Information fusion method and system

Abstract

The invention provides an information fusion method and system, and the method comprises the steps: receiving a plurality of pieces of target information sent by a plurality of intelligent systems in real time, generating an adjacency relation matrix corresponding to the plurality of intelligent systems in real time according to the plurality of pieces of target information based on a preset rule, and enabling each intelligent system to correspond to one piece of target information; screening corresponding target matrix parameters from the adjacency relation matrix in real time, and generating a corresponding information matrix in real time according to the target matrix parameters; performing feature extraction processing on the information matrix to generate a corresponding target feature vector in real time, and calculating an information weight corresponding to each piece of target information in real time according to the target feature vector; and performing convolution fusion processing according to the target feature vector and the information weight to generate a target information vector corresponding to the plurality of pieces of target information in real time. According to the method, complex calculation and data can be avoided, and the working efficiency is correspondingly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an information fusion method and system. Background Art

[0002] With the advancement of science and technology and the development of the times, computer technology and Internet technology have become popular in people's daily lives, and have been deeply applied in many fields, which has made people's lives more convenient.

[0003] Among them, existing technologies have developed intelligent systems with different functions based on existing computers and the Internet, and in the existing multi-agent system, information fusion of heterogeneous agents is a key process, which can combine information from multiple different agents to obtain more accurate and comprehensive scene understanding and decision-making.

[0004] Furthermore, in the process of fusing information of different intelligent agents, most of the existing technologies complete data processing through existing Bayesian theory or deep learning networks. However, although this processing method can ultimately achieve data fusion, it has high computational complexity and will generate high-dimensional complex data. It has certain usage limitations and reduces work efficiency. Summary of the invention

[0005] Based on this, the purpose of the present invention is to provide an information fusion method and system to solve the problem that in the process of data fusion in the prior art, the calculation complexity is high and high-dimensional complex data will be generated, which correspondingly reduces the work efficiency.

[0006] The first aspect of the embodiment of the present invention proposes: An information fusion method, wherein the method comprises: Receiving multiple target information sent by multiple intelligent systems in real time, and generating an adjacency relationship matrix corresponding to the multiple intelligent systems in real time according to the multiple target information based on preset rules, wherein each intelligent system corresponds to one target information; In the adjacency matrix, corresponding target matrix parameters are screened out in real time, and corresponding information matrix is ​​generated in real time according to the target matrix parameters; Performing feature extraction processing on the information matrix to generate a corresponding target feature vector in real time, and calculating the information weight corresponding to each target information in real time according to the target feature vector; Convolution fusion processing is performed according to the target feature vector and the information weight to generate a target information vector corresponding to the plurality of target information in real time.

[0007] The beneficial effect of the present invention is that by receiving the target information sent by the intelligent system in real time, the corresponding processing object can be determined, based on which, the current target information can be immediately quantized according to pre-set rules, and the corresponding adjacency relationship matrix can be generated, based on which the current adjacency relationship matrix can be secondary processed, and the target feature vector for subsequent fusion can be extracted in real time, based on which, only the final target feature vector and information weight need to be convolutionally fused to obtain the required target information vector, thereby completing the corresponding fusion processing, and then quickly and effectively completing the fusion of data, avoiding complex calculations and data, and correspondingly improving work efficiency.

[0008] Furthermore, the step of generating an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time according to the plurality of target information based on preset rules includes: When a plurality of target information is acquired in real time, the plurality of target information is input into a preset feature extraction network accordingly, so that the feature extraction network outputs a corresponding initial association vector in real time; The initial association vector is matrix-processed to generate adjacency relationship matrices corresponding to the plurality of intelligent systems in real time.

[0009] Furthermore, the step of performing matrix processing on the initial association vector to generate adjacency relationship matrices corresponding to the plurality of intelligent systems in real time includes: When the initial association vector is obtained in real time, the initial association vector is input into a preset softmax layer, and the corresponding probability matrix is ​​output in real time through the preset softmax layer; The probability matrix is ​​input into a preset onehot coding layer, and the probability matrix is ​​coded in real time by the preset onehot coding layer to output the corresponding target relationship code in real time; The target relationship code is converted in real time to generate an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time.

[0010] Furthermore, the step of outputting the corresponding probability matrix in real time through the preset softmax layer includes: When the initial association vector is obtained in real time, the corresponding fully connected network is called out in real time in the preset softmax layer; The fully connected network is fully scanned to detect in real time a number of original network nodes corresponding to the interior of the fully connected network, and each of the initial association vectors is correspondingly filled into the interior of each of the original network nodes to output the probability matrix in real time.

[0011] Furthermore, the expression of the algorithm for performing real-time encoding processing on the probability matrix through the preset onehot encoding layer is:

[0012] Among them, g ij represents the target relation encoding, p i represents the horizontal matrix parameter in the probability matrix, h i represents the vertical matrix parameter in the probability matrix, τ represents the temperature coefficient, and N represents the number of target relationship codes.

[0013] Furthermore, the step of calculating in real time based on the target feature vector the information weight corresponding to each of the target information comprises: When the target feature vector is acquired in real time, the corresponding preset algorithm is called out in real time in the preset database; Each of the target feature vectors is input into the preset algorithm in real time, so that the preset algorithm outputs the information weight corresponding to each of the target information in real time.

[0014] Furthermore, the expression of the preset algorithm is:

[0015] Among them, w j (Q, I) represents the information weight, K represents the number of target feature vectors, QI j T represents the target feature vector, D 1 represents the size of the target feature vector.

[0016] The second aspect of the embodiment of the present invention proposes: An information fusion system, wherein the system comprises: A receiving module, used for receiving a plurality of target information sent by a plurality of intelligent systems in real time, and generating an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time according to the plurality of target information based on a preset rule, wherein each intelligent system corresponds to one piece of target information; A screening module, used for screening corresponding target matrix parameters in the adjacency matrix in real time, and generating corresponding information matrix in real time according to the target matrix parameters; A calculation module, used for performing feature extraction processing on the information matrix to generate a corresponding target feature vector in real time, and calculating the information weight corresponding to each target information in real time according to the target feature vector; A fusion module is used to perform convolution fusion processing according to the target feature vector and the information weight to generate a target information vector corresponding to the target information in real time.

[0017] Furthermore, the receiving module is specifically used for: When a plurality of target information is acquired in real time, the plurality of target information is input into a preset feature extraction network accordingly, so that the feature extraction network outputs a corresponding initial association vector in real time; The initial association vector is matrix-processed to generate adjacency relationship matrices corresponding to the plurality of intelligent systems in real time.

[0018] Furthermore, the receiving module is specifically used for: When the initial association vector is obtained in real time, the initial association vector is input into a preset softmax layer, and the corresponding probability matrix is ​​output in real time through the preset softmax layer; The probability matrix is ​​input into a preset onehot coding layer, and the probability matrix is ​​coded in real time by the preset onehot coding layer to output the corresponding target relationship code in real time; The target relationship code is converted in real time to generate an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time.

[0019] Furthermore, the receiving module is specifically used for: When the initial association vector is obtained in real time, the corresponding fully connected network is called out in real time in the preset softmax layer; The fully connected network is fully scanned to detect in real time a number of original network nodes corresponding to the interior of the fully connected network, and each of the initial association vectors is correspondingly filled into the interior of each of the original network nodes to output the probability matrix in real time.

[0020] Furthermore, the expression of the algorithm for performing real-time encoding processing on the probability matrix through the preset onehot encoding layer is:

[0021] Among them, g ij represents the target relation encoding, p i represents the horizontal matrix parameter in the probability matrix, h i represents the vertical matrix parameter in the probability matrix, τ represents the temperature coefficient, and N represents the number of target relationship codes.

[0022] Furthermore, the calculation module is specifically used for: When the target feature vector is acquired in real time, the corresponding preset algorithm is called out in real time in the preset database; Each of the target feature vectors is input into the preset algorithm in real time, so that the preset algorithm outputs the information weight corresponding to each of the target information in real time.

[0023] Furthermore, the expression of the preset algorithm is:

[0024] Among them, w j (Q, I) represents the information weight, K represents the number of target feature vectors, QI j T represents the target feature vector, D 1 represents the size of the target feature vector.

[0025] The third aspect of the embodiment of the present invention proposes: A computer comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the information fusion method as described above when executing the computer program.

[0026] The fourth aspect of the embodiments of the present invention proposes: A readable storage medium stores a computer program, wherein the program, when executed by a processor, implements the information fusion method as described above.

[0027] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A flowchart of the information fusion method provided by the first embodiment of the present invention; Figure 2 This is a structural block diagram of an information fusion system provided in the third embodiment of the present invention.

[0029] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0030] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0031] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0033] See also Figure 1 , which is shown as the information fusion method provided by the first embodiment of the present invention. The information fusion method provided by this embodiment can avoid the generation of complex calculations and data, so that the fusion of various target information can be completed quickly and effectively, thereby correspondingly improving work efficiency.

[0034] Specifically, this embodiment provides: An information fusion method specifically comprises the following steps: Step S10, receiving in real time a plurality of target information sent in real time by a plurality of intelligent systems, and generating in real time an adjacency relationship matrix corresponding to the plurality of intelligent systems according to the plurality of target information based on a preset rule, wherein each of the intelligent systems corresponds to one piece of target information; Step S20, selecting corresponding target matrix parameters in the adjacency matrix in real time, and generating corresponding information matrix in real time according to the target matrix parameters; Step S30, performing feature extraction processing on the information matrix to generate a corresponding target feature vector in real time, and calculating the information weight corresponding to each target information in real time according to the target feature vector; Step S40, performing convolution fusion processing according to the target feature vector and the information weight to generate a target information vector corresponding to the plurality of target information in real time.

[0035] Specifically, in this embodiment, it should be noted that, in order to quickly and effectively complete the data fusion processing, it is necessary to parse and process each piece of information received in real time, wherein it should be noted that, in the process of actual application, the information fusion method provided by the present invention is implemented based on a server set in the background, and specifically, the server can establish a communication connection with each existing intelligent system, so that the server provided by the present invention can receive in real time a number of target information corresponding to each intelligent system, wherein it should be noted that each existing intelligent system will only send one target information at a time. Based on this, in order to facilitate the fusion processing of each current target information, the present invention will immediately call out the pre-set information processing rules in the background, and can quantify the current several target information through the preset rules, and can generate a corresponding adjacency relationship matrix, that is, a matrix that can indicate the connection between each current target information, based on this, the present invention will parse the current adjacency relationship matrix in real time for subsequent processing.

[0036] Furthermore, after the required adjacency relationship matrix is ​​obtained in real time through the above steps, it should be noted that the adjacency relationship matrix contains a large number of matrix parameters, but not every matrix parameter needs to be subsequently fused. Based on this, the present invention will perform corresponding screening processing inside the current adjacency relationship matrix, and can screen out the corresponding target matrix parameters in real time in the current adjacency relationship matrix. At the same time, it can create a corresponding information matrix in real time according to the target matrix parameters. Based on this, the current information matrix will be subjected to feature extraction processing again, and the corresponding target feature vector can be generated synchronously. On this basis, the current target feature vector is finally subjected to corresponding calculation processing, and the information weight corresponding to each of the above target information can be finally calculated. Based on this, the current information weights can be used as the fusion basis, and the current target feature vector and the information weight can be convolutionally fused in real time, so that the required target information vector can be finally fused, thereby avoiding complex calculations and data, and correspondingly improving work efficiency.

[0037] Second embodiment Furthermore, the step of generating an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time according to the plurality of target information based on preset rules includes: When a plurality of target information is acquired in real time, the plurality of target information is input into a preset feature extraction network accordingly, so that the feature extraction network outputs a corresponding initial association vector in real time; The initial association vector is matrix-processed to generate adjacency relationship matrices corresponding to the plurality of intelligent systems in real time.

[0038] Furthermore, the step of performing matrix processing on the initial association vector to generate adjacency relationship matrices corresponding to the plurality of intelligent systems in real time includes: When the initial association vector is obtained in real time, the initial association vector is input into a preset softmax layer, and the corresponding probability matrix is ​​output in real time through the preset softmax layer; The probability matrix is ​​input into a preset onehot coding layer, and the probability matrix is ​​coded in real time by the preset onehot coding layer to output the corresponding target relationship code in real time; The target relationship code is converted in real time to generate an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time.

[0039] Furthermore, the step of outputting the corresponding probability matrix in real time through the preset softmax layer includes: When the initial association vector is obtained in real time, the corresponding fully connected network is called out in real time in the preset softmax layer; The fully connected network is fully scanned to detect in real time a number of original network nodes corresponding to the interior of the fully connected network, and each of the initial association vectors is correspondingly filled into the interior of each of the original network nodes to output the probability matrix in real time.

[0040] Furthermore, the expression of the algorithm for performing real-time encoding processing on the probability matrix through the preset onehot encoding layer is:

[0041] Among them, g ij represents the target relation encoding, p i represents the horizontal matrix parameter in the probability matrix, h i represents the vertical matrix parameter in the probability matrix, τ represents the temperature coefficient, and N represents the number of target relationship codes.

[0042] Furthermore, the step of calculating in real time based on the target feature vector the information weight corresponding to each of the target information comprises: When the target feature vector is acquired in real time, the corresponding preset algorithm is called out in real time in the preset database; Each of the target feature vectors is input into the preset algorithm in real time, so that the preset algorithm outputs the information weight corresponding to each of the target information in real time.

[0043] Furthermore, the expression of the preset algorithm is:

[0044] Among them, w j (Q, I) represents the information weight, K represents the number of target feature vectors, QI j T represents the target feature vector, D 1 represents the size of the target feature vector.

[0045] In addition, in this embodiment, it is also necessary to explain that, for ease of understanding, it is assumed that 𝑖 is the information observed by agent i, 𝑚 j (j=1,2,..,N, j≠i) is the observation information of other agents. 𝑂𝑖 and 𝑚j are concatenated and input into the feature extraction network, and the output is the correlation vector 𝑒 between agent i and other agents. 𝑖𝑗 , which represents the information 𝑚 j The closeness of the relationship with the agent i itself. The process can be expressed as a function, as shown in the formula: (1) 𝑓(O i， m j )→𝑒 ij Since the number of agents is N, the final output is (e i1 ,e i2 ,e i3 ,...e iN ). Finally, the output of the feature extraction network (e i1 ,e i2 ,e i3 ,...e iN ) is input to softmax, and finally outputs an adjacency matrix G=[g i1 ,g i2 ,g i3 ,...g iN If g ij is 0, indicating that agent i refuses to receive information from agent j; if g ij is 1, indicating that agent i receives the information of agent j.

[0046] In order to convert the correlation vector into the one-hot adjacency matrix G. Assume that the local observation O i The dimension is 𝐷 1 , other agent information 𝑚 𝑗 The dimension is 𝐷 2 , then the correlation vector (e i1 ,e i2 ,e i3 ,...e iN) is of dimension N×(D1+D2), and the linear transformation matrix of the fully connected network is of dimension (D1+D2)×1, so the dimension of the relevance vector after passing through the fully connected network is N×1. After the Softmax function, a probability matrix P can be obtained, and the dimension of P is N×1, which is then encoded as follows according to onehot:

[0047] Among them, g ij represents the target relation encoding, p i represents the horizontal matrix parameter in the probability matrix, h i represents the vertical matrix parameter in the probability matrix, τ represents the temperature coefficient, N represents the number of target relationship codes, and by adjusting τ, g ij Close to onehot encoding, after onehot encoding, we get the final Nx1 relational encoding G=[g i1 ,g i2 ,g i3 ,...g iN ] for subsequent processing.

[0048] According to the relationship encoding matrix G=[g i1 ,g i2 ,g i3 ,...g iN ], the information of the agent corresponding to 1 in G will be what agent i needs to receive. Assuming that agent i receives information from K agents in total, the information matrix is ​​recorded as M, and the dimension of M is K×D2. The local observation information of agent i is extracted by feature extraction to obtain a 1×D 1 The information matrix M is obtained by feature extraction to obtain a K×D 1 The information matrix M is then transformed into a vector I through feature extraction.

[0049] The weight of each agent's information is calculated based on vector Q and vector I. The formula is as follows:

[0050] Among them, g ij represents the target relation encoding, p i represents the horizontal matrix parameter in the probability matrix, h i represents the vertical matrix parameter in the probability matrix, τ represents the temperature coefficient, and N represents the number of target relationship codes.

[0051] We get a vector W=[w 1 m 1 ,w 2 m 2 ,...wK m K ], and finally convolve W and vector V to obtain 1×D 3 Information vector Mesg.

[0052] See also Figure 2 , the third embodiment of the present invention provides: An information fusion system, wherein the system comprises: A receiving module, used for receiving a plurality of target information sent by a plurality of intelligent systems in real time, and generating an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time according to the plurality of target information based on a preset rule, wherein each intelligent system corresponds to one piece of target information; A screening module, used for screening corresponding target matrix parameters in the adjacency matrix in real time, and generating corresponding information matrix in real time according to the target matrix parameters; A calculation module, used for performing feature extraction processing on the information matrix to generate a corresponding target feature vector in real time, and calculating the information weight corresponding to each target information in real time according to the target feature vector; A fusion module is used to perform convolution fusion processing according to the target feature vector and the information weight to generate a target information vector corresponding to the target information in real time.

[0053] Furthermore, the receiving module is specifically used for: When a plurality of target information is acquired in real time, the plurality of target information is input into a preset feature extraction network accordingly, so that the feature extraction network outputs a corresponding initial association vector in real time; The initial association vector is matrix-processed to generate adjacency relationship matrices corresponding to the plurality of intelligent systems in real time.

[0054] Furthermore, the receiving module is specifically used for: When the initial association vector is obtained in real time, the initial association vector is input into a preset softmax layer, and the corresponding probability matrix is ​​output in real time through the preset softmax layer; The probability matrix is ​​input into a preset onehot coding layer, and the probability matrix is ​​coded in real time by the preset onehot coding layer to output the corresponding target relationship code in real time; The target relationship code is converted in real time to generate an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time.

[0055] Furthermore, the receiving module is specifically used for: When the initial association vector is obtained in real time, the corresponding fully connected network is called out in real time in the preset softmax layer; The fully connected network is fully scanned to detect in real time a number of original network nodes corresponding to the interior of the fully connected network, and each of the initial association vectors is correspondingly filled into the interior of each of the original network nodes to output the probability matrix in real time.

[0056] Furthermore, the expression of the algorithm for performing real-time encoding processing on the probability matrix through the preset onehot encoding layer is:

[0057] Among them, g ij represents the target relation encoding, p i represents the horizontal matrix parameter in the probability matrix, h i represents the vertical matrix parameter in the probability matrix, τ represents the temperature coefficient, and N represents the number of target relationship codes.

[0058] Furthermore, the calculation module is specifically used for: When the target feature vector is acquired in real time, the corresponding preset algorithm is called out in real time in the preset database; Each of the target feature vectors is input into the preset algorithm in real time, so that the preset algorithm outputs the information weight corresponding to each of the target information in real time.

[0059] Furthermore, the expression of the preset algorithm is:

[0060] Among them, w j (Q, I) represents the information weight, K represents the number of target feature vectors, QI j T represents the target feature vector, D 1 represents the size of the target feature vector.

[0061] A fourth embodiment of the present invention provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the information fusion method described above when executing the computer program.

[0062] A fifth embodiment of the present invention provides a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the information fusion method as described above.

[0063] In summary, the information fusion method and system provided by the above embodiments of the present invention can avoid the generation of complex calculations and data, thereby being able to quickly and effectively complete the fusion of various target information, thereby correspondingly improving work efficiency.

[0064] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0065] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0066] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0067] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0068] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0069] The above-described embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. An information fusion method, characterized in that: The method comprises: Receiving multiple target information sent by multiple intelligent systems in real time, and generating an adjacency relationship matrix corresponding to the multiple intelligent systems in real time according to the multiple target information based on preset rules, wherein each intelligent system corresponds to one target information; In the adjacency matrix, corresponding target matrix parameters are screened out in real time, and corresponding information matrix is ​​generated in real time according to the target matrix parameters; Performing feature extraction processing on the information matrix to generate a corresponding target feature vector in real time, and calculating the information weight corresponding to each target information in real time according to the target feature vector; Convolution fusion processing is performed according to the target feature vector and the information weight to generate a target information vector corresponding to the plurality of target information in real time.

2. The information fusion method according to claim 1, characterized in that: The step of generating an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time according to the plurality of target information based on preset rules comprises: When a plurality of target information is acquired in real time, the plurality of target information is input into a preset feature extraction network accordingly, so that the feature extraction network outputs a corresponding initial association vector in real time; The initial association vector is matrix-processed to generate adjacency relationship matrices corresponding to the plurality of intelligent systems in real time.

3. The information fusion method according to claim 2, characterized in that: The step of performing matrix processing on the initial association vector to generate adjacency relationship matrices corresponding to the plurality of intelligent systems in real time comprises: When the initial association vector is obtained in real time, the initial association vector is input into a preset softmax layer, and the corresponding probability matrix is ​​output in real time through the preset softmax layer; The probability matrix is ​​input into a preset onehot coding layer, and the probability matrix is ​​coded in real time by the preset onehot coding layer to output the corresponding target relationship code in real time; The target relationship code is converted in real time to generate an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time.

4. The information fusion method according to claim 3, characterized in that: The step of outputting the corresponding probability matrix in real time through the preset softmax layer includes: When the initial association vector is obtained in real time, the corresponding fully connected network is called out in real time in the preset softmax layer; The fully connected network is fully scanned to detect in real time a number of original network nodes corresponding to the interior of the fully connected network, and each of the initial association vectors is correspondingly filled into the interior of each of the original network nodes to output the probability matrix in real time.

5. The information fusion method according to claim 3, characterized in that: The expression of the algorithm for real-time encoding processing of the probability matrix through the preset onehot encoding layer is: Among them, g ij represents the target relation encoding, p i represents the horizontal matrix parameter in the probability matrix, h i represents the vertical matrix parameter in the probability matrix, τ represents the temperature coefficient, and N represents the number of target relationship codes.

6. The information fusion method according to claim 1, characterized in that: The step of calculating in real time the information weight corresponding to each of the target information according to the target feature vector comprises: When the target feature vector is acquired in real time, the corresponding preset algorithm is called out in real time in the preset database; Each of the target feature vectors is input into the preset algorithm in real time, so that the preset algorithm outputs the information weight corresponding to each of the target information in real time.

7. The information fusion method according to claim 6, characterized in that: The expression of the preset algorithm is: Among them, w j (Q, I) represents the information weight, K represents the number of target feature vectors, QI j T represents the target feature vector, and D1 represents the size of the target feature vector.

8. An information fusion system, characterized in that: The system comprises: A receiving module, used for receiving a plurality of target information sent by a plurality of intelligent systems in real time, and generating an adjacency relationship matrix corresponding to the plurality of intelligent systems in real time according to the plurality of target information based on a preset rule, wherein each intelligent system corresponds to one piece of target information; A screening module, used for screening corresponding target matrix parameters in the adjacency matrix in real time, and generating corresponding information matrix in real time according to the target matrix parameters; A calculation module, used for performing feature extraction processing on the information matrix to generate a corresponding target feature vector in real time, and calculating the information weight corresponding to each target information in real time according to the target feature vector; A fusion module is used to perform convolution fusion processing according to the target feature vector and the information weight to generate a target information vector corresponding to the target information in real time.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the information fusion method according to any one of claims 1 to 7 is implemented.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the information fusion method according to any one of claims 1 to 7 is implemented.

Images