Double-recording quality inspection method and device and computer equipment

Abstract

The invention relates to a double-recording quality inspection method and device, computer equipment, a storage medium and a computer program product. Relates to the technical field of Internet. The method comprises the steps of calling a double-recording pre-quality-inspection intelligent model and displaying a pre-quality-inspection interface under the condition that a double-recording completion signal of a current double-recording node is received; based on the double-recording pre-quality-inspection intelligent model and a preset quality inspection standard, obtaining a pre-quality-inspection result of the current double-recording node; if it is determined that the pre-quality inspection result of the current double-recording node is not passed, obtaining a non-passing reason, and outputting a pre-quality inspection non-passing result and the non-passing reason through a pre-quality inspection interface; if it is determined that the pre-quality inspection result of the current double-recording node is passed, storing double-recording data corresponding to the current double-recording node, and outputting a pre-quality inspection passing result through a pre-quality inspection interface; and after the double-recording data and the pre-quality inspection result of each double-recording node, sending the double-recording data and the pre-quality inspection result of each double-recording node to a quality inspection terminal. By adopting the method, the double-recording quality inspection efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a double-recording quality inspection method, device, computer equipment, storage medium and computer program product. Background Art

[0002] With the development of Internet finance, in order to protect the rights and interests of customers, it is necessary to record and video the scene simultaneously, that is, double recording. In addition, the recorded audio and video need to be quality checked. If the audio and video quality can meet the specified requirements, the recorded audio and video will be saved; otherwise, it needs to be re-recorded.

[0003] However, the current dual-recording quality inspection relies on manual quality inspection, which requires that the audio and video of all nodes be recorded and uploaded, and then the quality inspectors watch the audio and video in full and inspect the audio and video of all nodes one by one, which is time-consuming. Therefore, there is currently a problem of low efficiency in dual-recording quality inspection. Summary of the invention

[0004] Based on this, it is necessary to provide a double recording quality inspection method, device, computer equipment, computer readable storage medium and computer program product to address the above-mentioned technical problem of low efficiency of double recording quality inspection.

[0005] In a first aspect, the present application provides a dual recording quality inspection method, comprising:

[0006] When receiving the dual recording completion signal of the current dual recording node, calling the dual recording pre-quality inspection intelligent model and displaying the pre-quality inspection interface; the current dual recording node is any node in the business process corresponding to the dual recording identifier;

[0007] Based on the dual-recording pre-quality inspection intelligent model and the preset quality inspection standard, obtaining the pre-quality inspection result of the dual-recording data corresponding to the current dual-recording node; wherein different dual-recording nodes correspond to different preset quality inspection standards;

[0008] According to the pre-quality inspection result, if it is determined that the pre-quality inspection result of the current dual-recording node is not passed, the reason for the failure is obtained, and the pre-quality inspection failure result of the current dual-recording node and the reason for the failure are output through the pre-quality inspection interface; if it is determined that the pre-quality inspection result of the current dual-recording node is passed, the dual-recording data corresponding to the current dual-recording node is saved, and the pre-quality inspection pass result of the current dual-recording node is output through the pre-quality inspection interface;

[0009] After obtaining the dual recording data and the pre-quality inspection result of each dual recording node in the business process, the dual recording data and the pre-quality inspection result of each dual recording node in the business process are sent to the quality inspection terminal.

[0010] In one of the embodiments, when the dual recording completion signal of the current dual recording node is received, the dual recording pre-quality inspection intelligent model is called and the pre-quality inspection interface is displayed, including: when the voice broadcast of the end of the last speech link of the current dual recording node is announced, the next operation option is activated; in response to the trigger operation of the next operation option, the dual recording pre-quality inspection intelligent model is called and the pre-quality inspection interface is displayed; based on the dual recording pre-quality inspection intelligent model and the preset quality inspection standard, the pre-quality inspection result of the dual recording data corresponding to the current dual recording node is obtained, including: based on the dual recording pre-quality inspection intelligent model, the preset quality inspection standard corresponding to each of the dual recording nodes is obtained respectively; wherein the preset quality inspection standard includes at least one of the passability of voice recognition, the frequency of occurrence of negative words, whether there is a correct face, and whether the data display is abnormal; the dual recording data corresponding to each of the dual recording nodes is compared with the preset quality inspection standard to obtain the pre-quality inspection result corresponding to each of the dual recording nodes.

[0011] In one embodiment, the pre-quality inspection results include passed, failed, and pending manual review; after comparing the dual recording data corresponding to each of the dual recording nodes with the preset quality inspection standards to obtain the pre-quality inspection results corresponding to each of the dual recording nodes, it includes: when the pre-quality inspection result of the current dual recording node is the above-mentioned pending manual review, outputting the above-mentioned pre-quality inspection result pending manual review through the pre-quality inspection interface, sending the pre-quality inspection result corresponding to the current dual recording node to the quality inspection terminal, and starting the manual review operation.

[0012] In one of the embodiments, the method further includes: when the pre-quality inspection result of each of the dual recording nodes in the business process is passed or pending manual review, in response to a trigger operation of the end recording option, the dual recording is stopped, a preset first end recording confirmation prompt is popped up, and in response to a confirmation operation on the first end recording confirmation prompt, the dual recording interface is exited; when the pre-quality inspection result of a dual recording node in the business process is failed, in response to a trigger operation of the end recording option, a preset second end recording confirmation prompt is popped up, and in response to a confirmation operation on the second end recording confirmation prompt, the dual recording is stopped and the dual recording interface is exited; in response to a cancel operation on the second end recording confirmation prompt, the second end recording confirmation prompt is closed, and dual recording is continued for the certain dual recording node.

[0013] In one of the embodiments, the method further includes: when the pre-quality inspection result of each of the dual-recording nodes in the business process is the pass or fail, selecting a single or multiple dual-way nodes and a re-recording button, popping up the node name of the single or multiple dual-recording nodes and a preset rectification confirmation prompt, responding to a confirmation operation on the preset rectification confirmation prompt, starting a rectification operation, and after completing the dual-recording of the rectification node, popping up a preset end-recording prompt, responding to the preset end-recording prompt, completing the dual-recording of the rectification node; and canceling the rectification operation in response to a cancel operation on the preset rectification confirmation prompt.

[0014] In one of the embodiments, the method further includes: setting a prompt box for portrait detection and comparison results in the business process, responding to portrait monitoring at a preset time node, obtaining the comparison result, responding to the prompt box according to the comparison result, and displaying information data of the user corresponding to the policyholder, the insured or the agent in the prompt box.

[0015] In a second aspect, the present application also provides a dual recording quality inspection device, comprising:

[0016] A signal receiving module, used to call the dual-recording pre-quality inspection intelligent model and display the pre-quality inspection interface when receiving the dual-recording completion signal of the current dual-recording node; the current dual-recording node is any node corresponding to the dual-recording identifier in the business process;

[0017] A result acquisition module, used to obtain the pre-quality inspection result of the dual-recording data corresponding to the current dual-recording node based on the dual-recording pre-quality inspection intelligent model and the preset quality inspection standard; wherein different dual-recording nodes correspond to different preset quality inspection standards;

[0018] A result output module is used to obtain the reason for failure based on the pre-quality inspection result, and output the pre-quality inspection failure result of the current dual recording node and the reason for failure through the pre-quality inspection interface if the pre-quality inspection result of the current dual recording node is determined to be failed; if the pre-quality inspection result of the current dual recording node is determined to be passed, save the dual recording data corresponding to the current dual recording node, and output the pre-quality inspection pass result of the current dual recording node through the pre-quality inspection interface;

[0019] The result sending module is used to send the dual recording data and the pre-quality inspection result of each dual recording node in the business process to the quality inspection terminal after obtaining the dual recording data and the pre-quality inspection result of each dual recording node in the business process.

[0020] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0021] When receiving the dual recording completion signal of the current dual recording node, calling the dual recording pre-quality inspection intelligent model and displaying the pre-quality inspection interface; the current dual recording node is any node in the business process corresponding to the dual recording identifier;

[0022] Based on the dual-recording pre-quality inspection intelligent model and the preset quality inspection standard, obtaining the pre-quality inspection result of the dual-recording data corresponding to the current dual-recording node; wherein different dual-recording nodes correspond to different preset quality inspection standards;

[0023] According to the pre-quality inspection result, if it is determined that the pre-quality inspection result of the current dual-recording node is not passed, the reason for the failure is obtained, and the pre-quality inspection failure result of the current dual-recording node and the reason for the failure are output through the pre-quality inspection interface; if it is determined that the pre-quality inspection result of the current dual-recording node is passed, the dual-recording data corresponding to the current dual-recording node is saved, and the pre-quality inspection pass result of the current dual-recording node is output through the pre-quality inspection interface;

[0024] After obtaining the dual recording data and the pre-quality inspection result of each dual recording node in the business process, the dual recording data and the pre-quality inspection result of each dual recording node in the business process are sent to the quality inspection terminal.

[0025] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0026] When receiving the dual recording completion signal of the current dual recording node, calling the dual recording pre-quality inspection intelligent model and displaying the pre-quality inspection interface; the current dual recording node is any node in the business process corresponding to the dual recording identifier;

[0027] Based on the dual-recording pre-quality inspection intelligent model and the preset quality inspection standard, obtaining the pre-quality inspection result of the dual-recording data corresponding to the current dual-recording node; wherein different dual-recording nodes correspond to different preset quality inspection standards;

[0028] According to the pre-quality inspection result, if it is determined that the pre-quality inspection result of the current dual-recording node is not passed, the reason for the failure is obtained, and the pre-quality inspection failure result of the current dual-recording node and the reason for the failure are output through the pre-quality inspection interface; if it is determined that the pre-quality inspection result of the current dual-recording node is passed, the dual-recording data corresponding to the current dual-recording node is saved, and the pre-quality inspection pass result of the current dual-recording node is output through the pre-quality inspection interface;

[0029] After obtaining the dual recording data and the pre-quality inspection result of each dual recording node in the business process, the dual recording data and the pre-quality inspection result of each dual recording node in the business process are sent to the quality inspection terminal.

[0030] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which implements the following steps when executed by a processor:

[0031] When receiving the dual recording completion signal of the current dual recording node, calling the dual recording pre-quality inspection intelligent model and displaying the pre-quality inspection interface; the current dual recording node is any node in the business process corresponding to the dual recording identifier;

[0032] Based on the dual-recording pre-quality inspection intelligent model and the preset quality inspection standard, obtaining the pre-quality inspection result of the dual-recording data corresponding to the current dual-recording node; wherein different dual-recording nodes correspond to different preset quality inspection standards;

[0033] According to the pre-quality inspection result, if it is determined that the pre-quality inspection result of the current dual-recording node is not passed, the reason for the failure is obtained, and the pre-quality inspection failure result of the current dual-recording node and the reason for the failure are output through the pre-quality inspection interface; if it is determined that the pre-quality inspection result of the current dual-recording node is passed, the dual-recording data corresponding to the current dual-recording node is saved, and the pre-quality inspection pass result of the current dual-recording node is output through the pre-quality inspection interface;

[0034] After obtaining the dual recording data and the pre-quality inspection result of each dual recording node in the business process, the dual recording data and the pre-quality inspection result of each dual recording node in the business process are sent to the quality inspection terminal.

[0035] The above-mentioned dual recording quality inspection method, device, computer equipment, storage medium and computer program product have the following beneficial effects in the process of dual recording quality inspection: first, when receiving the dual recording completion signal of the current dual recording node, the dual recording pre-quality inspection intelligent model is called and the pre-quality inspection interface is displayed; the current dual recording node is any node corresponding to a dual recording identifier in the business process; then, based on the dual recording pre-quality inspection intelligent model and the preset quality inspection standard, the pre-quality inspection result of the dual recording data corresponding to the current dual recording node is obtained; wherein different dual recording nodes correspond to different preset quality inspection standards; then, according to the preset Quality inspection results: if it is determined that the pre-quality inspection result of the current dual recording node is failed, the reason for failure is obtained, and the pre-quality inspection failure result and the reason for failure of the current dual recording node are output through the pre-quality inspection interface; if it is determined that the pre-quality inspection result of the current dual recording node is passed, the dual recording data corresponding to the current dual recording node is saved, and the pre-quality inspection pass result of the current dual recording node is output through the pre-quality inspection interface; finally, after obtaining the dual recording data and pre-quality inspection results of each dual recording node in the business process, the dual recording data and pre-quality inspection results of each dual recording node in the business process are sent to the quality inspection terminal. In the above process, the dual-recording pre-quality inspection intelligent model can quickly identify quality problems of dual-recording data, reduce the time of manual review, and improve quality inspection efficiency; and different dual-recording nodes have different preset quality inspection standards to ensure the quality of each dual-recording node; in addition, regardless of whether the pre-quality inspection result of the dual-recording node is passed or failed, it can be reflected to the quality inspection terminal in a timely manner, achieving real-time monitoring of the entire dual-recording pre-quality inspection process; therefore, the above process improves the efficiency of dual-recording quality inspection on the basis of ensuring the accuracy of dual-recording quality inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 This is an application environment diagram of a dual recording quality inspection method in an embodiment;

[0038] Figure 2 A schematic diagram of a flow chart of a double recording quality inspection method in one embodiment;

[0039] Figure 3 A detailed flowchart of a double recording quality inspection step in one embodiment;

[0040] Figure 4 It is a structural block diagram of a dual recording quality inspection device in one embodiment;

[0041] Figure 5FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] The dual recording quality inspection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the quality inspection terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. First, when the server 104 receives the dual recording completion signal of the current dual recording node, the dual recording pre-quality inspection intelligent model is called and the pre-quality inspection interface is displayed; the current dual recording node is any node in the business process that corresponds to a dual recording identifier; then, the server 104 obtains the pre-quality inspection result of the dual recording data corresponding to the current dual recording node based on the dual recording pre-quality inspection intelligent model and the preset quality inspection standard; wherein different dual recording nodes correspond to different preset quality inspection standards; then, the server 104 determines the pre-quality inspection result of the current dual recording node based on the pre-quality inspection result. If the pre-quality inspection result of the current dual recording node is determined to be passed, the dual recording data corresponding to the current dual recording node is saved, and the pre-quality inspection result of the current dual recording node is output through the pre-quality inspection interface; finally, after the server 104 obtains the dual recording data and pre-quality inspection result of each dual recording node in the business process, the dual recording data and pre-quality inspection result of each dual recording node in the business process are sent to the quality inspection terminal 102. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0044] In an exemplary embodiment, Figure 2 As shown, a double recording quality inspection method is provided, which is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S202 to S208. Among them:

[0045] Step S202, when receiving the dual recording completion signal of the current dual recording node, calling the dual recording pre-quality inspection intelligent model and displaying the pre-quality inspection interface; the current dual recording node is any node in the business process corresponding to the dual recording identifier.

[0046] Among them, the current dual recording node refers to the key point in the business process where dual recording and video recording are required at the current moment, which is usually used to ensure the accuracy and completeness of information feedback. Each current dual recording node has a clear function and purpose, such as customer identity confirmation, transaction records, etc.; the dual recording completion signal is a trigger signal, indicating that the recording and video recording of the current dual recording node have been completed; the dual recording pre-quality inspection intelligent model is an artificial intelligence-based model that can analyze the quality of dual recording data; the pre-quality inspection interface is an interface used to display business processes to users.

[0047] Step S204, based on the dual-recording pre-quality inspection intelligent model and the preset quality inspection standard, obtain the pre-quality inspection result of the dual-recording data corresponding to the current dual-recording node; wherein different dual-recording nodes correspond to different preset quality inspection standards.

[0048] Among them, the preset quality inspection standards are a series of quality inspection standards set for different dual recording nodes; the pre-quality inspection results refer to the results generated based on the pre-quality inspection standards and analyzed by the dual recording pre-quality inspection intelligent model, indicating whether the dual recording data of the current node meets the preset standards.

[0049] As an example, the preset quality inspection standards may include recording clarity, information completeness, time sequence, etc.

[0050] Step S206, based on the pre-quality inspection result, if it is determined that the pre-quality inspection result of the current dual recording node is failed, the reason for failure is obtained, and the pre-quality inspection failure result and the reason for failure of the current dual recording node are output through the pre-quality inspection interface; if it is determined that the pre-quality inspection result of the current dual recording node is passed, the dual recording data corresponding to the current dual recording node is saved, and the pre-quality inspection pass result of the current dual recording node is output through the pre-quality inspection interface.

[0051] Among them, passing means that the data recorded by the current dual recording node meets the quality standards; failing means that the data recorded by the current dual recording node needs to be improved.

[0052] As an example, when the pre-quality inspection result of the current dual recording node is failed, it is necessary to obtain the failure reason and the failure result and output them through the pre-quality inspection interface. When the pre-quality inspection result of the current dual recording node is passed, it is only necessary to output the pass result through the pre-quality inspection interface.

[0053] Step S208, after obtaining the dual recording data and the pre-quality inspection result of each dual recording node in the business process, the dual recording data and the pre-quality inspection result of each dual recording node in the business process are sent to the quality inspection terminal.

[0054] Among them, the quality inspection terminal can be a terminal for centrally managing and analyzing dual recording data and its pre-quality inspection results, and can be used to ensure that the dual recording data of each dual recording node is managed in a unified manner.

[0055] In the above-mentioned dual recording quality inspection method, first, when the dual recording completion signal of the current dual recording node is received, the dual recording pre-quality inspection intelligent model is called and the pre-quality inspection interface is displayed; the current dual recording node is any node corresponding to the dual recording identifier in the business process; then, based on the dual recording pre-quality inspection intelligent model and the preset quality inspection standard, the pre-quality inspection result of the dual recording data corresponding to the current dual recording node is obtained; wherein different dual recording nodes correspond to different preset quality inspection standards; then, according to the pre-quality inspection result, if it is determined that the pre-quality inspection result of the current dual recording node is failed, the reason for failure is obtained, and the pre-quality inspection failure result and the reason for failure of the current dual recording node are output through the pre-quality inspection interface; if it is determined that the pre-quality inspection result of the current dual recording node is passed, the dual recording data corresponding to the current dual recording node is saved, and the pre-quality inspection pass result of the current dual recording node is output through the pre-quality inspection interface; finally, after obtaining the dual recording data and pre-quality inspection results of each dual recording node in the business process, the dual recording data and pre-quality inspection results of each dual recording node in the business process are sent to the quality inspection terminal. In the above process, the dual-recording pre-quality inspection intelligent model can quickly identify quality problems of dual-recording data, reduce the time of manual review, and improve quality inspection efficiency; and different dual-recording nodes have different preset quality inspection standards to ensure the quality of each dual-recording node; in addition, regardless of whether the pre-quality inspection result of the dual-recording node is passed or failed, it can be reflected to the quality inspection terminal in a timely manner, achieving real-time monitoring of the entire dual-recording pre-quality inspection process; therefore, the above process improves the efficiency of dual-recording quality inspection on the basis of ensuring the accuracy of dual-recording quality inspection.

[0056] In one embodiment, when a dual recording completion signal of the current dual recording node is received, a dual recording pre-quality inspection intelligent model is called and a pre-quality inspection interface is displayed, including: when the voice broadcast of the last speech link of the current dual recording node ends, the next operation option is activated; in response to the trigger operation of the next operation option, the dual recording pre-quality inspection intelligent model is called and the pre-quality inspection interface is displayed; based on the dual recording pre-quality inspection intelligent model and the preset quality inspection standard, the pre-quality inspection result of the dual recording data corresponding to the current dual recording node is obtained, including: based on the dual recording pre-quality inspection intelligent model, the preset quality inspection standard corresponding to each dual recording node is obtained respectively; wherein the preset quality inspection standard includes at least one of the passability of speech recognition, the frequency of occurrence of negative words, whether there is a correct face, and whether the data display is abnormal; the dual recording data corresponding to each dual recording node is compared with the preset quality inspection standard to obtain the pre-quality inspection result corresponding to each dual recording node.

[0057] Among them, speech recognition passability refers to whether the speech content in the dual-recording data can be accurately recognized and transcribed, which is an important indicator for evaluating the quality of recording and is used to ensure that the information can be effectively understood and used; the frequency of negative words refers to the frequency of detecting negative words, such as "not" and "no", in the dual-recording data. High-frequency negative words may indicate user doubts or dissatisfaction, thereby affecting the processing of subsequent services and the management of user relationships; whether there is a correct face refers to checking whether the correct user face can be recognized in the dual-recording video, which is used to ensure the authenticity of the user's identity and the effectiveness of identity verification during the recording process; whether the data display is abnormal refers to evaluating whether there are any abnormalities in the display process of the dual-recording output data, such as too low recording volume, incomplete audio clips, or inconsistent display information, which helps to prevent potential data loss or misleading information dissemination. In addition, the current dual-recording node includes at least one of the above preset quality inspection standards.

[0058] In this embodiment, the preset quality inspection standards corresponding to each dual recording node are obtained by utilizing the dual recording pre-quality inspection intelligent model, which covers multiple important aspects, such as the accuracy of speech recognition, the frequency of negative words, the authenticity of the customer's face, and the integrity of data display. The dual recording data collected by each dual recording node will then be compared with the corresponding preset standards to ensure that the data of each dual recording node meets the corresponding quality requirements. If not, potential problems can be discovered and corrected in a timely manner.

[0059] Furthermore, in one embodiment, the pre-quality inspection results include passed, failed, and pending manual review; after comparing the dual recording data corresponding to each dual recording node with the preset quality inspection standard to obtain the pre-quality inspection results corresponding to each dual recording node, it includes: when the pre-quality inspection result of the current dual recording node is the above-mentioned pending manual review, the above-mentioned pre-quality inspection result pending manual review is output through the pre-quality inspection interface, and the pre-quality inspection result corresponding to the current dual recording node is sent to the quality inspection terminal, and the manual review operation is started.

[0060] Among them, the manual review operation refers to the manual review process that is initiated after the quality inspection terminal receives the pre-quality inspection results. This process usually involves quality inspectors conducting in-depth reviews of unqualified double-recording data, analyzing the causes, and providing correction plans to further ensure the quality of the double-recording data.

[0061] As an example, after the manual review operation, corresponding actions may be taken to improve the quality of dual-recording data, such as re-recording designated dual-recording nodes, training customer service personnel, adjusting service processes, modifying quality inspection standards, etc.

[0062] In this embodiment, by sending the pre-quality inspection results to the quality inspection terminal, the transmission of the pre-quality inspection result data can be realized, and the reliability of the transmission process is guaranteed, and sensitive information and user data are protected. In addition, quality inspectors can conveniently view the dual recording data quality assessment results of each dual recording node on the quality inspection terminal to ensure the quality of the dual recording data.

[0063] In an exemplary embodiment, when the pre-quality inspection result of each dual recording node in the business process is passed or pending manual review, in response to the trigger operation of the end recording option, the dual recording is stopped, and a preset first end recording confirmation prompt is popped up, and in response to the confirmation operation of the first end recording confirmation prompt, the dual recording interface is exited; if the pre-quality inspection result of a dual recording node in the business process is failed, in response to the trigger operation of the end recording option, a preset second end recording confirmation prompt is popped up, and in response to the confirmation operation of the second end recording confirmation prompt, the dual recording is stopped and the dual recording interface is exited; in response to the cancel operation of the second end recording confirmation prompt, the second end recording confirmation prompt is closed, and dual recording continues for a dual recording node.

[0064] Among them, the failure reason refers to the specific problems or defects caused by the dual recording node failing to meet the pre-quality inspection standards during the pre-quality inspection process, which may include voice recognition failure, too high frequency of negative words, failure to recognize the correct face, and abnormal data display; verification refers to the process of the quality inspection terminal re-confirming and checking the dual recording data corresponding to the dual recording node, that is, after the quality inspection terminal receives the failure reason, the quality inspector uses the received failure reason to re-analyze whether there is a problem with the specific dual recording data.

[0065] In this embodiment, by sending the reasons for failure to the quality inspection terminal, the quality inspectors can conduct an in-depth review of the double-recorded data based on the specific reasons for failure, and then obtain the root cause of the problem and specify corresponding improvement measures, which is crucial for continuously improving the overall data quality and optimizing the service experience.

[0066] Furthermore, in one embodiment, when the pre-quality inspection results of each dual-recording node in the business process are passed or failed, a single or multiple dual-way nodes and a re-recording button are selected, and the node names of the single or multiple dual-recording nodes and a preset rectification confirmation prompt are popped up. In response to the confirmation operation of the preset rectification confirmation prompt, the rectification operation is started. After the dual-recording of the rectification node is completed, a preset end-recording prompt is popped up. In response to the preset end-recording prompt, the dual-recording of the rectification node is completed; in response to the cancellation operation of the preset rectification confirmation prompt, the rectification operation is canceled.

[0067] Among them, double recording correction refers to the process of modifying or supplementing problematic double recording data, which may involve re-recording audio or video, correcting errors in the transcribed text, and adjusting the recording quality; updated double recording data refers to the new data obtained after double recording correction; updated pre-quality inspection results refer to the pre-quality inspection results of the new data.

[0068] As an example, no matter whether the pre-quality inspection result of the current dual recording node is passed or failed, dual recording correction can be performed to obtain updated dual recording data, and pre-quality inspection operation can be performed on the updated dual recording data.

[0069] In this embodiment, by performing double recording correction on the double recording data, the data quality can be checked again, including voice accuracy, identity authentication, face recognition and other aspects, which further improves the accuracy of the double recording data and lays a good foundation for improving service quality.

[0070] In one embodiment, a prompt box for portrait detection and comparison results is set in the business process, and portrait monitoring is responded to at a preset time node to obtain the comparison result. The prompt box is responded to according to the comparison result, and the information data of the user corresponding to the policyholder, the insured or the agent is displayed in the prompt box.

[0071] Among them, overwriting refers to applying new pre-quality inspection results to existing records to replace the original pre-quality inspection results that may be erroneous or inaccurate, ensuring that the pre-quality inspection interface of the quality inspection terminal outputs the latest quality inspection results.

[0072] As an example, before overwriting, it is necessary to confirm the relevance of the pre-quality inspection results to ensure that only the pre-quality inspection results related to the corresponding dual recording node are replaced to avoid affecting other irrelevant data; in addition, the overwriting operation may require logging for review and data tracking; and, it is also necessary to send the updated pre-quality inspection results to the quality inspection terminal in a timely manner to ensure that the quality inspectors obtain the updated quality inspection results in a timely manner.

[0073] In this embodiment, by sending the updated pre-quality inspection result to the quality inspection terminal and overwriting the pre-quality inspection result of the corresponding dual recording node, the accuracy and reliability of the data can be effectively improved.

[0074] This application provides a dual recording quality inspection method. In order to better understand the process of the dual recording quality inspection method, combined with Figure 3 As shown, the specific process of the double recording quality inspection method of this application is described in detail below, including the following steps:

[0075] Step S302: After the closing remarks of the last dual-recording node of the business process are finished, click Next to automatically jump to the pre-quality inspection interface.

[0076] Step S304, obtaining the pre-quality inspection result of each node.

[0077] Specifically, the pre-quality inspection results include passed, failed, and pending manual review. If all dual-recording nodes are passed, the final conclusion of the pre-quality inspection will display the words "Intelligent pre-quality inspection passed"; if it includes failed dual-recording nodes, the final conclusion of the pre-quality inspection will display the words "Intelligent pre-quality inspection failed".

[0078] Furthermore, for the failed dual recording nodes, the corresponding reasons for failure are provided. The reasons may be one or more of the following combinations: speech recognition failure, recognition of negative words, absence of relevant personnel, abnormal display of pictures or documents. As long as negative words are recognized or speech recognition fails, such as skipping speech recognition or not recognizing positive answers, the status of the dual recording node is failed, and the reasons for failure and rectification suggestions are given.

[0079] Step S306, click "End Recording" to stop dual recording.

[0080] If all dual recording nodes pass or are waiting for manual quality inspection, click "End Recording" to stop dual recording, and a prompt will pop up: "Are you sure to end this recording?" Click "OK" to exit the dual recording interface; if it includes failed dual recording nodes, click "End Recording" to display a pop-up prompt: "You have x problem nodes that have not been rectified, are you sure to end the recording?" Click the "Confirm" button to stop dual recording, exit the dual recording interface, click the "Cancel" button to close the pop-up window and continue recording.

[0081] In addition, regardless of whether the pre-quality inspection results are passed or not, you can select a single or multiple dual recording nodes for rectification. For example, if you select multiple dual recording nodes, record them in sequence according to the dual recording node order.

[0082] Specifically, after selecting the dual-recording node to be rectified, the "Re-recording" button changes from gray to clickable. After clicking, a pop-up window will prompt the user the name of the dual-recording node to be rectified. Click "Confirm" to start the rectification. Click "Cancel" to close the pop-up window. After the dual-recording node being rectified completes the recording, a pop-up window will automatically pop up to prompt the user that the self-rectification operation has been completed. Click "End Recording" to complete the recording. In addition, the pre-quality inspection results can be viewed on the review page.

[0083] What's more, after the recording is finished, the pre-quality inspection interface will jump directly to the video playback page, and only one screen recording video will be displayed on the playback page. If the resume recording function is turned on, there can be multiple videos. In addition, the video of the dual recording node in the pre-quality inspection interface supports video playback. Click the play icon in the node list to play back a single node. In addition, the quality inspection result video displayed on the playback page is a collection of the first recording and the dual recording correction. If the dual recording node has been corrected, the new pre-quality inspection result will overwrite the original pre-quality inspection result.

[0084] Step S308: Send the dual recording data and pre-quality inspection results of each dual recording node in the business process to the quality inspection terminal.

[0085] Furthermore, real-time intelligent auxiliary recognition is performed for each link. Part of the display page of the pre-quality inspection interface is a built-in page, and part is a called HTML (HyperText Markup Language) page. The image display part is a called h5 page. The front end uses JSBridge to feedback the real-time image anomaly detection results, such as the browser's built-in img.error (image loading status), to the pre-quality inspection interface. Voice recognition is an additional function in the pre-quality inspection interface. The voice recognition results of each dual-recording node are saved to the quality inspection terminal, and different situations are marked differently. Before submission, the intelligent pre-quality inspection node can promptly feedback the data obtained from the quality inspection terminal to the user without waiting time, so that the user can immediately make dual-recording corrections to the dual-recording nodes. When the user confirms the submission, all pre-quality inspection results are submitted to the quality inspection terminal. At the same time, at each node, if the voice recognition function of the pre-quality inspection interface does not recognize the correct wording, it will be sent through JSBridge (JavaScript The pre-quality inspection process is carried out by sending the pre-quality inspection result to the quality inspection terminal and displaying it in real time on the quality inspection terminal. For remote dual recording, the process is similar to local dual recording, and all pre-quality inspection results will be saved to the quality inspection terminal. Voice recognition results and display anomalies can be transmitted to the quality inspection terminal through messages. The data recorded in the database includes the specific reasons and time for failure of the dual recording node. In the pre-quality inspection interface, you can directly click the reasons for failure of the pre-quality inspection to jump to the corresponding position of the video corresponding to the dual recording node for verification. The judgment criteria of the pre-quality inspection process involve browser judgment, background algorithm judgment, etc. The audio quality inspection based on AI algorithm capability will involve the technology of voiceprint filtering and recognition. The reading and display of image files will be inspected based on the judgment tools provided by the browser and the agreed sliding browsing situation. In addition, during the recording process, real-time portraits are also detected and compared with relevant personnel collected in advance. A white box will be displayed outside to show whether the current role is the policyholder, agent or other identity. The detection is triggered every 10 seconds to ensure that the participants are online throughout the process. When an abnormality occurs, it will also be saved, that is, the AI ​​face recognition capability is applied to the business.

[0086] Through the above embodiments, artificial intelligence is applied to the pre-quality inspection process of the dual recording node, which improves the quality inspection efficiency and the quality of the dual recording. In addition, after the initial recording is completed, the problems in the dual recording can be known, and self-correction and re-recording can be carried out in time, further improving the efficiency of the dual recording quality inspection.

[0087] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0088] Based on the same inventive concept, the embodiment of the present application also provides a dual recording quality inspection device for implementing the dual recording quality inspection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more dual recording quality inspection device embodiments provided below can refer to the limitations of the dual recording quality inspection method above, and will not be repeated here.

[0089] In an exemplary embodiment, Figure 4 As shown, a dual recording quality inspection device is provided, including: a signal receiving module 401, a result acquisition module 402, a result output module 403 and a result sending module 404, wherein:

[0090] The signal receiving module 401 is used to call the dual-recording pre-quality inspection intelligent model and display the pre-quality inspection interface when receiving the dual-recording completion signal of the current dual-recording node; the current dual-recording node is any node in the business process corresponding to the dual-recording identifier.

[0091] The result acquisition module 402 is used to acquire the pre-quality inspection result of the dual recording data corresponding to the current dual recording node based on the dual recording pre-quality inspection intelligent model and the preset quality inspection standard; wherein different dual recording nodes correspond to different preset quality inspection standards.

[0092] The result output module 403 is used to obtain the reason for failure based on the pre-quality inspection result, and output the pre-quality inspection failure result and the reason for failure of the current dual recording node through the pre-quality inspection interface; if the pre-quality inspection result of the current dual recording node is determined to be passed, save the dual recording data corresponding to the current dual recording node, and output the pre-quality inspection pass result of the current dual recording node through the pre-quality inspection interface.

[0093] The result sending module 404 is used to send the dual recording data and the pre-quality inspection result of each dual recording node in the business process to the quality inspection terminal after obtaining the dual recording data and the pre-quality inspection result of each dual recording node in the business process.

[0094] Furthermore, in one embodiment, the result acquisition module 402 is also used to activate the next operation option when the voice broadcast of the last speech link of the current dual recording node ends; in response to the trigger operation of the next operation option, call the dual recording pre-quality inspection intelligent model and display the pre-quality inspection interface; based on the dual recording pre-quality inspection intelligent model, respectively obtain the preset quality inspection standards corresponding to each dual recording node; wherein the preset quality inspection standards include at least one of the passability of speech recognition, the frequency of occurrence of negative words, whether there is a correct face, and whether the data display is abnormal; compare the dual recording data corresponding to each dual recording node with the preset quality inspection standard to obtain the pre-quality inspection results corresponding to each dual recording node.

[0095] Furthermore, in one embodiment, the result acquisition module 402 is also used to output the pre-quality inspection result to be manually reviewed through the pre-quality inspection interface when the pre-quality inspection result of the current dual recording node is the one to be manually reviewed, and send the pre-quality inspection result corresponding to the current dual recording node to the quality inspection terminal, and start the manual review operation.

[0096] Furthermore, in one embodiment, the result acquisition module 402 is also used for stopping the dual recording in response to a trigger operation of the end recording option when the pre-quality inspection result of each of the dual recording nodes in the business process is passed or pending manual review, and popping up a preset first end recording confirmation prompt; in response to a confirmation operation on the first end recording confirmation prompt, exiting the dual recording interface; if the pre-quality inspection result of a dual recording node in the business process is failed, in response to a trigger operation of the end recording option, a preset second end recording confirmation prompt is popped up; in response to a confirmation operation on the second end recording confirmation prompt, stopping the dual recording and exiting the dual recording interface; in response to a cancel operation on the second end recording confirmation prompt, closing the second end recording confirmation prompt, and continuing to perform dual recording for the dual recording node.

[0097] Furthermore, in one embodiment, the result output module 403 is also used to select a single or multiple dual-way nodes and a re-recording button when the pre-quality inspection result of each of the dual-recording nodes in the business process is the pass or the fail, pop up the node name of the single or multiple dual-recording nodes and a preset rectification confirmation prompt, respond to the confirmation operation of the preset rectification confirmation prompt, start the rectification operation, and after completing the dual-recording of the rectification node, pop up a preset end-recording prompt, respond to the preset end-recording prompt, complete the dual-recording of the rectification node; respond to the cancellation operation of the preset rectification confirmation prompt, cancel the rectification operation.

[0098] Furthermore, in one embodiment, the result output module 403 is also used to set a prompt box for portrait detection and comparison results in the business process, respond to portrait monitoring at a preset time node, obtain the comparison result, respond to the prompt box according to the comparison result, and display the information data of the user corresponding to the policyholder, the insured or the agent in the prompt box.

[0099] Each module in the above-mentioned dual recording quality inspection device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0100] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store dual-recording quality inspection data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a dual-recording quality inspection method is implemented.

[0101] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0102] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0103] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0104] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0105] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0106] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0107] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A double recording quality inspection method, characterized in that: The method comprises: When receiving the dual recording completion signal of the current dual recording node, calling the dual recording pre-quality inspection intelligent model and displaying the pre-quality inspection interface; the current dual recording node is any node in the business process corresponding to the dual recording identifier; Based on the dual-recording pre-quality inspection intelligent model and the preset quality inspection standard, obtaining the pre-quality inspection result of the dual-recording data corresponding to the current dual-recording node; wherein different dual-recording nodes correspond to different preset quality inspection standards; According to the pre-quality inspection result, if it is determined that the pre-quality inspection result of the current dual-recording node is not passed, the reason for the failure is obtained, and the pre-quality inspection failure result of the current dual-recording node and the reason for the failure are output through the pre-quality inspection interface; if it is determined that the pre-quality inspection result of the current dual-recording node is passed, the dual-recording data corresponding to the current dual-recording node is saved, and the pre-quality inspection pass result of the current dual-recording node is output through the pre-quality inspection interface; After obtaining the dual recording data and the pre-quality inspection result of each dual recording node in the business process, the dual recording data and the pre-quality inspection result of each dual recording node in the business process are sent to the quality inspection terminal.

2. The method according to claim 1, characterized in that: When receiving the dual recording completion signal of the current dual recording node, calling the dual recording pre-quality inspection intelligent model and displaying the pre-quality inspection interface includes: When the voice broadcast of the last speech link of the current dual recording node ends, activating the next operation option; In response to the triggering operation of the next operation option, calling the dual recording pre-quality inspection intelligent model and displaying the pre-quality inspection interface; Based on the dual-recording pre-quality inspection intelligent model and the preset quality inspection standard, obtaining the pre-quality inspection result of the dual-recording data corresponding to the current dual-recording node, including: Based on the dual-recording pre-quality inspection intelligent model, the preset quality inspection standard corresponding to each dual-recording node is obtained respectively; wherein the preset quality inspection standard includes at least one of the passability of speech recognition, the frequency of occurrence of negative words, whether there is a correct face, and whether the data display is abnormal; The dual recording data corresponding to each of the dual recording nodes is compared with a preset quality inspection standard to obtain the pre-quality inspection result corresponding to each of the dual recording nodes.

3. The method according to claim 2, characterized in that The pre-quality inspection results include passed, failed, and pending manual review; After comparing the dual recording data corresponding to each of the dual recording nodes with a preset quality inspection standard to obtain the pre-quality inspection result corresponding to each of the dual recording nodes, the method includes: When the pre-quality inspection result of the current dual recording node is the one to be manually reviewed, the pre-quality inspection result to be manually reviewed is output through the pre-quality inspection interface, and the pre-quality inspection result corresponding to the current dual recording node is sent to the quality inspection terminal, and the manual review operation is started.

4. The method according to claim 1, characterized in that: The method further comprises: When the pre-quality inspection result of each dual recording node in the business process is passed or pending manual review, in response to a trigger operation of the end recording option, the dual recording is stopped, a preset first end recording confirmation prompt is popped up, and in response to a confirmation operation of the first end recording confirmation prompt, the dual recording interface is exited; The pre-quality inspection result of a dual recording node in the business process is failed. In response to the trigger operation of the end recording option, a preset second end recording confirmation prompt pops up. In response to the confirmation operation of the second end recording confirmation prompt, the dual recording is stopped and the dual recording interface is exited; in response to the cancel operation of the second end recording confirmation prompt, the second end recording confirmation prompt is closed, and the dual recording is continued for the dual recording node.

5. The method according to claim 4, characterized in that The method further comprises: When the pre-quality inspection result of each dual-recording node in the business process is passed or failed, select a single or multiple dual-way nodes and a re-recording button, pop up the node name of the single or multiple dual-recording nodes and a preset rectification confirmation prompt, respond to the confirmation operation of the preset rectification confirmation prompt, start the rectification operation, after completing the dual-recording of the rectification node, pop up a preset end-recording prompt, respond to the preset end-recording prompt, complete the dual-recording of the rectification node; respond to the cancellation operation of the preset rectification confirmation prompt, cancel the rectification operation.

6. The method according to claim 1, characterized in that The method further comprises: A prompt box for portrait detection and comparison results is set in the business process, and portrait monitoring is responded to at a preset time node to obtain the comparison result. The prompt box is responded to according to the comparison result, and information data of the user corresponding to the policyholder, the insured or the agent is displayed in the prompt box.

7. A dual recording quality inspection device, characterized in that: The device comprises: A signal receiving module, used to call the dual-recording pre-quality inspection intelligent model and display the pre-quality inspection interface when receiving the dual-recording completion signal of the current dual-recording node; the current dual-recording node is any node corresponding to the dual-recording identifier in the business process; A result acquisition module, used to obtain the pre-quality inspection result of the dual-recording data corresponding to the current dual-recording node based on the dual-recording pre-quality inspection intelligent model and the preset quality inspection standard; wherein different dual-recording nodes correspond to different preset quality inspection standards; A result output module is used to obtain the reason for failure based on the pre-quality inspection result, and output the pre-quality inspection failure result of the current dual recording node and the reason for failure through the pre-quality inspection interface if the pre-quality inspection result of the current dual recording node is determined to be failed; if the pre-quality inspection result of the current dual recording node is determined to be passed, save the dual recording data corresponding to the current dual recording node, and output the pre-quality inspection pass result of the current dual recording node through the pre-quality inspection interface; The result sending module is used to send the dual recording data and the pre-quality inspection result of each dual recording node in the business process to the quality inspection terminal after obtaining the dual recording data and the pre-quality inspection result of each dual recording node in the business process.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A 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 according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images