CN111212376B

CN111212376B - Method, apparatus, device and medium for correlating real-time location and voice quality results

Info

Publication number: CN111212376B
Application number: CN201811392550.7A
Authority: CN
Inventors: 付永振; 魏春来; 李飞; 曹雷雷; 王靖; 张利春
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Hebei Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Hebei Co Ltd
Priority date: 2018-11-21
Filing date: 2018-11-21
Publication date: 2021-06-11
Anticipated expiration: 2038-11-21
Also published as: CN111212376A

Abstract

The invention discloses a method, a device, equipment and a medium for correlating real-time position and voice quality results. The method comprises the following steps: associating the call ticket information and the user real-time position information by using the corresponding relation between the RX interface information and the GX interface information; performing quality evaluation on the voice media stream of the call to obtain voice fragment quality evaluation results of a plurality of preset durations, and associating the call ticket information with the voice fragment quality evaluation results of the plurality of preset durations; sequencing the voice fragment quality evaluation results of a plurality of preset durations belonging to the same call ticket information according to a time sequence; and according to the time sequence, associating the real-time position information of the users belonging to the same call ticket information with the voice fragment quality evaluation results of a plurality of preset durations. According to the technical scheme provided by the embodiment of the invention, the real-time position information of the user and the call voice quality evaluation result can be associated aiming at the whole call process, and reliable data support is provided for mobile network optimization.

Description

Method, apparatus, device and medium for correlating real-time location and voice quality results

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a method, an apparatus, a device, and a medium for associating real-time location and voice quality results.

Background

In the mobile communication network technology, there are two main ways for acquiring location information: measurement Report (MR) location techniques and signaling resolution.

First, MR refers to a mobile terminal periodically reporting information such as downlink signal strength and quality of a cell in which the mobile terminal is located to a base station in a measurement report manner at a certain time interval on a traffic channel through a control channel. The base station uploads the downlink information reported by the terminal and the uplink physical information collected by the base station to the base station controller, and the downlink information and the uplink physical information are collected and counted by the base station controller. All MR-based methods, the core algorithm of which is localization, currently mainly include the following MR localization methods: 1. application program (APP) positioning method: by analyzing the S1-U port signaling, the longitude and latitude reported by the user are extracted, and the user position information is obtained; the method is accurate in calibration, but accurate positioning can be achieved only outdoors, and the number of available sample points is limited because the longitude and latitude of most of APP of people are encrypted and cannot be directly obtained through analysis. The SI-U port may establish a tunnel between a GateWay (GateWay, GW) and an Evolved Node B (eNodeB) device to transmit user data traffic (i.e., user plane data).

2. Timing Advance (TA) + Angle of Arrival (AOA) location: firstly, the distance between a base station and a User Equipment (UE) can be estimated according to the TA value in the MR, and secondly, the location information of the terminal can be obtained according to the angle information of the AOA. The method has obvious influence on positioning accuracy by environment and is accurate in positioning in open areas; but in more areas of tall buildings the positioning accuracy will be poor.

3. And (3) triangulation positioning: and calculating a central point by combining the MR field intensity information and the network element parameter information and utilizing a triangle or polygon formed by the main service cell and the two or more strongest adjacent cells, and performing field intensity weighted offset to obtain positioning. However, the current MR data has a large percentage of incomplete neighbor information, so the three-point positioning method has poor implementability, low precision, large positioning error and obvious influence of inter-station distance.

4. The positioning method based on the fingerprint database comprises the following steps: i.e. feature matching methods, from database positioning. It requires the initial creation of a fingerprint database in which discrete signal strengths and location coordinates are stored. Since the multipath propagation of the signal has dependence on the environment, the multipath characteristics of the channel are different at different positions, and very strong specificity is presented. The position fingerprint positioning technology effectively utilizes the multipath effect and combines the multipath characteristics and the position information. Since the multipath influence of the channel has uniqueness in the same position point, the multipath characteristics can be used as fingerprints in the database. And the point to be measured acquires the wireless signal sent by the access point in the same environment, matches the received wireless signal strength with the fingerprint in the database, and finds out the most similar result for positioning. The positioning accuracy of the position fingerprint is related to factors such as the size of the fingerprint, a matching algorithm and the like.

However, the MR positioning technique described above relies on software, and the base station collects and counts the reported measurement reports, and in practical application, the following defects exist:

(1) the total acquisition cost of massive MR data is extremely high, so that the existing network mostly adopts a region and time interval alternate acquisition mode to reduce the cost, and the data integrity is poor and the requirement of total analysis cannot be met;

(2) most MR data are processed aiming at applications, and the data of a gathering level cannot meet the requirement of acquiring position information in the whole call process.

Secondly, regarding signaling analysis, the signaling information is a control instruction in the communication system, which can guide the terminals, the switching system and the transmission system to operate cooperatively, establish a temporary communication channel between the specified terminals, and maintain the normal operation of the network itself. The core of the signaling-based method is the analysis and association of the position information reported in the signaling. Currently, there are several following Long-Term Evolution Voice over Evolution (VoLTE) network location signaling analyses:

1. S1-MME port signaling resolution: an S1AP application protocol of an S1 interface, which is mainly responsible for System Architecture Evolution (SAE) bearer Management, initial context transmission, paging, S1UE context release, UE Mobility Management in LTE _ ACTIVE state, Network Attached Storage (NAS) signaling transmission of UE and Mobility Entity Management (MME) quality inspection, and the like, wherein the UE Mobility Management in LTE _ ACTIVE state is responsible for switching between MME/Serving SAE-GW (MME/Serving SAE-GW), and realizes Evolved Node B (Evolved Node B, enode bs) switching through an S1 interface; switching between Radio Access Networks (RANs) is realized through an S1 interface between different Radio Access Technologies (RATs), signaling analysis is performed on the interface, and location information acquisition of VoLTE calls can be realized.

2. And RX port signaling analysis: and analyzing by using the position reporting information in the policy charging control, and acquiring the position information of the VoLTE call.

3. And (3) GX port signaling analysis: in the specification of GX (3GPP TS 29.212), it is specifically specified that PCRF may request PCEF through RAR/CCA message, and report the location of the cell of the user when the location of the radio access network of the user changes. The specification further states that certain user events must be reported unconditionally. Whether a change in location must be reported is determined by operator policy.

However, the main drawbacks of the above signaling resolution are:

(1) based on the analysis association efficiency and method of the signaling big data, the position information analyzed by the signaling of the S1-MME port has limited acquisition accuracy and low reliability of position information data.

(2) At present, no RX and GX port signaling analysis correlation mature application for acquiring the position information in the whole call process exists.

Disclosure of Invention

The embodiment of the invention provides a method, a device, equipment and a medium for correlating real-time position and voice quality results, which can

In a first aspect, an embodiment of the present invention provides a method for associating real-time location information with a call voice quality assessment result, where the method includes:

associating the call ticket information of the RX interface message with the user real-time position information of the GX interface message by using the corresponding relation between the RX interface message and the GX interface message;

performing quality evaluation on the voice media stream of the call to obtain voice fragment quality evaluation results of a plurality of preset durations, and associating the call ticket information with the voice fragment quality evaluation results of the plurality of preset durations to obtain the call ticket information to which the voice fragment quality evaluation results of the plurality of preset durations belong;

sequencing the voice fragment quality evaluation results of a plurality of preset durations belonging to the same call ticket information according to a time sequence;

and according to the time sequence, associating the user real-time position information belonging to the same call ticket information with each of the voice fragment quality evaluation results with a plurality of preset durations so as to associate the user real-time position information with the call voice quality evaluation result.

According to the method for correlating the real-time position information with the call voice quality evaluation result, the method further comprises the following steps:

and continuously capturing user position information from a credit control request CCR message of the Gx interface to acquire the real-time position information of the user.

According to the method for associating the real-time position information with the call voice quality evaluation result, the user position information is captured from the credit control request CCR message of the Gx interface continuously to obtain the user real-time position information, and the method comprises the following steps:

when a call is initiated and when GX interface information carries updating, a policy charging execution unit (PCEF) sends a credit control update request (CCR-U) information for reporting the position change of a user to a policy charging control unit (PCRF) to the PCRF;

and continuously capturing user position information from the CCR-U message to acquire the real-time position information of the user.

According to the correlation method of the real-time position information and the call voice quality evaluation result, the corresponding relation between the RX interface message and the GX interface message comprises the following steps:

and the corresponding relation between the time and the IP quadruple of the RX interface message and the time and the IP quadruple of the GX interface message.

According to the method for associating the real-time position information with the call voice quality evaluation result, the quality of the call voice media stream is evaluated to obtain the quality evaluation results of the voice segments with a plurality of preset durations, and the method comprises the following steps:

encapsulating the voice media stream of the call in a real-time transport protocol (RTP) packet;

combining the RTP packets according to the preset time length to obtain a plurality of voice fragments with the preset time length;

and carrying out quality evaluation on the voice segments with the preset time length to obtain the voice segment quality evaluation results with the preset time length.

According to the correlation method of the real-time position information and the call voice quality evaluation result, the quality evaluation is carried out on the voice segments with the preset time length to obtain the voice segment quality evaluation results with the preset time length, and the method comprises the following steps:

and performing quality evaluation on the voice segments with the preset time length by using a deep neural network algorithm, a key word spectrum matching algorithm and/or a decision tree algorithm to obtain the voice segment quality evaluation results with the preset time length.

and collecting RTP code stream in the RTP packet, analyzing the RTP code stream according to an address resolution protocol, and acquiring the time and IP quadruplet of the SGi interface.

According to the method for associating the real-time position information with the call voice quality evaluation result, the call ticket information and the voice fragment quality evaluation results with the preset duration are associated to obtain the call ticket information to which the voice fragment quality evaluation results with the preset duration belong, and the method comprises the following steps:

and associating the call ticket information and the voice fragment quality evaluation results of the plurality of preset durations based on the time and IP quadruplet of the SGi interface to obtain the call ticket information to which the voice fragment quality evaluation results of the plurality of preset durations belong.

In a second aspect, an embodiment of the present invention provides an apparatus for associating real-time location information with a call voice quality evaluation result, where the apparatus includes:

the first association module is used for associating the call ticket information of the RX interface message with the user real-time position information of the GX interface message by using a corresponding relationship between the RX interface message and the GX interface message;

the second correlation module is used for carrying out quality evaluation on the voice media stream of the call to obtain voice fragment quality evaluation results with a plurality of preset durations, and correlating the call ticket information with the voice fragment quality evaluation results with the plurality of preset durations to obtain the call ticket information to which the voice fragment quality evaluation results with the plurality of preset durations belong;

the sequencing module is used for sequencing the voice fragment quality evaluation results of the plurality of preset durations belonging to the same call ticket information according to a time sequence;

and the third association module is used for associating the user real-time position information belonging to the same call ticket information with each of the voice fragment quality evaluation results with the preset duration according to a time sequence so as to associate the user real-time position information with the call voice quality evaluation results.

The device for correlating the real-time position information with the call voice quality evaluation result further comprises:

and the capturing module is used for continuously capturing the user position information from the credit control request CCR message of the Gx interface so as to acquire the real-time user position information.

According to the device for correlating the real-time position information with the call voice quality evaluation result, the capturing module is specifically used for:

when the call is initiated and when the GX interface message carries update, a policy charging enforcement unit (PCEF) sends a credit control update request (CCR-U) message for reporting the position change of the user to a policy charging control unit (PCRF) to the PCRF;

According to the device for correlating the real-time position information with the call voice quality evaluation result, the first correlation module is specifically configured to:

and associating the call ticket information of the RX interface message and the user real-time position information of the GX interface message by utilizing the corresponding relation between the time and the IP quadruple of the RX interface message and the time and the IP quadruple of the GX interface message.

According to the device for correlating the real-time position information with the call voice quality evaluation result, the second correlation module is specifically configured to:

combining the RTP packets according to a preset time length to obtain a plurality of voice fragments with the preset time length;

and performing quality evaluation on the voice segments with the preset time lengths to obtain the quality evaluation results of the voice segments with the preset time lengths.

and performing quality evaluation on the voice segments with the preset time lengths by utilizing a deep neural network algorithm, a key word spectrum matching algorithm and/or a decision tree algorithm to obtain the voice segment quality evaluation results with the preset time lengths.

and collecting RTP code stream in the RTP packet, analyzing the RTP code stream according to an address resolution protocol, and acquiring the time and IP four-tuple of the SGi interface.

According to the device for correlating the real-time position information with the call voice quality evaluation result, the second correlation module is specifically used for:

and associating the call ticket information with the voice fragment quality evaluation results of the plurality of preset durations based on the time and IP quadruplet of the SGi interface to obtain the call ticket information to which the voice fragment quality evaluation results of the plurality of preset durations belong.

In a third aspect, an embodiment of the present invention provides an apparatus for associating real-time location information with a call voice quality evaluation result, where the apparatus includes: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method of the first aspect as in the above embodiments.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which computer program instructions are stored, which, when executed by a processor, implement the method of the first aspect in the above implementation manner.

The method, the device, the equipment and the medium for associating the real-time position and the voice quality result, provided by the embodiment of the invention, can associate the real-time position information of the user with the call voice quality evaluation result aiming at the whole call process, and provide reliable data support for mobile network optimization.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a flowchart illustrating a method for associating real-time location information with a call voice quality evaluation result according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram illustrating an apparatus for associating real-time location information with a call voice quality evaluation result according to an embodiment of the present invention;

fig. 3 shows a flow diagram of acquiring real-time location information of a user by VoLTE according to an embodiment of the present invention;

fig. 4 shows a flow diagram of signaling resolution and association according to an embodiment of the invention;

fig. 5 is a schematic diagram illustrating an association of RX interface messages and GX interface messages according to an embodiment of the present invention;

FIG. 6 is a flow diagram illustrating a segmented speech quality assessment in accordance with an embodiment of the present invention;

fig. 7 is a schematic diagram illustrating a process of sorting a plurality of speech segment quality evaluation results belonging to the same call ticket information according to a time sequence according to an embodiment of the present invention;

FIG. 8 is a diagram illustrating the correlation of user real-time location information and speech quality assessment results according to an embodiment of the present invention;

fig. 9 is a block diagram illustrating an exemplary hardware architecture of a device for associating real-time location information with a call voice quality evaluation result according to an embodiment of the present invention.

Detailed Description

Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

For convenience of description, the technical terms and their meanings that may be referred to herein are first listed below, and it is to be understood that these technical terms are known in the art.

<P-CSCF>

The Proxy-Call Session Control function (P-CSCF) is a unified entry point for an IP Multimedia Subsystem (IMS) visited network. All session messages initiated and terminated by the IMS terminal pass through the P-CSCF.

<PCEF>

A Policy and Charging Enforcement Function (PCEF) configured to detect a traffic data flow, and acquire and implement a service-based control and Charging Policy from the PCRF.

<PCRF>

A Policy and Charging control Function (PCRF), which formulates and dynamically issues a control and Charging Policy to the PCEF according to the service characteristics and the user attributes.

<AF>

An Application Function (AF) entity interacts with the PCRF through an RX interface to provide the PCRF with relevant information of upper-layer service applications.

< RX interface >

The RX interface (RX interface for short) is an interface between the PCRF and the P-CSCF/Session Border Controller (SBC).

< GX interface >

The GX interface (abbreviated as the GX interface) is an interface between the PCRF and the PCEF, the PCRF provides or deletes the service policy rules to the PCEF through the GX interface, and the PCEF reports the event report to the PCRF through the GX interface. The GX interface may be used for charging control and policy control.

< Gm interface >

The Gm interface is the interface between the UE and the P-CSCF, and is primarily responsible for registration and session control.

< Call Ticket >

When a call passes through each interface, a call record can be formed, and the record is called a call ticket. For example, when a call passes through the Gm interface, a call ticket describing call signaling may be formed on the Gm interface; when a call passes through the SGi interface, a call ticket describing a call media stream can be formed on the SGi interface. The SGi interface may be used to establish a tunnel and transmit user plane data. The call ticket information mainly comprises the following query contents: serial number, subscriber identification, calling number, called number, start time, end time, duration of call, nature of call, rate, cost, discount, etc.

Based on the above, an embodiment of the present invention may provide a method for associating real-time location information with a call voice quality evaluation result, and referring to fig. 1, fig. 1 shows a flowchart of a method 100 for associating real-time location information with a call voice quality evaluation result according to an embodiment of the present invention, where the method includes:

s110, associating the call ticket information of the RX interface message and the user real-time position information of the GX interface message by using the corresponding relation between the RX interface message and the GX interface message;

s120, carrying out quality evaluation on the voice media stream of the call to obtain voice fragment quality evaluation results with a plurality of preset durations, and associating the call ticket information with the voice fragment quality evaluation results with the plurality of preset durations to obtain the call ticket information to which the voice fragment quality evaluation results with the plurality of preset durations belong;

s130, sorting the voice fragment quality evaluation results of a plurality of preset durations belonging to the same call ticket information according to a time sequence;

and S140, associating the user real-time position information belonging to the same call ticket information with each of the voice fragment quality evaluation results with a plurality of preset durations according to the time sequence so as to associate the user real-time position information with the call voice quality evaluation result.

By using the scheme provided by the invention, the call ticket information and the user real-time position information are associated, and then the call ticket information and the voice fragment quality evaluation result are associated, so that the user real-time position information and the call voice quality evaluation result are associated, and reliable data support is provided for mobile network optimization.

Referring to fig. 2, fig. 2 is a schematic structural diagram illustrating an apparatus 200 for associating real-time location information with a call voice quality evaluation result according to an embodiment of the present invention, where the apparatus includes:

a first associating module 210, configured to associate, by using a corresponding relationship between an RX interface message and a GX interface message, call ticket information of the RX interface message and user real-time location information of the GX interface message;

the second association module 220 is configured to perform quality evaluation on the voice media stream of the call to obtain voice fragment quality evaluation results of multiple predetermined durations, and associate the call ticket information with the voice fragment quality evaluation results of the multiple predetermined durations to obtain call ticket information to which the voice fragment quality evaluation results of the multiple predetermined durations belong;

the sorting module 230 is configured to sort the voice fragment quality evaluation results of multiple predetermined durations belonging to the same call ticket information according to a time sequence;

and the third associating module 240 is configured to associate the user real-time location information belonging to the same call ticket information with each of the voice segment quality evaluation results of a plurality of predetermined durations according to the time sequence, so as to associate the user real-time location information with the call voice quality evaluation result.

By utilizing the scheme provided by the invention, the call ticket information and the user real-time position information are associated through the first association module, and then the call ticket information and the voice fragment quality evaluation result are associated through the second association module, so that the user real-time position information and the call voice quality evaluation result are associated, and reliable data support is provided for mobile network optimization.

Fig. 3 shows a flow diagram of acquiring real-time location information of a user by VoLTE according to an embodiment of the present invention. As an example, a VoLTE user calls a VoLTE, 2G or 3G user, and when the calling user initiates a call attached to Long Term Evolution (LTE), the following procedure is performed:

1. P-CSCF receives invite request corresponding to voice/video call;

2. the P-CSCF initiates a Diameter AAR (AA-Request, AAR) Request to the PCRF, the Request is mainly used for establishing a proprietary bearer, meanwhile, a Request message carries a Specific-Action feature Value Pair (AVP), and the content of the AVP is filled as 'ACCESS _ NETWORK _ INFO _ REPORT', which indicates that the PCRF needs to REPORT the ACCESS location information of the user. Meanwhile, the AAR request includes Required-Access-Info AVP, which is filled as USER _ LOCATION (0), and indicates that the P-CSCF subscribes the LOCATION information to the PCRF, it should be noted that the LOCATION information reporting request is implemented by the subsequent PCRF requesting the PCEF to report the LOCATION CHANGE of the USER (that is, the RAR/CCA message carries an Event-Trigger-LOCATION _ CHANGE (13) parameter);

3. the PCRF returns a Diameter AAA (AA-Answer, AAA) response to the P-CSCF. The response message carries the access Type of the user, such as 3G or 4G network attributes like GERAN/UTRAN-FDD/UTRAN-TDD/E-UTRAN-FDD/E-UTRAN-TDD, etc., through "IP-CAN-Type" or "RAT-Type", but there is no specific cell identification information. The IMS network cannot implement a special location-related policy only according to the access type, where the AAA message does not usually carry user location information;

4. the PCRF sends a Diameter RAR Request (Re-Auth-Request, RAR) to the PCEF, indicates that the PCEF needs to report the LOCATION information and requests to report the LOCATION CHANGE of the user (namely, an Event-Trigger is carried in the RAR/CCA message as a parameter UER _ LOCATION _ CHANGE (13));

5. the PCEF returns a Diameter RAA response (Re-Auth-Answer, RAA) to the PCRF as a response to the Diameter RAR request;

6. the PCEF interacts with an access network to obtain user access position information, wherein the user access position information generally comprises a global cell identifier (CGI), a Service Area Identifier (SAI) or a Routing Area Identifier (RAI);

7. after a user ue (o) calls, in a short time (usually hundred milliseconds) when the P-CSCF sends an AAR message to the PCRF in step 2, the PCEF (combined with the P-GW) sends a first Credit Control Update request (CCR-U) to the PCRF, and reports location information when the call is initiated.

8. The PCRF stores the position information in local and returns a CCA-Update (simply called CCA-U) response to the PCEF; when a call is initiated and when a GX interface carries out updating, repeatedly sending a credit control update request CCR-U request to a PCRF by the PCEF in the step 7 and returning a CCA-U response to the PCEF by the PCRF in the step 8, and reporting the position information of a user (the position after X2 and S1 switching in the network) in real time through the interaction, wherein the CCR-U message is used for reporting the position change of the user to the PCRF;

9. to bearer validation and modification.

According to the steps from step 1 to step 9, the position information of the whole call process based on the signaling of the RX interface and the GX interface is obtained and associated with the application, and the specific steps and modes are as follows:

< analysis and association of RX, GX interface Signaling >

The RX and GX port signaling analysis and association according to the embodiment of the present invention is specifically described below with reference to fig. 4, and fig. 4 shows a flow diagram of the signaling analysis and association according to the embodiment of the present invention.

First, the AAR message of the RX interface is parsed: after receiving a Session Initiation Protocol (SIP) call attempt message invitation (invite) of a VoLTE user, a Gm interface triggers a call flow including an AAR message at an RX interface by a pcsc f or an SBC, and applies and reserves a dedicated bearer of the VoLTE user, and starts a charging policy, wherein the AAR message is mainly used for transmitting information such as charging and media parameters, and preparing for establishing the dedicated bearer.

Secondly, analyzing the CCR message of the GX interface: the charging strategy information is utilized to lead out a GX interface message process, and the CCR message is used to continuously capture the user position information, thereby realizing the tracking, slicing and analysis of the user real-time position information, wherein the CCR message carries the user specific position information and reports the position information change of the user to the PCRF.

Thirdly, associating messages of the RX interface and the GX interface: and associating the call ticket information and the user real-time position information by using the time and IP quadruplet corresponding relation.

Specifically, the call ticket is associated and the position information is obtained by analyzing by using the corresponding relation between the time and the IP quadruple of the RX interface and the time and the IP quadruple of the GX interface. The IP quadruplet is a source IP address, a destination IP address, a source IP port and a destination IP port.

As an example, referring to fig. 5, fig. 5 shows a schematic diagram of RX interface message and GX interface message association according to an embodiment of the present invention.

Specifically, the PCRF and an IP quadruple (i.e., an IP address and port information) of the user are utilized, wherein the IP quadruple is on the bottom layer of the PCRF, the call ticket information of the RX interface and the real-time location information of the GX interface are associated, and the user identity information of the RX interface is filled into the GX interface, so as to obtain the real-time (time point) location information containing the call and the user identity.

The user identity information of the RX interface may include an International Mobile Subscriber identity Number (IMSI) and a phone Number, and the location information of the GX interface may include a Tracking Area Code (TAC), an E-UTRAN Cell Identifier (ECI), and the like.

In addition, the IMSI of the RX interface is a flag for distinguishing a mobile Subscriber, and is stored in a Subscriber Identity Module (SIM) card, and can be used for distinguishing valid information of the mobile Subscriber.

The TAC of the GX interface is used to define a tracking area code to which a cell belongs, and one tracking area may cover one or more cells.

The ECI of the GX interface is used to identify cells within a Public Land Mobile Network (PLMN) domain.

By associating the subscriber identity information of the RX interface with the location information of the GX port, real-time location information including the call and subscriber identity, such as shown in fig. 3, can be obtained. Besides the time and IP quadruplet, the real-time location information containing the call and the user identity also comprises the IMSI and the telephone number of the RX port, and the TAC and the ECI of the GX port.

Through the process, the full association of the call ticket information and the user real-time reported position information can be realized, so that the tracking of the real-time position of the call is realized.

< evaluation flow of segmented Speech quality >

The embodiment of the present invention can provide a voice quality evaluation flow of segments having a predetermined time length such as 8 s.

As an example, referring to fig. 6, fig. 6 shows a schematic flow chart of the segmentation speech quality evaluation of the embodiment of the present invention, and the flow chart includes the following contents:

first, in VoLTE calls, a voice media stream may be encapsulated in a Real Time Transport Protocol (RTP) packet payload with a Time length such as 20ms (milliseconds) (voiced segments) and such as 160ms (silence frames).

And secondly, collecting an RTP code stream, analyzing the RTP code stream according to an address resolution protocol, and acquiring the time and IP four-tuple of an SGi interface. For example, Ethernet (Ethernet)/Internet Protocol (IP)/Datagram Protocol (UDP)/RTP/Adaptive Multi-Rate (AMR) information may be parsed.

Thirdly, when the segmentation analysis is carried out, whether the packet is lost or not is detected according to the packet header information of the RTP. And if the packet loss occurs, performing corresponding packet loss compensation, wherein the packet loss refers to the loss of the communication data packet. And if no packet loss occurs, no packet loss compensation is performed.

Fourthly, according to the AMR packet header information, resolving is carried out according to an Adaptive Multi-Rate Narrow-Band coding (AMR-NB)/Adaptive Multi-Rate Wide-Band coding (AMR-WB) voice decoding algorithm.

Fifth, several 20ms and 160ms RTP packets (including the compensation packet) are combined to form a plurality of fragmented voices of a predetermined duration, such as 8 s. It should be noted, however, that each group may not be exactly 8s due to the presence of the silence frames, with an error within ± 140 ms.

Sixthly, the acoustic features are obtained by digital signal processing after combination, and a series of time domain and frequency domain transformation and processing are mainly performed, for example, the common preprocessing flow is as follows: pre-emphasis, framing, windowing, Fast Fourier Transform (FFT), first order difference, and second order difference to obtain 39-dimensional Mel Frequency Cepstrum Coefficients (MFCC) characteristics, Discrete Cosine Transform (DCT), and the like.

And the evaluation results of Mean Opinion Score (MOS), single pass, intermittent and swallow word slice of the voice quality are calculated by using methods such as a deep neural network algorithm, keyword matching, decision tree and the like.

The neural network is a machine learning mode, the deep neural network is an evolved neural network, the number of hidden layers is large, the algorithm is optimized for multiple times, and the application range on artificial intelligence is wide; the key word matching is a technology on speech recognition, and is to capture a specific word by comparing and matching the characteristics of speech in time domain and frequency domain; a decision tree is a predictive model that represents a mapping between object attributes and object values, with each node in the tree representing an object, and each diverging path representing a possible attribute value, and each leaf node corresponding to the value of the object represented by the path traversed from the root node to the leaf node. Decision trees in data mining are a frequently used technique that can be used to analyze data and also to make predictions.

< result of evaluating call ticket information and voice quality of association >

As an example, the voice segment quality evaluation result is associated through an IP address, a User Datagram Protocol (UDP) port number (i.e., an IP quadruplet) and a sequence number (i.e., time), and finally a plurality of 8s (seconds) segmented voice quality evaluation results of one call are obtained, so that the association between the call ticket information and the voice segment quality evaluation result is realized, and it should be noted that the time of the last segmented result may be less than 8 s.

And then, sequencing the voice fragment quality evaluation results of a plurality of preset durations belonging to the same call ticket information according to a time sequence.

As an example, referring to fig. 7, fig. 7 is a schematic diagram illustrating that a plurality of speech segment quality evaluation results belonging to the same call ticket information are sorted according to a time sequence according to an embodiment of the present invention.

The quality evaluation results of a plurality of voice segments belonging to the same call ticket information, for example, the segment 1, the segment 2, the segment 3, and the segment 4 belonging to the same call ticket information shown in fig. 7, are sorted according to the time sequence, so as to obtain the quality evaluation results of a plurality of voice segments belonging to the same call ticket information sorted according to the time sequence shown in fig. 7.

< associated user real-time location information and Voice quality assessment result >

And associating the call ticket information with the segmented voice quality evaluation result by utilizing the corresponding relation between the time of a sending end and the time of a receiving end of the SGi interface and the IP four-tuple, and backfilling the corresponding user real-time position information in association with each 8-second result according to a time axis.

The associated backfill process is as follows: and associating corresponding messages of the RX port and the GX port by using the PCRF and the IP address and the port information of the user, and filling the user identity information of the RX port into the GX port to obtain real-time (time point) position information containing the calling and the user identity.

As an example, referring to fig. 8, fig. 8 shows a schematic diagram of associating user real-time location information with a voice quality assessment result according to an embodiment of the present invention.

And associating the segmented voice quality evaluation result with the real-time position information by using the time and the user identity information to obtain a segmented voice quality evaluation result containing the real-time position information:

in fig. 8, the user real-time location information belonging to the same call ticket information and the voice segment quality evaluation results of a plurality of predetermined time durations (for example, segment 1, segment 2, segment 3, and segment 4) are shown, and each of the plurality of segmented voice quality evaluation results is associated with the real-time location information including the call and the user identity according to a time sequence.

For example, the voice quality evaluation results of segment 1 and segment 2 are associated with cell a, and the voice quality evaluation results of segment 3 and segment 4 are associated with cell B, so as to obtain a segmented voice quality evaluation result containing real-time location information.

In summary, the invention adopts GX and RX interface signaling correlation analysis to obtain the real-time position, and obtains the voice quality through RTP data stream, and finally realizes the correlation between the user real-time position and the voice quality.

Therefore, through the process, the purpose of obtaining the call real-time position and the voice quality evaluation result is achieved, and various analysis applications can be developed based on the result.

In addition, the method for associating the real-time location information with the call voice quality evaluation result according to the embodiment of the present invention described in conjunction with fig. 1 may be implemented by an apparatus for associating the real-time location information with the call voice quality evaluation result. Fig. 9 is a schematic diagram illustrating a hardware structure of an apparatus for associating real-time location information with a result of estimating a speech quality provided by an embodiment of the present invention.

The apparatus for correlating real-time location information with call voice quality assessment results may include a processor 1001 and a memory 1002 having stored thereon computer program instructions.

Fig. 9 is a block diagram illustrating an exemplary hardware architecture of a device for associating real-time location information with a call voice quality evaluation result according to an embodiment of the present invention. As shown in fig. 9, computing device 1000 includes input device 1001, input interface 1002, processor 1003, memory 1004, output interface 1005, and output device 1006.

The input interface 1002, the processor 1003, the memory 1004, and the output interface 1005 are connected to each other via a bus 1010, and the input device 1001 and the output device 1006 are connected to the bus 1010 via the input interface 1002 and the output interface 1005, respectively, and further connected to other components of the computing device 1000.

Specifically, the input device 1001 receives input information from the outside and transmits the input information to the processor 1003 via the input interface 1002; the processor 1003 processes the input information based on computer-executable instructions stored in the memory 1004 to generate output information, stores the output information in the memory 1004 temporarily or permanently, and then transmits the output information to the output device 1006 through the output interface 1005; output device 1006 outputs the output information external to computing device 1000 for use by a user.

The computing device 1000 may perform the steps of the communication method described herein.

Processor 1003 may be one or more Central Processing Units (CPUs). In the case where the processor 1003 is one CPU, the CPU may be a single-core CPU or a multi-core CPU.

The memory 1004 may be, but is not limited to, one or more of Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM), compact disc read only memory (CD-ROM), a hard disk, and the like. The memory 1004 is used for storing program codes.

It is understood that, in the embodiment of the present application, the functions of any one or all of the first to third association modules provided in fig. 2 may be implemented by using the central processor 1003 shown in fig. 9.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the processes or functions described in accordance with embodiments of the invention, to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

All parts of the specification are described in a progressive manner, and the same and similar parts among the various embodiments can be mutually referred to, and each embodiment is mainly described in different points from other embodiments. In particular, as to the apparatus and system embodiments, since they are substantially similar to the method embodiments, the description is relatively simple and reference may be made to the description of the method embodiments in relevant places.

Claims

1. A method for associating real-time position information with a call voice quality evaluation result is characterized by comprising the following steps:

associating the call ticket information of the RX interface message and the user real-time position information of the GX interface message by using the time of the RX interface and the corresponding relation between the IP quadruple and the time of the GX interface and the IP quadruple;

performing quality evaluation on the voice media stream of the call to obtain voice fragment quality evaluation results with a plurality of preset durations, and associating the call ticket information with the voice fragment quality evaluation results with the plurality of preset durations to obtain the call ticket information to which the voice fragment quality evaluation results with the plurality of preset durations belong;

sequencing the voice fragment quality evaluation results of the plurality of preset durations belonging to the same call ticket information according to a time sequence;

and according to the time sequence, associating the user real-time position information belonging to the same call ticket information with each of the voice fragment quality evaluation results with the preset duration so as to associate the user real-time position information with the call voice quality evaluation result.

2. The method of claim 1, further comprising:

and continuously capturing user position information from a credit control request CCR message of the GX interface so as to acquire the real-time user position information.

3. The method as claimed in claim 2, wherein said continuously capturing user location information from a credit control request CCR message of the Gx interface to obtain the user real-time location information comprises:

4. The method of claim 1, wherein the correspondence between the RX interface message and the GX interface message comprises:

5. The method of claim 1, wherein the performing quality assessment on the voice media stream of the call to obtain a plurality of voice segment quality assessment results of a predetermined time length comprises:

6. The method according to claim 5, wherein said performing quality assessment on said plurality of voice segments with predetermined duration to obtain the quality assessment results of said plurality of voice segments with predetermined duration comprises:

7. The method of claim 5, further comprising:

and collecting RTP code stream in the RTP packet, analyzing the RTP code stream according to an address resolution protocol, and acquiring the time and IP four-tuple of an SGi interface.

8. The method according to claim 7, wherein the associating the call ticket information with the voice fragment quality evaluation results of the predetermined durations to obtain the call ticket information to which the voice fragment quality evaluation results of the predetermined durations belong comprises:

9. An apparatus for associating real-time location information with a call voice quality assessment result, the apparatus comprising:

the first association module is used for associating the call ticket information of the RX interface message and the user real-time position information of the GX interface message by utilizing the corresponding relation between the time of the RX interface and the time of the IP quadruple as well as the time of the GX interface and the IP quadruple;

10. An apparatus for associating real-time location information with a call voice quality assessment result, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method of any of claims 1-8.

11. A computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1-8.