Human-machine cooperation processing method, device and equipment

Abstract

The embodiment of the invention discloses a man-machine cooperation processing method, device and equipment, which are applied to a customer service system. The method comprises the following steps: receiving a customer service request of a user, and correspondingly distributing an artificial customer service to the user as a target artificial customer service; determining a target solution selected from a plurality of solutions through communication between the target manual customer service and the user; sending a robot hosting request to the user; and if agreement information of the user for the robot hosting request is received, switching from the target manual customer service to the mode that the robot adopts the target solution, and continuing to provide customer service for the user.

Description

Technical Field

[0001] This specification relates to the field of intelligent customer service technology, and in particular to a human-machine collaborative processing method, device, and equipment. Background Art

[0002] Many business platforms in daily life have a large user scale and business traffic scale. In order to better and promptly solve various problems of users, a customer service team of corresponding size is needed to serve users.

[0003] With the rapid growth of user demand and intensified market competition, traditional manual customer service faces heavy workloads, slow response times, and inconsistent service quality. These challenges are prompting companies to seek effective solutions to improve customer experience and reduce operating costs. Therefore, based on the development of language models, many platforms have introduced robots capable of intelligent conversation as intelligent customer service.

[0004] In this case, the robot will first communicate with the user. If the user feels that the robot cannot solve the problem, he or she can click to request manual service, and a manual customer will take over to solve the problem for the user. In this way,

[0005] The interaction between robots and users relies entirely on algorithms, and human customers cannot intervene. After transferring to manual service, the human customer service needs to completely solve the current problem, which will completely occupy the time of the human customer service. Moreover, since different customer service staff may have different solutions, the service quality may be affected.

[0006] Based on this, there is a need for a customer service solution that helps reduce the manual burden and is more reliable. Summary of the Invention

[0007] One or more embodiments of this specification provide a human-machine collaborative processing method, device, and equipment to solve the following technical problem: a customer service solution that helps reduce manual burden and is more reliable is needed.

[0008] To solve the above technical problems, one or more embodiments of this specification are implemented as follows:

[0009] One or more embodiments of this specification provide a human-machine collaborative processing method, which is applied to a customer service system. The method includes:

[0010] Receive a customer service request from a user and assign a human customer service representative to the user accordingly;

[0011] Determine a target solution selected from multiple solutions by communicating with the user through the target manual customer service;

[0012] Sending a robot hosting request to the user;

[0013] If the user's consent to the robot hosting request is received, the target manual customer service is switched to the robot using the target solution to continue providing customer service to the user.

[0014] One or more embodiments of this specification provide a human-machine collaborative processing device, which is applied to a customer service system. The device includes:

[0015] A target manual customer service assignment module receives a user's customer service request and assigns a manual customer service representative to the user as a target manual customer service representative accordingly;

[0016] a target solution determination module, determining a target solution selected from multiple solutions by communicating with the user through the target manual customer service;

[0017] A robot hosting request module sends a robot hosting request to the user;

[0018] The robot switching service module, if receiving the user's consent information to the robot hosting request, switches from the target manual customer service to the robot using the target solution to continue providing customer service to the user.

[0019] One or more embodiments of this specification provide a human-machine collaborative processing device, which is applied to a customer service system. The device includes:

[0020] at least one processor; and,

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores instructions executable by the at least one processor, wherein the instructions are executed by the at least one processor to enable the at least one processor to perform:

[0023] Receive a customer service request from a user and assign a human customer service representative to the user accordingly;

[0024] Determine a target solution selected from multiple solutions by communicating with the user through the target manual customer service;

[0025] Sending a robot hosting request to the user;

[0026] If the user's consent to the robot hosting request is received, the target manual customer service is switched to the robot using the target solution to continue providing customer service to the user.

[0027] At least one of the above-mentioned technical solutions adopted in one or more embodiments of this specification can achieve the following beneficial effects: it can enable human customer service to focus on efficiently and accurately identifying the problem for the current user, and then accurately select the target solution that can solve the problem from the relatively standardized solutions prepared in advance. After that, the human customer service can promptly withdraw to serve other users, and entrust subsequent services to the robot for processing. The robot can be responsible for the specific implementation of the target solution and continue to communicate with the current user; in this way, for human customer service, service efficiency is improved, and a single user is avoided from occupying a large amount of time and energy of human customer service, which helps to provide human customer service for more users; for robots, their work difficulty is reduced, and they are mainly responsible for accurately executing the target solution, reducing the probability of misunderstanding users and causing users to repeatedly request human customer service; for users, their problems can be solved more efficiently and reliably, and they do not need to face the robot throughout the process. They feel more valued, and the efficiency of communication with human customers will also be improved; therefore, this customer service solution based on human-computer collaboration has a better experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0029] Figure 1 A flowchart of a human-machine collaborative processing method provided in one or more embodiments of this specification;

[0030] Figure 2 A flowchart of a solution for automatically storing knowledge based on customer service hosting provided in one or more embodiments of this specification;

[0031] Figure 3 A schematic diagram of the interaction flow of a customer service processing solution in a hotline call scenario provided by one or more embodiments of this specification;

[0032] Figure 4 A schematic diagram of a business interface for a transfer hosting customer service provided in one or more embodiments of this specification;

[0033] Figure 5 A schematic diagram of a smooth switching solution between human customer service and robots provided in one or more embodiments of this specification;

[0034] Figure 6A flowchart of a manual customer service recall solution provided in one or more embodiments of this specification;

[0035] Figure 7 A schematic diagram of the structure of a human-machine collaborative processing device provided in one or more embodiments of this specification;

[0036] Figure 8 A schematic diagram of the structure of a human-machine collaborative processing device provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0037] The embodiments of this specification provide a human-machine collaborative processing method, apparatus, device, and storage medium.

[0038] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0039] To address the issues in the background technology, this application considers leveraging human customer service to play a crucial role in the shortest possible time, performing high-threshold, error-prone tasks. This allows robots to promptly take over and complete low-threshold, standardized tasks, thereby forming an efficient and reliable basic customer service solution based on this human-machine collaboration. Furthermore, this application also provides more options to further refine this basic customer service solution, contributing to a higher user experience.

[0040] Based on this general idea, the solution of this application will be further explained below.

[0041] Figure 1 A flow chart of a human-computer collaborative processing method provided for one or more embodiments of this specification, which is applied to a customer service system. The customer service system mainly includes a corresponding customer service server, and may also include a customer service terminal (such as one used by manual customer service or users). The process can be mainly executed on the customer service server. The customer service form can be selected as needed, such as window chat form, hotline form, video form, game form, etc. The interaction methods involved include text interaction, voice interaction, video interaction, action interaction, etc.

[0042] Figure 1 The process in includes the following steps:

[0043] S102: Receive a customer service request from a user, and accordingly assign a human customer service representative to the user as a target human customer service representative.

[0044] When a user encounters a problem and wants help from customer service, he or she can initiate a customer service request through the application end of the corresponding business platform on his or her terminal.

[0045] The customer service system assigns a human agent to each user, who then provides manual customer service. Alternatively, a robot can initially receive the user and conduct an initial conversation. If the robot can resolve the user's issue, it will provide full service without the need for a human agent. If the robot is unable to resolve the user's issue, a human agent will intervene. Users can request human agent assistance as needed.

[0046] Robots are intelligent systems used to automate customer service. They can take various forms, including more vivid and anthropomorphic robots, such as voice robots that automatically answer hotlines and conversational robots that automatically interact with users in chat windows.

[0047] In one or more embodiments of this specification, the focus is on the situation where a human customer intervenes first, and the situation where a robot intervenes first but switches to human customer service very briefly after the intervention; it should be emphasized that the work of human customer service in this application is about precision rather than quantity, and the core part of the work is completed in the shortest possible time.

[0048] S104: Determine a target solution selected from multiple solutions by communicating with the user through the target manual customer service.

[0049] Although the intelligence of robots has made great progress, in actual applications, although robots can communicate with users in a simple way, their efficiency and accuracy in understanding users' problems are still insufficient. Users easily lose patience, which wastes time and affects user experience. Not only that, in many cases, robots are unable to effectively solve problems for users and ultimately have to hand over to manual customer service, which takes up a lot of manual customer service's time.

[0050] Based on this, in one or more embodiments of this specification, the client system pre-prepares multiple possible solutions (more specifically, solutions can be prepared for various pre-defined problems) for efficient and ready access. Solutions can include steps and solutions for specific problems, and the robot can engage in conversations, perform tasks, and other tasks according to the solutions.

[0051] The target human customer service representative communicates with the user and first efficiently and manually determines the problem that the user actually wants to solve when initiating this customer service request (the confirmation of the problem can be just a psychological activity of the target human customer service representative and does not necessarily require explicit action in the system). Then, the human customer service representative selects a solution that is expected to solve the problem from among the multiple solutions based on his or her own understanding of the problem as the target solution.

[0052] It should be noted that the problem may not be a standard problem (for example, it is not a problem predefined by the customer service system), it may not be a typical problem, and it may not even be a problem that the customer service system has encountered before. This can especially reflect the advantages of this application. In this case, the existing technology using robots is usually difficult to reliably understand such problems, while this application is based on manual customer service and can understand such problems more efficiently and reliably, and thus has a higher probability of selecting the correct target solution. Not only that, in actual applications, due to the great differences in the expression ability of different users, it will bring greater difficulties for the robot to correctly understand the problem.

[0053] Based on the above ideas. For example, for example: multiple types of user problems are pre-divided, and solutions are created for these user problems in a standardized, targeted and corresponding manner, which are called standard solutions. User problems are associated with corresponding standard solutions to form a solution knowledge base. The association relationship can be one-to-one, many-to-one or one-to-many. Furthermore, the solution can be specific enough to be executed by a robot (the corresponding business resources can be automatically called), and the execution process does not require the intervention of human customer service, and can actually solve the corresponding problem.

[0054] Through communication with the user, the target agent can, based on their understanding of the conversation, infer the actual problem associated with the user's customer service request. They may also determine whether the problem is directly related to a user problem already defined by the platform, a problem that is similar to a user problem already defined by the platform, or a new problem that is sufficiently different from a user problem already defined by the platform. Furthermore, the target agent can select a corresponding target solution from the solution knowledge base based on existing associations.

[0055] It should be noted that even if the current problem belongs to the similar problems or new problems mentioned above, the existing solutions in the solution knowledge base may still be sufficient to solve it. In this case, the corresponding association relationship may not have been established yet, and the target manual customer service can judge the target solution based on his or her own experience. Subsequently, the current user problem corresponding to the customer service request determined by the target manual customer service and the user can be obtained; if the current user problem is not yet included in the predefined multiple types of user problems (for example, if the similarity with the defined problems is not high enough, it is considered not included), then for the solution knowledge base, an association relationship between the current user problem and the target solution is established, thereby making the solution knowledge base more complete, which will help to locate the correct solution more efficiently based on the newly established association next time, and thus solve the problem.

[0056] In one or more embodiments of the present specification, for user questions, the target human customer service representative may also explicitly confirm with the user to be more reliable. For example, assuming that the target human customer service representative believes that the current user's question is a user question of a certain target type, a confirmation request may be initiated to the user. The method of initiating the request may be a non-standard inquiry (for example, the target human customer service representative directly sends a hand-typed chat message to the user) or a call based on a confirmation component function (for example, the target human customer service representative triggers the immediate display of a confirmation button in the user's chat interface based on the user question of the target type, requiring the user to click to confirm).

[0057] Furthermore, assuming that confirmation information of the user for the above-mentioned target type of user problem is received, a standard solution associated with the target type of user problem can be selected from the solution knowledge base in response to the confirmation information as the target solution, which is more reliable.

[0058] In one or more embodiments of this specification, the target solution is selected by the target manual customer service in person, and in particular, it can be manually selected (for example, specifically clicking on the target solution and confirming it), which is more reliable. In order to reduce the operational burden of the target manual customer service, the query, screening or display method of these solutions can be optimized so that the target manual customer service can more easily and efficiently select the target solution after confirming the need to select the target solution. In the process of communication between the target manual customer service and the user, in order to improve communication efficiency, semantic understanding tools can be used as an aid, such as dialogue summary extraction and other processing. However, the final decision is made by the target manual customer service himself, so the reliability is higher.

[0059] In addition, assuming that there is no suitable solution among the existing solutions to solve the current user's problem, then it is necessary to further create a new solution to connect to the customer service system to solve this problem and other similar problems in the future.

[0060] S106: Send a robot hosting request to the user.

[0061] Selecting the target solution is the core customer service task for this application and is performed by the target human agent. This allows the target human agent to be freed up as quickly as possible, preventing a single user from significantly occupying the human agent's time. Subsequent tasks, such as implementing the target solution and conducting supplementary communication with users, can be quickly delegated to a robot.

[0062] Of course, in order to provide a better user experience, it is necessary to obtain the user's consent before transferring the work. Based on this idea, the target manual customer service can trigger a robot hosting request to the user to request that the next work be transferred to the robot, and the target manual customer service himself will first exit the service (for example, exit the chat window, exit the current hotline, etc.). Under the expected conditions, the robot is more likely to solve the user's problem, and the manual customer service does not need to intervene again.

[0063] S108: If the user's consent to the robot hosting request is received, the target manual customer service is switched to the robot using the target solution to continue providing customer service to the user.

[0064] In one or more embodiments of this specification, the target human customer service representative can provide the user with sufficient explanation of the target solution. For example, the target solution overview can be presented to the user, and the user's current problem can be immediately resolved. This facilitates user understanding and recognition, and helps the user send consent (e.g., verbally agree or click a button indicating consent, etc.), and more patiently and trustingly accept the robot's continued service. From the user's perspective, compared to existing robots, this application is equivalent to a human customer service representative's pre-endorsement of the robot, making it easier for users to accept such robot services.

[0065] Furthermore, the target solution is relatively standardized, so it is easy for robots to take over the work and execute it reliably. The robots basically no longer need to understand the user's ideas. The direction of the entire customer service has been accurately defined by the target human customer service, thereby lowering the working threshold of the robots. Compared with the target human customer service, robots can execute this standardized target solution more efficiently, allowing the target human customer service and the robots to be responsible for the part of the work that they are more advantageous in, respectively, achieving a human-machine collaboration effect that plays to their strengths and avoids their weaknesses, and each doing their own thing.

[0066] pass Figure 1 This method allows human customer service to focus on efficiently and accurately identifying the problem for the current user, and then accurately select the target solution that can solve the problem from the relatively standardized solutions prepared in advance. After that, the human customer service can withdraw in time to serve other users, and entrust the subsequent services to the robot. The robot can be responsible for the specific implementation of the target solution and continue to communicate with the current user. In this way, for human customer service, service efficiency is improved, and a single user is avoided from occupying a large amount of time and energy of human customer service, which helps to provide human customer service for more users. For robots, the difficulty of their work is reduced. They are mainly responsible for accurately executing the target solution, which reduces the probability of users repeatedly requesting human customer service due to misunderstanding the user. For users, their problems can be solved more efficiently and reliably, and they do not need to face the robot throughout the process. They feel more valued, and the efficiency of communication with human customers will also be improved. Therefore, this customer service solution based on human-machine collaboration has a better experience.

[0067] based on Figure 1 This specification also provides some specific implementation plans and extension plans of the method, which will be described below.

[0068] Based on the previous description, we can see that not only can users get a better customer service experience, but the customer system can also accumulate an increasingly powerful solution knowledge base, and can accurately associate more problems with solutions, which may be used for more business purposes.

[0069] More intuitively, one or more embodiments of this specification provide a flow chart of a solution knowledge automatic storage solution based on customer service hosting, see Figure 2 .

[0070] It should be noted that for the solution knowledge base, the applicant has also tried a manual solution, manually tagging problems and associating them with solutions. However, in actual use, it was found that the update process was cumbersome and untimely. Although some systems support automatic answers to basic common questions, they lack a mechanism for dynamically associating and storing complex problems and solutions. As a result, similar problems still require repeated manual participation, thus affecting overall efficiency. Based on this, the above-mentioned automatic storage solution was created and applied as part of the solution of this application.

[0071] Figure 2 The automatic storage solution in the ,focus is to automatically store the solution process of complex problems in the ,customer service hosting mechanism, thereby improving customer service efficiency and user ,user experience.,The automatic storage solution mainly includes the following steps:

[0072] When the robot cannot handle the user's problem, it will transfer the problem to a human operator. This step is optional, and a human operator can also be prioritized to directly connect with customer service.

[0073] Manual communication to clarify problems and identify target solutions;

[0074] The human customer service representative delegates the solution process to the robot, which then continues to communicate with the user and execute the target solution.

[0075] Automatic storage of association relationships: After executing the target solution, the robot solves the user's problem and automatically records the association relationship between the user's problem and the solution process in the knowledge base;

[0076] Optionally, operations staff review: Operations staff regularly review new entries in the knowledge base to ensure their accuracy and validity;

[0077] Automatic processing of similar issues: When similar issues are encountered later, the robot can directly determine the corresponding solution by matching the associations in the knowledge base, without having to transfer it to human customer service again.

[0078] This solution has the ability to automatically generate knowledge associations after human intervention. Robots can handle more and more complex problems, reducing the need for human intervention and improving processing efficiency and user experience. It realizes dynamic hosting and automatic warehousing between customer service and self-service mechanisms, forming a two-way feedback loop. The knowledge base is updated in a timely and accurate manner, improving the availability and accuracy of knowledge.

[0079] More completely, one or more embodiments of this specification also provide a schematic diagram of the interaction process of a customer service processing solution in a hotline call scenario, see Figure 3 It is applicable to all types of hotline service hotline systems, especially in the fields of customer service, technical support, consultation, etc. It can be widely used in telecommunications companies, financial institutions, e-commerce platforms and other customer service industries.

[0080] Regarding the problem mentioned in the background technology, compared with customer service in the form of text chat, hotline call customer service requires higher immediacy (because it is difficult to delay answering the user while maintaining a telephone conversation with the user), therefore, the problem is more severe. The hotline manual customer service has a heavy workload, slow response time, and unstable service quality, and the problem needs to be solved urgently.

[0081] Figure 3 The solution in [1] involves several interacting entities: users, self-service robots (as described above), human customer service representatives, a solution knowledge base, and operators. This solution includes both a pre-configured implementation and an online, real-time implementation.

[0082] The configuration part mainly includes:

[0083] Hotline solutions are classified according to business problems. Operations personnel configure standard solutions for specified types of problems in the solution knowledge base, such as dialogue processes, and the underlying business actions that provide substantive support, etc.

[0084] The service part mainly includes:

[0085] Human customer service answers the user hotline, communicates with the user to clarify the problem, determines the standard solution to be used, and locates the standard solution in the solution knowledge base;

[0086] After the manual customer service confirms and explains to the user, and obtains the user's consent, the call is transferred to the robot, for example, Figure 4 This is a schematic diagram of a business interface for a transfer hosting customer service provided in one or more embodiments of this specification. Figure 4 In the case of a hotline, the customer service is provided. At this point, the manual customer service (agent) has clarified the user's problem by communicating with the user over the phone, and has located the solution in the solution knowledge base. The hosting function can then be triggered. The "Hosting" window that pops up can be seen. The user can select the solution "Name Collection Outbound Call" through the drop-down box, and then click the "Transfer" button in the lower right corner to host the call to the robot.

[0087] After hosting, manual customer service can exit the service;

[0088] The robot is based on the standard solution positioned by human customer service, and continuously communicates with users through voice interaction to solve problems and execute tasks.

[0089] It should be noted that, in addition to the existing solutions mentioned in the background technology, the applicant has also tried fully automated chatbot solutions and manual customer service full response service solutions, but these solutions also have defects. Fully automated chatbots may not be able to handle complex issues, and manual customer service full response will result in high labor costs and long waiting times. Figure 3 The solution in the paper realizes dynamic switching between customer service and robots, adapts to various customer service scenarios, and overcomes the shortcomings of existing technologies in flexibility, reliability and efficiency.

[0090] In one or more embodiments of this specification, the above process switches between manual customer service and robots one or more times. In order to improve the user's consistent experience throughout the entire service process, this application considers customizing a robot dedicated to each manual customer service, which is called a companion robot. The customization method includes: personalized training based on the current manual customer service (for example, historical service data, voice timbre, voice calls, service rhythm, personalized and differentiated speech, etc., which reflect its service communication style).

[0091] Based on this idea, when hosting a robot, you can determine the companion robot corresponding to the target human customer service, switch from the target human customer service to the companion robot corresponding to the target human customer service, and use the target solution to continue providing customer service to users. In this way, from the user's perspective, it seems as if the target human customer service is still continuing to provide service, the switching is smoother, and it is easy to gain user trust.

[0092] Similarly, if a robot is required to make a preliminary judgment before manual customer service, a companion robot can also be used in conjunction, such as: before determining the target manual customer service through communication with the user and selecting the target solution from multiple solutions, a target companion robot is selected from the companion robots corresponding to multiple manual customer services to perform pre-response processing on the customer service request; based on the pre-response processing, it is judged whether the customer service request requires manual intervention, and if the result of the judgment is yes, the target companion robot is switched to the target manual customer service to communicate with the user; wherein, the target companion robot is the companion robot of the target manual customer service.

[0093] It's important to note that the order of determining which human agent or companion robot to use first can be determined as needed, as long as the human agent and companion robot are correctly associated. For example, if a human agent is selected first, then when a robot is needed later, the companion robot of that human agent will be preferred. If a companion robot is selected first, then when a human agent is needed later, the human agent to which the companion robot belongs will be preferred.

[0094] Furthermore, the applicant has also noticed that in actual applications, the switching between human customer service and robots is very abrupt. Users are skeptical about whether the robot understands what happened before, and may also feel uneasy about the exit of human customer service, which can easily lead to a feeling of being perfunctory. To solve this problem, one or more embodiments of this specification provide a flow chart of a smooth switching solution between human customer service and robots, see Figure 5 .

[0095] Figure 5 The process in includes the following steps:

[0096] S502: After allocating a human customer service representative as a target human customer service representative to the user and before sending a robot hosting request to the user, determining a customer service interaction domain provided for the user.

[0097] The customer service interaction domain refers to the space where customer service is provided, such as a corresponding chat window, a call, etc. Customer service staff communicate with users in the customer service interaction domain and provide services to users.

[0098] S504: Within the customer service interaction domain, the user, the target human customer service representative, and the robot accompanying the target human customer service representative conduct a three-party interaction, wherein the interaction method includes text interaction and / or voice interaction.

[0099] In existing technologies, either human or robot customer service representatives communicate with users within the customer service interaction domain, essentially involving two-party communication. This application considers using a target human customer service representative and their accompanying robot to simulate a scenario where multiple people from Party B participate in the communication and work together to solve a problem for Party A, thereby effectively enhancing the sense of sincerity and transparency. In such a scenario, the target human customer service representative and their accompanying robot participate in the communication at the same time.

[0100] S506: During the three-party interaction, the target human customer service representative and the accompanying robot perform one or more interactions that can be directly perceived by the user, so as to serve the user.

[0101] This application not only creates a three-party interactive communication scenario, but also emphasizes that the target human customer service will actively interact with the accompanying robot under the user's perception. For example, it can include explaining the current situation to the accompanying robot, asking the accompanying robot for corresponding resource support, and giving instructions to the accompanying robot immediately, etc. The accompanying robot will cater to the target human customer service for response communication. Of course, users can also join this communication process at any time, making it a scenario for three parties to communicate and discuss together. In this scenario, the user plays the role of Party A, the target human customer service plays the role of the person in charge of Party B or an ordinary employee, and the accompanying robot plays the role of the person in charge of Party B or an ordinary employee of Party B or a subordinate of the person in charge of Party B (especially this role, so that the advantage of the "accompaniment" feature can be better utilized).

[0102] In this way, clearer and more comprehensive communication can be achieved among the three parties, and users can also obtain more transparent information. They also have a clear understanding and information of the specific collaboration methods between the target human customer service and its accompanying robot, as well as the two parties' understanding of the user's own needs. Not only that, this method is very gentle and in line with human emotional needs. Users feel more valued, and it also helps to discover and correct misunderstandings in a timely manner during the three-party interaction process, avoiding back-and-forth situations, which helps to improve communication efficiency and reliability.

[0103] S510: In response to the user's consent to the robot hosting request, the three-party interaction is switched to the companion robot of the target human customer service adopting the target solution to continue providing customer service to the user.

[0104] Based on the sufficient preparation of three-party interaction, users can trust the companion robot more, thereby being able to further and more smoothly switch to being served solely by the companion robot.

[0105] Furthermore, after the switch, considering that the user may still need to recall the manual customer service during the current service process, in order to reduce the user's waiting time in this case and give the manual customer service more buffer time, one or more embodiments of this specification also provide a flow chart of the manual customer service recall solution, see Figure 6 .

[0106] Figure 6 The process in includes the following steps:

[0107] S602: After the target human customer service is switched to the robot using the target solution to continue providing customer service to the user, the accompanying robot of the target human customer service obtains the busy status of the target human customer service.

[0108] Among the different execution modes, the one that matches the current busy state is selected as the target execution mode. Different execution modes are matched to different levels of busyness, and are used to obtain different amounts of buffer time accordingly. In particular, a special execution mode can be created for situations where the target human customer service representative is relatively busy. S604 to S606 exemplify one execution mode, referred to as a complex execution mode.

[0109] S604: Determine whether the busy status reflects that the target human customer service representative is busy enough.

[0110] If the target customer service representative is currently providing services to another user, it is considered relatively busy. Of course, we can more precisely infer whether the service will end quickly. If not, it can be considered to be more busy. Similarly, we can pre-define the specific level of busyness as needed.

[0111] S606: If yes, select the complex execution mode as the target execution mode among different execution modes, wherein, in the complex execution mode, more interactive filling content is added to the interaction process between the companion robot and the user.

[0112] In complex execution mode, the companion robot can communicate with users in a more detailed manner and trigger more interactive scenarios, allowing users to more naturally engage in the service process. This effectively extends the service time and creates a more natural buffer, helping users wait for the target human agent to be unbusy and ready for recall. Conversely, if the target human agent is not currently busy, the companion robot can execute more simply and efficiently.

[0113] S608: In the target execution mode, adopt the target solution to continue providing customer service to the user, so as to prepare to recall the target manual customer service.

[0114] Furthermore, after selecting the complex execution mode as the target execution mode, when continuing to provide customer service to users, if the user interrupts and requests a manual customer service, try to recall the target manual customer service; collect interruption-related scenario data, and modify the complex execution mode based on the scenario data. For example, you can delete or reconstruct part of the interactive filling content to have a higher probability of satisfying the user and other similar users.

[0115] It should be noted that Figure 5 and Figure 6 The solution in this application does not necessarily require the use of the relatively special accompanying robot proposed in this application; a more common robot can also be used. In this case, the accompanying robot mentioned in the corresponding steps can be replaced with a robot, and there does not need to be a rigid correspondence or subordinate relationship between the target human customer service representative and the robot.

[0116] Based on the same idea, one or more embodiments of this specification also provide devices and apparatuses corresponding to the above methods, such as Figure 7 、 Figure 8 The apparatus and device can accordingly execute the above method and related optional solutions.

[0117] Figure 7This is a schematic diagram of the structure of a human-machine collaborative processing device provided in one or more embodiments of this specification, which is applied to a customer service system. The device includes:

[0118] The target manual customer service assignment module 702 receives a customer service request from a user and assigns a manual customer service representative to the user as a target manual customer service representative accordingly;

[0119] A target solution determination module 704 determines a target solution selected from multiple solutions through communication between the target human customer service representative and the user;

[0120] A robot hosting request module 706 sends a robot hosting request to the user;

[0121] The robot switching service module 708 switches from the target manual customer service to the robot using the target solution to continue providing customer service to the user if the user agrees to the robot hosting request.

[0122] Optionally, the target solution determination module 704 associates standard solutions with the divided multiple types of user problems to form a solution knowledge base before receiving the user's customer service request;

[0123] The target solution determination module 704 communicates with the user through the target manual customer service and receives confirmation information from the user on the target type of user problem;

[0124] In response to the confirmation information, a standard solution associated with the user problem of the target type is selected from the solution knowledge base as a target solution.

[0125] Optionally, the target solution determination module 704, after determining the target solution selected from multiple solutions through communication with the user by the target manual customer service, obtains a current user problem corresponding to the customer service request determined through communication with the user by the target manual customer service;

[0126] If the current user question is not included in the multiple types of user questions, then an association relationship between the current user question and the target solution is established for the solution knowledge base.

[0127] Optionally, the target solution is manually selected by the target manual customer service, and the robot hosting request is triggered and sent by the target manual customer service.

[0128] Optionally, the robot switching service module 708 determines a companion robot corresponding to the target human customer service representative, wherein different companion robots are individually trained according to their corresponding human customer service representatives;

[0129] Switch from the target human customer service to the accompanying robot corresponding to the target human customer service, adopt the target solution, and continue to provide customer service to the user.

[0130] Optionally, the robot switching service module 708 selects a target companion robot from the companion robots corresponding to the multiple human customer service representatives to perform pre-response processing on the customer service request before determining the target solution selected by the target human customer service representative from among the multiple solutions through communication with the user;

[0131] Determining whether the customer service request requires manual intervention based on the pre-response processing, and determining if the result of the determination is yes, switching to the target manual customer service to communicate with the user;

[0132] The target accompanying robot is the accompanying robot of the target manual customer service.

[0133] Optionally, the robot switching service module 708 determines a customer service interaction domain provided for the user after allocating a human customer service representative as a target human customer service representative and before sending a robot hosting request to the user;

[0134] In the customer service interaction domain, the user, the target human customer service representative, and the robot accompanying the target human customer service representative conduct a three-party interaction, wherein the interaction method includes text interaction and / or voice interaction;

[0135] During the three-party interaction, the target human customer service representative and the companion robot conduct one or more interactions that can be directly perceived by the user to serve the user;

[0136] The robot switching service module 708 switches from the three-party interaction to the companion robot of the target human customer service alone, adopting the target solution and continuing to provide customer service to the user.

[0137] Optionally, the robot switching service module 708 obtains the busy status of the target human customer service agent by the accompanying robot of the target human customer service agent after the target solution is switched from the target human customer service agent to the robot continuing to provide customer service to the user.

[0138] Selecting an execution mode that matches the current busy state from among different execution modes as a target execution mode;

[0139] In the target execution mode, the target solution is adopted to continue to provide customer service to the user in order to prepare for recalling the target manual customer service.

[0140] Optionally, the robot switching service module 708 determines whether the busy status reflects that the target human customer service representative is sufficiently busy;

[0141] If so, among different execution modes, a complex execution mode is selected as the target execution mode, wherein in the complex execution mode, more interactive filling content is added to the interaction process between the companion robot and the user.

[0142] Optionally, the robot switching service module 708, after selecting the complex execution mode as the target execution mode, attempts to recall the target human customer service if the user interrupts and requests a human customer service in the process of continuing to provide customer service to the user;

[0143] Collect the interruption-related scenario data, and modify the complex execution mode according to the scenario data.

[0144] Figure 8 This is a schematic diagram of the structure of a human-machine collaborative processing device provided in one or more embodiments of this specification, which is applied to a customer service system. The device includes:

[0145] at least one processor; and,

[0146] a memory communicatively connected to the at least one processor; wherein,

[0147] The memory stores instructions executable by the at least one processor, wherein the instructions are executed by the at least one processor to enable the at least one processor to perform:

[0148] Receive a customer service request from a user and assign a human customer service representative to the user accordingly;

[0149] Determine a target solution selected from multiple solutions by communicating with the user through the target manual customer service;

[0150] Sending a robot hosting request to the user;

[0151] If the user's consent to the robot hosting request is received, the target manual customer service is switched to the robot using the target solution to continue providing customer service to the user.

[0152] Based on the same idea, one or more embodiments of this specification further provide a non-volatile computer storage medium, which is applied to a customer service system. The medium stores computer-executable instructions, and the computer-executable instructions are configured as follows:

[0153] Receive a customer service request from a user and assign a human customer service representative to the user accordingly;

[0154] Determine a target solution selected from multiple solutions by communicating with the user through the target manual customer service;

[0155] Sending a robot hosting request to the user;

[0156] If the user's consent to the robot hosting request is received, the target manual customer service is switched to the robot using the target solution to continue providing customer service to the user.

[0157] In the 1990s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures like diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements today can now be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD through their own programming, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly done using "logic compiler" software. This is similar to the software compiler used when developing programs. Before compilation, the original code must also be written in a specific programming language, called a hardware description language (HDL). There is not just one HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also understand that by simply programming the method flow in one of these hardware description languages ​​and then programming it into an integrated circuit, a hardware circuit that implements the logic method flow can be easily obtained.

[0158] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to implementing the controller in a purely computer-readable program code format, the controller can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules that implement the method and structures within the hardware component.

[0159] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0160] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0161] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0162] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0163] These computer program instructions may 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, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0165] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0166] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0167] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The 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 disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, 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 transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0168] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0169] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0170] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0171] The foregoing description of this specification describes specific embodiments. 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 an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0172] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A human-machine collaborative processing method, applied to a customer service system, the method comprising: Receive a customer service request from a user, and accordingly assign a human customer service representative to the user as a target human customer service representative; Determine a target solution selected from multiple solutions by communicating with the user through the target manual customer service; Sending a robot hosting request to the user; If the user's consent information to the robot hosting request is received, the target manual customer service is switched to the robot using the target solution to continue providing customer service to the user.

2. The method according to claim 1, before receiving the customer service request of the user, the method further comprises: For the various types of user problems that have been divided, standard solutions are associated with each of them to form a solution knowledge base; The determining of the target solution selected from multiple solutions through the target manual customer service to communicate with the user specifically includes: Communicate with the user through the target manual customer service and receive confirmation information from the user on the user question of the target type; In response to the confirmation information, a standard solution associated with the user problem of the target type is selected in the solution knowledge base as a target solution.

3. The method according to claim 1 or 2, wherein after determining to communicate with the user through the target manual customer service and selecting a target solution from multiple solutions, the method further comprises: Obtaining a current user problem corresponding to the customer service request determined by communicating with the user through the target manual customer service; If the current user problem is not included in the multiple types of user problems, then an association relationship between the current user problem and the target solution is established for the solution knowledge base.

4. The method as claimed in claim 1, wherein the target solution is manually selected by the target human customer service, and the robot hosting request is triggered and sent by the target human customer service.

5. The method according to claim 1, wherein the switching from the target manual customer service to the robot using the target solution to continue to provide customer service to the user comprises: Determine a companion robot corresponding to the target human customer service, wherein different companion robots are obtained by performing personalized training according to their corresponding human customer service; Switch from the target manual customer service to the companion robot corresponding to the target manual customer service to adopt the target solution and continue to provide customer service to the user.

6. The method according to claim 5, wherein the determining the target manual customer service is performed by communicating with the user, and before the target solution is selected from multiple solutions, the method further comprises: Selecting a target companion robot from among the companion robots corresponding to the multiple manual customer service personnel to perform a pre-response process on the customer service request; According to the pre-response processing, determining whether the customer service request requires manual intervention, and determining that the result of the determination is yes, switching to the target manual customer service to communicate with the user; Among them, the target accompanying robot is the accompanying robot of the target manual customer service.

7. The method according to claim 5, after allocating a human customer service representative to the user as a target human customer service representative and before sending a robot hosting request to the user, the method further comprises: Determining a customer service interaction domain provided for the user; In the customer service interaction domain, the user, the target manual customer service, and the companion robot of the target manual customer service perform a three-party interaction, and the interaction method includes text interaction and / or voice interaction; During the three-party interaction, the target human customer service and the companion robot perform one or more interactions that can be directly perceived by the user, so as to serve the user; The switching to the robot adopting the target solution and continuing to provide customer service to the user specifically includes: From the three-party interaction, the companion robot switches to the target manual customer service alone, adopting the target solution to continue providing customer service to the user.

8. The method of claim 5, after switching from the target manual customer service to the robot using the target solution to continue to provide customer service to the user, the method further comprises: The companion robot of the target human customer service obtains the busy status of the target human customer service; Among different execution modes, selecting an execution mode that matches the current busy state as a target execution mode; In the target execution mode, the target solution is adopted to continue to provide customer service to the user in order to prepare for recalling the target manual customer service.

9. The method according to claim 8, wherein the step of selecting, from among different execution modes, an execution mode that matches the current busy state as the target execution mode, specifically comprises: Determining whether the busy status reflects that the target manual customer service is sufficiently busy; If so, among different execution modes, a complex execution mode is selected as the target execution mode, wherein in the complex execution mode, more interactive filling content is added for the interaction process between the companion robot and the user.

10. The method according to claim 9, after selecting the complex execution mode as the target execution mode, the method further comprises: During the process of continuing to provide customer service to the user, if the user interrupts and requests a manual customer service, then try to recall the target manual customer service; The interruption-related scenario data is collected, and the complex execution mode is modified according to the scenario data.

11. A human-machine collaborative processing device, applied to a customer service system, comprising: A target manual customer service assignment module receives a customer service request from a user and assigns a manual customer service to the user accordingly as a target manual customer service; A target solution determination module determines a target solution selected from multiple solutions by communicating with the user through the target manual customer service; A robot hosting request module, sending a robot hosting request to the user; The robot switching service module, if receiving the user's consent information to the robot hosting request, switches from the target manual customer service to the robot adopting the target solution to continue providing customer service to the user.

12. The device according to claim 11, wherein the target solution determination module, before receiving the customer service request of the user, associates standard solutions for the divided multiple types of user problems respectively to form a solution knowledge base; The target solution determination module communicates with the user through the target manual customer service and receives confirmation information of the user on the user problem of the target type; In response to the confirmation information, a standard solution associated with the user problem of the target type is selected in the solution knowledge base as a target solution.

13. The device according to claim 11 or 12, wherein the target solution determination module, after determining the target solution selected from multiple solutions through the communication between the target human customer service and the user, obtains the current user problem corresponding to the customer service request determined through the communication between the target human customer service and the user; If the current user problem is not included in the multiple types of user problems, then an association relationship between the current user problem and the target solution is established for the solution knowledge base.

14. The apparatus of claim 11, wherein the target solution is manually selected by the target human customer service, and the robot hosting request is triggered and sent by the target human customer service.

15. The device according to claim 11, wherein the robot switching service module determines a companion robot corresponding to the target human customer service, wherein: Different companion robots are trained individually according to their corresponding human customer service staff; Switch from the target manual customer service to the companion robot corresponding to the target manual customer service to adopt the target solution and continue to provide customer service to the user.

16. The device according to claim 15, wherein the robot switching service module selects a target accompanying robot from the accompanying robots corresponding to the plurality of artificial customer services, and performs a pre-response process on the customer service request before determining the target solution selected by the target artificial customer service through communication with the user from among the plurality of solutions; According to the pre-response processing, determining whether the customer service request requires manual intervention, and determining that the result of the determination is yes, switching to the target manual customer service to communicate with the user; in, The target accompanying robot is a companion robot of the target human customer service.

17. The device according to claim 15, wherein the robot switching service module determines a customer service interaction domain provided for the user after allocating a human customer service as a target human customer service and before sending a robot hosting request to the user; In the customer service interaction domain, the user, the target manual customer service, and the accompanying robot of the target manual customer service perform a three-party interaction, and the interaction method includes text interaction and / or voice interaction; During the three-party interaction, the target human customer service and the companion robot perform one or more interactions that can be directly perceived by the user, so as to serve the user; The robot switches the service module from the three-party interaction to the companion robot solely provided by the target human customer service, adopting the target solution and continuing to provide customer service to the user.

18. The device according to claim 15, wherein the robot switching service module, after the target human customer service is switched to the robot adopting the target solution to continue to provide customer service to the user, the companion robot of the target human customer service obtains the busy status of the target human customer service; Among different execution modes, selecting an execution mode that matches the current busy state as a target execution mode; In the target execution mode, the target solution is adopted to continue to provide customer service to the user in order to prepare for recalling the target manual customer service.

19. The device of claim 18, wherein the robot switching service module determines whether the busy state reflects that the target human customer service is sufficiently busy; If yes, among the different execution modes, select the complex execution mode as the target execution mode, where: In the complex execution mode, more interactive filling content is added to the interactive process between the companion robot and the user.

20. The device of claim 19, wherein the robot switching service module, after selecting the complex execution mode as the target execution mode, attempts to recall the target manual customer service if the user interrupts and requests a manual customer service during the process of continuing to provide customer service to the user; The interruption-related scenario data is collected, and the complex execution mode is modified according to the scenario data.

21. A human-machine collaborative processing device, applied to a customer service system, comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute: Receive a customer service request from a user, and accordingly assign a human customer service representative to the user as a target human customer service representative; Determine a target solution selected from multiple solutions by communicating with the user through the target manual customer service; Sending a robot hosting request to the user; If the user's consent information to the robot hosting request is received, the target manual customer service is switched to the robot using the target solution to continue providing customer service to the user.

Images