CN115278531B

CN115278531B - Abnormality detection method, device, equipment and storage medium for voice service

Info

Publication number: CN115278531B
Application number: CN202210844219.4A
Authority: CN
Inventors: 刘喜卿; 周诗雨; 赵振桥; 程新洲; 晁昆
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2022-07-18
Filing date: 2022-07-18
Publication date: 2024-04-09
Anticipated expiration: 2042-07-18
Also published as: CN115278531A

Abstract

The invention provides an abnormality detection method, a device, equipment and a storage medium of voice service, which relate to the field of communication and are used for detecting whether abnormality exists in the voice service so as to ensure the experience quality of a user using the voice service, and comprise the following steps: the voice service abnormality detection device acquires service data of each to-be-detected area in a plurality of to-be-detected areas; the plurality of areas to be detected comprise an area covered by a core network, an area covered by a base station and an area covered by a cell; the service data comprises xDR data of equipment in an area to be detected in a preset time period. Further, the voice service abnormality detection device determines a service index of the voice service in each to-be-detected area according to the service data of each to-be-detected area, and determines that the voice service in the first to-be-detected area is abnormal under the condition that the service index of the voice service in the first to-be-detected area does not meet the preset condition; the first to-be-detected area is any one of a plurality of to-be-detected areas.

Description

Abnormality detection method, device, equipment and storage medium for voice service

Technical Field

The present invention relates to the field of communications, and in particular, to a method, an apparatus, a device, and a storage medium for detecting an abnormality of a voice service.

Background

Voice services are a basic function provided to users by wireless communication networks, and are provided to users from the earliest second generation (2th Generation,2G)/third generation (3th Generation,3G) networks, but as network architecture evolves, an IP multimedia subsystem (IP multimedia subsystem, IMS) is newly introduced to implement a manner of carrying voice services over an IP network, i.e., voice over LTE (VoLTE), from voice services in a circuit switched domain provided by a 2G/3G network, starting from a long term evolution (long time evolution, LTE) mobile communication system.

As the network evolves to a fifth generation (5th Generation,5G) New Radio (NR) network, voice traffic continues in the manner that LTE carries voice traffic over IP networks. Because of the different network architecture, there are two designs for implementing 5G voice services. The first is that the user implements Voice services, i.e. Voice over NR (VoNR), with the IMS system through the access network and the core network of the 5G network. The second is that the voice service falls back from the NR network to the LTE network through an evolved packet system fallback (evolved packet system fallback) solution, and the existing VoLTE system of the LTE network is utilized to provide the voice service to the user.

The voice service is a basic service provided by an operator network, and the perception experience of a user on the voice service is important reference information for evaluating the operator network. Therefore, how to detect whether the voice services of the VoNR and the EPS fallback are abnormal is a basis for guaranteeing the user voice service experience under the network architecture of the 5G independent networking (SA).

Disclosure of Invention

The invention provides a voice service abnormality detection method, device, equipment and storage medium, which are used for detecting whether abnormality exists in voice service or not so as to ensure the experience quality of a user using the voice service.

In order to achieve the above purpose, the invention adopts the following technical scheme:

in a first aspect, a method for detecting abnormality of a voice service is provided, the method comprising: the voice service abnormality detection device acquires service data of each to-be-detected area in a plurality of to-be-detected areas; the plurality of areas to be detected comprise an area covered by a core network, an area covered by a base station and an area covered by a cell; the service data includes call/transaction detail record (call/transaction detail record, xDR) data of a device in an area to be detected for a preset period of time. Further, the abnormality detection device of the voice service determines a service index of the voice service in each region to be detected according to the service data of each region to be detected. Under the condition that the service index of the voice service in the first area to be detected does not meet the preset condition, the voice service abnormality detection device determines that the voice service in the first area to be detected is abnormal; the first to-be-detected area is any one of a plurality of to-be-detected areas.

In the voice service abnormality detection method provided by the invention, the voice service abnormality detection device determines the service index of the voice service in the area to be detected by acquiring the service data in the area to be detected and based on the acquired service data, judges whether the service index meets the preset condition, and determines that the voice service in the area to be detected is abnormal under the condition that the service index does not meet the preset condition. Therefore, the monitoring of the voice service in the area to be detected is realized, and the area with abnormal voice service can be positioned in time.

In one possible design, the method for detecting abnormality of voice service further includes: the voice service abnormality detection device determines a preset threshold value corresponding to a first service index and an index range; the first service index is any one type of service index of voice service in the first area to be detected. Further, the voice service abnormality detection device determines that the voice service corresponding to the first service index in the first to-be-detected area is abnormal under the condition that the first service index and the preset threshold do not meet the preset relation and the first service index is not in the index range. According to the design, the abnormal voice service is further located, follow-up adjustment of equipment related to the abnormal voice service by operation and maintenance personnel is facilitated, and the voice service use experience of a user is guaranteed.

In one possible design, the device for detecting abnormality of a voice service determines an index range corresponding to a first service index, including: the abnormality detection device of the voice service obtains a plurality of historical first service indexes in a first area to be detected in the same time period as a preset time period. Further, the abnormality detection device of the voice service determines the mean value and standard deviation of a plurality of historical first service indexes; and determining an index range corresponding to the first service index, wherein the minimum value of the index range is the difference value between the mean value and the standard deviation, and the maximum value is the sum of the mean value and the standard deviation. The design realizes the basis of detecting whether the service index is abnormal by the abnormality detection device of the voice service so as to ensure the accuracy of abnormality detection.

In one possible design, voice traffic includes new air voice VoNR and evolved packet system fallback EPS fallback. In the case that the voice service is VoNR, the service index comprises the call start and completion rate, the call delay and the call drop rate; under the condition that the voice service is EPS fallback, the service indexes comprise fall-back time delay, call starting and completing rate, call delay and call dropping rate. The voice service suitable for the voice service detection method provided by the invention is realized in the design, and whether the voice service is abnormal or not is determined according to the service index.

In one possible design, the method for detecting abnormality of voice service further includes: the abnormality detection means of the voice service determines a response code for reflecting abnormality of the voice service from the service data of the first area to be detected. Further, the abnormality detection device for the voice service clusters the response codes to obtain an abnormality cause of the first area to be detected, wherein the abnormality cause comprises the response codes and the number of each response code. According to the design, after the abnormality of the area to be detected is determined, how to determine the reason of the abnormality of the area to be detected, so that the operation and maintenance personnel can better solve the abnormality of the voice service.

In a possible design, when the abnormal device of the voice service determines that there are a plurality of first areas to be detected, a third area to be detected having a coverage relationship with a second area to be detected is determined, where the second area to be detected is any one of the plurality of first areas to be detected, and the third area to be detected is one or more of the plurality of first areas to be detected except the second area to be detected. Further, the abnormality detection device of the voice service determines an abnormality solution for solving the voice service in the second to-be-detected area and the voice service in the third to-be-detected area based on the abnormality reason of the second to-be-detected area, the abnormality reason of the third to-be-detected area and the abnormality solution library established in advance; the mapping relation between the abnormal reasons and the abnormal solutions is stored in the abnormal solution library. After determining the reason for the abnormal voice service, the design realizes how to call the abnormal solution for solving the abnormal voice service according to the reason for the abnormal voice service, so that operation and maintenance personnel can quickly solve the abnormal voice service according to the called abnormal solution.

In a second aspect, there is provided an abnormality detection apparatus for a voice service, including an acquisition unit and a determination unit. The acquisition unit is used for acquiring service data of each to-be-detected area in the plurality of to-be-detected areas; the plurality of areas to be detected comprise an area covered by a core network, an area covered by a base station and an area covered by a cell; the service data comprises the call/transaction detail record xDR data of equipment in an area to be detected in a preset time period. The determining unit is used for determining the service index of the voice service in each area to be detected according to the service data of each area to be detected. The determining unit is further configured to determine that the voice service in the first to-be-detected area is abnormal if the service index of the voice service in the first to-be-detected area does not meet the preset condition; the first to-be-detected area is any one of a plurality of to-be-detected areas.

In one possible design, the determining unit is further configured to determine a preset threshold value and an index range corresponding to the first service index; the first service index is any one type of service index of voice service in the first area to be detected. The determining unit is further configured to determine that the voice service corresponding to the first service indicator in the first to-be-detected area is abnormal if the first service indicator and the preset threshold do not satisfy the preset relationship and the first service indicator is not in the indicator range.

In a possible design, the obtaining unit is further configured to obtain a plurality of historical first service indexes in the first to-be-detected area in a period identical to the preset period. The determining unit is further configured to determine a mean value and a standard deviation of the plurality of historical first business indexes. The determining unit is further configured to determine an index range corresponding to the first service index, where a minimum value of the index range is a difference between the mean value and the standard deviation, and a maximum value of the index range is a sum of the mean value and the standard deviation.

In one possible design, voice traffic includes new air voice VoNR and evolved packet system fallback EPS fallback. In the case that the voice service is VoNR, the service index comprises the call start and completion rate, the call delay and the call drop rate; under the condition that the voice service is EPS fallback, the service indexes comprise fall-back time delay, call starting and completing rate, call delay and call dropping rate.

In one possible design, the device for detecting abnormality of voice service further includes a processing unit. The determining unit is further configured to determine a response code for reflecting the voice service abnormality from the service data of the first to-be-detected area. The processing unit is used for clustering the response codes to obtain the abnormal reasons of the first area to be detected, wherein the abnormal reasons comprise the response codes and the number of each type of response codes.

In a possible design, the determining unit is further configured to determine a third to-be-detected area having a coverage relationship with a second to-be-detected area, where the second to-be-detected area is any one of the plurality of first to-be-detected areas, and the third to-be-detected area is one or more of the plurality of first to-be-detected areas except the second to-be-detected area. The determining unit is further configured to determine an anomaly solution for solving the voice service in the second to-be-detected area and the voice service in the third to-be-detected area based on the anomaly cause of the second to-be-detected area, the anomaly cause of the third to-be-detected area, and the pre-established anomaly solution library; the mapping relation between the abnormal reasons and the abnormal solutions is stored in the abnormal solution library.

In a third aspect, there is provided an abnormality detection apparatus of a voice service, the abnormality detection apparatus of a voice service including a memory and a processor; the memory is coupled to the processor for storing computer program code comprising computer instructions which, when executed by the processor, cause the voice traffic anomaly detection device to perform the voice traffic anomaly detection method as in the first aspect.

In a fourth aspect, there is provided a computer-readable storage medium having instructions stored therein that, when executed on an abnormality detection device of a voice service, cause the abnormality detection device of a voice service to perform the abnormality detection method of a voice service as in the first aspect.

Drawings

Fig. 1 is a schematic structural diagram of a communication system according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of a method for detecting abnormality of a voice service according to an embodiment of the present invention;

fig. 3 is a schematic flow chart II of a method for detecting abnormality of a voice service according to an embodiment of the present invention;

fig. 4 is a schematic flow chart III of a method for detecting abnormality of a voice service according to an embodiment of the present invention;

fig. 5 is a schematic flow chart diagram of a method for detecting abnormality of a voice service according to an embodiment of the present invention;

fig. 6 is a flowchart of a method for detecting an abnormality of a voice service according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of an abnormality detection device for voice service according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of an abnormality detection device for voice service according to an embodiment of the present invention;

Fig. 9 is a schematic structural diagram of a voice service abnormality detection device according to a second embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.

In embodiments of the invention, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

In the description of the present invention, "/" means "or" unless otherwise indicated, for example, A/B may mean A or B. "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. Further, "at least one", "a plurality" means two or more. The terms "first," "second," and the like do not limit the number and order of execution, and the terms "first," "second," and the like do not necessarily differ.

Voice services are basic functions provided for users by a wireless communication network, and the mode of carrying voice services through an IP network by LTE is adopted by voice services in the 5G age. Because of the different network architecture, there are two designs for implementing 5G voice services. The first is the VoNR voice service. The second is EPS fallback voice service, which falls back from the NR network to the LTE network, and provides voice service to the user by using the existing VoLTE system of the LTE network. The voice service is used as a basic service provided by an operator network, and the perception of the voice service by a user is an important new reference for evaluating the operator network. Therefore, how to detect whether the voice services of the VoNR and the EPS fallback are abnormal is a basis for guaranteeing the user voice service experience under the 5G SA network architecture.

In order to solve the problems, the invention provides a voice service abnormality detection method, a device, equipment and a storage medium. The voice service abnormality detection device acquires service data of each to-be-detected area in a plurality of to-be-detected areas; the plurality of areas to be detected comprise an area covered by a core network, an area covered by a base station and an area covered by a cell; the service data includes call/transaction detail record (call/transaction detail record, xDR) data of a device in an area to be detected for a preset period of time. Further, the abnormality detection device of the voice service determines a service index of the voice service in each region to be detected according to the service data of each region to be detected. Under the condition that the service index of the voice service in the first area to be detected does not meet the preset condition, the voice service abnormality detection device determines that the voice service in the first area to be detected is abnormal; the first to-be-detected area is any one of a plurality of to-be-detected areas. According to the voice service abnormality detection method provided by the invention, the service index of the voice service in the area to be detected is detected, and the voice service abnormality in the area to be detected is determined under the condition that the service index does not meet the preset condition, so that the monitoring of the voice service in the area to be detected is realized, and the area with the voice service abnormality can be located in time.

Fig. 1 shows a communication system, and the method for detecting an abnormality of a voice service provided in the embodiment of the present invention may be applied to a communication system 10 shown in fig. 1, and is used for detecting whether an abnormality exists in the voice service in the communication system 10. As shown in fig. 1, the communication system 10 includes an abnormality detection device 11 of voice traffic, a core network device 12, a core network device 13, a base station device 121, a base station device 122, and a base station device 131.

The abnormality detection device 11 is connected to the core network device 12, the core network device 13, the base station device 121, the base station device 122, and the base station device 131, respectively. The connection mode between the devices may be wired or wireless, which is not limited in the embodiment of the present invention.

The core network device 12, the core network device 13, the base station device 121, the base station device 122, and the base station device 131 are disposed within a preset area. The core network device 12 is configured to provide services to the base station device 121 and the base station device 122; the core network device 13 is used to provide services for the base station device 131.

As shown in fig. 1, the area covered by the core network device 12 is an area a, and the area covered by the core network device 13 is an area B; the area covered by the base station device 121 is an area C, the area covered by the base station device 122 is an area D, and the area covered by the base station device 131 is an area E; region F is the coverage area of one cell under base station apparatus 121, region G is the coverage area of another cell under base station apparatus 121, region H is the coverage area of one cell under base station apparatus 122, region I is the coverage area of one cell under base station apparatus 131, and region J is the coverage area of another cell under base station apparatus 131.

Wherein, the area A is covered with an area C, an area D, an area F, an area G and an area H; the area B is covered with an area E, an area I and an area J; the area C is covered with an area F and an area G; the area D is covered with an area H; the region E is covered with the regions I and J.

The core network device 12, the core network device 13, the base station device 121, the base station device 122, and the base station device 131 exemplarily shown in fig. 1 do not constitute a limitation on the number of core network devices and the number of base station devices.

The abnormality detection device 11 for voice service may be disposed in a predetermined area or may be disposed outside the predetermined area. The voice service abnormality detection apparatus 11 may be configured to collect xDR data of the core network device 12, the core network device 13, the base station device 121, the base station device 122, the base station device 131, and devices within coverage areas of the devices, that is, collect xDR data of all devices within a preset area, and detect whether the voice service within the preset area is abnormal according to the collected xDR data.

Fig. 2 is a flow diagram illustrating a method of anomaly detection for voice traffic, according to some example embodiments. In some embodiments, the above-described abnormality detection method of voice traffic may be applied to the abnormality detection device 11 of voice traffic in the communication system 10 as shown in fig. 1. Hereinafter, the embodiment of the present invention will be described with reference to the case where the abnormality detection method of a voice service is applied to the abnormality detection device 11 of a voice service.

As shown in fig. 2, the method for detecting abnormality of a voice service according to the embodiment of the present invention includes the following steps S201 to S204.

S201, the abnormality detection device of the voice service acquires service data of each to-be-detected area in a plurality of to-be-detected areas.

The plurality of areas to be detected comprise an area covered by a core network, an area covered by a base station and an area covered by a cell; the service data comprises xDR data of equipment in an area to be detected in a preset time period.

For example, as shown in fig. 1, the areas a-J in the preset area are the above-mentioned plural areas to be detected.

As a possible implementation manner, the abnormality detection device for voice service adopts a deep packet inspection (deep packet inspection, DPI) system to detect and analyze the flow and the packet of the interface of the device in the preset area, and performs filtering control on the flow according to the policy, so as to collect signaling plane and user plane messages, and synthesize xDR data. Further, the abnormality detection device of the voice service gathers the xDR data in each area to be detected according to the area to be detected to which each device belongs in the preset area and the collected xDR data of each device, and obtains the service data of each area to be detected.

It should be noted that, the DPI system is divided into a three-layer architecture, where the acquisition layer and the decoding layer are responsible for data acquisition, traffic analysis, and log synthesis, and generally, the data is stored in the database of the decoding layer in the manner of xDR data recording. The application layer mainly completes calculation, arrangement and statistics of xDR data, reasonably organizes and stores the data, and presents the data.

As another possible implementation manner, the abnormal detection device of the voice service detects and analyzes the flow and the message of the equipment interface in each to-be-detected area by adopting the DPI system for each to-be-detected area in the plurality of to-be-detected areas, performs filtering control on the flow according to a policy, collects signaling plane and user plane messages, synthesizes xDR data, and gathers the xDR data in each to-be-detected area to obtain the service data of each to-be-detected area.

It should be noted that the preset time period may be a time period with any time length in one day, and in general, the abnormality detection device for voice service selects a time period with a time length of 15 minutes as the preset time period, which is not specifically limited in the embodiment of the present invention.

S202, the abnormality detection device of the voice service determines a service index of the voice service in each area to be detected according to the service data of each area to be detected.

In the embodiment of the present invention, the voice service detected by the voice service abnormality detection device may be VoNR or EPS fallback.

In the case that the voice service is VoNR, the service indexes of the voice service include an originating call completing rate, a call delay, and a dropped call rate.

Under the condition that the voice service is EPS fallback, the service indexes comprise fall-back time delay, call starting and completing rate, call delay and call dropping rate.

As a possible implementation manner, the abnormality detection device of the voice service determines service data related to the service index according to the service data of the to-be-detected area and from the service data of the to-be-detected area, and calculates the service index of the voice service in the to-be-detected area.

In an exemplary case where the call start rate service index of the VoNR voice service is determined, the abnormality detection apparatus for the voice service first determines the service data of the VoNR voice service from the service data of the area to be detected. Further, the voice service abnormality detection device determines the number of times of call starting and call starting requests from the service data of the VoNR voice service, and further determines the call starting and call starting rate according to the following formula.

The voice service abnormality detection device determines the number of times of origination call connection and the total number of times of origination call requests based on the fields described in the xDR data.

Wherein the number of times of the initial call is the number of times of the initial call and the number of times of voice initial call recognition of the user reason. By field determination, it can be: the field "Interface" =mw, and "Service Type" =0, and "Procedure Type" =5, and "call_side" =0, and "alerting_time" notequal to the number of xDR data of full F in the xDR data.

The total number of origination requests is: the field "Interface" =mw, and "Service Type" =0, and "Procedure Type" =5, and "call_side" =0.

In an exemplary case of determining a call delay service index of a VoNR voice service, the abnormality detection apparatus of the voice service first determines service data of the VoNR voice service from service data of an area to be detected. Further, the voice service abnormality detection device determines the time interval from the sending of the INVITE message by the calling subscriber to the receiving of the ringing message sent by the called subscriber in each session from the service data of the VoNR voice service, and calculates the average value of the time intervals in all sessions as the call delay service index.

In an exemplary case where the drop rate service index of the VoNR voice service is determined, the abnormality detection means of the voice service first determines the service data of the VoNR voice service from the service data of the area to be detected. Further, the voice service abnormality detection device determines the call drop times and the response times from the service data of the VoNR voice service, and further determines the call drop rate according to the following formula.

Wherein the number of dropped calls is the number of times the border session controller (session border controller, SBC) receives a policy and charging rules function (policy and charging rule function, PCRF) sends an Abort Session Request (ASR) with a media type of voice, and the Abort reason (Abort Cause) in ASR is not included in the switch from data packet domain to circuit domain ("PS to CS Handover").

The abnormality detection device of the voice service determines the call drop times through xDR data as follows: "Interface" =rx, and "abort_type" =0, and "abort_cause" ++ PS to CS Handover ", and" media_type "=0.

The response times are the sum of the initial call response times and the final call response times.

In an exemplary case of determining a fallback service index of an EPS fallback voice service, the voice service anomaly detection device first determines service data of the EPS fallback voice service from service data of a to-be-detected area. Further, the abnormality detection device of the voice service determines a time interval between the sending of the INVITE message by the calling side interface Gm and the sending of the INVITE message by the calling side interface Mw in each session from the service data of the EPS fallback voice service, and calculates an average value of the time intervals in all sessions as a fallback time delay service index.

It should be noted that, under the condition of determining the call start rate, the call delay and the call drop rate service index of the EPS fallback voice service, the specific implementation manner may refer to the implementation manner of determining the call start rate, the call delay and the call drop rate service index in the VoNR voice service, and only the service data of the VoNR voice service is required to be replaced by the service data of the EPS fallback voice service, so that the call start rate, the call delay and the call drop rate service index of the EPS fallback voice service can be determined.

S203, the voice service abnormality detection device determines whether the service index of the voice service in the first to-be-detected area meets the preset condition.

The first to-be-detected area is any one of a plurality of to-be-detected areas.

As a possible implementation manner, the abnormality detection device for voice service detects a service index of the voice service in the first to-be-detected area according to a preset condition, and determines whether the service index of the voice service in the first to-be-detected area meets the preset condition.

It should be noted that, the preset condition may be set in advance in the abnormality detection device of the voice service by an operator of the abnormality detection device of the voice service, where the preset condition may be to determine whether the service index of the voice service and the corresponding preset threshold value satisfy a preset relationship.

The preset relation between the service index of the voice service and the preset threshold is that the call start and completion rate is larger than or equal to the first threshold, the call delay is smaller than or equal to the second threshold, the call drop rate is smaller than or equal to the third threshold, and the fall-back delay is smaller than or equal to the fourth threshold.

The first threshold, the second threshold, the third threshold, and the fourth threshold may be preset by an operator of the abnormality detection device for voice service, which is not particularly limited in the embodiment of the present invention.

As an example, the abnormality detection device for voice service determines that the originating call completing rate of the VoNR voice service is 99.45%, the call delay is 3471 milliseconds (ms), and the dropped call rate is 0.07% in the first area to be detected in the above step S202; the fall-back time delay in the EPS fallback voice service is 2100ms, the call starting and completing rate is 99.1%, the call time delay is 4500ms, and the drop-call rate is 0.05%. The preset threshold is shown in table 1 below:

table 1: preset threshold corresponding to business index

Under the condition that whether the preset conditions are the preset relations between the service indexes and the corresponding preset thresholds are met or not, the voice service abnormality detection device judges that the starting call completing rate and the call delay in the VoNR voice service meet the preset relations between the corresponding preset thresholds, and the call dropping rate does not meet the preset relations between the corresponding preset thresholds; the abnormality detection device of the voice service judges that the call start-up rate, the call delay and the call drop rate in the EPS fallback voice service meet the preset relation between the corresponding preset threshold values, and the fall-back delay is not full of the preset relation between the corresponding preset threshold values. Further, the abnormality detection device of the voice service determines that the drop rate service index in the VoNR voice service and the drop time delay in the EPS fallback voice service do not meet the preset condition.

S204, the voice service abnormality detection device determines that the voice service in the first to-be-detected area is abnormal under the condition that the service index of the voice service in the first to-be-detected area does not meet the preset condition.

For example, the abnormality detection device for voice service determines in the above step S203 that the drop rate of the VoNR voice service in the first to-be-detected area does not meet the preset condition, and the drop delay of the EPS fallback voice service does not meet the preset condition, and determines that the voice service in the first to-be-detected area is abnormal.

In one design, in order to more accurately determine whether the service index of the voice service is abnormal, as shown in fig. 3, the method for detecting the abnormality of the voice service provided in the embodiment of the invention further includes S301-S304.

S301, the abnormality detection device of the voice service determines a preset threshold value corresponding to the first service index and an index range.

The first service index is any one type of service index of voice service in the first area to be detected.

It should be noted that, according to the description in step S203 of the above embodiment, the types of the service indexes include the originating call completing rate, the call delay and the dropped call rate in the VoNR voice service; the method comprises the steps of fallback time delay, call starting and completing rate, call time delay and call dropping rate in EPS fallback voice service.

As one possible implementation manner, the abnormality detection device for the voice service determines a first service index, and invokes a preset threshold value and an index range corresponding to the first service index based on the first service index.

The index range corresponding to the first service index may be stored in the voice service abnormality detection device in advance, or may be dynamically determined according to the historical service data. The determining, by the abnormality detection device for voice service, the index range according to the historical service data may refer to the following description of the embodiment of the present invention, which is not repeated here.

S302, the abnormality detection device of the voice service determines whether the first service index and a preset threshold meet a preset relation.

It should be noted that, the abnormality detection device for voice service determines whether the first service index and the preset threshold meet the preset relationship, which may refer to the record in step S203 in the embodiment of the present invention, and will not be described herein.

S303, the abnormality detection device of the voice service determines whether the first service index is in the index range.

As one possible implementation manner, the abnormality detection device for the voice service determines whether the first service index is greater than the minimum value of the index range and less than the maximum value of the index range. In the case where the first service index is greater than the minimum value of the index range and less than the maximum value of the index range, the abnormality detection means of the voice service determines that the first service index is within the index range.

S304, the voice service abnormality detection device determines that the voice service corresponding to the first service index in the first area to be detected is abnormal under the condition that the first service index and the preset threshold value do not meet the preset relation and the first service index is not in the index range.

It can be understood that the voice service abnormality detection device determines that the voice service corresponding to the first service index in the first to-be-detected area is abnormal under the condition that the first service index and the preset threshold do not meet the preset relation and are not in the index range, so that the situation that the threshold is unreasonable to set or the index range is unreasonable to cause misjudgment of the voice service abnormality can be avoided, and the accuracy of detecting the abnormality of the voice service is improved.

In some embodiments, the voice service abnormality detection device performs threshold detection and index range detection in parallel for the first service index, determines that the first service index is abnormal when one of the detection modes detects the first service index abnormality, further determines that the voice service corresponding to the first service index is abnormal, and does not perform subsequent detection.

It can be understood that when an abnormality is detected in one detection mode, the abnormality of the voice service is determined, and the operation of the subsequent detection algorithm is stopped, so that the computing resources of the abnormality detection device of the voice service can be saved.

In one design, in order to make the index range for detecting the first service index more reasonable, as shown in fig. 4, the method for detecting the abnormality of the voice service provided in the embodiment of the present invention further includes S401-S403.

S401, the abnormality detection device of the voice service acquires a plurality of historical first service indexes in a first area to be detected in the same time period as a preset time period.

As a possible implementation manner, the abnormality detection device of the voice service determines a period in which the preset period is located. Further, the voice service abnormality detection device retrieves the historical service data, determines data of the historical service data in a time period where a preset time period is located, and determines a plurality of historical first service indexes in the time period based on the historical service data in the time period.

It should be noted that, the implementation manner of determining the historical first service index by the voice service abnormality detection device according to the historical service data may refer to the implementation manner of determining the first service index according to the service data in the foregoing embodiment of the present invention, which is not described herein.

For example, if the preset time period is 15 minutes and the time period of the preset time period is 14:00-14:15 in one day, the abnormality detection device for voice service invokes the service data in the first to-be-detected area of 14:00-14:15 in the previous 3 days, and determines the first service index of each day, that is, the plurality of historical first service indexes, based on the obtained service data.

If the first abnormal traffic index is determined in the previous 3 days, the first abnormal traffic index is continued until 3 normal samples are taken.

S402, the abnormality detection device of the voice service determines the mean value and the standard deviation of a plurality of historical first service indexes.

For example, taking 3 historical first business indexes as examples, the 3 historical first business indexes are z1, z2 and z3 respectively.

The abnormality detection means of the voice service determines that the average value is m=1/3 (z1+z2+z3);

the standard deviation is u=sqrt (((z 1-m)/(2+ (z 2-m)/(2+ (z 3-m)/(2))/3).

S403, the abnormality detection device of the voice service determines an index range corresponding to the first service index.

The minimum value of the index range is the difference value between the mean value and the standard deviation, and the maximum value is the sum of the mean value and the standard deviation.

As one possible implementation manner, the abnormality detection device for the voice service determines, after determining the mean value and the standard deviation of the plurality of historical first service indexes, a difference value and a sum of the mean value and the standard deviation, takes the determined difference value as the minimum value of the index range, and takes the determined sum as the maximum value of the index range.

The abnormality detection device for voice service, for example, has a mean value of m and a standard deviation of u for the plurality of historical first service indicators determined in step S402.

The abnormality detection device of the voice service determines that the index range of the first service index Z is [ m-u, m+u ], and determines that the first service index Z is normal when the first service index Z is within the index range; when Z < m-u or Z > m+u, determining that the first business index Z is abnormal.

In one design, in order to facilitate an operator to timely check the cause of the occurrence of the abnormality after the occurrence of the abnormality, as shown in fig. 5, the abnormality detection method for voice service provided by the embodiment of the present invention further includes S501-S502.

S501, the voice service abnormality detection device determines a response code for reflecting the voice service abnormality from service data of a first to-be-detected area.

The format of the response code is as follows: type, response code, and state description. For example: temporary acknowledgement (type), 100 (response code), and try are in process (state description).

As one possible implementation manner, the abnormality detection device for voice service determines signaling including a response code from service data of a first area to be detected, and determines a response code existing in the first area to be detected based on the response code reflecting abnormality of the voice service.

It should be noted that the response code for reflecting the voice service abnormality includes: 400bad request error request, 401unauthorized, 402 request payment to pay, 406 non-acceptable, 407proxy authentication required agent authentication required, 408request timeout, 410go away, 420bad expansion, 421extension required require expansion, 481call/transaction does not exist call/transaction not present, 482loop detected loop, 483 toman hops too many, 484address incomplete address incomplete, 485 advanced ambiguity, 491request pending request, 493 unrecognizable, 500server internal error server internal error, 501 non advanced ineligible, 502bad gateway, 503service unavailable service invalid, 504server timeout, 505version unsupported, 513message too large message too big.

S502, clustering response codes by the voice service abnormality detection device to obtain an abnormality reason of the first area to be detected.

Wherein the abnormality cause includes response codes, and the number of each of the response codes.

As a possible implementation manner, the voice service abnormality detection device counts response codes for reflecting the voice service abnormality in the first to-be-detected area, determines the number of each response code, and obtains the abnormality reason of the first to-be-detected area.

Illustratively, the abnormality detecting device for voice service determines that the response codes included in the first area to be detected are 408, 410, 483, and 504, and the number of response codes 408 is 32, the number of response codes 410 is 55, the number of response codes 483 is 43, and the number of response codes 504 is 57. The abnormality detection means of the voice traffic determines that the abnormality sources of the first to-be-detected area are 32 pieces 408, 55 pieces 410, 43 pieces 483, and 57 pieces 504.

In one design, in order to enable an operation and maintenance person to repair an abnormality existing in a voice service in time when the abnormality detection device for the voice service determines that a plurality of first areas to be detected exist, as shown in fig. 6, the abnormality detection method for the voice service provided by the embodiment of the invention further includes S601-S603.

S601, the abnormality detection device of the voice service determines a third to-be-detected area with a coverage relation with the second to-be-detected area.

The second to-be-detected area is any one of the first to-be-detected areas, and the third to-be-detected area is one or more of the first to-be-detected areas except the second to-be-detected area.

As one possible implementation manner, the abnormality detection device for voice service determines a second to-be-detected area and a third to-be-detected area having a coverage relationship from among the plurality of first to-be-detected areas.

The coverage relationship between the areas is complete coverage or is completely covered.

For example, referring to fig. 1, if the first to-be-detected area is the area C, the area F, and the area D, the abnormality detection device for the voice service determines that the second to-be-detected area and the third to-be-detected area are the area C and the area F.

S602, the abnormality detection device of the voice service determines the abnormality reasons of the second to-be-detected area and the third to-be-detected area.

The specific implementation manner of determining the reason for the abnormality of the second to-be-detected area and the third to-be-detected area by the abnormality detection device for the voice service may refer to the implementation manner of determining the reason for the abnormality of the first to-be-detected area in the above embodiment of the present invention, and will not be described herein.

S603, the voice service abnormality detection device determines abnormality solutions for solving the voice service in the second to-be-detected area and the voice service in the third to-be-detected area based on the abnormality reason of the second to-be-detected area, the abnormality reason of the third to-be-detected area and the pre-established abnormality solution library.

The mapping relation between the abnormal reasons and the abnormal solutions is stored in the abnormal solution library.

As a possible implementation manner, the abnormality detection device for the voice service inputs a pre-established abnormality solution library according to the abnormality reasons of the second to-be-detected area and the abnormality reasons of the third to-be-detected area, so as to obtain abnormality solutions for the abnormality reasons of the second to-be-detected area and the third to-be-detected area, namely, abnormality solutions for solving the voice service in the second to-be-detected area and the voice service in the third to-be-detected area.

The abnormality solution library is pre-established by an operator of the abnormality detection device of the voice service and stored in the abnormality detection device of the voice service, and the mapping relationship between the abnormality cause and the abnormality solution is exemplified in the following table 2.

Table 2: mapping relation between abnormality cause and abnormality solution

/>

In some embodiments, if the abnormality detection device of the voice service fails to determine a solution from the abnormality solution library, notifying an operation and maintenance personnel to generate a solution for the abnormality cause, and after the abnormality is resolved, storing the mapping relationship between the abnormality cause and the solution in the abnormality solution library, and updating the abnormality solution library, so that the abnormality in the voice service can be resolved quickly in case of facing the same abnormality cause again later.

According to the voice service abnormality detection method provided by the invention, the service index of the voice service in the area to be detected is detected, and the voice service abnormality in the area to be detected is determined under the condition that the service index does not meet the preset condition, so that the monitoring of the voice service in the area to be detected is realized, and the area with the voice service abnormality can be located in time.

The foregoing description of the solution provided by the embodiments of the present invention has been mainly presented in terms of a method. To achieve the above functions, it includes corresponding hardware structures and/or software modules that perform the respective functions. Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The embodiment of the invention can divide the functional modules of the user equipment according to the method example, for example, each functional module can be divided corresponding to each function, and two or more functions can be integrated in one processing module. The integrated modules may be implemented in hardware or in software functional modules. Optionally, the division of the modules in the embodiment of the present invention is schematic, which is merely a logic function division, and other division manners may be implemented in practice.

Fig. 7 is a schematic structural diagram of an abnormality detection device for voice service according to an embodiment of the present invention. The abnormality detection device of the reserved service is used for executing the abnormality detection method of the voice service. As shown in fig. 7, the abnormality detection device 70 for voice service includes an acquisition unit 701 and a determination unit 702.

An acquiring unit 701, configured to acquire service data of each of a plurality of areas to be detected, where the plurality of areas to be detected include an area covered by a core network, an area covered by a base station, and an area covered by a cell; the service data comprises the call/transaction detail record xDR data of equipment in an area to be detected in a preset time period. For example, as shown in fig. 2, the acquisition unit 701 may be used to perform S201.

A determining unit 702, configured to determine a service index of the voice service in each to-be-detected area according to the service data of each to-be-detected area. For example, as shown in fig. 2, the determination unit 702 may be used to perform S202.

The determining unit 702 is further configured to determine that the voice service in the first to-be-detected area is abnormal if the service index of the voice service in the first to-be-detected area does not meet the preset condition; the first to-be-detected area is any one of a plurality of to-be-detected areas. For example, as shown in fig. 2, the determination unit 702 may be used to perform S204.

Optionally, as shown in fig. 7, in the device 70 for detecting an abnormality of a voice service provided in the embodiment of the present invention, the determining unit 702 is further configured to determine a preset threshold value and an index range corresponding to a first service index; the first service index is any one type of service index of voice service in the first area to be detected. For example, as shown in fig. 3, the determination unit 702 may be used to perform S301.

The determining unit 702 is further configured to determine that the voice service corresponding to the first service indicator in the first area to be detected is abnormal if the first service indicator and the preset threshold do not satisfy the preset relationship and the first service indicator is not in the indicator range. For example, as shown in fig. 3, the determining unit 702 may be used to perform S304.

Optionally, as shown in fig. 7, in the device 70 for detecting an abnormality of a voice service provided in the embodiment of the present invention, the obtaining unit 701 is further configured to obtain a plurality of historical first service indicators in a first area to be detected in a period that is the same as a preset period. For example, as shown in fig. 4, the acquisition unit 701 may be used to perform S401.

The determining unit 702 is further configured to determine a mean value and a standard deviation of the plurality of historical first business indexes. For example, as shown in fig. 4, the determination unit 702 may be used to perform S402.

The determining unit 702 is further configured to determine an index range corresponding to the first service index, where a minimum value of the index range is a difference between the mean value and the standard deviation, and a maximum value of the index range is a sum of the mean value and the standard deviation. For example, as shown in fig. 4, the determination unit 702 may be used to perform S403.

Optionally, as shown in fig. 7, in the abnormality detection device 70 for a voice service provided in the embodiment of the present invention, the voice service includes a new air interface voice VoNR and an evolved packet system fallback EPS fallback. In the case of the voice service being the VoNR, the service index includes an originating call completing rate, a call delay, and a dropped call rate. Under the condition that the voice service is EPS fallback, the service indexes comprise fall-back time delay, call starting and completing rate, call delay and call dropping rate.

Optionally, as shown in fig. 7, the device 70 for detecting an abnormality of a voice service provided in the embodiment of the present invention further includes a processing unit 703.

The determining unit 702 is further configured to determine a response code for reflecting the voice service abnormality from the service data of the first to-be-detected area. For example, as shown in fig. 5, the determination unit 702 may be used to perform S501.

The processing unit 703 is configured to cluster the response codes to obtain an abnormality cause of the first to-be-detected area, where the abnormality cause includes the response codes and the number of each of the response codes. For example, as shown in fig. 5, the processing unit 703 may be used to perform S502.

Optionally, as shown in fig. 7, in the device 70 for detecting an abnormality of a voice service according to the embodiment of the present invention, the determining unit 702 is further configured to determine a third to-be-detected area having a coverage relationship with a second to-be-detected area, where the second to-be-detected area is any one of the plurality of first to-be-detected areas, and the third to-be-detected area is one or more of the plurality of first to-be-detected areas except the second to-be-detected area. For example, as shown in fig. 6, the determination unit 702 may be used to perform S601.

The determining unit 702 is further configured to determine an anomaly solution for resolving the voice service in the second to-be-detected area and the voice service in the third to-be-detected area based on the anomaly cause of the second to-be-detected area, the anomaly cause of the third to-be-detected area, and a pre-established anomaly solution library; the mapping relation between the abnormal reasons and the abnormal solutions is stored in the abnormal solution library. For example, as shown in fig. 6, the determination unit 702 may be used to perform S602.

In the case of implementing the functions of the integrated modules in the form of hardware, the embodiment of the present invention provides a possible structural schematic diagram of an abnormality detection device for a voice service. The abnormality detection apparatus of a voice service is used for executing the abnormality detection method of a voice service executed by the abnormality detection device of a voice service in the above-described embodiment. As shown in fig. 8, the abnormality detection device 80 for voice traffic includes a processor 801, a memory 802, and a bus 803. The processor 801 and the memory 802 may be connected by a bus 803.

The processor 801 is a control center of the abnormality detection device for voice traffic, and may be one processor or a collective name of a plurality of processing elements. For example, the processor 801 may be a general-purpose central processing unit (central processing unit, CPU), or may be another general-purpose processor. Wherein the general purpose processor may be a microprocessor or any conventional processor or the like.

As one example, processor 801 may include one or more CPUs, such as CPU 0 and CPU 1 shown in fig. 8.

Memory 802 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), magnetic disk storage or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

As a possible implementation, the memory 802 may exist separately from the processor 801, and the memory 802 may be connected to the processor 801 through the bus 803 for storing instructions or program code. When the processor 801 calls and executes the instructions or the program codes stored in the memory 802, the abnormality detection method for voice service provided by the embodiment of the present invention can be implemented.

In another possible implementation, the memory 802 may also be integrated with the processor 801.

Bus 803 may be an industry standard architecture (Industry Standard Architecture, ISA) bus, a peripheral component interconnect (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in fig. 8, but not only one bus or one type of bus.

Note that the structure shown in fig. 8 does not constitute a limitation of the abnormality detection device 80 for the voice service. In addition to the components shown in fig. 8, the abnormality detection device 80 of the voice service may include more or less components than those shown in fig. 8, or may combine some components, or may be arranged in different components.

As an example, in connection with fig. 7, the acquisition unit 701, the determination unit 702, and the processing unit 703 in the abnormality detection device 70 for voice traffic realize the same functions as those of the processor 801 in fig. 8.

Optionally, as shown in fig. 8, the device for detecting an abnormality of a voice service provided in the embodiment of the present invention may further include a communication interface 804.

A communication interface 804 for connecting with other devices via a communication network. The communication network may be an ethernet, a radio access network, a wireless local area network (wireless local area networks, WLAN), etc. The communication interface 804 may include an acquisition unit for receiving data, and a transmission unit for transmitting data.

In one design, in the device for detecting an abnormality of a voice service provided by the embodiment of the present invention, the communication interface may also be integrated in the processor.

Fig. 9 shows another hardware configuration of the abnormality detection apparatus for voice traffic in the embodiment of the present invention. As shown in fig. 9, the abnormality detection device 90 for voice traffic may include a processor 901 and a communication interface 902. The processor 901 is coupled to a communication interface 902.

The function of the processor 901 may be as described above with reference to the processor 801. The processor 901 also has a memory function, and the function of the memory 802 can be referred to.

The communication interface 902 is used to provide data to the processor 901. The communication interface 902 may be an internal interface of the voice service abnormality detection device, or an external interface of the voice service abnormality detection device (corresponding to the communication interface 804).

It is to be noted that the structure shown in fig. 9 does not constitute a limitation of the abnormality detection device of the voice service, and the abnormality detection device 90 of the voice service may include more or less parts than those shown in fig. 9, or may combine some parts, or may be arranged in different parts.

From the above description of embodiments, it will be apparent to those skilled in the art that the foregoing functional unit divisions are merely illustrative for convenience and brevity of description. In practical applications, the above-mentioned function allocation may be performed by different functional units, i.e. the internal structure of the device is divided into different functional units, as needed, to perform all or part of the functions described above. The specific working processes of the above-described systems, devices and units may refer to the corresponding processes in the foregoing method embodiments, which are not described herein.

The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, when the computer executes the instructions, the computer executes each step in the method flow shown in the method embodiment.

An embodiment of the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the method for detecting anomalies in voice traffic in the method embodiment described above.

The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: electrical connections having one or more wires, portable computer diskette, hard disk. Random access Memory (Random Access Memory, RAM), read-Only Memory (ROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), registers, hard disk, optical fiber, portable compact disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any other form of computer-readable storage medium suitable for use by a person or persons of skill in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuit, ASIC). In embodiments of the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

Since the apparatus, the device computer readable storage medium, and the computer program product in the embodiments of the present invention can be applied to the above-mentioned method, the technical effects that can be obtained by the apparatus, the device computer readable storage medium, and the computer program product can also refer to the above-mentioned method embodiments, and the embodiments of the present invention are not described herein again.

The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the present invention is not limited thereto, but any changes or substitutions within the technical scope of the present invention should be covered by the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for detecting anomalies in voice traffic, the method comprising:

acquiring service data of each to-be-detected area in a plurality of to-be-detected areas; the plurality of areas to be detected comprise an area covered by a core network, an area covered by a base station and an area covered by a cell; the service data comprises call/transaction detail record xDR data of equipment in a region to be detected in a preset time period;

determining service indexes of voice service in each region to be detected according to the service data of each region to be detected; the voice service comprises a new air interface voice VoNR and an evolution packet system fallback EPS fallback, the service index comprises an initial call completing rate, a call delay and a call drop rate under the condition that the voice service is VoNR, and the service index comprises the fallback delay, the initial call completing rate, the call delay and the call drop rate under the condition that the voice service is EPS fallback;

Under the condition that the service index of the voice service in the first area to be detected does not meet the preset condition, determining that the voice service in the first area to be detected is abnormal; the first to-be-detected area is any one of the plurality of to-be-detected areas;

determining a response code for reflecting voice service abnormality from the service data of the first region to be detected;

clustering the response codes to obtain an abnormal reason of the first area to be detected, wherein the abnormal reason comprises the response codes and the number of each response code;

determining a third to-be-detected area with a coverage relation with a second to-be-detected area under the condition that a plurality of first to-be-detected areas exist, wherein the second to-be-detected area is any one of the plurality of first to-be-detected areas, and the third to-be-detected area is one or more of the plurality of first to-be-detected areas except the second to-be-detected area;

determining an abnormality solution for solving the voice service in the second to-be-detected area and the voice service in the third to-be-detected area based on the abnormality reason of the second to-be-detected area, the abnormality reason of the third to-be-detected area and a pre-established abnormality solution library; and the mapping relation between the abnormal reasons and the abnormal solutions is stored in the abnormal solution library.

2. The abnormality detection method according to claim 1, characterized in that the method further comprises:

determining a preset threshold value and an index range corresponding to the first service index; the first service index is any one type of service index of voice service in the first region to be detected;

and determining that the voice service corresponding to the first service index in the first area to be detected is abnormal under the condition that the first service index and the preset threshold value do not meet the preset relation and the first service index is not in the index range.

3. The anomaly detection method of claim 2, wherein determining an index range corresponding to the first business index comprises:

acquiring a plurality of historical first business indexes in the first area to be detected in the same time period as the preset time period;

determining a mean value and a standard deviation of the plurality of historical first business indexes;

and determining an index range corresponding to the first service index, wherein the minimum value of the index range is the difference value between the mean value and the standard deviation, and the maximum value is the sum of the mean value and the standard deviation.

4. The abnormality detection device of the voice service is characterized by comprising an acquisition unit, a determination unit and a processing unit;

The acquisition unit is used for acquiring service data of each to-be-detected area in the plurality of to-be-detected areas; the plurality of areas to be detected comprise an area covered by a core network, an area covered by a base station and an area covered by a cell; the service data comprises call/transaction detail record xDR data of equipment in a region to be detected in a preset time period;

the determining unit is used for determining the service index of the voice service in each region to be detected according to the service data of each region to be detected; the voice service comprises a new air interface voice VoNR and an evolution packet system fallback EPS fallback, the service index comprises an initial call completing rate, a call delay and a call drop rate under the condition that the voice service is VoNR, and the service index comprises the fallback delay, the initial call completing rate, the call delay and the call drop rate under the condition that the voice service is EPS fallback;

the determining unit is further configured to determine that the voice service in the first to-be-detected area is abnormal if the service index of the voice service in the first to-be-detected area does not meet a preset condition; the first to-be-detected area is any one of the plurality of to-be-detected areas;

The determining unit is further configured to determine a response code for reflecting abnormality of the voice service from the service data of the first to-be-detected area;

the processing unit is used for clustering the response codes to obtain an abnormal reason of the first area to be detected, wherein the abnormal reason comprises the response codes and the number of each response code;

in the case that there are a plurality of first areas to be detected, the determining unit is further configured to determine a third area to be detected that has a coverage relationship with a second area to be detected, where the second area to be detected is any one of the plurality of first areas to be detected, and the third area to be detected is one or more of the plurality of first areas to be detected except the second area to be detected;

the determining unit is further configured to determine an anomaly solution for solving the voice service in the second to-be-detected area and the voice service in the third to-be-detected area based on the anomaly cause of the second to-be-detected area, the anomaly cause of the third to-be-detected area, and a pre-established anomaly solution library; and the mapping relation between the abnormal reasons and the abnormal solutions is stored in the abnormal solution library.

5. The anomaly detection apparatus according to claim 4, wherein the determining unit is further configured to determine a preset threshold value and an index range corresponding to the first traffic index; the first service index is any one type of service index of voice service in the first region to be detected;

the determining unit is further configured to determine that a voice service corresponding to the first service indicator in the first to-be-detected area is abnormal if the first service indicator and the preset threshold do not satisfy a preset relationship, and the first service indicator is not in the indicator range.

6. The abnormality detection apparatus according to claim 5, wherein said acquisition unit is further configured to acquire a plurality of historical first traffic indexes in said first area to be detected within the same period as said preset period;

the determining unit is further configured to determine a mean value and a standard deviation of the plurality of historical first service indexes;

the determining unit is further configured to determine an index range corresponding to the first service index, where a minimum value of the index range is a difference value between the mean value and the standard deviation, and a maximum value of the index range is a sum of the mean value and the standard deviation.

7. An abnormality detection apparatus for voice service, characterized by comprising a memory and a processor;

the memory is coupled to the processor;

the memory is used for storing computer program codes, and the computer program codes comprise computer instructions;

the abnormality detection apparatus for a voice service performs the abnormality detection method for a voice service according to any one of claims 1 to 3 when the processor executes the computer instructions.

8. A computer-readable storage medium having instructions stored therein, which when run on a voice service abnormality detection device, cause the voice service abnormality detection device to perform the voice service abnormality detection method according to any one of claims 1-3.