Target network event processing method, device, storage medium and electronic device

Abstract

The present application provides a method, device, storage medium and electronic device for processing target network events, which relates to the field of data processing, including: obtaining a set L of average values ​​of flow change degree; determining the propagation path corresponding to the average value of flow change degree greater than a preset flow change degree average value threshold in L as a key propagation path, and obtaining a set G of average values ​​of key flow change degree; according to G, obtaining a set GP of key propagation path influence value scores; according to GP, obtaining a set D of current opinion type scores; according to D, determining a target Markov model; and processing the target network event according to the target Markov model. The present application sets different Markov models for different opinion types, combines the comprehensive heat of multiple paths and the influence and participation of each opinion type, and selects a suitable Markov model, so that the processing is more targeted and the processing effect is better.

Description

Background Art

[0002] With the rapid development of the Internet industry, opinions on various topics can be positive, negative or neutral. How to quickly and accurately predict the development trend of network events and deal with them is of great significance to enterprises, media and other aspects. Summary of the invention

[0003] In response to the above technical problems, the present application provides a target network event processing method, device, storage medium and electronic device, which at least partially solve the problems existing in the prior art.

[0004] In one aspect of the present application, a target network event processing method is provided, the method comprising the following steps:

[0005] S100, obtaining propagation data of a target network event on each propagation path within a first target time window to obtain a set of average values ​​of flow variation L = (L1, L2, ..., L i , …, L n ); where i = 1, 2, ..., n; L i is the average value of the traffic change degree of the i-th propagation path with respect to the target network event; n is the number of propagation paths; and the end time of the first target time window is the current time.

[0006] S200, determining the propagation paths corresponding to the flow variation average values ​​greater than the preset flow variation average value threshold in L as key propagation paths, so as to obtain the key flow variation average value set G = (G1, G2, ..., G p , …, G q ), where p = 1, 2, ..., q, q is the number of critical propagation paths, G p is the average value of the traffic change degree of the pth key propagation path regarding the target network event.

[0007] S300, according to G, obtain the key propagation path impact value score set GP = (GP1, GP2, ..., GP p ,…,GP q );GP p Score the comprehensive impact value of the path of the pth key propagation path on the target network event; GP p =z1*G p +z2*Y p +z3*C p ; z1, z2, z3 are respectively the preset change degree weight, the preset data weight and the preset number of people weight; Y p is the data weight value of the pth key propagation path; C p is the number of participants in the pth key propagation path regarding the target network event.

[0008] S400, according to the current opinion type of GP and each key communication path, obtain the current opinion type score set D = (D1, D2, D3); wherein D1 is the sum of the path comprehensive impact value scores of all key communication paths in GP whose current opinion type is positive; D2 is the sum of the path comprehensive impact value scores of all key communication paths in GP whose current opinion type is negative; D3 is the sum of the path comprehensive impact value scores of all key communication paths in GP whose current opinion type is neutral.

[0009] S500, according to D, determine the target Markov model; wherein the viewpoint type of the target Markov model is the same as the path comprehensive impact value score in D and the highest current viewpoint type; each viewpoint type has a corresponding Markov model; any two different viewpoint types have different corresponding Markov models.

[0010] S600: Process the target network event according to the target Markov model.

[0011] In a second aspect of the present application, a target network event processing device is provided, the device comprising:

[0012] The data acquisition module is used to acquire the propagation data of the target network event on each propagation path within the first target time window to obtain the average value set of traffic change degree L = (L1, L2, ..., L i , …, L n ); where i = 1, 2, ..., n; L i is the average value of the traffic change degree of the i-th propagation path with respect to the target network event; n is the number of propagation paths; and the end time of the first target time window is the current time.

[0013] The average value acquisition module is used to determine the propagation path corresponding to the flow change degree average value greater than the preset flow change degree average value threshold in L as the key propagation path, so as to obtain the key flow change degree average value set G = (G1, G2, ..., G p , …, G q ), where p = 1, 2, ..., q, q is the number of critical propagation paths, G p is the average value of the traffic change degree of the pth key propagation path regarding the target network event.

[0014] The scoring acquisition module is used to obtain the key propagation path impact value scoring set GP = (GP1, GP2, ..., GP p ,…,GP q );GP p Score the comprehensive impact value of the path of the pth key propagation path on the target network event; GP p=z1*G p +z2*Y p +z3*C p ; z1, z2, z3 are respectively the preset change degree weight, the preset data weight and the preset number of people weight; Y p is the data weight value of the pth key propagation path; C p is the number of participants in the pth key propagation path regarding the target network event.

[0015] The score acquisition module is used to obtain the current opinion type score set D = (D1, D2, D3) according to the current opinion type of the GP and each key communication path; wherein D1 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is positive; D2 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is negative; D3 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is neutral.

[0016] The model determination module is used to determine the target Markov model according to D; wherein the viewpoint type of the target Markov model is the same as the path comprehensive impact value score in D and the highest current viewpoint type; each viewpoint type has a corresponding Markov model; and the Markov models corresponding to any two different viewpoint types are different.

[0017] The processing module is used to process the target network event according to the target Markov model.

[0018] In a third aspect of the present application, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the aforementioned target network event processing method.

[0019] In a fourth aspect of the present application, an electronic device is provided, comprising a processor and the above-mentioned non-transitory computer-readable storage medium.

[0020] This application has at least the following beneficial effects:

[0021] The target network event processing method provided by the present application first obtains the propagation data of the target network event for each propagation path within the first target time window to obtain the flow change degree of each propagation path. Secondly, several propagation paths with large flow change degrees are selected as key processing paths, and other propagation paths are ignored, thereby reducing the amount of data processing. Further, the score of each key propagation path is obtained according to the average flow change degree of each key propagation path, the data weight value, and the number of participants in the target network event. Here, z1, z2, and z3 can be determined according to the relevant experience of those skilled in the art. The larger any value of z1, z2, and z3 is, the more important the corresponding average flow change degree or data weight value or the impact value score of the number of participants in the target network event on the key propagation path is. Among them, the average value of the traffic change degree represents the traffic change degree of the key communication path. The greater the heat change, the higher the attention of the key communication path; each key communication path has a corresponding data weight value, and the data weight value represents the influence of the key communication path. The larger the data weight value, the greater the influence of the key communication path; the number of participants in the target network event represents the attention of the key communication path. The more participants, the higher the attention; otherwise, the lower. In summary, the larger the path comprehensive influence value score obtained, the higher the attention of the key communication path and the greater the influence. In addition, each key communication path has a point of view type at the current moment, which can be positive, negative or neutral. According to the point of view type of each key communication path at the current moment, all key communication paths are divided into three categories: positive key communication paths, negative key communication paths and neutral key communication paths. The sum of the path comprehensive influence value scores corresponding to each type of key communication path is obtained respectively. Here, the larger the sum of the path comprehensive influence value scores corresponding to a certain type of key communication path, the more participants support the corresponding point of view type. Therefore, the maximum path comprehensive impact value score and the corresponding opinion type are determined, and then the target Markov model is determined. Here, since each opinion type has a trained Markov model, and the Markov models corresponding to any two different opinion types are different, the Markov model with the same opinion type is determined as the target Markov model according to the maximum path comprehensive impact value score and the corresponding opinion type. Finally, the target network event is processed according to the target Markov model.

[0022] In this application, several key communication paths with great influence are first selected. Furthermore, based on the opinion type corresponding to each of the several communication paths, the sum of the path comprehensive influence value scores corresponding to each opinion type is determined. The highest opinion type represents that the number of people supporting this opinion type is the largest. In this way, the target Markov model corresponding to the opinion type is selected to process the target network event. This application sets different Markov models for different opinion types, combines the comprehensive heat of multiple paths with the influence and participation of each opinion type, and selects a suitable Markov model, so that the processing is more targeted and the processing effect is better. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flow chart of a target network event processing method provided in an embodiment of the present application;

[0025] Figure 2 This is a structural block diagram of a target network event processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0029] In order to enable those skilled in the art to use the contents of this application, the following implementation modes are provided. For those skilled in the art, the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application.

[0030] Please refer to Figure 1 As shown, an embodiment of the present application provides a method for processing a target network event, the method comprising the following steps:

[0031] S100, obtaining propagation data of a target network event on each propagation path within a first target time window to obtain a set of average values ​​of flow variation L = (L1, L2, ..., L i , …, L n ); where i = 1, 2, ..., n; L i is the average value of the traffic change degree of the i-th propagation path with respect to the target network event; n is the number of propagation paths; and the end time of the first target time window is the current time.

[0032] Specifically, the propagation path can be various network platforms. For example, the propagation path can be Weibo, Douyin, Xiaohongshu, etc. Here, the propagation data can be the total heat value of the target network event in each first target time period within the first target time window. Then, according to the propagation data, the average value of the flow change degree of each propagation path with respect to the target network event is obtained. Here, the average value of the flow change degree of each propagation path with respect to the target network event represents the heat change of each propagation path with respect to the target network event.

[0033] Furthermore, the first target time window includes m consecutive and equal first target time periods; each first target time period corresponds to a total heat value; L i Meet the following conditions:

[0034]

[0035] Ki，j K is the traffic change value of the target network event on the i-th propagation path from the j-th first target time period to the j+1-th first target time period; i，j =(R i，j+1 -R i，j ) / (T i，j+1 -T i，j );R i，j+1 is the total heat value of the i-th propagation path in the j+1-th first target time period; R i，j is the total heat value of the i-th propagation path in the j-th first target time period; T i，j+1 is the end time of the j+1th first target time period of the ith propagation path; T i，j is the end time of the jth first target time period of the i-th propagation path.

[0036] Here, K i，j The larger the value, the greater the difference in the heat value of the target network event from the jth first target time period to the j+1th first target time period, that is, the greater the degree of traffic change, which indicates that the attention of the target network event is rising or falling rapidly. i It reflects the overall traffic change degree of the target network event in the i-th propagation path within the first target time window. If the overall traffic change degree is large, it means that the propagation path has a high degree of attention and a large impact, so it needs to be paid special attention.

[0037] S200, determining the propagation paths corresponding to the flow variation average values ​​greater than the preset flow variation average value threshold in L as key propagation paths, so as to obtain the key flow variation average value set G = (G1, G2, ..., G p , …, G q ), where p = 1, 2, ..., q, q is the number of critical propagation paths, G p is the average value of the traffic change degree of the pth key propagation path regarding the target network event.

[0038] Specifically, if the overall traffic volume changes greatly, it means that the communication path has a high degree of attention and a large impact, so the communication path corresponding to the average value of the traffic volume change in L that is greater than the preset traffic volume change average value threshold is determined as the key communication path, and other communication paths that are not determined as key communication paths are not processed. This application determines several key communication paths with large impacts, reduces the amount of data processing, and improves data processing efficiency.

[0039] S300, according to G, obtain the key propagation path impact value score set GP = (GP1, GP2, ..., GP p ,…,GP q );GPp Score the comprehensive impact value of the path of the pth key propagation path on the target network event; GP p =z1*G p +z2*Y p +z3*C p ; z1, z2, z3 are respectively the preset change degree weight, the preset data weight and the preset number of people weight; Y p is the data weight value of the pth key propagation path; C p is the number of participants in the pth key propagation path regarding the target network event.

[0040] Specifically, the score of each key communication path is obtained according to the average value of the traffic change degree of each key communication path, the data weight value, and the number of participants in the target network event. Here, z1, z2, and z3 can be determined according to the relevant experience of those skilled in the art. The larger the value of z1, z2, and z3, the more important the corresponding average value of the traffic change degree or the data weight value or the number of participants in the target network event is for the key communication path. Here, the average value of the traffic change degree represents the magnitude of the traffic change degree of the key communication path. The greater the heat change, the higher the attention of the key communication path; each key communication path has a corresponding data weight value, and the data weight value represents the influence of the key communication path. The larger the data weight value, the greater the influence of the key communication path; the number of participants in the target network event represents the attention of the key communication path. The more participants, the higher the attention; otherwise, the lower. It should be noted that, as an example: the number of participants can be defined as the total number of users who have posted comments on the key communication path. Further, the aforementioned data weight value Y p Determine by following these steps:

[0041] S310, obtaining a path identifier corresponding to the p-th key propagation path; the path identifier is used to uniquely identify the corresponding key propagation path.

[0042] Here, each key propagation path has a unique corresponding path identifier.

[0043] S320, traverse the preset mapping table according to the path identifier corresponding to the pth key propagation path, and determine Y p ; Among them, the preset mapping table includes the correspondence between each path identifier and each data weight value.

[0044] Specifically, the preset mapping table includes the correspondence between each path identifier and each data weight value. The preset mapping table is traversed according to the path identifier corresponding to the p-th key propagation path to obtain the data weight value corresponding to the p-th key propagation path.

[0045] In summary, the greater the comprehensive impact value score of the path, the more attention the key communication path receives and the greater its influence.

[0046] S400, according to the current opinion type of GP and each key communication path, obtain the current opinion type score set D = (D1, D2, D3); wherein D1 is the sum of the path comprehensive impact value scores of all key communication paths in GP whose current opinion type is positive; D2 is the sum of the path comprehensive impact value scores of all key communication paths in GP whose current opinion type is negative; D3 is the sum of the path comprehensive impact value scores of all key communication paths in GP whose current opinion type is neutral.

[0047] Specifically, each key communication path has an opinion type at the current moment, and the opinion type can be positive, negative or neutral. Here, with the degree of fact disclosure of the target network event, the speech guidance of the participants and other factors, the opinion type for the same key communication path at different moments may be different. Here, according to the opinion type of each key communication path at the current moment, all key communication paths are divided into three categories: positive key communication paths, negative key communication paths and neutral key communication paths. The sum of the path comprehensive influence value scores corresponding to each type of key communication path is obtained respectively. Here, the larger the sum of the path comprehensive influence value scores corresponding to a certain type of key communication path, the more participants support the corresponding opinion type.

[0048] S500, according to D, determine the target Markov model; wherein the viewpoint type of the target Markov model is the same as the path comprehensive impact value score in D and the highest current viewpoint type; each viewpoint type has a corresponding Markov model; any two different viewpoint types have different corresponding Markov models.

[0049] Specifically, according to the sum of the path comprehensive influence value scores corresponding to each type of key propagation path in the positive key propagation path, the negative key propagation path and the neutral key propagation path obtained by the above calculation, the opinion type corresponding to the sum of the largest path comprehensive influence value scores is determined, and then the target Markov model is determined. Here, since each opinion type has a trained Markov model, and the Markov models corresponding to any two different opinion types are different. The selection of training samples for Markov models corresponding to different opinion types is also different: as an example: the training process of the Markov model corresponding to the positive opinion type is: the path comprehensive influence value score and the heat change value of several network events with the highest current opinion type being positive are used as the observation state of the initial Markov model, the traffic change trend is used as the hidden state of the initial Markov model, and the corresponding traffic change trend is used as the output of the initial Markov model; the initial Markov model is trained in this way to obtain the Markov model corresponding to the positive opinion type; the training process of the Markov model corresponding to the reverse opinion type and the neutral opinion type is the same as above.

[0050] Therefore, according to the maximum path comprehensive impact value score and the corresponding opinion type, the Markov model with the same opinion type is determined as the target Markov model, so that the subsequent prediction results will be more accurate.

[0051] S600: Process the target network event according to the target Markov model.

[0052] Specifically, processing the target network event according to the target Markov model includes the following steps:

[0053] S610, obtaining the heat change data corresponding to each key propagation path of the target network event to obtain a heat change information set X=(X1, X2, ..., X c , …, X m ), where c = 1, 2, ..., m; X c is the heat change information of the target network event in the cth first target time period within the first target time window; X c =(J c , Q c );J c is the heat change value sequence corresponding to the target network event in the cth first target time period; J c =(J c，1 , J c，2 , …, J c，p , …, J c，q );J c，p is the heat change value of the pth key propagation path of the target network event in the cth first target time period; J c，p =A c，p -Ac-1，p Among them, A c，p A is the heat value of the pth key propagation path of the target network event in the cth first target time period; c-1，p is the heat value of the pth key propagation path of the target network event in the c-1th first target time period; Q c is the flow change trend in the cth first target time period; if J c，0 -J c-1，0 >JY, then Q c is rising; if J c，0 -J c-1，0 <JE, then Q c is decreasing; if JY≥J c，0 -J c-1，0 ≥JE, then Q c For balance; J c，0 is the sum of the heat change values ​​of all key propagation paths in the cth first target time period; J c-1，0 is the sum of the heat change values ​​of all key propagation paths in the c-1th first target time period; JY is the first heat value threshold; JE is the second heat value threshold.

[0054] Here, the change in the heat value of the target network event in each key propagation path in the first target time window is obtained, so as to reflect the increase or decrease in the heat of the target network event in each key propagation path in the first target time window over time. At the same time, the corresponding traffic change trend (increase, decrease or balance) of the target network event in the time period is obtained according to the change in the sum of the heat change values ​​of all key propagation paths in every two adjacent first target time periods.

[0055] S620, using the heat change value as the observed state of the target Markov model, using the traffic change trend as the hidden state of the target Markov model, and obtaining the predicted traffic change trend set YQ of the target network event in the second target time window according to the target Markov model = (YQ1, YQ2, ..., YQ g ,…,YQ h );YQ g The predicted traffic change trend of the g-th second target time period of the target network event within the second target time window; the predicted traffic change trends include rising, falling and balanced; h is the number of second target time periods; the start time of the second target time window is the current time; the second target time window includes h consecutive and equal-length second target time periods.

[0056] Here, the heat change value of each key propagation path in the above-mentioned first target time window regarding the target network event in each first target time period is taken as the observation state sequence of the target Markov model, and the traffic change trend of the corresponding target network event in different first target time periods is taken as the hidden state sequence of the target Markov model. According to the target Markov model, the predicted traffic change trend set YQ of the target network event in the second target time window is obtained.

[0057] S630, obtaining the traffic change trend of the network event corresponding to each processing solution in the processing solution library within the third target time window, so as to obtain a traffic change trend list set F=(F1, F2, ..., F r , …, F s ), where r = 1, 2, ..., s; F r is a list of traffic change trends of network events corresponding to the rth processing solution in the processing solution library; F r =(F r，1 , F r，2 , …, F r，g , …, F r，h );F r，g The traffic change trend of the g-th third target time period of the network event corresponding to the r-th processing solution within the third target time window; the length of the third target time window is equal to the length of the second time window; and the number of the third target time periods is equal to the number of the second target time periods.

[0058] Here, in order to determine a suitable processing scheme for the target network event, the present application is provided with a processing scheme library, in which a number of processing schemes are provided, and each processing scheme has at least one network event adapted for processing. Here, firstly, the flow change trend of the network event corresponding to each processing scheme in the processing scheme library in the third target time window is obtained to obtain a flow change trend list set F. Here, the length of the third target time window is equal to the length of the second time window and the number of the third target time periods is equal to the number of the second target time periods. Further, the first time interval between the start time of the second target time window and the start time of the target network event is the same as the second time interval between the start time of the third target time window and the start time of the corresponding network event. That is, the start time of the third target time window is the same as the time interval between the start time of the second target time and the start time of the corresponding network event, so as to obtain a flow change trend list of network events corresponding to each processing scheme.

[0059] S640, according to YQ and F, obtain a matching list P = (P1, P2, ..., P r ,…,P s ), where P r For YQ and Fr The matching degree of P r =(YQ·F r ) / (|YQ|×|F r |).

[0060] S650, if P r If it is greater than the preset matching threshold, P r The corresponding treatment plan is determined as the target treatment plan.

[0061] Here, the traffic change trend list of network events corresponding to each of the above processing schemes and the matching degree of YQ are obtained. Since the selection principle of the time window is the same, the higher the matching degree, the more likely the heat development trend of the corresponding network events is similar. Therefore, the processing scheme corresponding to the matching degree greater than the preset matching degree threshold is determined as the target processing scheme.

[0062] S660: Process the target network event according to the target processing solution.

[0063] Finally, the target network event is processed according to the one or more target processing solutions determined above. In this embodiment, the processing solution can be fine-tuned according to the actual situation of the target network event, or the target processing solution can be directly used for processing, which is not further limited here.

[0064] In this embodiment, the change of the heat value of each key propagation path of the target network event in each first target time period in the first target time window is used as the observation state sequence of the target Markov model, and the flow change trend of the corresponding target network event in different first target time periods is used as the hidden state sequence of the target Markov model. The predicted flow change trend in the second target time window is further output according to the target Markov model, thereby predicting the change trend of the heat of the target network event, and matching it with the processing scheme of the same time dimension in the processing scheme library, so as to obtain an adapted processing scheme. The granularity of the observation state sequence selected in this embodiment is small, the data is more and richer, and the time dimension selected for the heat trend corresponding to the processing scheme in the processing scheme library is consistent with the second target time window. Therefore, the higher the matching degree of the processing scheme, the more likely it is that the heat development trend of the corresponding network event is similar to the heat development trend of the target network event. Therefore, the processing scheme with a matching degree greater than the preset matching degree threshold is determined as the target processing scheme to process the target network event. The target processing scheme obtained in this way is more suitable for the target network event and has a better processing effect.

[0065] The embodiment of the present application also provides a target network event processing device 200, such as Figure 2 As shown, the above device comprises:

[0066] The data acquisition module 210 is used to acquire the propagation data of the target network event on each propagation path within the first target time window to obtain the average value set of traffic change degree L = (L1, L2, ..., L i , …, L n ); where i = 1, 2, ..., n; L i is the average value of the traffic change degree of the i-th propagation path with respect to the target network event; n is the number of propagation paths; and the end time of the first target time window is the current time.

[0067] The average value acquisition module 220 is used to determine the propagation path corresponding to the flow change degree average value greater than the preset flow change degree average value threshold in L as the key propagation path, so as to obtain the key flow change degree average value set G = (G1, G2, ..., G p , …, G q ), where p = 1, 2, ..., q, q is the number of critical propagation paths, G p is the average value of the traffic change degree of the pth key propagation path regarding the target network event.

[0068] The scoring acquisition module 230 is used to obtain the key propagation path impact value scoring set GP = (GP1, GP2, ..., GP p ,…,GP q );GP p Score the comprehensive impact value of the path of the pth key propagation path on the target network event; GP p =z1*G p +z2*Y p +z3*C p ; z1, z2, z3 are respectively the preset change degree weight, the preset data weight and the preset number of people weight; Y p is the data weight value of the pth key propagation path; C p is the number of participants in the pth key propagation path regarding the target network event.

[0069] The score acquisition module 240 is used to obtain the current opinion type score set D = (D1, D2, D3) according to the current opinion type of the GP and each key communication path; wherein D1 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is positive; D2 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is negative; and D3 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is neutral.

[0070] The model determination module 250 is used to determine the target Markov model according to D; wherein the viewpoint type of the target Markov model is the same as the path comprehensive impact value score in D and the highest current viewpoint type; each viewpoint type has a corresponding Markov model; and the Markov models corresponding to any two different viewpoint types are different.

[0071] The processing module 260 is used to process the target network event according to the target Markov model.

[0072] An embodiment of the present application further provides a computer program product, which includes program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present application described above in this specification.

[0073] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0074] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0075] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0076] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0077] The electronic device according to this embodiment of the present application is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0078] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0079] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps described in the above “Exemplary Method” section of this specification according to various exemplary embodiments of the present application.

[0080] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0081] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0082] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0083] The electronic device can also communicate with one or more external devices (such as keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that enable users to interact with the electronic device, and / or communicate with any device (such as routers, modems, etc.) that enables the electronic device to communicate with one or more other computing devices. This communication can be carried out through an input / output (I / O) interface. In addition, the electronic device can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs) and / or public networks, such as the Internet) through a network adapter. As shown in the figure, the network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0084] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0085] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present application can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present application described in the above "Exemplary Method" section of the present specification.

[0086] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The 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 readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable 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.

[0087] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0088] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0089] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0090] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0091] It should be noted that, although several modules or units of the device for action execution are 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.

[0092] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for processing a target network event, characterized in that: The method comprises: S100, obtaining propagation data of a target network event on each propagation path within a first target time window to obtain a set of average values ​​of flow variation L = (L1, L2, ..., L i , …, L n ); where i = 1, 2, ..., n; L i is the average value of the traffic change degree of the i-th propagation path with respect to the target network event; n is the number of propagation paths; the end time of the first target time window is the current time; S200, determining the propagation paths corresponding to the flow variation average values ​​greater than the preset flow variation average value threshold in L as key propagation paths, so as to obtain the key flow variation average value set G = (G1, G2, ..., G p , …, G q ), where p = 1, 2, ..., q, q is the number of critical propagation paths, G p is the average value of the traffic change degree of the pth key propagation path with respect to the target network event; S300, according to G, obtain the key propagation path impact value score set GP = (GP1, GP2, ..., GP p ,…,GP q );GP p Score the comprehensive impact value of the path of the pth key propagation path on the target network event; GP p =z1*G p +z2*Y p +z3*C p ; z1, z2, z3 are respectively the preset change degree weight, the preset data weight and the preset number of people weight; Y p is the data weight value of the pth key propagation path; C p is the number of participants in the pth key communication path regarding the target network event; S400, according to the current opinion type of the GP and each key communication path, obtain the current opinion type score set D = (D1, D2, D3); wherein D1 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is positive; D2 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is negative; D3 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is neutral; S500, determining a target Markov model according to D; wherein the viewpoint type of the target Markov model is the same as the path comprehensive impact value score in D and the highest current viewpoint type; each viewpoint type has a corresponding Markov model; any two different viewpoint types have different corresponding Markov models; S600: Process the target network event according to the target Markov model.

2. The target network event processing method according to claim 1, characterized in that: The first target time window includes m consecutive and equal first target time periods; each first target time period corresponds to a total heat value; L i Meet the following conditions: K i，j K is the traffic change value of the target network event on the i-th propagation path from the j-th first target time period to the j+1-th first target time period; i，j =(R i，j+1 -R i，j ) / (T i，j+1 -T i，j );R i，j+1 is the total heat value of the i-th propagation path in the j+1-th first target time period; R i，j is the total heat value of the i-th propagation path in the j-th first target time period; T i，j+1 is the end time of the j+1th first target time period of the ith propagation path; T i，j is the end time of the jth first target time period of the i-th propagation path.

3. The target network event processing method according to claim 1, characterized in that: Y p Determine by following these steps: S310, obtaining a path identifier corresponding to the pth key propagation path; the path identifier is used to uniquely identify the corresponding key propagation path; S320, traverse the preset mapping table according to the path identifier corresponding to the pth key propagation path, and determine Y p ; Among them, the preset mapping table includes the correspondence between each path identifier and each data weight value.

4. The target network event processing method according to claim 2, characterized in that: The step S600 includes: S610, obtaining the heat change data corresponding to each key propagation path of the target network event to obtain a heat change information set X=(X1, X2, ..., X c , …, X m ), where c = 1, 2, ..., m; X c is the heat change information of the target network event in the cth first target time period within the first target time window; X c =(J c , Q c );J c is the heat change value sequence corresponding to the target network event in the cth first target time period; J c =(J c，1 , J c，2 , …, J c，p , …, J c，q );J c，p is the heat change value of the pth key propagation path of the target network event in the cth first target time period; J c，p =A c，p -A c-1，p Among them, A c，p A is the heat value of the pth key propagation path of the target network event in the cth first target time period; c-1，p is the heat value of the pth key propagation path of the target network event in the c-1th first target time period; Q c is the flow change trend in the cth first target time period; if J c，0 -J c-1，0 >JY, then Q c is rising; if J c，0 -J c-1，0 <JE, then Q c is decreasing; if JY≥J c，0 -J c-1，0 ≥JE, then Q c For balance; J c，0 is the sum of the heat change values ​​of all key propagation paths in the cth first target time period; J c-1，0 is the sum of the heat change values ​​of all key propagation paths in the c-1th first target time period; JY is the first heat value threshold; JE is the second heat value threshold; S620, using the heat change value as the observed state of the target Markov model, using the traffic change trend as the hidden state of the target Markov model, and obtaining the predicted traffic change trend set YQ of the target network event in the second target time window according to the target Markov model = (YQ1, YQ2, ..., YQ g ,…,YQ h );YQ g is the predicted traffic change trend of the g-th second target time period of the target network event within the second target time window; the predicted traffic change trend includes rising, falling and balanced; h is the number of second target time periods; the start time of the second target time window is the current time; the second target time window includes h consecutive and equal-length second target time periods; S630, obtaining the traffic change trend of the network event corresponding to each processing solution in the processing solution library within the third target time window, so as to obtain a traffic change trend list set F=(F1, F2, ..., F r , …, F s ), where r = 1, 2, ..., s; F r is a list of traffic change trends of network events corresponding to the rth processing solution in the processing solution library; F r =(F r，1 , F r，2 , …, F r，g , …, F r，h );F r，g is the traffic change trend of the g-th third target time period of the network event corresponding to the r-th processing solution within the third target time window; the length of the third target time window is equal to the length of the second time window; the number of the third target time periods is equal to the number of the second target time periods; S640, according to YQ and F, obtain a matching list P = (P1, P2, ..., P r ,…,P s ), where P r For YQ and F r The matching degree of P r =(YQ·F r ) / (|YQ|×|F r |); S650, if P r If the value is greater than the preset matching threshold, P r The corresponding treatment plan is determined as the target treatment plan; S660: Process the target network event according to the target processing solution.

5. The target network event processing method according to claim 4, characterized in that: The first time interval between the start time of the second target time window and the start time of the target network event is the same as the second time interval between the start time of the third target time window and the start time of the corresponding network event.

6. A target network event processing device, characterized in that: The device comprises: The data acquisition module is used to acquire the propagation data of the target network event on each propagation path within the first target time window to obtain the average value set of traffic change degree L = (L1, L2, ..., L i , …, L n ); where i = 1, 2, ..., n; L i is the average value of the traffic change degree of the i-th propagation path with respect to the target network event; n is the number of propagation paths; the end time of the first target time window is the current time; The average value acquisition module is used to determine the propagation path corresponding to the flow change degree average value greater than the preset flow change degree average value threshold in L as the key propagation path, so as to obtain the key flow change degree average value set G = (G1, G2, ..., G p , …, G q ), where p = 1, 2, ..., q, q is the number of critical propagation paths, G p is the average value of the traffic change degree of the pth key propagation path with respect to the target network event; The scoring acquisition module is used to obtain the key propagation path impact value scoring set GP = (GP1, GP2, ..., GP p ,…,GP q );GP p Score the comprehensive impact value of the path of the pth key propagation path on the target network event; GP p =z1*G p +z2*Y p +z3*C p ; z1, z2, z3 are respectively the preset change degree weight, the preset data weight and the preset number of people weight; Y p is the data weight value of the pth key propagation path; C p is the number of participants in the pth key communication path regarding the target network event; The score acquisition module is used to obtain the current opinion type score set D = (D1, D2, D3) according to the current opinion type of the GP and each key communication path; wherein D1 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is positive; D2 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is negative; D3 is the path comprehensive impact value score sum of all key communication paths in the GP whose current opinion type is neutral; A model determination module is used to determine a target Markov model according to D; wherein the viewpoint type of the target Markov model is the same as the path comprehensive impact value score in D and the highest current viewpoint type; each viewpoint type has a corresponding Markov model; any two different viewpoint types have different corresponding Markov models; The processing module is used to process the target network event according to the target Markov model.

7. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method as claimed in any one of claims 1 to 5.

8. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 7.

Images