Multimode protocol data processing method, system, equipment and medium

Abstract

The invention discloses a multimode protocol data processing method and device, equipment and a medium, and generally relates to the technical field of communication. The method comprises the steps that at least two first arrays are obtained, the at least two first arrays are data collected by at least two collection devices, and the data formats of the at least two first arrays comprise at least two data formats; the at least two first arrays are input into a multi-mode protocol adaptation model, at least two second arrays corresponding to the at least two first arrays are generated, the at least two second arrays are data in a target data format, and the multi-mode protocol adaptation model is used for processing the data formats of the second arrays into the data in the target data format; and performing data fusion processing on the at least two second arrays to obtain fused data, the fused data being ad hoc network data corresponding to the at least two first arrays.

Description

Technical Field

[0001] The present disclosure generally relates to the field of communication technology, and more particularly to a multi-mode protocol data processing method, system, device and medium. Background Art

[0002] With the continuous development of communication technology, ad hoc networking technology has become a very important network technology model in communication technology.

[0003] Self-organizing network technology has the characteristics of distribution, independent networking, and self-organization. In related technologies, self-organizing network has a wide range of application fields. For example, it can be applied to marine stereo wireless self-organizing network communication technology. In marine stereo wireless self-organizing network communication technology, due to the existence of water communication and underwater communication, in order to achieve self-organizing network communication technology, there may be multiple modes of communication equipment, that is, a multi-modal data form is formed. In this way, there will be many types of data, messy data, low quality, chaotic data architecture, and different storage. Summary of the invention

[0004] In view of the large number of data types in the self-organizing network communication technology in the related technology, the data is messy, the quality is low, the data structure is chaotic, and the storage is inconsistent.

[0005] In a first aspect, a multi-mode protocol data processing method is provided, the method comprising: Acquire at least two first arrays, where the at least two first arrays are data collected by at least two collection devices, and data formats of the at least two first arrays include at least two data formats; Inputting the at least two first arrays into a multimode protocol adaptation model, generating at least two second arrays corresponding to the at least two first arrays, wherein the at least two second arrays are data in a target data format, and the multimode protocol adaptation model is used to process the data format of the second arrays into data in the target data format; Data fusion processing is performed on the at least two second arrays to obtain fused data, where the fused data is the self-organizing network data corresponding to the at least two first arrays.

[0006] In the present application, at least two first arrays of at least two data formats collected by at least two acquisition devices are first obtained, and then the first arrays are input into the multi-mode protocol adaptation model to generate at least two second arrays corresponding to the at least two first arrays, wherein at least two second arrays are data in the target data format, and the multi-mode protocol adaptation model is used to process the data format of the second array into data in the target data format; finally, data fusion processing is performed on the at least two second arrays to obtain fused data. In this way, in the case of many data formats and rich acquisition devices, after collecting data through devices with multiple different protocols, the data can be input into the data used to process the data into the same target data format, unifying the data format, so that the data can be quickly fused in the future to obtain self-organizing network data for self-organizing network communication, greatly improving the data processing process, and at the same time greatly saving the resources consumed by the data processing process.

[0007] In a second aspect, a multimode protocol data processing system is provided, the system comprising a multimode protocol adaptation model, the system comprising an acquisition unit and an execution unit: The acquisition unit is used to acquire at least two first arrays, where the at least two first arrays are data collected by at least two acquisition devices, and the data formats of the first arrays include at least two data formats; The execution unit is used to input the at least two first arrays into the multimode protocol adaptation model to generate at least two second arrays corresponding to the at least two first arrays, the at least two second arrays are data in a target data format, and the multimode protocol adaptation model is used to process the data format of the second arrays into data in the target data format; The execution unit is further used to perform data fusion processing on the at least two second arrays to obtain fused data, where the fused data is the self-organizing network data corresponding to the at least two first arrays.

[0008] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the first aspect is implemented.

[0009] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the program is executed by a processor, the method described in the first aspect is implemented.

[0010] In a fifth aspect, a computer program product is provided. The computer program product includes instructions, and the instructions are executed by a processor to implement the method described in the first aspect.

[0011] 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

[0012] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 A flowchart of a multi-mode protocol data processing method provided in an embodiment of the present application; Figure 2 A schematic diagram of a multi-mode protocol data processing model in a multi-mode protocol data processing method provided in an embodiment of the present application; Figure 3 Another structural diagram of the multi-mode protocol data processing device provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0014] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The application scenario of the present application will be described as follows.

[0015] With the continuous development of communication technology, the Internet of Things technology is also developing continuously. Among them, self-organizing network is one of the key components of the perception layer of the Internet of Things, and it undertakes the task of distributed data collection and transmission.

[0016] The application scenarios of ad hoc network technology are very wide, for example, three-dimensional ocean wireless ad hoc network. With the improvement of the performance and large-scale application of three-dimensional ocean wireless ad hoc network, the amount of data in its three-dimensional ocean wireless ad hoc network has reached a massive level. At the same time, the data presents multimodal characteristics, a wide range of sources, and is not uniform. In ad hoc network communication, it is ultimately necessary to fuse and process data from all sources in order to transmit data to the communication devices in the entire ad hoc network. However, the above-mentioned data sources are complex, the data formats are different, and the amount of data is extremely large, which brings great challenges to data fusion processing.

[0017] In the related technologies, facing the above multi-source data, most of the data fusion technologies are designed from four levels: data processing model, stage-based strategy, feature representation-based method and semantic-based application, and multi-source multi-modal data fusion and integration technology is designed. In addition, multi-modal data fusion modes and key technologies are designed, and intra-network and inter-network multi-modal data fusion systems are established. The advantages and disadvantages of the three major architectures of collaboration, union and codec are analyzed, and problems such as multi-modal video clip retrieval, information generation content summary, and multi-modal human-computer dialogue system are solved.

[0018] However, the above methods can realize the fusion processing of multimodal data in the fields of electricity and agriculture, but because these technologies are cumbersome and have high computational complexity, they are difficult to meet the real-time requirements in the marine environment. Therefore, the application effect in the field of three-dimensional marine self-organizing networks is less ideal.

[0019] Based on this, the present application proposes a multi-mode protocol data processing method, device, equipment and medium, which can solve the problems of a large number of data types, messy data, low data quality, chaotic data structure, and inconsistent storage in the self-organizing network communication technology in the related technology.

[0020] Figure 1 FIG. 1 is a flow chart of a multi-mode protocol data processing method provided by an embodiment of the present application. Figure 1 As shown, the method includes the following steps 301 to 303: Step 301: Obtain at least two first arrays.

[0021] In an embodiment of the present application, the first array is data collected by at least two collection devices, and the data format of the first array includes at least two data formats.

[0022] In the embodiment of the present application, each of the above-mentioned first arrays includes multiple data.

[0023] It can be understood that, for each first array, it is the communication data collected by any device within a period of time. Therefore, the communication data will include multiple data to form a series, and each series constitutes a first array.

[0024] It should be noted that the period of time for any of the above-mentioned devices to collect communication data can be customized by the user, preset by the device, or uniformly agreed upon by the self-organizing network. That is, the first array of devices in the self-organizing network is an array composed of data obtained within a fixed period of time. The embodiments of the present application do not limit this.

[0025] In the embodiment of the present application, the data included in the at least two first arrays are data acquired by at least two different acquisition devices, and the data formats included in the at least two first arrays are also different.

[0026] Exemplarily, the data in the at least two first arrays are highly heterogeneous. Specifically, the data in the first arrays may differ in at least one of the three parameters of data format, acquisition frequency, and resolution.

[0027] It is understandable that in the embodiment of the present application, since its application scenario is a self-organizing network scenario including multiple devices and different device protocols, based on this, the data formats corresponding to the arrays generated by different devices are also different, and based on this situation, the situation of large data volume, complex data format and chaotic data in the related technology is generated. For related problems in the related technology, no matter how many types of devices generate data, the essence of the problem lies in the different protocols generated by different devices. Therefore, the subsequent multi-mode protocol adaptation model in the embodiment of the present application is required to unify the format of the above-mentioned at least two first arrays.

[0028] In the embodiment of the present application, after obtaining the above-mentioned at least two first arrays, the multimode protocol adaptation model is subsequently used in step 302 to unify the formats of the above-mentioned at least two first arrays with different formats. In order to improve processing efficiency and processing accuracy, the at least two first arrays input into the multimode protocol adaptation model are first arrays that have been subjected to noise reduction processing. The noise reduction processing process is described as follows.

[0029] Optionally, in an embodiment of the present application, the above-mentioned acquisition and at least two first arrays include: acquiring a third array through the above-mentioned at least two acquisition devices, performing noise reduction processing on the above-mentioned at least two third arrays, and generating at least two first arrays corresponding to the above-mentioned third arrays.

[0030] Exemplarily, the above-mentioned noise reduction process includes at least one of the following: an NLM algorithm and a Kalman filter algorithm.

[0031] It is understandable that when there are many types of devices and different types of data are generated, the data needs to be denoised first.

[0032] Exemplarily, the above-mentioned noise reduction process may include at least one of the following: filtering out data noise and removing redundant data. The process of filtering out noise is completed by the NLM algorithm, and the process of removing redundant data is completed by the Kalman filter algorithm.

[0033] In one example, in the process of collecting the third array by the self-organizing network, assuming that the self-organizing network is a marine stereoscopic self-organizing network, in the third array obtained by the at least two acquisition devices, there will be data collected by various types of acquisition devices such as various sensors, underwater acoustic communication equipment, satellite remote sensing, etc. These data are the data in the third array.

[0034] It is understandable that when the ad hoc network is a marine stereoscopic ad hoc network, the above-mentioned marine environment changes rapidly, and the marine observation system will generate a large amount of real-time data streams, the amount of data is large and will continue to increase over time. At the same time, ad hoc network communication often requires real-time analysis and response, so the acquisition frequency of each acquisition device is relatively high. In the process of acquisition, due to the complex marine environment, the acquisition equipment is located in different locations in the ocean, the sea area and depth are different, which will generate various noise interferences, such as waves, tides, strong winds, etc., which will be collected by the acquisition equipment, thereby generating redundant data and noisy data.

[0035] Furthermore, in the case where the ad hoc network is a marine stereoscopic ad hoc network, the process of performing noise reduction processing on the third array may include both the NLM algorithm and the Kalman filter algorithm.

[0036] In this way, before performing data format processing and data fusion, the collected original data (that is, the third data mentioned above) is first effectively denoised through a noise reduction algorithm. In the subsequent data format processing and data fusion process, the reliability and effectiveness of the data can be greatly improved, providing high-quality data input for the subsequent self-organizing network communication application process.

[0037] Optionally, in an embodiment of the present application, when the above-mentioned noise reduction processing includes an NLM algorithm, the above-mentioned noise reduction processing is performed on the above-mentioned at least two third arrays to generate at least two first arrays corresponding to the above-mentioned third arrays, including: determining the target data from the above-mentioned at least two third arrays, and determining a search box according to the third array to which the above-mentioned target data belongs and the data interval of the third array, the above-mentioned target data is located at the center of the above-mentioned search box, and the above-mentioned search box includes multiple search points and denoised points corresponding to the above-mentioned target data; determining multiple similarities between the above-mentioned multiple search points and the denoised points; determining the neighborhood weight values ​​of the above-mentioned denoised points based on the above-mentioned multiple similarities; and determining the denoised data value of the above-mentioned denoised points through the NML algorithm based on the neighborhood weight values ​​of the above-mentioned denoised points.

[0038] Exemplarily, in each of the third arrays mentioned above, it can be seen from the above content that it includes multiple data, and each data may have noise. Therefore, it is necessary to remove noise from each data in each third array to obtain the third array after noise removal.

[0039] The noise removal process is described below through Example 1: Example 1: Assume that among multiple devices in an ad hoc network, one of the devices collects a third data array: , where the array is used to represent the real-time characteristics of real-time data in the ad hoc network. express Real-time data sequence of self-organizing network collected at all times, Indicates the total number of real-time data sequences collected from the ad hoc network.

[0040] Since each data sequence in the third array is composed of multiple different modal data, it is recorded as , Indicates time Collect the first data, Represents the total amount of data in the real-time data series.

[0041] When using the NLM algorithm to remove noise from real-time data, the core of the algorithm is to use the weighted average of similar blocks in the data to eliminate noise. The specific steps are as follows: Step 1: Randomly select a target modal data (i.e. the target data) from a data sequence in the third array, and take a box around the target modal data, set it as the search box, with search point a, side length s, and the target in the center of the search box. Set the denoising point b, side length d, and construct a neighborhood box to slide in the search box. The side length d of the search box is determined by the average interval between different data in the data sequence, and the side length s of the neighborhood box is determined by the side length of the search box.

[0042] Step 2: Calculate the similarity between point a and point b, expressed as follows: Formula 1 In the formula, Indicates the similarity between data points a and b; represents the normalization coefficient; Represents the search window With neighborhood window distance; represents the smoothing parameter.

[0043] The larger the value of the calculation result W(a, b) obtained by formula (1), the smaller the distance between point a and point b is, and the higher the similarity is.

[0044] Step 3: Traverse all the search points b in the search window and apply formula (1) to calculate all similarities W(a, b). Based on the calculation results, obtain the target denoised point The neighborhood weight value. Apply the NLM algorithm to process the target denoising point a to obtain the denoising result. The processing process uses the following formula (2): Formula (2) In the above formula (2), Represents the real-time data of the ad hoc network after denoising; Indicates the neighborhood weight value of the target denoising point.

[0045] Step 4: Apply formula (2) to process all collected data to obtain the denoised self-organizing network data set .

[0046] Optionally, in an embodiment of the present application, when the noise reduction processing includes a Kalman filtering algorithm, the noise reduction processing is performed on the at least two third arrays to generate at least two first arrays corresponding to the third arrays, including: determining the redundant data in each third array based on the posterior state estimate value of each data in each third array.

[0047] The Kalman filter algorithm is introduced as follows.

[0048] The basic mathematical model expression of the Kalman filter algorithm is: Formula (3) In formula (3), and Represents the posterior state estimate at the current moment and the previous moment; Represents process redundant data; represents the error adjustment term; Represents the actual data at the current moment; Represents the actual redundant data; A, B, and C represent the state transfer parameters, input control parameters, and output control parameters, respectively.

[0049] Example 2: In combination with the above example 1, in the marine ad hoc network, the data of the third array may be denoised first, and then the redundant data may be removed from the denoised data.

[0050] It can be understood that, combined with the self-organizing network data set in the above example 1 , each data in the above self-organizing network data set V is the , the state transfer parameters, input control parameters and output control parameters, that is, ABC in the above formula (3) are preset in advance, then according to these known quantities, we can calculate , that is, the process redundancy parameter, is used as the redundant data in the ad hoc network data set V.

[0051] Step 302: Input the at least two first arrays into a multi-mode protocol adaptation model to generate at least two second arrays corresponding to the at least two first arrays.

[0052] In an embodiment of the present application, the at least two second arrays are data in a target data format, and the multimode protocol adaptation model is used to process the data format of the second arrays into data in the target data format.

[0053] In the embodiment of the present application, the above-mentioned multi-mode protocol adaptation model is mainly used to unify the data format of the data in the first array to facilitate subsequent data fusion.

[0054] In the embodiment of the present application, the above-mentioned target data format can be user-defined or preset in the model.

[0055] It is understandable that different ad hoc networks may use different collection devices, and thus the data protocols corresponding to the collection devices are different. Therefore, the target data format may be determined according to the specific circumstances of the ad hoc network.

[0056] Furthermore, for communication data, the possible data protocols are limited, so multiple possible target data formats can be set in the multi-mode protocol adaptation model, and different target data formats correspond to different ad hoc networks. That is, the above multi-mode protocol adaptation model can be configured as a model that can be applied to any ad hoc network scenario.

[0057] In the embodiment of the present application, in order to unify the data in the first array, the general multi-mode protocol adaptation model will be constructed according to the usual protocol structure of the first array during the process of constructing the multi-mode protocol adaptation model.

[0058] In one example, the logical structure of the core protocol of the self-organizing network is mostly based on a tree structure. Therefore, in order to unify the data in the arrays of different protocols, all protocols will be converted into a tree semantic model that conforms to it. At the same time, the protocol adapter will be implemented with differentiated evolution to build a multi-mode protocol adaptation model.

[0059] Example 3: Figure 2 , introduces the layers of the multi-mode protocol adaptation model: Each node of the multimode protocol adaptation model has the same status as the multimode protocol adapter used to execute the method, so it is divided into a root node 201, a virtual node 202, a real node 203 and a branch node 204 according to its hierarchy.

[0060] The functions of these nodes are as follows: 1) Root node 201: The initial node of the multimode protocol adaptation model is set as the root node. The root node is the entry of the multimode protocol adaptation model and can be used to represent the initial state of the multimode protocol adapter.

[0061] 2) Virtual node 202: There is no direct association between this node and the protocol data element. It is used to represent the intermediate state in the process of protocol state transfer and to indicate that subsequent operations must be performed according to the previous state.

[0062] 3) Branch node 203: used to identify the data protocol corresponding to the first array.

[0063] 4) Real node 204: used to represent the adaptation status of different first arrays under different protocols and to unify the data format of the first arrays.

[0064] Step 303: Perform data fusion processing on the at least two second arrays to obtain fused data.

[0065] In the embodiment of the present application, the above-mentioned fused data is the self-organizing network data corresponding to the above-mentioned at least two first arrays.

[0066] It can be understood that in the embodiment of the present application, after the first data with different formats are processed using the multi-mode protocol adaptation model, they have been unified into the target data format. On this basis, in order to meet the real-time characteristics of self-organizing network data, a fast data fusion algorithm is adopted to achieve fast data fusion and optimize data quality.

[0067] Optionally, in an embodiment of the present application, the above-mentioned data fusion processing of the at least two second arrays to obtain fused data includes: performing data fusion on the at least two second arrays according to the weight coefficient of each second array in the at least two second arrays, the unbiased estimate value of each second array and the historical data mean of each second array to obtain fused data.

[0068] It is understandable that, during the fusion process of the at least two second arrays, the weight coefficients of different arrays need to be preset in advance, so that the fused data of the ad hoc network generated after the fusion is the data most needed by the user.

[0069] Exemplarily, the above-mentioned weight coefficient may be user-defined or preset, and the embodiments of the present application are not limited to this.

[0070] Exemplarily, the unbiased estimate value may be user-defined or preset, and this is not limited in the embodiments of the present application.

[0071] In one example, the method for fusing data may be a federation-based weighted average algorithm.

[0072] The following describes the process of fusing data using Example 4: Combined with the above example 3: Assuming that n second arrays are generated by the multimode protocol adaptation model in the above example 3 (n second arrays are at least two second arrays), the n second arrays can be defined as At the same time, according to the preset weight coefficient of each second array , and the unbiased estimate Q of each second array According to the data fusion formula, as shown in the following formula (4), the total mean square error of each second array is first determined.

[0073] Formula (4) Afterwards, the optimal weighting coefficient for all second arrays is solved according to the total mean square error of each second array, as shown in the following formula (5), and the optimal weighting coefficient is obtained by using the multivariate function extreme value solution method: Formula (5) Finally, combined with The historical data mean of the second array , minimize the mean square error , combined with the following formula (6), the fusion data of the ad hoc network is obtained as follows: Formula (6) In the method provided in the embodiment of the present application, after the authorization node receives the message from the requesting node requesting the credential, it can determine the authorized resource address of the service node for the requesting node, that is, the resource address accessible to the requesting node. Furthermore, the above-mentioned authorized resource address can also be compressed to obtain compressed resource information. Compared with the authorized resource address, the compressed resource information has a significantly reduced data volume, which greatly reduces the data volume of the authorized resource address. The compressed resource information is then filled into the credential and sent to the requesting node. While indicating the authorized resource address with the help of the compressed resource information, the problem of excessive data occupancy of the entire credential due to the authorized resource address is avoided, effectively saving the data volume overhead of the credential, thereby also saving the transmission resources between the requesting node and the service node to a certain extent, and improving the transmission efficiency.

[0074] Optionally, in an embodiment of the present application, a process of how the multimode protocol adaptation model specifically generates a second array is also provided. The step of inputting the first array into the multimode protocol adaptation model to generate the second array includes, in the multimode protocol data processing method provided in the present application: determining the data protocol type of each group of the at least two first arrays; according to the data protocol type of the first array, converting the data format of the first array into a target format through a data conversion formula to generate a second array.

[0075] It is understandable that, based on the aforementioned introduction of the hierarchical structure of the multimode protocol adaptation model, the real nodes of the multimode protocol adaptation model can be used to unify the format of each of the at least two second arrays.

[0076] In one example, the above-mentioned process of unifying the format of each second array is completed by adding formulas and programs for different protocols to the multi-mode protocol adaptation model. After the branch node identifies the specific protocol of each array in at least two second arrays, the determined protocol can be transmitted to the real node, and the real node starts format conversion for each second array according to the preset formulas and programs.

[0077] The following describes the data of Modbus protocol, CAN protocol, Ethernet protocol and other protocol data. Figure 2 , as shown in Example 5 below: Example 5: / / Convert Modbus protocol data into a unified target data format structModbusData { uint16_t address; uint16_t value; }; structUnifiedData { int id; float value; }; UnifiedDatamodbusToUnified(ModbusData data) { UnifiedData unified; unified.id = data.address; unified.value = static_cast <float>(data.value); return unified; } / / Convert CAN protocol data into a unified target data format structCANData { int id; int value; }; structUnifiedData { int id; float value; }; UnifiedDatacanToUnified(CANData data) { UnifiedData unified; unified.id = data.id; unified.value = static_cast <float>(data.value); return unified; } / / Convert Ethernet protocol data into a unified target data format structEthernetData { int protocol; int value; }; structUnifiedData { int id; float value; }; UnifiedDataethernetToUnified(EthernetData data) { UnifiedData unified; unified.id = data.protocol; unified.value = static_cast <float>(data.value); return unified; } / / Convert other protocol data into a unified target data format structOtherData { int type; int value; }; structUnifiedData { int id; float value; }; UnifiedDataotherToUnified(OtherData data) { UnifiedData unified; unified.id = data.type; unified.value = static_cast <float>(data.value); return unified; } Optionally, in an embodiment of the present application, a training method for a multimode protocol adaptation model is also disclosed. Exemplarily, before the above acquisition and at least two first arrays, the above method also includes: acquiring multiple groups of original arrays and multiple groups of target arrays; inputting the above multiple groups of original arrays into the above multimode protocol adaptation model to generate multiple groups of test arrays corresponding to the multiple groups of original arrays; comparing the above multiple groups of test data with the above multiple groups of target data, and determining the difference between the above multiple groups of test data and the above multiple groups of target data; when the above difference is greater than a preset threshold, adjusting the above multimode protocol adaptation model according to the above difference, so that the difference between the test data and the target data generated by the multimode protocol adaptation model is less than the preset threshold.

[0078] Exemplarily, the target array is an array composed of data in a target format corresponding one-to-one to the original arrays, the multiple groups of original arrays include data collected by at least two acquisition devices, and the multiple groups of original arrays include arrays corresponding to at least two protocols.

[0079] Exemplarily, the above-mentioned preset threshold may be preset in advance or may be user-defined.

[0080] Exemplarily, the above-mentioned preset threshold can be used to indicate whether the training results of the multi-mode protocol matching model meet user requirements. When the difference between the above-mentioned test data and the target data is less than the preset threshold, the training can be stopped to generate a qualified multi-mode protocol matching model. Otherwise, it is necessary to input multiple groups of original arrays again for training until the difference between the test data and the target data is less than the preset threshold.

[0081] It is understandable that after the multimode protocol adaptation model is constructed, it is necessary to train the multimode protocol adaptation model so that the multimode protocol adaptation model can accurately complete the above-mentioned process of processing the different data formats of at least two second arrays into the target data format.

[0082] Furthermore, multiple groups of original arrays for training and target arrays corresponding to the original arrays can be preset in advance, and then the multiple groups of original arrays are input into the multi-mode protocol adaptation model to generate multiple groups of test arrays.

[0083] It is understandable that during the training process, the difference between the generated test array and the target array corresponding to the original array that meets user requirements may be greater than the preset threshold. In this case, it is necessary to input multiple sets of original arrays into the multi-mode protocol adaptation model again and continue training until the difference between the test data and the target data is less than the preset threshold.

[0084] The present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the training rule determination method described in the present application is implemented. For example, the following can be executed: Figure 1 The individual steps of the method are shown.

[0085] The present invention provides a computer program product, which includes instructions that are executed by a processor when the processor executes the instructions. Figure 1 The individual steps of the method are shown.

[0086] It should be noted that although the operations of the method of the present invention are described in a particular order in the drawings, this does not require or imply that the operations must be performed in this particular order or that all illustrated operations must be performed to achieve desired results.

[0087] Figure 3 FIG. 1 is a block diagram of a multi-mode protocol data processing system according to an embodiment of the present application, wherein the system includes a multi-mode protocol adaptation model. Figure 3 , acquisition unit 601 and execution unit 602: The acquisition unit 601 is used to acquire at least two first arrays, where the at least two first arrays are data collected by at least two acquisition devices, and the data formats of the first arrays include at least two data formats; The execution unit 602 is used to input the at least two first arrays into the multimode protocol adaptation model to generate at least two second arrays corresponding to the at least two first arrays, the at least two second arrays are data in a target data format, and the multimode protocol adaptation model is used to process the data format of the second arrays into data in the target data format; The execution unit 602 is further used to perform data fusion processing on the at least two second arrays to obtain fused data, where the fused data is the self-organizing network data corresponding to the at least two first arrays.

[0088] In one embodiment, the execution unit 602 is specifically used to determine the data protocol type of each group of the at least two first arrays; according to the data protocol type of the first array, convert the data format of the first array into the target format through a data conversion formula to generate a second array.

[0089] In one embodiment, the execution unit 602 is also used to obtain multiple groups of original arrays and multiple groups of target arrays, wherein the target array is an array composed of data in a target format corresponding to the original array one-to-one, the multiple groups of original arrays include data collected by at least two acquisition devices, and the multiple groups of original arrays include arrays corresponding to at least two protocols; input the multiple groups of original arrays into the multi-mode protocol adaptation model to generate multiple groups of test arrays corresponding to the multiple groups of original arrays; compare the multiple groups of test data with the multiple groups of target data, and determine the difference between the multiple groups of test data and the multiple groups of target data; when the difference is greater than a preset threshold, adjust the multi-mode protocol adaptation model according to the difference, so that the difference between the test data generated by the multi-mode protocol adaptation model and the target data is less than the preset threshold.

[0090] In one embodiment, the acquisition unit 601 is specifically used to: acquire a third array through the at least two acquisition devices, perform noise reduction processing on the at least two third arrays, and generate at least two first arrays corresponding to the third arrays; wherein the noise reduction processing includes at least one of the following: NLM algorithm and Kalman filter algorithm.

[0091] In one embodiment, the acquisition unit 601 is specifically used to: determine the target data from the at least two third arrays, and determine a search box based on the third array to which the target data belongs and the data interval of the third array, wherein the target data is located at the center of the search box, and the search box includes multiple search points and denoised points corresponding to the target data; determine multiple similarities between the multiple search points and the denoised points; determine a neighborhood weight value of the denoised point based on the multiple similarities; and determine the denoised data value of the denoised point through the NML algorithm based on the neighborhood weight value of the denoised point.

[0092] In one embodiment, the execution unit 602 is specifically used to: perform data fusion on the at least two second arrays according to the weight coefficient of each second array in the at least two second arrays, the unbiased estimate value of each second array and the historical data mean of each second array to obtain fused data.

[0093] It should be understood that the units recorded in the multimode protocol data processing system correspond to the various steps in the method described in the accompanying drawings. Therefore, the operations and features described above for the method are also applicable to the multimode protocol data processing system and the units contained therein, and will not be repeated here. The multimode protocol data processing system can be pre-implemented in a browser or other security application of a computer device, or can be loaded into a browser or its security application of a computer device by downloading or the like. The corresponding units in the multimode protocol data processing system can cooperate with the units in the computer device to implement the solution of the embodiment of the present application.

[0094] For the several modules or units mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0095] It should be noted that for details not disclosed in the multi-mode protocol data processing system of the embodiments of the present application, please refer to the details disclosed in the above embodiments of the present application, which will not be repeated here.

[0096] Reference below Figure 4 , Figure 4 A schematic diagram of the structure of a computer device suitable for implementing the embodiments of the present application is shown. Figure 4 As shown, the computer system 1700 includes a central processing unit (CPU) 1701, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1702 or the program loaded from the storage part 1708 to the random access memory (RAM) 1703. In the RAM 1703, various programs and data required for the operation instructions of the system are also stored. The CPU 1701, the ROM 1702, and the RAM 1703 are connected to each other through a bus 1704. An input / output (I / O) interface 1705 is also connected to the bus 1704.

[0097] The following components are connected to the I / O interface 1705: an input section 1706 including a keyboard, a mouse, etc.; an output section 1707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1708 including a hard disk, etc.; and a communication section 1709 including a network interface card such as a LAN card, a modem, etc. The communication section 1709 performs communication processing via a network such as the Internet. A drive 1710 is also connected to the I / O interface 1705 as needed. A removable medium 1711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1710 as needed, so that a computer program read therefrom is installed into the storage section 1708 as needed.

[0098] In particular, according to an embodiment of the present application, the above reference flow chart Figure 1 The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 1709, and / or installed from a removable medium 1711. When the computer program is executed by the central processing unit (CPU) 1701, the above-mentioned functions defined in the system of the present application are executed.

[0099] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium such as a computer-readable storage medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0100] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operating instructions of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the aforementioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, the boxes represented by two connections can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operating instruction, or can be implemented with a combination of dedicated hardware and computer instructions.

[0101] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be set in a processor. For example, it may be described as: a processor includes a first receiving module, a second receiving module, and a sending module. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.

[0102] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the multi-mode protocol data processing method described in the present application.

[0103] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present application (but not limited to) by each other to form a technical solution.< / float> < / float> < / float> < / float>

Claims

1. A multi-mode protocol data processing method, characterized in that: The method comprises: Acquire at least two first arrays, where the at least two first arrays are data collected by at least two collection devices, and data formats of the first arrays include at least two data formats; Inputting the at least two first arrays into a multimode protocol adaptation model, generating at least two second arrays corresponding to the at least two first arrays, wherein the at least two second arrays are data in a target data format, and the multimode protocol adaptation model is used to process the data format of the second arrays into data in the target data format; Data fusion processing is performed on the at least two second arrays to obtain fused data, where the fused data is the self-organizing network data corresponding to the at least two first arrays.

2. The method according to claim 1, characterized in that The step of inputting the first array into a multimode protocol adaptation model to generate a second array comprises: Determine a data protocol type of each group of first arrays in the at least two first arrays; According to the data protocol type of the first array, the data format of the first array is converted into a target format through a data conversion formula to generate a second array.

3. The method according to claim 1, characterized in that Before acquiring at least two first arrays, the method further includes: Acquire multiple groups of original arrays and multiple groups of target arrays, wherein the target array is an array composed of data in a target format corresponding to the original arrays one by one, the multiple groups of original arrays include data collected by at least two collection devices, and the multiple groups of original arrays include arrays corresponding to at least two protocols; Inputting the multiple groups of original arrays into the multi-mode protocol adaptation model to generate multiple groups of test arrays corresponding to the multiple groups of original arrays; Comparing the multiple sets of test data with the multiple sets of target data, and determining differences between the multiple sets of test data and the multiple sets of target data; When the difference is greater than a preset threshold, the multimode protocol adaptation model is adjusted according to the difference so that the difference between the test data generated by the multimode protocol adaptation model and the target data is less than the preset threshold.

4. The method according to claim 1, characterized in that The acquiring of at least two first arrays comprises: Acquire a third array through the at least two acquisition devices, Performing noise reduction processing on the at least two third arrays to generate at least two first arrays corresponding to the third arrays; The noise reduction process includes at least one of the following: an NLM algorithm and a Kalman filter algorithm.

5. The method according to claim 4, characterized in that In the case where the noise reduction process includes an NLM algorithm, the performing noise reduction process on the at least two third arrays to generate at least two first arrays corresponding to the third arrays includes: Determine target data from the at least two third arrays, and determine a search frame according to the third array to which the target data belongs and the data interval of the third array, wherein the target data is located at the center of the search frame, and the search frame includes a plurality of search points and denoised points corresponding to the target data; Determining multiple similarities between the multiple search points and the denoised points; Determining a neighborhood weight value of the denoised point according to the multiple similarities; According to the neighborhood weight value of the denoised point, the data value of the denoised point after denoising is determined by the NML algorithm.

6. The method according to claim 1, characterized in that The performing data fusion processing on the at least two second arrays to obtain fused data includes: According to the weight coefficient of each second array in the at least two second arrays, the unbiased estimated value of each second array and the historical data mean of each second array, data fusion is performed on the at least two second arrays to obtain fused data.

7. A multi-mode protocol data processing system, characterized in that: The system includes a multi-mode protocol adaptation model, and the system includes an acquisition unit and an execution unit: The acquisition unit is used to acquire at least two first arrays, where the at least two first arrays are data collected by at least two acquisition devices, and the data formats of the first arrays include at least two data formats; The execution unit is used to input the at least two first arrays into the multimode protocol adaptation model to generate at least two second arrays corresponding to the at least two first arrays, the at least two second arrays are data in a target data format, and the multimode protocol adaptation model is used to process the data format of the second arrays into data in the target data format; The execution unit is further used to perform data fusion processing on the at least two second arrays to obtain fused data, where the fused data is the self-organizing network data corresponding to the at least two first arrays.

8. A computer device 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 program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising instructions, characterized in that: When the instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images