Method for processing work order, electronic equipment, storage medium and program product
By generating and processing plans and executing outbound calls using intelligent agents, the problems of high labor costs and low efficiency in existing work order processing methods are solved, and intelligent automated work order processing and user communication are realized.
Patent Information
- Application Number
- CN202511114086.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-08
- Publication Date
- 2025-11-25
AI Technical Summary
Existing work order processing methods are inadequate for handling complex user needs and suffer from high labor costs and low processing efficiency.
By leveraging intelligent agents to generate processing plans and execute outbound call actions, work orders can be processed automatically, including generating outbound call scripts and communicating with users.
It reduces labor costs, significantly improves the efficiency of work order processing, and is able to handle complex work orders and realize intelligent outbound call operations.
Smart Images

Figure CN121008722A_ABST
Abstract
Description
Technical Field
[0001] This disclosure generally relates to the field of computers, and more specifically to methods for processing work orders, electronic devices, computer-readable storage media, and computer program products. Background Technology
[0002] With the continuous development of internet technology, users are increasingly able to engage in various activities such as shopping, browsing multimedia content, and creating multimedia content through applications provided by online platforms. While using the various functions offered by these applications, users may encounter a variety of problems or needs, such as issues related to product specifications during shopping or problems encountered during multimedia content creation.
[0003] Typically, users initiate customer service requests to the online platform through channels such as instant messaging or hotlines. The platform's customer service team will address these requests promptly. For cases where immediate resolution is not possible, the platform will create a support ticket. The platform can then follow up on these support tickets to resolve the user's issues or needs. Summary of the Invention
[0004] According to exemplary embodiments of this disclosure, a method, electronic device, and computer storage medium for processing work orders are provided.
[0005] In a first aspect of this disclosure, a method for processing a work order is provided. The method includes: inputting first information to a first intelligent agent, so that the first intelligent agent performs the following operations: generating a processing plan for the work order based on the first information, wherein the first information includes at least one of the following: work order information or information of a business object associated with the work order, and wherein the processing plan includes a processing time and a processing action for processing the work order; and generating an outbound call script associated with the outbound call action in response to a processing action in the processing plan including an outbound call action. The method further includes: inputting second information to a second intelligent agent, so that the second intelligent agent performs the outbound call action from the processing time, wherein the second information includes the outbound call script, and wherein the second intelligent agent performs an outbound call based on the outbound call script to process the work order.
[0006] In a second aspect of this disclosure, an electronic device is provided, comprising: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform a method for processing a work order when executed by the at least one processing unit. The method includes: inputting first information to a first agent to cause the first agent to perform the following operations: generating a processing plan for the work order based on the first information, wherein the first information includes at least one of the following: work order information or information of a business object associated with the work order, and wherein the processing plan includes a processing time and a processing action for processing the work order; and generating an outbound call script associated with the outbound call action in response to a processing action in the processing plan including an outbound call action. The method further includes: inputting second information to a second agent to cause the second agent to perform the outbound call action from the processing time, wherein the second information includes the outbound call script, and wherein the second agent performs the outbound call action based on the outbound call script to process the work order.
[0007] In a third aspect of this disclosure, a computer-readable storage medium is provided having machine-executable instructions stored thereon, which, when executed by a device, cause the device to perform a method for processing a work order. The method includes: inputting first information to a first intelligent agent to perform the following operations: generating a processing plan for the work order based on the first information, wherein the first information includes at least one of the following: work order information or information of a business object associated with the work order, and wherein the processing plan includes a processing time and a processing action for processing the work order; and generating an outbound call script associated with the outbound call action in response to a processing action in the processing plan for processing the work order, including an outbound call action. The method further includes: inputting second information to a second intelligent agent to perform the outbound call action from the processing time, wherein the second information includes the outbound call script, and wherein the second intelligent agent performs the outbound call action based on the outbound call script to process the work order.
[0008] A fourth aspect of this disclosure provides a computer program product including computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement a method for processing a work order. The method includes: inputting first information to a first intelligent agent to cause the first intelligent agent to perform the following operations: generating a processing plan for the work order based on the first information, wherein the first information includes at least one of the following: work order information or information of a business object associated with the work order, and wherein the processing plan includes a processing time and a processing action for processing the work order; and generating an outbound call script associated with the outbound call action in response to a processing action in the processing plan including an outbound call action. The method further includes: inputting second information to a second intelligent agent to cause the second intelligent agent to perform the outbound call action from the processing time, wherein the second information includes the outbound call script, and wherein the second intelligent agent performs the outbound call action based on the outbound call script to process the work order.
[0009] The summary section is provided to introduce a series of concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify key or essential features of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description
[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:
[0011] Figure 1 A schematic diagram of an example system in which embodiments of the present disclosure can be implemented is shown;
[0012] Figure 2 A flowchart of a method for processing work orders according to an embodiment of the present disclosure is shown;
[0013] Figure 3 A schematic diagram of an intelligent agent unit according to an embodiment of the present disclosure is shown;
[0014] Figure 4 A schematic block diagram of an example apparatus according to some embodiments of the present disclosure is shown; and
[0015] Figure 5 A block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation
[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.
[0017] It is understood that, in accordance with the technical solutions disclosed in the embodiments of this disclosure, users have been informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure through appropriate means and their authorization has been obtained, in accordance with the provisions of relevant laws and regulations.
[0018] Online platforms can automate the process of tracking and processing work orders. Currently, this automation is typically based on preset rules and procedures, executing actions (e.g., following up on the work order, closing it, or sending an SMS to the user) when appropriate. While it can handle common problems and needs, current work order automation methods have significant drawbacks. For example, current methods often rely on message queues and rule conditions to trigger actions, making it difficult to handle complex decision-making logic. Furthermore, this approach usually only addresses the follow-up or closure of work orders, failing to establish communication with users (e.g., outbound call negotiation), thus not fully addressing complex user needs.
[0019] Another approach to handling work orders is a manual-assisted solution. This solution typically utilizes tools to translate or convert the work order's processing workflow knowledge base document into a Standard Operating Procedure (SOP). This method primarily serves to determine system nodes. However, this solution still involves a significant number of manual decision-making steps, requiring customer service representatives to manually select actions to keep the SOP running. Because this approach still requires substantial manual judgment, it suffers from high labor costs and relatively low processing efficiency.
[0020] In view of the above, embodiments of this disclosure provide a method for processing work orders. The method includes: inputting first information to a first intelligent agent, so that the first intelligent agent performs the following operations: generating a processing plan for the work order based on the first information, wherein the first information includes at least one of the following: work order information of the work order or information of a business object associated with the work order, and wherein the processing plan includes a processing time and a processing action for processing the work order; and generating an outbound call script associated with the outbound call action in response to a processing action in the processing plan including an outbound call action. The method further includes: inputting second information to a second intelligent agent, so that the second intelligent agent executes the outbound call action from the processing time, wherein the second information includes the outbound call script, and wherein the second intelligent agent executes the outbound call action based on the outbound call script to process the work order.
[0021] According to the method of the present disclosure, work orders can be processed automatically on the work order chain using an intelligent agent. Not only can complex work orders be processed by the intelligent agent, but also outbound call operations can be established through the intelligent agent. This fully leverages the reasoning and language processing capabilities of the intelligent agent, greatly reduces labor costs, and significantly improves the efficiency of work order processing.
[0022] The embodiments of this disclosure will now be described in further detail with reference to the accompanying drawings, wherein... Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Example environment 100 includes an electronic device 110, a network 120, a work order processing device 130, and an intelligent agent unit 140. Users can operate the electronic device 110, for example, by performing various activities such as shopping, browsing multimedia content, and creating multimedia content through applications provided by the network platform. When a problem or need arises, the user can send the problem or need (hereinafter referred to as a "user request") via the network 120 to the work order processing device 130 through a communication application (e.g., an instant messaging program) on the electronic device 110.
[0023] In some embodiments, the work order processing device 130 can process received user requests. In response to a user request being resolved, the work order processing device 130 can terminate the operation for the current user request. In response to a user request not being resolved, the work order processing device 130 can invoke the intelligent agent unit 140 to create a work order for the unresolved user request and process the created work order.
[0024] In some embodiments, the intelligent agent unit 140 may include a first intelligent agent 141 and a second intelligent agent 142. The work order processing device 130 may input first information to the first intelligent agent 141, so that the first intelligent agent 141 performs the following operations: generating a processing plan for the work order based on the first information, wherein the first information includes at least one of the following: work order information or information of a business object associated with the work order, and wherein the processing plan includes a processing time and processing action for processing the work order; and generating an outbound call script associated with the outbound call action in response to a processing action in the processing plan including an outbound call action. The work order processing device 130 may also input second information to the second intelligent agent 142, so that the second intelligent agent 142 performs an outbound call action from the processing time, wherein the second information includes the outbound call script, and wherein the second intelligent agent performs the outbound call action based on the outbound call script to process the work order. In some embodiments, the second intelligent agent 142 may perform an outbound call operation for a user who made a user request, such as... Figure 1 The dashed lines in the diagram indicate this. In some embodiments, the second agent 142 can also perform outbound calls to third parties other than the user who made the user request.
[0025] Any electronic device in electronic device 110 and work order processing device 130 includes, but is not limited to, personal computers, server computers, handheld or laptop devices, mobile devices (such as mobile phones, personal digital assistants (PDAs), media players, etc.), multiprocessor systems, consumer electronics, wearable electronic devices, smart home devices, minicomputers, mainframe computers, edge computing devices, and distributed computing environments that include any of the above systems or devices.
[0026] Furthermore, despite Figure 1 The intelligent agent unit 140 is disposed separately from the work order processing device 130, but this disclosure is not limited thereto. In some embodiments, the intelligent agent unit 140 may be included within the work order processing device 130. Alternatively, at least a portion of the intelligent agents in the intelligent agent unit 140 may be included within the work order processing device 130, while other portions may be disposed separately from the work order processing device 130; this disclosure does not limit this.
[0027] The above combination Figure 1 A block diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is described. The following is in conjunction with… Figure 2 A flowchart describing a method 200 for processing work orders according to an embodiment of the present disclosure. Figure 2 A flowchart of a method for processing work orders according to an embodiment of the present disclosure is shown. Method 200 can be performed in... Figure 1The process is executed at the work order processing device 130 and any suitable computing device. It should be understood that the numbers in the flowchart of method 200 do not indicate the order in which these steps are executed; some or all of these steps can be executed in parallel, or their execution order can be interchanged, and this disclosure does not limit this. Furthermore, Figure 2 Method 200 may also include additional steps not shown and / or the steps shown may be omitted, and the scope of this disclosure is not limited in this respect.
[0028] like Figure 2 As shown, in block 202, the work order processing device 130 can input first information to the first intelligent agent 141 so that the first intelligent agent 141 can perform the following operations: generate a processing plan for the work order based on the first information, wherein the first information includes at least one of the following: work order information of the work order or information of a business object associated with the work order, and wherein the processing plan includes processing time and processing actions for processing the work order; and generate an outbound call script associated with the outbound call action in response to the processing actions in the processing plan including outbound call actions.
[0029] In some embodiments, a work order can be created for user requests (e.g., problems or needs) that are difficult to resolve immediately by the customer service terminal. For example, a work order can be created by a third agent in the agent unit 140, and the creation of a work order by a third agent will be described below.
[0030] After a work order is created, the work order processing device 130 can input first information into the first intelligent agent 141, so that the first intelligent agent 141 can generate a processing plan for the work order. The first information may include at least one of the following: work order information or information of a business object associated with the work order. In addition, the first information may also include graphic information associated with the business object.
[0031] In some embodiments, the work order information may include the user request that the work order needs to be processed. Typically, the work order processing device 130 can obtain the work order information based on user input. The business object associated with the work order may include, for example, an order, created multimedia, or viewed multimedia. The information of the business object associated with the work order may include, for example, information related to the order or information related to the multimedia, and this disclosure is not limited thereto. The graphic and textual information associated with the business object may include information in the form of images and text associated with the business object. Taking an order as an example, the graphic and textual information may include graphic and textual voucher information, such as graphic and textual shopping vouchers generated by the user during the purchase of goods.
[0032] In some embodiments, the first agent 141 can be a work order planning agent, and the first agent 141 can generate a processing plan for the work order based on first information. The processing plan may include one or more of the following: processing action, processing time, target to be contacted, and processing purpose. In some embodiments, the processing action may be an action taken for the work order, such as, but not limited to, work order transfer processing, work order reassignment processing, sending an SMS, outbound call action, closing the work order after sending an SMS, and closing the work order. Work order transfer processing includes transferring the work order to other customer service terminals for processing. Work order reassignment processing refers to forwarding the work order to a human customer service representative for processing. Sending an SMS refers to sending an SMS to the target to be contacted (e.g., a user or a third party other than a user). Outbound call action refers to establishing contact with the target to be contacted by means such as making a phone call. Closing the work order after sending an SMS refers to closing the work order after the user requests processing to be completed and an SMS notification is sent. The processing purpose may include the purpose achieved by processing the work order.
[0033] In some embodiments, the first agent 141 may generate an outbound call script associated with an outbound call action in response to a processing action in the processing plan. The outbound call script may include a planning of the outbound call process. Furthermore, the outbound call script may include multiple script questions, and each of the multiple script questions has a corresponding positive script statement and a negative script statement. In some embodiments, the positive script statement is a response statement in the event of user confirmation of the corresponding script question; the negative script statement is a statement in the event of user denial or failure to receive a response from the user to the corresponding script question after a predetermined time. It is understood that the above examples are for illustrative purposes only, and the first agent 141 of this disclosure may generate any desired outbound call script based on input information.
[0034] Furthermore, in some embodiments, the first intelligent agent 141 may combine first information, such as work order information in the first information, to generate an outbound call script that includes deviation prediction. Deviation prediction includes predictions of deviations from normal work order processing, and the prediction may include a predicted deviation topic and a solution corresponding to the deviation topic.
[0035] At box 204, the work order processing device 130 can input second information to the second agent 142 so that the second agent 142 can perform an outbound call action from the processing time, wherein the second information includes an outbound call script (e.g., an outbound call script generated at box 202), and wherein the second agent 142 performs an outbound call action based on the outbound call script to process the work order.
[0036] In some embodiments, the second agent 142 may be an outbound calling agent, used to establish a connection with the object to be contacted (e.g., a user or a third party other than a user) to process the work order. The second information may include an outbound calling script. Furthermore, the second information may also include a work order summary and information about the business objects associated with the work order, and the work order summary is generated by the first agent 141. Additionally, the second information may include one or more of the following: the outbound phone number, the outbound object (e.g., the object to be contacted), the current time, the processing purpose, etc.
[0037] In some embodiments, the second agent 142 coordinates with the call recipient during the outbound call process. Through coordination, the second agent 142 can determine the appropriate action to be performed. The second agent 142 can execute the action by calling the tool interface corresponding to the action. In some embodiments, the tool interface corresponding to the action may be included in the outbound call script. For example, the second agent 142 can select the tool interface corresponding to the action from the outbound call script, thereby processing the work order by executing the action. For example, during the execution of an outbound call action, through coordination with the call recipient, the second agent 142 determines that "Action A" should be performed. The second agent 142 can select the tool interface corresponding to "Action A" from the outbound call script and call the tool interface to execute "Action A". After executing "Action A", the second agent 142 can send the execution result to the call recipient.
[0038] According to the method of the present disclosure embodiments, work orders can be processed automatically on the work order chain using intelligent agents. Not only can complex work orders be processed through intelligent judgment, but also outbound call operations can be established through intelligent agents. This fully leverages the reasoning and language processing capabilities of intelligent agents, greatly reduces labor costs, and significantly improves the efficiency of work order processing.
[0039] Figure 3 A schematic diagram of an intelligent agent unit according to an embodiment of the present disclosure is shown. For example... Figure 3 As shown, the agent unit 300 may include a first agent 310, a second agent 320, and a third agent 330. In some embodiments, an unresolved user request may be sent from a customer service terminal to the agent unit 300, whereby the third agent 330 in the agent unit 300 creates a work order for the unresolved request.
[0040] In some embodiments, the work order processing device 130 may input third information to a third intelligent agent 330, so that the third intelligent agent 330 can create a work order for the unresolved user request. The third information may include at least one of the following: information about the business object corresponding to the work order or dialogue information. Dialogue information is dialogue information authorized by the outbound call object or the user. In some embodiments, the business object associated with the work order may include, for example, an order, created multimedia, or viewed multimedia. The information of the business object associated with the work order may include, for example, information related to an order or information related to multimedia, etc., and this disclosure does not limit this.
[0041] In some embodiments, the third agent 330 may create a work order for an unresolved user request based on third information, and the created work order may include the pending item (e.g., a "work order follow-up tag") and the follow-up time. In some embodiments, the third agent 330 may create a work order in response to dialogue information from a customer service terminal; and the third agent 330 may update the work order in response to the dialogue information being generated based on an outbound call action, as detailed below.
[0042] The created work order can be distributed to the work order configuration platform 340. In some embodiments, the work order processing device 130 can be located at the work order configuration platform 340. At the work order configuration platform 340, the work order processing device 130 can determine whether the work order meets the closure conditions. In response to the work order meeting the closure conditions, the work order processing device 130 can close the work order and stop processing it. In response to the work order not meeting the closure conditions, the work order processing device 130 can invoke the first intelligent agent 310 to process the work order. In some embodiments, the work order processing device 130 can invoke the first intelligent agent 310 based on the follow-up time in the work order to trigger the first intelligent agent 310 to perform the operation shown in block 202. For example, when the work order processing device 130 determines that the follow-up time has arrived, the work order processing device 130 can invoke the first intelligent agent 310 to process the work order.
[0043] In some embodiments, the work order processing device 130 may input first information into the first intelligent agent 310 so that the first intelligent agent 310 may perform the following operations: generate a processing plan for the work order based on the first information, wherein the first information includes at least one of the following: work order information of the work order or information of a business object associated with the work order, and wherein the processing plan includes processing time and processing actions for processing the work order; and generate an outbound call script associated with the outbound call action in response to the processing actions in the processing plan including an outbound call action.
[0044] The first intelligent agent 310 can generate a processing plan for the work order based on the first information. In some embodiments, the first information includes at least one of the following: work order information of the work order or information of a business object associated with the work order. The first information may also include graphic and textual information associated with the business object. The first information can be understood with reference to the description above, and for the sake of simplicity, it will not be repeated here.
[0045] The first intelligent agent 310 can generate a processing plan for the work order based on the first information. The processing plan may include one or more of the following: processing actions, processing time, processing objects, or processing purposes. In some embodiments, the processing action may be a processing action taken for the work order, such as, but not limited to, work order transfer processing, work order reassignment processing, sending an SMS message, outbound call action, closing the work order after sending an SMS message, and closing the work order.
[0046] In some embodiments, the first agent 310 may generate an outbound call script associated with an outbound call action in response to a processing action in the processing plan, including an outbound call action. The outbound call script may include a planning of the outbound call process and multiple script questions. Each of the multiple script questions has corresponding positive and negative script statements. Furthermore, in some embodiments, the first agent 310 may combine first information to generate an outbound call script that includes a deviation prediction, where the deviation prediction represents a prediction of a deviation from the normal processing work order, and the deviation prediction includes the predicted deviation topic and a solution corresponding to the deviation topic.
[0047] In some embodiments, in response to a processing action including an outbound call, the work order processing device 130 can input second information to the second intelligent agent 320, so that the second intelligent agent 320 can execute the outbound call from the processing time scheduled in the work order. In some embodiments, the second information may include an outbound call script, a work order summary generated by the first intelligent agent 310, and information about the business object. For example, the work order processing device 130 can receive the outbound call script and work order summary from the first intelligent agent 310, and input them together with the information about the business object to the second intelligent agent 320.
[0048] Based on the second information, the second agent 320 can execute an outbound call action from the start of the processing time. The second information includes an outbound call script, and the second agent 320 can execute the outbound call action to process the work order based on the outbound call script. The outbound call script may include the planning of the outbound call process and multiple script questions. Accordingly, the second agent 320 can establish a connection with the outbound call object according to the outbound call process planning in the outbound call script. Each script question in the outbound call script has corresponding positive and negative script statements. The second agent 320 can establish a connection with the outbound call object by searching for the script statement corresponding to the response in the outbound call script, based on the response from the outbound call object.
[0049] In some embodiments, the outbound call script in the second information may further include one or more tool interfaces that the second agent 320 may potentially use, and the second agent 320 may invoke candidate tool interfaces from one or more tool interfaces to process the work order when performing an outbound call action. For example, during the outbound call process, the second agent 320 may coordinate with the outbound call object. Through coordination, the action to be performed can be determined. The second agent 320 may invoke the tool interface included in the outbound call script to perform the action.
[0050] In some embodiments, the second intelligent agent 320 can perform outbound call actions based on automatic speech recognition and text-to-speech. For example, the second intelligent agent 320 can convert the speech received from the outbound call recipient into text based on automatic speech recognition, and convert the statements in the outbound call script into speech and output them to the outbound call recipient using text-to-speech technology.
[0051] In some embodiments, when an outbound call is completed, the work order processing device 130 can determine whether the work order has been resolved by the outbound call, thereby determining whether the work order can be closed. If the work order cannot be closed, the work order processing device 130 can input the dialogue information between the second agent 320 and the outbound object (i.e., the dialogue information is generated based on the outbound call action; for example, the dialogue information may include outbound call records) and the information of the business object associated with the work order back to the third agent 330, so that the third agent 330 can update the work order. Upon receiving the dialogue information generated based on the outbound call action, the third agent 330 can update the work order. For example, the third agent 330 can update the work order follow-up tag and work order follow-up time in the work order, and send the updated work order to the work order configuration console 340 for the next round of processing. Specific processing methods can be combined with... Figure 2 and Figure 3 The description in [the document] is for reference only; for the sake of brevity, it will not be repeated here. By utilizing intelligent agents for multi-round work order follow-up processing, labor costs can be greatly reduced and work order processing efficiency can be improved.
[0052] In some embodiments, the work order monitoring device 350 can monitor whether the outbound call script generated by the first intelligent agent 310 is appropriate, and if it determines that the outbound call script is inappropriate, it generates an outbound call script update instruction and sends the outbound call script update instruction to the work order processing device 130. In response to the outbound call script update instruction, the work order processing device 130 can invoke the first intelligent agent 310 to generate an updated outbound call script based on first information. The first intelligent agent 310 can send the updated outbound call script to the work order processing device 130. The work order processing device 130 can input the updated outbound call script as second information to the second intelligent agent 320, thereby causing the second intelligent agent 320 to perform an outbound call action based on the updated outbound call script. In some embodiments, the work order monitoring device 350 can monitor the outbound call action performed by the second intelligent agent 320 in real time, and if it determines that the outbound call action is inappropriate, it generates a termination instruction to end the outbound call action. The work order monitoring device 350 can send the termination instruction to the work order processing device 130. In response to a termination command, the work order processing device 130 can control the second intelligent agent 320 to terminate the outbound call action.
[0053] In some embodiments, the monitoring function of the work order monitoring device 350 can be manually performed. If the outbound call script generated by the first intelligent agent 310 is detected to be inappropriate, the work order monitoring device 350 can be triggered to generate an outbound call script update instruction. If the outbound call action performed by the second intelligent agent 320 is detected to be inappropriate, the work order monitoring device 350 can be triggered to generate a termination instruction to end the outbound call action.
[0054] Figure 4 A schematic block diagram of an example apparatus 400 according to some embodiments of the present disclosure is shown. Apparatus 400 may be implemented in software, hardware, or a combination of both. Figure 4 As shown, the device 400 includes a first input module 410 and a second input module 420.
[0055] In some embodiments, the first input module 410 may input first information to the first intelligent agent so that the first intelligent agent performs the following operations: generating a processing plan for a work order based on the first information, wherein the first information includes at least one of the following: work order information of the work order or information of a business object associated with the work order, and wherein the processing plan includes processing time and processing actions for processing the work order; and generating an outbound call script associated with the outbound call action in response to the processing actions in the processing plan including an outbound call action.
[0056] In some embodiments, the second input module 420 may input second information to the second agent so that the second agent may perform a call action from the start of the processing time, wherein the second information includes an outbound call script, and wherein the second agent performs the outbound call action based on the outbound call script to process the work order.
[0057] In some embodiments, the device 400 may further include a third input module, which may be configured to input third information to a third agent for the third agent to create or update a work order. The third information includes at least one of the following: information about the business object and dialogue information, and wherein the created or updated work order includes pending matters and follow-up time.
[0058] In some embodiments, in response to dialogue information generated based on an outbound call action, the third agent updates the work order; or in response to dialogue information originating from a customer service terminal, the third agent creates a work order.
[0059] In some embodiments, the first agent is invoked at the follow-up time to perform the operation.
[0060] In some embodiments, the processing action may also include one or more of the following: work order flow processing, work order reassignment processing, sending SMS or closing the work order.
[0061] In some embodiments, the outbound call script includes a candidate tool interface, and the second agent invokes the candidate tool interface to process the work order when performing an outbound call action.
[0062] In some embodiments, the outbound call script includes deviation prediction, which includes a prediction of deviation from the normal processing work order, and the prediction includes the predicted deviation topic and a solution corresponding to the deviation topic.
[0063] In some embodiments, the second information further includes at least one of the following: a work order summary and information about the business object, wherein the work order summary is generated by the first agent.
[0064] In some embodiments, the device 400 may further include a calling module, which may be configured to: in response to receiving an outbound call script update instruction, call a first agent to generate an updated outbound call script based on first information, wherein the second information includes the updated outbound call script.
[0065] In some embodiments, the device 400 may further include a control module, which may be configured to control the second agent to terminate the outbound call action in response to receiving a termination command.
[0066] In some embodiments, the second intelligent agent performs outbound call actions based on automatic speech recognition and text-to-speech.
[0067] Figure 4 The device 400 can be used to achieve the above-mentioned combination. Figures 1 to 3 For the sake of brevity, the process described will not be repeated here.
[0068] The division of modules or units in the embodiments of this disclosure is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional units in the disclosed embodiments may be integrated into one unit, exist as separate physical entities, or two or more units may be integrated into one unit. The integrated unit described above can be implemented in hardware or as a software functional unit.
[0069] Figure 5 A block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. It should be understood that... Figure 5 The electronic device 500 shown is merely an example and should not be construed as limiting the functionality and scope of the implementation described herein. For example, electronic device 500 can be used in conjunction with the implementation described herein. Figure 1 The work order processing device 130 described above can be used to perform the tasks described above. Figures 1 to 4 The process described.
[0070] like Figure 5 As shown, electronic device 500 is in the form of a general-purpose computing device. Components of electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. Processing unit 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 500.
[0071] Electronic device 500 typically includes multiple computer storage media. Such media can be any available media accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof). Storage device 530 can be removable or non-removable media and may include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data (e.g., training data for training) and accessible within electronic device 500.
[0072] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 5 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various implementations of this disclosure.
[0073] Communication unit 540 enables communication with other computing devices via a communication medium. Additionally, the functionality of the components of electronic device 500 can be implemented as a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.
[0074] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).
[0075] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is provided that stores a computer program thereon, which, when executed by a processor, implements the methods described above.
[0076] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.
[0077] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.
[0078] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.
[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0080] Various implementations of this disclosure have been described above. The foregoing description is exemplary and not exhaustive, nor is it limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.
Claims
1. A method for processing work orders, comprising: The first information is input into the first intelligent agent, so that the first intelligent agent performs the following operations: Based on the first information, a processing plan for the work order is generated, wherein the first information includes at least one of the following: work order information of the work order or information of the business object associated with the work order, and wherein the processing plan includes the processing time and processing actions for processing the work order. as well as In response to the processing action in the processing plan, which includes an outbound call action, an outbound call script associated with the outbound call action is generated; as well as The second information is input to the second agent so that the second agent can execute the outbound call action from the processing time, wherein the second information includes the outbound call script, and wherein the second agent executes the outbound call action based on the outbound call script to process the work order.
2. The method according to claim 1, further comprising: A third piece of information is input to a third agent to create or update the work order. The third piece of information includes at least one of the following: information about the business object or dialogue information, and the created or updated work order includes pending items and follow-up time.
3. The method according to claim 2, wherein, In response to the dialogue information being generated based on the outbound call action, the third agent updates the work order; or in response to the dialogue information originating from a customer service terminal, the third agent creates the work order.
4. The method of claim 2, wherein the first agent is invoked at the follow-up time to perform the operation.
5. The method according to claim 1, wherein the processing action further includes one or more of the following: work order flow processing, work order reassignment processing, sending SMS or closing the work order.
6. The method according to claim 1, wherein the outbound call script includes a candidate tool interface, and wherein the second agent invokes the candidate tool interface to process the work order when performing the outbound call action.
7. The method of claim 1, wherein the outbound call script includes deviation prediction, the deviation prediction including a prediction of deviation from normal processing of the work order, and wherein the prediction includes a predicted deviation topic and a solution corresponding to the deviation topic.
8. The method according to claim 1, wherein the second information further includes at least one of the following: a work order summary and information of the business object, and wherein the work order summary is generated by the first intelligent agent.
9. The method according to claim 1, further comprising: In response to receiving an outbound call script update instruction, the first agent is invoked to generate an updated outbound call script based on the first information, wherein the second information includes the updated outbound call script.
10. The method according to claim 1, further comprising: In response to receiving a termination command, the second intelligent agent is controlled to terminate the outbound call action.
11. The method according to claim 1, wherein the second intelligent agent performs the outbound call action based on automatic speech recognition and text-to-speech.
12. An electronic device, comprising: At least one processing unit; At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 11 when executed by the at least one processing unit.
13. A computer-readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing the method according to any one of claims 1 to 11.
14. A computer program product having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 11.
Citation Information
Patent Citations
Customer service outbound management system
CN114189589A
User call-out method and device, processor and machine readable storage medium
CN117592946A
Task work order generation method and device, storage medium and electronic equipment
CN119151277A
Complaint automatic management system and method based on agent workflow
CN119168650A
Integrated customer service method and system based on multiple agents
CN119359316A