Online data flow monitoring optimization method, device, equipment and medium

Abstract

The invention provides an online data flow monitoring optimization method and device, equipment and a medium, and the method comprises the steps: obtaining an application program, dividing the application program into a plurality of groups, then pre-distributing a first bandwidth, obtaining a hotspot comment, setting a second bandwidth based on the hotspot comment, and setting the second bandwidth based on the hotspot comment; and finally, setting the bandwidth of each group based on the first bandwidth and the second bandwidth. The method has the beneficial effects that intelligent allocation and dynamic adjustment of the bandwidth are realized, the utilization efficiency of network resources is improved, and the network experience of a user is also improved. Meanwhile, through subsequent monitoring and optimization measures, the rationality and effectiveness of bandwidth allocation are ensured.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an online data flow monitoring optimization method, device, equipment and medium. Background Art

[0002] By monitoring network traffic and understanding the bandwidth usage of various applications, we can take measures to optimize it, thereby improving network performance and user experience. In the existing technology, regulation is generally based on the existing network traffic. However, network traffic is changing rapidly, and the bandwidth requirements of various applications are different in different time periods. Therefore, the bandwidth allocation range will be relatively large, resulting in a slow efficiency of bandwidth allocation. Summary of the invention

[0003] The main purpose of the present invention is to provide an online data flow monitoring optimization method, device, equipment and medium, aiming to solve the problem that the existing bandwidth allocation has a relatively large amplitude, resulting in a low efficiency of bandwidth allocation.

[0004] The present invention provides an online data flow monitoring optimization method, comprising:

[0005] Get multiple applications and divide each application into n groups;

[0006] Obtain historical data traffic of each application in the group, and convert the historical data traffic into historical usage values;

[0007] pre-allocating a first bandwidth to each group based on the historical usage value;

[0008] Obtain multiple hot comments related to multiple platform hot topics from the preset platform;

[0009] Obtain hot review words of each application from each hot review;

[0010] Convert each of the hot comment words corresponding to the application into a hot value according to a preset conversion relationship;

[0011] Calculate the sum of the hotspot values ​​of each application in the group to obtain the hotspot value of the group;

[0012] Setting the second bandwidth of each group according to the hotspot value of the group;

[0013] The bandwidth of each group is allocated based on the first bandwidth and the second bandwidth.

[0014] Furthermore, the step of obtaining a plurality of applications and dividing each application into n groups includes:

[0015] Acquire application information of each of the application programs, and convert each of the application information into text information according to a preset conversion method;

[0016] Classifying the text information according to a preset classification method and sorting them according to the order of categories, and separating each text information with a preset separator to obtain an application text;

[0017] Randomly select n-1 separators as the preset separators;

[0018] Calculate the fluctuation value between each sub-text separated by a preset separator;

[0019] If the fluctuation value is less than the preset fluctuation value, reselect the separator until the fluctuation value corresponding to the selected target separator is greater than or equal to the preset fluctuation value;

[0020] The corresponding application programs are divided into n groups based on the target separator.

[0021] Furthermore, after the step of allocating the bandwidth of each group based on the first bandwidth and the second bandwidth, the method further includes:

[0022] Get the usage frequency of each application in each group;

[0023] Setting a priority order for each application within the group according to the frequency of use;

[0024] A bandwidth priority satisfaction order is set for each application according to the priority order.

[0025] Furthermore, after the step of allocating the bandwidth of each group based on the first bandwidth and the second bandwidth, the method further includes:

[0026] Analyze the data information of each group through preset monitoring tools;

[0027] Determine whether the data information contains abnormal information;

[0028] If there is abnormal information, the bandwidth of each application in the group will be stopped.

[0029] Furthermore, after the step of allocating the bandwidth of each group based on the first bandwidth and the second bandwidth, the method further includes:

[0030] Monitor the fluctuation of traffic data of each group;

[0031] When the fluctuation of the flow data of a group exceeds the preset value, the fluctuation of the group and the corresponding application are sent to relevant personnel for confirmation;

[0032] After receiving the confirmation instructions from relevant personnel, the bandwidth of each group is recalculated and allocated.

[0033] Furthermore, the step of converting each of the hot comment words corresponding to the application into a hot value according to a preset conversion relationship includes:

[0034] Using sentiment analysis tools to analyze the hot comment words, and obtaining words representing sentiment tendencies and their sentiment polarity values;

[0035] Count the probability of occurrence of words with positive emotions; among them, words with emotional polarity values ​​greater than a set value are words with positive emotions, and words with emotional polarity values ​​less than or equal to the set value are words with negative emotions;

[0036] A hotspot value of the application is calculated according to the probability of occurrence of words with positive emotions.

[0037] Furthermore, the step of pre-allocating the first bandwidth for each group based on the historical usage value includes:

[0038] Set a base bandwidth for each group;

[0039] pre-allocating additional bandwidth to each group based on the historical usage values;

[0040] The basic bandwidth is added to the additional bandwidth to obtain a first bandwidth pre-allocated to each group.

[0041] The present invention also provides an online data flow monitoring and optimization device, comprising:

[0042] A first acquisition module is used to acquire multiple applications and divide each application into n groups;

[0043] The second acquisition module is used to acquire the historical data flow of each application in the group and convert the historical data flow into a historical usage value;

[0044] An allocation module, configured to pre-allocate a first bandwidth to each group based on the historical usage value;

[0045] The third acquisition module is used to obtain multiple hot comments related to multiple platform hotspots from a preset platform;

[0046] The fourth acquisition module is used to obtain the hot comment words of each application from each hot comment;

[0047] A conversion module, used to convert each of the hot comment words corresponding to the application into a hot value according to a preset conversion relationship;

[0048] A calculation module, used to calculate the sum of the hotspot values ​​of each application in the group to obtain the hotspot value of the group;

[0049] A setting module, used for setting the second bandwidth of each group according to the hotspot value of the group;

[0050] An allocation module is used to allocate the bandwidth of each group based on the first bandwidth and the second bandwidth.

[0051] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0052] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0053] The beneficial effects of the present invention are as follows: by obtaining applications, dividing them into multiple groups, and then pre-allocating the first bandwidth, then obtaining hot comments, setting the second bandwidth based on the hot comments, and finally setting the bandwidth of each group based on the first bandwidth and the second bandwidth, the intelligent allocation and dynamic adjustment of bandwidth are realized. This method not only improves the utilization efficiency of network resources, but also improves the user's network experience. At the same time, through subsequent monitoring and optimization measures, the rationality and effectiveness of bandwidth allocation are ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flow chart of an online data flow monitoring optimization method according to an embodiment of the present invention;

[0055] Figure 2 It is a schematic block diagram of the structure of an online data flow monitoring and optimization device according to an embodiment of the present invention;

[0056] Figure 3 A schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. The connection can be a direct connection or an indirect connection.

[0060] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone.

[0061] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0062] Reference Figure 1 The present invention proposes an online data flow monitoring optimization method, comprising:

[0063] S1: Get multiple applications and divide each application into n groups;

[0064] S2: Obtain historical data traffic of each application in the group, and convert the historical data traffic into historical usage values;

[0065] S3: pre-allocate a first bandwidth for each group based on the historical usage value;

[0066] S4: obtaining multiple hot comments related to multiple platform hot topics from a preset platform;

[0067] S5: obtaining hot comment words of each application from each hot comment;

[0068] S6: converting each of the hot comment words corresponding to the application into a hot value according to a preset conversion relationship;

[0069] S7: Calculate the sum of the hotspot values ​​of each application in the group to obtain the hotspot value of the group;

[0070] S8: setting the second bandwidth of each group according to the hotspot value of the group;

[0071] S9: Allocate bandwidth for each group based on the first bandwidth and the second bandwidth.

[0072] As described in the above step S1, multiple applications are obtained, and each application is divided into n groups; wherein the number of applications should be more than the number of groups, wherein the grouping method is not predetermined, and can be classified based on the category of each application, or can be classified randomly, or can be classified according to the usage of data traffic, preferably classified by category, because the cache content used by the same category may be consistent, and grouping them into one group can optimize the bandwidth.

[0073] As described in step S2 above, the historical data traffic of each application in the group is obtained, and the historical data traffic is converted into a historical usage value. The historical data traffic is the recent data traffic, for example, it can be set to the recent day, or the recent hours, etc., and the historical data traffic of each application can be obtained. To convert the historical data traffic into a historical usage value, a correspondence table between historical traffic data and historical usage values ​​can be established in advance, and the historical usage values ​​can be obtained based on the correspondence table.

[0074] As described in step S3 above, a first bandwidth is pre-allocated to each group based on the historical usage value. The first bandwidth can be allocated based on the ratio of each historical usage value. In a preferred embodiment, a basic bandwidth can be pre-allocated to each group, and then the remaining bandwidth is allocated according to the historical usage value.

[0075] As described in the above steps S4-S7, multiple hot comments related to multiple platform hot spots are obtained from a preset platform, wherein the preset platform is a related platform, such as a platform for car reviews, so that multiple platform hot spots can be obtained, and then hot comment words are obtained from the comment area. Each of the hot comment words corresponding to the application is converted into a hot value according to a preset conversion relationship, wherein the conversion method can be based on the part of speech of each word, positive comment words can increase the hot value, and negative comment words can reduce the hot value, so that the hot value of each application can be obtained, and the hot value of each group can be obtained by summing up.

[0076] As described in the above steps S8-S9, the second bandwidth of each group is set according to the hot spot value of the group. The setting method can be allocated based on the ratio of each hot spot value, and the bandwidth of each group is allocated based on the first bandwidth and the second bandwidth. The allocation method can be to find the average value of the first bandwidth and the second bandwidth, or to trim the first bandwidth based on the second bandwidth. Specifically, a part of the bandwidth can be extracted from the first bandwidth in proportion as the spare bandwidth, and then the spare bandwidth can be redistributed to each group based on the ratio of the second bandwidth, so as to achieve the bandwidth allocation of each group. In this way, the hot spots can be integrated on the original basis, which can greatly improve the utilization rate of the bandwidth. In a preferred embodiment, a basic bandwidth can be allocated to each group in advance, and then the remaining bandwidth can be allocated according to the ratio of the hot spot value. By comprehensively considering the historical data traffic of the application and the current platform hot spots, the intelligent allocation and dynamic adjustment of bandwidth are realized. This method not only improves the utilization efficiency of network resources, but also improves the user's network experience. At the same time, through subsequent monitoring and optimization measures, the rationality and effectiveness of bandwidth allocation are ensured.

[0077] In one embodiment, the step S1 of obtaining a plurality of applications and dividing each application into n groups includes:

[0078] S101: Acquire application information of each application program, and convert each application information into text information according to a preset conversion method;

[0079] S102: Classifying the text information according to a preset classification method and sorting the text information according to the order of the categories, and separating each text information with a preset separator to obtain an application text;

[0080] S103: Randomly select n-1 separators as preset separators;

[0081] S104: Calculating the fluctuation value between each subtext separated by a preset separator;

[0082] S105: If the fluctuation value is less than the preset fluctuation value, reselect a separator until the fluctuation value corresponding to the selected target separator is greater than or equal to the preset fluctuation value;

[0083] S106: Divide the corresponding application into n groups based on the target separator.

[0084] As described in step S101 above, the application information of each application is obtained, and each application information is converted into text information according to a preset conversion method. The system can obtain relevant information (such as name, size, function description, etc.) from each application, and convert this information into text information in a preset manner (such as encoding, formatting, etc.) for subsequent processing.

[0085] As described in the above step S102, the text information is classified according to a preset classification method and sorted in the order of categories, and each text information is separated by a preset separator to obtain an application text. The system will classify the text information according to a preset classification method (such as based on function, size, user rating, etc.) and sort it in the order of categories. The sorted text information will be separated by a preset separator (such as a comma, a line break, etc.) to form a text containing all application information.

[0086] As described in the above step S103, n-1 separators are randomly selected as preset separators; n-1 separators are randomly selected (selected from the separators used in the above steps), and these separators will be used for subsequent sub-text division.

[0087] As described in step S104, the fluctuation values ​​between the sub-texts separated by the preset separators are calculated; the fluctuation values ​​between the sub-texts separated by these preset separators (i.e., the text information of each application) are calculated. This fluctuation value may be based on the difference, similarity or other metric of the text content. It should be noted that the larger the fluctuation value, the better the separation effect.

[0088] As described in step S105 above, if the fluctuation value is less than the preset fluctuation value, a separator is reselected until the fluctuation value corresponding to the selected target separator is greater than or equal to the preset fluctuation value. If the calculated fluctuation value is less than the preset fluctuation value, it means that the currently selected separator does not effectively separate the application text into distinct sub-texts. Therefore, the system will reselect separators and repeatedly calculate the fluctuation value until a set of separators is found so that the fluctuation value between the sub-texts separated by them is greater than or equal to the preset fluctuation value.

[0089] As described in step S106, the corresponding applications are divided into n groups based on the target separator. According to the selected target separator, the application text is divided into n groups. Each group contains a group of applications with similar or related features.

[0090] Automatically classify and group applications for better management and analysis. Flexible handling of different types of applications can be achieved by adjusting the preset classification methods, separators, and fluctuation values.

[0091] In one embodiment, after the step S9 of allocating the bandwidth of each group based on the first bandwidth and the second bandwidth, the method further includes:

[0092] S1001: Obtain the usage frequency of each application in each group;

[0093] S1002: setting the priority order of each application in the group according to the usage frequency;

[0094] S1003: Setting a bandwidth priority satisfaction order for each application according to the priority order.

[0095] As described in step S1001 above, the usage frequency of each application in each group is obtained. The usage data of each application in each group is collected and analyzed to determine the frequency of their use by users. This frequency may be based on the number of times the user opens the application, the length of time the application is used, or the usage in a specific time period (such as a day, a week), etc.

[0096] As described in step S1002, the priority order of each application in the group is set according to the frequency of use; once the frequency of use of each application is obtained, the system will set the priority order of each application in the group according to the frequency. Generally, applications with higher frequency of use will be given higher priority because they are more important or frequently used by the user.

[0097] As described in step S1003 above, a bandwidth priority satisfaction order is set for each application according to the priority order. According to the priority order set previously, a bandwidth priority satisfaction order is allocated to each application. This means that in the case of limited network resources or bandwidth competition, applications with higher priorities will have priority in obtaining the required bandwidth resources to ensure that they can operate normally and provide a good user experience. The allocation of network resources is optimized to ensure that the most important applications can get sufficient bandwidth support in a high-load or bandwidth-constrained environment. By dynamically adjusting the priority and bandwidth allocation of applications, the overall system performance and user satisfaction can be improved.

[0098] In one embodiment, after the step S9 of allocating the bandwidth of each group based on the first bandwidth and the second bandwidth, the method further includes:

[0099] S1101: Analyze data information of each group through a preset monitoring tool;

[0100] S1102: Determine whether the data information contains abnormal information;

[0101] S1103: If there is abnormal information, stop the bandwidth of each application in the group.

[0102] As described in step S1101 above, the data information of each group is analyzed by a preset monitoring tool; the data information of each group is collected and analyzed by using a preset monitoring tool (such as network monitoring software, performance analysis tool, etc.). Such information may include the running status of the application, network bandwidth usage, user behavior data, etc.

[0103] As described in step S1102 above, determine whether the data information contains abnormal information. Analyze the collected data information to determine whether it contains abnormal information. Abnormal information may indicate application failure, network attack, resource abuse and other problems. The system will identify these abnormal information according to the preset abnormal detection rules or algorithms.

[0104] As described in step S1103 above, if there is abnormal information, the bandwidth of each application in the group is stopped. If the system detects that the data information contains abnormal information, in order to protect the security and stability of the network, the system will take emergency measures to stop the bandwidth of each application in the group. This means that the system will temporarily cut off the network connection of these applications to prevent the further spread of abnormal information or cause greater impact on the network.

[0105] This monitoring and response mechanism can be used to protect the security and stability of the network and prevent abnormal behavior of applications from causing damage to the network. By timely detecting and responding to abnormal information, the system can quickly take measures to reduce potential risks and losses. However, in actual applications, stopping bandwidth may be an extreme measure, and is usually only taken after other milder solutions (such as restarting the application, adjusting the configuration, etc.) have been tried and failed. That is, in some embodiments, the application can also be restarted or the configuration can be adjusted.

[0106] In one embodiment, after the step S9 of allocating the bandwidth of each group based on the first bandwidth and the second bandwidth, the method further includes:

[0107] S1201: monitor the fluctuation of traffic data of each group;

[0108] S1202: When the fluctuation of the flow data of a group exceeds a preset value, the fluctuation of the group and the corresponding application are sent to relevant personnel for confirmation;

[0109] S1203: After receiving the confirmation instruction from the relevant personnel, recalculate the bandwidth of each group and allocate it.

[0110] As described in step S1201 above, the fluctuation of the flow data of each group is monitored, the flow data of each group is continuously monitored, and the fluctuation is analyzed. The fluctuation of the flow data may reflect the changes in the network activities of the application in the group, such as the increase in user visits, the launch of new functions, etc.

[0111] As described in step S1202 above, when the fluctuation of the flow data of a group exceeds the preset value, the fluctuation of the group and the corresponding application are sent to relevant personnel for confirmation. If the fluctuation of the flow data of a group exceeds the preset threshold (this threshold may be set based on historical data, network capacity planning, etc.), the system will trigger the alarm mechanism. The alarm information will include the flow fluctuation of the group and the corresponding application information, and will be sent to relevant personnel (such as network administrators, application maintenance personnel, etc.) for confirmation.

[0112] As described in the above step S1203, after receiving the confirmation instruction from the relevant personnel, the bandwidth of each group is recalculated and allocated. After receiving the confirmation instruction from the relevant personnel, the system will recalculate the bandwidth requirements of each group based on the current traffic data and network conditions. The recalculation method is the same as the above steps and will not be repeated here. After the calculation is completed, the system will reallocate the bandwidth of each group according to the new bandwidth allocation plan to ensure the rational use of network resources and the smooth operation of the application. It helps to timely discover and handle network traffic anomalies, prevent network congestion and degradation of application performance. Through monitoring, alarm and bandwidth reallocation, the system can dynamically adjust network resources to adapt to changes in application and user needs.

[0113] In one embodiment, the step S6 of converting each of the hot comment words corresponding to the application into a hot value according to a preset conversion relationship includes:

[0114] S601: Analyze the hot comment words using a sentiment analysis tool to obtain words representing sentiment tendencies and their sentiment polarity values;

[0115] S602: Counting the probability of occurrence of words with positive emotions; wherein, words with a sentiment polarity value greater than a set value are words with positive emotions, and words with a sentiment polarity value less than or equal to the set value are words with negative emotions;

[0116] S603: Calculate the hotspot value of the application program according to the probability of occurrence of words with positive emotions.

[0117] As described in the above steps S601-S603, the calculation of hot spot values ​​is realized. Specifically, the preset sentiment analysis tool SentiWordNet can be used. SentiWordNet can divide hot comment words into positivity and negativity according to the sentiment scores, and further count the probability of occurrence of positive emotional words and the probability of occurrence of negative emotional words in the comment content, and calculate the hot spot value of the application according to the probability of occurrence of positive emotional words and the probability of occurrence of negative emotional words.

[0118] In one embodiment, the step S3 of pre-allocating the first bandwidth for each group based on the historical usage value includes:

[0119] S301: Setting a basic bandwidth for each group;

[0120] S302: pre-allocate additional bandwidth for each group based on the historical usage value;

[0121] S303: Add the basic bandwidth to the additional bandwidth to obtain a first bandwidth pre-allocated to each group.

[0122] As described in the above steps S301-S303, the pre-allocation of the first bandwidth is achieved, that is, a basic bandwidth is set for each group. This basic bandwidth is the minimum network resource required to ensure the normal operation of the application program in the group. It is set based on factors such as the type of application, the number of users, and business needs. Additional bandwidth is pre-allocated to each group based on historical usage values ​​(such as traffic data, user access patterns, etc. over a period of time). This additional bandwidth is an additional network resource reserved to cope with traffic fluctuations, emergencies, or future growth. The basic bandwidth and the additional bandwidth are added together to obtain the first bandwidth pre-allocated to each group. This first bandwidth is the bandwidth resource initially obtained by the group in the network, which is used to support the normal operation of the application program in the group and future development needs.

[0123] Reference Figure 2 The present invention also provides an online data flow monitoring and optimization device, comprising:

[0124] A first acquisition module 10 is used to acquire multiple applications and divide each application into n groups;

[0125] The second acquisition module 20 is used to acquire the historical data flow of each application in the group and convert the historical data flow into a historical usage value;

[0126] An allocation module 30, configured to pre-allocate a first bandwidth to each group based on the historical usage value;

[0127] The third acquisition module 40 is used to acquire multiple hot comments related to multiple platform hotspots from a preset platform;

[0128] A fourth acquisition module 50 is used to acquire hot comment words of each application from each hot comment;

[0129] The conversion module 60 is used to convert each of the hot comment words corresponding to the application into a hot value according to a preset conversion relationship;

[0130] A calculation module 70, used to calculate the sum of the hotspot values ​​of each application in the group to obtain the hotspot value of the group;

[0131] A setting module 80, configured to set the second bandwidth of each group according to the group hotspot value;

[0132] The allocation module 90 is used to allocate the bandwidth of each group based on the first bandwidth and the second bandwidth.

[0133] In one embodiment, the first acquisition module 10 includes:

[0134] An application information acquisition submodule, used to acquire application information of each of the application programs, and convert each of the application information into text information according to a preset conversion method;

[0135] A classification submodule, used to classify the text information according to a preset classification method and sort it according to the order of categories, and separate each text information with a preset separator to obtain an application text;

[0136] A random selection submodule is used to randomly select n-1 delimiters as preset delimiters;

[0137] The fluctuation value calculation submodule is used to calculate the fluctuation value between each subtext separated by a preset separator;

[0138] A reselect submodule is used to reselect a separator if the fluctuation value is less than a preset fluctuation value, until the fluctuation value corresponding to the selected target separator is greater than or equal to the preset fluctuation value;

[0139] The division submodule is used to divide the corresponding application into n groups based on the target separator.

[0140] In one embodiment, the online data traffic monitoring and optimization device further includes:

[0141] A usage frequency acquisition module is used to acquire the usage frequency of each application in each group;

[0142] A priority order setting module, used to set the priority order of each application program in the group according to the usage frequency;

[0143] The bandwidth priority satisfaction order setting module is used to set the bandwidth priority satisfaction order for each application according to the priority order.

[0144] In one embodiment, the online data traffic monitoring and optimization device further includes:

[0145] Data information analysis module, used to analyze the data information of each group through preset monitoring tools;

[0146] A data information judgment module is used to judge whether the data information contains abnormal information;

[0147] The bandwidth stopping module is used to stop the bandwidth of each application in the group if there is abnormal information.

[0148] In one embodiment, the online data traffic monitoring and optimization device further includes:

[0149] Fluctuation monitoring module, used to monitor the fluctuation of traffic data of each group;

[0150] An information sending module is used to send the fluctuation of the group's flow data and the corresponding application to relevant personnel for confirmation when the fluctuation of the group's flow data exceeds a preset value;

[0151] The bandwidth recalculation module is used to recalculate the bandwidth of each group and allocate it after receiving the confirmation instruction from the relevant personnel.

[0152] In one embodiment, the conversion module 60 includes:

[0153] An analysis submodule is used to analyze the hot comment words using a sentiment analysis tool to obtain words representing sentiment tendencies and their sentiment polarity values;

[0154] The probability statistics submodule is used to count the probability of occurrence of words with positive emotions; wherein, words with a sentiment polarity value greater than a set value are words with positive emotions, and words with a sentiment polarity value less than or equal to the set value are words with negative emotions;

[0155] The hotspot value calculation submodule is used to calculate the hotspot value of the application according to the probability of occurrence of words with positive emotions.

[0156] In one embodiment, the allocation module 30 includes:

[0157] The basic bandwidth setting submodule is used to set a basic bandwidth for each group;

[0158] An additional bandwidth setting submodule, used for pre-allocating additional bandwidth for each group based on the historical usage value;

[0159] The first bandwidth setting submodule is used to add the basic bandwidth to the additional bandwidth to obtain the first bandwidth pre-allocated to each group.

[0160] The beneficial effects of the present invention are as follows: by obtaining applications, dividing them into multiple groups, and then pre-allocating the first bandwidth, then obtaining hot comments, setting the second bandwidth based on the hot comments, and finally setting the bandwidth of each group based on the first bandwidth and the second bandwidth, the intelligent allocation and dynamic adjustment of bandwidth are realized. This method not only improves the utilization efficiency of network resources, but also improves the user's network experience. At the same time, through subsequent monitoring and optimization measures, the rationality and effectiveness of bandwidth allocation are ensured.

[0161] Reference Figure 3 In the embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store various hot comments, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the online data flow monitoring optimization method described in any of the above embodiments can be implemented.

[0162] Those skilled in the art will understand that Figure 3 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied.

[0163] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the online data flow monitoring optimization method described in any of the above embodiments can be implemented.

[0164] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0165] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0166] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0167] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0168] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. An online data flow monitoring optimization method, characterized in that: include: Get multiple applications and divide each application into n groups; Obtain historical data traffic of each application in the group, and convert the historical data traffic into historical usage values; pre-allocating a first bandwidth to each group based on the historical usage value; Obtain multiple hot comments related to multiple platform hot topics from the preset platform; Obtain hot review words of each application from each hot review; Convert each of the hot comment words corresponding to the application into a hot value according to a preset conversion relationship; Calculate the sum of the hotspot values ​​of each application in the group to obtain the hotspot value of the group; Setting the second bandwidth of each group according to the hotspot value of the group; The bandwidth of each group is allocated based on the first bandwidth and the second bandwidth.

2. The online data flow monitoring and optimization method according to claim 1, characterized in that: The step of obtaining multiple applications and dividing each application into n groups includes: Acquire application information of each of the application programs, and convert each of the application information into text information according to a preset conversion method; Classifying the text information according to a preset classification method and sorting them according to the order of categories, and separating each text information with a preset separator to obtain an application text; Randomly select n-1 separators as the preset separators; Calculate the fluctuation value between each sub-text separated by a preset separator; If the fluctuation value is less than the preset fluctuation value, reselect the separator until the fluctuation value corresponding to the selected target separator is greater than or equal to the preset fluctuation value; The corresponding application programs are divided into n groups based on the target separator.

3. The online data flow monitoring and optimization method according to claim 1, characterized in that: After the step of allocating the bandwidth of each group based on the first bandwidth and the second bandwidth, the method further includes: Get the usage frequency of each application in each group; Setting a priority order for each application within the group according to the frequency of use; A bandwidth priority satisfaction order is set for each application according to the priority order.

4. The online data flow monitoring and optimization method according to claim 1, characterized in that: After the step of allocating the bandwidth of each group based on the first bandwidth and the second bandwidth, the method further includes: Analyze the data information of each group through preset monitoring tools; Determine whether the data information contains abnormal information; If there is abnormal information, the bandwidth of each application in the group will be stopped.

5. The online data flow monitoring and optimization method according to claim 1, characterized in that: After the step of allocating the bandwidth of each group based on the first bandwidth and the second bandwidth, the method further includes: Monitor the fluctuation of traffic data of each group; When the fluctuation of the flow data of a group exceeds the preset value, the fluctuation of the group and the corresponding application are sent to relevant personnel for confirmation; After receiving the confirmation instructions from relevant personnel, the bandwidth of each group is recalculated and allocated.

6. The online data flow monitoring and optimization method according to claim 1, characterized in that: The step of converting each of the hot comment words corresponding to the application into a hot value according to a preset conversion relationship includes: Using sentiment analysis tools to analyze the hot comment words, and obtaining words representing sentiment tendencies and their sentiment polarity values; Count the probability of occurrence of words with positive emotions; among them, words with emotional polarity values ​​greater than a set value are words with positive emotions, and words with emotional polarity values ​​less than or equal to the set value are words with negative emotions; A hotspot value of the application is calculated according to the probability of occurrence of words with positive emotions.

7. The online data flow monitoring and optimization method according to claim 1, characterized in that: The step of pre-allocating a first bandwidth for each group based on the historical usage value comprises: Set a base bandwidth for each group; pre-allocating additional bandwidth to each group based on the historical usage values; The basic bandwidth is added to the additional bandwidth to obtain a first bandwidth pre-allocated to each group.

8. An online data flow monitoring and optimization device, characterized in that: include: A first acquisition module is used to acquire multiple applications and divide each application into n groups; The second acquisition module is used to acquire the historical data flow of each application in the group and convert the historical data flow into a historical usage value; An allocation module, configured to pre-allocate a first bandwidth to each group based on the historical usage value; The third acquisition module is used to obtain multiple hot comments related to multiple platform hotspots from a preset platform; The fourth acquisition module is used to obtain the hot comment words of each application from each hot comment; A conversion module, used to convert each of the hot comment words corresponding to the application into a hot value according to a preset conversion relationship; A calculation module, used to calculate the sum of the hotspot values ​​of each application in the group to obtain the hotspot value of the group; A setting module, used for setting the second bandwidth of each group according to the hotspot value of the group; An allocation module is used to allocate the bandwidth of each group based on the first bandwidth and the second bandwidth.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images