Guidance control method and device of humanoid robot, electronic equipment and storage medium

Abstract

The application discloses a guiding control method and device of a humanoid robot, electronic equipment and a storage medium. The method comprises the following steps: obtaining a user request; identifying the user request, and determining a target position according to the user request when the user request is determined to be a guiding request; generating a guiding path and a motion sequence corresponding to the guiding path according to the position of the humanoid robot, the target position and a map of an exhibition area where the humanoid robot is located, the motion sequence corresponding to at least one guiding action, the guiding action comprising at least one of a double-arm action, a hand action, a head action, a voice action and a face action; and generating a first action execution strategy according to the guiding path and the motion sequence corresponding to the guiding path, the first action execution strategy being used to instruct the humanoid robot to execute at least one guiding action according to the motion sequence. The application is beneficial to improving the accuracy and comprehensiveness of human-computer interaction ability in special scenarios.

Description

Technical Field

[0001] This application relates to the field of robotics technology, specifically to a guidance and control method, device, electronic equipment, and storage medium for a humanoid robot. Background Technology

[0002] Humanoid robots, also known as androids, are robots designed to mimic human appearance and behavior. With the rapid development of artificial intelligence and robotics, humanoid robots, thanks to their human-like appearance and movements, are gradually being applied in the service sector. However, current humanoid robots largely rely on pre-programmed actions to perform fixed actions or respond to standardized information. In scenarios such as shopping mall guidance, government service hall signage, and tourist information consultation, humanoid robots cannot deeply understand users' natural language commands, nor can they adjust their guidance strategies according to users' real-time needs, resulting in a poor actual service experience. Summary of the Invention

[0003] This application provides a guidance and control method, device, electronic device, and storage medium for a humanoid robot, aiming to improve the accuracy and comprehensiveness of the humanoid robot's human-computer interaction capabilities in special scenarios.

[0004] In a first aspect, embodiments of this application provide a guidance and control method for a humanoid robot, applied to a humanoid robot motion library system. The humanoid robot motion library system includes the humanoid robot and a server, and the humanoid robot is connected to the server. The method includes:

[0005] Get user request;

[0006] Identify the user request, and when it is determined that the user request is a guidance request, determine the target location based on the user request;

[0007] Based on the position of the humanoid robot, the target position, and a preset environmental map of the exhibition area where the humanoid robot is located, a guidance path and a corresponding action sequence are generated. The action sequence corresponds to at least one guidance action, which includes at least one of arm movements, hand movements, head movements, voice movements, and facial movements.

[0008] A first action execution strategy is generated based on the guidance path and the action sequence corresponding to the guidance path. The first action execution strategy is used to instruct the humanoid robot to perform at least one guidance action according to the action sequence.

[0009] In one possible example of the first aspect, generating a guidance path and a corresponding action sequence based on the humanoid robot's position, the target position, and a preset environmental map of the exhibition area where the humanoid robot is located includes:

[0010] At least one guidance path is generated based on the location of the humanoid robot, the target location, and a preset environmental map of the exhibition area where the humanoid robot is located;

[0011] Each of the aforementioned guidance paths is divided into at least one sub-path, wherein two adjacent sub-paths within the same guidance path have different path directions;

[0012] Determine the execution order of each sub-path in the same guiding path and the relative positional relationship between the starting point orientation and the path direction of each sub-path;

[0013] The action sequence is determined based on the execution order and relative positional relationship of each of the sub-paths in each of the guidance paths.

[0014] In one possible example of the first aspect, when the guidance path comprises multiple paths, determining the action sequence based on the execution order and relative positional relationship of each sub-path in each guidance path includes:

[0015] The action subsequence corresponding to each guidance path is determined based on the execution order and relative positional relationship of each sub-path in each guidance path;

[0016] Determine the path sequence corresponding to multiple guidance paths based on preset conditions;

[0017] The action sequence is obtained by arranging multiple action sub-sequences according to the path sequence.

[0018] In one possible example of the first aspect, determining the action sub-sequence corresponding to each of the guidance paths based on the execution order and relative positional relationship of each of the sub-paths in each guidance path includes:

[0019] Obtain a preset guidance action mapping table, which is used to represent the correspondence between multiple relative positional relationships and multiple guidance actions, with one relative positional relationship corresponding to one guidance action;

[0020] The guidance action corresponding to each sub-path in each guidance path is determined according to the guidance action mapping table;

[0021] The action subsequence corresponding to each guidance path is determined based on the execution order of each sub-path in each guidance path and the corresponding guidance action.

[0022] In one possible example of the first aspect, determining the action sub-sequence corresponding to each of the guidance paths based on the execution order and relative positional relationship of each of the sub-paths in each guidance path includes:

[0023] Obtain a preset orientation action mapping table, which is used to represent the correspondence between multiple relative positional relationships and multiple orientation actions, with one relative positional relationship corresponding to one orientation action;

[0024] The orientation action corresponding to each sub-path in each guidance path is determined according to the orientation action mapping table;

[0025] Obtain the path information of each sub-path in each of the guidance paths and a preset explanation action mapping table. The explanation action mapping table is used to represent the correspondence between multiple path information and multiple explanation actions. One path information corresponds to at least one explanation action.

[0026] The narration action corresponding to each sub-path in each guidance path is determined according to the narration action mapping table;

[0027] Generate guidance actions corresponding to each sub-path based on the orientation action and explanation action corresponding to each sub-path;

[0028] The action subsequence corresponding to each guidance path is determined based on the execution order of each sub-path in each guidance path and the corresponding guidance action.

[0029] In one possible example of the first aspect, identifying the user request includes:

[0030] The user request is input into the pre-trained request recognition model;

[0031] The request identification model determines the weight values ​​of the user request and multiple preset function tags, and determines the request type based on the weight values ​​of the multiple preset power supply tags. The request type includes the guidance request and the general request.

[0032] In one possible example of the first aspect, when the user request is a general request, the method further includes:

[0033] Determine the request keywords based on the user request;

[0034] Obtain a general action mapping table, which is used to represent the correspondence between multiple request keywords and multiple general actions. One request keyword corresponds to at least one general action. The general actions include at least one of the following: arm movements, hand movements, head movements, voice movements, and facial movements.

[0035] The general action corresponding to the user request is determined based on the general action mapping table.

[0036] A second action execution strategy is generated based on the general action, and the second action execution strategy is used to instruct the humanoid robot to perform the general action.

[0037] Secondly, embodiments of this application provide a guidance and control device for a humanoid robot, applied to a humanoid robot motion library system. The humanoid robot motion library system includes the humanoid robot and a server, the humanoid robot being connected to the server. The device includes:

[0038] The acquisition unit is used to acquire user requests;

[0039] The identification unit is used to identify the user request and, when determining that the user request is a guidance request, to determine the target location based on the user request.

[0040] The first generation unit is used to generate a guidance path and a corresponding action sequence based on the location of the humanoid robot, the target location, and a map of the exhibition area where the humanoid robot is located. The action sequence corresponds to at least one guidance action, which includes at least one of arm movements, hand movements, head movements, voice movements, and facial movements.

[0041] The second generation unit is configured to generate a first action execution strategy based on the guidance path and the action sequence corresponding to the guidance path. The first action execution strategy is used to instruct the humanoid robot to perform at least one guidance action according to the action sequence.

[0042] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, a communication interface, and one or more programs, the one or more programs being stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the first aspect of embodiments of this application.

[0043] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the first aspect of this embodiment.

[0044] As can be seen, in this application, the humanoid robot obtains a user request; identifies the user request, and when the user request is determined to be a guidance request, determines the target location based on the user request; generates a guidance path and a corresponding action sequence based on the humanoid robot's position, the target location, and a preset environmental map of the exhibition area where the humanoid robot is located. The action sequence corresponds to at least one guidance action, which includes at least one of arm movements, hand movements, head movements, voice movements, and facial movements; and generates a first action execution strategy based on the guidance path and the corresponding action sequence. The first action execution strategy is used to instruct the humanoid robot to execute at least one guidance action according to the action sequence. Therefore, in this application, the humanoid robot can intelligently recognize and understand the natural language statements input by the user. Thus, when the parsing of the statement determines that the user has a guidance need, it determines the target location based on the user request and generates a guidance path and a corresponding action sequence from the humanoid robot's current position to the target location. The humanoid robot can execute the guidance actions in this action sequence to guide the user, achieving dynamic interaction with the user, meeting the user's real-time needs, improving the accuracy of user need recognition and response, and enhancing the user experience. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of the architecture of a humanoid robot motion library system provided in an embodiment of this application;

[0047] Figure 2 This is a schematic diagram of the architecture of another humanoid robot motion library system provided in an embodiment of this application;

[0048] Figure 3 This is a flowchart illustrating a guidance and control method for a humanoid robot provided in an embodiment of this application;

[0049] Figure 4 This is a schematic diagram illustrating an application scenario of a guidance and control method for a humanoid robot provided in an embodiment of this application;

[0050] Figure 5 This is a schematic diagram illustrating an application scenario of another guidance and control method for a humanoid robot provided in this application embodiment;

[0051] Figure 6 This is a schematic diagram of a guiding path provided in an embodiment of this application;

[0052] Figure 7 This is a structural block diagram of an electronic device provided in an embodiment of this application;

[0053] Figure 8 This is a functional unit block diagram of a guidance and control device for a humanoid robot provided in an embodiment of this application;

[0054] Figure 9 This is a block diagram of the functional units of another humanoid robot guidance and control device provided in the embodiments of this application. Detailed Implementation

[0055] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0056] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0057] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0058] The embodiments of this application will now be described with reference to the accompanying drawings.

[0059] The technical solution of this application can be applied to, for example... Figure 1 The humanoid robot motion library system 10 shown includes a server 110 and a humanoid robot 120. The server 110 is communicatively connected to the humanoid robot 120.

[0060] In this context, server 110 refers to a remote computer used to process large amounts of computing tasks and store data. Server 110 can be a physical server, a server cluster consisting of multiple physical servers, or a distributed system. In this embodiment, the number of servers is not specifically limited. Alternatively, server 110 can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. No further restrictions are imposed here. Alternatively, in a specific implementation, server 110 in the aforementioned humanoid robot motion library system 10 can also be a server cluster. In one possible example, server 110 can be configured on different servers within a server cluster, thereby reducing the configuration requirements when a single server is processing data.

[0061] The humanoid robot 120 includes a sound receiving module and an output module. The sound receiving module is used to collect the user's natural language statements (such as user requests as described below). When the humanoid robot collects the user's natural language statements through the sound receiving module, it can parse the statements for language understanding and recognition. The output module is used to output the corresponding action according to the first action execution strategy.

[0062] See Figure 2 The humanoid robot motion library system 10 may also include a user device 130, which can be a handheld device. Users can activate the system and select different modes for human-computer interaction via the handheld device. When the intelligent agent mode is selected via the handheld device, the humanoid robot can switch to an intelligent dialogue mode. Intelligent dialogue and / or actions using a large language model can wake up the humanoid robot, enabling human-computer interaction. For example, the user device 130 can be a smartphone (such as an Android phone, iOS phone, Windows Phone, etc.), a smart computer (such as a tablet computer, PDA, etc.), or a wearable device (such as a smartwatch, Bluetooth headset), etc. These are just examples, not an exhaustive list, and include, but are not limited to, the devices mentioned above.

[0063] Please see Figure 3 , Figure 3 This is a flowchart illustrating a guidance and control method for a humanoid robot provided in an embodiment of this application. This method can be applied to, for example... Figure 1 or Figure 2 The humanoid robot in the humanoid robot motion library system shown is a humanoid robot, such as Figure 3 As shown, the guidance and control method for this humanoid robot includes:

[0064] Step S310: Obtain the user request.

[0065] Among them, user requests are natural language statements input during user interactions collected by the humanoid robot. For example, a user request could be "I want to go to booth A, how do I get there?" Alternatively, user requests can be content parsed from the user's natural language statements using a large language model. For example, a user request could be "How do I get to booth A?"

[0066] Step S320: Identify the user request, and when the user request is determined to be a guidance request, determine the target location based on the user request.

[0067] User requests include general requests and guidance requests. General requests refer to requests for basic services, such as "What time does the exhibition open today?" Guidance requests refer to requests that require guidance on a specific path, such as "How do I get to booth A?"

[0068] The target location in the user request may include one or more locations.

[0069] Specifically, the humanoid robot can parse and identify user requests to determine the user's intent. Based on the user's intent, it can determine whether the request is a general request or a guidance request. If the request is determined to be a guidance request, the robot can determine the location of the corresponding target booth. For example, if the user request is "How do I get to booth A and booth B?", the humanoid robot can parse the request and determine that it is a guidance request, and the target locations include booths A and B.

[0070] Step S330: Generate a guidance path and a sequence of actions corresponding to the guidance path based on the position of the humanoid robot, the target position, and a preset environmental map of the exhibition area where the humanoid robot is located.

[0071] The action sequence corresponds to at least one guiding action, which includes at least one of the following: arm movements, hand movements, head movements, voice movements, and facial movements. Arm and hand movements coordinate pointing in the guiding direction, head movements synchronously face the guiding direction, voice movements output the guiding direction verbally, and facial movements display corresponding expressions for each guiding direction. This multi-dimensional approach, combining sound, form, and appearance, makes the guidance more vivid and engaging. For example, the guiding action also includes a path output action, which instructs the humanoid robot to display the guiding path on a preset environmental map via a dedicated display panel, thereby providing more accurate directional guidance to the user.

[0072] The humanoid robot's position represents its location in the real-time context when viewed from the user's perspective. For example, if the user's request is "How do I get to booth A?", then in the current real-time context, the humanoid robot's position is its actual location. If the user's request is for further interaction based on the above example, such as "How do I get to booth B later?", then in that real-time context, the humanoid robot's position is the location of booth A.

[0073] The target location can be a booth location or a restroom location, etc.

[0074] The generated guidance path may include the shortest path. Alternatively, the generated path may include multiple recommended paths, among which the shortest path is included.

[0075] For example, see Figure 4 The preset environment map can include entrances and exits (e.g., exit 1 and exit 2), restrooms, information desks, the actual locations of humanoid robots, and multiple booths (e.g., booth A, booth B, ..., booth T) within the exhibition area. Alternatively, see the example below. Figure 5 When the exhibition area includes multiple floors, the preset environment map includes not only the horizontal floor plan information of each floor, but also the vertical structural information of the multi-level exhibition area. For example, the preset environment map also includes the connection locations of stairwells between different floors (such as 1F and 2F).

[0076] In practice, if there are temporary additions to booths or temporary closures of passageways during the exhibition, exhibition staff can dynamically update the preset environmental map of the exhibition area through management equipment. This can prevent users from getting lost, being blocked, or wandering around when following the guidance path, which helps to improve the accuracy and adaptability of the generated guidance path and its corresponding action sequence, and improve the reliability of the humanoid robot guidance service.

[0077] Step S340: Generate a first action execution strategy based on the guidance path and the action sequence corresponding to the guidance path.

[0078] The first action execution strategy is used to instruct the humanoid robot to perform at least one guiding action according to the action sequence.

[0079] Specifically, the humanoid robot can output a guidance path to the user by performing at least one guiding action corresponding to the first action execution strategy, thereby realizing interaction with the user.

[0080] As can be seen, in this application, the humanoid robot obtains a user request; identifies the user request, and when the user request is determined to be a guidance request, determines the target location based on the user request; generates a guidance path and a corresponding action sequence based on the humanoid robot's position, the target location, and a preset environmental map of the exhibition area where the humanoid robot is located. The action sequence corresponds to at least one guidance action, which includes at least one of arm movements, hand movements, head movements, voice movements, and facial movements; and generates a first action execution strategy based on the guidance path and the corresponding action sequence. The first action execution strategy is used to instruct the humanoid robot to execute at least one guidance action according to the action sequence. Therefore, in this application, the humanoid robot can intelligently recognize and understand the natural language statements input by the user. Thus, when the parsing of the statement determines that the user has a guidance need, it determines the target location based on the user request and generates a guidance path and a corresponding action sequence from the humanoid robot's current position to the target location. The humanoid robot can execute the guidance actions in this action sequence to guide the user, achieving dynamic interaction with the user, meeting the user's real-time needs, improving the accuracy of user need recognition and response, and enhancing the user experience.

[0081] In one possible example, generating a guidance path and a corresponding action sequence based on the humanoid robot's position, the target position, and a preset environmental map of the exhibition area where the humanoid robot is located includes: obtaining a sequence mapping table, which represents the correspondence between the target position, the guidance path, and the action sequence of the guidance path, wherein a single target position corresponds to at least one guidance path and the action sequence of the guidance path; determining at least one guidance path and the action sequence of the guidance path corresponding to the target position based on the sequence mapping table; and generating an action sequence based on the action sequence of the at least one guidance path.

[0082] Specifically, the sequence mapping table stores at least one guide path from each marked location in the preset environment map to other marked locations and its corresponding action sequence.

[0083] In practical implementation, when generating guidance paths and their action sequences, the humanoid robot can first obtain a sequence mapping table corresponding to the robot's position. Then, based on the target position, it can query the table for at least one guidance path corresponding to the target position and the corresponding action sub-sequences for each guidance path. If there is only one guidance path, the action sub-sequence can be determined as the action sequence. If there are multiple guidance paths, the action sub-sequences corresponding to the multiple guidance paths can be arranged according to preset conditions to obtain the action sequence. These preset conditions include, but are not limited to, sorting by path distance from shortest to longest, and sorting by the number of turns from fewest to most. An action sub-sequence refers to an ordered set of multiple guidance actions corresponding to a single guidance path.

[0084] Alternatively, to alleviate the storage pressure on humanoid robots, the humanoid robot can generate guidance paths and corresponding action sequences in real time based on user interactions. In one possible example, generating guidance paths and corresponding action sequences based on the humanoid robot's location, the target location, and a preset environmental map of the exhibition area where the humanoid robot is located includes: generating at least one guidance path based on the humanoid robot's location, the target location, and the preset environmental map of the exhibition area where the humanoid robot is located; dividing each guidance path into at least one sub-path, with adjacent sub-paths within the same guidance path having different path directions; determining the execution order of each sub-path within the same guidance path and the relative positional relationship between the starting point orientation and path direction of each sub-path; and determining the action sequence based on the execution order and relative positional relationship of each sub-path within each guidance path.

[0085] The execution order refers to the sequential arrangement of sub-paths within the guiding path. Relative positional relationships refer to the spatial attributes of different sub-paths, such as orientation, distance, etc., including but not limited to front / back, left / right, up / down, angle, and spacing.

[0086] The starting point orientation refers to the path direction of the preceding sub-path adjacent to the current sub-path within the same guiding path. Relative positional relationships are used to characterize the relative positions between the path directions of two adjacent sub-paths within the same guiding path.

[0087] In practical implementation, the humanoid robot can perform global path planning based on its own position, the target position, and a preset environment map, thereby obtaining at least one guiding path. Then, for each guiding path, the following method can be executed: the guiding path is set with turning points as nodes (e.g., ...). Figure 6The guide path is divided into at least one sub-path (marked by a solid circle). For example, if the guide path does not involve turning, there is one sub-path; if the guide path involves turning, there are multiple sub-paths. When there are multiple sub-paths, the humanoid robot can determine the execution order of each sub-path by the order in which it moves within the guide path. Based on this execution order, it can determine adjacent sub-paths within the guide path, thereby determining the relative positional relationship of the path directions (i.e., the direction of travel) of two adjacent sub-paths. Furthermore, based on this relative positional relationship, it can determine the change information (such as left turn, right turn, or going upstairs) required to transition from one sub-path to the next. The humanoid robot can then determine the guiding action corresponding to each sub-path based on the change information and arrange these guiding actions according to the execution order to obtain the action sub-sequence corresponding to that guide path.

[0088] When there is only one planned guidance path, the sub-sequence of actions can be directly determined as the action sequence. Alternatively, when there are multiple planned guidance paths, one of them can be determined as the output content of the humanoid robot according to preset rules. For example, the guidance path with the shortest path among multiple guidance paths can be determined as the output content of the humanoid robot. In this case, the sub-sequence of actions corresponding to the shortest guidance path can be determined as the action sequence.

[0089] Alternatively, in one possible example, when the guidance path includes multiple paths, determining the action sequence based on the execution order and relative positional relationship of each sub-path in each guidance path includes: determining the action sub-sequence corresponding to each guidance path based on the execution order and relative positional relationship of each sub-path in each guidance path; determining the path sequence corresponding to multiple guidance paths based on preset conditions; and arranging the multiple action sub-sequences according to the path sequence to obtain the action sequence.

[0090] The preset conditions are used to constrain the arrangement rules of multiple action sub-sequences. Specifically, the preset conditions can be single conditions. For example, the preset conditions can be sorting by path distance from shortest to longest or by the number of turns from fewest to most. Alternatively, the preset conditions can be combined conditions. For example, when there are at least two guide paths with equal distances, these at least two guide paths can be sorted by the number of turns from fewest to most. In practical applications, the preset conditions can also include constraint conditions (such as guide paths that avoid specific areas being preferentially selected), etc., without further restrictions here.

[0091] Specifically, if there are multiple paths (such as...) Figure 6When the target location is booth N, and multiple guidance paths (including guidance paths corresponding to solid and dashed arrows) are provided, a path sequence of multiple guidance paths can be determined based on preset conditions. Then, the action sub-sequences corresponding to each guidance path are arranged according to the path sequence to obtain an action sequence. At this point, the humanoid robot will output all guidance paths for the user to choose from, ensuring comprehensive output content and allowing the user to select according to their needs, thereby improving the accuracy and adaptability of the guidance.

[0092] Specifically, in the process of arranging the action sub-sequences corresponding to each guide path according to the path sequence to obtain the action sequence, if there is an action conflict or a transition is needed between adjacent action sub-sequences (such as the end action of the previous action sub-sequence not being continuous with the start action of the next action sub-sequence), a transition action can be added between the two action sub-sequences. Among them, the transition action is a preset action, for example, the preset action can be a reset action for resetting limbs and facial expressions.

[0093] As can be seen in this example, the above steps can transform the abstract guidance path into a specific, executable sequence of actions. The entire process is flexible and adaptable, ensuring that the humanoid robot can efficiently and accurately complete user requests and improve the user experience.

[0094] As can be seen in this example, by generating a guidance path and then splitting the guidance path into at least one sub-path, the action sequence can be determined according to the execution order and relative position of each sub-path. This enables the dynamic generation of guidance strategies based on the user's real-time interaction content and the latest preset environment map, which helps to improve the accuracy of guidance and optimize the user experience.

[0095] In one possible example, determining the action subsequence corresponding to each guidance path based on the execution order and relative positional relationship of each sub-path in each guidance path includes: obtaining a preset guidance action mapping table, which is used to represent the correspondence between multiple relative positional relationships and multiple guidance actions, wherein one relative positional relationship corresponds to one guidance action; determining the guidance action corresponding to each sub-path in each guidance path based on the guidance action mapping table; and determining the action subsequence corresponding to each guidance path based on the execution order and corresponding guidance action of each sub-path in each guidance path.

[0096] The guidance action mapping table stores the guidance actions corresponding to each relative position relationship.

[0097] Specifically, when determining the action subsequence corresponding to a guidance path, the humanoid robot can first obtain a guidance action mapping table, and then query the table for the guidance action corresponding to the relative positional relationship of each sub-path in the guidance path, thereby obtaining the guidance action corresponding to each sub-path in a single guidance path. Then, according to the execution order of each guidance path, the guidance actions corresponding to each sub-path of the guidance path are sorted to obtain the action subsequence corresponding to the guidance path.

[0098] As can be seen in this example, by querying the guidance action mapping table, the guidance actions corresponding to each sub-path in the guidance path are determined. Then, the guidance actions are sorted according to the execution order of each sub-path in the guidance path to obtain the action sub-sequence. This ensures that each guidance path can be transformed into a unique and coherent action sub-sequence, which can improve the convenience and efficiency of action sub-sequence generation while ensuring the accuracy of the generated action sub-sequence.

[0099] Alternatively, in one possible example, determining the action sub-sequence corresponding to each guidance path based on the execution order and relative positional relationship of each sub-path in each guidance path includes: obtaining a preset directional action mapping table, which represents the correspondence between multiple relative positional relationships and multiple directional actions, with one relative positional relationship corresponding to one directional action; determining the directional action corresponding to each sub-path in each guidance path based on the directional action mapping table; obtaining path information of each sub-path in each guidance path and a preset explanation action mapping table, which represents the correspondence between multiple path information and multiple explanation actions, with one path information corresponding to at least one explanation action; determining the explanation action corresponding to each sub-path in each guidance path based on the explanation action mapping table; generating a guidance action corresponding to each sub-path based on the directional action and explanation action corresponding to each sub-path; and determining the action sub-sequence corresponding to each guidance path based on the execution order and corresponding guidance action of each sub-path in each guidance path.

[0100] The directional gestures are used to guide the user's direction of travel. The narration gestures are engaging interactive actions, which include at least voice gestures, and may also include at least one of arm gestures, hand gestures, head gestures, and facial gestures. For example, the content of the narration gestures can be used to perform interactive content such as historical narration, product introductions, or fun Q&A sessions.

[0101] The path information refers to the information of markers on the sub-path, which can be booths or other locations within the map. These markers can be pre-defined.

[0102] In specific implementation, when determining the action sub-sequence corresponding to the guidance path, the humanoid robot can first obtain the orientation action mapping table, and then query the corresponding orientation action based on the relative positional relationship of the sub-path. Simultaneously, the humanoid robot can also obtain the narration action mapping table. Specifically, the humanoid robot can first determine whether path information exists for the sub-path; if it does, it queries the narration action mapping table based on the path information to determine the narration action corresponding to that sub-path. After determining the orientation action and the narration action, the narration action can be arranged after the orientation action to merge and obtain the guidance action corresponding to that sub-path. Furthermore, the guidance actions corresponding to multiple sub-paths can be sorted according to the execution order of each sub-path in the guidance path to obtain the action sub-sequence corresponding to that guidance path. For example, see... Figure 6 When the sub-path corresponding to the dashed arrow turns left and proceeds to reach booth N, its directional action is the directional action corresponding to the left turn, and the explanatory action can be the content introduction of the booth L along the way. In this example, after outputting the directional action content of the directional action, the humanoid robot can also output the content corresponding to the explanatory action, so as to introduce the locations passed along the way to the user while pointing them out.

[0103] As can be seen in this example, generating guidance actions based on directional and explanatory actions, and determining the corresponding action sub-sequences for the guidance path based on the generated guidance actions, enables the final generated action sub-sequences to achieve coordination between physical movement and information explanation, improving the accuracy and interactivity of task execution. This is beneficial for enhancing the multidimensionality and richness of the humanoid robot's output content and improving the user's immersive experience.

[0104] In one possible example, identifying the user request includes: inputting the user request into a pre-trained request identification model; determining the weight values ​​corresponding to the user request and multiple preset function tags through the request identification model; and determining the request type based on the weight values ​​corresponding to the multiple preset power supply tags, wherein the request type includes the guidance request and the general request.

[0105] Among them, the request recognition model is a large language model, which is used to identify user intent.

[0106] The preset function tags include emotional color tags, actual function tags, general tags, and skill-showing tags. Specifically, the number and content of the preset function tags can be set according to actual needs, and no further restrictions are imposed here.

[0107] In practice, before acquiring user requests, a set of request samples can be obtained, and each request sample in the set can be labeled with its corresponding request type (guided request or general request) and a preset functional label related to that request. Then, a deep learning model (such as the BERT model) can be used as the initial model, and the labeled samples can be input into the initial model for training. The model parameters are adjusted through the backpropagation algorithm until the prediction results of the initial model reach the preset accuracy requirements, thereby obtaining a pre-trained request recognition model.

[0108] In practice, the humanoid robot can input user requests into a request recognition model, which performs semantic analysis and feature extraction to calculate the probability of weight values ​​corresponding to each functional tag. The robot then calculates the sum of the probability weight values ​​for functional tags corresponding to different request types, compares the sums of probability weight values ​​for guidance requests and general requests, and determines the request type with the larger sum of probability weight values—that is, the user's request type. For example, if guidance requests are associated with emotional color tags, actual function tags, and skill-related tags, and general requests are associated with emotional color tags, general tags, and skill-related tags, and the probability weight values ​​for the user request corresponding to these tags are 0.2, 0.4, 0.1, and 0.1 respectively, then the sum of probability weight values ​​for guidance requests is 0.7, and the sum of probability weight values ​​for general requests is 0.4, indicating that the user request is a guidance request.

[0109] Alternatively, in a specific implementation, when determining the request type corresponding to a user request, if the sum of the weight probabilities of the guiding requests is greater than that of the general requests, the sum of the weight probabilities of the guiding requests can be further compared with a preset threshold. If it is greater than or equal to the preset threshold, the user request is determined to be a guiding request; if it is less than the preset threshold, the user request is determined to be a general request. This helps improve the accuracy of guiding request identification. The preset threshold can be set according to requirements and is not further restricted here.

[0110] If the sum of the weight values ​​of the preset function tags related to the guidance request is greater than the sum of the weight values ​​of the preset function tags related to the general request, and exceeds a preset threshold, then the user request is determined to be a guidance request; otherwise, it is determined to be a general request.

[0111] As can be seen, in this example, determining the weight values ​​corresponding to multiple preset function tags by the request recognition model, and determining the type of user request based on these weight values, helps improve the accuracy and reliability of user request recognition. This, in turn, helps improve the accuracy of human-computer interaction between the humanoid robot and the user, and optimizes the user experience.

[0112] In one possible example, when the user request is a general request, the method further includes: determining request keywords based on the user request; obtaining a general action mapping table, the general action mapping table being used to characterize the correspondence between multiple request keywords and multiple general actions, wherein one request keyword corresponds to at least one general action, the general action including at least one of arm movements, hand movements, head movements, voice movements, and facial movements; determining the general action corresponding to the user request based on the general action mapping table; and generating a second action execution strategy based on the general action, the second action execution strategy being used to instruct the humanoid robot to perform the general action.

[0113] Among them, general actions refer to the actions output by humanoid robots that revolve around information acquisition, basic services, or simple assistance.

[0114] Specifically, when a user request is determined to be a general request, the humanoid robot can parse the request to obtain at least one keyword corresponding to it. It then retrieves an action mapping table and queries this table for each keyword to determine at least one general action corresponding to the general request. Based on this general action, a second action execution strategy is generated, causing the humanoid robot to execute the general action and interact with the user. When there are multiple keywords, and each keyword corresponds to a general action, the humanoid robot's second action execution strategy includes all general actions.

[0115] Specifically, one keyword can correspond to at least one general action. When there are multiple keywords, the general actions corresponding to each keyword can be sorted according to a preset sorting rule. This preset sorting rule can be based on the order in which each keyword appears in the user request, ranking the general actions corresponding to each keyword accordingly. Alternatively, different general actions can be prioritized, in which case the preset sorting rule can be based on priority, ranking the general actions corresponding to each keyword accordingly. The preset sorting order can be set according to requirements.

[0116] As can be seen in this example, by generating a second action execution strategy when the user request is a general request, instructing the humanoid robot to output a general action, the user's needs based on the general request can be met, and the functionality and flexibility of the humanoid robot's response can be improved.

[0117] The structural block diagram of the electronic device 70 in this application can be as follows: Figure 7As shown, the electronic device 70 is a server, handheld device, or humanoid robot in a humanoid robot motion library system, which can be used to execute the above-described methods. Specifically, the electronic device 70 may include a processor 710, a memory 720, a communication interface 730, and one or more programs 721, wherein the one or more programs 721 are stored in the memory 720 and configured to be executed by the processor 710, and the one or more programs 721 include instructions for performing any step in the above-described method embodiments.

[0118] The communication interface 730 is used to support communication between the electronic device 70 and other devices. The processor 710 may be, for example, a central processing unit (CPU), 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, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, units, and circuits described in conjunction with the embodiments of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0119] The memory 720 can be volatile memory or non-volatile memory, or may include both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SynchLinkDRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0120] In a specific implementation, the processor 710 is used to execute any step in the above method embodiments, and when performing data transmission such as sending, it can selectively call the communication interface 730 to complete the corresponding operation.

[0121] It should be noted that the above schematic diagram of the electronic device 70 is only an example, and the actual number of components included may be more or less, and no single limitation is made here.

[0122] This application can divide electronic devices into functional units based on the above method examples. For example, each function can be divided into its own functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0123] Figure 8 This is a functional unit block diagram of a guidance and control device for a humanoid robot provided in an embodiment of this application. The guidance and control device for the humanoid robot includes:

[0124] Acquisition unit 810 is used to acquire user requests;

[0125] The identification unit 820 is used to identify the user request and, when determining that the user request is a guidance request, to determine the target location based on the user request.

[0126] The first generation unit 830 is used to generate a guidance path and a corresponding action sequence based on the location of the humanoid robot, the target location and the map of the exhibition area where the humanoid robot is located. The action sequence corresponds to at least one guidance action, and the guidance action includes at least one of arm movements, hand movements, head movements, voice movements and facial movements.

[0127] The second generation unit 840 is configured to generate a first action execution strategy based on the guidance path and the action sequence corresponding to the guidance path. The first action execution strategy is used to instruct the humanoid robot to perform at least one guidance action according to the action sequence.

[0128] In one possible example, regarding the generation of a guidance path and a corresponding action sequence based on a preset environmental map of the humanoid robot's position, the target position, and the exhibition area where the humanoid robot is located, the first generation unit is specifically configured to: generate at least one guidance path based on the humanoid robot's position, the target position, and the preset environmental map of the exhibition area where the humanoid robot is located; divide each guidance path into at least one sub-path, wherein two adjacent sub-paths within the same guidance path have different path directions; determine the execution order of each sub-path within the same guidance path and the relative positional relationship between the starting point orientation and the path direction of each sub-path; and determine the action sequence based on the execution order and the relative positional relationship of each sub-path within each guidance path.

[0129] In one possible example, when the guidance path includes multiple paths, the first generation unit is further configured to: determine the action sub-sequence corresponding to each guidance path based on the execution order and relative positional relationship of each sub-path in each guidance path; determine the path sequence corresponding to multiple guidance paths based on preset conditions; and arrange the multiple action sub-sequences according to the path sequence to obtain the action sequence.

[0130] In one possible example, in determining the action subsequence corresponding to each guidance path based on the execution order and relative positional relationship of each sub-path in each guidance path, the first generation unit is further configured to: obtain a preset guidance action mapping table, the guidance action mapping table being used to characterize the correspondence between multiple relative positional relationships and multiple guidance actions, one relative positional relationship corresponding to one guidance action; determine the guidance action corresponding to each sub-path in each guidance path based on the guidance action mapping table; and determine the action subsequence corresponding to each guidance path based on the execution order and corresponding guidance action of each sub-path in each guidance path.

[0131] In one possible example, regarding the determination of the action sub-sequence corresponding to each guidance path based on the execution order and relative positional relationship of each sub-path in each guidance path, the first generation unit is further configured to: obtain a preset directional action mapping table, the directional action mapping table being used to characterize the correspondence between multiple relative positional relationships and multiple directional actions, where one relative positional relationship corresponds to one directional action; determine the directional action corresponding to each sub-path in each guidance path based on the directional action mapping table; obtain path information of each sub-path in each guidance path and a preset explanation action mapping table, the explanation action mapping table being used to characterize the correspondence between multiple path information and multiple explanation actions, where one path information corresponds to at least one explanation action; determine the explanation action corresponding to each sub-path in each guidance path based on the explanation action mapping table; generate a guidance action corresponding to each sub-path based on the directional action and explanation action corresponding to each sub-path; and determine the action sub-sequence corresponding to each guidance path based on the execution order and corresponding guidance action of each sub-path in each guidance path.

[0132] In one possible example, in terms of identifying the user request, the acquisition unit is specifically configured to: input the user request into a pre-trained request recognition model; determine the weight values ​​corresponding to the user request and multiple preset function tags through the request recognition model, and determine the request type based on the weight values ​​corresponding to the multiple preset power supply tags, wherein the request type includes the guidance request and the general request.

[0133] In one possible example, the guidance and control device of the humanoid robot further includes a general response unit, which is used to determine request keywords based on the user request when the user request is a general request; obtain a general action mapping table, which is used to represent the correspondence between multiple request keywords and multiple general actions, wherein one request keyword corresponds to at least one general action, and the general action includes at least one of arm movements, hand movements, head movements, voice movements, and facial movements; determine the general action corresponding to the user request based on the general action mapping table; and generate a second action execution strategy based on the general action, which is used to instruct the humanoid robot to perform the general action.

[0134] In the case of using integrated units, the functional unit composition block diagram of another humanoid robot guidance and control device provided in this application embodiment is as follows: Figure 9 As shown. In Figure 9 The humanoid robot's guidance and control device includes a processing module 920 and a communication module 910. The processing module 920 controls and manages the actions of the humanoid robot's guidance and control device, for example, the steps executed by the acquisition unit 810, the recognition unit 820, the first generation unit 830, and the second generation unit 840, and / or other processes for executing the techniques described herein. The communication module 910 supports interaction between the humanoid robot's guidance and control device and other devices. Figure 9 As shown, the guidance and control device of the humanoid robot may also include a storage module 930, which is used to store the program code and data of the guidance and control device of the humanoid robot.

[0135] The processing module 920 can be a processor or controller, such as a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication module 910 can be a transceiver, RF circuitry, or a communication interface, etc. The storage module 930 can be a memory.

[0136] All relevant content in each scenario involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here. The guidance and control devices of the humanoid robots described above can all perform the above-mentioned functions. Figure 3 The steps performed by the user equipment in the guidance and control method of the humanoid robot shown.

[0137] This application also provides a computer-readable storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes a server.

[0138] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0139] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0141] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0142] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0143] If the integrated units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0144] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include flash drives, ROM, RAM, magnetic disks, or optical disks, etc.

[0145] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A guidance and control method for a humanoid robot, characterized in that, A humanoid robot is used in a humanoid robot motion library system, the humanoid robot motion library system includes the humanoid robot and a server, the humanoid robot is connected to the server, and the method includes: Get user request; Identify the user request, and when it is determined that the user request is a guidance request, determine the target location based on the user request; Based on the position of the humanoid robot, the target position, and a preset environmental map of the exhibition area where the humanoid robot is located, a guidance path and a corresponding action sequence are generated. The action sequence corresponds to at least one guidance action, which includes at least one of arm movements, hand movements, head movements, voice movements, and facial movements, as well as a path output action. The preset environmental map is dynamically updated based on information from the management device. The path output action is used to instruct the humanoid robot to display the route of the guidance path in the preset environmental map through a matching display panel. A first action execution strategy is generated based on the guidance path and the action sequence corresponding to the guidance path. The first action execution strategy is used to instruct the humanoid robot to perform at least one guidance action according to the action sequence. The step of generating a guidance path and a corresponding action sequence based on the humanoid robot's position, the target position, and a preset environmental map of the exhibition area where the humanoid robot is located includes: generating at least one guidance path based on the humanoid robot's position, the target position, and the preset environmental map of the exhibition area where the humanoid robot is located; dividing each guidance path into at least one sub-path, with adjacent sub-paths within the same guidance path having different path directions; determining the execution order of each sub-path within the same guidance path and the relative positional relationship between the starting point orientation and the path direction of each sub-path; determining the action sequence based on the execution order and relative positional relationship of each sub-path within each guidance path; when there are multiple guidance paths, determining the action sequence based on the execution order and relative positional relationship of each sub-path within each guidance path includes: determining the action sub-sequence corresponding to each guidance path based on the execution order and relative positional relationship of each sub-path within each guidance path; determining the path sequence corresponding to multiple guidance paths based on preset conditions; and determining the action sequence based on the path sequence. Multiple action sub-sequences are arranged to obtain the action sequence; determining the action sub-sequence corresponding to each guidance path based on the execution order and relative positional relationship of each sub-path in each guidance path includes: obtaining a preset directional action mapping table, which represents the correspondence between multiple relative positional relationships and multiple directional actions, with one relative positional relationship corresponding to one directional action; determining the directional action corresponding to each sub-path in each guidance path based on the directional action mapping table; obtaining path information of each sub-path in each guidance path and a preset explanation action mapping table, which represents the correspondence between multiple path information and multiple explanation actions, with one path information corresponding to at least one explanation action; determining the explanation action corresponding to each sub-path in each guidance path based on the explanation action mapping table; generating a guidance action corresponding to each sub-path based on the directional action and explanation action corresponding to each sub-path; and determining the action sub-sequence corresponding to each guidance path based on the execution order and corresponding guidance action of each sub-path in each guidance path.

2. The method as described in claim 1, characterized in that, The process of identifying the user request includes: The user request is input into the pre-trained request recognition model; The request identification model determines the weight values ​​corresponding to the user request and multiple preset function tags, and determines the request type based on the weight values ​​corresponding to the multiple preset function tags. The request type includes the guidance request and the general request.

3. The method as described in claim 2, characterized in that, When the user request is a general request, the method further includes: Determine the request keywords based on the user request; Obtain a general action mapping table, which is used to represent the correspondence between multiple request keywords and multiple general actions. One request keyword corresponds to at least one general action. The general actions include at least one of the following: arm movements, hand movements, head movements, voice movements, and facial movements. The general action corresponding to the user request is determined based on the general action mapping table. A second action execution strategy is generated based on the general action, and the second action execution strategy is used to instruct the humanoid robot to perform the general action.

4. A guidance and control device for a humanoid robot, characterized in that, A humanoid robot used in a humanoid robot motion library system, the humanoid robot motion library system including the humanoid robot and a server, the humanoid robot being connected to the server, the device comprising: The acquisition unit is used to acquire user requests; The identification unit is used to identify the user request and, when determining that the user request is a guidance request, to determine the target location based on the user request. The first generation unit is used to generate a guidance path and a corresponding action sequence based on the position of the humanoid robot, the target position, and a preset environmental map of the exhibition area where the humanoid robot is located. The action sequence corresponds to at least one guidance action, which includes at least one of arm movements, hand movements, head movements, voice movements, and facial movements, as well as a path output action. The preset environmental map is dynamically updated based on information from the management device. The path output action is used to instruct the humanoid robot to display the route of the guidance path in the preset environmental map through a matching display panel. The second generation unit is configured to generate a first action execution strategy based on the guidance path and the action sequence corresponding to the guidance path. The first action execution strategy is used to instruct the humanoid robot to perform at least one guidance action according to the action sequence. In the process of generating a guidance path and a corresponding action sequence based on the position of the humanoid robot, the target position, and a preset environmental map of the exhibition area where the humanoid robot is located, the first generation unit is specifically used to: generate at least one guidance path based on the position of the humanoid robot, the target position, and a preset environmental map of the exhibition area where the humanoid robot is located; divide each guidance path into at least one sub-path, wherein the path directions of two adjacent sub-paths in the same guidance path are different; determine the execution order of each sub-path in the same guidance path and the relative positional relationship between the starting point orientation and the path direction of each sub-path; determine the action sequence based on the execution order and the relative positional relationship of each sub-path in each guidance path; when the guidance path includes multiple paths, in the process of determining the action sequence based on the execution order and the relative positional relationship of each sub-path in each guidance path, the first generation unit is further used to: determine the action sub-sequence corresponding to each guidance path based on the execution order and the relative positional relationship of each sub-path in each guidance path; determine the path sequence corresponding to multiple guidance paths based on preset conditions; and determine the action sequence based on the preset conditions. The path sequence is arranged to form multiple action sub-sequences to obtain the action sequence; in determining the action sub-sequence corresponding to each guidance path based on the execution order and relative positional relationship of each sub-path in each guidance path, the first generation unit is further configured to: obtain a preset directional action mapping table, the directional action mapping table being used to characterize the correspondence between multiple relative positional relationships and multiple directional actions, one relative positional relationship corresponding to one directional action; determine the directional action corresponding to each sub-path in each guidance path based on the directional action mapping table; obtain the action sub-sequence corresponding to each sub-path in each guidance path; and obtain the action sub-sequence corresponding to each sub-path in each guidance path. The document describes a mapping table between path information of each sub-path in a guidance path and a preset narration action mapping table. The narration action mapping table represents the correspondence between multiple path information and multiple narration actions, with one path information corresponding to at least one narration action. The document then determines the narration action corresponding to each sub-path in each guidance path based on the narration action mapping table. Finally, it generates a guidance action corresponding to each sub-path based on the directional action and narration action corresponding to each sub-path. Finally, it determines the action sub-sequence corresponding to each guidance path based on the execution order of each sub-path and the corresponding guidance action.

5. An electronic device, characterized in that, The method includes a processor, a memory, a communication interface, and one or more programs, said one or more programs being stored in the memory and configured to be executed by the processor, said programs including instructions for performing the steps of the method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, A computer program for storing electronic data interchange is provided, wherein the computer program causes a computer to perform the steps of the method as described in any one of claims 1-3.

Images