Voice quality inspection method, device, electronic device, and computer-readable storage medium

Abstract

The present disclosure provides a speech quality inspection method, apparatus, electronic device, and computer-readable medium, which are applied to multiple quality inspection processing nodes. The method includes: for each quality inspection processing node, obtaining task data corresponding to the quality inspection processing node; determining to-be-run data based on the task data; verifying an initial quality inspection result based on a reference result of the corresponding quality inspection processing node to obtain a verification result; and if the verification result is a pass, determining a target quality inspection result for the corresponding quality inspection processing node based on the initial quality inspection result. Embodiments of the present disclosure can ensure the accuracy of complete speech quality inspection results, thereby improving the performance of speech quality inspection.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a voice quality inspection method, device, electronic device, and computer-readable storage medium. Background Art

[0002] To standardize the quality of telephone customer service and provide support for customer service personnel's speech techniques, voice quality inspection is often used to provide data reference. Voice quality inspection examines the content of telephone customer service calls to determine whether the customer service personnel's speech techniques are standardized.

[0003] Currently, some commonly used voice quality inspection solutions rely on manual inspection, which is inefficient and subject to subjective influence from inspectors, resulting in low accuracy of inspection results. Other commonly used voice quality inspection solutions utilize automated inspections, but these are also subject to influences such as the configuration of the inspection process and the structure of the voice data, resulting in low accuracy of the inspection results.

[0004] In view of this, how to perform efficient and highly accurate speech quality inspection is an urgent problem that needs to be solved in this field. Summary of the Invention

[0005] The present disclosure provides a speech quality inspection method, apparatus, electronic device, and computer-readable storage medium.

[0006] In a first aspect, the present disclosure provides a speech quality inspection method, which is applied to multiple quality inspection processing nodes, wherein the multiple quality inspection processing nodes sequentially perform quality inspection tasks corresponding to the corresponding quality inspection processing nodes according to a preset process, and the method includes:

[0007] For each quality inspection processing node, obtain task data of the corresponding quality inspection processing node, wherein the task data refers to execution logic data of the corresponding quality inspection processing node for executing the quality inspection task;

[0008] Determine the data to be run according to the task data, wherein the data to be run includes the database to be called by the corresponding quality inspection processing node and the identifier of the data;

[0009] After performing quality inspection processing on the data to be run to obtain an initial quality inspection result, verifying the initial quality inspection result according to the reference result of the corresponding quality inspection processing node to obtain a verification result;

[0010] If the verification result is passed, the target quality inspection result of the corresponding quality inspection processing node is determined according to the initial quality inspection result.

[0011] In a second aspect, the present disclosure provides a speech quality inspection device, which is applied to multiple quality inspection processing nodes, wherein the multiple quality inspection processing nodes sequentially perform quality inspection tasks corresponding to the corresponding quality inspection processing nodes according to a preset process. The device includes:

[0012] An acquisition module is used to acquire, for each quality inspection processing node, task data of the corresponding quality inspection processing node, where the task data refers to execution logic data of the quality inspection task executed by the corresponding quality inspection processing node;

[0013] A determination module, configured to determine data to be run according to the task data, wherein the data to be run includes a database to be called by the corresponding quality inspection processing node and an identifier of the data;

[0014] A quality inspection module is used to verify the initial quality inspection result according to the reference result of the corresponding quality inspection processing node after performing quality inspection processing on the data to be run to obtain a verification result;

[0015] The determination module is further configured to determine a target quality inspection result of the corresponding quality inspection processing node according to the initial quality inspection result if the verification result is passed.

[0016] In a third aspect, the present disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores one or more computer programs executable by the at least one processor, and the one or more computer programs are executed by the at least one processor so that the at least one processor can perform the above-mentioned speech quality inspection method.

[0017] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the above-mentioned speech quality inspection method when executed by a processor.

[0018] In a fifth aspect, the present disclosure provides a computer program or a computer program product, which includes a computer program stored in a computer-readable storage medium, and the computer program implements the above-mentioned speech quality inspection method when executed by a processor.

[0019] In the embodiment provided by the present disclosure, the process of voice quality inspection is set as multiple quality inspection processing nodes, and the multiple quality inspection processing nodes can execute the quality inspection tasks corresponding to the corresponding quality inspection processing nodes in sequence according to the preset process. Based on this, in the embodiment of the present disclosure, for each quality inspection processing node, the task data of the corresponding quality inspection processing node can be obtained, and the data to be run can be determined based on the task data; after the initial quality inspection result is obtained by quality inspection processing based on the data to be run, the initial quality inspection result is verified based on the reference result of the corresponding quality inspection processing node to obtain a verification result; if the verification result is a passed verification, the target quality inspection result of the corresponding quality inspection processing node is determined based on the initial quality inspection result. Among them, the task data refers to the execution logic data of the quality inspection task executed by the corresponding quality inspection processing node, and the data to be run includes the database to be called by the corresponding quality inspection processing node and the identifier of the data, so that the corresponding quality inspection processing node automatically executes the above-mentioned quality inspection processing logic of the present disclosure according to the task data. That is, the embodiment of the present disclosure no longer relies on manual voice quality inspection, but deploys multiple quality inspection processing nodes according to the voice quality inspection process, and configures corresponding task data for each quality inspection processing node according to the quality inspection process to be performed by the quality inspection processing node, so that each quality inspection processing node performs quality inspection processing according to the corresponding task data, thereby realizing automated voice quality inspection. Furthermore, for any quality inspection processing node, the quality inspection processing node can automatically configure the data to be run according to the task data, and then automatically call the relevant data in the database for quality inspection processing, as well as verify and improve the quality inspection processing results of the quality inspection processing node and return the final results, and can automatically trigger the subsequent processing process. This not only improves the processing efficiency of voice quality inspection, but also because each node triggers the subsequent process according to the final processing result, it can ensure the accuracy of the quality inspection results of each node, thereby ensuring the accuracy of the complete voice quality inspection results, thereby improving the performance of voice quality inspection.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. The above and other features and advantages will become more apparent to those skilled in the art by describing detailed example embodiments with reference to the accompanying drawings. In the accompanying drawings:

[0022] Figure 1A A data flow diagram of a speech quality inspection processing node provided by an embodiment of the present disclosure;

[0023] Figure 1B A flow chart of a voice quality inspection method provided in an embodiment of the present disclosure;

[0024] Figure 2 A flowchart of an exemplary voice quality inspection method provided in an embodiment of the present disclosure;

[0025] Figure 3 A structural diagram of a speech quality inspection device provided in an embodiment of the present disclosure;

[0026] Figure 4 A structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] To enable those skilled in the art to better understand the technical solutions of the present disclosure, exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0028] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0029] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0030] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded. Similar words such as "connected" or "connected" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0031] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly defined as such herein.

[0032] The general process of voice quality inspection includes: converting the voice of customer service staff and customers into text, storing the text and quality inspection rules in a database, analyzing the text in the database using the quality inspection rules, obtaining analysis results, and using the analysis results as quality inspection results.

[0033] According to the processing process of speech quality inspection, the processing flow of speech quality inspection can usually be divided into multiple processing nodes. For example, Figure 1A As shown, a speech quality inspection processing flow may include the following processing nodes that are performed in sequence: login, quality inspection model building, batch processing, random inspection, re-inspection, and quality inspection result release. Each of these processing nodes can execute part of the processing flow in the speech quality inspection processing flow. For example, the login node can log in to the speech quality inspection system; the quality inspection model building node can build a quality inspection model according to pre-configured quality inspection rules; the batch processing node can match and process the speech content into text, and store the text in the database; the random inspection node can extract part of the text in the database for quality inspection; the re-inspection node can verify the quality inspection results obtained by the random inspection node; the quality inspection result node can output the quality inspection results obtained by the random inspection node and the re-inspection node.

[0034] For example, in actual implementation, each node can be triggered to perform the quality inspection process of the corresponding node by calling an interface. Accordingly, each of the above-mentioned quality inspection processing nodes can be implemented as an "interface".

[0035] In order to improve the efficiency of voice quality inspection, some conventional automated voice quality inspection methods deploy multiple processing nodes according to the voice quality inspection process, and then trigger each node to execute the corresponding processing action in sequence according to the voice quality inspection process. Figure 1A As can be seen from the description, the processing results generated by some processing nodes serve as data used by the next processing node of the processing node. For example, the quality inspection results or the text of the spot inspection generated by the sampling processing node serve as data used by the re-inspection node. In view of this, the accuracy of the data generated by each processing node will affect the accuracy of the data generated by all subsequent processing nodes of the processing node, as well as the final result of the voice quality inspection. In conventional automated voice quality inspection methods, some processing nodes usually transmit the response result of whether to start task processing as the processing result to the next processing node, or transmit data containing redundant information to the next processing node, resulting in poor accuracy of the voice quality inspection results and low quality inspection performance.

[0036] The disclosed embodiment provides a method for speech quality inspection, wherein each quality inspection processing node automatically configures the data to be run based on the task data corresponding to the corresponding quality inspection processing node, and then automatically calls the relevant data in the database to perform the quality inspection processing corresponding to the corresponding quality inspection processing node, and verifies and improves the quality inspection processing results of the quality inspection processing node. After that, the final result is returned or the subsequent processing flow is automatically triggered. This not only improves the processing efficiency of speech quality inspection, but also, because each node triggers the subsequent flow based on the final processing result, it can ensure the accuracy of the quality inspection results of each node, thereby ensuring the accuracy of the complete speech quality inspection results, thereby improving the performance of speech quality inspection.

[0037] The voice quality inspection method illustrated in the embodiments of the present disclosure can be performed by an electronic device, and the electronic device can be an access control device, an in-vehicle device, a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, etc. In some implementations, the voice quality inspection method can be implemented by a processor in the electronic device calling computer-readable program instructions stored in a memory.

[0038] The following describes the speech quality inspection method according to the embodiment of the present disclosure in conjunction with an exemplary implementation.

[0039] Figure 1B This is a flow chart of a voice quality inspection method provided by an embodiment of the present disclosure. Figure 1B The voice quality inspection method shown may include Figure 1A The multiple quality inspection processing nodes shown in the figure execute the quality inspection tasks corresponding to the corresponding quality inspection processing nodes in sequence according to the preset process. Figure 1B , the method comprising:

[0040] In step S11 , for each quality inspection processing node, task data corresponding to the quality inspection processing node is obtained.

[0041] The task data refers to the execution logic data for the quality inspection task executed by the corresponding quality inspection processing node, which can also be called interface use case data. The task data may include, for example, the identification of the corresponding quality inspection processing node, execution steps, database call information involved in each execution step, data call information, reference results, initial quality inspection result verification logic, data extraction logic, etc.

[0042] It should be noted that the task data for each quality inspection processing node can be pre-configured during the deployment of the multiple quality inspection processing nodes based on the quality inspection tasks to be performed by each quality inspection processing node. Each quality inspection processing node corresponds to the task data of a corresponding quality inspection processing node, and a correspondence between each quality inspection processing node and its corresponding task data can be established through the identification of the quality inspection processing node.

[0043] In step S12, data to be executed is determined according to the task data.

[0044] The data to be run includes the database to be called by the corresponding quality inspection processing node and the identifier of the data.

[0045] It should be pointed out that the voice quality inspection method of the embodiment of the present disclosure can be a general method, that is, the voice quality inspection method of the embodiment of the present disclosure can be applied to multiple voice quality inspection scenarios. Accordingly, the task data involved in the embodiment of the present disclosure may include the execution logic information of the corresponding quality inspection processing node, and when the specific database or data to be called is involved in the execution logic information, it can be represented by a task attribute field, and each task attribute field can be identification information or descriptive information of the task attribute value. When applied to a specific voice quality inspection scenario, the electronic device can replace the corresponding task attribute field with the specific parameters in the corresponding voice quality inspection scenario to obtain the data to be run that can be directly run by the corresponding quality inspection processing node.

[0046] Based on this, in some implementations, the electronic device can detect whether the task data contains a task attribute field. If the task data contains at least one task attribute field, the electronic device can perform parameter replacement processing on the at least one task attribute field to obtain primary replacement data, and determine the data to be executed based on the primary replacement data. If the task data does not contain the task attribute field, the task data is used as the data to be executed.

[0047] In actual implementation scenarios, when the task data includes a task attribute field, the task data will typically also include a to-be-queried field. However, when the task data does not include a task attribute field, the task data will typically not include a to-be-queried field. The to-be-queried field is used to indicate the database query operation to be performed by the corresponding quality inspection processing node before performing quality inspection processing. This processing of the to-be-queried field can be referred to as "pre-query processing."

[0048] Based on this, after obtaining the primary replacement data, the electronic device can obtain the data segment corresponding to each field to be queried from the first database, and use the corresponding data segment to replace the corresponding field to be queried to obtain the secondary replacement data. In some implementations, some data segments in the first database may contain task attribute fields. Furthermore, the electronic device can detect whether each data segment of the secondary replacement data contains a task attribute field. If all data segments do not contain a task attribute field, the secondary replacement data is used as the data to be run; if any data segment contains a task attribute field, the parameter replacement processing is performed on the contained task attribute field to obtain tertiary replacement data, and the tertiary replacement data is used as the data to be run.

[0049] For example, the attribute data corresponding to each task attribute field can be pre-deployed in the configuration file of the corresponding quality inspection processing node, or can be data generated during the process of querying the first database for the field to be queried. Based on this, the electronic device can obtain the attribute data corresponding to each task attribute field of the task data from the configuration file of the corresponding quality inspection processing node, and use the data generated during the query of the first database as the attribute data for the corresponding task attribute field in the secondary replacement data.

[0050] Exemplarily, the task attribute field can be implemented as a placeholder, and the presentation form of the placeholder is, for example, "#*#", where * can be the name of the attribute data to be replaced, and the attribute data corresponding to each task attribute field can be, for example, the specific value of the attribute represented by the corresponding placeholder, such as the placeholder "#TaskId#", "#agentGroup Id#", etc. The name of the attribute data to be replaced of the placeholder #TaskId# is the task identifier, and the attribute data can be, for example, "Task 008".

[0051] It can be seen that by adopting this implementation method, task attribute fields (such as placeholders) are used to form task data, so that when the corresponding quality inspection processing node is facing a specific application scenario, it can generate the waiting-to-run data suitable for the corresponding application scenario by replacing the task attribute fields, which will not destroy the data format and can flexibly adapt to various application scenarios.

[0052] In step S13, after quality inspection processing is performed on the data to be run to obtain an initial quality inspection result, the initial quality inspection result is verified according to the reference result of the corresponding quality inspection processing node to obtain a verification result.

[0053] In conjunction with step S12, the data to be run may include, for example, the access address of the data to be accessed, interface parameters and other specific information that can be run. The electronic device may run the data to be run to perform quality inspection processing of the corresponding quality inspection processing node.

[0054] The initial quality inspection result of the corresponding quality inspection processing node may refer to the quality inspection result generated by the corresponding quality inspection processing node when running the data to be run, and the reference result of the corresponding quality inspection processing node may refer to the expected quality inspection processing result of the corresponding quality inspection processing node, and the expected quality inspection processing result may be preset. Based on this, verifying the initial quality inspection result according to the reference result of the corresponding quality inspection processing node to obtain a verification result includes: detecting whether the initial quality inspection result is the same as the reference result; if the initial quality inspection result is the same as the reference result, determining that the verification result is a passed verification; if the initial quality inspection result is different from the reference result, determining that the verification result is a failed verification.

[0055] In some implementations, the corresponding processing node may perform quality inspection on a piece of voice data, thereby obtaining an initial quality inspection result. Accordingly, this implementation includes a reference result. In this implementation, the initial quality inspection result is identical to the reference result, i.e., the initial quality inspection result parameter has the same value as the reference result. That is, if the initial quality inspection result parameter has the same value as the reference result, the verification result is determined to be a passed verification; if the initial quality inspection result parameter differs from the reference result, the verification result is determined to be a failed verification.

[0056] In other implementations, the corresponding quality inspection processing node can perform quality inspection on at least two voice data, and then, an initial quality inspection result can be obtained for each voice data. Accordingly, in this implementation, the corresponding quality inspection processing node can correspond to multiple reference results. Then, in this implementation, the initial quality inspection result is the same as the reference result, that is, each initial quality inspection result parameter in the multiple initial quality inspection result parameters is the same as the corresponding reference result value. That is, if each initial quality inspection result parameter is the same as the corresponding reference result value, then the verification result is determined to be verification passed; if any of the initial quality inspection result parameters is different from the corresponding reference result value, then the verification result is determined to be verification failed.

[0057] For example, in a scenario where a corresponding quality inspection processing node has multiple reference result values, the multiple reference result values ​​can be pre-stored in a database. The database storing the multiple reference result values ​​can be, for example, a check database. Accordingly, each time an initial quality inspection result parameter is obtained, the electronic device can call the check database to read the reference result value corresponding to the initial quality inspection result parameter, and then detect whether the initial quality inspection result parameter is the same as the corresponding reference result value, until the detection of the last of the multiple initial quality inspection result parameters is completed. This implementation process can be called, for example, an "asynchronous interface call."

[0058] Using this implementation method, when the corresponding quality inspection processing node performs quality inspection on multiple voice data, the initial quality inspection results of each voice data can be cyclically verified through asynchronous interface calls until the verification of the initial quality inspection results of multiple voice data is completed, and then the final verification result is obtained, thereby obtaining a more accurate verification result.

[0059] In step S14, if the verification result is passed, the target quality inspection result of the corresponding quality inspection processing node is determined according to the initial quality inspection result.

[0060] Among them, if the verification result is verification passed, it means that the corresponding quality inspection processing node has successfully executed the quality inspection processing task, and subsequent processing can be continued based on the initial quality inspection result; if the verification result is verification failed, it means that the corresponding quality inspection processing node has failed to execute the quality inspection processing task, and the electronic device can terminate the voice quality inspection process.

[0061] In some implementations, the corresponding quality inspection result can be used only as the quality inspection result of the corresponding quality inspection processing node. In other implementations, the corresponding quality inspection result can be used not only as the quality inspection result of the corresponding quality inspection processing node, but also as task data of the next node of the corresponding quality inspection processing node.

[0062] It should be noted that, depending on the quality inspection tasks to be processed at the corresponding quality inspection processing node, in some implementations, the initial quality inspection result may include a field to be updated, and the field to be updated is used to indicate the specific data to be obtained. Optionally, the field to be updated can be implemented as a data capture rule or data indication information. In other implementations, the initial quality inspection result may not include a field to be updated. Based on this, after the electronic device obtains the initial quality inspection result, it can determine whether the initial quality inspection result contains a field to be updated; if the initial quality inspection result contains a field to be updated, the data corresponding to the field to be updated is obtained from the corresponding database according to the preset rules, and the data is used to replace the corresponding field to be updated in the initial quality inspection result, and the result after replacement is used as the target quality inspection result; if the initial quality inspection result contains a field to be updated, the initial quality inspection result is used as the target quality inspection result.

[0063] In some implementations, obtaining data corresponding to the field to be updated from the target database according to preset rules includes at least one of the following: capturing second data from a second data segment of a second database according to preset data capture rules, and using the second data as the data corresponding to the field to be updated; obtaining third data from a third database according to preset data indication information, and using the third data as the data corresponding to the field to be updated.

[0064] Exemplarily, the second data segment of the second database is data stored in JSON format, for example. Accordingly, the preset data capture rule may be a JSON expression, for example.

[0065] It can be seen that by adopting this implementation method, the electronic device can further use data capture to capture specific data in the data segment from the database based on the initial quality inspection results, thereby obtaining more accurate data and making the target quality inspection results obtained more accurate.

[0066] In some implementations, the preset data indication information may be implemented as a placeholder, and the process of the placeholder and obtaining the data corresponding to the placeholder is as described in the above implementations and will not be described in detail here.

[0067] Among them, the process of determining the corresponding quality inspection processing node based on the initial quality inspection results is the process of the corresponding quality inspection processing node after performing the quality inspection processing. The embodiment of the present disclosure can call the processing of step S15 "post-processing", and accordingly, the data capture can be called "post-capture processing", and the processing of data indication information can be called "post-query processing".

[0068] In addition, after step S14, the electronic device may also determine whether the corresponding quality inspection processing node is the last quality inspection processing node among the multiple quality inspection processing nodes. If the corresponding quality inspection processing node is the last quality inspection processing node among the multiple quality inspection processing nodes, the voice quality inspection process is terminated; if the corresponding quality inspection processing node is not the last quality inspection processing node among the multiple quality inspection processing nodes, the operations of steps S11 to S14 above are performed on the quality inspection processing node next to the corresponding quality inspection processing node until the voice quality inspection process is terminated. When the voice quality inspection process is terminated, the electronic device may output a voice quality inspection report, which may include the target quality inspection results corresponding to each quality inspection processing node among the multiple quality inspection processing nodes.

[0069] In some implementations, if each quality inspection processing node successfully executes its quality inspection task, and the corresponding quality inspection processing node is the last quality inspection processing node among the multiple quality inspection processing nodes, the speech quality inspection process is deemed to have concluded. In other implementations, if one of the quality inspection processing nodes fails to execute its quality inspection task, the speech quality inspection process is deemed to have concluded. If one of the quality inspection processing nodes fails to execute its quality inspection task, the target quality inspection result of the quality inspection processing node that did not execute speech quality inspection among the multiple quality inspection processing nodes may be empty or contain a prompt indicating that quality inspection was not completed.

[0070] It can be seen that by adopting this implementation method, the electronic device calls each quality inspection processing node in sequence according to the voice quality inspection process to perform the operations of the above steps S11 to S14 until the voice quality inspection process is completed, and then outputs a voice quality inspection report containing the target quality inspection results corresponding to each quality inspection processing node. This not only enables automated voice quality inspection, but also for each quality inspection processing node, only after obtaining the quality inspection processing results of the corresponding quality inspection processing node, will the subsequent quality inspection process be triggered. In this way, not only can the quality inspection results of each quality inspection processing node be obtained, but also the accuracy of the voice quality inspection results can be improved.

[0071] As can be seen from the foregoing description, the voice quality inspection method of the disclosed embodiment can be applied to a variety of voice quality inspection scenarios, and each execution of the voice quality inspection process of the disclosed embodiment generates processing data related to the executed voice quality inspection process, for example: the data to be executed includes the quality inspection results of attribute data and various quality inspection processing interfaces. Based on this, when some or all of the multiple quality inspection processing nodes correspond to historical processing data, before executing the above step S11, the electronic device can also clear the historical processing data corresponding to each quality inspection processing node, so that the data related to each node can be called in the voice quality inspection scenario involved in the disclosed embodiment.

[0072] It can be seen that by adopting this implementation method, the voice quality inspection method of the embodiment of the present disclosure can be applied to a variety of voice quality inspection scenarios, and is flexible to use and has wide applicability.

[0073] The following is an exemplary description of the speech quality inspection method of the embodiment of the present disclosure in conjunction with an exemplary processing flow.

[0074] Figure 2 A flowchart of an exemplary voice quality inspection method provided in an embodiment of the present disclosure. Figure 2 The illustrated embodiment is applied to multiple quality inspection processing nodes, and the electronic device sequentially calls the multiple quality inspection processing nodes according to the preset process. The multiple quality inspection processing nodes can be as follows Figure 1A In this example, each of the plurality of quality inspection processing nodes can be implemented as an interface to be called.

[0075] Figure 2 The illustrative method may include the following steps:

[0076] Step S21: clearing historical processing data corresponding to multiple quality inspection processing nodes.

[0077] For example, the electronic device can call a data cleaning task to clear the data generated by each quality inspection processing node during historical operations.

[0078] For each quality inspection processing node i to be called, perform the following processing:

[0079] Step S22: Obtain task data of quality inspection processing node i.

[0080] The task data of the quality inspection processing node i is also the interface use case data of the quality inspection processing node i.

[0081] For example, the interface use case data (ie, task data) may include: ID, name

[0082] (t it le), pre-query processing database (pre_sql), method (method), uniform resource locator

[0083] (Un iform Resource Locator, ur l), request parameters (request_data), verification database

[0084] (check_sql), data extraction rules (extract_res), post-query processing database (extract_sql), expected value (expected), actual value (actua l), and some or all fields in the result (resu lt).

[0085] Among them, id refers to the interface use case line number of quality inspection processing node i, title refers to the interface use case name of quality inspection processing node i, pre_sql refers to the database identifier corresponding to the pre-query processing, method refers to the interface request method of quality inspection processing node i, url refers to the interface request address of quality inspection processing node i, request_data refers to the interface request parameter of quality inspection processing node i, check_sql refers to the verification database identifier of quality inspection processing node i, extract_res refers to the post-data capture rule, such as the json extraction expression, extract_sql refers to the database identifier corresponding to the post-query processing, expected refers to the first reference result of quality inspection processing node i, actua l refers to the initial verification result of quality inspection processing node i, and resultt refers to the indication identifier of whether the quality inspection of quality inspection processing node i is successful or not.

[0086] Step S23, determine whether the placeholder is included, if yes, execute step S24; if no, execute step S27.

[0087] In combination with the above-mentioned embodiment, the placeholder in the interface use case data (ie, task data) is the task attribute field in the interface use case data.

[0088] It should be pointed out that if the interface use case data does not contain a placeholder, it usually does not contain pre_sql, that is, it does not contain the field to be queried, which means that the electronic device does not need to perform pre-query processing.

[0089] Step S24: performing parameter replacement on the placeholder.

[0090] After obtaining the interface use case data, the electronic device can determine the placeholders in the interface use case data through pattern matching, and then, for example, obtain the value corresponding to each placeholder from the configuration file of the quality inspection processing node i, that is, the attribute data of each task attribute field, and use the value corresponding to each placeholder to replace the corresponding placeholder to obtain replacement data.

[0091] For example, the interface use case data includes a placeholder #autoTaskId#, and the electronic device obtains autoTaskId=12 from the configuration file of the quality inspection processing node i. Therefore, #autoTaskId# is replaced with the value 12.

[0092] Step S25, determine whether pre_sql is included. If so, execute step S26; if not, execute step S27.

[0093] Wherein, pre_sql 1 represents the field to be queried as described in the above embodiment. The interface use case data includes pre_sql 1, which indicates that data needs to be queried from pre_sql 1 and the queried data is used to replace the field to be queried in the interface use case data.

[0094] Exemplarily, the fields to be queried indicated by pre_sql may also be implemented as placeholders, and the values ​​of these placeholders cannot be obtained from the configuration file of the quality inspection processing node i, for example.

[0095] Step S26, executing pre-query processing, and executing step S23 again on the data after executing pre-query processing.

[0096] Among them, for the placeholders (i.e., fields to be queried) in the interface use case data whose values ​​cannot be obtained from the configuration file of the quality inspection processing node i, the electronic device can perform pattern matching from pre_sql to obtain the values ​​of the corresponding placeholders. This process can be called pre-query processing.

[0097] For example, the placeholder #agentGroupId# included in the interface use case data can be obtained from the pre_sql

[0098] #agentGroupId# performs pattern matching, for example, agentGroupId=25. The electronic device will placeholder

[0099] #agentGroupId# is replaced with the value 25.

[0100] It should be noted that the value retrieved in pre_sql can contain data segments, which may contain placeholders. Based on this, after completing the pre-query processing, the electronic device can determine whether the secondary replacement data obtained after parameter replacement contains placeholders. If so, the parameter replacement process is performed again to obtain callable interface parameters, i.e., the data to be run.

[0101] Step S27: perform quality inspection and obtain the actual value.

[0102] After obtaining the data to be run, the electronic device can run the data to perform quality inspection processing at quality inspection processing node i, thereby obtaining an initial quality inspection result for quality inspection processing node i. Running the data to be run refers to executing an interface call operation for quality inspection processing node i. The initial quality inspection result is the actual value returned by the interface.

[0103] Exemplarily, the electronic device may obtain the ur l, method and request_data in the aforementioned interface use case data to request the interface, and then obtain the actual value returned by the interface.

[0104] Step S28: Verify the actual value according to check_sql or expected. If the verification passes, execute step S29; if the verification fails, execute step S32.

[0105] The expected value and the value in check_sql can be the reference result of the quality inspection processing node i, that is, the expected return value.

[0106] In some implementations, the interface use case data may not include the expected value and the check_sql flag. In this implementation, there is no need to verify the actual value. In other implementations, the interface use case data includes either the expected value or the check_sql flag. In this implementation, the electronic device may verify the actual value based on the data included in the interface use case data.

[0107] For example, if the interface use case data includes an expected value, the expected value is the aforementioned first reference result, and the actual value is the aforementioned first initial quality inspection result. The electronic device can detect whether the actual value is the same as the expected value. If the actual value is the same as the expected value, the quality inspection task of quality inspection processing node i is considered to have been successfully executed. If the actual value is different from the expected value, the quality inspection task of quality inspection processing node i is considered to have failed.

[0108] For another example, if the interface use case data includes the check_sq l identifier, then the check_sq l identifier indicates that multiple expected values ​​can be included in check_sq l, and the multiple expected values ​​are the aforementioned multiple second reference results. In this example, the quality inspection processing node i can perform quality inspection on multiple voice data, and obtain a value corresponding to each voice data, for example. The values ​​of the multiple voice data are, for example, actual values, that is, the actual values ​​contain multiple second initial quality inspection result parameters. In this example, every time the quality inspection value of a voice data is obtained, it is detected whether the quality inspection value is the same as the expected value corresponding to the quality inspection value in check_sq l. If each quality inspection value is the same as the corresponding expected value, it is considered that the quality inspection task of the quality inspection processing node i is successfully executed. Even if only one quality inspection value is different from the corresponding expected value, it is considered that the quality inspection task of the quality inspection processing node i has failed to execute.

[0109] Step S29, determine whether to perform post-processing, if so, execute step S30; if not, execute step S31.

[0110] In some implementations, the actual value may not include fields to be updated. In this case, the electronic device may use the actual value as the target quality inspection result, i.e., the result value, for quality inspection processing node i. In other implementations, the actual value may include fields to be updated, such as at least one of extract_res and extract_sql. Based on the indication of the fields to be updated, the electronic device may replace the fields to be updated in the actual value with corresponding specific values ​​to obtain the result value for quality inspection processing node i.

[0111] extract_res contains data crawling rules, and extract_sql indicates the database of the data to be obtained.

[0112] Step S30: perform post-processing to obtain a target quality inspection result of the quality inspection processing node i.

[0113] When the actua l value contains extract_res, the electronic device can capture data from the relevant data database according to the data capture strategy in extract_res, for example, capture data from the json database according to the json expression, and then fill the captured data into the actua l value.

[0114] When the actual value contains a placeholder corresponding to extract_sql, the electronic device can obtain the value corresponding to the placeholder from extract_sql and use the obtained value to replace the corresponding placeholder in the actual value.

[0115] Step S31, determine whether the quality inspection processing node i is the last quality inspection processing node among multiple quality inspection processing nodes. If so, execute step S32; if not, use the quality inspection processing node i+1 as the new quality inspection processing node i, and execute step 22 for the new quality inspection processing node i.

[0116] Step S32: Output the voice quality inspection report.

[0117] Illustratively, the speech quality inspection report may include the results of all quality inspection processing nodes that have performed quality inspection processing.

[0118] It can be seen that, by adopting the embodiment provided by the present disclosure, the process of voice quality inspection is set as multiple quality inspection processing nodes, and the multiple quality inspection processing nodes can execute the quality inspection tasks corresponding to the corresponding quality inspection processing nodes in sequence according to the preset process. Based on this, in the embodiment of the present disclosure, for each quality inspection processing node, the task data of the corresponding quality inspection processing node can be obtained, and the data to be run can be determined based on the task data; after the initial quality inspection result is obtained by performing quality inspection processing based on the data to be run, the initial quality inspection result is verified based on the reference result of the corresponding quality inspection processing node to obtain a verification result; if the verification result is a passed verification, the target quality inspection result of the corresponding quality inspection processing node is determined based on the initial quality inspection result. Among them, the task data refers to the execution logic data of the quality inspection task executed by the corresponding quality inspection processing node, and the data to be run includes the database to be called by the corresponding quality inspection processing node and the identifier of the data, so that the corresponding quality inspection processing node automatically executes the above-mentioned quality inspection processing logic of the present disclosure according to the task data. That is, the embodiment of the present disclosure no longer relies on manual voice quality inspection, but deploys multiple quality inspection processing nodes according to the voice quality inspection process, and configures corresponding task data for each quality inspection processing node according to the quality inspection process to be performed by the quality inspection processing node, so that each quality inspection processing node performs quality inspection processing according to the corresponding task data, thereby realizing automated voice quality inspection. Furthermore, for any quality inspection processing node, the quality inspection processing node can automatically configure the data to be run according to the task data, and then automatically call the relevant data in the database for quality inspection processing, as well as verify and improve the quality inspection processing results of the quality inspection processing node and return the final results, and can automatically trigger the subsequent processing process. This not only improves the processing efficiency of voice quality inspection, but also because each node triggers the subsequent process according to the final processing result, it can ensure the accuracy of the quality inspection results of each node, thereby ensuring the accuracy of the complete voice quality inspection results, thereby improving the performance of voice quality inspection.

[0119] It is understood that the above-mentioned various method embodiments mentioned in this disclosure can be combined with each other to form combined embodiments without violating the principle logic. Due to space limitations, this disclosure will not go into details. It is understood by those skilled in the art that in the above-mentioned methods of specific implementation, the specific execution order of each step should be determined by its function and possible internal logic.

[0120] In addition, the present disclosure also provides a speech quality inspection device, an electronic device, and a computer-readable storage medium, all of which can be used to implement any speech quality inspection method provided by the present disclosure. The corresponding technical solutions and descriptions are referred to the corresponding records in the method section and will not be repeated here.

[0121] Reference Figure 3The present disclosure provides a speech quality inspection apparatus for use with multiple quality inspection processing nodes. The multiple quality inspection processing nodes sequentially execute quality inspection tasks corresponding to the corresponding quality inspection processing nodes according to a preset process. The apparatus includes an acquisition module 31, a determination module 32, and a quality inspection module 33. Each module, when running, can implement some or all of the functions described in the aforementioned method implementation.

[0122] For example, the acquisition module 31 is used to obtain the task data of the corresponding quality inspection processing node for each quality inspection processing node, and the task data refers to the execution logic data of the corresponding quality inspection processing node to perform the quality inspection task; the determination module 32 is used to determine the data to be run based on the task data, and the data to be run includes the database to be called by the corresponding quality inspection processing node and the identification of the data; the quality inspection module 33 is used to verify the initial quality inspection result according to the reference result of the corresponding quality inspection processing node after performing quality inspection processing on the data to be run to obtain an initial quality inspection result, and obtain a verification result; the determination module 32 is also used to determine the target quality inspection result of the corresponding quality inspection processing node according to the initial quality inspection result if the verification result is verification passed.

[0123] For details on the implementation, see the above Figures 1A to 2 The illustrated method implementation will not be described in detail here.

[0124] It is understandable that the division of the above modules / units is only a division of logical functions. In actual implementation, the above modules / units can be integrated into hardware implementation. For example, the function of the acquisition module 31 can be integrated into the I / O interface, and the functions of the determination module 32 and the quality inspection module 33 can be integrated into the processor implementation. Figure 4 As shown, Figure 4 A block diagram of an electronic device provided in an embodiment of the present disclosure. Figure 4 An embodiment of the present disclosure provides an electronic device, which includes: at least one processor 401; at least one memory 402, and one or more I / O interfaces 403, connected between the processor 401 and the memory 402; wherein the memory 402 stores one or more computer programs that can be executed by the at least one processor 401, and the one or more computer programs are executed by the at least one processor 401 to enable the at least one processor 401 to perform the above-mentioned voice quality inspection method.

[0125] The present disclosure also provides a computer-readable storage medium, which may be a volatile or non-volatile computer-readable storage medium and stores a computer program. When the computer program is executed by the processor 401:

[0126] For each quality inspection processing node, obtain task data of the corresponding quality inspection processing node, wherein the task data refers to execution logic data of the corresponding quality inspection processing node for executing the quality inspection task;

[0127] Determine the data to be run according to the task data, wherein the data to be run includes the database to be called by the corresponding quality inspection processing node and the identifier of the data;

[0128] After performing quality inspection processing on the data to be run to obtain an initial quality inspection result, verifying the initial quality inspection result according to the reference result of the corresponding quality inspection processing node to obtain a verification result;

[0129] If the verification result is passed, the target quality inspection result of the corresponding quality inspection processing node is determined according to the initial quality inspection result.

[0130] In some embodiments, before obtaining the task data of the corresponding quality inspection processing node, the processor 401 is further used to: when some or all of the multiple quality inspection processing nodes correspond to historical processing data, clear the historical processing data corresponding to each quality inspection processing node.

[0131] In some embodiments, the processor 401 is further configured to: The speech quality inspection method described in 1, characterized in that determining the data to be run according to the task data comprises:

[0132] Detecting whether the task data contains a task attribute field;

[0133] If the task data includes at least one task attribute field, performing parameter replacement processing on the at least one task attribute field to obtain primary replacement data, and determining the data to be run according to the primary replacement data;

[0134] If the task data does not include the task attribute field, the task data is determined as the data to be executed.

[0135] In some embodiments, if the task data includes at least one task attribute field and the task data also includes at least one field to be queried, the processor 401 is further configured to: obtain a data segment corresponding to each field to be queried from the first database, and replace the corresponding field to be queried with the corresponding data segment to obtain secondary replacement data;

[0136] Detecting whether each data segment of the secondary replacement data contains a task attribute field;

[0137] If any data segment contains a task attribute field, performing parameter replacement processing on the contained task attribute field to obtain three replacement data, and using the three replacement data as the data to be run;

[0138] If all data segments do not contain the task attribute field, the secondary replacement data is determined as the data to be executed.

[0139] In some embodiments, the processor 401 is further configured to perform parameter replacement processing corresponding to any task attribute field, including:

[0140] Obtaining attribute data corresponding to the task attribute field;

[0141] The task attribute fields are replaced with the attribute data.

[0142] In some embodiments, when the initial quality inspection result is a first initial quality inspection result parameter, the reference result is a first reference result, and the processor 401 is further configured to:

[0143] Detecting whether the initial quality inspection result is the same as the reference result;

[0144] If the initial quality inspection result is the same as the reference result, the verification result is determined to be passed.

[0145] In some embodiments, the initial quality inspection result includes one or more initial quality inspection result parameters. If the initial quality inspection result is multiple initial quality inspection result parameters, the reference result includes multiple pre-stored reference result values, and the initial quality inspection result parameter is the same as the reference result, including: if the initial quality inspection result includes one initial quality inspection result parameter, the initial quality inspection result parameter is the same as the value of the reference result; if the initial quality inspection result includes multiple initial quality inspection result parameters, each initial quality inspection result parameter is the same as the corresponding reference result value.

[0146] In some embodiments, the processor 401 is further configured to: determine whether the initial quality inspection result includes a field to be updated;

[0147] If the initial quality inspection result contains a field to be updated, obtain data corresponding to the field to be updated from the target database according to a preset rule, use the data corresponding to the field to be updated to replace the corresponding field to be updated in the initial quality inspection result, and use the replaced result as the target quality inspection result;

[0148] If the initial quality inspection result contains a field to be updated, the initial quality inspection result is used as the target quality inspection result.

[0149] In some embodiments, the processor 401 is further configured to: obtain data corresponding to the to-be-updated field from the target database according to at least one of the following:

[0150] Capturing second data from a second data segment of a second database according to a preset data capture rule, and determining the second data as data corresponding to the field to be updated;

[0151] Acquire third data from a third database according to preset data indication information, and use the third data as data corresponding to the field to be updated.

[0152] In some embodiments, the target quality inspection result is determined as task data of a next quality inspection processing node of the corresponding quality inspection processing node.

[0153] In some embodiments, the processor 401 is further configured to: terminate the voice quality inspection process if the verification result is failure to pass.

[0154] In some embodiments, the processor 401 is further configured to: output target quality inspection processing results of the multiple quality inspection processing nodes when the speech quality inspection process is completed.

[0155] An embodiment of the present disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above-mentioned voice quality inspection method.

[0156] It will be understood by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium).

[0157] As is well known to those skilled in the art, the term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information (such as computer-readable program instructions, data structures, program modules or other data). Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those skilled in the art, communication media typically contains computer-readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0158] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0159] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0160] The computer program product described herein may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0161] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0162] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0163] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0164] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the prescribed logical function. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the prescribed function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0165] Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted only in a general illustrative sense and not for purposes of limitation. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly indicated, features, characteristics, and / or elements described in conjunction with a particular embodiment may be used alone or in combination with features, characteristics, and / or elements described in conjunction with other embodiments. Therefore, it will be understood by those skilled in the art that various changes in form and detail may be made without departing from the scope of the present disclosure as set forth in the appended claims.

Claims

1. A voice quality inspection method, characterized in that: Applied to multiple quality inspection processing nodes, the multiple quality inspection processing nodes sequentially execute quality inspection tasks corresponding to the corresponding quality inspection processing nodes according to a preset process, the method includes: For each quality inspection processing node, obtain task data of the corresponding quality inspection processing node, wherein the task data refers to execution logic data of the corresponding quality inspection processing node for executing the quality inspection task; Determine the data to be run according to the task data, wherein the data to be run includes the database to be called by the corresponding quality inspection processing node and the identifier of the data; After performing quality inspection processing on the data to be run to obtain an initial quality inspection result, verifying the initial quality inspection result based on the reference result of the corresponding quality inspection processing node to obtain a verification result; wherein the initial quality inspection result is the quality inspection result generated by the corresponding quality inspection processing node running the data to be run; If the verification result is passed, the target quality inspection result of the corresponding quality inspection processing node is determined according to the initial quality inspection result.

2. The voice quality inspection method according to claim 1, wherein: Before obtaining the task data of the corresponding quality inspection processing node, the method further includes: If some or all of the multiple quality inspection processing nodes correspond to historical processing data, the historical processing data corresponding to each quality inspection processing node is cleared.

3. The voice quality inspection method according to claim 1, wherein: The determining of the data to be run according to the task data includes: Detecting whether the task data contains a task attribute field; If the task data includes at least one task attribute field, performing parameter replacement processing on the at least one task attribute field to obtain primary replacement data, and determining the data to be run according to the primary replacement data; If the task data does not include the task attribute field, the task data is determined as the data to be executed.

4. The voice quality inspection method according to claim 3, characterized in that: If the task data includes at least one task attribute field, and the task data also includes at least one field to be queried, determining the data to be run based on the primary replacement data includes: Obtaining a data segment corresponding to each to-be-queried field from the first database, and replacing the corresponding to-be-queried field with the corresponding data segment to obtain secondary replacement data; Detecting whether each data segment of the secondary replacement data contains a task attribute field; If any data segment contains a task attribute field, performing parameter replacement processing on the contained task attribute field to obtain three replacement data, and using the three replacement data as the data to be run; If all data segments do not contain the task attribute field, the secondary replacement data is determined as the data to be executed.

5. The speech quality inspection method according to claim 3 or 4, characterized in that: Corresponding to any task attribute field, parameter replacement processing is performed, including: Obtaining attribute data corresponding to the task attribute field; The task attribute fields are replaced with the attribute data.

6. The voice quality inspection method according to claim 1, characterized in that: The verifying the initial quality inspection result according to the reference result of the corresponding quality inspection processing node to obtain a verification result includes: Detecting whether the initial quality inspection result is the same as the reference result; If the initial quality inspection result is the same as the reference result, the verification result is determined to be passed.

7. The voice quality inspection method according to claim 6, characterized in that: The initial quality inspection result includes one or more initial quality inspection result parameters. If the initial quality inspection result includes multiple initial quality inspection result parameters, the reference result includes multiple pre-stored reference result values. The initial quality inspection result parameters are the same as the reference result, including: If the initial quality inspection result includes an initial quality inspection result parameter, the initial quality inspection result parameter is the same as the value of the reference result; If the initial quality inspection result includes multiple initial quality inspection result parameters, each initial quality inspection result parameter is the same as the corresponding reference result value.

8. The voice quality inspection method according to claim 1, wherein: Determining the target quality inspection result of the corresponding quality inspection processing node according to the initial quality inspection result includes: Determining whether the initial quality inspection result contains a field to be updated; If the initial quality inspection result contains a field to be updated, obtain data corresponding to the field to be updated from the target database according to a preset rule, use the data corresponding to the field to be updated to replace the corresponding field to be updated in the initial quality inspection result, and use the replaced result as the target quality inspection result; If the initial quality inspection result includes a field to be updated, the initial quality inspection result is determined as the target quality inspection result.

9. The voice quality inspection method according to claim 8, characterized in that: The acquiring data corresponding to the to-be-updated field from the target database according to a preset rule includes at least one of the following: Capturing second data from a second data segment of a second database according to a preset data capture rule, and using the second data as data corresponding to the field to be updated; Acquire third data from a third database according to preset data indication information, and use the third data as data corresponding to the field to be updated.

10. A speech quality inspection device, characterized in that: Applied to multiple quality inspection processing nodes, the multiple quality inspection processing nodes sequentially perform quality inspection tasks corresponding to the corresponding quality inspection processing nodes according to a preset process, the device includes: An acquisition module is used to acquire, for each quality inspection processing node, task data of the corresponding quality inspection processing node, where the task data refers to execution logic data of the quality inspection task executed by the corresponding quality inspection processing node; A determination module, configured to determine data to be run according to the task data, wherein the data to be run includes a database to be called by the corresponding quality inspection processing node and an identifier of the data; a quality inspection module configured to, after performing quality inspection processing on the data to be run to obtain an initial quality inspection result, verify the initial quality inspection result based on a reference result of the corresponding quality inspection processing node to obtain a verification result; wherein the initial quality inspection result is a quality inspection result generated by the corresponding quality inspection processing node running the data to be run; The determination module is further configured to determine a target quality inspection result of the corresponding quality inspection processing node according to the initial quality inspection result if the verification result is passed.

11. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs that can be executed by the at least one processor, and the one or more computer programs are executed by the at least one processor so that the at least one processor can perform the speech quality inspection method according to any one of claims 1 to 9.

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

Images