Task Processing Method and Device

Abstract

An embodiment of the present application provides a task processing method and apparatus. A user return visit task to be processed and its corresponding return visit control are displayed on a task processing terminal. After receiving a first input from a first user to the return visit control, a user return visit request is sent to a server to trigger the server to automatically control the task processing terminal to return visit a user terminal corresponding to the user return visit task. In this way, the seat management personnel can not only view the return visit tasks to be processed in a timely manner, but also quickly trigger the sending of a user return visit request to the server through the return visit control. Thus, the seat management personnel can timely return visit and comfort the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits. And since the user return visit tasks are automatically generated for information interaction events between the seat terminal and the user terminal, the process of generating return visit tasks is not affected by human factors, improving the accuracy of the user return visit tasks displayed on the task processing terminal.

Description

Technical Field

[0001] This application relates to the technical field of intelligent customer service, and particularly to a task processing method and device. Background Art

[0002] Currently, with the rapid development of intelligent customer service technology, in order to provide more efficient online business services for customers, intelligent contact center systems have emerged. Seat personnel can make calls to customers or answer customer calls more efficiently and conveniently through the intelligent contact center system to answer some of the customers' questions. However, some unexpected situations may occur during the call between the seat personnel and the customer. For example, due to the poor attitude of the seat personnel in answering questions, the customer may be dissatisfied with the seat personnel. Another example is that the customer has an emergency and has a bad attitude, but the seat personnel does not use the correct handling method to relieve the customer's doubts. These situations may all lead to subsequent customer complaint incidents. Therefore, in order to reduce the probability of customer complaint incidents, professional personnel need to specifically appease the customers who may initiate complaints. However, in the prior art, professional personnel cannot quickly and accurately identify the customers who need to be appeased in a timely manner, resulting in the problem of untimely customer appeasement. Summary of the Invention

[0003] The purpose of the embodiments of this application is to provide a task processing method and device. The seat manager can not only view the to-be-processed return visit tasks in the first time, but also quickly trigger and send a user return visit request to the server through the return visit control. Thus, the seat manager can timely return visit and appease the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits. And because the user return visit tasks displayed on the task processing terminal are automatically generated based on the information interaction events between the seat terminal and the user terminal, the generation process of the return visit tasks is not affected by human factors. In this way, it can not only improve the timeliness of return visits to customers, but also improve the accuracy of the user return visit tasks displayed on the task processing terminal.

[0004] In order to achieve the above technical solution, the embodiments of this application are implemented as follows:

[0005] In a first aspect, a task processing method provided by the embodiments of this application includes:

[0006] Receiving a first input from a first user to a return visit control; the return visit control is configured for the user return visit task displayed on the visual interface, and the user return visit task is generated based on the information interaction event between the seat terminal and the user terminal;

[0007] In response to the first input, generate a user return visit request; the user return visit request carries the identification information of the task processing terminal corresponding to the agent terminal and the identification information of the user terminal;

[0008] Send the user return visit request to the server, so that in response to the user return visit request through the server, control the task processing terminal to make a return visit to the user terminal.

[0009] In a second aspect, a task processing method provided by an embodiment of the present application includes:

[0010] Receive a user return visit request from a task processing terminal; the user return visit request is sent after detecting a first input by a first user to a return visit control, and the return visit control is configured for a user return visit task displayed on a visual interface, and the user return visit task is generated based on an information interaction event between an agent terminal and a user terminal;

[0011] In response to the user return visit request, control the task processing terminal to make a return visit to the user terminal.

[0012] In a third aspect, a task processing device provided by an embodiment of the present application includes:

[0013] A first input receiving module, configured to receive a first input by a first user to a return visit control; the return visit control is configured for a user return visit task displayed on a visual interface, and the user return visit task is generated based on an information interaction event between an agent terminal and a user terminal;

[0014] A return visit request generating module, configured to generate a user return visit request in response to the first input; the user return visit request carries the identification information of the task processing terminal corresponding to the agent terminal and the identification information of the user terminal;

[0015] A return visit request sending module, configured to send the user return visit request to the server, so that in response to the user return visit request through the server, control the task processing terminal to make a return visit to the user terminal.

[0016] In a fourth aspect, a task processing device provided by an embodiment of the present application includes:

[0017] A return visit request receiving module, configured to receive a user return visit request from a task processing terminal; the user return visit request is sent after detecting a first input by a first user to a return visit control, and the return visit control is configured for a user return visit task displayed on a visual interface, and the user return visit task is generated based on an information interaction event between an agent terminal and a user terminal;

[0018] A user return visit control module, configured to control the task processing terminal to make a return visit to the user terminal in response to the user return visit request.

[0019] In a fifth aspect, a task processing device provided by an embodiment of the present application includes:

[0020] A processor; and a memory arranged to store computer-executable instructions, the executable instructions being configured to be executed by the processor, the executable instructions including steps for executing the methods described in the first aspect or the second aspect.

[0021] In a sixth aspect, a storage medium provided by an embodiment of the present application, wherein the storage medium is used to store computer-executable instructions, and the executable instructions cause a computer to execute the steps in the methods described in the first aspect or the second method.

[0022] It can be seen that in the embodiment of the present application, the user return visit tasks to be processed and their corresponding return visit controls are displayed on the task processing terminal. After receiving the first input of the first user to the return visit control, a user return visit request is sent to the server to trigger the server to automatically control the task processing terminal to make a return visit to the user terminal corresponding to the user return visit task. In this way, the seat management personnel can not only view the return visit tasks to be processed in a timely manner, but also quickly trigger the sending of a user return visit request to the server through the return visit control. Thus, the seat management personnel can timely make a return visit and comfort the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits; and since the user return visit tasks are automatically generated for the information interaction events between the seat terminal and the user terminal, the generation process of the return visit tasks is not affected by human factors, improving the accuracy of the user return visit tasks displayed on the task processing terminal, and thus realizing more accurate and timely comfort for key users. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some of the embodiments described in one or more of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0024] Figure 1 It is a schematic diagram of the application scenario of the task processing system provided by the embodiment of the present application;

[0025] Figure 2 It is the first flowchart of the task processing method provided by the embodiment of the present application;

[0026] Figure 3aSchematic diagram of multi - terminal interaction for the task processing method provided by the embodiments of the present application;

[0027] Figure 3b The first interface display schematic diagram of the user return visit task in the task processing method provided by the embodiments of the present application;

[0028] Figure 3c The second interface display schematic diagram of the user return visit task in the task processing method provided by the embodiments of the present application;

[0029] Figure 4 The third interface display schematic diagram of the user return visit task in the task processing method provided by the embodiments of the present application;

[0030] Figure 5 The fourth interface display schematic diagram of the user return visit task in the task processing method provided by the embodiments of the present application;

[0031] Figure 6a The fifth interface display schematic diagram of the user return visit task in the task processing method provided by the embodiments of the present application;

[0032] Figure 6b The sixth interface display schematic diagram of the user return visit task in the task processing method provided by the embodiments of the present application;

[0033] Figure 7 The second process schematic diagram of the task processing method provided by the embodiments of the present application;

[0034] Figure 8 The first module composition schematic diagram of the task processing device provided by the embodiments of the present application;

[0035] Figure 9 The second module composition schematic diagram of the task processing device provided by the embodiments of the present application;

[0036] Figure 10 Structure schematic diagram of the task processing device provided by the embodiments of the present application. Detailed implementation manners

[0037] In order to enable those skilled in the art to better understand the technical solutions in one or more of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part, rather than all, of the embodiments of one or more of the present application. Based on the embodiments in one or more of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0038] It should be noted that, without conflict, one or more embodiments in the present application and the features in the embodiments may be combined with each other. The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0039] Considering that during the process of information interaction between the seat terminal and the user terminal, the customer may be dissatisfied with the seat personnel due to insufficient professionalism or bad attitude of the seat personnel in answering questions. Therefore, in order to reduce the probability of customer complaints, it is necessary for the seat management personnel to conduct timely follow-up visits and comfort the customers. However, if the seat management personnel manually call the customers to be followed up for follow-up visits, the operation steps of the entire user follow-up visit process are relatively cumbersome. Based on this, in the embodiments provided in the present application, by displaying the user follow-up visit tasks to be processed and their corresponding follow-up visit controls on the task processing terminal, after receiving the first input of the first user to the follow-up visit control, a user follow-up visit request is sent to the server to trigger the server to automatically control the task processing terminal to conduct a follow-up visit to the user terminal corresponding to the user follow-up visit task. In this way, the seat management personnel can not only view the follow-up visit tasks to be processed in a timely manner, but also quickly trigger the sending of a user follow-up visit request to the server through the follow-up visit control. Thus, the seat management personnel can timely conduct a follow-up visit and comfort to the target users involved in the user follow-up visit tasks, thereby improving the timeliness of user follow-up visits; and since the user follow-up visit tasks are automatically generated for the information interaction events between the seat terminal and the user terminal, the generation process of the follow-up visit tasks is not affected by human factors, improving the accuracy of the user follow-up visit tasks displayed on the task processing terminal, and thus realizing more accurate and timely comfort to key users.

[0040] Also considering the generation process of user return visit tasks, if the managers of the artificial agents monitor the calls, and when the managers identify sensitive words during the call, it is determined that there are user return visit tasks to be processed, and then the customers are visited and comforted. This not only increases the workload of the managers and the labor cost, but also has the problems of high task processing cost and low efficiency. Based on this, this technical solution obtains the sensitive word detection result corresponding to the target interaction data, where the target interaction data is generated based on the information interaction event between the agent terminal and the user terminal; if the sensitive word detection result meets the first abnormal constraint condition, then based on the sensitive word detection result, the return visit task information of the target user is generated; the return visit task information is sent to the target management terminal corresponding to the agent terminal, so that the target management terminal displays the user return visit task corresponding to the received return visit task information on the visualization interface, so that the managers can view the user return visit tasks to be processed in the first time, and thus the managers can timely visit and comfort the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits; also considering that if the call voice data between the agent terminal and the user terminal is automatically detected for sensitive words, and then the managers judge whether to visit and comfort the customers based on the sensitive word detection result, there is a problem that the human participation in whether to visit and comfort the customers leads to low accuracy of customer return visits. Based on this, since this technical solution automatically generates the return visit task information based on the sensitive word detection result of the target interaction data and then automatically generates the user return visit task based on the return visit task information, the generation process of the user return visit task is not affected by human factors, and thus the accuracy of the user return visit task displayed on the target management terminal can be improved.

[0041] Figure 1 It is a schematic diagram of the application scenario of the task processing system provided by the embodiment of this application, as Figure 1 shown. The system includes: a background server, a user terminal, an agent terminal, and a management terminal. Among them, the user terminal, the agent terminal, and the management terminal can be mobile terminals such as smart phones and tablet computers, and the user terminal, the agent terminal, and the management terminal can also be terminal devices such as personal computers. The background server can be a business server for monitoring the target interaction data between the agent terminal and the user terminal and triggering the management terminal to display the corresponding user return visit tasks. The background server can be an independent server or a server cluster composed of multiple servers. The management terminal can be a terminal device used by professional personnel specifically responsible for customer return visits or the superior of the agent personnel, such as the original management terminal of the agent terminal, the superior management terminal of the original management terminal, or the allocated management terminal after the return visit task is allocated; among them, the specific process of task processing is as follows:

[0042] The background server obtains the target interaction data corresponding to the target information interaction event, and performs sensitive word detection on the target interaction data to obtain the sensitive word detection result; wherein, the target interaction data includes the interaction data generated during the information interaction between the agent terminal and the user terminal;

[0043] If the above sensitive word detection result meets the first abnormal constraint condition, the background server generates the return visit task information of the target user based on the above sensitive word detection result;

[0044] After the background server generates the return visit task information for the above target information interaction event, it sends the return visit task information to the task processing terminal; in specific implementation, the generated return visit task information can be directly sent to the task processing terminal, or the return visit task information can be first sent to the original management terminal corresponding to the agent terminal, and then sent to the task processing terminal (i.e., the allocated management terminal) after receiving the task allocation request;

[0045] The task processing terminal receives the return visit task information sent by the background server, and displays the user return visit task and the return visit control corresponding to the received return visit task information on the visualization interface;

[0046] The task processing terminal receives the first input of the first user to the return visit control, and generates a user return visit request in response to the first input, and sends the user return visit request to the background server;

[0047] The background server responds to the above user return visit request, and controls the task processing terminal to return visit the user terminal.

[0048] In specific implementation, during the information interaction between the agent terminal and the user terminal, the background server can obtain the target interaction sub-data between the agent terminal and the user terminal at a preset time interval, and perform sensitive word detection on the target interaction sub-data to obtain the sensitive word sub-detection result; if the sensitive word sub-detection result meets the second abnormal constraint condition, an interaction abnormal alarm information is generated based on the sensitive word sub-detection result; the interaction abnormal alarm information is sent to the above agent terminal; the agent terminal receives and displays the interaction abnormal alarm information, so as to realize the abnormal alarm for the agent personnel using the agent terminal; then, after the information interaction between the agent terminal and the user terminal ends, based on the sensitive word sub-detection results of multiple target interaction sub-data, a sensitive word detection result is generated, and then a return visit task information is generated based on the sensitive word detection result.

[0049] Figure 2 It is the first process schematic diagram of the task processing method provided by one or more embodiments of the present application, Figure 2 The method in Figure 1executed by the management terminal therein. The management terminal can be the original management terminal of the agent terminal, or the superior management terminal of the original management terminal, or the allocated management terminal for processing user return visit tasks, or the terminal device used by professionals specifically responsible for customer return visits, such as Figure 2 As shown in

[0050] S202, receiving a first input from a first user to a return visit control; wherein, the return visit control is configured based on a user return visit task displayed on a visual interface, and the user return visit task is generated based on an information interaction event between an agent terminal and a user terminal;

[0051] Specifically, a corresponding return visit control can be configured for each user return visit task; wherein, the above first input can be a triggering operation of the first user on the return visit control, such as a click operation; in a specific implementation, a user return visit request can also be triggered and generated by means of a voice command or a specific gesture. Specifically, the first input can also be a voice command input by the user, or a specific gesture input by the user, which can be specifically determined according to actual usage requirements, and the embodiments of the present application do not limit this; in addition, the specific gesture can be any one of a click gesture, a swipe gesture, a drag gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double press gesture, and a double click gesture; the click operation can be a single click, a double click, or a click trigger operation of any number of times, and can also be a long press or short press trigger operation.

[0052] Specifically, the user return visit task is generated based on the return visit task information sent by the server, and the return visit task information is generated when the sensitive word detection result corresponding to the target interaction data satisfies a first abnormal constraint condition, and the target interaction data is generated based on an information interaction event between an agent terminal and a user terminal.

[0053] S204, generating a user return visit request in response to the above first input; wherein, the user return visit request carries the identification information of the task processing terminal corresponding to the agent terminal and the identification information of the user terminal;

[0054] Specifically, after detecting the first input, the task processing terminal determines the target user corresponding to the user return visit task targeted by the first input, and the target user is the service object in the information interaction event corresponding to the user return visit task; then, a user return visit request carrying the identification information of the task processing terminal and the identification information of the user terminal corresponding to the target user is automatically generated.

[0055] S206, sending the above user return visit request to the server, so that the server responds to the above user return visit request and controls the task processing terminal to return visit the user terminal.

[0056] Specifically, to simplify the return visit operation steps of seat managers, thereby improving the customer return visit efficiency of seat managers and enabling one-key triggering of user return visits, the background server receives a user return visit request from the task processing terminal; among them, the user return visit request is generated by the task processing terminal based on detecting a return visit trigger operation of the first user, and the return visit trigger operation is a trigger operation of the first user on the return visit control corresponding to the user return visit task, and the return visit control is displayed on the visual interface of the task processing terminal;

[0057] In response to the received user return visit request, the background server controls the establishment of a voice call link between the task processing terminal and the user terminal, or controls the task processing terminal to display an instant chat window with the user terminal.

[0058] Among them, for each user return visit task, the management terminal that first receives the return visit task information corresponding to the user return visit task is the target management terminal, and the management terminal that finally receives the return visit task information corresponding to the user return visit task is the task processing terminal; in specific implementation, considering that there may be task allocation and task allocation includes task delegation or task assignment, the target management terminal can be the original management terminal or the allocated management terminal. Similarly, the above task processing terminal can be the original management terminal or the allocated management terminal. Therefore, the target management terminal and the task processing terminal can be the same management terminal or different management terminals;

[0059] Specifically, for the case of no task allocation, the target management terminal and the task processing terminal are the same, that is, both are the original management terminal of the seat terminal; for the case where the task allocation is task delegation, the target management terminal and the task processing terminal are the same, that is, the allocated management terminal. That is to say, after receiving the task allocation request, the return visit task information is directly sent to the allocated management terminal; for the case where the task allocation is task assignment, the target management terminal and the task processing terminal are different, that is, the target management terminal is the original management terminal and the task processing terminal is the allocated management terminal. That is to say, the return visit task information is first sent to the original management terminal, and then after receiving the task allocation request, the return visit task information is sent to the allocated management terminal.

[0060] Specifically, during the process of the task processing terminal making a return visit to the user terminal, a voice call return visit method can be adopted, or a return visit method based on an instant messaging window can be used (i.e., sending an instant messaging message to the user terminal for a return visit), or other return visit methods can be adopted. Specifically, at least one return visit control is configured for each user return visit task. The seat management staff can trigger the task processing terminal to send a user return visit request to the background server by clicking the return visit control, that is, request the background server to make a return visit to the target user, so that the background server triggers the establishment of an information interaction link between the task processing terminal and the user terminal, and sends the return visit request response information returned for the user return visit request to the task processing terminal. Among them, the return visit request response information includes the response information for instructing the establishment of a voice call link with the user terminal, or the response information for instructing the display of an instant messaging window with the user terminal. In this way, the seat management staff can directly click the return visit control on the visual interface to automatically trigger a call back to the target user (i.e., perform an outbound operation on the user terminal) or open an instant messaging chat interface with the target user to make a return visit and comfort the target user.

[0061] In specific implementation, multiple return visit controls can be configured for each user return visit task, and each return visit control corresponds to a return visit method. For example, the return visit method corresponding to return visit control 1 is the voice call return visit method, and the return visit method corresponding to return visit control 2 is the return visit method based on an instant messaging window. Specifically, different return visit methods can be specified for different user return visit tasks. For example, the return visit method is consistent with the interaction method adopted in the information interaction process. It can also be that the seat management staff selects the required return visit method according to the actual situation. If it is necessary to make a return visit to the target user by using the voice call return visit method, the seat management staff can click return visit control 1. Correspondingly, if it is necessary to make a return visit to the target user based on an instant messaging window, the seat management staff can click return visit control 2.

[0062] In specific implementation, the above-mentioned return visit control can be displayed on the return visit task display page, or on the task details display page, or on both the return visit task display page and the task details display page. Taking the display of the return visit control on the task details display page as an example, as Figure 4As shown, after the seat manager enters the task details display page of a certain user return visit task, the seat manager can click the return visit control 1 to trigger a voice call to the target user, and the seat manager can also click the return visit control 2 to trigger entering an instant conversation window with the user terminal; moreover, the return visit result information can also be displayed on the task details display page, and the return visit result information can be manually filled in by the seat manager or automatically generated and displayed; for example, the information items included in the return visit result information can be: the unique identifier callID of the management terminal, the user appeasement result, the note information, the task processing result, etc.

[0063] Specifically, for the generation process of the user return visit task displayed on the target management terminal or the task processing terminal, before receiving the first input of the first user to the return visit control in S202 above, it further includes:

[0064] Receiving the return visit task information sent by the server; wherein, the return visit task information is generated when the sensitive word detection result corresponding to the above information interaction event meets the interaction exception constraint condition, and the sensitive word detection result is obtained based on the target interaction data generated by the above information interaction event;

[0065] Among them, the above interaction exception constraint condition is the above first exception constraint condition; the above first exception constraint condition may include at least one of the number of sensitive words being greater than the first preset threshold, the danger level of the sensitive words being higher than the first level threshold (i.e., high-risk sensitive words), and the number of high-risk sensitive words being greater than the second preset threshold; specifically, when the sensitive word detection result is obtained, if the sensitive word detection result meets the first exception constraint condition, it means that the current call between the seat terminal and the user terminal is unpleasant and the user needs to be appeased in time. Therefore, the return visit task information of the target user can be generated based on the above sensitive word detection result.

[0066] Generating a user return visit task based on the above return visit task information; wherein, the return visit task information includes at least one of the sensitive word detection result, the user portrait information of the target user, the task processing priority of the user return visit task, and the task processing validity period.

[0067] Displaying the above user return visit task and the return visit control corresponding to the user return visit task on the visualization interface.

[0068] Further, for the process of displaying the user return visit task on the visualization interface of the management terminal, in order to facilitate the seat manager to quickly locate the key information items of the user return visit task and facilitate the seat manager to quickly locate the user return visit tasks that need to be processed preferentially, based on this, generating the user return visit task based on the above return visit task information includes:

[0069] Determine multiple sub-information in the above return visit task information as the first information item;

[0070] Generate a user return visit task based on the above first information item and second information item; wherein, the second information item may include task dynamic change information, and the task dynamic change information includes: task processing status information and / or remaining processing time limit information;

[0071] Correspondingly, after generating a user return visit task based on the above return visit task information, it further includes:

[0072] Update the above task dynamic change information based on the above return visit task information and the current task node information.

[0073] Specifically, the above target management terminal or task processing management terminal displays the first information item and the second information item corresponding to the user return visit task on the visualization interface; wherein, the above first information item includes multiple sub-information in the received return visit task information, and the above second information item includes task processing status information and / or remaining processing time limit information determined based on the received return visit task information.

[0074] In specific implementation, the above first information item may include the first information item subset displayed on the return visit task display page and the second information item subset displayed on the task details display page. For the above second information item, since the second information item is determined based on the return visit task information, it is usually used to characterize the processing situation of the user return visit task. For example, task processing status information and / or remaining processing time limit information. Based on this, the second information item can also be used as a task brief information item, that is, task processing status information and / or remaining processing time limit information are displayed on the return visit task display page; that is to say, the above visualization interface may include a return visit task display page and a task details display page.

[0075] Furthermore, in order to facilitate the seat management staff to view the task details information, a details viewing control is configured for each user return visit task. The seat management staff can view the task details information of the corresponding user return visit task by clicking the details viewing control. Based on this, after generating a user return visit task based on the above return visit task information, it further includes:

[0076] Receive a third input from the first user to the task details viewing control;

[0077] In response to the above third input, display the task detailed information of the user return visit task corresponding to the task details viewing control.

[0078] Among them, the above third input may be a triggering operation of the first user on the task details viewing control, such as a click operation; in specific implementation, it can also trigger the viewing of task details through voice commands or specific gestures. Specifically, the third input can also be a voice command input by the user, or a specific gesture input by the user, which can be specifically determined according to actual usage requirements, and this application embodiment does not make limitations in this regard; in addition, the specific gesture can be any one of a click gesture, a slide gesture, a drag gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double press gesture, and a double click gesture; the click operation can be a single click, a double click, or a click triggering operation of any number of times, and can also be a long press or short press triggering operation.

[0079] Specifically, the specific process of generating a return visit task information for the target interaction data corresponding to the information interaction event between the agent terminal and the user terminal is as follows:

[0080] Step 1, obtain the sensitive word detection result corresponding to the target interaction data, where the target interaction data is generated during the information interaction between the agent terminal and the user terminal; among them, the target interaction data may include the call voice data generated by the call between the agent terminal and the user terminal, or the conversation text data (such as instant messaging messages) generated by the conversation between the agent terminal and the user terminal.

[0081] It should be noted that in this application embodiment, the application scenario of voice call interaction between the agent terminal and the user terminal is taken as an example for detailed description. The specific implementation process for text conversation interaction between the agent terminal and the user terminal can refer to the specific implementation process of voice call interaction, which will not be elaborated here.

[0082] Specifically, for the application scenario of voice call interaction, after establishing a call connection between the agent terminal and the user terminal, obtain the call voice data (i.e., the target interaction data) between the agent terminal and the user terminal, and then obtain the sensitive word detection result corresponding to the call voice data.

[0083] In specific implementation, after the call between the seat staff and the target user ends, the call voice data generated during the entire call process can be obtained, and the sensitive word detection is performed on the call voice data to obtain the sensitive word detection result. Further, in order to detect in real time whether sensitive words appear during the call between the seat staff and the target user, so as to give an abnormal alarm to the seat staff in a timely manner, therefore, the call voice segments (i.e., target interaction sub-data) between the seat terminal and the user terminal can be obtained at preset time intervals, and the sensitive word detection is performed on the call voice segments to obtain the sensitive word sub-detection result, that is, during the entire call process between the seat terminal and the user terminal (i.e., a call event), the sensitive word detection is performed on multiple call voice segments to obtain multiple sensitive word sub-detection results; then, after the call between the seat staff and the target user ends, based on the multiple sensitive word sub-detection results corresponding to this call event, the sensitive word detection result corresponding to the call voice data generated by this call event is generated.

[0084] It should be noted that the determination process of the above sensitive word detection result can be executed by the first server that generates the return visit task information, or can be executed by other servers, such as the second server specifically responsible for sensitive word detection, and the second server sends the sensitive word detection result to the first server; among them, the above sensitive word detection result can include not only the detected sensitive word information, but also at least one of the danger level of each sensitive word, the type to which the sensitive word belongs (such as violent tendency words, unhealthy color words, or uncivilized words, etc.), and the source information of the sensitive word (such as the seat staff or the target user).

[0085] Step 2, if the above sensitive word detection result meets the first abnormal constraint condition, then based on the above sensitive word detection result, generate the return visit task information of the target user, where the target user is the service object in the information interaction process.

[0086] Among them, the above return visit task information may include: the first sub-information included in the sensitive word detection result, for example, at least one of the detected sensitive word information, the danger level of each sensitive word, the type to which the sensitive word belongs (such as violent tendency words, unhealthy color words, or uncivilized words, etc.), and the source information of the sensitive word (such as the seat personnel or the target user); the return visit task information may also include: the second sub-information obtained based on the first sub-information included in the sensitive word detection result, for example, at least one of the return visit task type (such as high customer complaint probability, unprofessional language of the seat, major risk, general risk, etc.), the task processing priority, the task processing validity period, and the sensitive word change trend. Among them, the task processing validity period may be determined based on the task processing priority and the return visit task type. For example, for return visit tasks with the same return visit task type, the higher the task processing priority, the shorter the task processing validity period; the return visit task information may also include: the third sub-information related to the attribute information of the target user, such as user portrait information.

[0087] Specifically, after generating the corresponding return visit task information for a certain information interaction event, the above return visit task information is sent to the target management terminal and / or the task processing terminal corresponding to the seat terminal; then, after receiving the return visit task information, the target management terminal or the task processing terminal displays a user return visit task on the visualization interface based on some or all of the information items in the return visit task information.

[0088] In specific implementation, a part of the information items in the return visit task information (i.e., the task brief information item, the first information item subset) can be displayed on the return visit task display page, and another part of the information items in the return visit task information (i.e., the task details information item, the second information item subset) can be displayed on the task details display page; correspondingly, a details viewing control can be configured for each user return visit task, and the task details information items in the return visit task information are displayed on the task details display page. Specifically, after the target management terminal detects the trigger operation of the user on the details viewing control, a task details display page including the details information items is displayed. The task details information items may include user portrait information, sensitive word details information (i.e., the correspondence between the sensitive word information, the danger level of each sensitive word, the type to which the sensitive word belongs, and the source information of the sensitive word), and the sensitive word change trend.

[0089] Specifically, after generating the return visit task information, not only can the return visit task information be sent to the target management terminal and / or the task processing terminal, but also the return visit task information can be sent to the superior management terminal of the target management terminal, so that the superior management terminal can display the corresponding user return visit task on the visualization interface. In this way, the superior management personnel can timely understand what user return visit tasks the seat management personnel under their responsibility need to handle, how the processing progress of the user return visit tasks is, etc., and can also make task allocation in a timely manner.

[0090] In an embodiment of the present application, by obtaining the sensitive word detection result corresponding to the target interaction data generated during the information interaction between the agent terminal and the user terminal; if the sensitive word detection result meets the first abnormal constraint condition, then based on the sensitive word detection result, generate the return visit task information of the target user; send the return visit task information to the target management terminal corresponding to the agent terminal, so that the target management terminal displays the user return visit task corresponding to the received return visit task information on the visualization interface, so that the management personnel can view the user return visit task to be processed in a timely manner, so that the management personnel can timely conduct a return visit and comfort the target user involved in the user return visit task, thereby improving the timeliness of the user return visit; and, since the return visit task information is automatically generated based on the sensitive word detection result of the target interaction data, and then the user return visit task is automatically generated based on the return visit task information, therefore, the generation process of the user return visit task is not affected by human factors, so as to improve the accuracy of the user return visit task displayed on the target management terminal, and then realize more accurate and timely comfort of key users.

[0091] Furthermore, in order to detect in real time whether sensitive words appear during the information interaction between the agent and the target user, so as to timely give an abnormal alarm to the agent and timely correct the irregular business behavior of the agent. Based on this, before step 1 of obtaining the sensitive word detection result corresponding to the target interaction data, it further includes:

[0092] Step A1, obtain the sensitive word sub-detection result corresponding to the target interaction sub-data; wherein, the target interaction sub-data is generated during a specified time period in the information interaction between the agent terminal and the user terminal, and the sensitive word detection result corresponding to the above-mentioned target interaction data is generated based on at least one sensitive word sub-detection result;

[0093] Specifically, still taking the application scenario of voice call interaction as an example, during the call, obtain the call voice segments between the agent terminal and the user terminal at preset time intervals, and perform sensitive word detection on the call voice segments, that is, detect in real time whether the call voice segments contain sensitive words, and generate corresponding sensitive word sub-detection results;

[0094] It should be noted that the process of determining the above-mentioned sensitive word sub-detection result can also be executed by the first server that generates the callback task information, or by other servers, such as the second server specifically responsible for sensitive word detection. The second server sends the sensitive word sub-detection result to the first server. Among them, the above-mentioned sensitive word sub-detection result can include not only the detected sensitive word information, but also at least one of the danger level of each sensitive word, the type to which the sensitive word belongs (such as words with violent tendencies, words with unhealthy colors, or uncivilized words, etc.), and the source information of the sensitive word (such as the seat staff or the target user).

[0095] In addition, in specific implementation, still taking the application scenario of voice call interaction as an example, for the case of obtaining the call voice segments between the seat terminal and the user terminal at preset time intervals, the above-mentioned sensitive word sub-detection result can be the sensitive word sub-detection result for the call voice segments in a certain unit time period (i.e., one time interval). Correspondingly, after the call ends, the sensitive word sub-detection results of the call voice segments obtained in each unit time period are summarized to obtain the sensitive word detection result; it can also be the sensitive word sub-detection result obtained by summarizing the sensitive word sub-detection results of multiple call voice segments (i.e., the call voice segments corresponding to multiple unit time periods) between the start time of the call and the current call time. In this way, the sensitive word sub-detection result obtained at the end of the call can be used as the sensitive word detection result.

[0096] Step A2, if the above-mentioned sensitive word sub-detection result meets the second abnormal constraint condition, then based on the above-mentioned sensitive word sub-detection result, generate an interactive abnormal alarm message.

[0097] Among them, the above-mentioned second abnormal constraint condition can include at least one of the number of sensitive words being greater than the third preset threshold (the third preset threshold is less than or equal to the above-mentioned first preset threshold), the danger level of the sensitive word being higher than the first level threshold (i.e., high-risk sensitive words), and the number of high-risk sensitive words being greater than the fourth preset threshold (the fourth preset threshold is less than or equal to the above-mentioned second preset threshold). Specifically, when the sensitive word sub-detection result is obtained, if the sensitive word sub-detection result meets the second abnormal constraint condition, it indicates that an unexpected situation has occurred during the information interaction between the seat terminal and the user terminal, and it is necessary to give an alarm prompt to the seat staff. Therefore, an interactive abnormal alarm message can be generated based on the above-mentioned sensitive word sub-detection result.

[0098] Step A3, send the above-mentioned interactive abnormal alarm message to the seat terminal, where the seat terminal is used to display the received interactive abnormal alarm message to give an abnormal alarm to the seat staff using the seat terminal.

[0099] Specifically, not only the interactive anomaly warning information is sent to the agent terminal, but also it can be sent to the target management terminal at the same time, so that the target management terminal can timely understand the emergencies in the information interaction process. When the emergencies are relatively urgent, corresponding control measures can be adopted;

[0100] Specifically, for the process of generating a sensitive word detection result based on at least one sensitive word sub-detection result, at least one of the total number of sensitive words, the detailed information of sensitive words, and the change trend of sensitive words can be determined based on at least one sensitive word sub-detection result to obtain the sensitive word detection result;

[0101] In the embodiments of the present application, sensitive word detection is performed on the target interaction sub-data obtained during the information interaction process to obtain a sensitive word sub-detection result, and then a sensitive word detection result is generated based on the sensitive word sub-detection result. Therefore, after the information interaction between the agent terminal and the user terminal ends, there is no need to perform sensitive word detection on the target interaction data generated during the entire information interaction process. Instead, based on at least one sensitive word sub-detection result obtained during the information interaction process, the sensitive word detection result corresponding to the target interaction data can be determined. In this way, the generation efficiency of the sensitive word detection result can also be improved, thereby improving the generation efficiency of the return visit task information, and further improving the timeliness of the user return visit task displayed by the target management terminal.

[0102] Further, for the situation of sending interactive anomaly warning information to the agent terminal during the information interaction process, in order to make the interactive anomaly warning information play a better warning and prompting role, step A2, generating the interactive anomaly warning information based on the above sensitive word sub-detection result, specifically includes:

[0103] Step A21, determining the sensitive word level corresponding to the sensitive word information based on the pre-stored sensitive word level mapping relationship and the sensitive word information in the above sensitive word sub-detection result;

[0104] Specifically, for the situation where the sensitive word sub-detection result only contains sensitive word information but does not contain the sensitive word level information, the sensitive word level corresponding to the sensitive word information in the sensitive word sub-detection result can be determined based on the pre-stored sensitive word level mapping relationship; if the sensitive word sub-detection result contains the sensitive word level, step A21 can be omitted, that is, during the process of performing sensitive word detection on the target interaction sub-data between the agent terminal and the user terminal, not only the sensitive word information included in the target interaction sub-data is determined, but also the level information of the sensitive word information is determined.

[0105] Step A22, determining the target interaction method prompt information corresponding to the above sensitive word sub-detection result based on the pre-stored set of interaction method prompt information;

[0106] Specifically, in order to enable the seat staff to promptly understand the emergency handling solutions that can be adopted for the current emergency situation, so as to guide the seat staff to adjust the communication method in a timely manner during the call, improve the seat staff's ability to respond to emergencies, and thus achieve the purpose of alleviating the customer's negative emotions to the greatest extent, therefore, the corresponding relationship (i.e., the set of interactive method prompt messages) between the sensitive word detection results and the target interactive method prompt messages can be pre-stored, and then quickly determine the target interactive method prompt message corresponding to the current obtained sensitive word sub-detection result; among them, the target interactive method prompt message can include at least one of the reference answering phrases, compensation standard information, and professional terms in the current business scenario.

[0107] Step A23, generate an interactive anomaly warning message based on the above-mentioned sensitive word information, sensitive word level, and target interactive method prompt message.

[0108] That is to say, the above-mentioned interactive anomaly warning message can include: the fourth sub-information included in the sensitive word sub-detection result, for example, at least one of the detected sensitive word information, the danger level of each sensitive word, the type of sensitive word (such as violent tendency words, unhealthy color words, or uncivilized words, etc.), and the source information of the sensitive word (such as the seat staff or the target user); the interactive anomaly warning message can also include: the fifth sub-information obtained based on the fourth sub-information included in the sensitive word sub-detection result, for example, at least one of the target interactive method prompt message, the severity level of the violation in this call, and the sensitive word change trend.

[0109] Furthermore, in order to guide the seat management staff to conduct user follow-up visits more pertinently and improve the success rate of follow-up visit appeasement, therefore, in the above-mentioned step two, generate the follow-up visit task information of the target user based on the above-mentioned sensitive word detection result, specifically including:

[0110] Step B1, obtain the user portrait information of the target user; and,

[0111] Step B2, determine the task processing priority and task processing validity period of the follow-up visit task of the target user based on the above-mentioned sensitive word detection result;

[0112] Step B3, generate the follow-up visit task information of the target user based on the above-mentioned sensitive word detection result, user portrait information, task processing priority, and task processing validity period; among them, since the interactive anomaly warning message generated during the information interaction process can also include the target interactive method prompt message, the follow-up visit task information can also include the target interactive method prompt message.

[0113] Among them, the above user portrait information may include at least one of: user preference information, user basic attribute information (such as age, occupation, gender, etc.), business-related information (such as user credit rating, cumulative loan amount, number of overdue repayments, etc.), call success rate, user personality type; in specific implementation, considering that the dimensions involved in user portrait information are relatively many, that is, the information included in user portrait information is relatively many, so user portrait information can be used as a task details information item, that is, the seat management personnel can enter the task details display page by clicking the details view control to view the user portrait information of the target user; while the task processing priority and task processing validity period are usually key information items for guiding the seat management personnel to conduct return visits, so the task processing priority and task processing validity period can be used as task brief description information items, that is, the task processing priority and task processing validity period are displayed on the return visit task display page.

[0114] It should be noted that the determination process of the above user portrait information can be executed by the first server that generates the return visit task information, or can be executed by other servers, such as the third server that provides the target service. The third server sends the user portrait information to the first server, that is, making full use of the user portrait information that has been generated for the target user in using the target service, without regenerating the user portrait information, which can not only ensure the information richness of the return visit task information, but also improve the generation efficiency of the return visit task information, thereby improving the timeliness of the user return visit task displayed by the target management terminal.

[0115] Specifically, for the process of the target management terminal displaying the user return visit task corresponding to the received return visit task information on the visual interface, such as Figure 3a shown, the specific implementation process of multi-terminal interaction in the above task processing system is given. Taking the application scenario of voice call interaction between the seat terminal and the user terminal as an example, it specifically includes:

[0116] S301, the background server obtains the sensitive word sub-detection result corresponding to the call voice segment between the seat terminal and the user terminal;

[0117] S302, if the above sensitive word sub-detection result meets the second anomaly constraint condition, the background server generates a call anomaly warning message based on the sensitive word sub-detection result;

[0118] S303, the background server sends the above call anomaly warning message to the seat terminal;

[0119] S304, the seat terminal receives and displays the call anomaly warning message on the visual interface;

[0120] S305. After the call between the seat terminal and the user terminal ends, the background server generates a sensitive word detection result based on the sensitive word sub-detection results of multiple call voice segments.

[0121] S306. If the above sensitive word detection result meets the first abnormal constraint condition, the background server generates a return visit task information based on the above sensitive word detection result.

[0122] S307. The background server sends the above return visit task information to the target management terminal corresponding to the seat terminal.

[0123] S308. The target management terminal receives the above return visit task information and displays the user return visit task corresponding to the received return visit task information on the visualization interface.

[0124] Specifically, for the process of the task processing terminal making a return visit to the user terminal, on the basis of the above Figure 3a The specific implementation process of multi-terminal interaction in the above task processing system further includes:

[0125] The task processing terminal receives the trigger operation of the return visit control for a certain user return visit task by the seat management personnel.

[0126] The task processing terminal sends a user return visit request to the background server; wherein, the user return visit request carries the identification information of the task processing terminal and the identification information of the user terminal.

[0127] The background server responds to the above user return visit request and sends an outbound call request to the intelligent outbound call server so that the intelligent outbound call server establishes a call link between the task processing terminal and the user terminal.

[0128] In specific implementation, for the process of displaying the user return visit task on the seat management terminal, as Figure 3b shown, a display schematic diagram of the return visit task display page in the task processing method is given; specifically, for each return visit task information, a user return visit task is displayed on the return visit task display page, and the information items corresponding to each user return visit task may include the return visit task type, task processing priority, task processing validity period, task processing status information, remaining processing time limit information, etc.

[0129] Among them, the above task processing status information may include any one of the tasks about to time out, the tasks that have timed out, being processed, tasks to be processed, and tasks that have been processed. The above task processing priority may be a risk prediction score or a risk level identifier; the above remaining processing time limit information is used to remind the remaining or timeout specific time of the task processing; in addition, when the remaining task time is less than the preset time threshold, the seat management personnel are reminded to process the task in at least one way of a prompt tone, vibration, and pop-up window.

[0130] In specific implementation, for the process of displaying task details information on the agent management terminal, such as Figure 3c shown, a display schematic diagram of the task details display page in the task processing method is given; specifically, for each user return visit task, task details information items corresponding to the user return visit task are displayed on the task details display page. The task details information items may include at least one of task basic information, such as task serial number, agent name, and call voice ID. In addition, by clicking on the play control near the call voice ID, the user can trigger the playback of the corresponding call voice. The task details information items may also include at least one of user portrait information, sensitive word details information (i.e., the correspondence between sensitive word information, the danger level of each sensitive word, the type to which the sensitive word belongs, and the source information of the sensitive word), and sensitive word change trend.

[0131] In specific implementation, still taking the application scenario of voice call interaction as an example, considering that the background server may include multiple servers. For example, the background server includes an intelligent outbound call server and an intelligent quality inspection server. The specific implementation process of the above task processing method includes:

[0132] After the intelligent outbound call server determines that the call link between the agent terminal and the user terminal has been connected, it determines whether the call voice detection function is enabled; specifically, a switch option for the call voice detection function can be set in advance for the preset outbound call service, and in specific implementation, the switch option for the call voice detection function can be configured separately for different agent skill groups for easy independent control;

[0133] If it is detected that the call voice detection function is enabled, a call voice detection request carrying call voice stream information is sent to the intelligent quality inspection server;

[0134] After receiving the call voice detection request, the intelligent quality inspection server obtains the call voice stream information, performs sensitive word detection on the call voice stream information to obtain a sensitive word sub-detection result, and, in the case where the sensitive word sub-detection result meets the second abnormal constraint condition, generates a call abnormal alarm message based on the above sensitive word sub-detection result, and stores the sensitive word sub-detection result and the call abnormal alarm message in the local database;

[0135] The intelligent quality inspection server sends the sensitive word sub-detection result and the call abnormal alarm message to the intelligent outbound call server;

[0136] The intelligent outbound call server sends the sensitive word sub-detection result and the call abnormal alarm message to the agent terminal;

[0137] After the intelligent outbound call server determines that the call between the agent terminal and the user terminal has ended, it sends a voice detection stop request to the intelligent quality inspection server;

[0138] The intelligent quality inspection server determines whether it has received a voice detection stop request from the intelligent outbound call server;

[0139] If the voice detection stop request is received, the intelligent quality inspection server generates a sensitive word detection result based on at least one sensitive word sub-detection result, and, when the sensitive word detection result meets the first abnormal constraint condition, generates a return visit task information based on the above-mentioned sensitive word detection result; and stores the sensitive word detection result and the return visit task information in the local database;

[0140] The intelligent quality inspection server sends the sensitive word detection result and the return visit task information to the intelligent outbound call server;

[0141] The intelligent outbound call server sends the sensitive word detection result and the return visit task information to the target management terminal.

[0142] Furthermore, considering that the original management personnel in charge of the seat personnel may need to take leave or have a large number of tasks to be processed, it is necessary to allocate the user return visit tasks. Therefore, in order to improve the allocation efficiency of the return visit tasks, based on this, before receiving the first input of the first user to the return visit control in the above S202, it further includes:

[0143] Step 1, receive a second input of a second user to the task allocation control;

[0144] Among them, the above-mentioned second input may be a triggering operation of the second user on the task allocation control, such as a click operation; in specific implementation, a return visit task allocation request may also be triggered and generated by means of a voice command or a specific gesture. Specifically, the second input may also be a voice command input by the user, or a specific gesture input by the user, which can be specifically determined according to actual usage requirements, and this application embodiment does not limit this; in addition, the specific gesture may be any one of a click gesture, a slide gesture, a drag gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double press gesture, and a double click gesture; the click operation may be a single click, a double click or a click trigger operation of any number of times, and may also be a long press or short press trigger operation.

[0145] Step 2, in response to the above-mentioned second input, generate a return visit task allocation request;

[0146] Specifically, after detecting the second input, the task allocation terminal determines at least one of the identification information of the original management terminal, the relevant information of the task to be allocated, and the identification information of the management terminal to be allocated; then, automatically generates a return visit task allocation request carrying at least one of the identification information of the original management terminal, the relevant information of the task to be allocated, and the identification information of the management terminal to be allocated; among them, the relevant information of the task to be allocated may include: the generation time period information of the task to be assigned, or the task identification information of the task to be assigned.

[0147] Step three: sending the above-mentioned return task allocation request to the server, so that the server responds to the above-mentioned task allocation request and sends the return task information corresponding to the task to be allocated to the task processing terminal.

[0148] Specifically, the specific process of the background server receiving and responding to the above task allocation request includes:

[0149] Step C1, the backend service end receives a task dispatching request from a task dispatching terminal; wherein the task dispatching terminal includes: an original management terminal corresponding to the seat terminal, or a superior management terminal of the original management terminal, the original management terminal is a management terminal used by a direct manager of the seat personnel or a management terminal used by a professional return visitor, and the task dispatching request is generated based on detecting a triggering operation of a task dispatching control by a second user; wherein the second user may be the original manager of the seat terminal, or a superior manager of the original manager;

[0150] Step C2: the backend server determines the allocated management terminal (ie, the task processing terminal) for processing the user return visit task to be allocated in response to the return visit task allocation request.

[0151] In specific implementation, the superior management terminal may initiate a return task allocation request to the background service end; then, the background service end determines the allocated management terminal in response to the return task allocation request; wherein, the determination process of the allocated management terminal may be the allocated management terminal specified by the superior management terminal, that is, the return task allocation request carries the identification information of the allocated management terminal; or the background service end may automatically determine the allocated management terminal for processing the user return task to be allocated; or the background service end may automatically determine multiple candidate management terminals based on the user return task to be allocated, and then the superior management terminal selects the allocated management terminal for processing the user return task to be allocated based on the multiple candidate management terminals;

[0152] In addition, considering that the callback task allocation request can also be directly initiated online by the original management terminal, that is, the original management terminal can directly send a callback task allocation request to the background server. Then, in response to this callback task allocation request, the background server sends a task allocation instruction request to the superior management terminal of the original management terminal, and then determines the allocated management terminal based on the task allocation feedback information sent by the superior management terminal. Among them, for the determination process of the allocated management terminal, it can be the allocated management terminal designated by the superior management terminal, that is, the task allocation feedback information includes the identification information of the allocated management terminal. It can also be that the background server automatically determines multiple candidate management terminals based on the user callback tasks to be allocated, and then the superior management terminal selects the allocated management terminal for processing the user callback tasks to be allocated from the multiple candidate management terminals, that is, the task allocation instruction request carries the identification information of the candidate management terminals. Correspondingly, the task allocation feedback information includes the allocated management terminal selected by the superior management personnel from the multiple candidate management terminals.

[0153] Among them, for the determination process of the allocated management terminal, step C2 above, in response to the above callback task allocation request, determines the allocated management terminal for processing the user callback tasks to be allocated, specifically including:

[0154] Based on the first identification information of the management terminal carried in the above callback task allocation request, determine the allocated management terminal corresponding to the agent terminal in the information interaction process. This allocated management terminal is the management terminal for processing the user callback tasks to be allocated; that is, the task allocation terminal can directly specify the management terminal that receives the callback tasks to be allocated.

[0155] Or,

[0156] Based on the second identification information of the original management terminal carried in the above callback task allocation request, determine the candidate management terminals related to the original management terminal, and determine the corresponding allocated management terminal based on the candidate management terminals; that is, the background server can first determine multiple candidate management terminals, and then the superior management terminal selects at least one management terminal that receives the callback tasks to be allocated from the multiple candidate management terminals.

[0157] In specific implementation, for the determination process of the candidate management terminals, based on the current task volume of the agent management terminals whose business association degree with the original management terminal is greater than the preset threshold, determine the candidate management terminals, that is, comprehensively measure the current task volume of each agent management terminal, and automatically recommend candidate management terminals that can process the callback tasks to be allocated to the superior management terminal.

[0158] Further, considering that the original management terminal may allocate the user return visit tasks generated in future time periods to other management terminals. For example, when the original management terminal has a vacation requirement, it is necessary to allocate the user return visit tasks during the vacation period to other management terminals. That is, before the user return visit tasks are generated, a request for task allocation has been initiated. Correspondingly, the above-mentioned request for task allocation of return visit tasks includes: a request for delegation of return visit tasks;

[0159] Specifically, step one, receiving a second input from a second user to the task allocation control, specifically includes:

[0160] Receiving a second input from the second user to the task delegation control; wherein, the task delegation control can be an information input box, or an add control and an edit control, or also a task allocation confirmation control corresponding to the task delegation prompt information;

[0161] Correspondingly, step two, in response to the above second input, generating a request for task allocation of return visit tasks, specifically includes:

[0162] In response to the above second input, determining the generation time period information of the task to be delegated; wherein, the task to be delegated is the user return visit task corresponding to the return visit task information generated after the current moment;

[0163] Generating a request for task allocation of return visit tasks carrying the generation time period information of the above-mentioned task to be delegated.

[0164] Specifically, for the case where the request for task allocation of return visit tasks is a request for delegation of return visit tasks, what the background server mainly receives and responds to the above-mentioned task allocation request is:

[0165] Among them, step C1 above, the background server receives the request for task allocation of return visit tasks from the task allocation terminal, specifically includes:

[0166] The background server receives the request for delegation of return visit tasks from the task allocation terminal, wherein the request for delegation of return visit tasks carries the generation time period information of the task to be delegated, and the task to be delegated is the user return visit task corresponding to the return visit task information generated after the current moment;

[0167] After the background server generates the return visit task information corresponding to the request for delegation of return visit tasks, it sends the above return visit task information to the allocated management terminal for processing the user return visit tasks.

[0168] Specifically, for the case where the request for task allocation of return visit tasks is a request for delegation of return visit tasks, the return visit task information is directly sent to the allocated management terminal (i.e., the target management terminal, also the delegated management terminal), and there is no need to send the return visit task information to the original management terminal.

[0169] That is to say, in the process of task delegation, the above-mentioned target management terminal is the allocated management terminal, that is, the return visit task information is directly sent to the allocated management terminal.

[0170] Specifically, the specific implementation process of multi-terminal interaction for the return visit task delegation request in the above-mentioned task processing system specifically includes:

[0171] The background server receives the return visit task delegation request from the task allocation terminal, and the return visit task delegation request carries the identification information of the original management terminal and the generation time period information of the task to be delegated;

[0172] The background server responds to the above return visit task delegation request and determines the allocated management terminal for processing the task to be delegated;

[0173] The background server obtains the sensitive word detection result corresponding to the target interaction data generated during the information interaction between the target seat terminal and the user terminal; among them, the target seat terminal belongs to the seat terminal of the above original management terminal;

[0174] If the above sensitive word detection result meets the first abnormal constraint condition, the background server generates return visit task information based on the sensitive word detection result;

[0175] The background server sends the above return visit task information to the determined allocated management terminal;

[0176] The allocated management terminal displays the user return visit task corresponding to the above return visit task information.

[0177] Such as Figure 5 As shown, at least one task delegation entry can be generated for each return visit task delegation request. After the superior management personnel enter the task delegation display page, they can view the multiple generated task delegation entries and edit the generated task delegation entries through the editing control, or add new task delegation entries through the adding control.

[0178] Furthermore, considering that the original management terminal may also allocate the already generated user return visit tasks to other management terminals. For example, when the original management terminal has a relatively large number of user return visit tasks to be processed currently, it is necessary to allocate some of the user return visit tasks to be processed to other management terminals. That is, after the user return visit task is generated, a return visit task allocation request is initiated to the background server. Correspondingly, the above return visit task allocation request includes: a return visit task assignment request;

[0179] Specifically, step one, receiving the second input of the second user to the task allocation control specifically includes:

[0180] Receive a second input from a second user to a task assignment control; wherein, the task assignment control can be an information input box, or a selection control and a submission control, or a task allocation confirmation control corresponding to a task assignment prompt message;

[0181] Correspondingly, in the above step 2, in response to the above second input, generate a return visit task allocation request, which specifically includes:

[0182] In response to the above second input, determine the task identification information of the task to be assigned; wherein, the task to be assigned is a user return visit task corresponding to the return visit task information generated before the current moment;

[0183] Generate a return visit task allocation request carrying the task identification information of the above task to be assigned.

[0184] Specifically, after generating a return visit task allocation request carrying the task identification information of the above task to be assigned, it further includes:

[0185] Receive the task transfer instruction information from the server; delete the task to be assigned from the task list of the original management terminal of the agent terminal.

[0186] Specifically, for the case where the return visit task allocation request is a return visit task assignment request, the main operations of the background server for receiving and responding to the above task allocation request are:

[0187] Among them, in the above step C1, the background server receives the return visit task allocation request from the task allocation terminal, which specifically includes:

[0188] The background server receives the return visit task assignment request from the task allocation terminal, wherein the return visit task assignment request carries the task identification information of the task to be assigned, and the task to be assigned is a user return visit task corresponding to the return visit task information generated before the current moment;

[0189] After the background server sends the return visit task information corresponding to the task to be assigned to the target management terminal (i.e., the original management terminal), it sends the above return visit task information to the determined allocated management terminal, and sends a task deletion prompt message to the original management terminal; wherein, the allocated management terminal is used to display the user return visit task corresponding to the received return visit task information, and the original management terminal is used to delete the user return visit task corresponding to the received task deletion prompt message.

[0190] Specifically, for the case where the return visit task allocation request is a return visit task assignment request, the initiation time of the return visit task assignment request is later than the generation time of the task to be allocated, that is, the return visit task information corresponding to the task to be allocated has been sent to the target management terminal (i.e., the original management terminal), and the task to be allocated is displayed on the original management terminal. Therefore, after receiving the return visit task assignment request, the task to be allocated needs to be transferred from the original management terminal to the allocated management terminal (i.e., the assigned management terminal).

[0191] That is to say, during the process of task assignment, the above-mentioned target management terminal is the original management terminal, and the above-mentioned task processing terminal is the allocated management terminal. That is, the task to be allocated is first displayed on the visual interface of the original management terminal, and then, after receiving the return visit task assignment request subsequently, the task to be allocated is cancelled from display on the visual interface of the original management terminal and is displayed on the visual interface of the allocated management terminal.

[0192] Specifically, the specific implementation process of multi-terminal interaction for the return visit task assignment request in the above-mentioned task processing system specifically includes:

[0193] The background server obtains the sensitive word detection result corresponding to the target interaction data generated during the information interaction between the target seat terminal and the user terminal; among them, the target seat terminal belongs to the seat terminal of the above-mentioned original management terminal;

[0194] If the above-mentioned sensitive word detection result meets the first abnormal constraint condition, the background server generates return visit task information based on the sensitive word detection result;

[0195] The background server sends the above-mentioned return visit task information to the original management terminal and the superior management terminal;

[0196] The original management terminal and the superior management terminal display the user return visit task corresponding to the above-mentioned return visit task information;

[0197] The background server receives the return visit task assignment request from the original management terminal or the superior management terminal. The return visit task assignment request carries the identification information of the original management terminal and the task identification information of the task to be assigned;

[0198] In response to the above-mentioned return visit task assignment request, the background server determines the allocated management terminal for processing the task to be assigned;

[0199] The background server sends the above-mentioned return visit task information to the determined allocated management terminal;

[0200] The allocated management terminal displays the user return visit task corresponding to the above-mentioned return visit task information;

[0201] The background server sends a task deletion prompt message to the original management terminal;

[0202] The original management terminal cancels the display of the above-mentioned tasks to be assigned.

[0203] As Figure 6a shown, after the superior management personnel enter the task assignment display page (which displays the pending user return visit tasks of multiple seat terminals under their responsibility), they can view the pending user return visit tasks, select the user return visit tasks to be assigned from them, and send a return visit task assignment request to the background server; among them, the task assignment display page can be a return visit task display page in the editing state.

[0204] In addition, in specific implementation, the original management terminal can first send a return visit task assignment request to the superior management terminal through the background server, which is reviewed by the superior management personnel, and then the superior management terminal sends a return visit task assignment request with the review passed to the background server.

[0205] In specific implementation, when the original management terminal determines that the remaining task time of at least one user return visit task is less than the preset time threshold, it not only automatically reminds the seat management personnel to process the task, but also can display task allocation prompt information and corresponding task allocation confirmation controls. For example, the task allocation prompt information can be "Please confirm whether you need to allocate the following user return visit tasks to other management terminals for processing?", and then the original management terminal sends a return visit task allocation request to the background server based on the user's trigger operation on the task allocation confirmation control.

[0206] In specific implementation, the above-mentioned task allocation control can be an information input box for inputting the generation time period information of the task to be delegated or the task identification information of the task to be assigned; it can also be the above Figure 5 add control, edit control, or the above Figure 6a select control, submit control in it, that is, the user manually inputs the relevant information of the task to be allocated; further, in order to improve the task allocation efficiency of the seat management personnel, the above-mentioned task allocation control can also be a task allocation confirmation control configured based on the task allocation prompt information, where the task allocation prompt information is determined based on the personnel leave submission information of the personnel leave system, so that the user can directly trigger the "task allocation confirmation control" to initiate a one-key task allocation;

[0207] Specifically, the background server receives the personnel leave submission information sent by the personnel leave system; the personnel leave submission information includes the leave time information of the leave-taking personnel and the unique personnel identifier;

[0208] The background server generates task allocation prompt information based on the personnel leave submission information and sends the task allocation prompt information to the corresponding task allocation terminal; wherein, the task allocation prompt information includes a first prompt information for indicating whether to allocate the generated user return visit task, and / or a second prompt information for indicating whether to allocate the user return visit task during the leave period; specifically, the first prompt information can be determined according to at least one of the task processing efficiency of the leave-taking personnel, the total number of tasks to be processed, the task processing priority of the generated user return visit task, and the remaining processing time limit information.

[0209] The above task allocation terminal receives the task allocation prompt information and displays the task allocation prompt information and task allocation confirmation control.

[0210] After detecting the triggering operation of the second user on the task allocation confirmation control, the above task allocation terminal sends a return visit task allocation request to the background server; as Figure 6b shown, taking the task allocation terminal as the original management terminal and the task allocation as task delegation as an example, after receiving the task allocation prompt information from the background server, the task allocation terminal displays a prompt information "Please confirm whether it is necessary to allocate and process the return visit tasks from xx time to yy time during the leave period?" and a task allocation confirmation control. After detecting the triggering operation of the user on the task allocation confirmation control, the task allocation terminal sends a return visit task allocation request to the background server; in addition, considering that the user may have a need to modify the relevant information of the tasks to be allocated in the prompt information, or may choose not to allocate tasks during the leave period, therefore, an edit control and a cancel control can also be displayed; and in order to facilitate the user to view the relevant information of the requested task delegation later, corresponding task delegation entries can be generated.

[0211] Specifically, still taking the task allocation terminal as the original management terminal as an example, after the original management terminal detects the triggering operation of the user on the task allocation confirmation control, it sends a first task allocation request to the background server; in response to the first task allocation request, the background server sends a second task allocation request to the superior management terminal of the original management terminal. Among them, the first task allocation request and the second task allocation request may be the same. For example, if the first task allocation request carries the first identification information of the allocated management terminal, the second task allocation request also carries the first identification information; correspondingly, the first task allocation request and the second task allocation request may also be different. For example, if the first task allocation request does not include the first identification information of the allocated management terminal, the second task allocation request may include the third identification information of the candidate management terminal automatically determined by the background server; the background server receives the task allocation response information sent by the superior management terminal based on the second task allocation request, and performs task allocation based on the task allocation response information, that is, triggers the original management terminal to delete the allocated user return visit task based on the task allocation response information, and triggers the allocated management terminal to display the allocated user return visit task; among them, if the second task allocation request carries the third identification information of the candidate management terminal, the task allocation response information includes the identification information of the allocated management terminal selected by the superior management terminal from the candidate management terminal.

[0212] In the task processing method in the embodiment of the present application, the user return visit task to be processed and its corresponding return visit control are displayed on the task processing terminal. After receiving the first input of the first user on the return visit control, a user return visit request is sent to the server to trigger the server to automatically control the task processing terminal to return visit the user terminal corresponding to the user return visit task. In this way, the seat management personnel can not only view the return visit tasks to be processed in a timely manner, but also quickly trigger the sending of a user return visit request to the server through the return visit control. Thus, the seat management personnel can timely return visit and comfort the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits; and since the user return visit tasks are automatically generated for the information interaction events between the seat terminal and the user terminal, the generation process of the return visit tasks is not affected by human factors, improving the accuracy of the user return visit tasks displayed on the task processing terminal, and thus realizing more accurate and timely comfort for key users.

[0213] Corresponding to the above Figures 2 to 6b described task processing method, based on the same technical concept, the embodiment of the present application also provides a task processing method, Figure 7 is a schematic flowchart of the task processing method provided by the embodiment of the present application, Figure 7 The method in can be executed by the background server, as Figure 7 shown, this method at least includes the following steps:

[0214] S702, receive a user feedback request from a task processing terminal; wherein, the user feedback request is sent after detecting a first input by a first user to a feedback control, the feedback control is configured based on a user feedback task displayed on a visualization interface, and the user feedback task is generated based on an information interaction event between an agent terminal and a user terminal;

[0215] S704, in response to the above user feedback request, control the task processing terminal to conduct a feedback to the user terminal.

[0216] Specifically, the task processing terminal receives feedback task information sent by a server; the feedback task information may be generated based on a sensitive word detection result when the sensitive word detection result of target interaction data meets a first abnormal constraint condition, and the target interaction data is generated based on an information interaction event between an agent terminal and a user terminal; then, based on the received feedback task information, display a corresponding user feedback task and a feedback control on the visualization interface.

[0217] Wherein, before the above S702, receiving the user feedback request from the task processing terminal, it further includes:

[0218] Receive a feedback task allocation request; wherein, the feedback task allocation request is sent after detecting a second input by a second user to a task allocation control;

[0219] In response to the above feedback task allocation request, send the feedback task information corresponding to the task to be allocated to the task processing terminal.

[0220] It should be noted that for each user feedback task, the management terminal that first receives the feedback task information corresponding to the user feedback task is the target management terminal, and the management terminal that finally receives the feedback task information corresponding to the user feedback task is the task processing terminal; in specific implementation, considering that there may be task allocation and the task allocation includes task delegation or task assignment, the target management terminal may be the original management terminal or the allocated management terminal. Similarly, the above task processing terminal may be the original management terminal or the allocated management terminal. Therefore, the target management terminal and the task processing terminal may be the same management terminal or different management terminals;

[0221] Specifically, for the case where no task allocation is performed, the target management terminal and the task processing terminal are the same, that is, the original management terminal of the agent terminal; for the case where the task allocation is task delegation, the target management terminal and the task processing terminal are the same, that is, the allocated management terminal. That is to say, after receiving the task allocation request, the return visit task information is directly sent to the allocated management terminal; for the case where the task allocation is task assignment, the target management terminal and the task processing terminal are different, that is, the target management terminal is the original management terminal, and the task processing terminal is the allocated management terminal. That is to say, the return visit task information is first sent to the original management terminal, and then after receiving the task allocation request, the return visit task information is sent to the allocated management terminal.

[0222] In the task processing method of the embodiment of the present application, the user return visit task to be processed and its corresponding return visit control are displayed on the task processing terminal. After receiving the first input of the first user to the return visit control, a user return visit request is sent to the server to trigger the server to automatically control the task processing terminal to return visit the user terminal corresponding to the user return visit task. In this way, the agent management personnel can not only view the return visit tasks to be processed in a timely manner, but also quickly trigger the sending of a user return visit request to the server through the return visit control. Thus, the agent management personnel can timely return visit and comfort the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits; and since the user return visit tasks are automatically generated for the information interaction events between the agent terminal and the user terminal, the process of generating return visit tasks is not affected by human factors, improving the accuracy of the user return visit tasks displayed on the task processing terminal, and thus realizing more accurate and timely comfort for key users.

[0223] It should be noted that this embodiment in the present application and the previous embodiment in the present application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned task processing method, and the repeated parts will not be elaborated.

[0224] Corresponding to the above Figures 2 to 6b described task processing method, based on the same technical concept, the embodiment of the present application also provides a task processing device, which is set in the agent management terminal, Figure 8 is the first module composition schematic diagram of the task processing device provided by the embodiment of the present application. This device is used to execute Figures 2 to 6b the described task processing method. As Figure 8 shown, this device includes:

[0225] A first input receiving module 802, configured to receive the first input of the first user to the return visit control; the return visit control is configured for the user return visit task displayed on the visual interface, and the user return visit task is generated based on the information interaction event between the agent terminal and the user terminal;

[0226] A return visit request generation module 804, configured to generate a user return visit request in response to the first input; the user return visit request carries identification information of a task processing terminal corresponding to the agent terminal and identification information of the user terminal;

[0227] A return visit request sending module 806, configured to send the user return visit request to a server, so that in response to the user return visit request through the server, the task processing terminal is controlled to make a return visit to the user terminal.

[0228] In the task processing device in the embodiment of the present application, a user return visit task to be processed and its corresponding return visit control are displayed on the task processing terminal. After receiving a first input from a first user on the return visit control, a user return visit request is sent to the server to trigger the server to automatically control the task processing terminal to make a return visit to the user terminal corresponding to the user return visit task. In this way, the agent management personnel can not only view the return visit tasks to be processed in a timely manner, but also quickly trigger the sending of a user return visit request to the server through the return visit control. Thus, the agent management personnel can timely make a return visit and comfort the target user involved in the user return visit task, thereby improving the timeliness of user return visits; and since the user return visit task is automatically generated for the information interaction event between the agent terminal and the user terminal, the generation process of the return visit task is not affected by human factors, improving the accuracy of the user return visit task displayed on the task processing terminal, and thus realizing more accurate and timely comfort for key users.

[0229] It should be noted that the embodiment of the task processing device in the present application and the embodiment of the task processing method in the present application are based on the same inventive concept. Therefore, for the specific implementation of this embodiment, reference can be made to the corresponding task processing method described above, and the repeated parts will not be elaborated.

[0230] Corresponding to the above Figure 7 described task processing method, based on the same technical concept, the embodiment of the present application further provides a task processing device, which is set in the background server, Figure 9 is the second module composition schematic diagram of the task processing device provided in the embodiment of the present application. This device is used to execute Figure 7 the described task processing method, as Figure 9 shown, this device includes:

[0231] A return visit request receiving module 902, configured to receive a user return visit request from a task processing terminal; the user return visit request is sent after detecting a first input from a first user on the return visit control, and the return visit control is configured for the user return visit task displayed on the visual interface, and the user return visit task is generated based on the information interaction event between the agent terminal and the user terminal;

[0232] The user return visit control module 904 is configured to control the task processing terminal to make a return visit to the user terminal in response to the user return visit request.

[0233] In the task processing device according to the embodiment of the present application, the to-be-processed user return visit tasks and their corresponding return visit controls are displayed on the task processing terminal. After receiving the first input of the first user to the return visit control, a user return visit request is sent to the server to trigger the server to automatically control the task processing terminal to make a return visit to the user terminal corresponding to the user return visit task. In this way, the seat management personnel can not only view the to-be-processed return visit tasks in a timely manner, but also quickly trigger the sending of a user return visit request to the server through the return visit control. Thus, the seat management personnel can timely make a return visit and comfort the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits. And since the user return visit tasks are automatically generated for the information interaction events between the seat terminal and the user terminal, the generation process of the return visit tasks is not affected by human factors, improving the accuracy of the user return visit tasks displayed on the task processing terminal, and further realizing more accurate and timely comfort for key users.

[0234] It should be noted that the embodiment of the task processing device in the present application and the embodiment of the task processing method in the present application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the corresponding task processing method described above, and the repeated parts will not be elaborated.

[0235] Further, corresponding to the Figures 2 to 7 method shown above, based on the same technical concept, the embodiment of the present application also provides a task processing device, which is used to execute the above-mentioned task processing method, as Figure 10 shown.

[0236] The task processing device may vary greatly due to configuration or performance differences, and may include one or more processors 1001 and a memory 1002. One or more application programs or data may be stored in the memory 1002. Among them, the memory 1002 may be a transient storage or a persistent storage. The application programs stored in the memory 1002 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in the task processing device. Further, the processor 1001 may be set to communicate with the memory 1002 and execute a series of computer-executable instructions in the memory 1002 on the task processing device. The task processing device may also include one or more power supplies 1003, one or more wired or wireless network interfaces 1004, one or more input / output interfaces 1005, one or more keyboards 1006, etc.

[0237] In a specific embodiment, the task processing device includes a memory and one or more programs. One or more of the programs are stored in the memory, and one or more of the programs may include one or more modules. Each module may include a series of computer-executable instructions in the task processing device and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0238] Receive a first input from a first user to a callback control; the callback control is configured for a user callback task displayed on a visual interface, and the user callback task is generated based on an information interaction event between an agent terminal and a user terminal;

[0239] In response to the first input, generate a user callback request; the user callback request carries the identification information of the task processing terminal corresponding to the agent terminal and the identification information of the user terminal;

[0240] Send the user callback request to the server, so that in response to the user callback request through the server, control the task processing terminal to callback the user terminal.

[0241] In the task processing device in the embodiment of the present application, the user callback task to be processed and its corresponding callback control are displayed on the task processing terminal. After receiving the first input from the first user to the callback control, a user callback request is sent to the server to trigger the server to automatically control the task processing terminal to callback the user terminal corresponding to the user callback task. In this way, the agent management personnel can not only view the pending callback tasks in a timely manner, but also quickly trigger the sending of a user callback request to the server through the callback control. Thus, the agent management personnel can timely callback and comfort the target users involved in the user callback tasks, thereby improving the timeliness of user callbacks; and since the user callback tasks are automatically generated for the information interaction events between the agent terminal and the user terminal, the generation process of the callback tasks is not affected by human factors, improving the accuracy of the user callback tasks displayed on the task processing terminal, and further realizing more accurate and timely comfort for key users.

[0242] In another specific embodiment, the task processing device includes a memory and one or more programs. One or more of the programs are stored in the memory, and one or more of the programs may include one or more modules. Each module may include a series of computer-executable instructions in the task processing device and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0243] receiving a user return visit request from a task processing terminal; the user return visit request is issued after detecting a first input of a first user to a return visit control, the return visit control is configured for a user return visit task displayed on a visual interface, and the user return visit task is generated based on an information interaction event between an agent terminal and a user terminal;

[0244] In response to the user return visit request, the task processing terminal is controlled to return visit to the user terminal.

[0245] The task processing device in the embodiment of the present application displays the pending user return visit tasks and their corresponding return visit controls on the task processing terminal, and after receiving the first input of the first user to the return visit control, sends a user return visit request to the server to trigger the server to automatically control the task processing terminal to return the user terminal corresponding to the user return visit task, so that the agent manager can not only view the pending return visit tasks in the first time, but also quickly trigger the sending of the user return visit request to the server through the return visit control, so that the agent manager can promptly return and appease the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits; and because the user return visit tasks are automatically generated for the information interaction events between the agent terminal and the user terminal, the return visit task generation process is not affected by human factors, which improves the accuracy of the user return visit tasks displayed on the task processing terminal, thereby achieving more accurate and timely appeasement of key users.

[0246] It should be noted that the embodiment of the task processing device in the present application and the embodiment of the task processing method in the present application are based on the same inventive concept, so the specific implementation of this embodiment can refer to the implementation of the corresponding task processing method mentioned above, and the repeated parts will not be repeated.

[0247] Furthermore, corresponding to the above Figures 2 to 7 The method shown is based on the same technical concept. The embodiment of the present application also provides a storage medium for storing computer executable instructions. In a specific embodiment, the storage medium can be a USB flash drive, an optical disk, a hard disk, etc. When the computer executable instructions stored in the storage medium are executed by the processor, the following process can be implemented:

[0248] Receiving a first input of a first user to a return visit control; the return visit control is configured for a user return visit task displayed on a visual interface, and the user return visit task is generated based on an information interaction event between an agent terminal and a user terminal;

[0249] In response to the first input, a user return visit request is generated; the user return visit request carries identification information of the task processing terminal corresponding to the seat terminal and identification information of the user terminal;

[0250] Send the user return visit request to the server, so that the server responds to the user return visit request and controls the task processing terminal to return visit the user terminal.

[0251] When the computer executable instructions stored in the storage medium in the embodiment of the present application are executed by a processor, the user return visit tasks to be processed and their corresponding return visit controls are displayed on the task processing terminal. After receiving the first input of the first user to the return visit control, a user return visit request is sent to the server to trigger the server to automatically control the task processing terminal to return visit the user terminal corresponding to the user return visit task. In this way, the seat management personnel can not only view the return visit tasks to be processed in the first time, but also quickly trigger the sending of the user return visit request to the server through the return visit control. Thus, the seat management personnel can timely return visit and comfort the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits; and since the user return visit tasks are automatically generated for the information interaction events between the seat terminal and the user terminal, the generation process of the return visit tasks is not affected by human factors, improving the accuracy of the user return visit tasks displayed on the task processing terminal, and thus realizing more accurate and timely comfort for key users.

[0252] In another specific embodiment, the storage medium may be a USB flash drive, an optical disc, a hard disk, etc. When the computer executable instructions stored in the storage medium are executed by a processor, the following process can be realized:

[0253] Receive the user return visit request of the task processing terminal; the user return visit request is sent after detecting the first input of the first user to the return visit control, the return visit control is configured for the user return visit tasks displayed on the visual interface, and the user return visit tasks are generated based on the information interaction events between the seat terminal and the user terminal;

[0254] Respond to the user return visit request and control the task processing terminal to return visit the user terminal.

[0255] When the computer-executable instructions stored in the storage medium in the embodiments of the present application are executed by a processor, user return visit tasks to be processed and their corresponding return visit controls are displayed on the task processing terminal. After receiving a first input from a first user to the return visit control, a user return visit request is sent to the server to trigger the server to automatically control the task processing terminal to return visit the user terminal corresponding to the user return visit task. In this way, the agent management personnel can not only view the return visit tasks to be processed in a timely manner, but also quickly trigger the sending of a user return visit request to the server through the return visit control. Thus, the agent management personnel can timely return visit and appease the target users involved in the user return visit tasks, thereby improving the timeliness of user return visits. And since the user return visit tasks are automatically generated for information interaction events between the agent terminal and the user terminal, the process of generating return visit tasks is not affected by human factors, improving the accuracy of the user return visit tasks displayed on the task processing terminal, and thus achieving more accurate and timely appeasement of key users.

[0256] It should be noted that the embodiments of the storage medium in the present application and the embodiments of the task processing method in the present application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the corresponding task processing method described above, and the repeated parts will not be elaborated.

[0257] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0258] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the embodiments of the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0259] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in one or more flows Figure 1 or more flows and / or blocks Figure 1 or more blocks.

[0260] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one or more flows Figure 1 or more flows and / or blocks Figure 1 or more blocks.

[0261] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows Figure 1 or more flows and / or blocks Figure 1 or more blocks.

[0262] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory. The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0263] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0264] It should also be noted that the term "includes", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, commodity or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the statement "including one..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements. The embodiments of the present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0265] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The above is only an embodiment of this document and is not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this document should be included in the scope of the claims of this document.

Claims

1. A task processing method, characterized in that, The method includes: Generating a user return visit task based on return visit task information and task dynamic change information; the return visit task information is generated when the sensitive word detection result corresponding to the information interaction event between the agent terminal and the user terminal satisfies the interaction anomaly constraint condition; the task dynamic change information includes task processing status information and / or remaining processing time limit information; the interaction anomaly constraint condition includes at least one of the number of sensitive words being greater than a first preset threshold, the danger level of the sensitive words being higher than a first level threshold, and the number of high-risk sensitive words being greater than a second preset threshold, and the high-risk sensitive words include sensitive words with a danger level higher than the first level threshold; Receiving a first input from a first user to a return visit control; the return visit control is configured for the user return visit task displayed on the visual interface of the task processing terminal, and the user return visit task is generated based on the information interaction event between the agent terminal and the user terminal; In response to the first input, generating a user return visit request; the user return visit request carries the identification information of the task processing terminal corresponding to the agent terminal and the identification information of the user terminal, and the task processing terminal includes the original management terminal of the agent terminal or the reassigned management terminal after the return visit task is allocated; Sending the user return visit request to the server, so that the server, in response to the user return visit request, controls the task processing terminal to make a return visit to the user terminal.

2. The method according to claim 1, characterized in that, Before receiving the first input from the first user to the return visit control, it further includes: Receiving a second input from a second user to a task allocation control; In response to the second input, generating a return visit task allocation request; Sending the return visit task allocation request to the server, so that the server, in response to the task allocation request, sends the return visit task information corresponding to the task to be allocated to the task processing terminal.

3. The method according to claim 2, characterized in that, The receiving the second input from the second user to the task allocation control includes: Receiving a second input from the second user to a task delegation control; The generating the return visit task allocation request in response to the second input includes: In response to the second input, determining the generation time period information of the task to be delegated; the task to be delegated is the user return visit task corresponding to the return visit task information generated after the current moment; Generating a return visit task allocation request carrying the generation time period information of the task to be delegated.

4. The method according to claim 2, characterized in that, The receiving the second input from the second user to the task allocation control includes: Receiving a second input from the second user to a task assignment control; The generating the return visit task allocation request in response to the second input includes: In response to the second input, determining the task identification information of the task to be assigned; the task to be assigned is the user return visit task corresponding to the return visit task information generated before the current moment; Generating a return visit task allocation request carrying the task identification information of the task to be assigned.

5. The method according to claim 4, wherein After generating the return visit task allocation request carrying the task identification information of the task to be assigned, it further includes: Receiving the task transfer instruction information from the server; Deleting the task to be assigned from the task list of the original management terminal of the agent terminal.

6. The method according to claim 1, wherein Before receiving the first input of the first user to the callback control, it further includes: Display the user callback task and the corresponding callback control on the visualization interface.

7. The method according to claim 6, characterized in that, The callback task information includes at least one of the sensitive word detection result, the user portrait information of the target user, the task processing priority of the user callback task, and the task processing validity period; The target user is the object being served in the information interaction event.

8. The method according to claim 6, wherein After generating the user callback task based on the callback task information, it further includes: Update the task dynamic change information based on the callback task information and the current task node information.

9. The method according to claim 1, characterized in that, It further includes: Receive a third input of the first user to the task details viewing control; In response to the third input, display the task details of the user callback task corresponding to the task details viewing control.

10. A task processing method, characterized in that, The method includes: Receive a user callback request from the task processing terminal; the user callback request is sent after detecting the first input of the first user to the callback control, and the callback control is configured for the user callback task displayed on the visualization interface of the task processing terminal. The user callback task is generated based on the information interaction event between the agent terminal and the user terminal; wherein, the user callback task is generated based on the callback task information and the task dynamic change information, and the callback task information is generated when the sensitive word detection result corresponding to the information interaction event meets the interaction anomaly constraint condition; the task dynamic change information includes task processing status information and / or remaining processing time limit information; the interaction anomaly constraint condition includes at least one of the number of sensitive words being greater than a first preset threshold, the danger level of the sensitive words being higher than a first level threshold, and the number of high-risk sensitive words being greater than a second preset threshold, and the high-risk sensitive words include sensitive words with a danger level higher than the first level threshold; In response to the user callback request, control the task processing terminal to callback the user terminal, and the task processing terminal includes the original management terminal of the agent terminal or the reassigned management terminal after the callback task is reassigned.

11. The method according to claim 10, wherein Before receiving the user callback request from the task processing terminal, it further includes: Receive a callback task reassignment request; the callback task reassignment request is sent after detecting the second input of the second user to the task reassignment control; In response to the callback task reassignment request, send the callback task information corresponding to the task to be reassigned to the task processing terminal.

12. A task processing device, characterized in that, The device includes: Generate a user return visit task based on the return visit task information and the task dynamic change information; the return visit task information is generated when the sensitive word detection result corresponding to the information interaction event between the agent terminal and the user terminal meets the interaction exception constraint condition; the task dynamic change information includes task processing status information and / or remaining processing time limit information; the interaction exception constraint condition includes at least one of the number of sensitive words being greater than a first preset threshold, the risk level of the sensitive words being higher than a first level threshold, and the number of high-risk sensitive words being greater than a second preset threshold, and the high-risk sensitive words include sensitive words with a risk level higher than the first level threshold; A first input receiving module, configured to receive a first input from a first user to a return visit control; the return visit control is configured for the user return visit task displayed on the visual interface of the task processing terminal, and the user return visit task is generated based on the information interaction event between the agent terminal and the user terminal; A return visit request generating module, configured to generate a user return visit request in response to the first input; the user return visit request carries the identification information of the task processing terminal corresponding to the agent terminal and the identification information of the user terminal, and the task processing terminal includes the original management terminal of the agent terminal or the reassigned management terminal after the return visit task is allocated; A return visit request sending module, configured to send the user return visit request to the server, so that the server responds to the user return visit request and controls the task processing terminal to make a return visit to the user terminal.

13. A task processing device, characterized in that, The device includes: A return visit request receiving module, configured to receive a user return visit request from the task processing terminal; the user return visit request is sent after detecting a first input from a first user to a return visit control, and the return visit control is configured for the user return visit task displayed on the visual interface of the task processing terminal, and the user return visit task is generated based on the information interaction event between the agent terminal and the user terminal; wherein, the user return visit task is generated based on the return visit task information and the task dynamic change information, and the return visit task information is generated when the sensitive word detection result corresponding to the information interaction event meets the interaction exception constraint condition; the task dynamic change information includes task processing status information and / or remaining processing time limit information; the interaction exception constraint condition includes at least one of the number of sensitive words being greater than a first preset threshold, the risk level of the sensitive words being higher than a first level threshold, and the number of high-risk sensitive words being greater than a second preset threshold, and the high-risk sensitive words include sensitive words with a risk level higher than the first level threshold; A user return visit control module, configured to control the task processing terminal to make a return visit to the user terminal in response to the user return visit request, and the task processing terminal includes the original management terminal of the agent terminal or the reassigned management terminal after the return visit task is allocated.

14. A task processing device, characterized in that, The device includes: A processor; and A memory arranged to store computer-executable instructions, the executable instructions being configured to be executed by the processor, the executable instructions including steps for performing the method according to any one of claims 1 to 9 or any one of claims 10 to 11.

15. A storage medium, characterized in that, The storage medium is used to store computer-executable instructions, the executable instructions causing the computer to execute the method according to any one of claims 1 to 9 or any one of claims 10 to 11.

Images