Service robot control method and related device

Abstract

The invention provides a service robot control method and a related device, and the method comprises the steps: detecting a non-business demand of a second service customer in a conversation process with a first service customer, and determining a potential transaction factor under a current task node according to the non-business demand, the first service customer and the second service customer are customers in a target customer group corresponding to the target task flow; a derivative task flow is generated according to the potential transaction factors, the derivative task flow comprises a service task flow and a marketing task flow, and the marketing task flow refers to a task flow for marketing by the target service robot in combination with the potential transaction factors; and executing the derivative task flow. Thus, the service robot can carry out key marketing based on the mined potential transaction point, the situation that the potential transaction point is ignored under the condition that a client does not explicitly express the function requirement corresponding to the potential transaction point is avoided, the flexibility and the intelligent degree of the service robot in the service process are enhanced, and the business transaction rate is improved.

Description

Technical Field

[0001] The present application belongs to the field of electronic digital processing technology, and specifically relates to a service robot control method and related devices. Background Art

[0002] At present, offline service scenarios are trying to use service robots to provide services to customers instead of humans in order to improve the quality of business services. However, in service scenarios where the service target is a customer group, when a traditional service robot is talking to one of the customers to provide business services, if another customer from the customer group calls the service robot to consult about non-business needs, the traditional service robot cannot analyze the potential transaction points in the current business based on the non-business needs of the customer and provide marketing services based on this. If the customer does not explicitly express certain functional requirements, the potential transaction points are easily overlooked. It can be seen that the existing service robots still lack the function of exploring potential transaction points based on the non-business needs of customers during the service process, and their intelligence level is not high and they lack flexibility, which affects the business transaction rate. Summary of the invention

[0003] The embodiments of the present application provide a service robot control method and related devices, so as to enable the service robot to explore potential transaction points while meeting the non-business needs of the service goals, enhance the flexibility and intelligence of the service robot in the service process, and improve the business transaction rate.

[0004] In a first aspect, an embodiment of the present application provides a service robot control method, which is applied to a controller of a target service robot, and the method includes: During the conversation with the first service customer, a non-business demand of the second service customer is detected, and a potential transaction factor under the current task node is determined according to the non-business demand, the first service customer and the second service customer are customers in the target customer group corresponding to the target task flow, and the target task flow refers to the task flow in which the target service robot provides services for the business demand of the target customer group; Generate a derivative task flow according to the potential transaction factors, the derivative task flow including a service task flow and a marketing task flow, the service task flow refers to a task flow in which the target service robot provides services for the non-business needs of the second service customer, and the marketing task flow refers to a task flow in which the target service robot performs marketing in combination with the potential transaction factors; The derived task flow is executed.

[0005] It can be seen that in the embodiment of the present application, the controller of the target service robot can detect the non-business needs of the second service customer during the conversation with the first service customer, and determine the potential transaction factors under the current task node based on the non-business needs. The first service customer and the second service customer are customers in the target customer group corresponding to the target task flow. The target task flow refers to the task flow in which the target service robot provides services for the business needs of the target customer group; then a derivative task flow is generated and executed based on the potential transaction factors. The derivative task flow includes a service task flow and a marketing task flow. The service task flow refers to the task flow in which the target service robot provides services for the non-business needs of the second service customer, and the marketing task flow refers to the task flow in which the target service robot performs marketing in combination with the potential transaction factors. In this way, the target service robot can receive and detect the non-business needs of the second service customer while providing business services to the first service customer, and determine the potential transaction factors under the current task node based on their non-business needs, and then generate a derivative task flow based on the potential transaction factors and execute the derived task flow, so as to carry out key marketing based on the mined potential transaction points, avoid ignoring the potential transaction points when the customer does not explicitly express the functional requirements corresponding to the potential transaction points, enhance the flexibility and intelligence of the service robot in the service process, and improve the business transaction rate.

[0006] In combination with the first aspect, in a possible embodiment, before the non-business needs of the second service customer are detected during the conversation with the first service customer, the method also includes: calling the visual perception component to collect facial images of each customer in the target customer group to obtain a target facial image set; and storing the target facial image set.

[0007] It can be seen that the controller can call the visual perception component to collect and store the facial images of each customer in the target customer group, and can mark each customer currently being served to distinguish their identity information, which is conducive to carrying out follow-up services and improving the flexibility of the service robot during the service process.

[0008] In combination with the first aspect, in a possible embodiment, the non-business needs of the second service customer are detected during the conversation with the first service customer, including: during the conversation with the first service customer through the first data channel, a call request of the user to be identified is detected through the second data channel, and the call request is used to indicate the non-business need; calling the visual perception component to collect the facial image of the user to be identified; detecting that the feature similarity between the facial image of the user to be identified and a target facial image in the target facial image set is greater than a preset similarity, and determining that the user to be identified is the second service customer, and the target facial image refers to any other facial image in the target facial image set except the facial image corresponding to the first service customer.

[0009] It can be seen that the controller can receive external information through the second data channel during the conversation with the first service customer through the first data channel, and collect the facial image of the user to be identified and compare it with the target facial image in the pre-stored target facial image set one by one to determine that the received external information is the non-business demand of the second service customer, and then determine the potential transaction factors under the current task node based on the non-business demand, thereby improving the flexibility and intelligence of the service robot in providing services.

[0010] In combination with the first aspect, in a possible embodiment, determining the potential transaction factors under the current task node based on the non-business demand includes: determining the potential demand portrait of the second service customer based on the non-business demand; obtaining multiple marketing tasks under the current task node; determining the target portrait feature in the potential demand portrait, the target portrait feature refers to the portrait feature in the potential demand portrait that has a correlation with the target marketing task in the multiple marketing tasks; determining the potential transaction factors based on the target portrait feature and the target marketing task.

[0011] It can be seen that the controller can determine the potential demand profile of the second service customer based on non-business needs, and obtain multiple marketing tasks under the current task node, and then determine the target profile features that are associated with the target marketing tasks in the potential demand profile, and then determine the potential transaction factors. In this way, the controller can mine the potential transaction factors under the current task node based on the non-business needs of the second service customer, avoiding ignoring the potential transaction point when the customer does not explicitly express the functional requirements corresponding to the potential transaction point, thereby enhancing the flexibility and intelligence of the service robot in the service process.

[0012] In combination with the first aspect, in a possible embodiment, generating a derivative task flow based on the potential transaction factors includes: generating the service task flow based on the non-business needs of the second service customer; generating target marketing scripts based on the target portrait features and the target marketing task; generating the marketing task flow based on the target marketing scripts; and determining the derivative task flow based on the service task flow and the marketing task flow.

[0013] It can be seen that the controller can generate a service task flow based on the non-business needs of the second service customer, generate target marketing words based on the target portrait features and target marketing tasks, generate a marketing task flow based on the target marketing words, and then determine the derivative task flow. In this way, the service robot can focus on marketing based on the potential transaction points mined, avoiding ignoring the potential transaction points when the customer does not explicitly express the functional needs corresponding to the potential transaction points, enhancing the flexibility and intelligence of the service robot in the service process and improving the business transaction rate.

[0014] In combination with the first aspect, in a possible embodiment, the generating the target marketing script according to the target portrait characteristics and the target marketing task includes: generating a marketing guidance script according to the target portrait characteristics and the non-business needs of the second service customer, the marketing guidance script being used to indicate a product function associated with the non-business needs of the second service customer; generating the target marketing script according to the marketing guidance script and the initial marketing script corresponding to the target marketing task.

[0015] It can be seen that the controller can generate marketing guidance words according to the target portrait characteristics and the non-business needs of the second service customer, and generate target marketing words in combination with the initial marketing words corresponding to the target marketing task. In this way, the controller can carry out key marketing based on the potential transaction points mined, enhance the flexibility and intelligence of the service robot in the service process, and improve the business transaction rate.

[0016] In combination with the first aspect, in a possible embodiment, the service task flow includes a target switching flag, and the target switching flag is used to indicate that the service task flow has been executed, and the execution of the derived task flow includes: executing the service task flow; when the target switching flag is detected, switching to execute the marketing task flow.

[0017] It can be seen that when executing the derived task flow, the controller first executes the service task flow. When the target switching mark is detected, it determines that the service task flow is completed and switches to execute the marketing task flow, which ensures the smoothness of the task flow execution and improves the flexibility and intelligence of the service robot in the service process.

[0018] In a second aspect, an embodiment of the present application provides a service robot control device, which is applied to a controller of a target service robot, and the device includes: A first processing unit is configured to detect a non-business demand of a second service customer during a conversation with a first service customer, and determine a potential transaction factor under a current task node according to the non-business demand, wherein the first service customer and the second service customer are customers in a target customer group corresponding to a target task flow, and the target task flow refers to a task flow in which the target service robot provides services for the business demand of the target customer group; a second processing unit, configured to generate a derivative task flow according to the potential transaction factors, wherein the derivative task flow includes a service task flow and a marketing task flow, wherein the service task flow refers to a task flow in which the target service robot provides services for the non-business needs of the second service customer, and the marketing task flow refers to a task flow in which the target service robot performs marketing in combination with the potential transaction factors; The third processing unit is used to execute the derived task flow.

[0019] In a third aspect, an embodiment of the present application provides a controller comprising 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 program comprises instructions for executing the steps in the first aspect of the embodiment of the present application.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implements the steps in the first aspect of the embodiment of the present application.

[0021] It can be understood that the beneficial effects of the embodiments described in the second to fourth aspects can refer to the beneficial effects of the method described in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 is a structural block diagram of a service robot provided in an embodiment of the present application; Figure 2 It is a flow chart of a service robot control method provided in an embodiment of the present application; Figure 3This is an example diagram of a task flow of a business service provided by an embodiment of the present application; Figure 4 This is a schematic diagram of a service interaction process provided by an embodiment of the present application; Figure 5 This is another service interaction flow diagram provided by an embodiment of the present application; Figure 6 is a structural block diagram of a service robot control device provided in an embodiment of the present application; Figure 7 is a structural block diagram of another service robot control device provided in an embodiment of the present application; Figure 8 It is a structural block diagram of a controller provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this 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 1As 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 can be arranged on the face of the service robot 10 to collect image information facing the direction, and the force feedback sensor can be arranged on a dexterous hand to feedback the grasping force in real time. 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 and / or smart device set in the offline service scene to perform data interaction to realize instruction allocation and resource management. The smart devices involved in the offline service scenario may include the smart robotic arm of the service bar. For example, the service robot can issue instructions to the smart robotic arm to make drinks at the service bar. In particular, when the offline service scenario is a vehicle sales service scenario, the smart device may also include a vehicle system for displaying vehicles. The service robot can remotely control the vehicle system through data interaction with the vehicle system to cooperate with business services for functional display, further improving the flexibility of the service process.

[0028] A service robot control method provided by an embodiment of the present application is introduced below.

[0029] See also Figure 2 , Figure 2 is a flow chart of a service robot 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, detecting a non-business demand of a second service customer during a conversation with a first service customer, and determining potential transaction factors under a current task node according to the non-business demand.

[0030] Among them, the first service customer and the second service customer are customers in the target customer group corresponding to the target task flow. In the embodiment of the present application, the service object of the service robot is a target customer group including multiple customers, that is, the business needs of each customer in the target customer group are the same. For example, in a vehicle sales service scenario, a family of three comes to consult about the trial ride service, then the target customer group includes three customers, and the business needs of the three customers are all trial ride services.

[0031] The target task flow refers to the task flow of the target service robot providing services for the business needs of the target customer group. In the embodiment of the present application, the task flow specifically refers to a process with multiple task nodes pre-created by the controller. In a specific application scenario, each business need of the customer corresponds to a set of business services, and each business service has a corresponding business process from the perspective of the service provider. The controller can create multiple task nodes based on the corresponding business process, and then generate a task flow that corresponds to the business service one by one. Figure 3 As shown, taking the offline vehicle sales service scenario as an example, the business service includes a variety of service tasks such as vehicle test ride service 31, vehicle test drive service 32, vehicle purchase consulting service 33, and financial insurance service 34. Specifically, taking the vehicle test ride service 31 as an example, its corresponding complete task flow may include: reception 311, pre-communication 312, vehicle exterior configuration introduction 313, vehicle boarding guidance 314, vehicle interior configuration introduction 315 and other multiple task nodes, and there is a switching feature between each task node. Further, each task node may include multiple marketing tasks, and the marketing task mainly refers to the task of conducting marketing to improve the transaction rate through function introduction, function demonstration, and preferential introduction. Taking the vehicle interior configuration introduction 315 task node as an example, the vehicle interior configuration introduction 315 task node specifically includes: the first marketing task 3151, the second marketing task 3152, etc., wherein the first marketing task 3151 may be, for example, a marketing task related to a vehicle refrigerator, and the second marketing task 3152 may be, for example, a marketing task related to a vehicle water dispenser.

[0032] Among them, the non-business needs refer to needs that are not related to business in offline service scenarios, such as the need for cold drinks, the need for hot water, and the location of the toilet. In actual services, customers' non-business needs are random, and some non-business needs can reflect customer preferences. If we can dig out factors that match customer preferences at the current task node in random events and focus on marketing, they may become potential business transaction points and improve the business transaction rate.

[0033] S202: Generate a derivative task flow according to the potential transaction factors.

[0034] Among them, the derived task flow includes a service task flow and a marketing task flow. The service task flow refers to the task flow in which the target service robot provides services for the non-business needs of the second service customer, and the marketing task flow refers to the task flow in which the target service robot performs marketing in combination with the potential transaction factors.

[0035] S203: Execute the derived task flow.

[0036] Among them, the front-end representation of the service robot facing the user at the same time can only be for a single customer, and the front-end representation is, for example, dialogue, action, etc., to avoid communication confusion. When the controller needs to execute multiple task flows, and the task nodes of multiple task flows at the same time all need to perform front-end representations for their respective customers, the controller will control the service robot to select a task flow with a higher priority for execution according to the priority of the task flow. For example, in this example, if the target task flow requires the target service robot to have a dialogue with the first service customer, and the derived task flow requires the target service robot to have a dialogue with the second service customer, the controller will control according to the priority of the task flow. For example, if the priority of the derived task flow is higher than the priority of the target task flow, the target service robot will switch to execute the derived task flow.

[0037] For example, assuming that the non-business demand of the second service customer is to drink ice cola, the service task flow in the derived task flow includes the process of making ice cola. If the smart devices involved in the current offline service scenario cannot assist in making ice cola, for example, the smart robotic arm at the service bar is not included, then Figure 4 As shown, the service task flow may specifically include: the target service robot outputs a first preset speech to the second service customer, the first preset speech may be "prepare to go to the service bar to make ice cola, and send it to you later", and goes to the service bar to make the target item and transfers it to the second service customer, the target item is ice cola. In this scenario, the entire service task flow belongs to the user-oriented front-end representation. At this time, the target service robot needs to interrupt the target task flow first and switch to execute the derived task flow.

[0038] In particular, if the target service robot is in dialogue with the first service client, that is, when executing the target task flow, the derived task flow does not need to perform front-end representation for the second service client at the current time point, then the target task flow and the derived task flow can be executed in parallel.

[0039] For example, assuming that the non-business demand of the second service customer is to drink ice cola, the service task flow in the derived task flow includes the production process of ice cola. If the smart device involved in the current offline service scene includes the smart robotic arm of the service bar, then Figure 5As shown, the service task flow may specifically include: the target service robot sends an instruction to make ice cola to the intelligent mechanical arm, and outputs a second preset speech to the second service customer. The second preset speech may be "Ice cola is being made and will be delivered to you later". Among them, the process of the target service robot sending the instruction to make ice cola to the intelligent mechanical arm belongs to the data interaction on the device side, and does not belong to the front-end representation facing the user. Therefore, the task flow corresponding to this part can be executed in parallel with the target task flow, that is, the target service robot can still talk to the first service customer at this time. Among them, the process of outputting the preset speech to the second service customer belongs to the front-end representation facing the user. At this time, the target service robot needs to interrupt the target task flow first, continue to execute the derivative task flow, and output the preset speech to the second service customer. Then the controller continuously monitors the completion signal of the mechanical arm to detect whether the ice cola is completed. This process still belongs to the data interaction on the device side. At this time, the target service robot can resume executing the target task flow and continue to talk to the first service customer. When the controller detects the completion signal of the robotic arm, the target service robot needs to go to the service bar to pick up the target item and transfer it to the second service customer. The target item is an ice cola. This process belongs to the user-oriented front-end representation. At this time, the target service robot needs to continue to interrupt the target task flow and continue to execute the derived task flow.

[0040] It is understandable that when the controller detects that the target service robot is still in a conversation state with the first service customer before interrupting the target task flow, the controller will interrupt the target task flow after the current conversation state ends to avoid interrupting the conversation and affecting the service experience. The current conversation state includes that the target service robot is in a listening state or a language output state.

[0041] It can be seen that in the embodiment of the present application, the controller of the target service robot can detect the non-business needs of the second service customer during the conversation with the first service customer, and determine the potential transaction factors under the current task node based on the non-business needs. The first service customer and the second service customer are customers in the target customer group corresponding to the target task flow. The target task flow refers to the task flow in which the target service robot provides services for the business needs of the target customer group; then a derivative task flow is generated and executed based on the potential transaction factors. The derivative task flow includes a service task flow and a marketing task flow. The service task flow refers to the task flow in which the target service robot provides services for the non-business needs of the second service customer, and the marketing task flow refers to the task flow in which the target service robot performs marketing in combination with the potential transaction factors. In this way, the target service robot can receive and detect the non-business needs of the second service customer while providing business services to the first service customer, and determine the potential transaction factors under the current task node based on their non-business needs, and then generate a derivative task flow based on the potential transaction factors and execute the derived task flow, so as to carry out key marketing based on the mined potential transaction points, avoid ignoring the potential transaction points when the customer does not explicitly express the functional requirements corresponding to the potential transaction points, enhance the flexibility and intelligence of the service robot in the service process, and improve the business transaction rate.

[0042] In one possible example, before the non-business needs of the second service customer are detected during the conversation with the first service customer, the method further includes: calling a visual perception component to collect facial images of each customer in the target customer group to obtain a target facial image set; and storing the target facial image set.

[0043] Among them, the controller can automatically call the visual perception component to collect the facial image of each user when the user enters the offline service scene, so as to query information in advance and analyze whether it is a customer who has made an appointment on the same day, thereby improving service efficiency. Among them, after determining the target task flow, the controller will further determine the target customer group corresponding to the target task flow based on characteristic factors such as user behavior characteristics and user language characteristics and through dialogue, and re-collect the facial images of the corresponding customers to obtain a target facial image set, thereby marking multiple customers currently being served for distinguishing identity information.

[0044] It can be seen that in this example, the controller can call the visual perception component to collect and store the facial images of each customer in the target customer group, and can mark each customer currently being served to distinguish identity information, which is conducive to carrying out subsequent services and improving the flexibility of the service robot in the service process.

[0045] In one possible example, the non-business demand of the second service customer is detected during the conversation with the first service customer, including: during the conversation with the first service customer through the first data channel, a call request of the user to be identified is detected through the second data channel, and the call request is used to indicate the non-business demand; calling the visual perception component to collect the facial image of the user to be identified; detecting that the feature similarity between the facial image of the user to be identified and a target facial image in the target facial image set is greater than a preset similarity, and determining that the user to be identified is the second service customer, and the target facial image refers to any other facial image in the target facial image set except the facial image corresponding to the first service customer.

[0046] Among them, the controller of the target service robot involved in the embodiment of the present application can have the ability to simultaneously receive and process multiple input data streams based on full-duplex communication technology, that is, the controller can receive and process data information from the first service customer through the first data channel to execute the target task flow to realize the dialogue with the first service customer, and can also receive external information through the second data channel to detect in real time whether the external information belongs to the non-business needs of the second service customer. It can be understood that the process of receiving and detecting external information through the second data channel does not belong to the user-oriented front-end representation described in the above embodiment, so the controller does not need to interrupt the execution of the target task flow during the execution of this process, that is, the parallel processing process.

[0047] In this example, the call request of the user to be identified directly includes non-business needs, such as "I want a cup of ice cola", then the controller can directly determine that the non-business need of the user to be identified is "ice cola" through basic data processing such as intent recognition and semantic understanding. Furthermore, the controller calls the visual perception component to collect the facial image of the user to be identified, and compares it one by one with each target facial image in the pre-stored target facial image set, calculates the feature similarity, and compares it with the preset similarity to determine the second service customer. It can be understood that the target facial image used for comparison calculation refers to any other facial image except the facial image corresponding to the first service customer.

[0048] It can be seen that in this example, the controller can receive external information through the second data channel during the conversation with the first service customer through the first data channel, and collect the facial image of the user to be identified and compare it with the target facial images in the pre-stored target facial image set one by one to determine that the received external information is the non-business demand of the second service customer, and then determine the potential transaction factors under the current task node based on the non-business demand, thereby improving the flexibility and intelligence of the service robot in providing services.

[0049] In a possible example, determining the potential transaction factors under the current task node based on the non-business demand includes: determining the potential demand portrait of the second service customer based on the non-business demand; obtaining multiple marketing tasks under the current task node; determining the target portrait feature in the potential demand portrait, the target portrait feature refers to the portrait feature in the potential demand portrait that has an association with the target marketing task in the multiple marketing tasks; determining the potential transaction factors based on the target portrait feature and the target marketing task.

[0050] Among them, the potential demand portrait of the second service customer refers to the character portrait composed of the demand characteristics obtained after analyzing and disassembling the non-business demand of the second service customer. For example, the non-business demand of the second service customer is "ice cola", and the controller can determine that the potential portrait characteristics corresponding to the non-business demand are "cold drink" and "cola", and these potential portrait characteristics together constitute the potential demand portrait of the second service customer. On this basis, the current task node is recorded as the in-vehicle configuration introduction task node, and the controller further obtains multiple marketing tasks under the in-vehicle configuration introduction task node, such as marketing tasks related to car refrigerators, marketing tasks related to car water dispensers, etc. Further, the controller performs a correlation test on multiple potential portrait characteristics in the potential demand portrait and marketing tasks respectively, and determines the target marketing tasks and target portrait characteristics with correlation relationships. Exemplarily, the marketing tasks related to car refrigerators include the functional introduction of car refrigerators, and the functions of car refrigerators include making cold drinks, which can be associated with the potential portrait feature "cold drink", and then determine that the target portrait feature is "cold drink" and the target marketing task is a marketing task related to car refrigerators. For another example, if the non-business demand of the second service customer is "need hot water", the controller can determine that the potential portrait feature corresponding to the non-business demand is "hot water", and then determine that the marketing task that is associated with the potential portrait feature "hot water" is a marketing task related to the vehicle-mounted water dispenser.

[0051] It can be seen that in this example, the controller can determine the potential demand profile of the second service customer based on non-business needs, and obtain multiple marketing tasks under the current task node, and then determine the target profile features in the potential demand profile that are associated with the target marketing tasks, and then determine the potential transaction factors. In this way, the controller can mine the potential transaction factors under the current task node based on the non-business needs of the second service customer, avoiding ignoring the potential transaction point when the customer does not explicitly express the functional requirements corresponding to the potential transaction point, thereby enhancing the flexibility and intelligence of the service robot in the service process.

[0052] In a possible example, generating a derivative task flow based on the potential transaction factors includes: generating the service task flow based on the non-business needs of the second service customer; generating target marketing scripts based on the target portrait features and the target marketing task; generating the marketing task flow based on the target marketing scripts; and determining the derivative task flow based on the service task flow and the marketing task flow.

[0053] Among them, the derived task flow is composed of a service task flow and a marketing task flow. The service task flows corresponding to different non-business needs are different. The service task flows corresponding to the same non-business needs in different offline service scenarios may also be different, such as offline service scenarios with robotic arms to assist in making cold drinks and offline service scenarios without robotic arms to assist in making cold drinks. In an embodiment of the present application, the marketing task flow refers to the task flow of the target service robot for marketing in combination with the potential transaction factors, that is, the marketing task flow is a more targeted task flow obtained by the controller reproducing the task flow corresponding to the target marketing task in the target task flow in combination with the target portrait features. Specifically, the controller generates the target marketing script according to the target portrait features and the target marketing task, and then generates the marketing task flow according to the target marketing script.

[0054] It can be seen that in this example, the controller can generate a service task flow based on the non-business needs of the second service customer, generate target marketing words based on the target portrait features and target marketing tasks, generate a marketing task flow based on the target marketing words, and then determine the derivative task flow. In this way, the service robot can focus on marketing based on the potential transaction points mined, avoiding ignoring the potential transaction points when the customer does not explicitly express the functional requirements corresponding to the potential transaction points, enhancing the flexibility and intelligence of the service robot in the service process and improving the business transaction rate.

[0055] In one possible example, generating the target marketing words according to the target portrait characteristics and the target marketing task includes: generating a marketing guidance words according to the target portrait characteristics and the non-business needs of the second service customer, the marketing guidance words being used to indicate product functions associated with the non-business needs of the second service customer; generating the target marketing words according to the marketing guidance words and the initial marketing words corresponding to the target marketing task.

[0056] The generating of marketing guidance words according to the target portrait features and the non-business needs of the second service customer includes: generating marketing guidance words according to a pre-stored marketing guidance words template, the target portrait features and the non-business needs of the second service customer. For example, if the non-business need of the second service customer is "ice cola" and the target portrait features are "cold drinks", the marketing guidance words may be "This is your ice cola, please hold it firmly. If you want to enjoy cold drinks on the road, this car refrigerator may be able to meet your needs."

[0057] Among them, the target marketing task originally belongs to a marketing task under the current task node in the target task flow, which corresponds to an initial marketing speech. Exemplarily, taking the target marketing task as a marketing task related to a car refrigerator as an example, the initial marketing speech includes a connection speech and a functional marketing speech, wherein the connection speech is used to introduce a marketing strategy related to the car refrigerator, such as "Next, I will introduce another highlight function to you, the car refrigerator", wherein the functional marketing speech includes an introduction to the hardware information, software function and preferential means of the car refrigerator. The generating of the target marketing speech according to the marketing guidance speech and the initial marketing speech corresponding to the target marketing task includes: combining the marketing guidance speech with the functional marketing speech in the initial marketing speech to generate the target marketing speech.

[0058] It can be seen that in this example, the controller can generate marketing guidance words according to the target portrait characteristics and the non-business needs of the second service customer, and generate target marketing words in combination with the initial marketing words corresponding to the target marketing task. In this way, the controller can carry out key marketing based on the potential transaction points mined, enhance the flexibility and intelligence of the service robot in the service process, and improve the business transaction rate.

[0059] In one possible example, the service task flow includes a target switching flag, and the target switching flag is used to indicate that the service task flow has been executed. The execution of the derived task flow includes: executing the service task flow; when the target switching flag is detected, switching to execute the marketing task flow.

[0060] For example, taking the non-business demand of the second service customer to drink ice cola as an example, the detection of the target switching mark can be specifically: the grasping force is detected in real time by the force feedback sensor on the dexterous hand, and when the grasping force reaches the preset force corresponding to the second service customer holding the water cup firmly, it is determined that the target switching mark is detected. At this time, the marketing task flow is switched to focus on the marketing of the functions related to the car refrigerator.

[0061] In terms of marketing, the service robot can establish a communication connection with the vehicle computer system, and then remotely control the pop-up, start-up, mode adjustment and other functions of the vehicle refrigerator. Combined with marketing words, the functions of the vehicle refrigerator can be introduced more clearly. At the same time, the configuration and discount information of the vehicle refrigerator can be displayed on the vehicle computer central control display.

[0062] After the marketing task flow is executed, it is determined that the derived task flow is executed, and the controller switches to the target task flow. It can be understood that since the marketing task flow is a task flow obtained by reproducing the task flow corresponding to the target marketing task in the target task flow, after the derived task flow is executed, the controller will delete the corresponding part of the task flow in the target task flow to avoid repeated marketing.

[0063] It can be seen that in this example, when executing the derived task flow, the controller first executes the service task flow. When the target switching flag is detected, it determines that the service task flow is completed and switches to execute the marketing task flow, which ensures the smoothness of the task flow execution and improves the flexibility and intelligence of the service robot in the service process.

[0064] In accordance with the above-mentioned embodiments, please refer to Figure 6 , Figure 6 is a structural block diagram of a service robot control device provided in an embodiment of the present application, wherein the service robot control device is applied to Figure 1 In the controller 11 shown, the service robot control device 60 includes: a first processing unit 601, which is used to detect the non-business needs of the second service customer during the conversation with the first service customer, and determine the potential transaction factors under the current task node according to the non-business needs, the first service customer and the second service customer are customers in the target customer group corresponding to the target task flow, and the target task flow refers to the task flow of the target service robot providing services for the business needs of the target customer group; a second processing unit 602, which is used to generate a derivative task flow according to the potential transaction factors, and the derivative task flow includes a service task flow and a marketing task flow. The service task flow refers to the task flow of the target service robot providing services for the non-business needs of the second service customer, and the marketing task flow refers to the task flow of the target service robot performing marketing in combination with the potential transaction factors; a third processing unit 603, which is used to execute the derivative task flow.

[0065] In one possible example, before detecting the non-business needs of the second service customer during the conversation with the first service customer, the service robot control device 60 is also used to: call the visual perception component to collect facial images of each customer in the target customer group to obtain a target facial image set; and store the target facial image set.

[0066] In one possible example, in terms of detecting the non-business needs of the second service customer during the conversation with the first service customer, the first processing unit 601 is specifically used to: detect a call request of the user to be identified through the second data channel during the conversation with the first service customer through the first data channel, and the call request is used to indicate the non-business need; call the visual perception component to collect the facial image of the user to be identified; detect that the feature similarity between the facial image of the user to be identified and a target facial image in the target facial image set is greater than a preset similarity, and determine that the user to be identified is the second service customer, and the target facial image refers to any other facial image in the target facial image set except the facial image corresponding to the first service customer.

[0067] In one possible example, in terms of determining the potential transaction factors under the current task node based on the non-business needs, the first processing unit 601 is specifically used to: determine the potential demand portrait of the second service customer based on the non-business needs; obtain multiple marketing tasks under the current task node; determine the target portrait features in the potential demand portrait, and the target portrait features refer to the portrait features in the potential demand portrait that have an association with the target marketing tasks in the multiple marketing tasks; determine the potential transaction factors based on the target portrait features and the target marketing tasks.

[0068] In one possible example, in terms of generating the derivative task flow based on the potential transaction factors, the second processing unit 602 is specifically used to: generate the service task flow based on the non-business needs of the second service customer; generate target marketing scripts based on the target portrait features and the target marketing task; generate the marketing task flow based on the target marketing scripts; and determine the derivative task flow based on the service task flow and the marketing task flow.

[0069] In one possible example, in terms of generating the target marketing words according to the target portrait characteristics and the target marketing task, the second processing unit 602 is specifically used to: generate a marketing guidance words according to the target portrait characteristics and the non-business needs of the second service customer, the marketing guidance words being used to indicate product functions associated with the non-business needs of the second service customer; and generate the target marketing words according to the marketing guidance words and the initial marketing words corresponding to the target marketing task.

[0070] In one possible example, the service task flow includes a target switching flag, which is used to indicate that the service task flow has been executed. In terms of executing the derived task flow, the third processing unit 603 is specifically used to: execute the service task flow; and when the target switching flag is detected, switch to execute the marketing task flow.

[0071] 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 repeated here.

[0072] In the case of an integrated unit, such as Figure 7 As shown, Figure 7 is a structural block diagram of another service robot control device provided in an embodiment of the present application. Figure 7 In the embodiment, the service robot 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 service robot control device, for example, to execute the steps of the first processing unit 601, the second processing unit 602 and the third processing unit 603, and / or to execute other processes of the technology described herein. The communication module 61 is used to support the interaction between the service robot control device and other devices. Figure 6 As shown, the service robot control device may further include a storage module 63, and the storage module 63 is used to store program codes and data of the service robot control device.

[0073] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here. The above service robot control device 60 can execute the above Figure 2 The service robot control method shown.

[0074] Based on the description of the above method embodiment and device embodiment, please refer to Figure 8 , Figure 8 A schematic diagram of the structure of a controller provided in an embodiment of the present application. Figure 8 The controller shown includes a memory 801, a processor 802, a communication interface 803 and a bus 804. The memory 801, the processor 802 and the communication interface 803 are connected to each other through the bus 804.

[0075] The memory 801 may be a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM).

[0076] The memory 801 can store programs. 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 the various steps of the service robot control method of the embodiment of the present application.

[0077] The processor 802 can adopt 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 to execute relevant programs to implement the functions that need to be performed by the units in the controller of the embodiment of the present application, or to execute the service robot control method of the method embodiment of the present application.

[0078] The processor 802 may also be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the service robot control method of the present application may be completed by an integrated logic circuit of hardware or software instructions in the processor 802. 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 gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. 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 the embodiments of the present application may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a 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. The 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 to be performed by the units included in the controller of the embodiment of the present application, or executes the service robot control method of the method embodiment of the present application.

[0079] The communication interface 803 uses a transceiver device such as, but not limited to, a transceiver to implement communication between the controller and other devices or a communication network. For example, data can be obtained through the communication interface 803 .

[0080] The bus 804 may include a path for transmitting information between various components of the controller (eg, the memory 801 , the processor 802 , and the communication interface 803 ).

[0081] It should be noted that although Figure 8 The controller shown only shows the memory 801, the processor 802, and the communication interface 803, but in the specific implementation process, the technicians in this field should understand that the controller also includes other devices necessary for normal operation. At the same time, according to specific needs, the technicians in this field should understand that the controller can also include hardware devices for implementing other additional functions. In addition, the technicians in this field should understand that the controller can also only include the devices necessary to implement the embodiments of the present application, and does not necessarily include Figure 8 All devices shown in .

[0082] An 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, part or all of the steps of any method recorded in the above method embodiment are implemented.

[0083] An embodiment of the present application also provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is executed on a computer or a processor, the computer or the processor executes one or more steps in any of the above methods.

[0084] The embodiment of the present application further provides a computer program product including instructions. When the computer program product is run on a computer or a processor, the computer or the processor executes one or more steps in the above embodiment.

[0085] Those skilled in the art will appreciate that the functions described in conjunction with the various illustrative logic blocks, modules, and algorithm steps disclosed herein can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions described in the various illustrative logic blocks, modules, and steps can be stored or transmitted as one or more instructions or codes on a computer-readable medium and executed by a hardware-based processing unit. Computer-readable media may include computer-readable storage media, which corresponds to tangible media, such as data storage media, or includes any media that facilitates the transfer of computer programs from one place to another (e.g., based on a communication protocol). In this manner, computer-readable media may generally correspond to (1) non-temporary tangible computer-readable storage media, or (2) communication media, such as signals or carrier waves. Data storage media may be any available media that can be accessed by one or more computers or one or more processors to retrieve instructions, codes, and / or data structures for implementing the techniques described in this application. A computer program product may include a computer-readable medium.

[0086] As an example and not limitation, such computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, flash memory, or any other media that can be used to store the desired program code in the form of instructions or data structures and can be accessed by a computer. Also, any connection is properly referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using a coaxial cable, optical fiber cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, then the coaxial cable, optical fiber cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of media. However, it should be understood that the computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other temporary media, but are actually directed to non-temporary tangible storage media. Disks and optical disks include compact disks, laser optical disks, optical optical disks, digital versatile disks, and Blu-ray disks, where disks typically reproduce data magnetically, while optical disks reproduce data optically using lasers. Combinations of the above items should also be included in the scope of computer-readable media.

[0087] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Thus, the term "processor" as used herein may refer to any of the aforementioned structures or any other structures suitable for implementing the techniques described herein. Additionally, in some aspects, the functions described by the various illustrative logic blocks, modules, and steps described herein may be provided within dedicated hardware and / or software modules configured for encoding and decoding, or incorporated in a combined codec. Moreover, the techniques may be fully implemented in one or more circuits or logic elements.

[0088] The techniques of the present application may be implemented in a variety of devices or apparatuses, including a wireless handset, an integrated circuit (IC), or a set of ICs (e.g., a chipset). Various components, modules, or units are described in the present application to emphasize the functional aspects of the device for performing the disclosed techniques, but they do not necessarily need to be implemented by different hardware units. In fact, as described above, the various units may be combined in an encoded hardware unit in conjunction with appropriate software and / or firmware, or provided by interoperating hardware units (including one or more processors as described above).

[0089] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the specific descriptions of the corresponding steps in the aforementioned method embodiments, and will not be repeated here.

[0090] In the description of the present application, unless otherwise specified, " / " means 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 a single item or plural items. 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, and c may be single or multiple. Additionally, for the convenience of clearly describing 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 identical or similar items with basically the same functions and roles. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and "first", "second", etc. 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. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner for easy understanding.

[0091] In several embodiments provided by the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device 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 couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0092] 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 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.

[0093] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0094] 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 can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A service robot control method, characterized in that: A controller applied to a target service robot, the method comprising: During the conversation with the first service customer, a non-business demand of the second service customer is detected, and a potential transaction factor under the current task node is determined according to the non-business demand, the first service customer and the second service customer are customers in the target customer group corresponding to the target task flow, and the target task flow refers to the task flow in which the target service robot provides services for the business demand of the target customer group; Generate a derivative task flow according to the potential transaction factors, the derivative task flow including a service task flow and a marketing task flow, the service task flow refers to a task flow in which the target service robot provides services for the non-business needs of the second service customer, and the marketing task flow refers to a task flow in which the target service robot performs marketing in combination with the potential transaction factors; The derived task flow is executed.

2. The method according to claim 1, characterized in that Before detecting the non-business demand of the second service client during the dialogue with the first service client, the method further includes: Calling the visual perception component to collect the facial image of each customer in the target customer group to obtain a target facial image set; The target face image set is stored.

3. The method according to claim 2, characterized in that The detecting of the non-business demand of the second service client during the conversation with the first service client includes: During the conversation with the first service client through the first data channel, a call request of the user to be identified is detected through the second data channel, wherein the call request is used to indicate the non-business demand; Calling the visual perception component to collect the facial image of the user to be identified; It is detected that the feature similarity between the facial image of the user to be identified and the target facial image in the target facial image set is greater than a preset similarity, and the user to be identified is determined to be a second service customer, and the target facial image refers to any other facial image in the target facial image set except the facial image corresponding to the first service customer.

4. The method according to claim 3, characterized in that The determining of potential transaction factors under the current task node according to the non-business requirements includes: Determining a potential demand profile of the second service customer according to the non-business demand; Obtain multiple marketing tasks under the current task node; Determining a target portrait feature in the potential demand portrait, wherein the target portrait feature refers to a portrait feature in the potential demand portrait that is associated with a target marketing task in the multiple marketing tasks; Determine potential transaction factors based on the target portrait characteristics and the target marketing tasks.

5. The method according to claim 4, characterized in that The generating of the derived task flow according to the potential transaction factors includes: generating the service task flow according to the non-business requirements of the second service customer; Generate target marketing words according to the target portrait features and the target marketing tasks; Generate the marketing task flow according to the target marketing words; The derived task flow is determined according to the service task flow and the marketing task flow.

6. The method according to claim 5, characterized in that Generating target marketing words according to the target portrait features and the target marketing tasks includes: generating a marketing guidance script according to the target profile feature and the non-business needs of the second service customer, wherein the marketing guidance script is used to indicate a product function associated with the non-business needs of the second service customer; The target marketing words are generated according to the marketing guidance words and the initial marketing words corresponding to the target marketing task.

7. The method according to any one of claims 1 to 6, characterized in that: The service task flow includes a target switching flag, and the target switching flag is used to indicate that the service task flow has been executed. The execution of the derived task flow includes: Executing the service task flow; When the target switching flag is detected, the marketing task flow is switched to be executed.

8. A service robot 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 non-business demand of a second service customer during a conversation with a first service customer, and determine a potential transaction factor under a current task node according to the non-business demand, wherein the first service customer and the second service customer are customers in a target customer group corresponding to a target task flow, and the target task flow refers to a task flow in which the target service robot provides services for the business demand of the target customer group; a second processing unit, configured to generate a derivative task flow according to the potential transaction factors, wherein the derivative task flow includes a service task flow and a marketing task flow, wherein the service task flow refers to a task flow in which the target service robot provides services for the non-business needs of the second service customer, and the marketing task flow refers to a task flow in which the target service robot performs marketing in combination with the potential transaction factors; The third processing unit is used to execute the derived task flow.

9. 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 7.

10. 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 7 are implemented.

Images