CN111209943B

CN111209943B - Data fusion method and device and server

Info

Publication number: CN111209943B
Application number: CN201911400699.XA
Authority: CN
Inventors: 费红琳; 肖巧巧; 丁杰
Original assignee: Guangzhou Gaoqi Cloud Information Technology Co ltd
Current assignee: Guangzhou Gaoqi Cloud Information Technology Co ltd
Priority date: 2019-12-30
Filing date: 2019-12-30
Publication date: 2020-08-25
Anticipated expiration: 2039-12-30
Also published as: CN111209943A

Abstract

The invention relates to the technical field of data processing, in particular to a data fusion method, a data fusion device and a server. The invention extracts the matrix characteristic sequence and the matrix node sequence of each service data on the corresponding data conversion matrix and obtains the data fusion parameters of each incidence matrix node, thereby performing data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence and the data fusion parameters of each incidence matrix node of each service data to obtain the fusion service data. The invention represents the fusion process parameters of the incidence matrix nodes when the incidence matrix nodes are fused with other service data aiming at the service data independently through the data fusion parameters of the incidence matrix nodes, and performs data fusion of each service data, thereby realizing uniform analysis processing when analyzing the data, being convenient for analyzing the required analysis service data from the fusion service data through a uniform analysis strategy in the later period, and improving the data analysis efficiency.

Description

Data fusion method and device and server

Technical Field

The invention relates to the technical field of data processing, in particular to a data fusion method, a data fusion device and a server.

Background

When business data (for example, media data, traffic data, agricultural data, communication data, e-commerce data, industrial data and the like) collected by a data collection terminal are accessed and analyzed at present, the dimensionalities of different business data are different, uniform analysis processing is difficult to realize when the business data are analyzed, the business data are generally analyzed one by one, and therefore the business data are not convenient to analyze in a later stage by adopting a uniform analysis strategy, and the data analysis is complicated and low in efficiency.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, the present application provides a data fusion method, device and server to solve or improve the above problems.

In a first aspect, the present application provides a data fusion method applied to a server, where the server is in communication connection with a plurality of data acquisition terminals, and the server is preconfigured with a data conversion matrix corresponding to each data acquisition terminal, where the method includes:

acquiring service data respectively acquired by the data acquisition terminals, and extracting a matrix characteristic sequence and a matrix node sequence of each service data on a data conversion matrix corresponding to the corresponding data acquisition terminal, wherein the matrix characteristic sequence comprises service type confidence coefficients corresponding to each incidence matrix node of the service data in the data conversion matrix, and the matrix node sequence comprises a calculation relationship among the incidence matrix nodes;

generating data fusion parameters of each incidence matrix node according to the matrix characteristic sequence and the matrix node sequence, wherein the data fusion parameters of the incidence matrix nodes comprise fusion process parameters used for representing that the incidence matrix nodes individually participate in fusion with other service data aiming at the service data;

and performing data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence and the data fusion parameters of each incidence matrix node of each service data to obtain fusion service data.

In a possible design of the first aspect, the step of extracting a matrix characteristic sequence and a matrix node sequence of each service data on a data conversion matrix corresponding to a corresponding data acquisition terminal includes:

extracting a plurality of service conversion channels of each service data on a data conversion matrix corresponding to a corresponding data acquisition terminal;

inputting the service data into the data conversion matrix according to the plurality of service conversion channels for matrix conversion processing to obtain a plurality of matrix conversion service results with different dimensions;

for each service conversion channel in the plurality of service conversion channels, selecting a matrix conversion service result of a corresponding dimension for the service conversion channel from the matrix conversion service results of the plurality of different dimensions, judging whether the service conversion channel is matched with a preset matrix conversion template by using matrix conversion information corresponding to the matrix conversion service result, and reserving the service conversion channel when the service conversion channel is matched with the preset matrix conversion template so as to obtain a plurality of reserved service conversion channels;

inputting the service data into the data conversion matrix through the reserved service conversion channels for service conversion, acquiring a corresponding service conversion matrix node sequence and service conversion process information of a target matrix node in the service conversion matrix node sequence, and determining a service conversion interval of the target matrix node according to the service conversion process information of the target matrix node;

taking a coincidence interval of the service conversion intervals of the target matrix nodes as a service association interval, acquiring a service conversion position of each target matrix node in the service association interval, performing target matrix node recombination according to a position confidence coefficient of the service conversion position of each target matrix node to obtain corresponding candidate association matrix nodes, acquiring a service type confidence coefficient corresponding to the service data in the candidate association matrix nodes, establishing calculation relationship information between the candidate association matrix nodes and a calculation relationship according to the service type confidence coefficient, and processing each candidate association matrix node by taking the calculation relationship as a reference to determine service conversion process information corresponding to the calculation relationship information of each candidate association matrix node;

and determining each incidence matrix node in each candidate incidence matrix node according to the service conversion process information corresponding to the calculation relation information of each candidate incidence matrix node so as to obtain the service type confidence corresponding to each incidence matrix node in the data conversion matrix of the service data and the calculation relation among the incidence matrix nodes.

In a possible design of the first aspect, the step of generating the data fusion parameters of each incidence matrix node according to the matrix feature sequence and the matrix node sequence includes:

determining normalized fusion information of the business data for each incidence matrix node according to the matrix characteristic sequence and the matrix node sequence, and converting the normalized fusion information of the business data for each incidence matrix node into a normalized fusion sampling graph;

constructing a corresponding fusion data range sample map according to the normalized fusion sample map, and analyzing the constructed fusion data range sample map to obtain a plurality of fusion data range areas;

acquiring an average value of the data quantity in each fused data range area, and calculating a difference value between the data quantity in each fused data range area and the average value to obtain a data quantity determination value of each fused data range area;

classifying a plurality of fusion data range regions associated with the data quantity determination value to generate a corresponding classification fusion data range region map composed of classification combinations of the plurality of classified fusion data range regions;

selecting a fusion data range region with the largest fusion data range and a fusion data range region with the smallest fusion data range from the classified fusion data range region map as a first fusion data range region and a second fusion data range region respectively, calculating data quantity determination value differences between each fusion data range region and the first fusion data range region and the second fusion data range region respectively, allocating a fusion data range region with a data quantity determination value difference with the first fusion data range region being less than or equal to a data quantity determination value difference with the second fusion data range region to a first fusion data range region sequence, allocating a fusion data range region with a data quantity determination value difference with the first fusion data range region being greater than a data quantity determination value difference with the second fusion data range region to a second fusion data range region sequence A sequence of data range regions;

calculating an average of the data quantity determination values of all the fusion data range regions in the first fusion data range region sequence, obtaining a first fusion data range region with the average of the actual data quantity determination values as a region, calculating an average of the data quantity determination values of all the fusion data range regions in the second fusion data range region sequence, and obtaining a second fusion data range region with the average of the actual data quantity determination values as a region;

determining a plurality of corresponding third fusion data range regions and a plurality of corresponding fourth fusion data range regions according to the contact ratio of the first fusion data range region and the second fusion data range region to each fusion data range region in the classified fusion data range region diagram;

according to the plurality of third fusion data range areas and the plurality of fourth fusion data range areas, determining normalization fusion parameter information corresponding to the normalization fusion information, and analyzing the normalization fusion parameter information to obtain normalization fusion process control information in the normalization fusion parameter information;

and determining a fusion affine transformation range of the normalized fusion process control information as a fusion affine transformation range corresponding to the incidence matrix node, and determining fusion process parameters of the incidence matrix node when the incidence matrix node participates in fusion with other service data independently according to the fusion affine transformation range corresponding to the incidence matrix node and the normalized fusion process control information.

In a possible design of the first aspect, the step of performing data fusion on each service data according to the matrix feature sequence, the matrix node sequence, and the data fusion parameters of each incidence matrix node of each service data to obtain fused service data includes:

determining fusion matrix information of each service data according to the matrix characteristic sequence and the matrix node sequence of each service data, and determining fusion matrix nodes corresponding to each service data according to the fusion matrix information;

acquiring a data fusion strategy of a fusion matrix node corresponding to each service data from a data fusion parameter of each incidence matrix node, wherein the data fusion strategy is used for expressing fusion participation information of the fusion matrix node;

establishing a mapping relation between the fusion matrix node and a fusion participation position according to the data fusion strategy;

determining a plurality of position association states of each data recording position in each service data according to the established mapping relation between the fusion matrix node and the fusion participation position, acquiring a matching relation between a state recording value of the corresponding position association state of the data recording position of other service data matched with each data recording position and a state recording value of the corresponding position association state of a preset number of data recording positions behind each data recording position aiming at each position association state, and acquiring fusion participation state configuration information of each data recording position at the position association state according to the matching relation so as to acquire fusion participation state configuration information of each data recording position;

acquiring the fusion control state of each data recording position in the fusion process according to the fusion participation state configuration information of each data recording position;

obtaining a plurality of control feature sequences corresponding to each data recording position according to the fusion control state, and determining first control feature information and second control feature information of the plurality of control feature sequences, wherein the first control feature information comprises the control feature information when the fusion control state of each data recording position is in an open state, and the second control feature information comprises the control feature information when the fusion control state of each data recording position is in a closed state;

determining the position sequence of the first control feature information in the control feature sequence, determining a fusion participation level of the first control feature information according to the position sequence, determining a fusion project sequence corresponding to the control feature sequence of the fusion participation position corresponding to each data recording position according to the fusion participation level, and calculating fusion project features corresponding to the fusion project sequence, wherein the fusion project sequence is determined according to the fusion project record information generated based on a fusion part and corresponding to the control feature sequence of the fusion participation position corresponding to the data recording position in the fusion process, and the fusion project record information corresponding to different fusion parts is different;

acquiring a matching degree lower limit corresponding to a fusion participation position corresponding to each data recording position, and determining a mapping relation between the fusion project sequence and the matching degree lower limit according to the fusion project characteristics;

determining a plurality of fusion items at each data recording position and a fusion sequence corresponding to each fusion item from the fusion item sequence according to the determined mapping relation between the fusion item sequence and the lower limit of the matching degree;

screening a plurality of fusion items with the same preset fusion sequence from the plurality of fusion items to obtain a plurality of first fusion items, and taking the fusion items except the first fusion items from the plurality of fusion items as second fusion items;

determining the fusion interval number aiming at each data recording position according to a first ratio between the number of the first fusion projects and the number of the second fusion projects, a second ratio between the number of the first fusion sequences and the number of the second fusion sequences in all the first fusion projects and a third ratio between the number of the first fusion sequences and the number of the second fusion sequences in all the second fusion projects;

and performing data fusion on each service data according to the fusion interval number and the fusion project characteristics of each data recording position in each service data to obtain fusion service data.

In a possible design of the first aspect, after the step of performing data fusion on each service data according to the matrix feature sequence, the matrix node sequence, and the data fusion parameters of each incidence matrix node of each service data to obtain fused service data, the method further includes:

when a data analysis request is received, analyzing analysis service data corresponding to the data analysis request from the fusion service data according to a preset analysis strategy of the fusion service data.

In a second aspect, an embodiment of the present application further provides a data fusion device, which is applied to a server, where the server is in communication connection with a plurality of data acquisition terminals, and the server is preconfigured with a data conversion matrix corresponding to each data acquisition terminal, where the device includes:

the acquisition and extraction module is used for acquiring the service data acquired by the data acquisition terminals respectively and extracting a matrix characteristic sequence and a matrix node sequence of each service data on a data conversion matrix corresponding to the corresponding data acquisition terminal, wherein the matrix characteristic sequence comprises a service type confidence coefficient corresponding to each incidence matrix node of the service data in the data conversion matrix, and the matrix node sequence comprises a calculation relationship among the incidence matrix nodes;

a generating module, configured to generate data fusion parameters of each incidence matrix node according to the matrix feature sequence and the matrix node sequence, where the data fusion parameters of the incidence matrix nodes include a fusion process parameter used for indicating that the incidence matrix nodes participate in fusion with other service data separately for the service data;

and the data fusion module is used for carrying out data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence and the data fusion parameters of each incidence matrix node of each service data to obtain fusion service data.

In a third aspect, an embodiment of the present application further provides a server, where the server includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is used for being communicatively connected to at least one data acquisition terminal, the machine-readable storage medium is used for storing a program, an instruction, or a code, and the processor is used for executing the program, the instruction, or the code in the machine-readable storage medium to perform the data fusion method in the first aspect or any one of the possible designs in the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are detected on a computer, the instructions cause the computer to perform the data fusion method in the first aspect or any one of the possible designs of the first aspect.

Based on any one of the above aspects, the application extracts the matrix characteristic sequence and the matrix node sequence of each service data on the corresponding data conversion matrix, and obtains the data fusion parameters of each incidence matrix node, so as to perform data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence and the data fusion parameters of each incidence matrix node of each service data, and obtain the fusion service data. Therefore, the fusion process parameters of the incidence matrix nodes when the incidence matrix nodes participate in fusion with other business data independently aiming at the business data are represented by the data fusion parameters of the incidence matrix nodes, and the data fusion of each business data is carried out, so that the uniform analysis processing can be realized when the data is analyzed, the required analysis business data can be analyzed from the fusion business data through a uniform analysis strategy in the later period, and the data analysis efficiency is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a schematic view of an application scenario of a data fusion system provided in an embodiment of the present application;

fig. 2 is a schematic flowchart of a data fusion method provided in an embodiment of the present application;

fig. 3 is a schematic functional block diagram of a data fusion apparatus according to an embodiment of the present application;

fig. 4 is a block diagram illustrating a structure of a server for implementing the data fusion method according to an embodiment of the present application.

Detailed Description

The present application will now be described in detail with reference to the drawings, and the specific operations in the method embodiments may also be applied to the apparatus embodiments or the system embodiments. In the description of the present application, "at least one" includes one or more unless otherwise specified. "plurality" means two or more. For example, at least one of A, B and C, comprising: a alone, B alone, a and B in combination, a and C in combination, B and C in combination, and A, B and C in combination. In this application, "/" means "or, for example, A/B may mean A or B; "and/or" herein is merely a relational expression describing a relational relationship relating target nuclear magnetic resonance apparatuses, and means that three relations may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone.

Fig. 1 is an interaction diagram of a data fusion system 10 according to an embodiment of the present application. The data fusion system 10 may include a server 100 and a data acquisition terminal 200 communicatively connected to the server 100, and the server 100 may include a processor for executing instruction operations. The data fusion system 10 shown in fig. 1 is only one possible example, and in other possible embodiments, the data fusion system 10 may include only one of the components shown in fig. 1 or may also include other components.

In some embodiments, the server 100 may be a single server or a group of servers. The set of operating servers may be centralized or distributed (e.g., the server 100 may be a distributed system). In some embodiments, the server 100 may be local or remote to the data collection terminal 200. For example, the server 100 may access information stored in the data collection terminal 200 and a database, or any combination thereof, via a network. As another example, the server 100 may be directly connected to at least one of the data collection terminal 200 and a database to access information and/or data stored therein. In some embodiments, the server 100 may be implemented on a cloud platform; by way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (community cloud), a distributed cloud, an inter-cloud, a multi-cloud, and the like, or any combination thereof.

In some embodiments, the server 100 may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described herein. A processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a reduced Instruction Set computer (reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.

The network may be used for the exchange of information and/or data. In some embodiments, one or more components (e.g., the server 100, the data collection terminal 200, and the database) in the data fusion system 10 may send information and/or data to other components. In some embodiments, the network may be any type of wired or wireless network, or combination thereof. Merely by way of example, Network 130 may include a wired Network, a Wireless Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a WLAN, a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a ZigBee Network, a Near Field Communication (NFC) Network, or the like, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include wired or wireless network access points, such as base stations and/or network switching nodes, through which one or more components of the data fusion system 10 may connect to the network to exchange data and/or information.

The aforementioned database may store data and/or instructions. In some embodiments, the database may store data obtained from the data collection terminal 200. In some embodiments, the database may store data and/or instructions for the exemplary methods described herein. In some embodiments, the database may include mass storage, removable storage, volatile Read-write Memory, or Read-Only Memory (ROM), among others, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state drives, and the like; removable memory may include flash drives, floppy disks, optical disks, memory cards, zip disks, tapes, and the like; volatile read-write memory may include Random Access Memory (RAM); the RAM may include Dynamic RAM (DRAM), Double data Rate Synchronous Dynamic RAM (DDR SDRAM); static RAM (SRAM), Thyristor-Based Random Access Memory (T-RAM), Zero-capacitor RAM (Zero-RAM), and the like. By way of example, ROMs may include Mask Read-Only memories (MROMs), Programmable ROMs (PROMs), Erasable Programmable ROMs (PERROMs), Electrically Erasable Programmable ROMs (EEPROMs), compact disk ROMs (CD-ROMs), digital versatile disks (ROMs), and the like. In some embodiments, the database may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, across clouds, multiple clouds, or the like, or any combination thereof.

In some embodiments, the database may be connected to a network to communicate with one or more components in the data fusion system 10 (e.g., the server 100, the data collection terminal 200, etc.). One or more components in the data fusion system 10 may access data or instructions stored in a database via a network. In some embodiments, the database may be directly connected to one or more components in the data fusion system 10 (e.g., the server 100, the data collection terminal 200, etc.); alternatively, in some embodiments, the database may also be part of the server 100.

To solve the technical problem in the foregoing background, fig. 2 is a schematic flowchart of a data fusion method provided in an embodiment of the present application, and the data fusion method provided in this embodiment may be executed by the server 100 shown in fig. 1, and the data fusion method is described in detail below.

Step S110, obtaining service data respectively collected by a plurality of data collection terminals 200, and extracting a matrix characteristic sequence and a matrix node sequence of each service data on a data conversion matrix corresponding to the corresponding data collection terminal 200, where the matrix characteristic sequence includes a service type confidence corresponding to each incidence matrix node of the service data in the data conversion matrix, and the matrix node sequence includes a calculation relationship between each incidence matrix node.

And step S120, generating data fusion parameters of each incidence matrix node according to the matrix characteristic sequence and the matrix node sequence, wherein the data fusion parameters of the incidence matrix nodes comprise fusion process parameters used for representing that the incidence matrix nodes individually participate in fusion with other service data aiming at the service data.

And step S130, performing data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence and the data fusion parameters of each incidence matrix node of each service data to obtain fusion service data.

Based on the above design, in this embodiment, the matrix characteristic sequence and the matrix node sequence of each service data on the corresponding data conversion matrix are extracted, and the data fusion parameters of each incidence matrix node are obtained, so that data fusion is performed on each service data according to the matrix characteristic sequence, the matrix node sequence, and the data fusion parameters of each incidence matrix node of each service data, and the fusion service data is obtained. Therefore, the fusion process parameters of the incidence matrix nodes when the incidence matrix nodes participate in fusion with other business data independently aiming at the business data are represented by the data fusion parameters of the incidence matrix nodes, and the data fusion of each business data is carried out, so that the uniform analysis processing can be realized when the data is analyzed, the required analysis business data can be analyzed from the fusion business data through a uniform analysis strategy in the later period, and the data analysis efficiency is improved.

In a possible design, for step S110, this embodiment may extract a plurality of service conversion channels of each service data on the data conversion matrix corresponding to the corresponding data acquisition terminal 200, and input the service data into the data conversion matrix according to the plurality of service conversion channels to perform matrix conversion processing, so as to obtain a plurality of matrix conversion service results with different dimensions.

Then, for each service conversion channel in the plurality of service conversion channels, selecting a matrix conversion service result of a corresponding dimension from matrix conversion service results of a plurality of different dimensions for the service conversion channel, and determining whether the service conversion channel matches a preset matrix conversion template by using matrix conversion information corresponding to the matrix conversion service result, and when the service conversion channel matches the preset matrix conversion template, reserving the service conversion channel to obtain a plurality of reserved service conversion channels.

Then, the service data can be input into the data conversion matrix through a plurality of reserved service conversion channels for service conversion, the corresponding service conversion matrix node sequence and the service conversion process information of the target matrix node in the service conversion matrix node sequence are obtained, and the service conversion interval of the target matrix node is determined according to the service conversion process information of the target matrix node.

Then, the coincidence interval of the service conversion intervals of the target matrix nodes can be used as a service association interval, the service conversion position of each target matrix node is obtained in the service association interval, target matrix node recombination is carried out according to the position confidence of the service conversion position of each target matrix node, corresponding candidate association matrix nodes are obtained, the service type confidence corresponding to the service data in the candidate association matrix nodes is obtained, calculation relation information between the candidate association matrix nodes and the calculation relation is established according to the service type confidence, each candidate association matrix node is processed by taking the calculation relation as a reference, and the service conversion process information corresponding to the calculation relation information of each candidate association matrix node is determined.

Then, according to the service conversion process information corresponding to the calculation relationship information of each candidate incidence matrix node, each incidence matrix node in each candidate incidence matrix node is determined, so as to obtain the service type confidence corresponding to each incidence matrix node in the data conversion matrix of the service data and the calculation relationship among each incidence matrix node.

In a possible design, for step S120, the embodiment may specifically determine, according to the matrix feature sequence and the matrix node sequence, normalized fusion information of the service data for each incidence matrix node, and convert the normalized fusion information of the service data for each incidence matrix node into a normalized fusion sampling graph.

Then, a corresponding fusion data range sample map can be constructed according to the normalized fusion sample map, and the constructed fusion data range sample map is analyzed to obtain a plurality of fusion data range areas.

Then, an average value of the data number in each fused data range region may be obtained, and a difference between the data number in the fused data range region and the average value may be calculated to obtain a data number determination value of the fused data range region.

The plurality of fused data range regions with which the data quantity determination values are associated may then be classified to generate a corresponding classified fused data range region map comprised of a classified combination of the classified fused data range regions of the plurality of classifications.

Then, a fused data range region with the largest fused data range and a fused data range region with the smallest fused data range may be selected in the classified fused data range region map as the first fused data range region and the second fused data range region, and calculating data quantity determination value differences between each fusion data range region and the first fusion data range region and the second fusion data range region in the classified fusion data range region map respectively, allocating a fusion data range region having a data quantity determination value difference with the first fusion data range region smaller than or equal to a data quantity determination value difference with the second fusion data range region to the first fusion data range region sequence, and allocating a fusion data range region having a data quantity determination value difference with the first fusion data range region larger than a data quantity determination value difference with the second fusion data range region to the second fusion data range region sequence.

Next, an average of the data quantity determinations for all of the fused data range regions in the first sequence of fused data range regions may be calculated, a first fused data range region having the average of the actual data quantity determinations as a region may be obtained, an average of the data quantity determinations for all of the fused data range regions in the second sequence of fused data range regions may be calculated, and a second fused data range region having the average of the actual data quantity determinations as a region may be obtained.

Then, a plurality of corresponding third and fourth fused data range regions may be determined according to the degree of coincidence of the first and second fused data range regions with each fused data range region in the classified fused data range region map.

Then, normalized fusion parameter information corresponding to the normalized fusion information may be determined according to the plurality of third fusion data range regions and the plurality of fourth fusion data range regions, and the normalized fusion parameter information may be analyzed to obtain normalized fusion process control information in the normalized fusion parameter information.

Then, the fusion affine transformation range of the normalized fusion process control information can be determined as the fusion affine transformation range corresponding to the incidence matrix node, and the fusion process parameters of the incidence matrix node when the incidence matrix node participates in fusion with other service data are determined according to the fusion affine transformation range corresponding to the incidence matrix node and the normalized fusion process control information.

In a possible design, for step S130, the embodiment may specifically determine fusion matrix information of each service data according to the matrix feature sequence and the matrix node sequence of each service data, and determine a fusion matrix node corresponding to each service data according to the fusion matrix information.

Then, a data fusion policy of the fusion matrix node corresponding to each service data may be obtained from the data fusion parameters of each incidence matrix node, where the data fusion policy is used to represent fusion participation information of the fusion matrix node.

Then, a mapping relation between the fusion matrix node and the fusion participation position can be established according to the data fusion strategy.

Then, a plurality of position association states of each data recording position in each service data can be determined according to the established mapping relationship between the fusion matrix node and the fusion participation position, for each position association state, a matching relationship between a state recording value of a corresponding position association state of a data recording position of other service data matched with each data recording position and a state recording value of a corresponding position association state of a preset number of data recording positions behind each data recording position is obtained, and fusion participation state configuration information of each data recording position at the position association state is obtained according to the matching relationship, so that fusion participation state configuration information of each data recording position is obtained.

Then, the fusion control state of each data recording position in the fusion process can be obtained according to the fusion participation state configuration information of each data recording position.

Then, a plurality of control feature sequences corresponding to each data recording position can be obtained according to the fusion control state, and first control feature information and second control feature information of the plurality of control feature sequences are determined, wherein the first control feature information comprises control feature information when the fusion control state of each data recording position is in an open state, and the second control feature information comprises control feature information when the fusion control state of each data recording position is in a closed state.

Then, the position sequence of the first control feature information in the control feature sequence can be determined, the fusion participation level of the first control feature information is determined according to the position sequence, the fusion project sequence corresponding to the control feature sequence of the fusion participation position corresponding to each data recording position is respectively determined according to the fusion participation level, the fusion project characteristic corresponding to the fusion project sequence is calculated, the fusion project sequence is determined according to the fusion project record information generated by the fusion part and corresponding to the control feature sequence of the fusion participation position corresponding to the data recording position in the fusion process, and the fusion project record information corresponding to different fusion parts is different.

Then, a lower matching degree limit corresponding to the fusion participation position corresponding to each data recording position can be obtained, and a mapping relation between the fusion item sequence and the lower matching degree limit is determined according to the fusion item characteristics.

Then, according to the mapping relationship between the determined fusion item sequence and the lower limit of the matching degree, a plurality of fusion items at each data recording position and a fusion sequence corresponding to each fusion item can be determined from the fusion item sequence.

Then, a plurality of fusion items identical to a preset fusion sequence may be screened out from the plurality of fusion items, a plurality of first fusion items may be obtained, and fusion items other than the first fusion items in the plurality of fusion items may be used as second fusion items.

Then, the fusion interval number for each data recording position may be determined according to a first ratio between the number of the first fusion items and the number of the second fusion items, a second ratio between the number of the first fusion orders and the number of the second fusion orders in all the first fusion items, and a third ratio between the number of the first fusion orders and the number of the second fusion orders in all the second fusion items.

Then, data fusion can be performed on each service data according to the fusion interval number and the fusion project characteristics of each data recording position in each service data, so as to obtain fusion service data.

In a possible design, after step S130, the embodiment may further parse, when receiving the data parsing request, parsing, according to a preset parsing policy of the converged service data, parsing, from the converged service data, the parsed service data corresponding to the data parsing request.

Fig. 3 is a schematic functional module diagram of a data fusion device 300 according to an embodiment of the present application, and the present embodiment may divide the functional module of the data fusion device 300 according to the method embodiment executed by the server 100. For example, the functional blocks may be divided for the respective functions, or two or more functions may be integrated into one processing block. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, the division of the modules in the present application is schematic, and is only a logical function division, and there may be another division manner in actual implementation. For example, in the case of dividing each function module according to each function, the data fusion apparatus 300 shown in fig. 3 is only a schematic apparatus. The data fusion apparatus 300 may include an obtaining and extracting module, a generating module 320, and a data fusion module 330, and the functions of the functional modules of the data fusion apparatus 300 are described in detail below.

The obtaining and extracting module 310 is configured to obtain service data respectively collected by the multiple data collection terminals 200, and extract a matrix feature sequence and a matrix node sequence of each service data on a data conversion matrix corresponding to the corresponding data collection terminal 200, where the matrix feature sequence includes service type confidence corresponding to each incidence matrix node of the service data in the data conversion matrix, and the matrix node sequence includes a calculation relationship between each incidence matrix node.

The generating module 320 is configured to generate data fusion parameters of each incidence matrix node according to the matrix characteristic sequence and the matrix node sequence, where the data fusion parameters of the incidence matrix nodes include fusion process parameters used for representing that the incidence matrix nodes participate in fusion with other service data separately for the service data.

And the data fusion module 330 is configured to perform data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence, and the data fusion parameters of each incidence matrix node of each service data, so as to obtain fused service data.

In one possible design, the obtaining and extracting module 310 is configured to extract a matrix feature sequence and a matrix node sequence of each service data on a data transformation matrix corresponding to the corresponding data acquisition terminal 200 by:

a plurality of service conversion channels of each service data on the data conversion matrix corresponding to the corresponding data acquisition terminal 200 are extracted.

And inputting the service data into the data conversion matrix according to the plurality of service conversion channels for matrix conversion processing to obtain a plurality of matrix conversion service results with different dimensions.

And aiming at each service conversion channel in the plurality of service conversion channels, selecting a matrix conversion service result of a corresponding dimension for the service conversion channel from matrix conversion service results of a plurality of different dimensions, judging whether the service conversion channel is matched with a preset matrix conversion template by utilizing matrix conversion information corresponding to the matrix conversion service result, and reserving the service conversion channel when the service conversion channel is matched with the preset matrix conversion template so as to obtain a plurality of reserved service conversion channels.

And inputting the service data into the data conversion matrix through a plurality of reserved service conversion channels for service conversion, acquiring the corresponding service conversion matrix node sequence and the service conversion process information of the target matrix node in the service conversion matrix node sequence, and determining the service conversion interval of the target matrix node according to the service conversion process information of the target matrix node.

The method comprises the steps of taking a coincidence interval of service conversion intervals of target matrix nodes as a service association interval, obtaining a service conversion position of each target matrix node in the service association interval, carrying out target matrix node recombination according to the position confidence coefficient of the service conversion position of each target matrix node to obtain corresponding candidate association matrix nodes, obtaining the service type confidence coefficient of service data corresponding to the candidate association matrix nodes, establishing calculation relation information between the candidate association matrix nodes and the calculation relation according to the service type confidence coefficient, and processing each candidate association matrix node by taking the calculation relation as a reference to determine service conversion process information corresponding to the calculation relation information of each candidate association matrix node.

And determining each incidence matrix node in each candidate incidence matrix node according to the service conversion process information corresponding to the calculation relation information of each candidate incidence matrix node so as to obtain the service type confidence corresponding to each incidence matrix node in the data conversion matrix of the service data and the calculation relation among each incidence matrix node.

In one possible design, the generating module 320 is configured to generate the data fusion parameters of each incidence matrix node by:

and determining normalized fusion information of the service data for each incidence matrix node according to the matrix characteristic sequence and the matrix node sequence, and converting the normalized fusion information of the service data for each incidence matrix node into a normalized fusion sampling graph.

And constructing a corresponding fusion data range sample map according to the normalized fusion sample map, and analyzing the constructed fusion data range sample map to obtain a plurality of fusion data range areas.

And acquiring the average value of the data quantity in each fusion data range area, and calculating the difference value between the data quantity in the fusion data range area and the average value to obtain the data quantity determination value of the fusion data range area.

The plurality of fused data range regions associated with the data quantity determination value are classified to generate a corresponding classified fused data range region map composed of classified combinations of the plurality of classified fused data range regions.

Selecting a fusion data range region with the largest fusion data range and a fusion data range region with the smallest fusion data range from the classified fusion data range region map as a first fusion data range region and a second fusion data range region, and calculating data quantity determination value differences between each fusion data range region and the first fusion data range region and the second fusion data range region in the classified fusion data range region map respectively, allocating a fusion data range region having a data quantity determination value difference with the first fusion data range region smaller than or equal to a data quantity determination value difference with the second fusion data range region to the first fusion data range region sequence, and allocating a fusion data range region having a data quantity determination value difference with the first fusion data range region larger than a data quantity determination value difference with the second fusion data range region to the second fusion data range region sequence.

Calculating the average of the data quantity determinations of all the fused data range regions in the first sequence of fused data range regions, obtaining a first fused data range region having the average of the actual data quantity determinations as a region, calculating the average of the data quantity determinations of all the fused data range regions in the second sequence of fused data range regions, and obtaining a second fused data range region having the average of the actual data quantity determinations as a region.

And determining a plurality of corresponding third fusion data range regions and a plurality of corresponding fourth fusion data range regions according to the coincidence degree of the first fusion data range region and the second fusion data range region and each fusion data range region in the classified fusion data range region diagram.

And determining normalized fusion parameter information corresponding to the normalized fusion information according to the plurality of third fusion data range areas and the plurality of fourth fusion data range areas, and analyzing the normalized fusion parameter information to obtain normalized fusion process control information in the normalized fusion parameter information.

And determining a fusion affine transformation range of the normalized fusion process control information as a fusion affine transformation range corresponding to the incidence matrix node, and determining fusion process parameters of the incidence matrix node when the incidence matrix node is alone engaged in fusion with other service data according to the fusion affine transformation range corresponding to the incidence matrix node and the normalized fusion process control information.

In one possible design, the data fusion module 330 is configured to perform data fusion on each service data to obtain fused service data by:

determining fusion matrix information of each service data according to the matrix characteristic sequence and the matrix node sequence of each service data, and determining fusion matrix nodes corresponding to each service data according to the fusion matrix information.

And acquiring a data fusion strategy of the fusion matrix node corresponding to each service data from the data fusion parameters of each incidence matrix node, wherein the data fusion strategy is used for expressing fusion participation information of the fusion matrix node.

And establishing a mapping relation between the fusion matrix nodes and the fusion participation positions according to the data fusion strategy.

Determining a plurality of position association states of each data recording position in each service data according to the established mapping relation between the fusion matrix node and the fusion participation position, acquiring the matching relation between the state recording value of the corresponding position association state of the data recording position of other service data matched with each data recording position and the state recording value of the corresponding position association state of the corresponding position of a preset number of data recording positions behind each data recording position aiming at each position association state, and acquiring the fusion participation state configuration information of each data recording position at the position association state according to the matching relation so as to acquire the fusion participation state configuration information of each data recording position.

And acquiring the fusion control state of each data recording position in the fusion process according to the fusion participation state configuration information of each data recording position.

And obtaining a plurality of control characteristic sequences corresponding to each data recording position according to the fusion control state, and determining first control characteristic information and second control characteristic information of the plurality of control characteristic sequences, wherein the first control characteristic information comprises the control characteristic information when the fusion control state of each data recording position is in an open state, and the second control characteristic information comprises the control characteristic information when the fusion control state of each data recording position is in a closed state.

Determining the position sequence of the first control feature information in the control feature sequence, determining the fusion participation level of the first control feature information according to the position sequence, respectively determining the fusion project sequence corresponding to the control feature sequence of the fusion participation position corresponding to each data recording position according to the fusion participation level, and calculating the fusion project characteristics corresponding to the fusion project sequence, wherein the fusion project sequence is determined according to the fusion project recording information generated by the fusion part corresponding to the control feature sequence of the fusion participation position corresponding to the data recording position in the fusion process, and the fusion project recording information corresponding to different fusion parts is different.

And acquiring a lower matching degree limit corresponding to the fusion participation position corresponding to each data recording position, and determining a mapping relation between the fusion project sequence and the lower matching degree limit according to the fusion project characteristics.

And determining a plurality of fusion items at each data recording position and a fusion sequence corresponding to each fusion item from the fusion item sequence according to the mapping relation between the determined fusion item sequence and the lower limit of the matching degree.

And screening a plurality of fusion items with the same preset fusion sequence from the plurality of fusion items to obtain a plurality of first fusion items, and taking the fusion items except the first fusion items from the plurality of fusion items as second fusion items.

And determining the fusion interval number aiming at each data recording position according to a first ratio between the number of the first fusion items and the number of the second fusion items, a second ratio between the number of the first fusion sequences and the number of the second fusion sequences in all the first fusion items and a third ratio between the number of the first fusion sequences and the number of the second fusion sequences in all the second fusion items.

Further, fig. 4 is a schematic structural diagram of a server 100 for performing the data fusion method according to an embodiment of the present application. As shown in FIG. 4, the server 100 may include a network interface 110, a machine-readable storage medium 120, a processor 130, and a bus 140. The processor 130 may be one or more, and one processor 130 is illustrated in fig. 4 as an example. The network interface 110, the machine-readable storage medium 120, and the processor 130 may be connected by a bus 140 or otherwise, as exemplified by the connection by the bus 140 in fig. 4.

The machine-readable storage medium 120 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the data fusion method in the embodiment of the present application (for example, the acquisition extraction module, the generation module 320, and the data fusion module 330 of the data fusion apparatus 300 shown in fig. 3). The processor 130 executes various functional applications and data processing of the terminal device by detecting the software programs, instructions and modules stored in the machine-readable storage medium 120, that is, the data fusion method is implemented, and details are not described herein.

The machine-readable storage medium 120 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the machine-readable storage medium 120 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double data rate Synchronous Dynamic random access memory (DDR SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous link SDRAM (SLDRAM), and direct memory bus RAM (DR RAM). It should be noted that the memories of the systems and methods described herein are intended to comprise, without being limited to, these and any other suitable memory of a publishing node. In some examples, the machine-readable storage medium 120 may further include memory located remotely from the processor 130, which may be connected to the server 100 over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The processor 130 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 130. The processor 130 may be a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.

The server 100 can perform information interaction with other devices (such as the data acquisition terminal 200) through the network interface 110. Network interface 110 may be a circuit, bus, transceiver, or any other device that may be used to exchange information. Processor 130 may send and receive information using network interface 110.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various changes and modifications may be made in the embodiments of the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to encompass such modifications and variations.

Claims

1. A data fusion method is applied to a server, the server is in communication connection with a plurality of data acquisition terminals, the server is pre-configured with a data conversion matrix corresponding to each data acquisition terminal, and the method comprises the following steps:

performing data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence and the data fusion parameters of each incidence matrix node of each service data to obtain fusion service data;

the step of generating the data fusion parameters of each incidence matrix node according to the matrix characteristic sequence and the matrix node sequence comprises the following steps:

determining a fusion affine transformation range of the normalized fusion process control information as a fusion affine transformation range corresponding to the incidence matrix node, and determining fusion process parameters of the incidence matrix node when the incidence matrix node participates in fusion with other service data independently according to the fusion affine transformation range corresponding to the incidence matrix node and the normalized fusion process control information;

the step of performing data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence and the data fusion parameters of each incidence matrix node of each service data to obtain fusion service data includes:

2. The data fusion method of claim 1, wherein the step of extracting the matrix characteristic sequence and the matrix node sequence of each service data on the data transformation matrix corresponding to the corresponding data acquisition terminal comprises:

3. The data fusion method according to any one of claims 1-2, wherein after the step of performing data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence of each service data and the data fusion parameters of each incidence matrix node to obtain the fused service data, the method further comprises:

4. A data fusion device is applied to a server, the server is in communication connection with a plurality of data acquisition terminals, the server is pre-configured with a data conversion matrix corresponding to each data acquisition terminal, and the device comprises:

the data fusion module is used for carrying out data fusion on each service data according to the matrix characteristic sequence, the matrix node sequence and the data fusion parameters of each incidence matrix node of each service data to obtain fusion service data;

the generation module is used for generating the data fusion parameters of the incidence matrix nodes in the following modes:

the data fusion module is used for performing data fusion on each service data in the following way to obtain fusion service data:

5. The data fusion device of claim 4, wherein the acquisition and extraction module is configured to extract a matrix feature sequence and a matrix node sequence of each service data on the data transformation matrix corresponding to the corresponding data acquisition terminal in the following manner:

6. A server, characterized in that the server comprises a processor, a machine-readable storage medium, and a network interface, the machine-readable storage medium, the network interface and the processor are connected through a bus system, the network interface is used for being connected with at least one network communication node terminal in a communication mode, the machine-readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, the instructions or the codes in the machine-readable storage medium to execute the data fusion method of any one of claims 1 to 3.