Network point determination method and apparatus, computer device, and storage medium

Abstract

The application relates to a network access point determination method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining service configuration data of a target user, determining evaluation weights of each evaluation index corresponding to a network access point based on the service configuration data; for each network access point in a target network, determining a target evaluation score of the network access point based on the evaluation weights of the evaluation indexes and index values of each evaluation index corresponding to the network access point; and determining a target network access point corresponding to the target user by taking a network access point satisfying a preset network access point screening condition as the target network access point. According to the method, the evaluation weights of each evaluation index corresponding to the network access point can be dynamically adjusted based on the service configuration data of the user, so that a more accurate network access point selection result is obtained, and the accuracy of determining the network access point is improved.

Description

Technical Field

[0001] This application relates to the field of network technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for determining network access points. Background Technology

[0002] To ensure all network and security functions are available anywhere, and to enable data processing and security functions to operate at the edge, a Secure Access Service Edge (SASE) network has emerged. This SASE network can meet the dynamic needs of cloud and mobile services. User equipment can access the SASE network through a Point-of-Presence (POP).

[0003] In related technologies, the POPs that can currently provide network access services to user equipment are determined based on the resource load of each POP in the SASE network, the location information of the user equipment, and the weights of the corresponding evaluation indicators. However, when facing multiple services, the weights of the evaluation indicators in this determination process are fixed, resulting in poor accuracy of the determined POPs. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining network entry points that can dynamically change the weights of the evaluation indicators, in order to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for determining network access points. The method includes:

[0006] Obtain the business configuration data of the target user, and determine the evaluation weight of each evaluation indicator corresponding to the entry point based on the business configuration data;

[0007] For each entry point in the target network, the target evaluation score of the entry point is determined based on the evaluation weight of each of the evaluation indicators and the indicator value of each evaluation indicator corresponding to the entry point.

[0008] The entry points that meet the preset entry point screening criteria in the target evaluation score are determined as the target entry points for the target user.

[0009] In one embodiment, the service configuration data includes ranking data of evaluation indicators corresponding to the target user; the step of obtaining the service configuration data of the target user and determining the evaluation weight of each evaluation indicator corresponding to the entry point based on the service configuration data includes:

[0010] Based on the ranking data of the evaluation indicators corresponding to the target users, the importance sequence of each evaluation indicator corresponding to the entry point is determined.

[0011] The evaluation weights corresponding to each evaluation index are determined based on the importance sequence and the preset weight allocation algorithm.

[0012] In one embodiment, the service configuration data includes the target service type corresponding to the target user; the step of obtaining the service configuration data of the target user and determining the evaluation weight of each evaluation indicator corresponding to the entry point based on the service configuration data includes:

[0013] Based on the mapping relationship between business type and the evaluation weights corresponding to each evaluation indicator, the evaluation weights of each evaluation indicator corresponding to the target business type are determined.

[0014] In one embodiment, before the step of determining the evaluation weights based on the evaluation indicators and the indicator values ​​of the evaluation indicators corresponding to the network entry point, the method further includes:

[0015] Based on the service type corresponding to the service configuration data, obtain the network access point selection data corresponding to the service type; wherein, the network access point selection data includes the number of times each network access point is selected;

[0016] The selection probability of each entry point is determined based on the number of times each entry point is selected.

[0017] In one embodiment, determining the target evaluation score of the network entry point based on the evaluation weights of each of the evaluation indicators and the indicator values ​​of each evaluation indicator corresponding to the network entry point includes:

[0018] The initial evaluation score of the network entry point is obtained by weighting the evaluation weights of each of the evaluation indicators and the indicator values ​​of each evaluation indicator corresponding to the network entry point.

[0019] Based on the selection probability of the entry point, the initial evaluation score of the entry point is updated to obtain the target evaluation score of the entry point.

[0020] In one embodiment, determining the entry point whose target evaluation score meets the preset entry point screening criteria as the target entry point for the target user includes:

[0021] Among the target evaluation scores of each entry point, the entry point with the highest target evaluation score is determined as the target entry point corresponding to the target user.

[0022] Secondly, this application also provides a device for determining network access points. The device includes:

[0023] The weight determination module is used to obtain the business configuration data of the target user and determine the evaluation weight of each evaluation indicator corresponding to the entry point based on the business configuration data.

[0024] The score determination module is used to determine the target evaluation score of each entry point in the target network based on the evaluation weight of each evaluation indicator and the indicator value of each evaluation indicator corresponding to the entry point.

[0025] The entry point determination module is used to determine the entry points that meet the preset entry point screening conditions as the target entry points for the target user.

[0026] In one embodiment, the business configuration data includes ranking data of evaluation indicators corresponding to the target user; the weight determination module is specifically used for:

[0027] Based on the ranking data of the evaluation indicators corresponding to the target users, the importance sequence of each evaluation indicator corresponding to the entry point is determined; according to the importance sequence and the preset weight allocation algorithm, the evaluation weight corresponding to each evaluation indicator is determined.

[0028] In one embodiment, the service configuration data includes the target service type corresponding to the target user; the weight determination module is further configured to:

[0029] Based on the mapping relationship between business type and the evaluation weights corresponding to each evaluation indicator, the evaluation weights of each evaluation indicator corresponding to the target business type are determined.

[0030] In one embodiment, the device further includes:

[0031] The data acquisition module is used to acquire network access point selection data corresponding to the service type based on the service type corresponding to the service configuration data; wherein, the network access point selection data includes the number of times each network access point is selected;

[0032] The probability determination module is used to determine the selection probability of each entry point based on the number of times each entry point is selected.

[0033] In one embodiment, the score determination module is specifically used for:

[0034] The initial evaluation score of the entry point is obtained by weighting the evaluation weights of each evaluation indicator and the indicator values ​​of each evaluation indicator corresponding to the entry point; the initial evaluation score of the entry point is updated based on the selection probability of the entry point to obtain the target evaluation score of the entry point.

[0035] In one embodiment, the entry point determination module is specifically used for:

[0036] Among the target evaluation scores of each entry point, the entry point with the highest target evaluation score is determined as the target entry point corresponding to the target user.

[0037] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in the first aspect.

[0038] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0039] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect.

[0040] The aforementioned method, apparatus, computer equipment, storage medium, and computer program product for determining network access points acquire the service configuration data of the target user, determine the evaluation weights of each evaluation indicator corresponding to the network access point based on the service configuration data; for each network access point in the target network, determine the target evaluation score of the network access point based on the evaluation weights of each evaluation indicator and the indicator values ​​of each evaluation indicator corresponding to the network access point; and determine the network access points whose target evaluation scores meet the preset network access point screening conditions as the target network access points corresponding to the target user.

[0041] It can be seen that by obtaining the business configuration data of the target user, the specific needs of the business can be determined, thereby dynamically adjusting the evaluation weights of each evaluation indicator for the business. This allows for the determination of different evaluation weights when facing different businesses, and the evaluation score corresponding to each entry point can be obtained based on the evaluation weights. This evaluation score can more accurately reflect the evaluation indicators emphasized by different businesses, thereby obtaining more accurate entry point selection results and ultimately improving the accuracy of determining entry points. Attached Figure Description

[0042] Figure 1 This is an application environment diagram of the network entry point determination method in one embodiment;

[0043] Figure 2 This is a flowchart illustrating a method for determining the entry point in one embodiment;

[0044] Figure 3 This is a flowchart illustrating the steps for determining the evaluation weights of each evaluation indicator at a network entry point in one embodiment.

[0045] Figure 4 This is a flowchart illustrating the method for determining the entry point in another embodiment;

[0046] Figure 5 This is a structural block diagram of an entry point determination device in one embodiment;

[0047] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0049] The network access point determination method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. Users send service configuration data to server 104 through terminal 102, and can also receive specific target access points from server 104 through terminal 102. A data storage system stores the data that server 104 needs to process, including the indicator values ​​of various evaluation metrics corresponding to each access point. The data storage system can be integrated on server 104, or it can be located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers. This application environment may also include a SASE network, which includes at least multiple access points. The user's terminal can access the SASE network through these access points.

[0050] In one embodiment, such as Figure 2 As shown, a method for determining the entry point is provided, which is applied to... Figure 1 Taking server 104 as an example, the following steps are included:

[0051] S202, obtain the service configuration data of the target user, and determine the evaluation weight of each evaluation indicator corresponding to the entry point based on the service configuration data.

[0052] In this system, the target user can be any user with network access needs, such as a user sending a network access request to the server. The target user's service configuration data represents the configuration information of the service corresponding to that user, which can represent the user's service requirements or the user's emphasis on each evaluation metric. The access point can be an access point within the target network, which can be a SASE network with multiple independent access points. Users can access the SASE network through these access points. Evaluation metrics are used to calculate the evaluation score of each access point configured in the SASE network. This score represents the priority for the target user to access the SASE network through that access point. Evaluation metrics can include one or more, and the evaluation weight is used to measure the importance of each metric. For example, the evaluation weight of each metric can be determined based on the target user's corresponding business scenario. Furthermore, for multiple access points for the same user, the evaluation weights for each metric at each access point can be the same. In one example, the higher the evaluation score of an access point, the higher the priority the server can determine for recommending that access point to the user.

[0053] Regarding business configuration data, it should be understood that since different target users have different business needs, users attach different levels of importance to the evaluation indicators of the network access point. The server can determine the user's level of importance to each evaluation indicator based on the business configuration data received from the user, and determine the corresponding evaluation weight of each evaluation indicator based on the user's level of importance to each evaluation indicator.

[0054] For example, if user A prioritizes resource load metrics, user B prioritizes link network performance metrics, and user C prioritizes distance metrics, then the server, based on user A's business configuration data, will assign a higher evaluation weight to the resource load metric when calculating the evaluation score. Similarly, since user B's link network performance metrics will have a higher evaluation weight, the server will assign a higher score to the resource load metric when calculating the evaluation score. Likewise, user C's distance metrics will have a higher evaluation weight, resulting in a higher score for the distance metric when calculating the evaluation score.

[0055] Specifically, when using the SASE network, users need to select a Point of Presence (POP) within the SASE network, also known as the access point, for network access. It should be understood that when a user needs to access the SASE network, they can generate an access request and send it to the server. Based on the received access request, the server can obtain the target user's service configuration data carried in the request. Based on this, the server can determine the evaluation weights of various evaluation indicators for the access point corresponding to the target user, based on the service configuration information of that target user.

[0056] In one example, there are multiple evaluation metrics for each entry point in the SASE network. The server can determine the evaluation weights of each metric based on the service configuration data and then calculate the overall evaluation score for each entry point in the SASE network. Evaluation metrics for entry points can include resource load metrics, link network performance metrics, and distance metrics. Resource load metrics can include information such as CPU utilization, memory utilization, storage utilization, and bandwidth utilization. Link network performance metrics can include information such as packet loss rate, latency, and jitter for each link. Distance metrics can be calculated based on the geographical location of the user terminal and the geographical location of the entry point. For example, the evaluation metrics for an entry point could be CPU utilization, memory utilization, latency and packet loss rate of the first link, latency and packet loss rate of the second link, and distance, etc.

[0057] S204, for each entry point in the target network, based on the evaluation weights of each of the evaluation indicators and the indicator values ​​of each evaluation indicator corresponding to the entry point, determine the target evaluation score of the entry point.

[0058] Among them, the indicator values ​​of each evaluation indicator corresponding to the entry point can be the numerical values ​​of each evaluation indicator corresponding to the entry point. For example, the evaluation indicator of the entry point can be the storage utilization rate, and the corresponding indicator value can be the specific value of the storage utilization rate. The target evaluation score can be determined based on the indicator values ​​of each evaluation indicator of the entry point and the evaluation weight of each evaluation indicator.

[0059] Specifically, each entry point in the network has multiple evaluation indicators, and each indicator has a corresponding evaluation weight. Thus, the server can iterate through each entry point in the target network and calculate the target evaluation score for each entry point. The specific process for determining the target evaluation score for each entry point in the target network can be as follows: the server obtains the evaluation score for each evaluation indicator based on the determined indicator values ​​and evaluation weights for that entry point; the server can then calculate the target evaluation score for that entry point based on the calculated evaluation scores for each indicator.

[0060] Optionally, the target evaluation score for other entry points in the target network is determined through a similar calculation process, which will not be elaborated here. Based on this, the server can determine the target evaluation score for each entry point in the target network, which is convenient for use in subsequent steps.

[0061] Optionally, as an embodiment, the indicator values ​​of each evaluation indicator corresponding to the network access point are indicator values ​​within a preset time range stored in the server. The preset time range can be a time range configured based on the actual application scenario, such as a time range of one month from now. This application embodiment does not specifically limit the specific values ​​of the preset time range, and those skilled in the art can determine them specifically based on the actual application scenario.

[0062] S206, the entry points whose target evaluation scores meet the preset entry point screening conditions are determined as the target entry points corresponding to the target users.

[0063] Specifically, after determining the target evaluation score for each access point, the server obtains the target evaluation scores for all access points in the target network. Using preset access point filtering criteria, the server selects access points that meet the preset criteria from all access points in the target network and designates them as the target access points for the target user. Furthermore, the server can output the determined target access points for the target user to the target user's terminal. Based on this, the target user can select the access point to access the SASE network through their terminal.

[0064] Optionally, the entry point screening criteria can be based on limiting a preset range of evaluation scores, selecting entry points whose evaluation scores fall within the preset range as determined entry points. The number of entry points can be one or more, and this embodiment does not impose a specific limitation. Alternatively, the entry point screening criteria can be based on sorting the entry points by evaluation scores from highest to lowest, and selecting the top-ranked entry points.

[0065] In the above-mentioned method for determining entry points, by acquiring the business configuration data of the target user, the specific needs of the business can be determined. This allows for dynamic adjustment of the evaluation weights corresponding to each evaluation indicator for the business, enabling the determination of different evaluation weights when facing different businesses. Based on the evaluation weights, an evaluation score is obtained for each entry point. This evaluation score can more accurately reflect the evaluation indicators emphasized by different businesses, thereby obtaining a more accurate selection result for entry points and ultimately improving the accuracy of determining entry points.

[0066] In one embodiment, the step of obtaining the service configuration data, which includes ranking data of evaluation indicators corresponding to the target user, and determining the evaluation weights of each evaluation indicator corresponding to the entry point based on the service configuration data, includes:

[0067] Based on the ranking data of the evaluation indicators corresponding to the target users, the importance sequence of each evaluation indicator corresponding to the entry point is determined.

[0068] The evaluation weights corresponding to each evaluation index are determined based on the importance sequence and the preset weight allocation algorithm.

[0069] The business configuration data can be the ranking data of evaluation indicators corresponding to the target user. The ranking data of evaluation indicators is the sorted sequence after the user sorts all the evaluation indicators of the network entry point by a custom or preset weight allocation algorithm. The importance sequence includes the evaluation indicators arranged in descending order of importance; the importance sequence can also include data pairs, where the data pair is the evaluation indicator and the corresponding importance of the evaluation indicator. The data pairs contained in the importance sequence can be arranged in descending order of importance.

[0070] It should be understood that the ranking data of evaluation indicators for the target user can be the data showing the relative importance of each evaluation indicator configured by the user. Based on the ranking data of evaluation indicators for the target user, the server can obtain an importance sequence and assign different evaluation weights to each evaluation indicator according to the order of the importance sequence.

[0071] In one example, the terminal can assign evaluation weights from high to low to each rating indicator contained in the importance sequence, in descending order of importance.

[0072] In this embodiment, by assigning higher weights to evaluation indicators with higher importance, the user’s emphasis on the evaluation indicators required for the business is reflected. The more important the evaluation indicator, the more evaluation score it can get, which is reflected in the final evaluation score of the network entry point, thus achieving the effect of accurately determining the evaluation score.

[0073] Alternatively, as an example, such as Figure 3 As shown, before connecting to the network access point, users can sort the importance of each evaluation indicator. The control center then uses an algorithm to assign weights to each evaluation indicator based on the sorting.

[0074] The user initiates a request to connect to the Point of Presence (POP). After the user sends this request to the control center, the user needs to assign corresponding weights to multiple evaluation metrics for the POP. At this point, the user will rank the various evaluation metrics by importance and input the ranking results as business configuration data into the control center. The control center then assigns corresponding weights to the multiple evaluation metrics based on their importance ranking. In one example, the control center can be a server.

[0075] In this embodiment, the importance sequence of evaluation indicators provides a basis for determining evaluation weights, which can more accurately determine evaluation weights according to the needs of user business, thereby improving the accuracy of evaluation scores.

[0076] In one embodiment, the step of obtaining the service configuration data, which includes the target service type corresponding to the target user, and determining the evaluation weights of each evaluation indicator corresponding to the entry point based on the service configuration data, includes:

[0077] Based on the mapping relationship between business type and the evaluation weights corresponding to each evaluation indicator, the evaluation weights of each evaluation indicator corresponding to the target business type are determined.

[0078] The business configuration data can be the target business type for the target user. The server can pre-configure corresponding evaluation weights for each business type based on actual application scenarios; that is, for each business type, the server can pre-configure the evaluation weights for each corresponding evaluation indicator. In other words, the mapping relationship between business types and the evaluation weights corresponding to each evaluation indicator includes multiple business types and the evaluation weights corresponding to each evaluation indicator for each business type.

[0079] Specifically, after determining the target user's target business type based on business configuration data, the server can query the mapping relationship between the business type and the corresponding evaluation weights of each evaluation indicator to obtain the evaluation weights of each evaluation indicator corresponding to the target business type.

[0080] The evaluation weights of each evaluation indicator can be different for each business type. For example, when the target user's business type is live streaming, multiple evaluation indicators of the network access point are bound to this type. The server can determine that the evaluation weight of the link network performance indicator is 0.5, the evaluation weight of the resource load indicator is 0.3, and the evaluation weight of the distance indicator is 0.1, etc. When other target users' business types are also live streaming, the evaluation weights of the above evaluation indicators remain unchanged.

[0081] In this embodiment, the evaluation weight corresponding to each business type is obtained by mapping the business type and the evaluation weight corresponding to each evaluation indicator, thereby improving the accuracy of allocating evaluation weights.

[0082] In one embodiment, the specific implementation process prior to the step of basing the evaluation weights of each of the evaluation indicators and the indicator values ​​of each evaluation indicator corresponding to the entry point further includes:

[0083] Based on the service type corresponding to the service configuration data, obtain the network access point selection data corresponding to the service type;

[0084] The selection probability of each entry point is determined based on the number of times each entry point is selected.

[0085] The network access point selection data includes the number of times each network access point is selected; the network access point selection data corresponding to the service type is the number of times each network access point in the SASE network is selected by the terminal to access the SASE network within a preset time period under the service type, and the selection probability is the probability value of the network access point being selected based on the number of times each network access point is selected.

[0086] Regarding the entry point selection data, it should be understood that the server can use the selection data of historical users when determining the entry point as reference data to provide data support for the target user to determine the entry point. On this basis, the server can use the historical entry point selection data of the target user with the same business type as the target user as a variable to adjust the evaluation score, and ultimately provide a reference for subsequent target users with the same business type.

[0087] Specifically, the server can determine the service type of the target user based on the target user's service configuration data, and query the server's local storage database to find the number of times each entry point in the SASE network under that service type has been selected. Based on the obtained number of times each entry point in the SASE network under that service type has been selected, the server can obtain the selection probability corresponding to each entry point through a preset probability allocation algorithm.

[0088] In one example, the entry point selection data under a certain service type can be the number of times each entry point is selected. For instance, when the service type is live streaming, the entry point selection data is the data of historical user selections of entry points when performing live streaming services. For example, entry point A might be selected 15 times, entry point B 5 times, and entry point C 0 times. Based on the number of selections, the selection probability of each entry point can be determined. In this case, the selection probability of entry point A is 75%, the selection probability of entry point B is 25%, and the selection probability of entry point C is 0%.

[0089] In this embodiment, by obtaining the selection data of each entry point corresponding to the target business type, the selection probability can be obtained, thereby providing a new reference for determining the evaluation score and improving the accuracy of determining the evaluation score.

[0090] In one embodiment, the specific implementation process of the step of determining the target evaluation score of the entry point based on the evaluation weights of each of the evaluation indicators and the indicator values ​​of each evaluation indicator corresponding to the entry point includes:

[0091] The initial evaluation score of the network entry point is obtained by weighting the evaluation weights of each of the evaluation indicators and the indicator values ​​of each evaluation indicator corresponding to the network entry point.

[0092] Based on the selection probability of the entry point, the initial evaluation score of the entry point is updated to obtain the target evaluation score of the entry point.

[0093] The initial evaluation score can be calculated by the server using the weighted average of the evaluation indicators and their values. For example, for each evaluation indicator, the server multiplies the evaluation weight and value, and uses the product as the evaluation score for that indicator. After determining the evaluation scores for all indicators, the server can sum these scores to determine the initial evaluation score for that entry point. The target evaluation score is determined after the server has calculated the initial evaluation score, using the selection probability as an adjustment factor. Based on this, the server can adjust the initial evaluation score of each entry point according to its selection probability, resulting in the adjusted initial evaluation score, i.e., the target evaluation score.

[0094] Specifically, the server calculates a single evaluation score for each evaluation indicator based on its evaluation weight and indicator value. After calculating the evaluation scores for all evaluation indicators, the server sums these scores to obtain the initial evaluation score for the entry point. Then, using the selection probability of the entry point as an evaluation parameter, the server multiplies this selection probability by the initial evaluation score and determines the final target evaluation score as the product.

[0095] Optionally, the values ​​of each evaluation indicator can be specific scores mapped from a preset range of specific indicator values, and these scores can be used as new indicator values. For example, the server sets the specific scores to 0 to 100. When the CPU utilization rate is 80%, the specific score corresponding to the CPU utilization rate is 80. Or, when the average network latency is 100ms, the specific score corresponding to the average network latency is 60. In this case, the indicator value of CPU utilization rate changes from 80% to 80, and the indicator value of average network latency changes from 100ms to 60, thereby eliminating units and unifying the score range.

[0096] It is understandable that different evaluation indicators have different values, which may be due to different units or data types. Therefore, processing them all into specific numerical scores can enable unified calculation and improve computational efficiency.

[0097] In this embodiment, the initial evaluation score is obtained by weighted calculation, which can accurately reflect the characteristics of the evaluation weight in the initial evaluation score. The target evaluation score is obtained by calculating the selection probability of the entry point, which can obtain a target evaluation score that is close to the historical selection data, thereby improving the implicit characteristics of the evaluation score and achieving the effect of accurately reflecting the evaluation score of the entry point.

[0098] In one embodiment, the specific implementation process of determining the entry point corresponding to the target user as the target entry point for the target evaluation score that meets the preset entry point screening conditions includes:

[0099] Among the target evaluation scores of each entry point, the entry point with the highest target evaluation score is determined as the target entry point corresponding to the target user.

[0100] Specifically, the server can calculate the target evaluation score for each entry point in the SASE network, and then select the entry point with the highest target evaluation score as the target entry point. The server can then send this target entry point to the target user's terminal, indicating that it is the final selected entry point. For example, if multiple entry points have the same target evaluation score, all of them will be selected as the final entry point.

[0101] Optionally, the server can sort the target evaluation scores of all entry points to obtain a target evaluation score sequence, and select multiple entry points corresponding to the top-ranking target evaluation scores from the sequence as target entry points. The number of top-ranking target evaluation scores can be set according to user needs, and this embodiment does not impose specific limitations.

[0102] In this embodiment, by determining the entry point with the highest target evaluation score as the target entry point corresponding to the target user, the most suitable target entry point can be obtained and used as the optimal entry point for the target user, thus achieving the effect of accurately determining the optimal entry point.

[0103] like Figure 4 As shown, the following describes in detail the specific execution process of the above-mentioned method for determining network access points, including the following steps, with reference to a specific embodiment:

[0104] S401, each POP periodically reports its resource load-related indicators to the control center.

[0105] Points of Presence (POPs) report the average resource load (CPU utilization, memory utilization, bandwidth utilization, etc.) of each POP to the control center in real time.

[0106] S402, the control center compiles network performance metrics for all links at each POP point over the past month.

[0107] Points of Presence (POPs) report the average network quality (packet loss rate, jitter, latency, etc.) of each link to the control center in real time.

[0108] S403, the control center generates weight values ​​for each evaluation indicator in real time according to user needs.

[0109] The control center sets the weight of each evaluation indicator according to the user's specific needs, and the sum of the weights of all indicators is 1.

[0110] S404, The control center calculates the probability of a POP point being selected in the past month in this scenario.

[0111] The control center uses historical log information from the past month to calculate the probability of each POP point being selected for each type of demand.

[0112] S405, the control center comprehensively evaluates the node score based on the weight of the evaluation indicators and the probability of POP point selection.

[0113] The control center extracts the indicator data from the most recent month and calculates the comprehensive score of the POP point based on specific weights. The control center uses scores corresponding to specific indicator values ​​set in the database (scores between 0 and 100) as the indicator count in the comprehensive score calculation. The comprehensive score of the POP point is then multiplied by the probability of a POP point being selected in the most recent month under this type of demand scenario to obtain the final score for the POP point.

[0114] S406 assigns the highest-scoring POP point to the user.

[0115] The control center recommends the optimal node to the user based on the final score ranking of the POP points.

[0116] For example, suppose there are 4 POPs in a certain SASE network. A user wants to access this SASE network and has high requirements for packet loss rate. The average scores of each evaluation indicator over the past month are shown in the table below, and the weights of each indicator are shown in Tables 1 and 2. Assume that in this scenario, the probabilities of the 4 POPs being selected in the past month are as follows: POP1: 58%, POP2: 24%, POP3: 16%, POP4: 2%.

[0117] Table 1 Scores of POP Points

[0118]

[0119] Table 2 Weights of various indicators for POP points

[0120]

[0121] Without considering specific user needs, the optimal node in the evaluation could be any of POP1 to POP4, which may not meet the user's requirements. Since the current user has high requirements for packet loss rate, its packet loss rate is given higher weight. Therefore, the final score, with POP1 having the highest packet loss rate score, is obtained.

[0122] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0123] Based on the same inventive concept, this application also provides an access point determination apparatus for implementing the access point determination method described above. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more access point determination apparatus embodiments provided below can be found in the limitations of the access point determination method described above, and will not be repeated here.

[0124] In one embodiment, such as Figure 5 As shown, a network entry point determination device 500 is provided, including: a weight determination module 501, a score determination module 502, and a network entry point determination module 503, wherein:

[0125] The weight determination module 501 is used to obtain the business configuration data of the target user and determine the evaluation weight of each evaluation indicator corresponding to the entry point based on the business configuration data.

[0126] The score determination module 502 is used to determine the target evaluation score of each entry point in the target network based on the evaluation weight of each evaluation indicator and the indicator value of each evaluation indicator corresponding to the entry point.

[0127] The entry point determination module 503 is used to determine the entry points that meet the preset entry point screening conditions as the target entry points corresponding to the target user.

[0128] Furthermore, in one embodiment, the weight determination module 501 is also used to determine the importance sequence of each evaluation indicator corresponding to the entry point based on the evaluation indicator ranking data corresponding to the target user; and to determine the evaluation weight corresponding to each evaluation indicator according to the importance sequence and the preset weight allocation algorithm, wherein the business configuration data includes the evaluation indicator ranking data corresponding to the target user.

[0129] Furthermore, in one embodiment, the weight determination module 501 is also used to determine the evaluation weight of each evaluation indicator corresponding to the target business type based on the mapping relationship between the business type and the evaluation weight corresponding to each evaluation indicator, wherein the business configuration data includes the target business type corresponding to the target user.

[0130] Furthermore, in one embodiment, the device further includes a data acquisition module, configured to acquire access point selection data corresponding to the service type based on the service type corresponding to the service configuration data; wherein the access point selection data includes the number of times each access point is selected;

[0131] The probability determination module is used to determine the selection probability of each entry point based on the number of times each entry point is selected.

[0132] Furthermore, in one embodiment, the score determination module 502 is also used to perform weighted calculation based on the evaluation weights of each of the evaluation indicators and the indicator values ​​of each evaluation indicator corresponding to the entry point, to obtain the initial evaluation score of the entry point; and to update the initial evaluation score of the entry point based on the selection probability of the entry point, to obtain the target evaluation score of the entry point.

[0133] Furthermore, in one embodiment, the entry point determination module 503 is also used to determine the entry point with the largest target evaluation score among the target evaluation scores of each entry point as the target entry point corresponding to the target user.

[0134] Each module in the aforementioned network access point determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0135] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores the evaluation indicators corresponding to the network entry points and their values. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a network entry point determination method.

[0136] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0137] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0138] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0139] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0141] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0142] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0143] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining network entry points, characterized in that, The method includes: Obtain the business configuration data of the target user, wherein the business configuration data includes the target business type corresponding to the target user; Based on the mapping relationship between business type and the evaluation weights corresponding to each evaluation indicator, the evaluation weights of each evaluation indicator corresponding to the target business type are determined, and the evaluation weights of each evaluation indicator are used as the evaluation weights of each evaluation indicator corresponding to the network entry point; the mapping relationship includes multiple business types and the evaluation weights of each evaluation indicator corresponding to each business type, and the evaluation weights of each rating indicator corresponding to each business type are determined in advance based on the actual application scenario. For each entry point in the target network, a weighted calculation is performed based on the evaluation weights of each of the evaluation indicators and the indicator values ​​of each evaluation indicator corresponding to the entry point to obtain the initial evaluation score of the entry point. Obtain access point selection data corresponding to the target service type; wherein, the access point selection data includes the number of times each access point with the same service type as the target user has been selected; The selection probability of each entry point is determined based on the number of times each entry point is selected. Based on the selection probability of the entry point, the initial evaluation score of the entry point is updated to obtain the target evaluation score of the entry point; The entry points that meet the preset entry point screening criteria in the target evaluation score are determined as the target entry points for the target user.

2. The method according to claim 1, characterized in that, The service configuration data includes ranking data of evaluation indicators corresponding to the target user; the process of obtaining the service configuration data of the target user and determining the evaluation weight of each evaluation indicator corresponding to the entry point based on the service configuration data includes: Based on the ranking data of the evaluation indicators corresponding to the target users, the importance sequence of each evaluation indicator corresponding to the entry point is determined. The evaluation weights corresponding to each evaluation index are determined based on the importance sequence and the preset weight allocation algorithm.

3. The method according to claim 1, characterized in that, The step of determining the entry points whose target evaluation scores meet the preset entry point screening conditions as the target entry points for the target users includes: Among the target evaluation scores of each entry point, the entry point with the highest target evaluation score is determined as the target entry point corresponding to the target user.

4. The method according to claim 1, characterized in that, The step of determining the entry points whose target evaluation scores meet the preset entry point screening conditions as the target entry points for the target users includes: Sort all the target evaluation scores of the network entry points to obtain the target evaluation score sequence; From the target evaluation score sequence, select multiple entry points corresponding to the target evaluation scores that are at the top of the sequence as the target entry points for the target user.

5. A device for determining network entry points, characterized in that, The device includes: The weight determination module is used to acquire the business configuration data of the target user, which includes the target business type corresponding to the target user; based on the mapping relationship between the business type and the evaluation weights corresponding to each evaluation indicator, the module determines the evaluation weights of each evaluation indicator corresponding to the target business type, and uses the evaluation weights of each evaluation indicator as the evaluation weights of each evaluation indicator corresponding to the network entry point; the mapping relationship includes multiple business types and the evaluation weights corresponding to each evaluation indicator of each business type, and the evaluation weights of each rating indicator corresponding to each business type are determined in advance based on the actual application scenario; The score determination module is used to perform weighted calculations on each entry point in the target network based on the evaluation weights of the evaluation indicators and the indicator values ​​of the evaluation indicators corresponding to the entry point, so as to obtain the initial evaluation score of the entry point. The data acquisition module is used to acquire access point selection data corresponding to the target service type; wherein, the access point selection data includes the number of times each access point with the same service type as the target user has been selected; The probability determination module is used to determine the selection probability of each entry point based on the number of times each entry point is selected. The score determination module is further configured to update the initial evaluation score of the entry point based on the selection probability of the entry point, and obtain the target evaluation score of the entry point; the selection probability of the entry point is determined based on the historical selection count of entry points with the same business type as the target user. The entry point determination module is used to determine the entry points that meet the preset entry point screening conditions as the target entry points for the target user.

6. The apparatus according to claim 5, characterized in that, The business configuration data includes ranking data of evaluation indicators corresponding to the target users; The weight determination module is used to determine the importance sequence of each evaluation indicator corresponding to the entry point based on the evaluation indicator ranking data corresponding to the target user. The evaluation weights corresponding to each evaluation index are determined based on the importance sequence and the preset weight allocation algorithm.

7. The apparatus according to claim 6, characterized in that, The entry point determination module is further configured to determine the entry point with the highest target evaluation score among the target evaluation scores of each entry point as the target entry point corresponding to the target user.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images