Multi-interface association method and device for new air interface carrying voice VoNR service

Abstract

The present disclosure relates to the field of communication technology, and to a multi-interface association method and device, storage medium and electronic device for VoNR services, including: constructing a first vector set according to the voice call list information of the current domain, and determining an intervention factor from the feature field items contained in the first vector set; traversing the feature field items in the first vector set based on the intervention factor, and obtaining a combination of target feature field items to determine a second vector set; using each second vector in the second vector set to associate the process data interface of the current domain with the process data interface of other domains, and determining the parameters to be optimized of the second vector according to the association result; using a particle swarm optimization algorithm based on yarn resource utilization to update the parameters to be optimized, and determining the target vector from the second vector set according to the updated parameters to be optimized, so as to realize multi-interface association according to the target vector. The present disclosure can comprehensively, efficiently and accurately realize the global multi-interface association and data synthesis of VoNR services.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and more specifically, to a multi-interface association method for a new air interface carrying a voice VoNR service, a multi-interface association device for a new air interface carrying a voice VoNR service, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the rapid development of communication technology, the voice solution of the fifth generation mobile communication technology (5G) uses the evolved packet system fallback (EPSFB) to fall back to the 4G network for VoLTE (Voice over Long-Term Evolution) calls. The new air interface voice bearer (Voice on New Radio, VoNR) solution of the 5G network is also gradually beginning to be used.

[0003] Compared with 4G network VoLTE voice, 5G voice service process load and coverage scenarios are rich, such as the coordinated implementation of network elements in multiple domains such as wireless, 4G core network (EPC), 5G core network (5GC), IP Multimedia Subsystem (IMS), etc., and also includes user data interaction and PCC policy management, EPSFB switching and redirection, VoNR voice 5-4 switching and other scenario intersections and judgments. However, in the face of complex scenario intersections and scenario identification, the related technology based on single interface failure cause location has the disadvantages of isolated judgment and lack of context association, which affects the accuracy and efficiency of fault location and affects the user experience to a certain extent.

[0004] Therefore, it is necessary to provide a multi-interface association method for a new air interface to carry voice VoNR services.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] The purpose of the present disclosure is to provide a multi-interface association method and device for a new air interface carrying a voice VoNR service, a computer-readable storage medium and an electronic device, so as to comprehensively, efficiently and accurately realize the global multi-interface association and data synthesis of the VoNR service.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to one aspect of the present disclosure, a multi-interface association method for a new air interface carrying a voice VoNR service is provided, including: constructing a first vector set based on voice call record information of the current domain, and determining at least one as an intervention factor from the feature field items contained in the first vector set; traversing the feature field items in the first vector set based on the intervention factor, and obtaining a combination of target feature field items to determine a second vector set; using each second vector in the second vector set to associate the process data interface of the current domain with the process data interfaces of other domains, and determining the parameters to be optimized of the second vector according to the association result; using a particle swarm optimization algorithm based on yarn resource utilization to update the parameters to be optimized, and determining the target vector from the second vector set according to the updated parameters to be optimized, so as to realize multi-interface association according to the target vector.

[0009] In an exemplary embodiment of the present disclosure, the first vector set is constructed based on the voice call record information of the current domain, including: obtaining the voice call record information of the current domain based on YARN cluster resources; according to preset key feature fields, obtaining feature field items corresponding to the preset key feature fields from the voice call record information, and forming the first vector set according to the feature field items; wherein, the support count corresponding to the feature field item is determined according to the frequency of occurrence of the feature field item in the voice call record information.

[0010] In an exemplary embodiment of the present disclosure, determining at least one of the feature field items included in the first vector set as an intervention factor includes: determining at least one feature field item corresponding to the maximum support count in the first vector set as the intervention factor.

[0011] In an exemplary embodiment of the present disclosure, the feature field items in the first vector set are traversed based on the intervention factor to obtain a combination of target feature field items for determining the second vector set, including: pruning the feature field items in the first vector set according to a preset support threshold and a support count corresponding to each of the feature field items; traversing the feature field items in the first vector set after the pruning based on the intervention factor, and determining the second vector as a combination of the intervention factor and each of the traversed feature field items as the target feature field item; and determining the second vector set according to each of the second vectors.

[0012] In an exemplary embodiment of the present disclosure, there are multiple intervention factors; based on the feature field items in the first vector set after traversal and pruning by each intervention factor, the intervention factor and each traversed feature field item are used as a combination of target feature field items to determine a second vector; and the second vector set is determined according to each second vector corresponding to each intervention factor.

[0013] In an exemplary embodiment of the present disclosure, after determining the second vector set according to each second vector, it also includes: updating the second vector to the intervention factor, and continuing to traverse the feature field items in the first vector set after pruning based on the second vector, so as to add the obtained combination of target feature field items as a newly added second vector to the second vector set; looping the following process until the number of loops meets the set threshold, and outputting the final second vector set: updating the newly added second vector to the intervention factor, and continuing to traverse the feature field items in the first vector set after pruning based on the newly added second vector, so as to add the obtained combination of target feature field items as a newly added second vector to the second vector set.

[0014] In an exemplary embodiment of the present disclosure, each second vector in the second vector set is used to associate the process data interface of the current domain with the process data interfaces of other domains, and the parameters to be optimized of the second vector are determined based on the association result, including: using each second vector to associate the process data interface of the current domain with the process data interfaces of other domains respectively; obtaining the parameters to be optimized corresponding to each successfully associated second vector, and the parameters to be optimized include the time consumption of this round of association corresponding to the second vector.

[0015] In an exemplary embodiment of the present disclosure, the particle swarm optimization algorithm based on yarn resource utilization is used to update the parameters to be optimized, and the target vector is determined from the second vector set according to the updated parameters to be optimized, including: based on the correspondence between yarn resource utilization and the influencing factor, obtaining the target influencing factor corresponding to the current yarn resource utilization when the process data interface of the current domain is associated with the process data interface of the other domain using the second vector; generating a particle population according to each of the second vectors, each second vector corresponding to a particle; updating the current round association time of each particle based on the target influencing factor to obtain the current round target time corresponding to each particle; comparing the current round target time with the historical optimal association time, and determining the target vector from the particle according to the comparison result.

[0016] In an exemplary embodiment of the present disclosure, comparing the current round target time consumption with the historical optimal association time consumption, and determining the target vector from the particles according to the comparison result, includes: if the current round target time consumption is less than the historical optimal association time consumption, determining that the current round association result converges, determining the current round target time consumption as the historical optimal association time consumption, and the particle corresponding to the current round target time consumption is used as the target vector; if the current round target time consumption is greater than the historical optimal association time consumption, determining that the current round association result does not converge, the historical optimal association time consumption remains unchanged, and the particle corresponding to the historical optimal association time consumption is used as the target vector.

[0017] In an exemplary embodiment of the present disclosure, generating a particle population according to each of the second vectors includes: performing time shifting on a time field item in each of the second vectors according to a preset method; and generating the particle population according to each of the second vectors after the time shifting.

[0018] In an exemplary embodiment of the present disclosure, the time field items in each of the second vectors are time-shifted in a preset manner, including: time-shifting the start time item and the end time item in the time field item respectively, so that the time interval indicated by the time field item after the time shift includes the time interval indicated by the time field item before the time shift.

[0019] In an exemplary embodiment of the present disclosure, before constructing the first vector set based on the voice call record information of the current domain, the method also includes: collecting multi-domain original data, the multi-domain original data at least including O domain data, configuration data and B domain data; preprocessing the multi-domain original data, and obtaining the voice call record information of the current domain from the preprocessed data; wherein the preprocessing includes one or more of screening of key process data, marking of key processes, marking of abnormal processes, and data partitioning and storage according to number partitions.

[0020] In an exemplary embodiment of the present disclosure, after realizing multi-interface association between the current domain and other domains according to the target vector, the method also includes: merging the process interface data corresponding to each domain for realizing multi-interface association based on the target vector, and outputting global voice call record information; performing operation and maintenance processing on cross-domain VoNR services based on the global voice call record information.

[0021] According to one aspect of the present disclosure, a multi-interface association device for a VoNR service carrying voice over a new air interface is provided, the device comprising:

[0022] A determination module, used to construct a first vector set based on the voice call record information of the current domain, and determine at least one as an intervention factor from the feature field items contained in the first vector set; a first association module, used to traverse the feature field items in the first vector set based on the intervention factor, and obtain a combination of target feature field items to determine a second vector set; a second association module, used to use each second vector in the second vector set to associate the process data interface of the current domain with the process data interface of other domains, and determine the parameters to be optimized of the second vector based on the association result; an association optimization module, used to update the parameters to be optimized using a particle swarm optimization algorithm based on yarn resource utilization, and determine the target vector from the second vector set based on the updated parameters to be optimized, so as to realize multi-interface association according to the target vector.

[0023] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any one of the above methods is implemented.

[0024] According to one aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned methods by executing the executable instructions.

[0025] The multi-interface association method for the new air interface carrying voice VoNR service in the exemplary embodiment of the present disclosure, on the one hand, constructs a first vector set according to the voice call record information of the current domain and determines at least one intervention factor from the characteristic field items therein, traverses the characteristic field items in the first vector set under the intervention of the intervention factor to obtain a combination of valid characteristic field items in the traversal process, and outputs a second vector set, through which the self-association of the process data interface within the current domain can be realized; on the other hand, different second vectors in the second vector set are called to associate the process data interface of the current domain with the process data interfaces of other domains, and on the basis of the association, introduces a particle swarm optimization algorithm for yarn resource utilization The parameters to be optimized of the second vector are updated to evaluate the optimal feature vector according to the updated parameters to be optimized, and the target vector is output, so as to use the target vector to realize efficient multi-domain multi-interface association, and the target vector can be preferentially called in the subsequent multi-interface association process, so as to further improve the efficiency of VoNR voice multi-interface association, which is beneficial to the self-optimization of the synthesis efficiency of multi-interface association data; on the other hand, the present invention adopts the method of front-to-back decoupling of the application layer and the DPI layer, which can be flexibly deployed, avoiding the DPI environment restrictions across domains and multiple manufacturers, and realizing the full-domain multi-interface association and data synthesis of VoNR services in a comprehensive, efficient and accurate manner, which is of practical significance for improving operation and maintenance efficiency, reducing costs and increasing efficiency.

[0026] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0028] Figure 1 A schematic diagram of a process of associating multiple interfaces of a new air interface carrying a voice VoNR service according to an exemplary embodiment of the present disclosure is shown;

[0029] Figure 2 A flowchart of constructing a first vector set according to voice call record information of a current domain according to an exemplary embodiment of the present disclosure is shown;

[0030] Figure 3 A flowchart for determining a second vector set according to an exemplary embodiment of the present disclosure is shown;

[0031] Figure 4 A flowchart of expanding a second vector set according to an exemplary embodiment of the present disclosure is shown;

[0032] Figure 5 A schematic diagram showing the corresponding relationship between yarn resource utilization and influencing factors in an existing network environment according to an exemplary embodiment of the present disclosure is shown;

[0033] Figure 6 A flowchart of association self-optimization within an association cycle according to an exemplary embodiment of the present disclosure is shown;

[0034] Figure 7 shows various application scenario examples according to exemplary embodiments of the present disclosure;

[0035] Figure 8 A schematic diagram of abnormal scenario analysis in an application scenario according to an exemplary embodiment of the present disclosure is shown;

[0036] Fig. 9 A flowchart of the arrangement involved in the association of multiple interfaces for carrying a voice VoNR service over a new air interface according to an exemplary embodiment of the present disclosure is shown;

[0037] Fig.10 A schematic diagram showing a first vector set and support counts corresponding to each feature field item according to an exemplary embodiment of the present disclosure is shown;

[0038] Fig.11 A schematic diagram showing a second vector set and support counts corresponding to each feature field item according to an exemplary embodiment of the present disclosure is shown;

[0039] Fig.12 A schematic diagram of an evaluation result of associating a process data interface of a current domain with process data interfaces of other domains by using each second vector in a second vector set according to an exemplary embodiment of the present disclosure is shown;

[0040] Fig.13 A schematic structural diagram of a multi-interface association device for carrying a voice VoNR service on a new air interface according to an exemplary embodiment of the present disclosure is shown;

[0041] Fig.14 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown.

[0042] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0043] The exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present disclosure will be more comprehensive and complete and the concepts of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the figures represent the same or similar structures, and thus their detailed description will be omitted.

[0044] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known structures, methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0045] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or these functional entities or parts of functional entities may be implemented in one or more software hardened modules, or these functional entities may be implemented in different networks and / or processor devices and / or microcontroller devices.

[0046] In the related technologies in this field, in order to solve the problems of fault location and complaint handling efficiency in VoNR voice scenarios, manual auditing and underlying stream synthesis methods can be used. Among them, the manual auditing method is to query and audit the events of each single interface to realize the judgment and association of events related to the VoNR voice business process, but the voice process of VoNR involves multiple domains, multiple interfaces and multiple events, and the manual auditing method is inefficient and has a high error rate, which affects the accuracy of the audit.

[0047] In another related technology, the underlying streaming synthesis method is used to achieve the fusion of key events and related fields of multiple domains and multiple interfaces based on the original code stream information collected by the underlying DPI (Deep Packet Inspection). However, it has strict requirements on the objective environment and requires that the interfaces involved in the underlying voice process must be from the same underlying manufacturer. The application and collection are not decoupled, the development is difficult, the cycle is long, and efficient query and auditing cannot be achieved.

[0048] Based on one or more of the above problems, in an exemplary embodiment of the present disclosure, a multi-interface association method for a new air interface carrying a voice VoNR service is first provided. Figure 1 A schematic diagram of a multi-interface association method for a new air interface carrying a voice VoNR service according to an exemplary embodiment of the present disclosure is shown. Figure 1 As shown, the process includes steps S110 to S140:

[0049] Step S110: constructing a first vector set according to the voice call record information of the current domain, and determining at least one as an intervention factor from the feature field items included in the first vector set;

[0050] Step S120: traversing the feature field items in the first vector set based on the intervention factor, obtaining a combination of target feature field items to determine the second vector set;

[0051] Step S130: using each second vector in the second vector set to associate the process data interface of the current domain with the process data interfaces of other domains, and determining the parameters to be optimized of the second vector according to the association result;

[0052] Step S140: using a particle swarm optimization algorithm based on yarn resource utilization to update the parameters to be optimized, and determining a target vector from the second vector set according to the updated parameters to be optimized, so as to realize multi-interface association according to the target vector.

[0053] According to the multi-interface association method for the new air interface carrying voice VoNR service of the exemplary embodiment of the present disclosure, on the one hand, a first vector set is constructed according to the voice call record information of the current domain and at least one intervention factor is determined from the characteristic field items therein, and the characteristic field items in the first vector set are traversed under the intervention of the intervention factor to obtain a combination of valid characteristic field items in the traversal process, and a second vector set is output. The self-association of the process data interface within the current domain can be achieved through the second vector set; on the other hand, different second vectors in the second vector set are called to associate the process data interface of the current domain with the process data interfaces of other domains, and on the basis of the association, a particle swarm optimization algorithm for yarn resource utilization is introduced. The parameters to be optimized of the second vector are updated to evaluate the optimal feature vector according to the updated parameters to be optimized, and the target vector is output, so as to use the target vector to realize efficient multi-domain multi-interface association, and the target vector can be preferentially called in the subsequent multi-interface association process, so as to further improve the efficiency of VoNR voice multi-interface association, and self-optimize the synthesis efficiency of multi-interface association data; on the other hand, the present invention adopts a method of front-to-back decoupling of the application layer and the DPI layer, which can be flexibly deployed, avoiding the limitations of the DPI environment across domains and multiple manufacturers, and realizing the full-domain multi-interface association and data synthesis of VoNR services in a comprehensive, efficient and accurate manner, which is of practical significance for improving operation and maintenance efficiency, reducing costs and increasing efficiency.

[0054] Hereinafter, the multi-interface association method of the new air interface carrying voice VoNR service of the exemplary embodiment of the present disclosure will be explained and illustrated in detail with reference to the accompanying drawings.

[0055] First, the purpose of the invention of the exemplary embodiment of the present disclosure is explained and illustrated. Specifically, the exemplary embodiment of the present disclosure obtains a combination of key feature field items from the feature field items in the first vector set based on the intervention of the intervention factor to output the second vector set, so as to realize the self-association of the process data interface within the current domain; at the same time, in order to further improve the efficiency of multi-interface association, different second vectors in the second vector set can be used to complete the association of process data interfaces between different domains, and according to the voice process and environmental characteristics, the parameters to be optimized of the second vector are updated based on the particle swarm optimization algorithm that introduces the yarn resource utilization, so as to realize the evaluation of the optimal feature vector according to the updated parameters to be optimized, that is, the output target vector is called first, so as to improve the efficiency of VoNR voice multi-interface synthesis.

[0056] In step S110, a first vector set is constructed according to the voice call record information of the current domain, and at least one of the characteristic field items included in the first vector set is determined as an intervention factor.

[0057] In the exemplary embodiment of the present disclosure, the current domain refers to the current IMS domain involved in the 5G voice service process. Correspondingly, other domains corresponding to the current IMS domain may be one or more of EPC, 5GC, and other IMS domains different from the current IMS domain, and there is no special limitation on this. The voice call list information may be a voice XDR call list that collects voice conversations based on actual network services. The XDR call list is a session-level detailed record of the signaling process and service transmission process generated after processing the full amount of Internet data, including but not limited to basic information (such as service start and end time, session ID, etc.), network element information (such as user access network type, policy control function PCF, base station identification, cell, etc.), user information (such as mobile phone number / user account, international mobile subscriber identity IMSI, network access identification, etc.), quality information (such as latency), etc.

[0058] In an exemplary embodiment, before constructing the first vector according to the voice call record information of the current domain, the method further includes:

[0059] First, multi-domain raw data is collected, and then preprocessed, and voice call record information of the current domain is obtained from the preprocessed data.

[0060] Among them, the multi-domain original data includes at least O domain (operation support system, operation domain) data, configuration data and B domain (business support system, business domain) data. O domain data can be XDR data output by the DPI of O domain, such as obtained based on the following process data interfaces N1N2, N4, N7, N11, Gm, Mw, ISC, Gx, Rx, Sh, Zh, Cx, Mr, Mj, Mg, N26, etc. Configuration data includes but is not limited to terminal translation configuration table data, network element translation configuration table data, cell alarm table data and cell configuration table, etc. B domain data includes but is not limited to package information, account opening information, arrears information, etc.

[0061] The preprocessing may include one or more of screening of key process data, marking of key processes, marking of abnormal processes, and partitioning and storing data according to number partitions.

[0062] In actual implementation, the process data that is not related to the VoNR service in the obtained multi-domain original data can be eliminated to screen out key process data, such as access (Attach), voice call, IMS registration, release (Detach), dedicated bearer establishment, session establishment, context release, switching and resource reservation and other key process data; the abnormal processes and related data corresponding to the key processes in the session establishment process can also be marked, and number partitioning and storage of associated data can be performed based on numbers. Of course, the embodiments of the present disclosure can also perform other pre-processing operations on the multi-domain original data according to actual application requirements. The embodiments of the present disclosure include but are not limited to the above data pre-processing operations.

[0063] By preprocessing the multi-domain raw data, memory storage is reduced and the subsequent multi-interface association and data synthesis efficiency is further increased.

[0064] In an exemplary embodiment, constructing a first vector set according to voice call record information of the current domain may include steps S210 and S220:

[0065] Step S210: Identify the voice call record information of the current domain based on the YARN cluster resources.

[0066] Based on the YRAN cluster resources, a streaming resource task can be established to identify the signaling interface data in the current domain (current IMS domain) and obtain the voice call record information of the current domain.

[0067] Step S220: According to the preset key feature field, a feature field item corresponding to the preset key feature field is obtained from the voice call record information, and a first vector set is formed according to the feature field item.

[0068] The preset key feature fields are key feature fields predetermined according to the VoNR service, such as those determined based on the key feature fields involved in the specification details. Exemplarily, the key feature fields may include "start time", "end time", "user number", "IP address of the terminal user", "IMS billing ID", "destination network element port number", "called number", etc. Obtain the feature field items corresponding to these preset key feature fields in the voice call sheet information, such as the feature field item corresponding to the "called number" is "186******26", the "destination network element port number" is "5060", etc., which will not be listed one by one here.

[0069] The support count corresponding to the feature field item can be determined according to the frequency of occurrence of the feature field item in the voice call record information. The support count is used to characterize the frequency of occurrence of the feature field item in the voice call record information, and to a certain extent indicates the criticality of the feature field item in the voice call record information.

[0070] For example, Table 1 schematically shows a type of voice call record information. As shown in Table 1, the voice call record information of a single voice session includes multiple transaction records M={L1},{L2},…,{Li}, and each transaction record includes a feature field set, such as L1={number 1, IMSI1, time 1, billing ID1, port 1, session ID1, network element IP1, URL1…}.

[0071] Table 1

[0072] Transaction 1 Number 1 IMSI1 Time 1 Billing ID1 Port 1 Session ID1 NE IP1 URL1 Transaction 2 Number 1 IMSI1 IMEI1 Time 1 Billing ID2 Port 1 Session ID2 NE IP2 URL1 Transaction 3 Number 1 IMSI1 IMEI2 Time 1 Billing ID2 Port 3 Session ID5 Network element IP3 URL1 Transaction 4 Number 1 IMSI1 IMEI3 Time 1 Billing ID2 Port 5 Session ID2 NE IP4 URL1 … … … … … … … … … …

[0073] Based on Table 1 and according to the preset key feature fields, first, the first vector set can be obtained = {number 1, IMSI1, IMEI1, IMEI2, IMEI3, time 1, billing ID1, billing ID2, port 1, port 3, port 5, session ID1, session ID2, session ID5, network element IP1, network element IP2, network element IP3, network element IP4, URL1, ...}; secondly, according to the frequency of occurrence of each feature field item in the first vector set in the voice call record information in Table 1, the support count corresponding to each feature field item is determined, as shown in Table 2, which shows some feature field items in the first vector set and the corresponding support counts.

[0074] Table 2

[0075] Feature Field Item Support Count Number 1 4 IMSI1 4 IMEI1 1 Time 1 4 Billing ID1 1 Billing ID2 3 Port 1 2 Port 3 1 Port 5 1 … …

[0076] It should be noted that Table 2 is only the result of support count statistics based on the feature fields shown in Table 1. The omitted parts are not involved in the calculation. The support count in actual implementation is obtained based on the actual data of all feature field items in the first feature vector set.

[0077] The exemplary embodiment of the present disclosure performs unified conversation voice process judgment on multiple interfaces in the current domain based on the voice process feature service information field, obtains key frequently appearing feature fields in voice call sheet information and constructs a first vector set.

[0078] Further, after constructing the first vector set according to the voice call record information of the current domain, at least one is determined as an intervention factor from the feature field items included in the first vector set.

[0079] Among them, at least one feature field item corresponding to the maximum support count in the first vector set can be determined as an intervention factor (that is, intervention factor Factor = max(li, Support), li is the feature field item in the first vector set, and Support is the support count corresponding to the feature field item). The intervention factor is used to form a combination of target feature field items with the traversed feature field items in the process of traversing the feature field items in the first vector set one by one, so as to realize the association judgment of the intervention factor.

[0080] Continuing to refer to Table 2, the intervention factors determined according to the support calculation include "Number 1", "IMIS1" and "Time 1", and the support calculations corresponding to these intervention factors are all 4, that is, the feature field items corresponding to the maximum support calculation can be one or more, and the corresponding number of intervention factors can be one or more.

[0081] In step S120, the feature field items in the first vector set are traversed based on the intervention factor to obtain a combination of target feature field items to determine the second vector set.

[0082] In an exemplary embodiment of the present disclosure, the feature field items in the first vector set are traversed and associated with each other using the intervention factor as an interference item, so as to construct a combination of target feature field items according to the intervention factor and the traversed feature field items.

[0083] In an exemplary embodiment, an implementation manner for determining a second vector set is provided. Figure 3 A flowchart of determining a second vector set according to an exemplary embodiment of the present disclosure is shown, and the process includes steps S310 to S330:

[0084] Step S310: Pruning the feature field items in the first vector set according to a preset support threshold and the support count corresponding to each feature field item.

[0085] The preset support threshold is a support termination threshold based on the configuration. When the support count corresponding to the feature field item is less than the preset support threshold (Support(x)<Support threshold), the feature field item in the first vector set is pruned, and the feature field item is not added as the second vector to the second vector set to achieve the cleaning of redundant items.

[0086] Step S320: based on the intervention factor, the feature field items in the first vector set after traversal and pruning are determined, and the intervention factor and each of the traversed feature field items are used as a combination of target feature field items to form a second vector.

[0087] Under the intervention of the intervention factor, the feature field items in the first vector set after pruning are traversed to reorganize and obtain the second vector, wherein the combination of the target feature field items (the second vector) is the combination of the intervention factor and the traversed feature field items.

[0088] Exemplarily, referring to the feature field items shown in Table 2, if the preset support threshold is 2, the first vector set after pruning = {number 1, IMSI1, time 1, billing ID2, port 1}, and the intervention factors are "number 1", "IMIS1" and "time 1", then first under the intervention of the intervention factor "number 1", the combination of target feature field items (second vector) obtained in the traversal process includes: (number 1, IMSI1), (number 1, IMEI1), (number 1, time 1), (number 1, billing ID2), (number 1, port 1); then under the intervention of the intervention factor "IMIS1", the combination of target feature field items (second vector) obtained in the traversal process includes: (IMSI1, time 1), (IMSI1, billing ID2), (IMSI1, port 1), and then the second vector is obtained under the intervention of the intervention factor "time 1", which will not be listed here.

[0089] That is to say, if there are multiple pre-factors, then based on each intervention factor traversing the feature field items in the first vector set after pruning, the intervention factor and each traversed feature field item are used as a combination of the target feature field items to determine the second vector.

[0090] Under the intervention of the intervention factor, the association and combination of the intervention factor and the characteristic field in the first vector set is realized, so that the association of multiple ports in the current domain can be realized.

[0091] Step S330: Determine a second vector set according to each second vector.

[0092] A second vector set is formed according to the obtained second vectors. Correspondingly, when there are multiple intervention factors, the second vector set is determined according to the second vectors corresponding to the intervention factors.

[0093] In an exemplary embodiment, in order to further enable the second vector set to fully express the key content of the voice call record information of the current domain and the process data interface association characteristics, the first vector set after pruning can also be traversed based on the second vector, and the newly added second vector is determined to be added to the second vector set. The embodiment of the present disclosure also provides an implementation method for expanding the second vector set by iteratively traversing the first vector set.

[0094] Figure 4 A flowchart of expanding a second vector set according to an exemplary embodiment of the present disclosure is shown. Figure 4 , the process includes steps S410 to S430:

[0095] Step S410: Update the second vector to the intervention factor, and continue to traverse the feature field items in the first vector set after the pruning process based on the second vector, so as to add the obtained combination of target feature field items as a newly added second vector to the second vector set.

[0096] The second vector is updated to the intervention factor, that is, the characteristic field corresponding to the second vector is used as the intervention factor. For example, referring to Table 2, the second vector is (number 1, IMSI1), then "number 1, IMSI1" is used as the intervention factor, and the first vector set after pruning is continued to be traversed = {number 1, IMSI1, time 1, billing ID2, port 1}, and the combination of target field items obtained (the newly added second vector) includes: (number 1, IMSI1, time 1), (number 1, IMSI1, billing ID2) and (number 1, IMSI1, port 1). Correspondingly, the other second vectors are updated to the intervention factors respectively, and the combination of target field items is obtained under the intervention of each intervention factor respectively, and the combination of target characteristic field items is added to the second vector set as the newly added second vector.

[0097] Step S420: Determine whether the number of loop iterations meets a set threshold.

[0098] If the number of loop iterations meets the set threshold, the final expanded second vector set is output; if the number of loop iterations does not meet the set threshold, the process goes to step S430.

[0099] Step S430: Update the newly added second vector to the intervention factor, and continue to traverse the feature field items in the first vector set after pruning based on the newly added second vector, so as to add the obtained combination of target feature field items as the newly added second vector to the second vector set.

[0100] Continuing to refer to step S410, the newly added second vector (number 1, IMSI 1, time 1) is updated as the intervention factor, and under the intervention of the newly added second vector, the feature field items in the first vector set after pruning are continued to be traversed. The traversal process is similar to step S410 and will not be repeated here. Finally, the combination of the obtained target feature field items is added to the second vector set as the newly added second vector, and the process returns to step S420 for the next round of iterative judgment.

[0101] Through the above iterative process, the second vector set is further expanded, so that the second vector set includes second vectors with different numbers of feature field items, such as a combination with two target feature field items, a combination with three target feature field items, a combination with four target feature fields, etc. The embodiment of the present disclosure can limit the number of combinations of different numbers of feature field items included in the second vector set by setting a threshold, such as looping for 2, 3, 4 or 5 times, without special limitation.

[0102] Based on this, the expression of the second vector in the second vector set is enriched, which facilitates the efficient and accurate association of the subsequent process data interface.

[0103] In step S130, each second vector in the second vector set is used to associate the process data interface of the current domain with the process data interfaces of other domains, and the parameters to be optimized of the second vector are determined according to the association result.

[0104] In an exemplary embodiment of the present disclosure, based on the process logic of the VoNR service and the second vector set, each second vector is used to automatically associate the process data interface of the current domain with the process data interface of other domains. Wherein, successful association means that the characteristic field items corresponding to the second vector contained in the process data interface of the current domain are completely consistent with the characteristic field items contained in the process data interface of other domains, such as both containing (2022-11-16 17:50:43.395, psbc23bhw.1ab.5091.20221116095043, 1530*****576, 32198); on the contrary, based on the second vector, the process interface data of the current domain does not have a process data interface of other domains that is completely consistent with it, and the association fails.

[0105] The embodiment of the present disclosure can obtain the parameter to be optimized corresponding to the successfully associated second vector, and the parameter to be optimized includes the time consumption of this round of association corresponding to the second vector. In other words, the parameter to be optimized is the time consumed to complete this round of association.

[0106] In addition, when calling the second vector for this round of association, the utilization of the yarn cluster resources, such as the yarn resource utilization rate, can also be obtained at the same time, so as to use the yarn cluster resource utilization as an influencing factor to intervene in the evaluation of the target vector, which will be introduced later.

[0107] In step S140, a particle swarm optimization algorithm based on yarn resource utilization is used to update the parameters to be optimized, and a target vector is determined from the second vector set according to the updated parameters to be optimized, so as to realize multi-interface association according to the target vector.

[0108] In an exemplary embodiment of the present disclosure, when the second vector set is used to associate the process data interface of other domains for each process, the target impact factor corresponding to the current yarn resource utilization when the process data interface of the current domain is associated with the process data interface of other domains using the second vector can be obtained based on the correspondence between the yarn resource utilization and the impact factor. Usually, as the yarn resource utilization continues to increase, the impact factor changes accordingly, which affects the target vector evaluation of each round. By introducing the target impact factor corresponding to the current yarn resource utilization when multiple interfaces are associated into the determination process of the target vector, the impact of the yarn resource utilization is fully considered, and the accuracy of the target vector evaluation is improved.

[0109] like Figure 5 A schematic diagram of the correspondence between yarn resource utilization and impact factors in an existing network environment according to an exemplary embodiment of the present disclosure is shown, and a target impact factor corresponding to the current yarn resource utilization can be obtained based on the diagram.

[0110] It should be noted that in order to update the target impact factor corresponding to the current yarn resource utilization and the parameter to be optimized (the time consumed in this round of association), the target impact factor corresponding to the current yarn resource utilization can also be converted into a time evaluation value according to a preset conversion method so as to perform associated calculation with the parameter to be optimized. The conversion method of the embodiment of the present disclosure is not specifically limited.

[0111] The particle swarm optimization algorithm that introduces the target impact factor corresponding to the current yarn resource utilization rate may include: first, generating a particle population according to each second vector, each second vector corresponds to a particle; second, updating the current round association time consumption of each particle based on the target impact factor to obtain the current round target time consumption corresponding to each particle; finally, comparing the current round target time consumption with the historical optimal association time consumption, and determining the target vector from the particle according to the comparison result.

[0112] Figure 6 A flowchart of self-optimization of association within an association cycle according to an exemplary embodiment of the present disclosure is shown below. Figure 6The process of determining the target vector according to the embodiment of the present disclosure is described.

[0113] Step S610: basic parameter configuration.

[0114] Basic parameters include time offset, data storage location, library name, number partition and other VoNR service-related configuration parameters.

[0115] Step S620: using the i-th second vector in the second vector set to perform an association process between the process data interface of the current domain and the process data interfaces of other domains, and obtaining the association time consumption of this round.

[0116] Step S630: Obtain a target impact factor corresponding to the current yarn resource utilization based on the corresponding relationship between the yarn resource utilization and the impact factor.

[0117] Step S640: The particle swarm optimization algorithm based on the target impact factor updates the current round association time consumption to obtain the current round target time consumption.

[0118] Step S650: Compare the current round target time consumption with the historical optimal association time consumption, and determine whether the association result converges according to the comparison result.

[0119] Among them, in step S660, if the target time of this round is less than the historical optimal association time, it is determined that the result of this round of association converges, and the target time of this round is determined as the historical optimal association time and the particle corresponding to the target time of this round is used as the target vector, so that the target vector is applied to the next association.

[0120] In step S670, if the target time of this round is greater than the historical optimal association time, it is determined that the result of this round of association does not converge, the historical optimal association time remains unchanged, and the particle corresponding to the historical optimal association time is used as the target vector, and the i+1th second vector in the second vector set is continued to be used to associate the process data interface of the current domain with the process data interface of other domains, and the process steps S630 to S670 are repeated until the result of this round of association in the association process converges.

[0121] Among them, based on formula (1), particle regression can be performed when using each second vector to associate multiple interfaces, guiding the optimal target vector in this round:

[0122] vi=(vi+c1×rand()×(pbesti-xi)+c2×rand()×(gbesti-xi)+f(yi)) (1)

[0123] xi=xi+vi(optimal value update)

[0124] i=1,2,3…,N, N is the size of the particle swarm generated by the second vector, i is the particle corresponding to each second vector; rand() is a random number in (0,1); c1 and c2 are learning factors, which can be configured as 2 by default; vi is the association time corresponding to each particle in this round, and the maximum value of vi is Vmax. If vi is greater than Vmax, then vi=Vmax; xi is the particle corresponding to the second vector, f(yi) is the mapping relationship between the current resource utilization and efficiency (target impact factor); yi is the target impact factor, which is used to reflect the impact of yarn resource utilization on computing efficiency and output convergence results.

[0125] Among them, c1×rand()×(pbesti-xi) is the second vector corresponding to the optimal solution of the particle individual, that is, the second vector corresponding to the current round target time, and c2×rand()×(gbesti-xi) is the second vector corresponding to the optimal solution of the particle group, that is, the second vector corresponding to the historical optimal key time. In the process of running the particle swarm optimization algorithm based on yarn resource utilization, based on the historical optimal key time, the optimal solution pbesti of the particle individual and the optimal solution gbesti of the particle group are updated in real time to determine whether the current round of association results converge under the intervention of the target influencing factor, so as to output the optimal target vector.

[0126] The target vector can be recorded so that in subsequent multi-interface association, the combination of target feature field items corresponding to the target vector can be used preferentially for association operations, thereby improving the efficiency of association and data synthesis.

[0127] In an exemplary embodiment, in order to further meet the deviation of time field items across multiple domains and manufacturers, the embodiment of the present disclosure also provides an implementation method for associating and offsetting the second vectors. Generating a particle population according to each second vector may also include:

[0128] Performing time shift on each time field item in the second vector according to a preset method;

[0129] The particle population is generated according to each second vector after time shifting.

[0130] The start time item and the end time item in the time field item may be time-shifted respectively, so that the time interval indicated by the time field item after the time shift includes the time interval indicated by the time field item before the time shift.

[0131] For example, if the start time item in the second vector is "2022-11-16 17:50:43.395" and the end time item is "2022-11-16 17:51:45.373", the start time item can be reduced and the end time item can be increased, so that the time interval between the start time item and the end time item is extended by a preset time, such as 1 minute. Of course, the preset time can also be configured according to actual conditions, and there is no special restriction on this.

[0132] Based on this, when the particle swarm optimization algorithm based on yarn resource utilization is used to update the parameters to be optimized and determine the target vector from the second vector set according to the updated parameters to be optimized, the particle population generated after time offset processing is used for calculation to avoid the time deviation when associating multiple interfaces across manufacturers, thereby realizing cross-domain and cross-manufacturer process data interface association.

[0133] In an exemplary embodiment, the process interface data corresponding to each domain that realizes multi-interface association based on the target vector can also be merged to output global voice call record information so as to perform operation and maintenance processing for cross-domain VoNR services based on the global voice call record information.

[0134] For example, VoNR scene recognition and various abnormal scene localization and localization can be performed based on global voice call record information. Figure 7 FIG. 2 shows various application scenario examples according to exemplary embodiments of the present disclosure. Figure 7 As shown, based on the global voice call record information, cross-domain call record association, business analysis, scenario identification, and scenario analysis can be performed. For details, see Figure 7 .

[0135] Among them, the judgment and analysis of abnormal process nodes can be realized based on the business process logic. Figure 8 The diagram shows an abnormal scenario analysis in an application scenario. When an abnormality occurs, the contextual information of the abnormality can be obtained based on the output global voice call record information, so as to quickly and accurately locate the problem, such as "abnormal scenario-dropped call", and propose solutions to improve the efficiency of operation and maintenance support.

[0136] Fig. 9 The following is a flowchart of the multi-interface association involved in a new air interface carrying a voice VoNR service according to an exemplary embodiment of the present disclosure. Fig. 9 The multi-interface association method for a new air interface carrying a voice VoNR service in an embodiment of the present disclosure is described.

[0137] First, collect multi-domain raw data, which includes at least O-domain data, configuration data, and B-domain data. For details, see Fig. 9 shown.

[0138] Secondly, the multi-domain raw data is preprocessed, and the voice call record information of the current domain is obtained from the preprocessed data. The preprocessing includes one or more of the screening of key process data, marking of key processes, marking of abnormal processes, and data partitioning and storage according to number partitions.

[0139] Next, based on the yarn cluster resources, the voice call record information of the current domain is obtained, and according to the preset key feature fields, the feature field items corresponding to the preset key feature fields are obtained from the voice call record information, and the first vector set (such as NE-IP, billing ID, time, number, etc.) is formed according to the feature field items, and the support count corresponding to the feature field items is determined according to the frequency of occurrence of the feature field items in the voice call record information. Fig.10 A schematic diagram showing a first vector set and support counts corresponding to each feature field item according to an exemplary embodiment of the present disclosure is shown.

[0140] Then, at least one feature field item corresponding to the maximum support count in the first vector set is determined as an intervention factor. Fig.10 , the intervention factors were determined to include "2022-11-16 17:50:43.395, 2022-11-1617:51:45.37 and psbc23bhw.1ab.5091.20221116095043".

[0141] Furthermore, according to the preset support threshold and the support count corresponding to each feature field item, the feature field items in the first vector set are pruned, that is, "iOS / 15.3.1 device manufacturer 1", "asbc7GV400vCwL4knoKXCWeKGz6U" and "5060" are removed and not added to the second vector set.

[0142] Furthermore, based on each intervention factor, the characteristic field items in the pruned first vector set are traversed to obtain a combination of target characteristic field items to determine the second vector set. Fig.11 The second vector set shown in FIG. 1 and each second vector in the second vector set has a corresponding support count (determined according to the traversed feature field items). It is worth noting that Fig.11 Only some of the second vectors are shown, and they are not listed one by one.

[0143] In addition, the second vector can also be updated to the intervention factor, and the feature field items in the first vector set after the pruning process are continued to be traversed based on the second vector, so as to add the obtained combination of target feature field items as a newly added second vector to the second vector set, and the following process is looped until the number of loops meets the set threshold: the newly added second vector is updated to the intervention factor, and the feature field items in the first vector set after the pruning process are continued to be traversed based on the second vector, so as to add the obtained combination of target feature field items as a newly added second vector to the second vector set, and finally the second vector set is outputted = {(2022-11-1617:50:43.395,2022-11-1617:51:45.373,1530*****576,ffffffffffffff ffffffffff0500f1c4),(2022-11-1617:50:43.395,2022-11-1617:51:45.373,psbc23bh w.1ab.5091.20221116095043,ffffffffffffffffffffffff05035ed6),(2022-11-1 617:50:43.395,psbc23bhw.1ab.5091.20221116095043,1530*****576,32198)…}.

[0144] It is worth noting that when performing intra-domain self-association, a VoNR business process interface module can be constructed according to the calling party, called party, call forwarding, roaming type, and end-to-end scenarios (VoNR-VoNR, VoNR-VoLTE, VoNR-different network, VoNR-service number, VoLTE-VoNR, etc.) of the VoNR voice business process. Then, based on the end-to-end VoNR business process interface model, identification and matching are performed according to the arrangement of the calling party, called party, and interface process timing to complete the SIP protocol process association within the IMS domain. Then, based on the matching results, XDR feature bullets are output to achieve synthetic output within the IMS domain based on the VoNR business model and the application requirements of multiple interfaces in the IMS domain, that is, to achieve interface association within the IMS domain based on the time and process relationship in the specification details, and output the second vector set.

[0145] Furthermore, each second vector in the second vector set is used to associate the process data interface of the current domain with the process data interfaces of other domains, and the current round association time of the second vector is determined according to the association result, and the current round association time is updated by a particle swarm optimization algorithm based on yarn resource utilization, and the target vector is determined from the second vector set according to the updated current round target time, so as to realize multi-interface association according to the target vector.

[0146] Finally, the process interface data corresponding to each domain that realizes multi-interface association based on the target vector are merged, and the fusion output result, that is, the global voice call record information, is output, so as to perform operation and maintenance processing on the cross-domain VoNR service based on the global voice call record information, such as VoNR model judgment, EPSFB model judgment, voice 5-4 conversion, abnormal problem location, etc., without special restrictions.

[0147] See also Fig.12 FIG. 1 shows a schematic diagram of an evaluation result of associating a process data interface of a current domain with process data interfaces of other domains by using each second vector in a second vector set according to an exemplary embodiment of the present disclosure. Fig.12 , Taking the voice media process as an example, if the second vector (2022-11-1617:50:43.395,psbc23bhw.1ab.5091.20221116095043,1530*****576,32198) fails to be associated, the time consumption of this round of association is "invalid", and the target time consumption of this round after the target impact factor is updated is "invalid", then the result of this round of association does not converge; and based on the second vector (2022-11-1617:50:43.395,2022-11-16 17:51:45.373,psbc23bhw.1ab.5091.20221116095043,ffffffffffffffffffffffffff05035ed6) The round association time is 10.6min, and the round target time after updating based on the target influence factor is 13.5min. The result of this round of association converges, and the round target time is determined as the historical optimal association time and the particle corresponding to the round target time is taken as the target vector.

[0148] Furthermore, the current round of association time based on the second vector (2022-11-16 17:50:43.395, 2022-11-16 17:51:45.373, 1530*****576, 240e055b20918e45143e8ee2d058556) is 9.5, and the current round of target time based on the target impact factor update is 10.3min, and the current round of target time is less than the historical optimal association time of 13.5min, then the current round of association results converge, and the current round of target time of 10.3min is determined as the historical optimal association time and the particle corresponding to the current round of target time is used as the target vector. By analogy, the optimal target vector is obtained from the second vector set and automatically applied to the next multi-interface data association.

[0149] In the above process, the second vectors in the second vector set are used to associate multiple interfaces, which can solve the multi-process event association of the VoNR business process across domains, manufacturers, platforms and interfaces. The multi-interface association efficiency is high. Based on the output of global voice call list information, the EPSFB of 5G network voice, the 5-4 switching service of VoNR, and the low accuracy of the judgment of the associated scenarios of VoNR, and the inaccurate location information before and after EPSFB fallback and before and after 5-4 switching can be solved. In addition, the rapid positioning and identification of abnormal signaling nodes can be achieved based on the global voice call list information. In summary, the multi-interface association method of the VoNR service carrying voice on the new air interface of the disclosed embodiment provides an important basis for improving operation and maintenance efficiency, and has a very high positive significance for operators to reduce costs and increase efficiency.

[0150] In addition, according to an exemplary embodiment of the present disclosure, a multi-interface association device for a VoNR service carrying voice over a new air interface is also provided, such as Fig.13 As shown, the device 1300 includes:

[0151] A determination module 1310 is configured to construct a first vector set according to the voice call record information of the current domain, and determine at least one as an intervention factor from the feature field items included in the first vector set;

[0152] A first associating module 1320, configured to traverse the feature field items in the first vector set based on the intervention factor, and obtain a combination of target feature field items to determine a second vector set;

[0153] A second associating module 1330, configured to associate the process data interface of the current domain with the process data interfaces of other domains using each second vector in the second vector set, and determine a parameter to be optimized of the second vector according to the association result;

[0154] The association optimization module 1340 is used to update the parameters to be optimized by using a particle swarm optimization algorithm based on yarn resource utilization, and determine a target vector from the second vector set according to the updated parameters to be optimized, so as to realize multi-interface association according to the target vector.

[0155] In an exemplary embodiment of the present disclosure, the determination module 1310 is configured to: obtain the voice call record information of the current domain based on the YARN cluster resources; obtain the feature field items corresponding to the preset key feature fields from the voice call record information according to the preset key feature fields, and form the first vector set according to the feature field items; wherein the support count corresponding to the feature field item is determined according to the frequency of occurrence of the feature field item in the voice call record information.

[0156] In an exemplary embodiment of the present disclosure, the determination module 1310 is further configured to: determine at least one feature field item corresponding to the maximum support count in the first vector set as the intervention factor.

[0157] In an exemplary embodiment of the present disclosure, the first associating module 1320 is configured to:

[0158] The feature field items in the first vector set are pruned according to a preset support threshold and the support count corresponding to each of the feature field items; the feature field items in the first vector set after pruning are traversed based on the intervention factor, and a combination of the intervention factor and each of the traversed feature field items as target feature field items is determined as a second vector; and the second vector set is determined according to each of the second vectors.

[0159] In an exemplary embodiment of the present disclosure, there are multiple intervention factors; the first association module 1320 is configured to: based on the feature field items in the first vector set after traversal and pruning by each intervention factor, determine the second vector as a combination of the intervention factor and each traversed feature field item as the target feature field item; determine the second vector set according to each second vector corresponding to each intervention factor.

[0160] In an exemplary embodiment of the present disclosure, the apparatus 1300 further includes:

[0161] An updating module is used to update the second vector to the intervention factor, and continue to traverse the feature field items in the first vector set after pruning based on the second vector, so as to add the obtained combination of target feature field items as a newly added second vector to the second vector set; and loop the following process until the number of loops meets a set threshold, and output a final second vector set: update the newly added second vector to the intervention factor, and continue to traverse the feature field items in the first vector set after pruning based on the newly added second vector, so as to add the obtained combination of target feature field items as a newly added second vector to the second vector set.

[0162] In an exemplary embodiment of the present disclosure, the second association module 1330 is configured to: respectively use each of the second vectors to associate the process data interface of the current domain with the process data interfaces of other domains; obtain the parameters to be optimized corresponding to each successfully associated second vector, and the parameters to be optimized include the time consumption of this round of association corresponding to the second vector.

[0163] In an exemplary embodiment of the present disclosure, the association optimization module 1340 is configured to:

[0164] Based on the correspondence between the yarn resource utilization and the impact factor, the target impact factor corresponding to the current yarn resource utilization when the process data interface of the current domain is associated with the process data interface of the other domains by using the second vector is obtained; a particle population is generated according to each of the second vectors, and each second vector corresponds to a particle; based on the target impact factor, the current round association time of each particle is updated to obtain the current round target time corresponding to each particle; the current round target time is compared with the historical optimal association time, and the target vector is determined from the particle according to the comparison result.

[0165] In an exemplary embodiment of the present disclosure, the association optimization module 1340 is configured to:

[0166] If the target time of this round is less than the historical optimal association time, it is determined that the association result of this round converges, and the target time of this round is determined as the historical optimal association time, and the particle corresponding to the target time of this round is used as the target vector; if the target time of this round is greater than the historical optimal association time, it is determined that the association result of this round does not converge, the historical optimal association time remains unchanged, and the particle corresponding to the historical optimal association time is used as the target vector.

[0167] In an exemplary embodiment of the present disclosure, the association optimization module 1340 is configured to: perform time shift on the time field item in each of the second vectors according to a preset method; and generate the particle population according to each of the second vectors after the time shift.

[0168] In an exemplary embodiment of the present disclosure, the association optimization module 1340 is configured to: time-shift the start time item and the end time item in the time field item respectively, so that the time interval indicated by the time field item after the time shift includes the time interval indicated by the time field item before the time shift.

[0169] In an exemplary embodiment of the present disclosure, the apparatus 1300 further includes:

[0170] A data processing module is used to collect multi-domain raw data, which includes at least O domain data, configuration data and B domain data; pre-process the multi-domain raw data and obtain the voice call record information of the current domain from the pre-processed data; wherein the pre-processing includes one or more of the screening of key process data, marking of key processes, marking of abnormal processes and data partitioning and storage according to number partitions.

[0171] In an exemplary embodiment of the present disclosure, the apparatus 1300 further includes:

[0172] The result processing module is used to merge the process interface data corresponding to each domain that realizes multi-interface association based on the target vector, and output the global voice call record information; based on the global voice call record information, the cross-domain VoNR service is operated and maintained.

[0173] Since the specific details of each functional module (unit) of the multi-interface association device for the VoNR service carrying voice over the new air interface of the exemplary embodiment of the present disclosure have been described in detail in the invention embodiment of the multi-interface association method for the VoNR service carrying voice over the new air interface above, they will not be repeated here.

[0174] It should be noted that although several modules or units of the multi-interface association device of the VoNR service carrying voice over the new air interface are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0175] In addition, in the exemplary embodiment of the present disclosure, a computer storage medium capable of implementing the above method is also provided. A program product capable of implementing the above method of this specification is stored thereon. In some possible embodiments, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0176] The embodiment of the present disclosure also provides a program product for implementing the above method, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0177] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0178] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0179] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0180] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0181] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided. It will be appreciated by those skilled in the art that various aspects of the present disclosure may be implemented as a system, method, or program product. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which may be collectively referred to herein as a "circuit", "module", or "system".

[0182] Refer to the following Fig.14 1400 according to this embodiment of the present disclosure is described. Fig.14 The electronic device 1400 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0183] like Fig.14 As shown, the electronic device 1400 is in the form of a general computing device. The components of the electronic device 1400 may include, but are not limited to: the at least one processing unit 1410, the at least one storage unit 1420, a bus 1430 connecting different system components (including the storage unit 1420 and the processing unit 1410), and a display unit 1440.

[0184] The storage unit stores program codes, which can be executed by the processing unit 1410, so that the processing unit 1410 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0185] The storage unit 1420 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 1421 and / or a cache storage unit 1422 , and may further include a read-only storage unit (ROM) 1423 .

[0186] The storage unit 1420 may also include a program / utility 1424 having a set (at least one) of program modules 1425, such program modules 1425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0187] Bus 1430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0188] The electronic device 1400 may also communicate with one or more external devices 1500 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1400, and / or communicate with any device that enables the electronic device 1400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 1450. Furthermore, the electronic device 1400 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 1460. As shown, the network adapter 1460 communicates with other modules of the electronic device 1400 via a bus 1430. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0189] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0190] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0191] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A multi-interface association method for a new air interface carrying a voice VoNR service, characterized in that: include: Acquire a feature field item corresponding to a preset key feature field from the voice call record information of the current domain, form a first vector set according to the feature field item, and determine at least one as an intervention factor from the feature field items included in the first vector set; Traversing the feature field items in the first vector set based on the intervention factor, obtaining a combination of target feature field items to determine a second vector set; Associating the process data interface of the current domain with the process data interfaces of other domains by using each second vector in the second vector set, and determining the parameters to be optimized of the second vector according to the association result; Based on the correspondence between the yarn resource utilization and the impact factor, a target impact factor corresponding to the current yarn resource utilization when the process data interface of the current domain is associated with the process data interface of the other domain by using the second vector is obtained, and a particle population is generated according to each of the second vectors, each second vector corresponding to a particle; Based on the target impact factor, the current round association time consumption of each particle is updated to obtain the current round target time consumption corresponding to each particle, and the current round target time consumption is compared with the historical optimal association time consumption, and a target vector is determined from the particle according to the comparison result, so as to realize the multi-interface association between the current domain and other domains according to the target vector; The traversing the feature field items in the first vector set based on the intervention factor to obtain a combination of target feature field items to determine the second vector set includes: Performing pruning processing on the feature field items in the first vector set according to a preset support threshold and a support count corresponding to each of the feature field items; Based on the intervention factor traversing the feature field items in the first vector set after pruning, the intervention factor and each of the traversed feature field items are combined as target feature field items to determine a second vector, so as to determine the second vector set according to each of the second vectors.

2. The method according to claim 1, characterized in that The acquiring a feature field item corresponding to a preset key feature field from the voice call record information of the current domain, and forming a first vector set according to the feature field item, includes: Acquire voice call record information of the current domain based on yarn cluster resources; Wherein, the support count corresponding to the characteristic field item is determined according to the appearance frequency of the characteristic field item in the voice call record information.

3. The method according to claim 2, characterized in that Determining at least one of the feature field items included in the first vector set as an intervention factor includes: At least one feature field item corresponding to the maximum support count in the first vector set is determined as the intervention factor.

4. The method according to claim 1, characterized in that: The number of the intervention factors is multiple; based on each of the intervention factors traversing the feature field items in the first vector set after pruning, the intervention factor and each of the traversed feature field items are used as a combination of target feature field items to determine the second vector; The second vector set is determined according to each of the second vectors corresponding to each of the intervention factors.

5. The method according to claim 1, characterized in that After determining the second vector set according to each of the second vectors, the method further includes: The second vector is updated to the intervention factor, and the feature field items in the first vector set after the pruning process are continuously traversed based on the second vector, so as to add the obtained combination of target feature field items as a newly added second vector to the second vector set; The following process is executed repeatedly until the number of cycles meets the set threshold, and the final second vector set is output: The newly added second vector is updated to the intervention factor, and the feature field items in the first vector set after pruning are continuously traversed based on the newly added second vector, so as to add the obtained combination of target feature field items to the second vector set as the newly added second vector.

6. The method according to claim 1, characterized in that The step of associating the process data interface of the current domain with the process data interfaces of other domains by using each second vector in the second vector set, and determining the parameters to be optimized of the second vector according to the association result, includes: Associating the process data interface of the current domain with the process data interfaces of other domains respectively by using each of the second vectors; The parameters to be optimized corresponding to each successfully associated second vector are obtained, where the parameters to be optimized include the current round of association time consumption corresponding to the second vector.

7. The method according to claim 1, characterized in that The step of comparing the current round target time consumption with the historical optimal association time consumption and determining the target vector from the particle according to the comparison result includes: If the current round target time consumption is less than the historical optimal association time consumption, it is determined that the current round association result converges, and the current round target time consumption is determined as the historical optimal association time consumption and the particle corresponding to the current round target time consumption is used as the target vector; If the current round target time consumption is greater than the historical optimal association time consumption, it is determined that the current round association result does not converge, the historical optimal association time consumption remains unchanged, and the particle corresponding to the historical optimal association time consumption is used as the target vector.

8. The method according to claim 1, characterized in that The generating a particle population according to each of the second vectors comprises: Performing time shift on each time field item in the second vector according to a preset method; The particle population is generated according to each second vector after time shifting.

9. The method according to claim 8, characterized in that The performing time shifting on each time field item in the second vector according to a preset manner includes: The start time item and the end time item in the time field item are respectively time-shifted, so that the time interval indicated by the time field item after the time shift includes the time interval indicated by the time field item before the time shift.

10. The method according to any one of claims 1 to 9, characterized in that Before acquiring a feature field item corresponding to a preset key feature field from the voice call record information of the current domain and forming a first vector set according to the feature field item, the method further includes: Collecting multi-domain raw data, wherein the multi-domain raw data at least includes O-domain data, configuration data, and B-domain data; Preprocessing the multi-domain original data, and obtaining voice call record information of the current domain from the preprocessed data; The preprocessing includes one or more of screening of key process data, marking of key processes, marking of abnormal processes, and partitioning and storing data according to number partitions.

11. The method according to any one of claims 1 to 10, characterized in that After implementing the multi-interface association between the current domain and other domains according to the target vector, the method further includes: Merging the process interface data corresponding to each domain that realizes multi-interface association based on the target vector, and outputting global voice call record information; Based on the global voice call record information, operation and maintenance processing is performed on the cross-domain VoNR service.

12. A multi-interface association device for a VoNR service carrying voice over a new air interface, characterized in that: include: A determination module, configured to obtain a feature field item corresponding to a preset key feature field from the voice call record information of the current domain, form a first vector set according to the feature field item, and determine at least one as an intervention factor from the feature field items included in the first vector set; A first association module, configured to traverse the feature field items in the first vector set based on the intervention factor, and obtain a combination of target feature field items to determine a second vector set; A second associating module, configured to associate the process data interface of the current domain with the process data interfaces of other domains using each second vector in the second vector set, and determine a parameter to be optimized of the second vector according to the association result; Association optimization module for Based on the correspondence between the yarn resource utilization and the impact factor, a target impact factor corresponding to the current yarn resource utilization when the process data interface of the current domain is associated with the process data interface of the other domain by using the second vector is obtained, and a particle population is generated according to each of the second vectors, each second vector corresponding to a particle; Based on the target impact factor, the current round association time consumption of each particle is updated to obtain the current round target time consumption corresponding to each particle, and the current round target time consumption is compared with the historical optimal association time consumption, and a target vector is determined from the particle according to the comparison result to realize multi-interface association according to the target vector; The traversing the feature field items in the first vector set based on the intervention factor to obtain a combination of target feature field items to determine the second vector set includes: Performing pruning processing on the feature field items in the first vector set according to a preset support threshold and a support count corresponding to each of the feature field items; Based on the intervention factor traversing the feature field items in the first vector set after pruning, the intervention factor and each of the traversed feature field items are combined as target feature field items to determine a second vector, so as to determine the second vector set according to each of the second vectors.

13. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 11 when executed by a processor.

14. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 11 by executing the executable instructions.

Images