be stored according to a pre-constructed storage frame to obtain a storage strategy; wherein, the storage frame includes at least: a plurality of user nodes; a user node corresponds to a template data packet, each template data packet comprises a plurality of template data, and one template data corresponds to one or a plurality of transmission objects; a user node corresponds to a node name and a node ID; one template data corresponds to a plurality of template features;
S4: processing data to be stored according to a storage strategy to obtain a plurality of storage sub-data, and storing the plurality of storage sub-data; wherein, the storage strategy at least comprises: the storage nodes, the storage sequence number of each storage node and the number of segments to be segmented;
The sub-steps of the reliability verification according to the storage request are as follows:
S21: performing user reliability verification according to the storage request to obtain a user reliability result, wherein the user reliability result is reliable or unreliable; if the user reliability result is reliable, executing S22; if the user reliability result is unreliable, generating a reliability verification result, wherein the generated reliability verification result is unreliable;
S22: verifying the reliability of the equipment according to the storage request to obtain an equipment reliability result, wherein the equipment reliability result is reliable or unreliable; if the equipment reliability result is reliable, generating a reliability verification result, wherein the generated reliability verification result is reliable; if the equipment reliability result is unreliable, generating a reliability verification result, wherein the generated reliability verification result is unreliable;
Wherein, according to the storage frame constructed in advance, carry on the automatic analysis to the data to be stored, the substeps to obtain the storage policy are as follows:
S31: traversing a plurality of user nodes in the storage frame according to the user names and the equipment IDs, determining that the node names are the same as the user names, and taking the user nodes with the same node IDs as the equipment IDs as request nodes;
s32: analyzing the data to be stored by using a template data packet of the request node, and determining a plurality of transmission nodes;
s33: carrying out node security analysis on each transmission node to obtain node fault probability, analyzing the node fault probability according to a preset fault probability threshold, and taking the transmission node with the node fault probability smaller than or equal to the fault probability threshold as a storage node;
s34: generating a storage sequence number for each storage node according to the random sequence, and sequentially increasing the storage sequence numbers according to the random sequence;
S35: and generating the number of the segments to be segmented according to the storage sequence numbers, and taking the storage sequence numbers of the storage nodes and each storage node and the number of the segments to be segmented as a storage strategy.
2. The artificial intelligence based data analysis method of claim 1, wherein the sub-steps of performing device reliability verification based on the storage request to obtain a device reliability result are as follows:
S221: generating an acquisition instruction according to the equipment ID, and sending the acquisition instruction to a corresponding user node and a corresponding acquisition subsystem, wherein the acquisition instruction at least comprises: executing an object, collecting the object and collecting a target;
S222: receiving equipment data obtained after executing an acquisition instruction, wherein the equipment data at least comprises: energy consumption data and various safety data;
S223: analyzing the equipment data to obtain an equipment safety value;
S224: analyzing the equipment safety value according to the equipment safety threshold value to generate an equipment reliability result, and if the equipment safety value is greater than or equal to the equipment safety threshold value, generating the equipment reliability result to be reliable; if the device security value is less than the device security threshold, the generated device reliability result is unreliable.
3. The artificial intelligence based data analysis method of claim 2, wherein the expression of the device security value is as follows:
；
Wherein, Is a device security value; /(I)For/>The impact weight corresponding to the seed safety data; /(I)For/>Secure data,/>，/>Is the total number of security data; /(I)Is energy consumption data; /(I)The energy consumption time for generating the energy consumption data for the user node; /(I)The actual unit energy consumption of the user node; /(I)The unit energy consumption of the preset user node in the normal operation state is obtained.
4. The artificial intelligence based data analysis method of claim 1, wherein the sub-steps of analyzing the data to be stored using template packets of the requesting node, determining the plurality of transmitting nodes are as follows:
s321: extracting features of data to be stored to obtain a plurality of main features;
s322: analyzing the plurality of main features with a plurality of template features of each template data in the template data packet respectively to obtain a similarity value;
S323: judging each similarity value according to a preset similarity threshold, and if the similarity value which is larger than or equal to the similarity threshold is not available in the plurality of similarity values, executing S324; if one or more similarity values larger than or equal to a similarity threshold exist in the similarity values, template data corresponding to the maximum value in all the similarity values are used as a target template, and one or more transmission objects corresponding to the target template are used as transmission nodes;
S324: generating a selection request according to a plurality of user nodes of the storage framework, sending the selection request to a request node, receiving a selection result sent by the request node after executing the selection request, and taking one or more user nodes in the selection result as transmission nodes.
5. The artificial intelligence based data analysis method of claim 4, wherein the expression of the number of segments to be segmented is:
；
Wherein, The number of the segments to be segmented; /(I)Is a positive integer; /(I)To store the total number of sequence numbers.
6. The artificial intelligence based data analysis method of claim 1, wherein the sub-steps of performing user reliability verification based on the storage request to obtain the user reliability result are as follows:
s211: traversing the user database according to the equipment ID, and taking the user data packet with the registered equipment ID identical to the equipment ID as pre-verification user data;
S212: analyzing the user name and the user password according to the pre-verification user data to generate a first pre-verification result, wherein the first pre-verification result is reliable or unreliable; if the user name is consistent with the registered name in the pre-verification user data, the user password is consistent with the registered password in the pre-verification user data, the generated first pre-verification result is reliable, and S213 is executed; if the user name and/or the user password are inconsistent with the registration name and/or the registration password in the pre-verification user data, the generated first pre-verification result is unreliable, and S215 is executed;
S213: judging the request times according to the pre-verification user data to generate a second pre-verification result, wherein the second pre-verification result is reliable or unreliable; if the number of requests is equal to the preset number of requests in the pre-verification user data, zeroing the sequence number of the number of requests and executing S215; if the number of requests is smaller than the preset number of requests in the pre-verification user data, executing S214;
S214: acquiring a card punching time range according to a user name, analyzing the request time according to the card punching time range, and directly generating a user reliability result if the request time belongs to the card punching time range, wherein the user reliability result is reliable; if the request time does not belong to the time range of punching, executing S215;
S215: randomly selecting one or more biological verification methods as a current biological verification method, collecting real-time biological data according to the current biological verification method, and extracting features of the real-time biological data to obtain biological features to be verified;
s216: analyzing the biological characteristics to be verified by utilizing the biological characteristics in the user data packet, and if the biological characteristics are the same as the biological characteristics to be verified, generating a user reliability result to be reliable; if the biological characteristics are different from the biological characteristics to be verified, the generated user reliability result is unreliable.
7. The artificial intelligence based data analysis method of claim 6, wherein the biometric verification method comprises at least: iris verification method, video verification method, audio verification method, and fingerprint verification method.
8. An artificial intelligence based data analysis system comprising at least: a plurality of user nodes, a plurality of acquisition subsystems and an artificial intelligence analysis center; one user node corresponds to one acquisition subsystem;
wherein, the user node: for sending a storage request;
And an acquisition subsystem: the system comprises an artificial intelligent analysis center, a user node, a device data acquisition module and a data acquisition module, wherein the artificial intelligent analysis center is used for receiving and executing an acquisition instruction sent by the artificial intelligent analysis center, acquiring the data of the user node, and sending the device data to the artificial intelligent analysis center;
Artificial intelligence analysis center: for performing the artificial intelligence based data analysis method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410413347.2A CN118018330B (en) | 2024-04-08 | 2024-04-08 | Data analysis method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410413347.2A CN118018330B (en) | 2024-04-08 | 2024-04-08 | Data analysis method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118018330A CN118018330A (en) | 2024-05-10 |
| CN118018330B true CN118018330B (en) | 2024-06-11 |
Family
ID=90943285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410413347.2A Active CN118018330B (en) | 2024-04-08 | 2024-04-08 | Data analysis method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118018330B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377850A (en) * | 2021-06-09 | 2021-09-10 | 深圳前海墨斯科技有限公司 | Big data technology platform of cognitive Internet of things |
| WO2021223025A1 (en) * | 2020-05-04 | 2021-11-11 | 10644137 Canada Inc. | Artificial-intelligence-based e-commerce system and method for manufacturers, suppliers, and purchasers |
| WO2021248143A2 (en) * | 2020-06-05 | 2021-12-09 | Supinger Kevin Scott | Sensor multistage data concentration |
| CN113780990A (en) * | 2021-09-07 | 2021-12-10 | 江苏波瑞电气有限公司 | Cloud intelligence manufacturing platform based on artificial intelligence production management mode and processing method |
| CN114840770A (en) * | 2022-07-04 | 2022-08-02 | 睿至科技集团有限公司 | Management method and system based on big data |
| CN115952211A (en) * | 2023-03-14 | 2023-04-11 | 天云融创数据科技（北京）有限公司 | Data processing method and system based on artificial intelligence |
| CN116992346A (en) * | 2023-08-08 | 2023-11-03 | 安徽米乐信息科技有限公司 | Enterprise production data processing system based on artificial intelligence big data analysis |
-
2024
- 2024-04-08 CN CN202410413347.2A patent/CN118018330B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021223025A1 (en) * | 2020-05-04 | 2021-11-11 | 10644137 Canada Inc. | Artificial-intelligence-based e-commerce system and method for manufacturers, suppliers, and purchasers |
| WO2021248143A2 (en) * | 2020-06-05 | 2021-12-09 | Supinger Kevin Scott | Sensor multistage data concentration |
| CN113377850A (en) * | 2021-06-09 | 2021-09-10 | 深圳前海墨斯科技有限公司 | Big data technology platform of cognitive Internet of things |
| CN113780990A (en) * | 2021-09-07 | 2021-12-10 | 江苏波瑞电气有限公司 | Cloud intelligence manufacturing platform based on artificial intelligence production management mode and processing method |
| CN114840770A (en) * | 2022-07-04 | 2022-08-02 | 睿至科技集团有限公司 | Management method and system based on big data |
| CN115952211A (en) * | 2023-03-14 | 2023-04-11 | 天云融创数据科技（北京）有限公司 | Data processing method and system based on artificial intelligence |
| CN116992346A (en) * | 2023-08-08 | 2023-11-03 | 安徽米乐信息科技有限公司 | Enterprise production data processing system based on artificial intelligence big data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118018330A (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109564641B (en) | Data filling method and device | |
| CN111818198B (en) | Domain name detection method, domain name detection device, equipment and medium | |
| CN106650799A (en) | Electronic evidence classification extraction method and system | |
| WO2021218312A1 (en) | Method and apparatus for constructing service fraud identification database, and computer device | |
| CN110674790A (en) | Abnormal scene processing method and system in video monitoring | |
| CN112367273A (en) | Knowledge distillation-based flow classification method and device for deep neural network model | |
| CN111461231A (en) | Short message sending control method, device and storage medium | |
| CN111506635A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive naive Bayes algorithm | |
| CN116150651A (en) | AI-based depth synthesis detection method and system | |
| CN113158771B (en) | Community personnel information acquisition method, system and application | |
| CN118018330B (en) | Data analysis method and system based on artificial intelligence | |
| CN117592778A (en) | Risk early warning system | |
| CN112883380A (en) | Big data component safety risk analysis method and system of intelligent education platform | |
| CN115205761A (en) | Accident reason off-line intelligent diagnosis system | |
| CN115240647A (en) | Sound event detection method and device, electronic equipment and storage medium | |
| EP1264253A1 (en) | Method and arrangement for modelling a system | |
| CN113515771A (en) | Data sensitivity determination method, electronic device, and computer-readable storage medium | |
| CN111291376B (en) | Web vulnerability verification method based on crowdsourcing and machine learning | |
| CN111241139A (en) | Data statistical method, device, computer equipment and storage medium | |
| CN117911930B (en) | Data security early warning method and device based on intelligent video monitoring | |
| CN116739387B (en) | Method and device for multidimensional analysis of data and computer storage medium | |
| CN117319084B (en) | Medical examination data sharing method and system based on cloud authentication | |
| CN113723524B (en) | Data processing method based on prediction model, related equipment and medium | |
| CN114329060A (en) | Method and system for automatically generating multiple labels of video frame based on neural network model | |
| CN117077972A (en) | Matching degree detection method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |