Multifunctional online service management system and method based on digital platform

Abstract

The invention discloses a multifunctional online service management system and method based on a digital platform, and belongs to the technical field of dynamic monitoring. The method comprises the following steps: acquiring network traffic data of all functions included in a single online service in a digital platform, and constructing a function-network traffic coordinate system and a network traffic fluctuation curve; based on the network traffic fluctuation curve, constructing a traffic peak value function pair and a traffic valley value function pair, and constructing a traffic peak value function pair set and a traffic valley value function pair set; the mode in the flow peak value function pair set is recorded as a hot function, and the mode in the flow valley value function pair set is recorded as a cold function; and calculating the occurrence probability of the hot function at the next time node, presetting a probability threshold value, and performing analysis and maintenance management. According to the method, the stability and the resource utilization rate of online services of the digital platform are improved, user behaviors and demand changes can be mined through function analysis, the business process is further optimized, and the service value is further expanded.

Description

Technical Field

[0001] The present invention relates to the field of service management technology, and specifically to a multifunctional online service management system and method based on a digital platform. Background Art

[0002] In recent years, with the deepening of digital transformation, the application of online service platforms in multiple industries has gradually deepened; traditional online service management methods usually rely on fixed functional modules and static resource allocation strategies. While this method meets basic service needs, it is difficult to adapt to the dynamic changes in user needs and the diversification of business scenarios; with the rapid development of network technology and the increasing complexity of user behavior, the data traffic of online service platforms has shown diversity and volatility; in order to improve user experience and system performance, the industry has gradually begun to pay attention to data-driven service management methods, and realize dynamic optimization of system functions through analysis and mining of network traffic data; however, current technical solutions are mostly focused on traffic monitoring and simple resource allocation and scheduling, lacking in-depth analysis and prediction of complex relationships between functions, resulting in problems such as inefficient resource utilization and untimely service response.

[0003] Existing online service management technologies fail to fully combine historical data to predict hot functions for the hot and cold distribution status of function usage, and thus lack the ability to proactively optimize system resources; the correlation between functions and the dynamic response mechanism to network traffic are not effectively utilized; for example, when certain functions are overloaded due to high traffic, it is often difficult to adjust resource allocation in a timely manner, which may lead to service interruption; most methods only manage unpopular functions at the level of simple deactivation or integration decisions, but fail to explore the potential value of functions through data-driven methods and make adjustments based on user needs. This simplistic approach may ignore the long-tail effect of function optimization, which is not conducive to the long-term stability and scalability of the system. Summary of the invention

[0004] The purpose of the present invention is to provide a multifunctional online service management system and method based on a digital platform to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A multifunctional online service management method based on a digital platform, the method comprising the following steps: step S1: obtaining network traffic data of all functions included in a single online service in the digital platform; step S2: constructing a function-network traffic coordinate system and a network traffic fluctuation curve of the online service at a single time node based on the network traffic data; step S3: constructing traffic peak function pairs and traffic valley function pairs based on the network traffic fluctuation curve; sorting them in sequence according to the time node order to construct a traffic peak function pair set and a traffic valley function pair set; step S4: recording the majority of the traffic peak function pair set as a popular function, and recording the majority of the traffic valley function pair set as a cold function; calculating the probability of the popular function appearing at the next time node, presetting a probability threshold, analyzing and performing maintenance management.

[0007] As a preferred solution of the multifunctional online service management method based on a digital platform described in the present invention, a network traffic data log library of a single online service in the digital platform in the historical working state is constructed, and the network traffic data log library records the network traffic data logs of all functions included in the single online service, and one function corresponds to one network traffic data log; the network traffic data log contains the network traffic data of the corresponding function at all time nodes in the historical working state.

[0008] Obtain the network traffic data log of the ith function in the ath online service in the digital platform, and record the network traffic data of the ith function in the ath online service at time node t as NT a，i (t).

[0009] As a preferred solution of the multifunctional online service management method based on a digital platform described in the present invention, based on network traffic data NT a，i (t), construct a function-network traffic coordinate system for the a-th online service at time node t, the horizontal axis of the function-network traffic coordinate system is all functions of the a-th online service arranged in sequence, and the vertical axis of the function-network traffic coordinate system is the network traffic data corresponding to all functions of the a-th online service arranged in sequence.

[0010] Obtain the coordinate points of the function and the network traffic data corresponding to the function in the function-network traffic coordinate system; obtain all the coordinate points, and connect them in sequence to form a fluctuation curve, and record the fluctuation curve as the network traffic fluctuation curve NFF of the a-th online service at time node t a (t).

[0011] As a preferred solution of the multifunctional online service management method based on a digital platform described in the present invention, the network traffic fluctuation curve NFF is obtained respectively. aThe functions and network traffic data corresponding to the peaks and troughs of (t) are expressed as a traffic peak function pair and recorded as [F a，i , NT a，i (t) max ], the function corresponding to the trough and the network traffic data are expressed as a traffic valley function pair, and recorded as [F a，j , NT a，j (t) min ], where F a，i represents the i-th function in the a-th online service corresponding to the peak, NT a，i (t) max Indicates the network traffic data corresponding to the peak, F a，j represents the jth function in the ath online service corresponding to the trough, NT a，j (t) min Indicates the network traffic data corresponding to the trough.

[0012] Obtain the traffic peak function pairs and traffic valley function pairs corresponding to the network traffic fluctuation curves at all time nodes, and sort them in sequence according to the time node order to construct the traffic peak function pair set and traffic valley function pair set, which are respectively denoted as PFF = {[F a，i , NT a，i (t) max ]|i∈[1,I],t∈[1,T]} and PVF={[F a，j , NT a，j (t) min ]|j∈[1,I],t∈[1,T]}, where I represents the total number of functions in the ath online service, and T represents all time nodes in the historical working status.

[0013] As a preferred solution of the multifunctional online service management method based on a digital platform described in the present invention, based on the flow peak function pair set PFF = {[F a，i , NT a，i (t) max ]|i∈[1,I],t∈[1,T]} and the flow valley function pair set PVF={[F a，j , NT a，j (t) min ]|j∈[1,I],t∈[1,T]}, obtain the mode of the traffic peak function pair set and the traffic valley function pair set at all time nodes, that is, the function with the most occurrences.

[0014] The majority of the traffic peak function pairs are recorded as popular functions, and the majority of the traffic valley function pairs are recorded as unpopular functions.

[0015] Calculate the probability of popular functions appearing at time node T+1. The calculation formula is as follows:

[0016]

[0017] Among them, P(PF a |PFF) represents the probability of the popular function appearing at time node T+1, PF a represents the popular function in the ath online service, P(PF a ∩PFF) represents the popular function PF a The probability of appearing in the traffic peak function pair set PFF, P(PFF) represents the probability of appearing in the traffic peak function pair set PFF.

[0018] Preset probability threshold, if the popular function PF a The probability of occurrence P(PF) at time node T+1 a |PFF) is greater than the probability threshold, then before time node T+1, remind the staff to check the hot function PF a Perform advance maintenance and optimize the unpopular functions.

[0019] Let a=a+1, and manage all online services on the digital platform.

[0020] It should be noted that popular functions represent the functions that are most often in the peak traffic state throughout the entire historical working state. These functions are the "hot spots" of online services and are crucial to the allocation and optimization of system resources. For example, if a function is the majority, then special attention should be paid to server resource allocation, bandwidth guarantee, etc. to ensure that it can run stably during high traffic, avoid service interruption or performance degradation due to insufficient resources, thereby affecting user experience and the normal development of business. From a business perspective, the majority function may be the most popular or the most critical part for business processes. The characteristics and user usage scenarios of these functions can be further analyzed to carry out targeted optimization and expansion, such as adding relevant functional modules, improving the user interface, etc., to improve user satisfaction and business value; unpopular functions reflect functions that are relatively infrequently used and in a low traffic state. This helps the operation team evaluate the value and necessity of these functions. If a function is the majority and has little impact on the core business process, it may be considered to be optimized or integrated to reduce maintenance costs and system complexity. For example, simplify its code, reduce database access, etc., or integrate it with other related functions to improve resource utilization efficiency; on the other hand, it may also indicate that the usage scenarios or user needs of certain functions may have changed. For example, if a function was not originally a valley mode, but recently became the mode, it may be necessary to further investigate user behavior and market dynamics to see whether the function needs to be repositioned or improved to adapt to the new business environment and user needs.

[0021] A multifunctional online service management system based on a digital platform, the system includes: a data acquisition module, a coordinate system and curve construction module, a set construction module and a probability calculation and maintenance management module.

[0022] The data acquisition module is used to acquire network traffic data of all functions included in a single online service in the digital platform.

[0023] The coordinate system and curve construction module: based on network traffic data, constructs the functions of online services at a single time node - the network traffic coordinate system and the network traffic fluctuation curve.

[0024] The set construction module: constructs traffic peak function pairs and traffic valley function pairs based on the network traffic fluctuation curve; sorts them in sequence according to the time node order to construct the traffic peak function pair set and the traffic valley function pair set.

[0025] The probability calculation and maintenance management module: records the majority of the traffic peak function pairs as popular functions, and records the majority of the traffic valley function pairs as unpopular functions; calculates the probability of the popular function appearing at the next time node, presets the probability threshold, analyzes and performs maintenance management.

[0026] Furthermore, the data acquisition module includes a data acquisition unit.

[0027] The data acquisition unit: constructs a network traffic data log library of a single online service in the digital platform when it is in a historical working state, wherein the network traffic data log library records the network traffic data logs of all functions included in the single online service, and one function corresponds to one network traffic data log; the network traffic data log contains the network traffic data of the corresponding function at all time nodes in the historical working state.

[0028] Furthermore, the coordinate system and curve construction module includes a coordinate system construction unit and a curve construction unit.

[0029] The coordinate system construction unit: constructs a function-network traffic coordinate system of a single online service at a single time node based on network traffic data, wherein the horizontal axis of the function-network traffic coordinate system is all functions of the single online service arranged in sequence, and the vertical axis of the function-network traffic coordinate system is the network traffic data corresponding to all functions of the single online service arranged in sequence.

[0030] The curve construction unit: obtains the coordinate points of the function and the network traffic data corresponding to the function in the function-network traffic coordinate system; obtains all the coordinate points and connects them in sequence to form a fluctuation curve, and records the fluctuation curve as the network traffic fluctuation curve of a single online service at a single time node.

[0031] Furthermore, the set construction module includes a set construction unit.

[0032] The set construction unit: respectively obtains the functions and network traffic data corresponding to the peaks and troughs of the network traffic fluctuation curve, expresses the functions and network traffic data corresponding to the peaks as traffic peak function pairs, and expresses the functions and network traffic data corresponding to the troughs as traffic valley function pairs; obtains the traffic peak function pairs and traffic valley function pairs corresponding to the network traffic fluctuation curves at all time nodes, and sorts them in sequence according to the time node order to construct traffic peak function pair sets and traffic valley function pair sets.

[0033] Furthermore, the probability calculation and maintenance management module includes a probability calculation unit and a maintenance management unit.

[0034] The probability calculation unit: based on the traffic peak function pair set and the traffic valley function pair set, obtains the mode of the traffic peak function pair set and the traffic valley function pair set at all time nodes, that is, the function that appears the most times; records the mode of the traffic peak function pair set as the popular function, and records the mode of the traffic valley function pair set as the unpopular function; calculates the probability of the popular function appearing at the next time node.

[0035] The maintenance management unit: presets a probability threshold. If the probability of occurrence of a popular function at the next time node is greater than the probability threshold, the staff is reminded to perform advance maintenance on the popular functions and optimize the unpopular functions before the next time node; iterates the online services and manages all online services on the digital platform.

[0036] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in a multifunctional online service management system and method based on a digital platform provided by the present invention, by acquiring all functional network traffic data of a single online service in the digital platform, a coordinate system and fluctuation curve of the function and network traffic are established, and the traffic distribution and fluctuation of the function are clearly displayed; the peaks and troughs of the traffic fluctuation curve are further extracted, traffic peak function pairs and valley function pairs are constructed, and a function set is formed by sorting time nodes, which provides accurate basic data for subsequent analysis; by counting the mode in the traffic peak function pair set and the valley function pair set, popular functions and unpopular functions are identified, and predictive maintenance management is performed in combination with the occurrence probability threshold, so that the system can optimize resource allocation in advance to ensure the stable operation of popular functions under high traffic, and at the same time optimize or integrate unpopular functions to improve the overall system efficiency and user experience; the present invention not only improves the stability and resource utilization of online services on the digital platform, but also can explore user behavior and demand changes through functional analysis, thereby further optimizing business processes and expanding service value. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0038] Figure 1 It is a schematic diagram of the steps of a multifunctional online service management method based on a digital platform of the present invention;

[0039] Figure 2 It is a structural schematic diagram of a multifunctional online service management system based on a digital platform of the present invention. DETAILED DESCRIPTION

[0040] 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.

[0041] See also Figure 1In the first embodiment of the present invention, a multifunctional online service management method based on a digital platform is provided, and the method comprises the following steps:

[0042] Step S1: Obtain network traffic data of all functions included in a single online service in the digital platform.

[0043] Specifically, a network traffic data log library of a single online service in a digital platform in a historical working state is constructed, wherein the network traffic data log library records the network traffic data logs of all functions included in the single online service, and one function corresponds to one network traffic data log; the network traffic data log contains the network traffic data of the corresponding function at all time nodes in the historical working state.

[0044] Further, the network traffic data log of the ith function in the ath online service in the digital platform is obtained, and the network traffic data of the ith function in the ath online service at time node t is recorded as NT a,i (t).

[0045] Step S2: Based on the network traffic data, construct the function of the online service at a single time node - the network traffic coordinate system and the network traffic fluctuation curve.

[0046] Specifically, based on network traffic data NT a,i (t), construct a function-network traffic coordinate system for the a-th online service at time node t, the horizontal axis of the function-network traffic coordinate system is all functions of the a-th online service arranged in sequence, and the vertical axis of the function-network traffic coordinate system is the network traffic data corresponding to all functions of the a-th online service arranged in sequence.

[0047] Further, the coordinate points of the function and the network traffic data corresponding to the function in the function-network traffic coordinate system are obtained; all the coordinate points are obtained and connected in sequence to form a fluctuation curve, and the fluctuation curve is recorded as the network traffic fluctuation curve NFF of the a-th online service at time node t a (t).

[0048] Step S3: Based on the network traffic fluctuation curve, construct traffic peak function pairs and traffic valley function pairs; sort them in order of time nodes to construct traffic peak function pair sets and traffic valley function pair sets.

[0049] Specifically, obtain the network traffic fluctuation curve NFF a The functions and network traffic data corresponding to the peaks and troughs of (t) are expressed as a traffic peak function pair and recorded as [F a，i , NT a，i (t)max ], the function corresponding to the trough and the network traffic data are expressed as a traffic valley function pair, and recorded as [F a，j , NT a，j (t) min ], where F a，i represents the i-th function in the a-th online service corresponding to the peak, NT a，i (t) max Indicates the network traffic data corresponding to the peak, F a，j represents the jth function in the ath online service corresponding to the trough, NT a，j (t) min Indicates the network traffic data corresponding to the trough.

[0050] Furthermore, the traffic peak function pairs and traffic valley function pairs corresponding to the network traffic fluctuation curves at all time nodes are obtained, and they are sorted in sequence according to the time node order to construct the traffic peak function pair set and the traffic valley function pair set, which are respectively denoted as PFF = {[F a，i , NT a，i (t) max ]|i∈[1,I],t∈[1,T]} and PVF={[F a，j , NT a，j (t) min ]|j∈[1,I],t∈[1,T]}, where I represents the total number of functions in the ath online service, and T represents all time nodes in the historical working status.

[0051] Step S4: record the majority of the traffic peak function pairs as hot functions, and record the majority of the traffic valley function pairs as unpopular functions; calculate the probability of the hot function appearing at the next time node, preset the probability threshold, analyze and perform maintenance management.

[0052] Specifically, based on the flow peak function set PFF = {[F a，i , NT a，i (t) max ]|i∈[1,I],t∈[1,T]} and the flow valley function pair set PVF={[F a，j , NT a，j (t) min ]|j∈[1,I],t∈[1,T]}, obtain the mode of the traffic peak function pair set and the traffic valley function pair set at all time nodes, that is, the function with the most occurrences;

[0053] The majority of the traffic peak function pairs are recorded as popular functions, and the majority of the traffic valley function pairs are recorded as unpopular functions;

[0054] Furthermore, the probability of the popular function appearing at time node T+1 is calculated using the following formula:

[0055]

[0056] Among them, P(PF a |PFF) represents the probability of the popular function appearing at time node T+1, PF a represents the popular function in the ath online service, P(PF a ∩PFF) represents the popular function PF a The probability of appearing in the flow peak function pair set PFF, P(PFF) represents the probability of appearing in the flow peak function pair set PFF;

[0057] Furthermore, a probability threshold is preset, if the popular function PF a The probability of occurrence P(PF) at time node T+1 a |PFF) is greater than the probability threshold, then before time node T+1, remind the staff to check the hot function PF a Perform advance maintenance and optimize the unpopular functions;

[0058] Let a=a+1, and manage all online services on the digital platform.

[0059] It should be noted that popular functions represent the functions that are most often in the peak traffic state throughout the entire historical working state. These functions are the "hot spots" of online services and are crucial to the allocation and optimization of system resources. For example, if a function is the majority, then special attention should be paid to server resource allocation, bandwidth guarantee, etc. to ensure that it can run stably under high traffic and avoid service interruption or performance degradation due to insufficient resources, thereby affecting user experience and the normal development of business. From a business perspective, the majority function may be the most popular or the most critical part for business processes. The characteristics and user usage scenarios of these functions can be further analyzed to carry out targeted optimization and expansion, such as adding relevant functional modules, improving the user interface, etc., to improve user satisfaction and business value; unpopular functions reflect functions that are relatively infrequently used and in a low traffic state. This helps the operation team evaluate the value and necessity of these functions. If a function is the majority and has little impact on the core business process, it may be considered to be optimized or integrated to reduce maintenance costs and system complexity. For example, simplify its code, reduce database access, etc., or integrate it with other related functions to improve resource utilization efficiency; on the other hand, it may also indicate that the usage scenarios or user needs of certain functions may have changed. For example, if a function was not originally a valley mode, but recently became the mode, it may be necessary to further investigate user behavior and market dynamics to see whether the function needs to be repositioned or improved to adapt to the new business environment and user needs.

[0060] Specifically, for the microfinance digital platforms on the market, a digital microfinance academy can be created based on artificial intelligence and digital human technology. This digital microfinance academy can provide microfinance institutions, microenterprises and related practitioners with a digital platform that integrates learning functions, communication functions, recruitment functions and innovation functions, etc.; this digital platform integrates online courses, lectures and training to help microfinance practitioners and microentrepreneurs improve relevant knowledge and skills, promote knowledge dissemination and talent training in the field of microfinance, promote cooperation between microfinance institutions, microenterprises, government regulatory departments and educational institutions, build a microfinance industry ecosystem, and jointly promote the development of the microfinance field.

[0061] On the other hand, the digital platform can be tested and optimized through the inventive content of the present invention. Specifically, a network traffic data log library of a single online service in the digital platform in the historical working state is constructed. For example, for the learning function, the network traffic data at each time node is recorded to form a corresponding network traffic data log. The same is true for other functions.

[0062] Next, based on these network traffic data, a function-network traffic coordinate system is constructed for the digital platform of the Small and Micro Finance College at a specific time node. The horizontal axis lists all functions, and the vertical axis corresponds to the network traffic data of the corresponding functions, and then the coordinate points are connected to form a network traffic fluctuation curve.

[0063] Then, the traffic peak function pairs and traffic valley function pairs are determined from the fluctuation curve, and the corresponding sets are constructed in the order of time nodes; for example, if the recruitment function is at the traffic peak at multiple time nodes, it may become the majority of the traffic peak function pairs, that is, the popular function; and some relatively less used functions may become unpopular functions.

[0064] Finally, for popular functions (such as learning functions, which are the most popular and often at traffic peaks), calculate their probability of appearing at the next time node and compare them with preset thresholds; if the threshold is exceeded, maintain popular functions in advance and optimize unpopular functions; popular learning functions are related to knowledge dissemination and talent training, and their stable operation must be guaranteed; unpopular functions can be evaluated and integrated to reduce costs, jointly promote the digital development of the microfinance field, and build a good industrial ecosystem.

[0065] See also Figure 2 In the second embodiment of the present invention, a multifunctional online service management system based on a digital platform is provided, the system comprising: a data acquisition module, a coordinate system and curve construction module, a set construction module and a probability calculation and maintenance management module.

[0066] The data acquisition module is used to acquire network traffic data of all functions included in a single online service in the digital platform.

[0067] The coordinate system and curve construction module: based on network traffic data, constructs the functions of online services at a single time node - the network traffic coordinate system and the network traffic fluctuation curve.

[0068] The set construction module: constructs traffic peak function pairs and traffic valley function pairs based on the network traffic fluctuation curve; sorts them in sequence according to the time node order to construct the traffic peak function pair set and the traffic valley function pair set.

[0069] The probability calculation and maintenance management module: records the majority of the traffic peak function pairs as popular functions, and records the majority of the traffic valley function pairs as unpopular functions; calculates the probability of the popular function appearing at the next time node, presets the probability threshold, analyzes and performs maintenance management.

[0070] Furthermore, the data acquisition module includes a data acquisition unit.

[0071] The data acquisition unit: constructs a network traffic data log library of a single online service in the digital platform when it is in a historical working state, wherein the network traffic data log library records the network traffic data logs of all functions included in the single online service, and one function corresponds to one network traffic data log; the network traffic data log contains the network traffic data of the corresponding function at all time nodes in the historical working state.

[0072] Furthermore, the coordinate system and curve construction module includes a coordinate system construction unit and a curve construction unit.

[0073] The coordinate system construction unit: constructs a function-network traffic coordinate system of a single online service at a single time node based on network traffic data, wherein the horizontal axis of the function-network traffic coordinate system is all functions of the single online service arranged in sequence, and the vertical axis of the function-network traffic coordinate system is the network traffic data corresponding to all functions of the single online service arranged in sequence.

[0074] The curve construction unit: obtains the coordinate points of the function and the network traffic data corresponding to the function in the function-network traffic coordinate system; obtains all the coordinate points and connects them in sequence to form a fluctuation curve, and records the fluctuation curve as the network traffic fluctuation curve of a single online service at a single time node.

[0075] Furthermore, the set construction module includes a set construction unit.

[0076] The set construction unit: respectively obtains the functions and network traffic data corresponding to the peaks and troughs of the network traffic fluctuation curve, expresses the functions and network traffic data corresponding to the peaks as traffic peak function pairs, and expresses the functions and network traffic data corresponding to the troughs as traffic valley function pairs; obtains the traffic peak function pairs and traffic valley function pairs corresponding to the network traffic fluctuation curves at all time nodes, and sorts them in sequence according to the time node order to construct traffic peak function pair sets and traffic valley function pair sets.

[0077] Furthermore, the probability calculation and maintenance management module includes a probability calculation unit and a maintenance management unit.

[0078] The probability calculation unit: based on the traffic peak function pair set and the traffic valley function pair set, obtains the mode of the traffic peak function pair set and the traffic valley function pair set at all time nodes, that is, the function that appears the most times; records the mode of the traffic peak function pair set as the popular function, and records the mode of the traffic valley function pair set as the unpopular function; calculates the probability of the popular function appearing at the next time node.

[0079] The maintenance management unit: presets a probability threshold. If the probability of occurrence of a popular function at the next time node is greater than the probability threshold, the staff is reminded to perform advance maintenance on the popular functions and optimize the unpopular functions before the next time node; iterates the online services and manages all online services on the digital platform.

[0080] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0081] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A multifunctional online service management method based on a digital platform, characterized in that: The method comprises the following steps: Step S1: Obtain network traffic data of all functions included in a single online service in the digital platform; Step S2: Based on the network traffic data, construct the function of the online service at a single time node - the network traffic coordinate system and the network traffic fluctuation curve; Step S3: Based on the network traffic fluctuation curve, construct traffic peak function pairs and traffic valley function pairs; sort them in order of time nodes to construct traffic peak function pair sets and traffic valley function pair sets; Step S4: record the majority of the traffic peak function pairs as hot functions, and record the majority of the traffic valley function pairs as unpopular functions; calculate the probability of the hot function appearing at the next time node, preset the probability threshold, analyze and perform maintenance management.

2. A multifunctional online service management method based on a digital platform according to claim 1, characterized in that: The specific implementation process of step S1 includes: Construct a network traffic data log library of a single online service in a digital platform in a historical working state, wherein the network traffic data log library records network traffic data logs of all functions included in the single online service, and one function corresponds to one network traffic data log; the network traffic data log contains network traffic data of the corresponding function at all time nodes in the historical working state; Obtain the network traffic data log of the ith function in the ath online service in the digital platform, and record the network traffic data of the ith function in the ath online service at time node t as NT a,i (t).

3. A multifunctional online service management method based on a digital platform according to claim 2, characterized in that: The specific implementation process of step S2 includes: Based on network traffic data NT a,i (t), constructing a function-network flow coordinate system of the a-th online service at time node t, wherein the horizontal axis of the function-network flow coordinate system is all functions of the a-th online service arranged in sequence, and the vertical axis of the function-network flow coordinate system is the network flow data corresponding to all functions of the a-th online service arranged in sequence; Obtain the coordinate points of the function and the network traffic data corresponding to the function in the function-network traffic coordinate system; obtain all the coordinate points and connect them in sequence to form a fluctuation curve, and record the fluctuation curve as the network traffic fluctuation curve NFF of the a-th online service at time node t a (t).

4. A multifunctional online service management method based on a digital platform according to claim 3, characterized in that: The specific implementation process of step S3 includes: Get the network traffic fluctuation curve NFF respectively a The functions and network traffic data corresponding to the peaks and troughs of (t) are expressed as a traffic peak function pair and recorded as [F a,i ,NT a,i (t) max ], the function corresponding to the trough and the network traffic data are expressed as a traffic valley function pair, and recorded as [F a,j ,NT a,j (t) min ], where F a,i represents the i-th function in the a-th online service corresponding to the peak, NT a,i (t) max Indicates the network traffic data corresponding to the peak, F a,j represents the jth function in the ath online service corresponding to the trough, NT a,j (t) min Indicates network traffic data corresponding to the trough; Obtain the traffic peak function pairs and traffic valley function pairs corresponding to the network traffic fluctuation curves at all time nodes, and sort them in sequence according to the time node order to construct the traffic peak function pair set and traffic valley function pair set, which are respectively denoted as PFF = {[F a,i ,NT a,i (t) max ]|i∈[1,I],t∈[1,T]} and PVF={[F a,j ,NT a,j (t) min ]|j∈[1,I],t∈[1,T]}, where I represents the total number of functions in the ath online service, and T represents all time nodes in the historical working status.

5. A multifunctional online service management method based on a digital platform according to claim 4, characterized in that: The specific implementation process of step S4 includes: Based on the flow peak function set PFF = {[F a,i ,NT a,i (t) max ]|i∈[1,I],t∈[1,T]} and the flow valley function pair set PVF={[F a,j ,NT a,j (t) min ]|j∈[1,I],t∈[1,T]}, obtain the mode of the traffic peak function pair set and the traffic valley function pair set at all time nodes, that is, the function with the most occurrences; The majority of the traffic peak function pairs are recorded as popular functions, and the majority of the traffic valley function pairs are recorded as unpopular functions; Calculate the probability of popular functions appearing at time node T+1. The calculation formula is as follows: Among them, P(PF a |PFF) represents the probability of the popular function appearing at time node T+1, PF a represents the popular function in the ath online service, P(PF a ∩PFF) represents the popular function PF a The probability of appearing in the flow peak function pair set PFF, P(PFF) represents the probability of appearing in the flow peak function pair set PFF; Preset probability threshold, if the popular function PF a The probability of occurrence P(PF) at time node T+1 a |PFF) is greater than the probability threshold, then before time node T+1, remind the staff to check the hot function PF a Perform advance maintenance and optimize the unpopular functions; Let a=a+1, and manage all online services on the digital platform.

6. A multifunctional online service management system based on a digital platform, executing a multifunctional online service management method based on a digital platform as claimed in any one of claims 1 to 5, characterized in that: The system comprises: a data acquisition module, a coordinate system and curve construction module, a set construction module and a probability calculation and maintenance management module; The data acquisition module is used to acquire network traffic data of all functions included in a single online service in the digital platform; The coordinate system and curve construction module: constructs the network traffic coordinate system and network traffic fluctuation curve of the online service at a single time node based on the network traffic data; The set construction module: constructs traffic peak function pairs and traffic valley function pairs based on the network traffic fluctuation curve; sorts them in order of time nodes to construct traffic peak function pair sets and traffic valley function pair sets; The probability calculation and maintenance management module: records the majority of the traffic peak function pairs as popular functions, and records the majority of the traffic valley function pairs as unpopular functions; calculates the probability of the popular function appearing at the next time node, presets the probability threshold, analyzes and performs maintenance management.

7. A multifunctional online service management system based on a digital platform according to claim 6, characterized in that: The data acquisition module includes a data acquisition unit; The data acquisition unit: constructs a network traffic data log library of a single online service in the digital platform when it is in a historical working state, wherein the network traffic data log library records the network traffic data logs of all functions included in the single online service, and one function corresponds to one network traffic data log; the network traffic data log contains the network traffic data of the corresponding function at all time nodes in the historical working state.

8. A multifunctional online service management system based on a digital platform according to claim 7, characterized in that: The coordinate system and curve construction module includes a coordinate system construction unit and a curve construction unit; The coordinate system construction unit: constructs a function-network flow coordinate system of a single online service at a single time node based on the network flow data, wherein the horizontal axis of the function-network flow coordinate system is all functions of the single online service arranged in sequence, and the vertical axis of the function-network flow coordinate system is the network flow data corresponding to all functions of the single online service arranged in sequence; The curve construction unit: obtains the coordinate points of the functions and the network flow data corresponding to the functions in the function-network flow coordinate system; All coordinate points are obtained and connected in sequence to form a fluctuation curve, and the fluctuation curve is recorded as a network traffic fluctuation curve of a single online service at a single time node.

9. A multifunctional online service management system based on a digital platform according to claim 8, characterized in that: The set construction module includes a set construction unit; The set construction unit: respectively obtains the functions and network traffic data corresponding to the peaks and troughs of the network traffic fluctuation curve, expresses the functions and network traffic data corresponding to the peaks as traffic peak function pairs, and expresses the functions and network traffic data corresponding to the troughs as traffic valley function pairs; obtains the traffic peak function pairs and traffic valley function pairs corresponding to the network traffic fluctuation curves at all time nodes, and sorts them in sequence according to the time node order to construct traffic peak function pair sets and traffic valley function pair sets.

10. A multifunctional online service management system based on a digital platform according to claim 9, characterized in that: The probability calculation and maintenance management module includes a probability calculation unit and a maintenance management unit; The probability calculation unit: based on the traffic peak function pair set and the traffic valley function pair set, obtains the mode of the traffic peak function pair set and the traffic valley function pair set at all time nodes, that is, the function with the most occurrences; records the mode of the traffic peak function pair set as a popular function, and records the mode of the traffic valley function pair set as a cold function; calculates the probability of the popular function appearing at the next time node; The maintenance management unit: presets a probability threshold. If the probability of occurrence of a popular function at the next time node is greater than the probability threshold, the staff is reminded to perform advance maintenance on the popular functions and optimize the unpopular functions before the next time node; iterates the online services and manages all online services on the digital platform.

Images