Industrial innovation resource data analysis method and system

Abstract

The present application provides an industrial innovation resource data analysis method and system, which performs dimensionality reduction processing on the network resource interaction data to be analyzed, thereby obtaining the reduced-dimensional network resource interaction data, and then determines it as interactive event sample data in combination with the reduced-dimensional network resource interaction data, and then analyzes the sample set corresponding to the above interactive event sample data in the network resource interaction data to be analyzed to determine whether each sample set is the first interactive event, that is, to determine the interactive event analysis results in the network resource interaction data to be analyzed, and the interactive event analysis results are the location to which the interactive event belongs. Since the interactive event sample data is selected through dimensionality reduction processing, it is only necessary to perform significance analysis on the sample set that matches the interactive event sample data, which reduces the difficulty of analysis, thereby improving the accuracy and credibility of the analysis, and therefore, can ensure the integrity and readability of the interactive event analysis results.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and specifically, to an industrial innovation resource data analysis method and system. Background Art

[0002] Data analysis refers to the use of appropriate statistical analysis methods to analyze a large amount of collected data, summarize, understand and digest them, in order to maximize the development of data functions and give full play to the role of data. Data analysis is the process of detailed study and summary of data in order to extract useful information and form conclusions.

[0003] At present, with the continuous development of science and technology, more and more fields need to apply data analysis technology. As a result, data analysis technology has gradually become an irreplaceable technology. After combining data analysis with industrial innovation resource data, the inventor found that there may be problems such as high analysis difficulty, making it difficult to ensure the integrity and readability of interactive event analysis results. Summary of the invention

[0004] In view of this, the present application provides an industrial innovation resource data analysis method and system.

[0005] In a first aspect, a method for analyzing industrial innovation resource data is provided, which is applied to a data analysis system, and the method at least comprises:

[0006] Obtaining network resource interaction data to be analyzed, wherein the data analysis task matching the network resource interaction data to be analyzed includes a first interaction event; performing dimensionality reduction processing on the network resource interaction data to be analyzed to obtain dimensionality-reduced network resource interaction data, and determining interaction event sample data in combination with the dimensionality-reduced network resource interaction data;

[0007] The sample set corresponding to the interactive event sample data in the network resource interactive data to be analyzed is analyzed to determine the interactive event analysis result of the network resource interactive data to be analyzed, wherein the interactive event analysis result is the location to which the first interactive event belongs.

[0008] In an independently implemented embodiment, the network resource interaction data to be analyzed is a set of network resource interaction data of the network resource interaction data set to be analyzed, and the data analysis task matched by the network resource interaction data set to be analyzed includes a first interaction event; the method further includes:

[0009] Based on the interaction event analysis results of the network resource interaction data to be analyzed and the interaction event analysis results of the example network resource interaction data, determine the abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis results of the example network resource interaction data, wherein the example network resource interaction data is a group of network resource interaction data before the network resource interaction data to be analyzed in the network resource interaction data set to be analyzed.

[0010] In an independently implemented embodiment, the abnormal situation of interaction data of the first interaction event that matches the interaction event analysis result of the example network resource interaction data is determined based on the interaction event analysis result of the network resource interaction data to be analyzed and the interaction event analysis result of the example network resource interaction data, includes:

[0011] Determine a weighted processing result of each interactive event analysis result of the example network resource interactive data and each interactive event analysis result of the network resource interactive data to be analyzed;

[0012] The weighted processing results of the interaction event analysis results of the example network resource interaction data and each interaction event analysis result of the network resource interaction data to be analyzed are lower than the first judgment value set in advance to determine that the abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis result of the example network resource interaction data is abnormal;

[0013] Based on the weighted processing result of the interaction event analysis result of the example network resource interaction data and one of the interaction event analysis results of the network resource interaction data to be analyzed being not less than the first judgment value, the abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis result of the example network resource interaction data is determined to be normal.

[0014] In an independently implemented embodiment, the abnormal situation of interaction data of the first interaction event that matches the interaction event analysis result of the example network resource interaction data is determined based on the interaction event analysis result of the network resource interaction data to be analyzed and the interaction event analysis result of the example network resource interaction data, includes:

[0015] Determine a key description weight depolarization processing result of a global key description in the interactive event analysis result of the example network resource interactive data as a first depolarization processing result, and determine a key description weight depolarization processing result of a global key description in the interactive event analysis result matched in the network resource interactive data to be analyzed as a second depolarization processing result;

[0016] On the basis that the error result between the first depolarization processing result and the second depolarization processing result exceeds the first key description determination value set previously, determining the abnormality of the interaction data of the analysis index matched by the interaction event analysis result as abnormal;

[0017] On the basis that the error result between the first depolarization processing result and the second depolarization processing result is not greater than the first key description judgment value set in advance, the abnormal situation of the interaction data of the analysis index matching the interaction event analysis result is determined to be normal.

[0018] In an independently implemented embodiment, the dimensionality reduction processing of the network resource interaction data to be analyzed includes:

[0019] Determine a key description difference value of each key description tuple between the network resource interaction data to be analyzed and the example network resource interaction data, wherein the location of one key description content in the key description tuple in the network resource interaction data to be analyzed is consistent with the location of another key description content in the example network resource interaction data;

[0020] In the global key description binary groups, a first number of key description binary groups whose key description difference values ​​exceed a second key description judgment value set previously is determined; on the basis that a ratio of the first number to the number of global key description binary groups exceeds a previously set judgment value, the network resource interaction data to be analyzed is subjected to dimensionality reduction processing.

[0021] In an independently implemented embodiment, before the dimensionality reduction processing is performed on the network resource interaction data to be analyzed, the method further includes: switching the network resource interaction data to be analyzed into real-time network interaction data.

[0022] In an independently implemented embodiment, before determining the interactive event sample data in the reduced-dimensionality network resource interactive data, it also includes: performing network resource interactive data filtering processing on the reduced-dimensionality network resource interactive data.

[0023] In an independently implemented embodiment, determining interactive event sample data in combination with the reduced-dimensionality network resource interactive data includes: determining that a data sample interaction set constructed from normal key descriptions in the reduced-dimensionality network resource interactive data is the interactive event sample data.

[0024] In an independently implemented embodiment, before determining the interactive event sample data in combination with the reduced-dimensionality network resource interactive data, it also includes: eliminating the data sample interaction set whose recognition result is lower than the previously set recognition target value in the reduced-dimensionality network resource interactive data.

[0025] In an independently implemented embodiment, the sample set corresponding to the interactive event sample data in the network resource interactive data to be analyzed is analyzed to determine the interactive event analysis result of the network resource interactive data to be analyzed, including: loading each of the sample sets into a previously configured CNN thread, the CNN thread outputting a distinction result of each of the sample sets, wherein the distinction result includes a first interactive event and a second interactive event; and determining the sample set whose distinction result is the first interactive event as the interactive event analysis result.

[0026] In an independently implemented embodiment, obtaining the network resource interaction data to be analyzed includes: obtaining a group of network resource interaction data whose segment gap with the example network resource interaction data is a pre-set gap length from the network resource interaction data set to be analyzed to determine them as the network resource interaction data to be analyzed.

[0027] In an independently implemented embodiment, it also includes: removing the example network resource interaction data, recording the network resource interaction data to be analyzed as example network resource interaction data, and recording the interaction event analysis results of the network resource interaction data to be analyzed.

[0028] In a second aspect, an industrial innovation resource data analysis system is provided, comprising a processor and a memory communicating with each other, wherein the processor is used to retrieve a computer program from the memory and implement the above method by running the computer program.

[0029] The industrial innovation resource data analysis method and system provided in the embodiment of the present application obtains the network resource interaction data to be analyzed, and performs dimensionality reduction processing on the network resource interaction data to be analyzed, thereby obtaining the reduced-dimensional network resource interaction data, and then determines it as interactive event sample data in combination with the reduced-dimensional network resource interaction data, and then analyzes the sample set corresponding to the above interactive event sample data in the network resource interaction data to be analyzed to determine whether each sample set is the first interactive event, that is, to determine the interactive event analysis results in the network resource interaction data to be analyzed, and the interactive event analysis results are the location to which the interactive event belongs. Since the interactive event sample data is selected through dimensionality reduction processing, it is only necessary to perform significance analysis on the sample set that matches the interactive event sample data, which reduces the difficulty of analysis, thereby improving the accuracy and credibility of the analysis, and therefore, can ensure the integrity and readability of the interactive event analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 A flowchart of an industrial innovation resource data analysis method provided in an embodiment of the present application.

[0032] Figure 2 A block diagram of an industrial innovation resource data analysis device provided in an embodiment of the present application.

[0033] Figure 3 An architectural diagram of an industrial innovation resource data analysis system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0035] See also Figure 1 , shows a method for analyzing industrial innovation resource data, which may include the technical solutions described in the following steps 101-103.

[0036] In step 101, network resource interaction data to be analyzed is obtained, wherein the data analysis task matched by the network resource interaction data to be analyzed includes a first interaction event.

[0037] The network resource interaction data to be analyzed can be understood as the network resource interaction data analyzed in the above multi-dimensional way, or a group of network resource interaction data in the network resource interaction data set analyzed in different analysis directions. The data analysis system can record the network resource interaction data according to specific segment intervals, and obtain each recorded network resource interaction data as the network resource interaction data to be analyzed; the data analysis system can continuously record the network resource interaction data set, and can select a network resource interaction data set group from the above network resource interaction data set according to specific segment intervals, and use each selected network resource interaction data set group as the network resource interaction data to be analyzed.

[0038] In step 102, the network resource interaction data to be analyzed is subjected to dimensionality reduction processing to obtain dimensionality-reduced network resource interaction data, and interaction event sample data is determined in combination with the dimensionality-reduced network resource interaction data.

[0039] If the network resource interaction data to be analyzed is real-time network interaction data, the network resource interaction data to be analyzed is directly subjected to dimensionality reduction processing. If the network resource interaction data to be analyzed is multiple network resource interaction data, the network resource interaction data to be analyzed can be switched to real-time network interaction data first, that is, the quantitative result of the matching can be determined based on the first, second, and third key description weights of each key description.

[0040] During dimensionality reduction processing, a simplified target value (for example, 460) can be set, and the reduced dimension of key descriptions that are not less than the simplified target value will be trimmed to 510, and the reduced dimension of key descriptions that are less than the simplified target value will be trimmed to 0, so that the reduced dimension of each key description is one of 510 (normal key description) and 0 (abnormal key description). Several close normal key descriptions can be constructed into a data sample interaction set, and several close abnormal key descriptions can also be constructed into a data sample interaction set. Then, the globally reduced dimensionality network resource interaction data includes a data sample interaction set constructed from normal key descriptions and a data sample interaction set constructed from abnormal key descriptions.

[0041] After the dimensionality reduction process, the reduced-dimensionality network resource interaction data can also be subjected to network resource interaction data filtering process, that is, normal key descriptions whose local key descriptions are all normal key descriptions are cached, and normal key descriptions that locally include abnormal key descriptions are trimmed to abnormal key descriptions. Through the network resource interaction data filtering process, the interference points in the reduced-dimensionality network resource interaction data can be eliminated, thereby improving the accuracy of the data sample interaction set in the reduced-dimensionality network resource interaction data.

[0042] After the dimensionality reduction process, the data sample interaction sets whose recognition results are lower than the previously set recognition target values ​​in the dimensionality reduction network resource interaction data can also be eliminated, because these data sample interaction sets lower than the recognition target values ​​may be interference points. Because the data sample interaction sets are identified as the location to which the analysis indicator belongs, the recognition target value can be determined based on the recognition results of the location to which the analysis indicator belongs. By eliminating the data sample interaction sets with small recognition results, the interference points can be weakened, thereby improving the accuracy and completeness of the recognition results.

[0043] In step 103, the sample set corresponding to the interactive event sample data in the network resource interactive data to be analyzed is analyzed to determine the interactive event analysis result of the network resource interactive data to be analyzed, wherein the interactive event analysis result is the location to which the interactive event belongs.

[0044] Furthermore, each of the sample sets can be loaded into a previously configured CNN thread, and the CNN thread outputs the distinction results of each of the sample sets, wherein the distinction results include a first interactive event and a second interactive event; and then the sample set whose distinction result is the first interactive event is determined as the interactive event analysis result.

[0045] The interactive event analysis result can be understood as the minimum matrix that can divide the nodes of the first interactive event. Each interactive event analysis result has a first interactive event, and the state of the first interactive event is an analysis indicator of a normal state. In other words, the interactive event analysis result of the network resource interactive data to be analyzed determined in this embodiment is the node of the first interactive event in the network resource interactive data to be analyzed that is in a normal state.

[0046] In this embodiment, the network resource interaction data to be analyzed is obtained, and the network resource interaction data to be analyzed is subjected to dimensionality reduction processing, thereby obtaining the reduced-dimensional network resource interaction data, and then the interactive event sample data is determined in combination with the reduced-dimensional network resource interaction data, and then the sample set corresponding to the above interactive event sample data in the network resource interaction data to be analyzed is analyzed to determine whether each sample set is the first interactive event, that is, to determine the interactive event analysis result in the network resource interaction data to be analyzed, and the interactive event analysis result is the location to which the interactive event belongs. Since the interactive event sample data is selected through dimensionality reduction processing, it is only necessary to perform significance analysis on the sample set matching the interactive event sample data, which reduces the difficulty of analysis, thereby improving the accuracy and credibility of the analysis, and therefore, the integrity and readability of the interactive event analysis results can be guaranteed.

[0047] In a possible implementation example, the network resource interaction data to be analyzed is a group of network resource interaction data of the network resource interaction data set to be analyzed, and the data analysis task matched by the network resource interaction data set to be analyzed includes the first interaction event. After step 101, the industrial innovation resource data analysis method also includes step 104: based on the interaction event analysis results of the network resource interaction data to be analyzed and the interaction event analysis results of the example network resource interaction data, determine the abnormal situation of the interaction data of the first interaction event matched by the interaction event analysis results of the example network resource interaction data, wherein the example network resource interaction data is a group of network resource interaction data before the network resource interaction data set to be analyzed in the network resource interaction data set to be analyzed. Among them, this embodiment is iteratively run for each obtained network resource interaction data to be analyzed, therefore, each time the network resource interaction data to be analyzed is obtained from the network resource interaction data set to be analyzed, the interaction event analysis results are determined according to steps 101 to 103. Since the network resource interaction data to be analyzed obtained in the previous round also determined the interaction event analysis results, the abnormal situation of the interaction data of the first interaction event matched by each target data in the network resource interaction data to be analyzed in the previous round can be determined by comparing the target data of the network resource interaction data to be analyzed in this round with the target data of the network resource interaction data to be analyzed in the previous round. For example, if any target data in the network resource interaction data to be analyzed in the previous round also has target data at the corresponding position in the network resource interaction data to be analyzed in this round, then it is considered that the first interaction event matched by the target data is in a normal state, that is, there is no interference with the first interaction event between the two rounds of network resource interaction data to be analyzed; if any target data in the network resource interaction data to be analyzed in the previous round does not have target data at the corresponding position in the network resource interaction data to be analyzed in this round, then it is considered that the first interaction event matched by the target data is in an abnormal state, that is, there is interference with the first interaction event between the two rounds of network resource interaction data to be analyzed.

[0048] Furthermore, in order to distinguish and compare the network resource interaction data to be analyzed obtained in the two rounds, the network resource interaction data to be analyzed obtained in the previous round can be understood as the example network resource interaction data, and the network resource interaction data to be analyzed obtained in the current round can continue to be understood as the network resource interaction data to be analyzed. Therefore, the network resource interaction data to be analyzed and the example network resource interaction data are two sets of inconsistent fragments of network resource interaction data in the network resource interaction data set to be analyzed, with the example network resource interaction data in the front and the network resource interaction data to be analyzed in the back.

[0049] Since the network resource interaction data to be analyzed obtained each time, after the interactive event analysis result is determined, needs to be used as the example network resource interaction data after the interactive event analysis result is determined in the next round of network resource interaction data to be analyzed, so the network resource interaction data to be analyzed obtained each time is recorded for use after the interactive event analysis result is determined. In addition, since the network resource interaction data to be analyzed obtained each time is only used as the example network resource interaction data once, after step 104 determines the abnormal situation of the interactive data of the first interactive event that matches each interactive event analysis result of the example network resource interaction data, the example network resource interaction data can be eliminated, the network resource interaction data to be analyzed is recorded as the example network resource interaction data, and the interactive event analysis result of the network resource interaction data to be analyzed is recorded, that is, the example network resource interaction data is updated, thereby improving the accuracy of determining the abnormal situation of the interactive event interaction data.

[0050] Specifically, after the network resource interaction data to be analyzed is obtained from the network resource interaction data set to be analyzed for the first time, after the interaction event analysis result of the network resource interaction data to be analyzed is determined, step 104 is not executed, but the network resource interaction data to be analyzed is directly recorded as example network resource interaction data, and the interaction event analysis result of the network resource interaction data to be analyzed is recorded.

[0051] In an alternative embodiment, the network resource interaction data to be analyzed can be obtained according to a specific segment gap, that is, when obtaining the network resource interaction data to be analyzed, a group of network resource interaction data with a segment gap of a preset gap length with the example network resource interaction data is obtained from the network resource interaction data set to be analyzed to determine it as the network resource interaction data to be analyzed. The preset gap length can be understood as 6 seconds, and the network resource interaction data set to be analyzed can be obtained uninterruptedly according to the preset gap length.

[0052] In an alternative embodiment, based on the interaction event analysis results of the network resource interaction data to be analyzed and the interaction event analysis results of the example network resource interaction data, the abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis results of the example network resource interaction data is determined, including step 301 to step 303.

[0053] In step 301, a weighted processing result of each interactive event analysis result of the example network resource interactive data and each interactive event analysis result of the network resource interactive data to be analyzed is determined.

[0054] Each interactive event analysis result in the example network resource interactive data is obtained one by one according to the sorting, and after each interactive event analysis result is obtained, the weighted processing result of the interactive event analysis result and each interactive event analysis result of the network resource interactive data to be analyzed is determined one by one.

[0055] In step 302, based on the weighted processing results of the interaction event analysis results of the example network resource interaction data and each interaction event analysis result of the network resource interaction data to be analyzed being lower than the first judgment value set in advance, the abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis results of the example network resource interaction data is determined as abnormal.

[0056] In step 303, based on the weighted processing result of the interaction event analysis result of the example network resource interaction data and one of the interaction event analysis results of the network resource interaction data to be analyzed, the abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis result of the example network resource interaction data is determined to be normal based on a value that is not less than the first judgment value.

[0057] If the weighted processing result of the interaction event analysis results of the example network resource interaction data and the interaction event analysis results of the network resource interaction data to be analyzed exceeds the first judgment value set in advance, it indicates that the two interaction event analysis results match each other. For the same first interaction event under the data analysis task, that is, the interaction event analysis results in the example network resource interaction data have a matching interaction event analysis result in the network resource interaction data to be analyzed, it can be preliminarily determined that the first interaction event matched by the interaction event analysis result is still in a normal state without interference. Therefore, the abnormal situation of the interaction data of the first interaction event matched by the interaction event analysis result is normal.

[0058] If the weighted processing result of one of the interactive event analysis results of the example network resource interactive data and one of the interactive event analysis results of the network resource interactive data to be analyzed is lower than the previously set judgment value, it means that there is no interactive event analysis result matching the interactive event analysis result in the network resource interactive data to be analyzed. Therefore, it can be determined that the abnormal situation of the interactive data of the first interactive event matched by the interactive event analysis result of the example network resource interactive data is abnormal.

[0059] In this embodiment, the abnormality of the interaction data of the first interaction event is determined by weighted processing of the interaction event analysis results. Since the interaction event analysis results are the location to which the interaction event belongs, this method of determining the abnormality of the interaction data of the interaction event is more reliable.

[0060] In an alternative embodiment, based on the interaction event analysis results of the network resource interaction data to be analyzed and the interaction event analysis results of the example network resource interaction data, the abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis results of the example network resource interaction data is determined, including step 401 to step 403.

[0061] In step 401, a key description weight depolarization processing result of a global key description in the interaction event analysis result of the example network resource interaction data is determined as a first depolarization processing result, and a key description weight depolarization processing result of a global key description in the interaction event analysis result matched in the network resource interaction data to be analyzed is determined as a second depolarization processing result.

[0062] In step 402, based on the fact that the error result between the first depolarization processing result and the second depolarization processing result exceeds the first key description judgment value set in advance, the abnormal situation of the interaction data of the first interaction event matched by the interaction event analysis result is determined as abnormal.

[0063] In step 403, the abnormal situation of the interaction data of the first interaction event matched by the first interaction event pending frame is determined to be normal on the basis that the error result between the first depolarization processing result and the second depolarization processing result is not greater than the first key description judgment value set in advance.

[0064] The first key description determination value may be preset to be 200. The abnormal state indicates that the first interaction event is disturbed after the segment matched by the example network resource interaction data.

[0065] In this embodiment, by using the key description difference value of the depolarization processing corresponding to the target data, it is accurately determined whether interference occurs in the interactive event, thereby improving the reliability of the analysis of abnormal situations of the interactive event interaction data.

[0066] It can be understood that one of the two methods for determining the abnormal situation of the interaction data of the first interaction event can be selected for implementation, or they can be used simultaneously. When the two methods are combined to determine the abnormal situation of the interaction data of the first interaction event, when executing step 302, the weighted processing results of the interaction event analysis results of the example network resource interaction data and each interaction event analysis result of the network resource interaction data to be analyzed are both lower than the first judgment value set in advance, so as to determine the interaction event analysis results of the example network resource interaction data as the target data to be selected; and then the key description weight depolarization processing result of only determining the global key description in the target data to be selected in step 401 is used as the first depolarization processing result, and only determining the key description weight of the global key description in the interaction event analysis results of the network resource interaction data to be analyzed that matches the target data to be selected. The re-depolarization processing result is the second depolarization processing result. In step 402 and step 403, only the first depolarization processing result and the second depolarization processing result are used to determine the abnormal situation of the interaction data of the first interaction event that matches the interaction event sample data, that is, when the error result between the first depolarization processing result and the second depolarization processing result exceeds the first key description judgment value set previously, it is determined that the abnormal situation of the interaction data of the first interaction event that matches the interaction event sample data is abnormal; when the error result between the first depolarization processing result and the second depolarization processing result is not greater than the first key description judgment value set previously, it is determined that the abnormal situation of the interaction data of the first interaction event that matches the first interaction event sample data is normal.

[0067] Combining the two methods to determine the abnormality of the interaction data of the first interaction event that matches the interaction event analysis results, first use the weighted processing results between the target data to select the target values ​​that may interfere, that is, the sample data, and then focus on the key descriptions of the sample data for comparison to determine the abnormality of the interaction data of the first interaction event. This improves the accuracy of the judgment of abnormality of the interaction data of the interaction event.

[0068] In a possible implementation, the network resource interaction data to be analyzed can be processed for dimension reduction in the following manner: first, the key description difference value of each key description tuple between the network resource interaction data to be analyzed and the example network resource interaction data is determined, wherein the location of one key description content in the key description tuple in the network resource interaction data to be analyzed is consistent with the location of the other key description content in the example network resource interaction data; further, the first number of key description tuples whose key description difference value exceeds the second key description judgment value set previously is determined in the global key description tuples; finally, on the basis that the ratio of the first number to the number of global key description tuples exceeds the second judgment value set previously, the network resource interaction data to be analyzed is processed for dimension reduction. The key description difference value can be obtained by weighting the two matched key descriptions. The size of the key description difference value can be used to indicate the matching of the objects matched by the network resource interaction data to be analyzed and the objects matched by the example network resource interaction data. A key description difference value that is not greater than the second key description judgment value indicates that the objects matched by the key description in the two sets of network resource interaction data are consistent, and a key description difference value that exceeds the second key description judgment value indicates that the objects matched by the key description in the two sets of network resource interaction data are inconsistent. Further, the ratio of the first number to the number of global key description tuples exceeds the second judgment value set in advance, indicating that the objects matched by the two sets of network resource interaction data are consistent, that is, the analysis direction of the data analysis system when obtaining the two sets of network resource interaction data is consistent, and no migration changes occur after obtaining the example network resource interaction data. Therefore, on this basis, the network resource interaction data to be analyzed can be subjected to dimensionality reduction processing, and further according to the subsequent steps, the abnormality of the interaction data of the first interaction event that matches the target data of the example network resource interaction data can be determined.

[0069] If the ratio of the first number to the number of global key description tuples is not greater than the second judgment value set in advance, it means that the objects matched by the two sets of network resource interaction data are inconsistent, that is, the analysis direction of the data analysis system when obtaining the two sets of network resource interaction data is inconsistent, and migration changes have occurred after obtaining the sample network resource interaction data. Therefore, on this basis, the network resource interaction data to be analyzed is not subjected to dimensionality reduction processing, that is, the network resource interaction data to be analyzed is abandoned, and the network resource interaction data to be analyzed can be further obtained.

[0070] In this embodiment, each time the network resource interaction data to be analyzed is obtained, it is determined whether the object matching the network resource interaction data to be analyzed is consistent with the example network resource interaction data, that is, it is determined whether the data analysis system has undergone migration changes. If the object is inconsistent, it is discarded; if the object is consistent, the abnormal situation of the interaction data of the first interaction event is further determined, thereby improving the problem of unreliable analysis results caused by migration changes of the data analysis system, and improving the analysis accuracy of the interaction event analysis results and the reliability of determining the abnormal situation of the interaction data of the interaction event.

[0071] Based on the above, please refer to Figure 2 , provides an industrial innovation resource data analysis device 200, which is applied to an industrial innovation resource data analysis system, and the device comprises:

[0072] The data acquisition module 210 is used to obtain the network resource interaction data to be analyzed, wherein the data analysis task matching the network resource interaction data to be analyzed includes a first interaction event; perform dimensionality reduction processing on the network resource interaction data to be analyzed to obtain dimensionality-reduced network resource interaction data, and determine interaction event sample data in combination with the dimensionality-reduced network resource interaction data;

[0073] The result analysis module 220 is used to analyze the sample set corresponding to the interactive event sample data in the network resource interactive data to be analyzed to determine the interactive event analysis result of the network resource interactive data to be analyzed, wherein the interactive event analysis result is the location to which the first interactive event belongs.

[0074] Based on the above, please refer to Figure 3 , shows an industrial innovation resource data analysis system 300, including a processor 310 and a memory 320 that communicate with each other, and the processor 310 is used to read and execute a computer program from the memory 320 to implement the above method.

[0075] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0076] In summary, based on the above scheme, by obtaining the network resource interaction data to be analyzed, and performing dimensionality reduction processing on the network resource interaction data to be analyzed, the reduced-dimensional network resource interaction data is obtained, and then the reduced-dimensional network resource interaction data is determined as interactive event sample data, and then the sample set corresponding to the above interactive event sample data in the network resource interaction data to be analyzed is analyzed to determine whether each sample set is the first interactive event, that is, to determine the interactive event analysis results in the network resource interaction data to be analyzed, and the interactive event analysis results are the positioning to which the interactive event belongs. Since the interactive event sample data is selected through dimensionality reduction processing, it is only necessary to perform significance analysis on the sample set matching the interactive event sample data, which reduces the difficulty of analysis, thereby improving the accuracy and credibility of the analysis, and therefore, the integrity and readability of the interactive event analysis results can be guaranteed.

[0077] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0078] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

[0079] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0080] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0081] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0082] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0083] The computer program codes required for the operation of each part of the present application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0084] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0085] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0086] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used for the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0087] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0088] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present application may be considered to be consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.

[0089] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for analyzing industrial innovation resource data, characterized in that: Applied to a data analysis system, the method at least comprises: Obtaining network resource interaction data to be analyzed, wherein the data analysis task matching the network resource interaction data to be analyzed includes a first interaction event; performing dimensionality reduction processing on the network resource interaction data to be analyzed to obtain dimensionality-reduced network resource interaction data, and determining interaction event sample data in combination with the dimensionality-reduced network resource interaction data; Analyzing a sample set corresponding to the interactive event sample data in the network resource interactive data to be analyzed to determine an interactive event analysis result of the network resource interactive data to be analyzed, wherein the interactive event analysis result is a location to which the first interactive event belongs; The network resource interaction data to be analyzed is a set of network resource interaction data of the network resource interaction data set to be analyzed, and the data analysis task matched by the network resource interaction data set to be analyzed includes a first interaction event; the method further includes: Based on the interaction event analysis results of the network resource interaction data to be analyzed and the interaction event analysis results of the example network resource interaction data, determining the abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis results of the example network resource interaction data, wherein the example network resource interaction data is a group of network resource interaction data before the network resource interaction data to be analyzed in the network resource interaction data to be analyzed; The abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis result of the example network resource interaction data is determined based on the interaction event analysis result of the network resource interaction data to be analyzed and the interaction event analysis result of the example network resource interaction data, including: Determine a weighted processing result of each interactive event analysis result of the example network resource interactive data and each interactive event analysis result of the network resource interactive data to be analyzed; The weighted processing results of the interaction event analysis results of the example network resource interaction data and each interaction event analysis result of the network resource interaction data to be analyzed are lower than the first judgment value set in advance to determine that the abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis result of the example network resource interaction data is abnormal; On the basis that a weighted processing result of an interaction event analysis result of the example network resource interaction data and one of the interaction event analysis results of the network resource interaction data to be analyzed is not less than the first judgment value, determining that an abnormal situation of interaction data of the first interaction event that matches the interaction event analysis result of the example network resource interaction data is normal; The abnormal situation of the interaction data of the first interaction event that matches the interaction event analysis result of the example network resource interaction data is determined based on the interaction event analysis result of the network resource interaction data to be analyzed and the interaction event analysis result of the example network resource interaction data, including: Determine a key description weight depolarization processing result of a global key description in the interactive event analysis result of the example network resource interactive data as a first depolarization processing result, and determine a key description weight depolarization processing result of a global key description in the interactive event analysis result matched in the network resource interactive data to be analyzed as a second depolarization processing result; On the basis that the error result between the first depolarization processing result and the second depolarization processing result exceeds the first key description determination value set previously, determining the abnormality of the interaction data of the analysis index matched by the interaction event analysis result as abnormal; On the basis that the error result between the first depolarization processing result and the second depolarization processing result is not greater than the first key description determination value set previously, determining that the abnormality of the interaction data of the analysis index matched by the interaction event analysis result is normal; The step of performing dimensionality reduction processing on the network resource interaction data to be analyzed includes: Determine a key description difference value of each key description tuple between the network resource interaction data to be analyzed and the example network resource interaction data, wherein the location of one key description content in the key description tuple in the network resource interaction data to be analyzed is consistent with the location of another key description content in the example network resource interaction data; Determine, in the global key description binary group, a first number of key description binary groups whose key description difference value exceeds a second key description judgment value set previously; and perform dimensionality reduction processing on the network resource interaction data to be analyzed based on the fact that the ratio of the first number to the number of global key description binary groups exceeds the judgment value set previously; Before the dimensionality reduction processing is performed on the network resource interaction data to be analyzed, the method further includes: switching the network resource interaction data to be analyzed into real-time network interaction data; Before determining the interactive event sample data in the reduced-dimensional network resource interactive data, the method further includes: performing network resource interactive data filtering processing on the reduced-dimensional network resource interactive data; The step of determining the interactive event sample data in combination with the reduced-dimensionality network resource interactive data includes: determining a data sample interaction set constructed from normal key descriptions in the reduced-dimensionality network resource interactive data as the interactive event sample data; Before determining the interactive event sample data in combination with the reduced-dimensionality network resource interactive data, the method further includes: removing the data sample interaction set whose recognition result is lower than the previously set recognition target value in the reduced-dimensionality network resource interactive data; The step of analyzing the sample set corresponding to the interactive event sample data in the network resource interactive data to be analyzed to determine the interactive event analysis result of the network resource interactive data to be analyzed comprises: loading each of the sample sets into a previously configured CNN thread, wherein the CNN thread outputs a distinction result of each of the sample sets, wherein the distinction result includes a first interactive event and a second interactive event; and determining the sample set whose distinction result is the first interactive event as the interactive event analysis result; The obtaining of the network resource interaction data to be analyzed includes: obtaining a group of network resource interaction data having a segment gap of a preset gap length with the example network resource interaction data from the network resource interaction data to be analyzed to determine as the network resource interaction data to be analyzed; The method further includes: removing the example network resource interaction data, recording the network resource interaction data to be analyzed as example network resource interaction data, and recording the interaction event analysis results of the network resource interaction data to be analyzed.

2. An industrial innovation resource data analysis system, characterized in that: The invention comprises a processor and a memory communicating with each other, wherein the processor is used to call a computer program from the memory and implement the method according to claim 1 by running the computer program.

Images