Task flow switching control method and related device

Abstract

The invention provides a task flow switching control method and a related device, and is applied to a controller of a target service robot, and the method comprises the steps: detecting a call request of a discrete user for the target service robot when a target task flow is executed, and outputting a topic interruption verbal skill to a target client to interrupt the execution of the target task flow; and determining a temporary task flow according to call requests of discrete users. Thus, even in the process that the target service robot provides service for the target customer, the controller of the target service robot can timely detect the call request of the discrete user and timely output the topic interruption verbal skill to interrupt execution of the target task flow, and then temporary service is provided for the discrete user according to the call request of the discrete user. The number of received customers can be increased, customer loss caused by no idle service robot in a service scene is avoided, and the flexibility and intelligence of the service robot are improved.

Description

Technical Field

[0001] This application belongs to the technical field of digital signal processing, and specifically relates to a task flow switching control method and related devices. Background Art

[0002] Currently, offline service scenarios are attempting to use service robots to replace humans in providing services to customers. However, during the process of traditional service robots communicating with current customers, if other users come to inquire about information, since the task flow of traditional service robots is still in the process of serving the current customer, they cannot make a temporary switch and thus cannot attend to the calls of other users, easily resulting in the loss of potential customers. It can be seen that existing service robots still lack flexibility in task flow switching during the service process, have a low level of intelligence, and a poor experience. Summary of the Invention

[0003] Embodiments of this application provide a task flow switching control method and related devices, aiming to enable service robots to attend to the calls of other users during the service process, improve the flexibility and intelligence level of service robots, and optimize the service experience.

[0004] In a first aspect, embodiments of this application provide a task flow switching control method, which is applied to the controller of a target service robot. The method includes: When a call request from a discrete user for the target service robot is detected during the execution of a target task flow, output a topic interruption message to the target customer to interrupt the execution of the target task flow. The target task flow refers to the task flow in which the target service robot serves the business needs of the target customer; Determine a temporary task flow according to the call request of the discrete user. The temporary task flow refers to the task flow in which the target service robot provides temporary service to the discrete user; Execute the temporary task flow.

[0005] It can be seen that in the embodiments of the present application, the controller of the target service robot can detect a call request from a discrete user for the target service robot when executing the target task flow, output a topic interruption message to the target customer to interrupt the execution of the target task flow, where the target task flow refers to the task flow for the target service robot to serve the business needs of the target customer; then, the controller determines a temporary task flow according to the call request of the discrete user and executes the temporary task flow, where the temporary task flow refers to the task flow for the target service robot to provide temporary services to the discrete user. In this way, even during the process of the target service robot serving the target customer, the controller of the target service robot can timely detect the call request of the discrete user, and appropriately output a topic interruption message to interrupt the execution of the target task flow, and then provide temporary services to the discrete user according to the call request of the discrete user, which can increase the number of customers received, avoid customer loss due to no idle service robot in the service scenario, and improve the flexibility and intelligence of the service robot.

[0006] In combination with the first aspect, in a possible embodiment, the detecting a call request from a discrete user for the target service robot when executing the target task flow includes: when executing the target task flow through a first data channel, detecting, through a second data channel, a user to be identified and a call request output by the user to be identified; invoking a visual perception component to collect image information of the user to be identified; determining, through voiceprint recognition and face recognition, that the user to be identified is the discrete user; determining, according to the image information of the user to be identified, the behavior characteristics of the user to be identified when outputting the call request; and determining that the call request of the user to be identified is a call request for the target service robot according to the behavior characteristics.

[0007] It can be seen that the controller of the target service robot can receive external information while executing the target task flow based on the full-duplex communication technology, and further determine that the received external information is a call request from a discrete user for the target service robot through identity recognition and call intention pointing recognition, thereby triggering the task flow switching mechanism, improving the flexibility and intelligence of the robot when providing services, avoiding potential customer loss, and optimizing the service experience.

[0008] In combination with the first aspect, in a possible embodiment, the determining a temporary task flow according to the call request of the discrete user includes: determining the demand information of the discrete user according to the call request of the discrete user; and determining a temporary task flow according to the demand information.

[0009] It can be seen that the controller determines the demand information of the discrete user according to the call request of the discrete user, and then determines the temporary task flow according to the demand information. In this way, the temporary task flow can be associated with the demand information of the discrete user, and the overall service duration for the discrete user can be controlled within a reasonable range, avoiding dissatisfaction of the target customer due to too long service duration in the future, improving the flexibility and intelligence of the service robot when providing services, and optimizing the service experience.

[0010] Combined with the first aspect, in a possible embodiment, the determining the demand information of the discrete user according to the call request of the discrete user includes: performing semantic understanding on the call request of the discrete user to determine whether the call request of the discrete user contains the demand direction of the discrete user; if so, determining the demand information of the discrete user according to the demand direction of the discrete user; if not, searching whether the identity information of the discrete user is stored in the user information database; if not, outputting a first demand guiding message to the discrete user to guide the discrete user to output a first reply content, and determining the demand information of the discrete user according to the first reply content, where the first reply content is used to indicate the demand information of the discrete user; if so, detecting whether the reservation information of the discrete user is stored in the reservation information database according to the identity information of the discrete user, where the reservation information includes reservation demand information; if not, outputting the first demand guiding message to the discrete user to guide the discrete user to output a first reply content, and determining the demand information of the discrete user according to the first reply content; if so, outputting a second demand guiding message to the discrete user according to the reservation information to guide the discrete user to output a second reply content, and determining the demand information of the discrete user according to the second reply content, where the second reply content is used to confirm or deny the reservation demand information.

[0011] It can be seen that the controller of the target service robot can directly determine the demand information from the call request of the discrete user through semantic understanding, and can also guide the discrete user to output the demand information based on the communication with the discrete user. Furthermore, it can determine the temporary task flow according to the demand information, improving the flexibility and intelligence of the service robot when providing services, and optimizing the service experience.

[0012] In combination with the first aspect, in a possible embodiment, the demand information includes business requirements and non-business requirements, and determining the temporary task flow based on the demand information includes: if the demand information is a business requirement, determining that the temporary task flow is a service allocation task flow; if the demand information is a non-business requirement, obtaining the estimated time corresponding to the non-business requirement; if the estimated time is less than or equal to a preset time, determining that the temporary task flow is the task flow corresponding to the non-business requirement; if the estimated time is greater than the preset time, determining that the temporary task flow is the service allocation task flow; wherein the service allocation task flow includes the following steps: detecting whether there is an idle service robot currently in an idle state; if there is , then send a service allocation instruction carrying the conversation content with the discrete user to the idle service robot, the service allocation instruction is used to instruct the idle service robot to provide service to the discrete user; and, output service allocation words to the discrete user, the service allocation words are used to inform the discrete user that the service will be provided by the idle service robot; if it does not exist, synchronize the conversation record with the discrete user to the server to instruct the server to send the service allocation instruction to the idle service robot when detecting the existence of an idle service robot in an idle state; and output service waiting words to the discrete user, the service waiting words are used to inform the discrete user that he needs to wait for the idle service robot for subsequent service.

[0013] It can be seen that the controller can determine the corresponding temporary task flow according to the classification of demand information, associate the temporary task flow with the demand information of discrete users, and control the overall service time for discrete users within a reasonable range, thereby avoiding subsequent dissatisfaction among target customers due to excessive service time, improving the flexibility and intelligence of service robots in providing services, and optimizing the service experience.

[0014] In combination with the first aspect, in a possible embodiment, after executing the temporary task flow, the method also includes: if an execution termination node is detected, switching to execute the target task flow, and the execution termination node is used to indicate that the temporary task flow has been executed; if the execution termination node is not detected and it is detected that the service duration is greater than the preset duration, outputting a service timeout statement to the discrete user, and switching to execute the target task flow, and the service timeout statement is used to inform the discrete user that the service has timed out and needs to wait for an idle service robot to provide subsequent service.

[0015] It can be seen that when the controller detects the execution end node, it confirms that the temporary task flow has been executed, switches to execute the target task flow, so as to reconnect to the service process for the target customer, and when it does not detect the execution end node and detects that the service duration is greater than the preset duration, it actively interrupts the temporary task flow, outputs a service timeout message and switches to execute the target task flow, avoiding dissatisfaction of the target customer and improving the flexibility and intelligence of the service robot when providing services, and optimizing the service experience.

[0016] Combined with the first aspect, in a possible embodiment, the temporary task flow is the service allocation task flow, and the detecting the execution end node includes: after outputting the service allocation message or the service waiting message, detecting the recognition intention of the discrete user.

[0017] It can be seen that when the temporary task flow is the service allocation task flow, the controller can determine whether the temporary task flow has been executed by detecting the recognition intention of the discrete user after outputting the service allocation message or the service waiting message, further improving the flexibility and intelligence of the service robot and optimizing the service experience.

[0018] In a second aspect, an embodiment of the present application provides a task flow switching control device, which is applied to the controller of a target service robot. The device includes: A first processing unit, configured to detect a call request from a discrete user for the target service robot when executing a target task flow, and output a topic interruption message to the target customer to interrupt the execution of the target task flow, where the target task flow refers to a task flow for the target service robot to serve the business needs of the target customer; A second processing unit, configured to determine a temporary task flow according to the call request of the discrete user, where the temporary task flow refers to a task flow for the target service robot to provide temporary services to the discrete user; A third processing unit, configured to execute the temporary task flow.

[0019] In a third aspect, an embodiment of the present application provides a controller, including a processor, a memory, and one or more programs. The one or more programs are stored in the memory and are configured to be executed by the processor. The programs include instructions for performing the steps in the first aspect of the embodiments of the present application.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the steps in the first aspect of the embodiments of the present application are implemented.

[0021] Understandably, the beneficial effects of the embodiments described in the second to fourth aspects can be referred to the beneficial effects in the method described in the first aspect, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 is a structural block diagram of a service robot provided by an embodiment of the present application; Figure 2 is a schematic flowchart of a task flow switching control method provided by an embodiment of the present application; Figure 3 is an example diagram of a task flow of a service provided by an embodiment of the present application; Figure 4 is a schematic diagram of data interaction of a service robot based on full-duplex communication technology provided by an embodiment of the present application; Figure 5 is a schematic flowchart of determining the demand information of discrete users provided by an embodiment of the present application; Figure 6 is a structural block diagram of a task flow switching control device provided by an embodiment of the present application; Figure 7 is a structural block diagram of another task flow switching control device provided by an embodiment of the present application; Figure 8 is a structural block diagram of a controller provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] See also Figure 1 , Figure 1 is a structural block diagram of a service robot provided in an embodiment of the present application. Figure 1 As shown, the service robot 10 includes a controller 11, a sensor component 12 and a motion component 13. The controller 11 is built into the service robot 10, and can be specifically set on the head or chest, and the installation position is not limited. The sensor component 12 includes various sensor devices arranged on the service robot 10, such as a visual perception component, a force feedback sensor, etc.; illustratively, the visual perception component is arranged on the face of the service robot 10 to collect image information facing the direction. The motion component 13 includes a mechanical arm, a mechanical foot, etc., and the motion component 13 is connected to the torso of the service robot 10 and is controlled by the controller 11. Among them, multiple service robots in the same offline service scene can establish communication connections with each other, and each service robot can also establish a communication connection with the Internet of Things server set up in the offline service scene to exchange data so as to better schedule and manage service tasks.

[0028] A task flow switching control method provided by an embodiment of the present application is introduced below.

[0029] See also Figure 2 , Figure 2 is a flowchart of a task flow switching control method provided by an embodiment of the present application, which is applied to Figure 1 In the controller 11 shown, as Figure 2 As shown, the method includes: S201. When a call request from a discrete user for the target service robot is detected during the execution of the target task flow, a topic interruption message is output to the target customer to interrupt the execution of the target task flow.

[0030] Among them, the target task flow refers to the task flow in which the target service robot serves the business needs of the target customer. In the embodiments of the present application, the task flow may specifically be a process with multiple task nodes pre-created by the controller. In a specific application scenario, each type of business need of the customer corresponds to a set of business services, and from the perspective of the service provider, each type of business service has a corresponding business process. The controller can create multiple task nodes based on the corresponding business process, and then generate a task flow corresponding to the business service one by one. As Figure 3 shown, taking the offline vehicle sales service scenario as an example, the business services include various service tasks such as vehicle test drive service 31, vehicle test ride service 32, car purchase consultation service 33, financial insurance service 34, etc. Specifically, taking the vehicle test ride service 31 as an example, its corresponding complete task flow may include: reception 311, pre-communication 312, exterior configuration introduction 313, boarding guidance 314, interior configuration introduction 315, etc. There are switching characteristics between each task node. For example, the switching characteristic between the pre-communication 312 task node and the exterior configuration introduction 313 task node may be detecting a specific switching term or detecting that the position of the target customer reaches near the target vehicle.

[0031] In this example, "during the execution of the target task flow" refers to the process in which the target service robot provides business services for the business needs of the target customer. At this time, while the controller calculates the data generated by the task flow, it can synchronously receive external information and perform detections. Among them, when a call request from a discrete user for the target service robot is detected, if there is no idle service robot in the same service scenario, the controller controls the target service robot to output a topic interruption message to the target customer to interrupt the execution of the target task flow. Exemplarily, the topic interruption message may specifically be: Please wait a moment, and we will continue to serve you later. Further, when the target service robot is in a conversation state, the target service robot will output the topic interruption message after the end of the current conversation state to avoid interrupting the conversation and affecting the service experience of the target customer; among them, the conversation state includes the target service robot being in a listening state or a language output state. Further, after outputting the topic interruption message to the target customer to interrupt the execution of the target task flow, the method further includes: recording the task interruption content of the target task flow, where the task interruption content includes the task interruption node and the conversation record at this task interruption node. In this way, seamless communication with the target customer can be achieved after switching back to the execution of the target task flow, improving flexibility and optimizing the service experience.

[0032] S202. Determine a temporary task flow according to the call request of the discrete user.

[0033] Among them, the temporary task flow refers to the task flow for the target service robot to provide temporary services to the discrete user. In the embodiments of the present application, the temporary service specifically refers to services with short time consumption such as temporary reception and demand synchronization, so that the target service robot can return to continue serving the target customer in time while responding to the call request of the discrete user, and avoid the target customer from having dissatisfaction due to the sudden departure of the target service robot.

[0034] S203. Execute the temporary task flow.

[0035] Among them, the service robot involved in the embodiments of the present application is provided with a language module with multiple languages. If the language of the call request of the discrete user is different from the language used when the target customer and the target service robot have a conversation, the target service robot will switch to the language used by the discrete user to have a conversation with it when executing the temporary task flow, so as to improve the service quality.

[0036] It can be seen that in the embodiments of the present application, the controller of the target service robot can detect the call request of the discrete user for the target service robot when executing the target task flow, output a topic interruption script to the target customer to interrupt the execution of the target task flow. The target task flow refers to the task flow for the target service robot to provide services for the business needs of the target customer; then, the controller determines a temporary task flow according to the call request of the discrete user and executes the temporary task flow. The temporary task flow refers to the task flow for the target service robot to provide temporary services to the discrete user. In this way, even during the process of the target service robot providing services to the target customer, the controller of the target service robot can timely detect the call request of the discrete user, and appropriately output a topic interruption script to interrupt the execution of the target task flow, and then provide temporary services to the discrete user according to the call request of the discrete user, which can increase the number of customers received, avoid customer loss due to no idle service robot in the service scenario, and improve the flexibility and intelligence of the service robot.

[0037] In a possible example, detecting a call request from a discrete user for the target service robot during the execution of the target task flow includes: when executing the target task flow through the first data channel, detecting, through the second data channel, a user to be identified and a call request output by the user to be identified; invoking a visual perception component to collect image information of the user to be identified; determining, through voiceprint recognition and face recognition, that the user to be identified is the discrete user; determining, according to the image information of the user to be identified, the behavior characteristics of the user to be identified when outputting the call request; and determining, according to the behavior characteristics, that the call request of the user to be identified is a call request for the target service robot.

[0038] Among them, the controller of the target service robot involved in the embodiments of the present application can, based on the full-duplex communication technology, have the ability to simultaneously receive and process multiple input data streams. For example, Figure 4 as shown, the service robot 10 receives and processes data information from the target customer 40 through the first data channel to execute the target task flow, and at the same time can receive external information from the user to be identified 41 through the second data channel to detect in real time whether the external information belongs to a call request for the service robot 10.

[0039] It can be understood that the data processing process of receiving external information through the second data channel and performing detection will not be presented to the front end. The front-end performance of the target service robot facing the user is still a process of serving the target service robot, such as dialogue, actions, etc. Further, since the service object corresponding to the target task flow may be a target customer group, and the target customer is a customer in the target customer group who conducts business communication with the target service robot. At this time, if the user to be identified is a customer in the target customer group, it does not belong to a discrete user. Therefore, when detecting, through the second data channel, the user to be identified and the call request output by the user to be identified, it is necessary to further detect whether the user to be identified is a discrete user, and detect whether the call request of the user to be identified is a call request for the target service robot.

[0040] Specifically, in terms of detecting whether the user to be identified is a discrete user, the controller collects the image information of the user to be identified through the visual perception component to extract the facial features of the user to be identified, and analyzes the voice data of the user to be identified to extract the voiceprint features of the user to be identified, and compares them with the facial features and / or voiceprint features of each service customer in the pre-stored target customer group, and then determines whether the user to be identified is a customer in the target customer group. If the judgment result is that the user is not a customer in the target customer group, it is determined that the user to be identified is the discrete user. Among them, the facial features and / or voiceprint features of each service customer in the target customer group can be collected at the beginning of the target task flow. There is a reception task node at the beginning of the target task flow. Under this task node, the target service robot will identify and mark each service customer in the target customer group currently being served, and record the facial features and / or voiceprint features for identity recognition in the subsequent service process.

[0041] Specifically, in terms of detecting whether the call request of the user to be identified is a call request for the target service robot, the controller determines the behavior characteristics of the user to be identified when outputting the call request through the image information of the user to be identified, and then determines the call intention direction of the user to be identified according to the behavior characteristics. For example, if the behavior characteristics of the user to be identified when outputting the call request are facing the target service robot and waving and the distance from the target service robot is less than the preset distance, the call intention direction corresponding to this behavior characteristic can be calculated through the call prediction model to be the target service robot. Further, a multi-modal call prediction model can also be trained to predict the call intention direction of the user by combining multi-faceted call expressions such as language emotion, language content, behavior characteristics, and call distance, further improving the prediction accuracy.

[0042] It can be seen that in this example, the controller of the target service robot can receive external information while executing the target task flow based on the full-duplex communication technology, and further determine that the received external information is a call request from a discrete user for the target service robot through identity recognition and call intention direction recognition, thereby triggering the task flow switching mechanism, improving the flexibility and intelligence of the robot when providing services, avoiding the loss of potential customers, and optimizing the service experience.

[0043] In a possible example, determining the temporary task flow according to the call request of the discrete user includes: determining the demand information of the discrete user according to the call request of the discrete user; determining the temporary task flow according to the demand information.

[0044] Among them, in the offline service scenario, the sudden call of discrete users may be a business requirement, such as the test ride service in the car sales service scenario, or it may also point to other non-business requirements in the service scenario, such as asking about the location of the toilet. Among them, the service durations required by the task flows under different requirements are different. The business goal focused on in this application is that the service robot can take into account the call requests of discrete users while providing services to target customers to provide temporary services, so as to avoid the loss of potential customers. The service duration of the temporary service should be controlled within a reasonable range to avoid dissatisfaction of target customers due to too long waiting time. Therefore, after detecting the call request of a discrete user for a target service robot, further determine its demand information according to the call request of the discrete user, and determine the temporary task flow according to the demand information, which can associate the temporary task flow with the user's demand, and control the overall service duration for the discrete user within a reasonable range at the creation stage of the task flow. Furthermore, while being able to receive discrete users and guide out demand information, it can also avoid dissatisfaction of target customers due to too long service duration.

[0045] It can be seen that in this example, the controller determines the demand information of the discrete user according to the call request of the discrete user, and then determines the temporary task flow according to the demand information. In this way, the temporary task flow can be associated with the demand information of the discrete user, and the overall service duration for the discrete user can be controlled within a reasonable range, avoiding dissatisfaction of target customers caused by too long service duration in the future, improving the flexibility and intelligence of the service robot when providing services, and optimizing the service experience.

[0046] In a possible example, determining the demand information of the discrete user according to the call request of the discrete user includes: performing semantic understanding on the call request of the discrete user to determine whether the call request of the discrete user contains the demand orientation of the discrete user; if so, determining the demand information of the discrete user according to the demand orientation of the discrete user; if not, searching whether the identity information of the discrete user is stored in the user information database; if not, outputting a first demand guiding speech to the discrete user to guide the discrete user to output a first reply content, and determining the demand information of the discrete user according to the first reply content, where the first reply content is used to indicate the demand information of the discrete user; if so, detecting whether the reservation information of the discrete user is stored in the reservation information database according to the identity information of the discrete user, where the reservation information includes reservation demand information; if not, outputting the first demand guiding speech to the discrete user to guide the discrete user to output a first reply content, and determining the demand information of the discrete user according to the first reply content; if so, outputting a second demand guiding speech to the discrete user according to the reservation information to guide the discrete user to output a second reply content, and determining the demand information of the discrete user according to the second reply content, where the second reply content is used to confirm or deny the reservation demand information.

[0047] Please refer to Figure 5 , Figure 5 which is a schematic flowchart of a process for determining the demand information of a discrete user provided by an embodiment of the present application. As Figure 5 shown, the process by which the controller determines the demand information of the discrete user according to the call request of the discrete user includes the following steps: S501, perform semantic understanding on the call request of the discrete user to determine whether the call request of the discrete user contains the demand orientation of the discrete user.

[0048] If so, execute S502; if not, execute S503.

[0049] Among them, the controller specifically first converts the call request of the discrete user into text information through the ASR (Automatic Speech Recognition) service, and then performs semantic understanding on the text information through the LLM (Large Language Model) service, and further determines whether the call request contains the demand orientation of the discrete user, where the demand orientation is used to characterize the demand or purpose reflected by the discrete user in the call request.

[0050] S502, determine the demand information of the discrete user according to the demand orientation of the discrete user.

[0051] Exemplarily, the call request output by the discrete user is: "Hello, may I ask where the toilet is?" At this time, after semantic understanding, the controller extracts the demand orientation included in the call request of the discrete user, and the demand orientation is the toilet and the location. Then, it is further determined that the demand information of the discrete user is to inquire about the location information of the toilet.

[0052] S503, search whether the identity information of the discrete user is stored in the user information database.

[0053] If so, execute S504; if not, execute S505.

[0054] Exemplarily, the call request output by the discrete user is: "Hello, I have a question to consult." At this time, after semantic understanding, the controller can determine that the call request does not contain a demand orientation. At this time, the controller further searches the user information database to determine whether the identity information of the discrete user is stored.

[0055] Among them, the user information database is stored in the server of the service scenario and is used to store the identity information of registered users. The identity information includes the face features of the user, etc. When the target service robot needs to call the user information database, it can obtain and temporarily store it through interaction with the server. Further, specifically searching whether the identity information of the discrete user is stored in the user information database can be to perform a matching search through the face features and the face features stored in the user information database to determine whether the identity information of the discrete user is stored.

[0056] S504, detect whether the reservation information of the discrete user is stored in the reservation information database according to the identity information of the discrete user.

[0057] If so, execute S506; if not, execute S505.

[0058] Among them, the reservation information database is stored in the server of the service scenario and is used to store the reservation information of registered users. The reservation information includes reservation demand information, and the reservation demand information refers to the demand information initially filled in by the user when making a reservation for offline services. Further, the reservation information database can also be used to store the user reservation information of the current day. In this case, the reservation information database can be stored in each service robot to achieve fast calling.

[0059] S505, output the first demand guiding words to the discrete user to guide the discrete user to output the first reply content, and determine the demand information of the discrete user according to the first reply content.

[0060] Among them, the first reply content is used to indicate the demand information of the discrete user. For example, when the call request of the discrete user is content such as "Hello, I have a question to consult" which does not contain a demand pointer, the first demand guiding words can be guiding words such as "Hello, what do you want to consult" to guide the discrete user to output the first reply content containing the demand information. For example, if the first reply content output by the discrete user is "I want to consult the test ride service", the demand information of the discrete user can be determined as the test ride service based on the above first reply content.

[0061] S506, output a second demand guiding word to the discrete user according to the reservation information to guide the discrete user to output a second reply content, and determine the demand information of the discrete user according to the second reply content.

[0062] Among them, the second reply content is used to confirm or deny the reservation demand information. For example, if the demand information initially filled in by the discrete user in the reservation information is the test ride service, the second demand guiding words can be: "Hello, do you want to consult the test ride service?" If the second reply content output by the discrete user is an affirmative reply, it is determined that the demand information of the discrete user is the test ride service; if the second reply content output by the discrete user is a negative reply, the first demand guiding words can be further output to guide the discrete user to output the real demand information.

[0063] It can be seen that in this example, the controller of the target service robot can directly determine the demand information from the call request of the discrete user through semantic understanding, and can also guide the discrete user to output the demand information based on the communication with the discrete user, and then can determine the temporary task flow according to the demand information, improving the flexibility and intelligence of the service robot when providing services and optimizing the service experience.

[0064] In a possible example, the requirement information includes business requirements and non-business requirements. Determining the temporary task flow according to the requirement information includes: if the requirement information is a business requirement, determining that the temporary task flow is a service allocation task flow; if the requirement information is a non-business requirement, obtaining the estimated time required for the non-business requirement; if the estimated time is less than or equal to a preset duration, determining that the temporary task flow is the task flow corresponding to the non-business requirement; if the estimated time is greater than the preset duration, determining that the temporary task flow is the service allocation task flow. Wherein, the service allocation task flow includes the following steps: detecting whether there is an idle service robot in the current state; if so, sending a service allocation instruction carrying the conversation content with the discrete user to the idle service robot, the service allocation instruction being used to instruct the idle service robot to provide services for the discrete user; and outputting a service allocation speech to the discrete user, the service allocation speech being used to inform the discrete user that the idle service robot will provide services; if not, synchronizing the conversation record with the discrete user to the server to instruct the server to send the service allocation instruction to the idle service robot when it detects that there is an idle service robot in the idle state; and outputting a service waiting speech to the discrete user, the service waiting speech being used to inform the discrete user that they need to wait for the idle service robot to perform subsequent services.

[0065] Among them, the controller can classify the requirement information while determining the requirement information of the discrete user. For example, the test ride business requirement belongs to the business requirement, and the requirement of asking for the location information of the toilet belongs to the non-business requirement. In this example, taking the service duration of the temporary service as the primary consideration factor, since the task flow corresponding to the business requirement requires a longer service duration, when it is detected that the requirement information is a business requirement, the target service robot determines that the temporary task flow to be executed next is the service allocation task flow, that is, the target service robot only needs to execute the service allocation process. When it is detected that the requirement information is a non-business requirement, the controller obtains the estimated time required for the non-business requirement, and the estimated time is the average time required for the service robot to execute the task flow corresponding to the non-business requirement obtained by historical data statistics. The historical data can specifically be experimental data, or can also be obtained by the service robot when executing the task flow corresponding to the non-business requirement for service customers, and the statistical method is not uniquely limited.

[0066] Among them, when the estimated time consumption is greater than or equal to the preset duration, it indicates that the service duration required by the task flow corresponding to this non-business requirement is relatively long. At this time, the temporary task flow is determined as the service allocation task flow, that is, the target service robot only needs to execute the service allocation process. Only by way of example, this non-business requirement is "want a glass of juice", and the task flow corresponding to this non-business requirement may require the target service robot to move, etc., and the service duration is relatively long. When the estimated time consumption is less than the preset duration, it indicates that the service duration required by the task flow corresponding to this non-business requirement is relatively short. At this time, the temporary task flow is determined as the task flow corresponding to this business requirement. Only by way of example, this non-business requirement is "ask about the location information of the toilet", and the task flow corresponding to this non-business requirement only needs the target service robot to find the location information of the toilet in the service scenario and output it through the voice module, and the service duration is relatively short. Among them, the preset duration refers to the time critical value that is obtained through statistical analysis of historical data and is likely to cause dissatisfaction among service customers, and it belongs to the empirical data verified through observation.

[0067] Among them, the service allocation task flow specifically includes the following steps: The controller first detects whether there is an idle service robot in the current service scenario, which can be specifically detected through signal interaction with other service robots. If there is an idle service robot, a service allocation instruction carrying the conversation content with the discrete user is sent to the idle service robot, so that the idle service robot can access the conversation with the discrete user without distinction and provide services; at the same time, the target service robot outputs a service allocation script to the discrete user, informing the discrete user that subsequent services will be provided by the idle service robot. For example, the service allocation script can be "Your needs have been understood, and subsequent services will be provided by another service robot for you". If there is no idle service robot, the conversation record with the discrete user is synchronized to the server in the service scenario. The server can monitor the busy and idle states of all service robots in real time. When the server detects that there is an idle service robot, a service allocation instruction is sent to it to instruct the idle service robot to access the conversation with the discrete user without distinction and provide services; at the same time, the target service robot outputs a service waiting script to the discrete user, informing the discrete user that they need to wait for the idle service robot to provide subsequent services. For example, the service waiting script can be "Your needs have been understood, but there is no idle service robot available to provide services at present. Please wait a moment".

[0068] It can be seen that in this example, the controller can determine the corresponding temporary task flow according to the classification of the demand information, associate the temporary task flow with the demand information of the discrete user, control the overall service duration for the discrete user within a reasonable range, avoid dissatisfaction among target customers due to too long service duration in the future, improve the flexibility and intelligence of the service robot when providing services, and optimize the service experience.

[0069] In a possible example, after the execution of the temporary task flow, the method further includes: if an execution end node is detected, switch to execute the target task flow, where the execution end node is used to indicate that the temporary task flow has been executed; if the execution end node is not detected and the service duration is detected to be greater than the preset duration, output a service timeout message to the discrete user and switch to execute the target task flow, where the service timeout message is used to inform the discrete user that the service has timed out and they need to wait for an idle service robot for subsequent services.

[0070] Among them, in the process of normal human-computer interaction and data processing, since the controller has planned the overall service duration of the executed temporary task flow in advance according to the demand information, generally, the temporary task flow can be executed within the preset duration. When the temporary task flow is executed, that is, when the execution end node is detected, switch to execute the target task flow. Specifically, obtain the task interruption content of the target task flow recorded after outputting the topic interruption message to the target customer, and access the target task flow according to the task interruption content to achieve seamless communication with the target customer. In particular, in some cases, in the process of having a conversation with a discrete user to guide the discrete user to output demand information, if the discrete user does not clarify the demand information for a long time in this stage, resulting in the service duration being greater than the preset duration, actively interrupt the temporary task flow, output a service timeout message and switch to execute the target task flow. Among them, the service timeout message can be "Since you have not clarified your demand for a long time, the current service process for you will be interrupted, and other service robots will provide services for you when they are idle later. Please wait a moment."

[0071] It can be seen that in this example, the controller confirms that the temporary task flow has been executed when detecting the execution end node, switches to execute the target task flow to reconnect to the service process for the target customer, and when the execution end node is not detected and the service duration is detected to be greater than the preset duration, actively interrupts the temporary task flow, outputs a service timeout message and switches to execute the target task flow, avoiding dissatisfaction of the target customer and improving the flexibility and intelligence of the service robot when providing services, and optimizing the service experience.

[0072] In a possible example, the temporary task flow is the service allocation task flow, and the detection of the execution end node includes: after outputting the service allocation message or the service waiting message, detecting the approval intention of the discrete user.

[0073] Among them, when the temporary task flow is a service assignment task flow, the execution of the termination node specifically may be that after the target service robot outputs the service assignment speech or the service waiting speech, the recognized intention is included in the reply content output by the discrete user. For example, the discrete user outputs a reply content such as "Okay" that includes the recognized intention.

[0074] It can be seen that in this example, when the temporary task flow is a service assignment task flow, the controller can determine whether the temporary task flow has been completed by detecting the recognized intention of the discrete user after outputting the service assignment speech or the service waiting speech, further improving the flexibility and intelligence of the service robot and optimizing the service experience.

[0075] Consistent with the above-described embodiments, please refer to Figure 6 , Figure 6 which is a structural block diagram of a task flow switching control device provided by an embodiment of the present application. The task flow switching control device is applied to a controller 11 as shown in Figure 1 . The task flow switching control device 60 includes: a first processing unit 601, configured to detect a call request of a discrete user for the target service robot when executing a target task flow, and output a topic interruption speech to the target customer to interrupt the execution of the target task flow. The target task flow refers to a task flow in which the target service robot serves the business needs of the target customer; a second processing unit 602, configured to determine a temporary task flow according to the call request of the discrete user. The temporary task flow refers to a task flow in which the target service robot provides temporary services to the discrete user; a third processing unit 603, configured to execute the temporary task flow.

[0076] In a possible example, in terms of detecting the call request of the discrete user for the target service robot when executing the target task flow, the first processing unit 601 is specifically configured to: when executing the target task flow through the first data channel, detect, through the second data channel, a user to be recognized and a call request output by the user to be recognized; call a visual perception component to collect image information of the user to be recognized; determine, through voiceprint recognition and face recognition, that the user to be recognized is the discrete user; determine, according to the image information of the user to be recognized, a behavior feature of the user to be recognized when outputting the call request; and determine, according to the behavior feature, that the call request of the user to be recognized is a call request for the target service robot.

[0077] In a possible example, in terms of determining the temporary task flow according to the call request of the discrete user, the second processing unit 602 is specifically configured to: determine demand information of the discrete user according to the call request of the discrete user; and determine the temporary task flow according to the demand information.

[0078] In a possible example, in terms of determining the demand information of the discrete user according to the call request of the discrete user, the second processing unit 602 is specifically configured to: perform semantic understanding on the call request of the discrete user, and determine whether the call request of the discrete user contains the demand orientation of the discrete user; if so, determine the demand information of the discrete user according to the demand orientation of the discrete user; if not, search whether the identity information of the discrete user is stored in the user information database; if not, output a first demand guiding speech to the discrete user to guide the discrete user to output a first reply content, and determine the demand information of the discrete user according to the first reply content, where the first reply content is used to indicate the demand information of the discrete user; if so, detect whether the reservation information of the discrete user is stored in the reservation information database according to the identity information of the discrete user, where the reservation information includes reservation demand information; if not, output the first demand guiding speech to the discrete user to guide the discrete user to output a first reply content, and determine the demand information of the discrete user according to the first reply content; if so, output a second demand guiding speech to the discrete user according to the reservation information to guide the discrete user to output a second reply content, and determine the demand information of the discrete user according to the second reply content, where the second reply content is used to confirm or deny the reservation demand information.

[0079] In a possible example, the requirement information includes business requirements and non-business requirements. In terms of determining the temporary task flow according to the requirement information, the second processing unit 602 is specifically configured to: if the requirement information is a business requirement, determine that the temporary task flow is a service allocation task flow; if the requirement information is a non-business requirement, obtain the estimated time required for the non-business requirement; if the estimated time is less than or equal to a preset duration, determine that the temporary task flow is the task flow corresponding to the non-business requirement; if the estimated time is greater than the preset duration, determine that the temporary task flow is the service allocation task flow; wherein, the service allocation task flow includes the following steps: detecting whether there is an idle service robot in an idle state currently; if there is, sending a service allocation instruction carrying the conversation content with the discrete user to the idle service robot, the service allocation instruction being used to instruct the idle service robot to provide services for the discrete user; and outputting a service allocation script to the discrete user, the service allocation script being used to inform the discrete user that the idle service robot will provide services; if there is no idle service robot, synchronizing the conversation record with the discrete user to the server to instruct the server to send the service allocation instruction to the idle service robot when it detects that there is an idle service robot in an idle state; and outputting a service waiting script to the discrete user, the service waiting script being used to inform the discrete user that they need to wait for the idle service robot to perform subsequent services.

[0080] In a possible example, after executing the temporary task flow, the task flow switching control device 60 is further configured to: if it detects an execution end node, switch to execute the target task flow, the execution end node being used to represent that the temporary task flow has been executed; if it does not detect the execution end node and detects that the service duration is greater than the preset duration, output a service timeout script to the discrete user and switch to execute the target task flow, the service timeout script being used to inform the discrete user that the service has timed out and they need to wait for the idle service robot to perform subsequent services.

[0081] In a possible example, when the temporary task flow is the service allocation task flow, in terms of detecting the execution end node, the task flow switching control device 60 is specifically configured to: after outputting the service allocation script or the service waiting script, detect the approval intention of the discrete user.

[0082] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part, and will not be elaborated here.

[0083] In the case of adopting an integrated unit, such asFigure 7 As shown Figure 7 is a structural block diagram of another task flow switching control device provided by an embodiment of the present application. In Figure 7 , the task flow switching control device 60 includes: a processing module 62 and a communication module 61. The processing module 62 is used to control and manage the actions of the task flow switching control device. For example, it executes the steps of the first processing unit 601, the second processing unit 602, and the third processing unit 603, and / or is used to execute other processes of the technologies described herein. The communication module 61 is used to support the interaction between the task flow switching control device and other devices. As Figure 6 shown, the task flow switching control device may further include a storage module 63, and the storage module 63 is used to store the program code and data of the task flow switching control device.

[0084] Among them, all relevant contents of each scenario involved in the above method embodiment can be cited in the function description of the corresponding functional module, and will not be elaborated here. The above task flow switching control device 60 can all execute the above Figure 2 shown task flow switching control method.

[0085] Based on the descriptions of the above method embodiment and device embodiment, please refer to Figure 8 , Figure 8 is a structural schematic diagram of a controller provided by an embodiment of the present application. Figure 8 The shown controller includes a memory 801, a processor 802, a communication interface 803, and a bus 804. Among them, the memory 801, the processor 802, and the communication interface 803 are communicatively connected to each other through the bus 804.

[0086] The memory 801 can be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).

[0087] The memory 801 can store a program. When the program stored in the memory 801 is executed by the processor 802, the processor 802 and the communication interface 803 are used to execute each step of the task flow switching control method of the embodiment of the present application.

[0088] The processor 802 may be a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits, and is used to execute relevant programs to implement the functions required by the units in the controller of the embodiments of the present application, or to execute the task flow switching control method of the method embodiments of the present application.

[0089] The processor 802 may also be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the task flow switching control method of the present application may be completed by the integrated logic circuit in the hardware of the processor 802 or the instructions in the form of software. The above-mentioned processor 802 may also be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application may be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 801, and the processor 802 reads the information in the memory 801 and combines its hardware to complete the functions required by the units included in the controller of the embodiments of the present application, or to execute the task flow switching control method of the method embodiments of the present application.

[0090] The communication interface 803 uses a transceiver device such as, but not limited to, a transceiver to achieve communication between the controller and other devices or communication networks. For example, data can be obtained through the communication interface 803.

[0091] The bus 804 may include a path for transmitting information between various components of the controller (for example, the memory 801, the processor 802, the communication interface 803).

[0092] It should be noted that although Figure 8The controller shown only shows the memory 801, the processor 802, and the communication interface 803. However, in the specific implementation process, those skilled in the art should understand that the controller also includes other devices necessary for normal operation. At the same time, according to specific needs, those skilled in the art should understand that the controller may also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the controller may also only include the devices necessary for implementing the embodiments of the present application, and do not necessarily include Figure 8 all the devices shown in

[0093] The embodiment of the present application also provides a computer storage medium, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, it implements part or all of the steps of any method described in the above method embodiments.

[0094] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0095] In the description of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship. For example, A / B may represent A or B; where A and B may be singular or plural. Also, in the description of the present application, unless otherwise specified, "a plurality of" means two or more than two. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (s) or plural item (s). For example, at least one (item) of a, b, or c may represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, c may be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the terms "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different. At the same time, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "exemplary" or "for example" aims to present relevant concepts in a specific way for easy understanding.

[0096] In several embodiments provided by the present application, it should be understood that the disclosed methods and apparatuses can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the apparatus or unit can be in electrical, mechanical or other forms.

[0097] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] In addition, the functional units in various embodiments of the present invention can be integrated in a processing unit, or each unit can be physically included separately, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0099] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and various modifications and changes can be made, including the combination of the above different functions and implementation steps, including software and hardware implementation methods, all within the protection scope of the present invention.

Claims

1. A task flow switching control method, characterized in that: A controller applied to a target service robot, the method comprising: When executing a target task flow, a call request from a discrete user to the target service robot is detected, and a topic interruption speech is output to the target customer to interrupt the execution of the target task flow, wherein the target task flow refers to a task flow for the target service robot to serve the business needs of the target customer; Determine a temporary task flow according to the call request of the discrete user, wherein the temporary task flow refers to a task flow for the target service robot to perform temporary service on the discrete user; Executing the temporary task flow; Wherein, after executing the temporary task flow, the method further includes: If an execution termination node is detected, switching to execute the target task flow, the execution termination node is used to indicate that the temporary task flow has been executed; If the execution termination node is not detected and it is detected that the service duration is greater than the preset duration, a service timeout statement is output to the discrete user, and the execution of the target task flow is switched. The service timeout statement is used to inform the discrete user that the service has timed out and that the user needs to wait for an idle service robot to provide subsequent service.

2. The method according to claim 1, characterized in that The detecting a call request from a discrete user to the target service robot when executing the target task flow includes: When executing the target task flow through the first data channel, detecting the user to be identified and the call request output by the user to be identified through the second data channel; Calling the visual perception component to collect image information of the user to be identified; Determining that the user to be identified is the discrete user through voiceprint recognition and face recognition; determining, according to the image information of the user to be identified, a behavior feature of the user to be identified when outputting the call request; The call request of the user to be identified is determined to be a call request for the target service robot according to the behavior characteristics.

3. The method according to claim 2, characterized in that The determining of the temporary task flow according to the call request of the discrete user comprises: Determining demand information of the discrete user according to the call request of the discrete user; A temporary task flow is determined according to the demand information.

4. The method according to claim 3, characterized in that The determining the demand information of the discrete user according to the call request of the discrete user includes: Performing semantic understanding on the call request of the discrete user to determine whether the call request of the discrete user contains the demand orientation of the discrete user; If so, determining the demand information of the discrete user according to the demand direction of the discrete user; If not, searching the user information database to see whether the identity information of the discrete user is stored; If not, outputting a first demand guiding speech to the discrete user to guide the discrete user to output a first reply content, determining the demand information of the discrete user according to the first reply content, wherein the first reply content is used to indicate the demand information of the discrete user; If yes, detecting whether reservation information of the discrete user is stored in a reservation information database according to the identity information of the discrete user, wherein the reservation information includes reservation requirement information; If not, outputting the first demand guiding words to the discrete user to guide the discrete user to output a first reply content, and determining the demand information of the discrete user according to the first reply content; If so, a second demand guidance script is output to the discrete user based on the appointment information to guide the discrete user to output a second reply content, and the demand information of the discrete user is determined based on the second reply content, and the second reply content is used to confirm or deny the appointment demand information.

5. The method according to claim 3 or 4, characterized in that: The demand information includes business demand and non-business demand, and determining the temporary task flow according to the demand information includes: If the demand information is a business demand, determining the temporary task flow to be a service allocation task flow; If the demand information is a non-business demand, obtaining the estimated time consumption corresponding to the non-business demand; If the estimated time consumption is less than or equal to the preset time duration, determining that the temporary task flow is the task flow corresponding to the non-business demand; If the estimated time consumption is greater than the preset time length, determining the temporary task flow as the service allocation task flow; The service allocation task flow includes the following steps: Detect whether there is an idle service robot currently in an idle state; If so, a service allocation instruction carrying the conversation content with the discrete user is sent to the idle service robot, the service allocation instruction is used to instruct the idle service robot to provide service for the discrete user; and a service allocation speech is output to the discrete user, the service allocation speech is used to inform the discrete user that the service will be provided by the idle service robot; If not, the conversation record with the discrete user is synchronized to the server to instruct the server to send the service allocation instruction to the idle service robot when detecting the existence of an idle service robot in an idle state; and, the service waiting words are output to the discrete user, and the service waiting words are used to inform the discrete user that he needs to wait for the idle service robot to provide subsequent service.

6. The method according to claim 5, characterized in that The temporary task flow is the task flow assigned to the service, and the detecting of the execution termination node includes: After the service allocation speech or the service waiting speech is output, the approval intention of the discrete user is detected.

7. A task flow switching control device, characterized in that: A controller applied to a target service robot, the device comprising: A first processing unit is configured to detect a call request from a discrete user to the target service robot when executing a target task flow, and output a topic interruption speech to the target customer to interrupt the execution of the target task flow, wherein the target task flow refers to a task flow for the target service robot to provide services for the business needs of the target customer; A second processing unit is used to determine a temporary task flow according to the call request of the discrete user, wherein the temporary task flow refers to a task flow for the target service robot to perform temporary service on the discrete user; A third processing unit, configured to execute the temporary task flow; Wherein, after executing the temporary task flow, the method further includes: If an execution termination node is detected, switching to execute the target task flow, the execution termination node is used to indicate that the temporary task flow has been executed; If the execution termination node is not detected and it is detected that the service duration is greater than the preset duration, a service timeout statement is output to the discrete user, and the execution of the target task flow is switched. The service timeout statement is used to inform the discrete user that the service has timed out and that the user needs to wait for an idle service robot to provide subsequent service.

8. A controller, characterized in that: The method comprises a processor, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images