Voice problem location method, device, electronic device and storage medium

Abstract

The present invention provides a method, device, electronic device and storage medium for locating voice problems. The method comprises: obtaining protocol signaling associated with an evolved packet system fallback process in drive test data; converting the protocol signaling into machine signaling; comparing the machine signaling with standard signaling in a pre-constructed expert rule base for locating failed nodes to obtain failed node signaling. The voice problem locating method provided by the present invention can accurately obtain failed node signaling, thereby improving the accuracy of voice problem judgment.

Description

Technical Field

[0001] The present invention relates to the field of network communication technology, and in particular to a voice problem locating method, device, electronic equipment and storage medium. Background Art

[0002] In the field of network communication technology, various communication problems may occur during the 5G voice communication process. Therefore, it is necessary to accurately locate the error when voice problems occur.

[0003] At present, the location of 5G voice problems mainly relies on personnel with certain skills to analyze and judge based on their own experience and skills. However, there is no effective judgment standard, the judgment result has no theoretical basis, and it consumes a lot of resources. Summary of the invention

[0004] The present invention provides a voice problem locating method, device, electronic device and storage medium, which are used to solve the technical problem of low accuracy in manually judging 5G voice problems.

[0005] In a first aspect, the present invention provides a method for locating a speech problem, comprising:

[0006] Acquiring protocol signaling associated with an evolved packet system fallback process in the drive test data;

[0007] Converting the protocol signaling into machine signaling;

[0008] The machine signaling is compared with the standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling.

[0009] In one embodiment, it further includes:

[0010] Based on the failed node signaling, deep iterative learning is performed on the influencing variable indicators to obtain the factors causing voice failure;

[0011] Based on the factors causing speech failure, the root cause causing speech failure is obtained through iterative calculation.

[0012] In one embodiment, converting the protocol signaling into machine signaling includes:

[0013] Screening the protocol signaling;

[0014] The filtered protocol signaling is correlated with the drive test data to obtain machine signaling that can match the drive test data.

[0015] In one embodiment, the comparing the machine signaling with the standard signaling in the pre-built failed node location expert rule base to obtain the failed node signaling includes:

[0016] The machine signaling is compared with the standard signaling, and the machine signaling that is inconsistent with the sequence of the standard signaling is output as the failed node signaling; wherein the standard signaling is arranged in chronological order in the failed node location expert rule base.

[0017] In one embodiment, the comparing the machine signaling with the standard signaling in the pre-built failed node location expert rule base to obtain the failed node signaling further includes:

[0018] The machine signaling is compared with the standard signaling, and the missing or extra machine signaling is output as the failed node signaling; wherein the standard signaling is stored in a fixed number in the failed node location expert rule base.

[0019] In one embodiment, the comparing the machine signaling with the standard signaling in the pre-built failed node location expert rule base to obtain the failed node signaling further includes:

[0020] Comparing the machine signaling with the standard signaling, and outputting a first machine signaling inconsistent with the standard signaling;

[0021] If the first machine signaling does not exist in the parallel rule, outputting the first machine signaling as the failed node signaling;

[0022] The parallel rule is a parallel sorting relationship between standard signaling in the failed node location expert rule base.

[0023] In a second aspect, the present invention provides a speech problem location device, comprising:

[0024] A signaling acquisition module, used to acquire protocol signaling associated with the Evolved Packet System fallback process in the drive test data;

[0025] A signaling conversion module, used to convert the protocol signaling into machine signaling;

[0026] The error location module is used to compare the machine signaling with the standard signaling in the pre-built failed node location expert rule base to obtain the failed node signaling.

[0027] In a third aspect, the present invention provides a terminal, including a memory, a transceiver, and a processor;

[0028] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0029] Acquiring protocol signaling associated with an evolved packet system fallback process in the drive test data;

[0030] Converting the protocol signaling into machine signaling;

[0031] The machine signaling is compared with the standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling.

[0032] In a fourth aspect, the present invention provides an electronic device, comprising a processor and a memory storing a computer program, wherein the processor implements the steps of the speech problem localization method described in the first aspect when executing the computer program.

[0033] In a fifth aspect, the present invention provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the steps of the speech problem localization method described in the first aspect.

[0034] The voice problem locating method, device, electronic device and storage medium provided by the present invention obtain the protocol signaling associated with the Evolved Packet System fallback process in the data, convert the protocol signaling into recognizable machine signaling, and then compare it with the standard signaling in the pre-built failure node locating expert rule base, so as to accurately obtain the failure node signaling and improve the accuracy of voice problem judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a flow chart of the method for locating speech problems provided by the present invention;

[0037] Figure 2 It is a schematic diagram of the time rule flow of the expert rule base for locating a failure node of the voice problem locating method provided by the present invention;

[0038] Figure 3 It is a schematic diagram of the existence or non-existence of a rule flow of the expert rule base for locating a failure node of the voice problem locating method provided by the present invention;

[0039] Figure 4 It is a schematic diagram of the parallel rule flow of the failure node location expert rule base of the voice problem location method provided by the present invention;

[0040] Figure 5 It is a structural schematic diagram of the speech problem locating device provided by the present invention;

[0041] Figure 6 is a schematic diagram of the structure of the terminal provided by the present invention;

[0042] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Combine the following Figure 1-Figure 7 The present invention describes a speech problem localization method, device, electronic device and storage medium.

[0045] Figure 1 is a flow chart of the method for locating speech problems provided by the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0046] Step 101: Acquire protocol signaling associated with an evolved packet system fallback process in drive test data.

[0047] It can be understood that during the communication process of the user equipment (UE) in the 5G core network, signaling interaction will occur with the base station. In the present invention, the tester will obtain relevant drive test data through drive testing.

[0048] After obtaining the drive test data, a total of 273 signaling related to the Evolved Packet System Fallback (EPSFB) process were extracted by referring to 57 protocols related to the 3rd Generation Partnership Project (3GPP) NR protocol and the Long Term Evolution (LTE) voice process.

[0049] Among them, road testing is the most commonly used test method for road wireless signals in the communications industry. To improve test efficiency, testers generally sit in a car and use professional test instruments to test the entire road section.

[0050] The Evolved Packet System consists of three parts: a 5G core network, a base station, and a user equipment. In the present invention, the Evolved Packet System fallback refers to the process of falling back from a 5G network to a 4G network.

[0051] Step 102: convert the protocol signaling into machine signaling.

[0052] It can be understood that after obtaining the protocol signaling associated with the Evolved Packet System fallback process in the drive test data, since the format of the protocol signaling is set for communication in the Evolved Packet System, the protocol signaling cannot be directly used by the machine after obtaining it. Therefore, after obtaining the protocol signaling, the protocol signaling will first be converted into machine signaling that can be used by the machine.

[0053] Step 103: Compare the machine signaling with the standard signaling in the pre-built failed node location expert rule base to obtain the failed node signaling.

[0054] It can be understood that the present invention will construct a failure node location expert rule base in advance, specifically, a standard signaling is set in the rule base, that is, the communication data without voice problems is composed of standard signaling. By comparing the signaling obtained from the drive test data with the standard signaling, and by comparing the difference between the signaling obtained from the drive test data and the standard signaling, the signaling of communication failure, that is, the failure node signaling, can be obtained. By obtaining the failure node signaling, the location node where the voice communication fails can be accurately located.

[0055] The present invention obtains the protocol signaling associated with the Evolved Packet System fallback process in the data, converts the protocol signaling into recognizable machine signaling, and then compares it with the standard signaling in the pre-built failure node positioning expert rule base to accurately obtain the failure node signaling, thereby improving the accuracy of voice problem judgment.

[0056] Optionally, it also includes:

[0057] Based on the failed node signaling, deep iterative learning is performed on the influencing variable indicators to obtain the factors causing voice failure;

[0058] Based on the factors causing speech failure, the root cause causing speech failure is obtained through iterative calculation.

[0059] It can be understood that, on the basis of obtaining the failed node signaling, other possible causes of voice failure are introduced for analysis, such as interference, physical resource block utilization (PRB utilization) and other indicators, and the indicators affecting voice failure are deeply iterated in turn to obtain the elements that cause voice failure.

[0060] After obtaining the variables causing voice failure, multiple iterations are performed to obtain the influence of various factors causing voice failure on voice communication failure, wherein the factor with the greatest influence (one or multiple factors with similar values) is the root cause of voice failure.

[0061] For example, the present invention uses the Gauss-Seidel iterative algorithm to analyze and determine the root cause of speech failure. By bringing indicators affecting speech, such as interference and physical resource block utilization (PRB utilization), into the Gauss-Seidel iterative algorithm, deep iterative learning is performed on the indicator variables affecting speech in turn. Each iteration will output a new result based on the previous variable. Through result verification, the variable with the greatest influence is obtained, and this variable is the root cause of speech failure.

[0062] The Gauss-Seidel iterative algorithm is as follows:

[0063] a i1 x1+a i2 x2+…+a in x n =b i (i=1,2,…,n),

[0064] Among them, a i1 is the 5G voice failure event caused by the first influencing variable in the i-th iteration, x1 is the first influencing variable, a i2 is the 5G voice failure event caused by the second influencing variable in the i-th iteration, x2 is the second influencing variable, a in is the 5G voice failure event caused by the nth influencing variable in the i-th iteration, x n is the nth influencing variable, b i is the result output after the i-th iteration, and n is the total number of iterations.

[0065] When i=1, x1 is a covering variable: a 11 x1=b1, when i=2, x2 is the interference variable: a 11 x1+a 21 x2=b2, when i=3, x3 is the PRB utilization variable: a 11 x1+a 21 x2+a 31 x3=b2.

[0066] As the variable x continues to increase, each new variable will produce a result b. By comparing the difference between the new result and the previous result, the one with the largest difference change is obtained, such as b3-b2>b2-b1>b1-0, that is, a 31 x3 has the greatest impact, and PRB utilization is the biggest factor leading to voice failure.

[0067]

[0068] (i=1,2,…,n; k=0,1,2…),

[0069] k is the category (the type of factor that causes 5G voice failure), i is the i-th iteration, x i k+1 is the influence degree of the (k+1) factor on speech failure in the i-th iteration. After i iterations, the influence degree of each of the i(k+1) factors on speech failure is obtained. The factor with the greatest influence (one or multiple factors with similar values) is the root cause of speech failure. i is the output result after the i-th iteration, j is the j-th iteration, a ij is the 5G voice failure event caused by the jth influencing variable in the i-th iteration, x j k+1 is the influence degree of speech failure caused by the factor in the jth iteration (k+1), n ​​is the total number of iterations, a ii is the 5G voice failure event caused by the i-th influencing variable in the i-th iteration.

[0070] As above, after three iterations, we can respectively obtain the influence of coverage, interference and PRB utilization on voice failure:

[0071] x1 1 =b1 / a 11

[0072] x2 2 =(b2-b1) / a 21

[0073] x3 3 =(b3-b2) / a 31

[0074] Among them, x1 1 is the coverage impact, b1 is the output result after the first iteration, a 11 This is the 5G voice failure event caused by the first influencing variable in the first iteration, x2 2 is the interference influence degree, b2 is the output result after the second iteration, a 21 5G voice failure event caused by the first influencing variable of the second iteration, x3 3 is the impact degree of PRB utilization, b3 is the result output after the third iteration, a 31 This is the 5G voice failure event caused by the first influencing variable of the third iteration.

[0075] Finally, compare x1 1 , x2 2 , x3 3 , where the maximum value is x3 3 (PRB utilization) is the root cause of voice failure.

[0076] The present invention introduces influencing environmental variables and adopts the Gauss-Seidel iterative algorithm to perform deep iterative learning on the influencing environmental variables, thereby obtaining the root cause of speech failure and improving the accuracy of speech problem locating.

[0077] Optionally, converting the protocol signaling into machine signaling includes:

[0078] Screening the protocol signaling;

[0079] The filtered protocol signaling is correlated with the drive test data to obtain machine signaling that can match the drive test data.

[0080] It can be understood that during the communication process, there will be a process of repeated transmission of signaling, so there will be repeated signaling in the process. After obtaining the protocol signaling in the road test data, the signaling will be screened, and 196 non-essential and repeated signalings involving the EPS FB process in the protocol signaling will be cleaned, and 77 necessary signalings will be retained.

[0081] After signaling screening, the EPS FB process is analyzed and the screened signaling is correlated with the drive test data to obtain machine signaling that matches the drive test data.

[0082] The present invention summarizes the 5G voice standard signaling process by studying and understanding the EPS FB process, ensuring the process is correct and avoiding abnormal situations.

[0083] Optionally, the comparing the machine signaling with a standard signaling in a pre-built failed node location expert rule base to obtain the failed node signaling includes:

[0084] The machine signaling is compared with the standard signaling, and the machine signaling that is inconsistent with the sequence of the standard signaling is output as the failed node signaling; wherein the standard signaling is arranged in chronological order in the failed node location expert rule base.

[0085] It can be understood that when locating failed node signaling in road test data, due to the complexity and diversity of actual road test data, when compared with the standard 5G signaling process, outputting signaling setting rules according to the chronological order can more effectively and accurately determine the problem node.

[0086] Figure 2 FIG. 1 is a schematic diagram of a time rule flow chart of a failure node location expert rule base of a voice problem location method provided by the present invention, such as Figure 2 As shown, in the present invention, time rules are set in the pre-constructed failure node location expert rule base, and the formulation of the time rules is to narrate the process of the development of things according to the passage of time. The standard signaling in the failure node location expert rule base is arranged in chronological order.

[0087] After obtaining the drive test data, the protocol signaling is converted into machine signaling (input signaling 1, input signaling 2...) that can be used by the machine and matches the drive test data, and the machine signaling is compared with the standard signaling (standard signaling 1, standard signaling 2...) in the expert rule base for failed node positioning, and the comparison results are output in time order. If the comparison result is that the machine signaling is consistent with the standard signaling in the expert rule base for failed node positioning, it is judged that the signaling in the acquired drive test data is normal. If the comparison result is that the machine signaling is inconsistent with the standard signaling in the expert rule base for failed node positioning, the abnormal time point and signaling are output.

[0088] The present invention sets time rules in a failure node location expert rule base, compares input machine signaling with standard signaling, outputs abnormal time points and signaling, and more accurately locates the failure node of the voice problem.

[0089] Optionally, the comparing the machine signaling with a standard signaling in a pre-built failed node location expert rule base to obtain the failed node signaling further includes:

[0090] The machine signaling is compared with the standard signaling, and the missing or extra machine signaling is output as the failed node signaling; wherein the standard signaling is stored in a fixed number in the failed node location expert rule base.

[0091] It can be understood that when locating failed node signaling in road test data, due to the complexity and diversity of actual road test data, when compared with the standard 5G signaling process, setting rules based on whether the number of signaling is consistent can more effectively and accurately determine the problem node.

[0092] Figure 3 FIG. 1 is a schematic diagram of the existence or non-existence of a rule flow of the expert rule base for locating a failed node in the voice problem locating method provided by the present invention, such as Figure 3 As shown, in the present invention, the presence or absence of rules is set in the pre-constructed failure node positioning expert rule base, and the presence or absence of rules is a judgment on whether the original signaling is missing or has extra normal signaling.

[0093] After obtaining the road test data, the protocol signaling is converted into machine signaling (input signaling 1, input signaling 3...) that can be used by the machine and matches the road test data, and the machine signaling is compared with the standard signaling (standard signaling 1, standard signaling 2, standard signaling 3...) in the expert rule base for failed node positioning, and the comparison results are compared according to whether there is a difference in the number of signaling. If the result of the comparison is that the machine signaling is consistent with the standard signaling in the expert rule base for failed node positioning, it is judged that the signaling in the obtained road test data is normal. If the result of the comparison is that the machine signaling is inconsistent with the standard signaling in the expert rule base for failed node positioning, the abnormal time point and signaling are output. The output abnormal results are further analyzed. If the number of input signaling is more than the number of standard signaling in the expert rule base for failed node positioning, the abnormal time point and the extra signaling are output; if the number of input signaling is less than the number of standard signaling in the expert rule base for failed node positioning, the abnormal time point and the missing signaling are output.

[0094] The present invention sets rules in a failure node location expert rule base, compares input machine signaling with standard signaling, and outputs abnormal time points, excess or missing signaling, thereby further improving the accuracy of locating failure nodes of voice problems.

[0095] Optionally, the comparing the machine signaling with a standard signaling in a pre-built failed node location expert rule base to obtain the failed node signaling further includes:

[0096] Comparing the machine signaling with the standard signaling, and outputting a first machine signaling inconsistent with the standard signaling;

[0097] If the first machine signaling does not exist in the parallel rule, outputting the first machine signaling as the failed node signaling;

[0098] The parallel rule is a parallel sorting relationship between standard signaling in the failed node location expert rule base.

[0099] It can be understood that when locating the failed node signaling of the drive test data, when comparing the signaling in the drive test data with the standard 5G signaling process, the signaling that is abnormal relative to the standard 5G signaling will be output, such as inconsistent sequence, missing or extra abnormalities, and then the parallel rule is used to determine whether the abnormal signaling is the failed node signaling. If the abnormal signaling is not within the scope of the parallel rule, the signaling is considered to be the failed node signaling. If the abnormal signaling is within the scope of the parallel rule, the signaling is considered to be normal.

[0100] Among them, the parallel rule refers to the existence of concepts of the same level in the same category, that is, they are arranged side by side without distinction of priority. Some signals in the expert rule base of failed node location are not arranged in chronological order, but in parallel relationship. Figure 4 FIG. 1 is a schematic diagram of a parallel rule flow of a failure node location expert rule base of the voice problem location method provided by the present invention, such as Figure 4 As shown, standard signaling 3 and standard signaling 4 are in a parallel relationship, that is, standard signaling 2 can be followed by either standard signaling 3 or standard signaling 4.

[0101] The present invention prevents positioning errors caused by the parallel relationship between signaling by setting parallel rules in the failed node positioning expert rule base, and further improves the accuracy of positioning the failed node of the voice problem.

[0102] The speech problem locating device provided by the present invention is described below. The speech problem locating device described below and the speech problem locating method described above can be referred to each other.

[0103] Figure 5 is a schematic diagram of the structure of the speech problem location device provided by the present invention, such as Figure 5 As shown, it mainly includes a signaling acquisition module 501, a signaling conversion module 502 and an error location module 503, wherein:

[0104] The signaling acquisition module 501 is used to acquire the protocol signaling associated with the Evolved Packet System fallback process in the drive test data;

[0105] A signaling conversion module 502, used to convert the protocol signaling into machine signaling;

[0106] The error location module 503 is used to compare the machine signaling with the standard signaling in the pre-built failed node location expert rule base to obtain the failed node signaling.

[0107] Optionally, the error locating module 503 is further configured to:

[0108] Based on the failed node signaling, deep iterative learning is performed on the influencing variable indicators to obtain the factors causing voice failure;

[0109] Based on the factors causing speech failure, the root cause causing speech failure is obtained through iterative calculation.

[0110] Optionally, the signaling conversion module 502 is further used to:

[0111] Screening the protocol signaling;

[0112] The filtered protocol signaling is correlated with the drive test data to obtain machine signaling that can match the drive test data.

[0113] Optionally, the error locating module 503 is further configured to:

[0114] The machine signaling is compared with the standard signaling, and the machine signaling that is inconsistent with the sequence of the standard signaling is output as the failed node signaling; wherein the standard signaling is arranged in chronological order in the failed node location expert rule base.

[0115] Optionally, the error locating module 503 is further configured to:

[0116] The machine signaling is compared with the standard signaling, and the missing or extra machine signaling is output as the failed node signaling; wherein the standard signaling is stored in a fixed number in the failed node location expert rule base.

[0117] Optionally, the error locating module 503 is further configured to:

[0118] Comparing the machine signaling with the standard signaling, and outputting a first machine signaling inconsistent with the standard signaling;

[0119] If the first machine signaling does not exist in the parallel rule, outputting the first machine signaling as the failed node signaling;

[0120] The parallel rule is a parallel sorting relationship between standard signaling in the failed node location expert rule base.

[0121] The terminal involved in the embodiments of the present application may be a device that provides voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem, etc. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called a user equipment (UE).

[0122] Figure 6 is a schematic diagram of the structure of the terminal provided by the present invention, such as Figure 6 As shown, the embodiment of the present application further provides a terminal, which may include: a memory 601, a transceiver 602 and a processor 603;

[0123] The memory 601 is used to store computer programs; the transceiver 602 is used to send and receive data under the control of the processor 603; the processor 603 is used to read the computer program in the memory 601 and perform the following operations:

[0124] Acquiring protocol signaling associated with an evolved packet system fallback process in the drive test data;

[0125] Converting the protocol signaling into machine signaling;

[0126] The machine signaling is compared with the standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling.

[0127] Among them, Figure 6 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 603 and various circuits of memory represented by memory 601 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 602 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. For different user devices, the user interface 604 may also be an interface capable of externally connecting or internally connecting required devices.

[0128] The processor 603 is responsible for managing the bus architecture and general processing, and the memory 601 can store data used by the processor 603 when performing operations.

[0129] The processor 603 is used to execute any of the methods provided in the embodiments of the present application according to the obtained executable signaling by calling the computer program stored in the memory 601. The processor and the memory may also be arranged physically separately.

[0130] Optionally, the processor 603 is further configured to perform the following operations:

[0131] Based on the failed node signaling, deep iterative learning is performed on the influencing variable indicators to obtain the factors causing voice failure;

[0132] Based on the factors causing speech failure, the root cause causing speech failure is obtained through iterative calculation.

[0133] Optionally, the processor 603 is further configured to perform the following operations:

[0134] Screening the protocol signaling;

[0135] The filtered protocol signaling is correlated with the drive test data to obtain machine signaling that can match the drive test data.

[0136] Optionally, the processor 603 is further configured to perform the following operations:

[0137] The machine signaling is compared with the standard signaling, and the machine signaling that is inconsistent with the sequence of the standard signaling is output as the failed node signaling; wherein the standard signaling is arranged in chronological order in the failed node location expert rule base.

[0138] Optionally, the processor 603 is further configured to perform the following operations:

[0139] The machine signaling is compared with the standard signaling, and the missing or extra machine signaling is output as the failed node signaling; wherein the standard signaling is stored in a fixed number in the failed node location expert rule base.

[0140] Optionally, the processor 603 is further configured to perform the following operations:

[0141] Comparing the machine signaling with the standard signaling, and outputting a first machine signaling inconsistent with the standard signaling;

[0142] If the first machine signaling does not exist in the parallel rule, outputting the first machine signaling as the failed node signaling;

[0143] The parallel rule is a parallel sorting relationship between standard signaling in the failed node location expert rule base.

[0144] It should be noted here that the terminal provided in the embodiment of the present invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. The parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0145] Figure 7 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 7 As shown, the electronic device may include: a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702 and the memory 703 communicate with each other via the communication bus 704. The processor 701 may call a computer program in the memory 703 to execute the steps of the method for locating a speech problem, for example, including:

[0146] Acquiring protocol signaling associated with an evolved packet system fallback process in the drive test data;

[0147] Converting the protocol signaling into machine signaling;

[0148] The machine signaling is compared with the standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling.

[0149] In addition, the logic instructions in the above-mentioned memory 703 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0150] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, the computer can perform the steps of the speech problem localization method provided by the above methods, for example, including:

[0151] Acquiring protocol signaling associated with an evolved packet system fallback process in the drive test data;

[0152] Converting the protocol signaling into machine signaling;

[0153] The machine signaling is compared with the standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling.

[0154] On the other hand, an embodiment of the present application further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, wherein the computer program is used to enable the processor to execute the steps of the methods provided in the above embodiments, for example, including:

[0155] Acquiring protocol signaling associated with an evolved packet system fallback process in the drive test data;

[0156] Converting the protocol signaling into machine signaling;

[0157] The machine signaling is compared with the standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling.

[0158] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0159] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0160] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for locating speech problems, characterized in that: include: Acquiring protocol signaling associated with an evolved packet system fallback process in the drive test data; Converting the protocol signaling into machine signaling; Compare the machine signaling with the standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling; The step of comparing the machine signaling with a standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling includes: Compare the machine signaling with the standard signaling, and output the machine signaling that is inconsistent with the standard signaling as the failed node signaling; wherein the standard signaling is arranged in chronological order in the failed node location expert rule base; The converting the protocol signaling into machine signaling comprises: Screening the protocol signaling to remove unnecessary and repeated signaling associated with an evolved packet system fallback process in the protocol signaling; Correlation analysis is performed on the filtered protocol signaling and the drive test data to obtain machine signaling that can match the drive test data; Also includes: Based on the failed node signaling, deep iterative learning is performed on the influencing variable indicators to obtain the factors causing voice failure; Based on the factors causing speech failure, obtaining the root cause of speech failure through iterative calculation; The Gauss-Seidel iterative algorithm is used to analyze the root cause of speech failure. The Gauss-Seidel iterative algorithm is as follows: ( i =1,2,…,n) in, a i1 For the i The 5G voice failure event caused by the first influencing variable of the iteration, x 1 is the first influencing variable, a i2 For the i The 5G voice failure event caused by the second influencing variable of the iteration, x 2 is the second influencing variable, a in For the i The iteration n 5G voice failure events caused by various influencing variables, x n For the n Influencing variables, b i For the i The output result after iterations is: n is the total number of iterations; ( i =1,2,…,n; k =0,1,2…) in, k For categories, i For the i Iterations, x i k+1 For the Iterations ( k +1) Factors that affect speech failure, For the i The output result after iterations is: j For the j Iterations, a ij For the i The iteration j 5G voice failure events caused by various influencing variables, x j k+1 For the j Iterations ( k +1) Factors that affect speech failure, n is the total number of iterations, a ii For the i The iteration i 5G voice failure events caused by various influencing variables.

2. The method for locating speech problems according to claim 1, characterized in that: The step of comparing the machine signaling with a standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling further includes: The machine signaling is compared with the standard signaling, and the missing or extra machine signaling is output as the failed node signaling; wherein the standard signaling is stored in a fixed number in the failed node location expert rule base.

3. The method for locating speech problems according to claim 2, characterized in that: The step of comparing the machine signaling with a standard signaling in a pre-built expert rule base for locating failed nodes to obtain failed node signaling further includes: Comparing the machine signaling with the standard signaling, and outputting a first machine signaling inconsistent with the standard signaling; If the first machine signaling does not exist in the parallel rule, outputting the first machine signaling as the failed node signaling; The parallel rule is a parallel sorting relationship between standard signaling in the failed node location expert rule base.

4. A speech problem location device, characterized in that: include: A signaling acquisition module, used to acquire protocol signaling associated with the Evolved Packet System fallback process in the drive test data; A signaling conversion module, used to convert the protocol signaling into machine signaling; An error location module, used to compare the machine signaling with the standard signaling in a pre-built expert rule base for failure node location to obtain the failure node signaling; The signaling acquisition module, the signaling conversion module and the error location module are used to execute the voice problem location method as described in any one of claims 1 to 3.

5. A terminal, characterized in that: Including memory, transceiver, processor; Memory for storing computer programs; a transceiver, for transmitting and receiving data under the control of the processor; A processor is used to read the computer program in the memory and execute the steps of the speech problem localization method as described in any one of claims 1 to 3.

6. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the method for locating speech problems described in any one of claims 1 to 3 are implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for locating speech problems as claimed in any one of claims 1 to 3 are implemented.

Images