A network communication method and system based on mass data transmission

Abstract

The present invention relates to the technical field of data transmission, and specifically discloses a network communication method and system based on mass data transmission, the method comprising: packaging the data to be transmitted according to preset data conditions; converting the data to be transmitted into a data graph, comparing the data graph, and determining a preset number of node graphs; randomly determining a prediction graph based on the node graph, comparing the prediction graph with the corresponding data graph, and obtaining an accuracy rate; when the accuracy rate reaches a preset accuracy rate threshold, packaging the node graph and sending it to the requesting end. The present invention performs packaged transmission on the data to be transmitted, determines the amount of data of the packaged content at one time according to the configuration of the requesting end and its request, determines a preset number of node data in the packaged content, and sends it to the user; the user only needs to receive a small amount of node data, and then combines it with the preset inference rules to obtain data within a period of time, while reducing the transmission pressure, ensuring the adequacy of the data as much as possible.

Description

Technical Field

[0001] The present invention relates to the technical field of data transmission, and in particular to a network communication method and system based on mass data transmission. Background Art

[0002] Some existing data, such as long-range monitoring maps, are large in volume and require real-time transmission. This places high demands on data transceiver equipment, but the equipment cost for ordinary people makes it difficult to meet both content integrity and real-time transmission requirements.

[0003] In order to balance the content integrity and transmission real-time, most of the existing data transmission solutions ensure real-time, simplify the data, and then transmit it to the user in real time; for some data transceiver devices, especially the receiving device, the performance of the signal receiving module is extremely low. In addition, combined with the influence of the network environment, the sender needs to reduce the amount of data details to a very low level to ensure real-time; it can be imagined that when the amount of details is low, the user's viewing experience is very poor; therefore, how to better balance the content integrity and transmission real-time is the technical problem that the technical solution of the present invention wants to solve. Summary of the invention

[0004] The object of the present invention is to provide a network communication method and system based on mass data transmission to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A network communication method based on mass data transmission, the method comprising:

[0007] Packing the data to be transmitted according to preset data conditions; the data conditions are related to the minimum configuration and communication requirements of the requesting end;

[0008] Converting the data to be transmitted into a data graph, comparing the data graph, and determining a preset number of node graphs;

[0009] Randomly determine a prediction graph based on the node graph, compare the prediction graph with the corresponding data graph, and obtain an accuracy rate;

[0010] When the accuracy reaches a preset accuracy threshold, the node graph is packaged and sent to the requesting end.

[0011] As a further solution of the present invention: the step of packaging the data to be transmitted according to the preset data conditions includes:

[0012] Querying the registered requesting end to determine the minimum configuration, and determining the first packaged data volume according to the minimum configuration;

[0013] Query the required time interval and data receiving and sending speed of the requesting end, and calculate the second packaged data volume according to the required time interval and data receiving and sending speed;

[0014] Compare the first packaged data volume with the second packaged data volume, and select the minimum value as the data condition;

[0015] The data to be transmitted is received in real time, and the data to be transmitted is packaged based on the data condition.

[0016] As a further solution of the present invention: the step of converting the data to be transmitted into a data graph, comparing the data graph, and determining a preset number of node graphs includes:

[0017] Calculate the characteristic value of each data to be transmitted according to a preset fitting formula to obtain a characteristic value group in time order;

[0018] Traversing the data to be transmitted, performing binarization processing on each pixel according to a preset color value condition, and obtaining a data graph;

[0019] Clustering pixels of the data graph to determine contours of various types of pixels;

[0020] The data graph containing the contour lines is compared, and a preset number of node graphs are determined according to the comparison result and the eigenvalue group.

[0021] As a further solution of the present invention: the step of clustering pixels of the data graph to determine the contours of various types of pixels includes:

[0022] Randomly select a point as the center point, take the center point as the center of the circle, and establish a detection circle with the preset value as the radius;

[0023] Acquire all data points in the detection circle, and calculate the offset based on all data points and the center point;

[0024] Update the center point according to the offset, and calculate the distance between the two center points;

[0025] The above steps are repeated until the distance between the two center points is less than the preset threshold, and a point cluster with the center point position as the label is obtained;

[0026] Determine contour lines from all point clusters.

[0027] As a further solution of the present invention: the step of obtaining all data points in the detection circle and calculating the offset based on all data points and the center point comprises:

[0028] Get the positions of all data points and the center point;

[0029] Query the color values ​​corresponding to all data points and the center point in the transmission data graph;

[0030] Input the position and the color value into a preset calculation formula to obtain an offset;

[0031] The calculation formula is:

[0032]

[0033] In the formula, P is the offset, C is the constant term, and h s is the radius in the color value domain, h r is the radius in the spatial domain, x s is the color value at the data point, is the color value at the center point, x r is the location of the data point, is the position of the center point, and K is the number of data points.

[0034] As a further solution of the present invention: the step of comparing the data graph containing contour lines and determining a preset number of node graphs according to the comparison result and the eigenvalue group comprises:

[0035] Input the data graph containing contour lines into the trained shape matching model, and calculate the similarity of adjacent data graphs in sequence;

[0036] Determine a similarity threshold of an arithmetic progression, segment the data graph according to the similarity threshold, obtain a data set and calculate the number of sets;

[0037] Calculate the deviation rate between the number of sets and a preset number, and select the number of sets and its data set corresponding to the minimum deviation rate;

[0038] Select the middle elements and end elements in the data set as the node graph.

[0039] As a further solution of the present invention: the step of randomly determining a prediction graph based on the node graph, comparing the prediction graph with the corresponding data graph, and obtaining the accuracy rate comprises:

[0040] Query the node graph and predict the motion trajectory based on the end elements and middle elements;

[0041] Determine a prediction graph according to the motion trajectory and the end elements;

[0042] Based on the time sequence query and prediction corresponding data graph and compare them to get the accuracy rate.

[0043] The technical solution of the present invention also provides a network communication system based on mass data transmission, the system comprising:

[0044] A data packaging module, used to package the data to be transmitted according to preset data conditions; the data conditions are related to the minimum configuration and communication requirements of the requesting end;

[0045] A node graph determination module, used to convert the data to be transmitted into a data graph, compare the data graph, and determine a preset number of node graphs;

[0046] An accuracy calculation module, used to randomly determine a prediction graph based on the node graph, compare the prediction graph with the corresponding data graph, and obtain an accuracy rate;

[0047] The data sending module is used to package the node graph and send it to the requesting end when the accuracy reaches a preset accuracy threshold.

[0048] As a further solution of the present invention: the data packaging module includes:

[0049] A first determining unit is used to query the requesting end of the record, determine the minimum configuration, and determine the first packaged data volume according to the minimum configuration;

[0050] A second determining unit, configured to query a required time interval and a data transmission and reception speed of the requesting end, and calculate a second packaged data volume according to the required time interval and the data transmission and reception speed;

[0051] A condition generating unit, used for comparing the first packaged data amount and the second packaged data amount, and selecting the minimum value as the data condition;

[0052] The data receiving unit is used to receive the data to be transmitted in real time and package the data to be transmitted based on the data condition.

[0053] As a further solution of the present invention: the node graph determination module includes:

[0054] The characteristic value determination unit is used to calculate the characteristic value of each data to be transmitted according to a preset fitting formula to obtain a characteristic value group in time order;

[0055] A data map generating unit, used for traversing the data to be transmitted, performing binarization processing on each pixel according to a preset color value condition, and obtaining a data map;

[0056] A contour line determination unit, used to cluster pixels of the data graph to determine contour lines of various types of pixels;

[0057] The comparison prediction unit is used to compare the data graph containing the contour line, and determine a preset number of node graphs according to the comparison result and the characteristic value group.

[0058] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention performs packaged transmission on the data to be transmitted, determines the data volume of the packaged content according to the configuration of the requesting end and its request, determines a preset number of node data in the packaged content, and sends it to the user; the user only needs to receive a small amount of node data, and then combines it with the preset inference rules to obtain data within a period of time, thereby reducing the transmission pressure while ensuring the adequacy of the data as much as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0060] Figure 1 The present invention is a flowchart of a network communication method based on mass data transmission.

[0061] Figure 2 This is a first sub-process flowchart of a network communication method based on mass data transmission.

[0062] Figure 3 This is a second sub-flow chart of the network communication method based on mass data transmission.

[0063] Figure 4 This is a block diagram of the third sub-process of the network communication method based on mass data transmission.

[0064] Figure 5 This is a structural block diagram of a network communication system based on mass data transmission. DETAILED DESCRIPTION

[0065] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0066] Example 1

[0067] Figure 1 The flowchart of the network communication method based on the mass data transmission is as follows. In the embodiment of the present invention, a network communication method based on the mass data transmission includes:

[0068] Step S100: Packing the data to be transmitted according to preset data conditions; the data conditions are related to the minimum configuration and communication requirements of the requesting end;

[0069] Before describing the method, the application scenario of the technical solution of the present invention is briefly described. The data faced by the technical solution of the present invention are high-altitude long-range images with large areas and small motion areas. These long-range images are completed by preset high-altitude acquisition equipment, such as cameras or drones installed at high altitudes; the images acquired by the high-altitude acquisition equipment have a very large amount of data, and users can only view the images through dedicated high-performance devices. If the performance of the equipment is not high or the transmission speed of the transmission module is low, the user's query process will be very inconvenient, either the real-time performance cannot be guaranteed, or the data integrity is difficult to guarantee. Therefore, the present invention obtains the minimum configuration and communication requirements (real-time requirements) of the requesting end, packages the data to be transmitted according to the minimum configuration and communication requirements of the requesting end, simplifies the packaged data, and then sends it to the user. Among them, the data to be transmitted is a high-altitude long-range image.

[0070] Step S200: converting the data to be transmitted into a data graph, comparing the data graph, and determining a preset number of node graphs;

[0071] By converting the data to be transmitted, relatively simple data that is easy to analyze can be obtained, that is, the data graph. By comparing the data graphs corresponding to multiple data to be transmitted in the same packaging result, a representative data graph can be selected as a reference node, which is called a node graph.

[0072] Step S300: randomly determining a prediction graph based on the node graph, and comparing the prediction graph with a corresponding data graph to obtain an accuracy rate;

[0073] Based on the node graph, the prediction graph is determined according to the preset inference rules, and then the prediction graph is compared with the corresponding real data graph to obtain an accuracy rate, which is used to reflect whether the node graph and the prediction process are accurate.

[0074] Step S400: When the accuracy reaches a preset accuracy threshold, the node graph is packaged and sent to the requesting end;

[0075] If the accuracy reaches the preset accuracy threshold, it means that it is accurate enough. At this time, the node graph is packaged and sent to the user as the final output. After receiving the packaged node graph, the user can obtain the desired content according to the user's needs and the inference rules. While ensuring the real-time transmission (less content is transmitted), the integrity of the data is guaranteed as much as possible.

[0076] Figure 2 This is a first sub-flow diagram of a network communication method based on mass data transmission, wherein the step of packaging the data to be transmitted according to the preset data conditions includes:

[0077] Step S101: querying the registered requesting end, determining the minimum configuration, and determining the first packaged data volume according to the minimum configuration;

[0078] Step S102: querying the required time interval and data receiving and sending speed of the requesting end, and calculating the second packaged data volume according to the required time interval and data receiving and sending speed;

[0079] Step S103: Compare the first packaged data volume and the second packaged data volume, and select the minimum value as the data condition;

[0080] Step S104: receiving the data to be transmitted in real time, and packaging the data to be transmitted based on the data condition.

[0081] The minimum configuration in the request end and the demand information sent by the request end jointly determine the amount of packaged data in a packaging process, and a smaller amount of packaged data is selected as the final amount of packaged data; in this method, the larger the amount of packaged data, the worse the real-time performance and the smaller the transmission pressure (the number of node graphs is certain, and the data represented is more).

[0082] Figure 3 The second sub-flow chart of the network communication method based on mass data transmission, wherein the steps of converting the data to be transmitted into a data graph, comparing the data graph, and determining a preset number of node graphs include:

[0083] Step S201: Calculate the characteristic value of each data to be transmitted according to a preset fitting formula to obtain a characteristic value group in time order;

[0084] The fitting formula can be determined based on the existing technology. For example, each data to be transmitted is first converted into grayscale, and then the mean of all grayscales is calculated. The final mean is the eigenvalue; the similarity of eigenvalues ​​is a necessary but not sufficient condition for the similarity of two data to be transmitted.

[0085] Step S202: traverse the data to be transmitted, and perform binarization processing on each pixel according to a preset color value condition to obtain a data graph;

[0086] The data to be transmitted is traversed, and each pixel is binarized according to the preset color value condition. The processing process is relatively easy. The pixel points that meet the color value condition are set to one, and the pixel points that do not meet the color value condition are set to zero. The graph composed of zero and one is called a data graph.

[0087] Step S203: clustering pixels of the data graph to determine contours of each type of pixel;

[0088] The zero in the data map is regarded as the background, and the one in the data map is regarded as the pixel point to be classified. After clustering the pixel points, some contour lines can be determined; in the application scenario of the technical solution of the present invention, the user will set the color value conditions according to the actual situation, so that the background is zero and the dynamic area is one.

[0089] Step S204: comparing the data graph containing the contour lines, and determining a preset number of node graphs according to the comparison result and the eigenvalue group;

[0090] By comparing the data graphs containing contour lines, the data graphs can be classified. For example, if there is a person walking in an area, all data graphs containing this person will be classified into one category. If a second person appears, the two will be different. Combining the two parameters of contour lines and eigenvalues, some node graphs can be determined. These node graphs are the focus of the packaged data graphs.

[0091] As a preferred embodiment of the technical solution of the present invention, the step of clustering pixels of the data graph to determine the contours of various types of pixels includes:

[0092] Randomly select a point as the center point, take the center point as the center of the circle, and establish a detection circle with the preset value as the radius;

[0093] Acquire all data points in the detection circle, and calculate the offset based on all data points and the center point;

[0094] Update the center point according to the offset, and calculate the distance between the two center points;

[0095] The above steps are repeated until the distance between the two center points is less than the preset threshold, and a point cluster with the center point position as the label is obtained;

[0096] The above content is a real-life application based on the meanshift clustering algorithm. The specific description of the meanshift clustering algorithm is as follows:

[0097] 1. Randomly select a point among the unlabeled data points as the original center point.

[0098] 2. Find all the data points in the sphere with the center point as the sphere center and the radius as R, and consider them as cluster C. At the same time, record the number of times these data points appear in cluster C + 1; because the data faced by the technical solution of the present invention is two-dimensional, what is determined is the detection circle, not the detection sphere.

[0099] 3. Take the center of the sphere as the starting point and the sample point inside the sphere as the end point, add their vectors and average them to get the meanshift value.

[0100] 4. The center of the sphere + the value of meanshift to get the updated center of the sphere.

[0101] 5. Repeat 234 until meanshift is very small or does not move, and record the center point at this time. Note that all points encountered during the iteration should be classified into C.

[0102] 6. Determine whether the distance between the center point of class C and the center points of other existing classes at the time of convergence is less than the threshold. If so, merge them and the number of occurrences of the data points should also be merged. If so, treat C as a new cluster.

[0103] 7. Repeat 123456 until all points are marked as visited.

[0104] 8. For each point, the point belongs to the class with the most visits.

[0105] Determine contour lines based on all point clusters;

[0106] After the point cluster is determined, the process of determining the contour line is not difficult. Connecting boundary points or optimizing on this basis are both feasible technical solutions. Since the role of the contour line is to compare with each other, the technical solution of the present invention does not limit its accuracy requirements.

[0107] As a preferred embodiment of the technical solution of the present invention, the step of obtaining all data points in the detection circle and calculating the offset based on all data points and the center point includes:

[0108] Get the positions of all data points and the center point;

[0109] Query the color values ​​corresponding to all data points and the center point in the transmission data graph;

[0110] Input the position and the color value into a preset calculation formula to obtain an offset;

[0111] The calculation formula is:

[0112]

[0113] In the formula, P is the offset, C is the constant term, and h s is the radius in the color value domain, h r is the radius in the spatial domain, x s is the color value at the data point, is the color value at the center point, x r is the location of the data point, is the position of the center point, and K is the number of data points.

[0114] It should be noted that the above formula determines the offset from both the spatial domain and the color value domain. This is a further expansion of the traditional meanshift algorithm (only spatial distance), that is, the color value parameter is introduced. Represents color information. The more similar the colors are, the larger the value is. The information representing the spatial position, the closer to the center point, the greater its value; it is worth mentioning that the color value refers to the color value in the data to be transmitted, and there is no parameter of color value in the data graph. This process involves the correspondence between the data graph and the data to be transmitted. Since the data graph originates from the data to be transmitted, this correspondence belongs to known data.

[0115] As a preferred embodiment of the technical solution of the present invention, the step of comparing the data graph containing contour lines and determining a preset number of node graphs according to the comparison result and the eigenvalue group includes:

[0116] Input the data graph containing contour lines into the trained shape matching model, and calculate the similarity of adjacent data graphs in sequence;

[0117] Contour lines are compared and similarity is calculated; the judging process of the contour line similarity is determined by a preset shape matching model, and the shape matching model is determined by the staff based on the existing technology.

[0118] Determine a similarity threshold of an arithmetic progression, segment the data graph according to the similarity threshold, obtain a data set and calculate the number of sets;

[0119] The data to be transmitted and the data graph in the technical solution of the present invention are sorted by time by default. Since they are monitoring images in reality, the contents of adjacent data graphs in the time domain are similar in themselves, unless a mutation occurs. By calculating the similarity of adjacent data graphs, some mutation moments (the similarity reaches a certain similarity threshold) can be determined, and the data graphs can be segmented based on these mutation moments to obtain multiple data sets.

[0120] Calculate the deviation rate between the number of sets and a preset number, and select the number of sets and its data set corresponding to the minimum deviation rate;

[0121] Select the middle elements and end elements in the data set as the node graph;

[0122] When the number of data sets meets the conditions, data graphs are selected from each database as node graphs.

[0123] Figure 4 The third sub-flow chart of the network communication method based on mass data transmission, wherein the step of randomly determining a prediction graph based on the node graph, comparing the prediction graph with the corresponding data graph, and obtaining the accuracy rate comprises:

[0124] Step S301: query the node graph and predict the motion trajectory according to the end elements and the middle elements;

[0125] Step S302: determining a prediction graph according to the motion trajectory and the end elements;

[0126] Step S303: query and compare the data graph corresponding to the prediction based on the time sequence to obtain the accuracy rate;

[0127] Step S300 and step S400 complement each other, therefore, only step S300 is described in detail. The change of the contour can be determined by the end distant elements and the middle elements, and this change is called the motion trajectory. Some conventional predictions can be made by the motion trajectory and the end elements to obtain a prediction graph. By querying the corresponding data graph based on time and comparing the prediction graph with the data graph, the accuracy of the prediction process can be determined.

[0128] Example 2

[0129] Figure 5 1 is a structural block diagram of a network communication system based on mass data transmission. In an embodiment of the present invention, a network communication system based on mass data transmission, the system 10 includes:

[0130] The data packaging module 11 is used to package the data to be transmitted according to the preset data conditions; the data conditions are related to the minimum configuration and communication requirements of the requesting end;

[0131] A node graph determination module 12, configured to convert the data to be transmitted into a data graph, compare the data graph, and determine a preset number of node graphs;

[0132] An accuracy calculation module 13 is used to randomly determine a prediction graph based on the node graph, compare the prediction graph with the corresponding data graph, and obtain an accuracy rate;

[0133] The data sending module 14 is used to package the node graph and send it to the requesting end when the accuracy reaches a preset accuracy threshold.

[0134] The data packaging module 11 includes:

[0135] A first determining unit is used to query the requesting end of the record, determine the minimum configuration, and determine the first packaged data volume according to the minimum configuration;

[0136] A second determining unit, configured to query a required time interval and a data transmission and reception speed of the requesting end, and calculate a second packaged data volume according to the required time interval and the data transmission and reception speed;

[0137] A condition generating unit, used for comparing the first packaged data amount and the second packaged data amount, and selecting the minimum value as the data condition;

[0138] The data receiving unit is used to receive the data to be transmitted in real time and package the data to be transmitted based on the data condition.

[0139] The node graph determination module 12 comprises:

[0140] The characteristic value determination unit is used to calculate the characteristic value of each data to be transmitted according to a preset fitting formula to obtain a characteristic value group in time order;

[0141] A data map generating unit, used for traversing the data to be transmitted, performing binarization processing on each pixel according to a preset color value condition, and obtaining a data map;

[0142] A contour line determination unit, used to cluster pixels of the data graph to determine contour lines of various types of pixels;

[0143] The comparison prediction unit is used to compare the data graph containing the contour line, and determine a preset number of node graphs according to the comparison result and the characteristic value group.

[0144] The functions that can be achieved by the above-mentioned network communication method based on large-scale data transmission are all completed by a computer device, and the computer device includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories. The program code is loaded and executed by the one or more processors to achieve the functions of the network communication method based on large-scale data transmission.

[0145] The processor takes out instructions from the memory one by one, analyzes the instructions, and then completes the corresponding operations according to the instruction requirements, generating a series of control commands, so that the various parts of the computer can automatically, continuously and coordinately move to become an organic whole, realize the input of programs, the input of data, and the calculation and output of results. The arithmetic operations or logical operations generated in this process are all completed by the operator; the memory includes a read-only memory (ROM), which is used to store computer programs, and a protection device is provided outside the memory.

[0146] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0147] Those skilled in the art will understand that the description of the above service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, etc.

[0148] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.

[0149] The memory can be used to store computer programs and / or modules. The processor can realize various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as an information collection template display function, a product information release function, etc.); the data storage area can store data created according to the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to release, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0150] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the modules / units in the above-mentioned embodiment system, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can realize the functions of the above-mentioned various system embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0151] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0152] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A network communication method based on mass data transmission, characterized in that: The method comprises: Packing the data to be transmitted according to preset data conditions; the data conditions are related to the minimum configuration and communication requirements of the requesting end; Converting the data to be transmitted into a data graph, comparing the data graph, and determining a preset number of node graphs; Randomly determine a prediction graph based on the node graph, compare the prediction graph with the corresponding data graph, and obtain an accuracy rate; When the accuracy reaches a preset accuracy threshold, the node graph is packaged and sent to the requesting end; The step of converting the data to be transmitted into a data graph, comparing the data graph, and determining a preset number of node graphs includes: Calculate the characteristic value of each data to be transmitted according to a preset fitting formula to obtain a characteristic value group in time order; Traversing the data to be transmitted, performing binarization processing on each pixel according to a preset color value condition, and obtaining a data graph; Clustering pixels of the data graph to determine contours of various types of pixels; Comparing the data graph containing the contour lines, and determining a preset number of node graphs according to the comparison result and the eigenvalue group; The step of clustering pixels of the data graph to determine the contours of various types of pixels comprises: Randomly select a point as the center point, take the center point as the center of the circle, and establish a detection circle with the preset value as the radius; Acquire all data points in the detection circle, and calculate the offset based on all data points and the center point; Update the center point according to the offset, and calculate the distance between the two center points; The above steps are repeated until the distance between the two center points is less than the preset threshold, and a point cluster with the center point position as the label is obtained; Determine contour lines based on all point clusters; The step of obtaining all data points in the detection circle and calculating the offset based on all data points and the center point comprises: Get the positions of all data points and the center point; Query the color values ​​corresponding to all data points and the center point in the transmission data graph; Input the position and the color value into a preset calculation formula to obtain an offset; The calculation formula is: In the formula, P is the offset, C is the constant term, and h s is the radius in the color value domain, h r is the radius in the spatial domain, x s is the color value at the data point, is the color value at the center point, x r is the location of the data point, is the position of the center point, K is the number of data points; the color value refers to the color value in the data to be transmitted; The step of comparing the data graph containing contour lines and determining a preset number of node graphs according to the comparison result and the eigenvalue group comprises: Input the data graph containing contour lines into the trained shape matching model, and calculate the similarity of adjacent data graphs in sequence; Determine a similarity threshold of an arithmetic progression, segment the data graph according to the similarity threshold, obtain a data set and calculate the number of sets; Calculate the deviation rate between the number of sets and a preset number, and select the number of sets and its data set corresponding to the minimum deviation rate; Select the middle elements and end elements in the data set as the node graph.

2. The network communication method based on mass data transmission according to claim 1, characterized in that: The step of packaging the data to be transmitted according to the preset data conditions comprises: Querying the registered requesting end to determine the minimum configuration, and determining the first packaged data volume according to the minimum configuration; Query the required time interval and data receiving and sending speed of the requesting end, and calculate the second packaged data volume according to the required time interval and data receiving and sending speed; Compare the first packaged data volume with the second packaged data volume, and select the minimum value as the data condition; The data to be transmitted is received in real time, and the data to be transmitted is packaged based on the data condition.

3. The network communication method based on mass data transmission according to claim 1, characterized in that: The step of randomly determining a prediction graph based on the node graph, and comparing the prediction graph with a corresponding data graph to obtain an accuracy rate comprises: Query the node graph and predict the motion trajectory based on the end elements and middle elements; Determine a prediction graph according to the motion trajectory and the end elements; Based on the time sequence query and prediction corresponding data graph and compare them to get the accuracy rate.

4. A network communication system based on mass data transmission, characterized in that: The system comprises: A data packaging module, used to package the data to be transmitted according to preset data conditions; the data conditions are related to the minimum configuration and communication requirements of the requesting end; A node graph determination module, used to convert the data to be transmitted into a data graph, compare the data graph, and determine a preset number of node graphs; An accuracy calculation module, used to randomly determine a prediction graph based on the node graph, compare the prediction graph with the corresponding data graph, and obtain an accuracy rate; A data sending module, used for packaging a node graph and sending it to a requesting end when the accuracy reaches a preset accuracy threshold; The node graph determination module comprises: The characteristic value determination unit is used to calculate the characteristic value of each data to be transmitted according to a preset fitting formula to obtain a characteristic value group in time order; A data map generating unit, used for traversing the data to be transmitted, performing binarization processing on each pixel according to a preset color value condition, and obtaining a data map; A contour line determination unit, used to cluster pixels of the data graph to determine contour lines of various types of pixels; A comparison prediction unit, used for comparing the data graph containing the contour line, and determining a preset number of node graphs according to the comparison result and the characteristic value group; The content of clustering pixels of the data graph to determine the contour lines of various types of pixels includes: Randomly select a point as the center point, take the center point as the center of the circle, and establish a detection circle with the preset value as the radius; Acquire all data points in the detection circle, and calculate the offset based on all data points and the center point; Update the center point according to the offset, and calculate the distance between the two center points; The above contents are executed repeatedly until the distance between the two center points is less than the preset threshold, and a point cluster with the center point position as the label is obtained; Determine contour lines based on all point clusters; The content of acquiring all data points in the detection circle and calculating the offset based on all data points and the center point includes: Get the positions of all data points and the center point; Query the color values ​​corresponding to all data points and the center point in the transmission data graph; Input the position and the color value into a preset calculation formula to obtain an offset; The calculation formula is: In the formula, P is the offset, C is the constant term, and h s is the radius in the color value domain, h r is the radius in the spatial domain, x s is the color value at the data point, is the color value at the center point, x r is the location of the data point, is the position of the center point, K is the number of data points; the color value refers to the color value in the data to be transmitted; The comparing the data graph containing contour lines and determining the content of the preset number of node graphs according to the comparing result and the eigenvalue group comprises: Input the data graph containing contour lines into the trained shape matching model, and calculate the similarity of adjacent data graphs in sequence; Determine a similarity threshold of an arithmetic progression, segment the data graph according to the similarity threshold, obtain a data set and calculate the number of sets; Calculate the deviation rate between the number of sets and a preset number, and select the number of sets and its data set corresponding to the minimum deviation rate; Select the middle elements and end elements in the data set as the node graph.

5. The network communication system based on mass data transmission according to claim 4, characterized in that: The data packaging module comprises: A first determining unit is used to query the requesting end of the record, determine the minimum configuration, and determine the first packaged data volume according to the minimum configuration; A second determining unit, configured to query a required time interval and a data transmission and reception speed of the requesting end, and calculate a second packaged data volume according to the required time interval and the data transmission and reception speed; A condition generating unit, used for comparing the first packaged data amount and the second packaged data amount, and selecting the minimum value as the data condition; The data receiving unit is used to receive the data to be transmitted in real time and package the data to be transmitted based on the data condition.

Images