Robot exhibition hall explanation method and device, electronic device and storage medium

Abstract

The application relates to a robot exhibition explanation method and device, an electronic device and a storage medium, wherein the explanation method comprises the following steps: establishing an action knowledge base based on candidate actions of a robot and interaction intentions of the candidate actions; establishing an exhibition scene knowledge base for a target exhibition scene; the exhibition scene knowledge base stores candidate explanation words; an association relationship between the candidate actions in the action knowledge base and the candidate explanation words in the exhibition scene knowledge base is established; target explanation words are determined from the candidate explanation words according to characteristics of a visitor and a preset explanation time length requirement; and target explanation actions of the robot are generated according to the target explanation words and the association relationship between the candidate actions and the candidate explanation words. Through the application, the problem of low efficiency of explanation setting of the robot in the related art is solved, and the efficiency of explanation setting of the robot is improved.

Description

Technical Field

[0001] This application relates to the field of human-computer interaction technology, and in particular to a method, apparatus, electronic device, and storage medium for robot exhibition hall explanation. Background Technology

[0002] With the continuous development of artificial intelligence, intelligent robot technology is becoming increasingly mature. Using robots to replace humans in certain tasks has become a mainstream trend. For example, intelligent robots are used to replace traditional tour guides, explaining exhibits to visitors. However, in these technologies, exhibition robots typically output pre-set, fixed scripts and actions in a fixed sequence. To output scripts and actions tailored to different exhibits and visitor groups, customized programming is required, resulting in a significant workload and low efficiency in setting up robot-specific explanations.

[0003] There is currently no effective solution to the problem of low efficiency in explaining and setting up robots in related technologies. Summary of the Invention

[0004] This embodiment provides a method, apparatus, electronic device, and storage medium for robot exhibition hall explanation, in order to solve the problem of low efficiency in setting up robot explanations in related technologies.

[0005] Firstly, this embodiment provides a method for explaining a robot in an exhibition hall, including:

[0006] An action knowledge base is established based on the robot's candidate actions and the interaction intent of the candidate actions;

[0007] A knowledge base for exhibition hall scenarios is established for the target exhibition hall scenarios; the knowledge base stores candidate explanatory terms;

[0008] Establish the association between the candidate actions in the action knowledge base and the candidate explanatory words in the exhibition hall scene knowledge base;

[0009] Based on the characteristics of the visitors and the preset duration of the explanation, the target explanation word is determined from the candidate explanation words;

[0010] Based on the target explanation words and the relationship between the candidate actions and the candidate explanation words, a target explanation action is generated for the robot.

[0011] In some embodiments, establishing an action knowledge base based on candidate robot actions and their interaction intentions includes:

[0012] Identify the interaction intent of each candidate action and generate an action knowledge base for the candidate actions and the interaction intent; the candidate actions and the interaction intent Figure 1 One-to-one correspondence.

[0013] In some embodiments, establishing an exhibition hall scene knowledge base for the target exhibition hall scene includes:

[0014] Obtain candidate explanatory words for the target explanatory scenario;

[0015] The candidate explanatory words are divided into segments to obtain each explanatory segment in the candidate explanatory words, and an explanation duration is set for each explanatory segment;

[0016] A knowledge base for exhibition hall scenes is established based on the explanatory information; the explanatory information includes at least the explanatory segments and the explanatory duration.

[0017] In some embodiments, establishing the association between the candidate actions in the action knowledge base and the candidate explanatory terms in the exhibition hall scene knowledge base includes:

[0018] The semantics of the explanation segment are analyzed and classified. Based on the classification results and the interaction intent of the candidate actions, the explanation segment is matched with the interaction intent. Figure 1 One match;

[0019] Based on the matching results between the explanation segment and the interaction intent, a correspondence between the candidate action and the explanation segment is established;

[0020] Based on the correspondence between the candidate actions and the explanatory segments, the association between the candidate actions and the candidate explanatory words is determined.

[0021] In some embodiments, determining the target explanation word from the candidate explanation words based on visitor characteristics and preset explanation duration requirements includes:

[0022] The playback priority of the explanation segment is determined based on the matching degree between the characteristics of the visitor and the explanation segment;

[0023] Based on the playback priority and the required explanation duration, the target explanation words are determined using a combination optimization solution.

[0024] In some embodiments, generating a target narration action for the robot based on the target narration word and the association between the candidate action and the candidate narration word includes:

[0025] Based on the correspondence between the candidate actions and the various explanatory segments in the candidate explanatory text, the target candidate action corresponding to the target explanatory segment is determined; the target explanatory segment constitutes the target explanatory text;

[0026] Based on the target candidate actions, generate the target explanation actions for the robot.

[0027] Secondly, this embodiment provides a robot exhibition hall explanation device, including a first establishment module, a second establishment module, an association module, a first generation module, and a second generation module, wherein:

[0028] The first establishment module is used to establish an action knowledge base based on the robot's candidate actions and the interaction intent of the candidate actions;

[0029] The second module is used to establish a knowledge base for the target exhibition hall scene; the knowledge base stores candidate explanatory terms.

[0030] The association module is used to establish the association relationship between the candidate actions in the action knowledge base and the candidate explanatory words in the exhibition hall scene knowledge base;

[0031] The first generation module is used to determine the target explanation word from the candidate explanation words based on the characteristics of the visitors and the preset explanation duration requirements;

[0032] The second generation module is used to generate a target explanation action for the robot based on the target explanation word and the relationship between the candidate action and the candidate explanation word.

[0033] Thirdly, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the robot exhibition hall explanation method described in the first aspect above.

[0034] Fourthly, this embodiment provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the robot exhibition hall explanation method described in the first aspect above.

[0035] Fifthly, this embodiment provides a storage medium storing a computer program that, when executed by a processor, implements the robot exhibition hall explanation method described in the first aspect above.

[0036] Compared with related technologies, the robot exhibition hall explanation method provided in this embodiment establishes an action knowledge base based on the robot's candidate actions and their interactive intentions. An exhibition hall scene knowledge base is also established for the target exhibition hall scene, storing candidate explanation terms. The method establishes a correlation between candidate actions in the action knowledge base and these candidate explanation terms. Based on visitor characteristics and preset explanation duration requirements, a target explanation term is determined from the candidate explanation terms. Finally, based on the target explanation term and the correlation between candidate actions and the candidate explanation terms, a target explanation action is generated for the robot. This solves the problem of low efficiency in setting up robot explanations in related technologies and improves the efficiency of robot explanation setup.

[0037] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0038] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0039] Figure 1 This is a block diagram of the terminal hardware structure of the robot exhibition hall explanation method in this embodiment.

[0040] Figure 2 This is a flowchart of the robot's exhibition hall explanation method in this embodiment.

[0041] Figure 3 This is a flowchart of the robot's exhibition hall explanation method according to a preferred embodiment.

[0042] Figure 4 This is a structural block diagram of the robot's exhibition hall explanation device in this embodiment.

[0043] Figure 5 This is a preferred structural block diagram of the robot's exhibition hall explanation device in this embodiment. Detailed Implementation

[0044] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0045] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning as understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0046] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of the terminal for the robot's exhibition hall explanation method in this embodiment. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0047] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the robot's exhibition hall explanation method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thereby implementing the aforementioned method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0048] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0049] This embodiment provides a method for explaining a robot in an exhibition hall. Figure 2 This is a flowchart of the robot's exhibition hall explanation method in this embodiment, such as... Figure 2 As shown, the process includes the following steps:

[0050] Step S201: Based on the robot's candidate actions and the interaction intentions of the candidate actions, establish an action knowledge base.

[0051] Specifically, the action knowledge base stores candidate actions that the robot can perform and their corresponding interaction intentions. Based on the application scenario, the interaction intention of each candidate action is identified, and the candidate action and its corresponding interaction intention are stored in the action knowledge base. Figure 1 One-to-one correspondence, such as the candidate action "nodding" corresponding to the interaction intent "agreeing", and the candidate action "extending arm" corresponding to the interaction intent "welcome", etc.

[0052] Step S202: Establish an exhibition hall scene knowledge base for the target exhibition hall scene; the exhibition hall scene knowledge base stores candidate explanatory words.

[0053] Specifically, in addition to storing candidate explanatory words, the scenario knowledge base can also store explanatory information such as explanatory duration and the location of exhibits in the target exhibition hall. Candidate explanatory words for the target explanatory scenario are obtained, and these words are segmented to obtain individual explanatory segments. The playback duration of each segment is recorded, and an explanatory duration is set for each segment based on this playback duration. The segmentation can be based on various rules, such as dividing candidate explanatory words into single-sentence segments or dividing them into paragraphs containing multiple sentences based on semantics and preset semantic segmentation standards; no specific limitation is made here.

[0054] Step S203: Establish the association between candidate actions in the action knowledge base and candidate explanatory words in the exhibition hall scene knowledge base.

[0055] Specifically, the semantics of explanatory segments can be analyzed and categorized using techniques such as keyword extraction. Based on the categorization results and the interactive intent of candidate actions, the explanatory segments can be linked to the interactive intent. Figure 1 First, a matching process is established. Based on the matching results between the explanatory segments and the interactive intents, a correspondence is established between candidate actions and explanatory segments, with each explanatory segment corresponding to one candidate action. Then, based on the correspondence between candidate actions and explanatory segments, the association between candidate actions and candidate explanatory words is determined. For example, in the action knowledge base, candidate action A corresponds to interactive intent A, and candidate action B corresponds to interactive intent B; in the exhibition hall scene knowledge base, explanatory segment A matches interactive intent A, and explanatory segment B matches interactive intent B; therefore, explanatory segment A corresponds to candidate action A, and explanatory segment B corresponds to candidate action B.

[0056] Step S204: Based on the characteristics of the visitors and the preset explanation duration requirements, determine the target explanation text from the candidate explanation texts.

[0057] Specifically, the playback priority of the aforementioned explanatory segments is first determined based on the characteristics of the visitors, and their importance is ranked. Visitor characteristics, such as occupation, hobbies, age, and real-time emotional state, are collected. Big data analysis is then used to determine the matching degree between these characteristics and each explanatory segment; the higher the matching degree, the higher the playback priority of the explanatory segment. The explanatory segments are then sorted according to their playback priority and assigned corresponding serial numbers. For ease of description, assuming the candidate explanatory terms are divided into m segments, after sorting by playback priority and assigning serial numbers, the explanatory segments are labeled as: Explanation Segment 1, Explanation Segment 2, Explanation Segment 3, ..., Explanation Segment m. Explanation Segment 1 is the explanatory segment with the highest relevance to the visitor's characteristics and the highest playback priority; Explanation Segment 2 is the explanatory segment with the second highest relevance to the visitor's characteristics and the second highest playback priority; ..., Explanation Segment m is the explanatory segment with the lowest relevance to the visitor's characteristics and the lowest playback priority.

[0058] Furthermore, the explanation segments are optimized and combined according to the preset explanation duration requirement to form the target explanation term. This ensures that the explanation segments included in the target explanation term are as relevant to the visitor's characteristics as possible, that the number of explanation segments included in the target explanation term is as large as possible, and that the total explanation duration of all explanation segments constituting the target explanation term does not exceed the preset explanation duration requirement. During the optimization and combination solution, explanation segments are added to the playlist sequentially according to playback priority. After each new explanation segment is added, the total explanation duration of the explanation segments in the playlist is calculated. When the total explanation duration of a segment exceeds the preset playback duration requirement, adding new explanation segments to the playlist stops, and the explanation segment with the lowest playback priority in the playlist is deleted. This current playlist is taken as the optimal list. The target explanation term is generated based on the explanation segments in the optimal list. When the target explanation term is output, the explanation segments constituting the target explanation term are played according to the aforementioned playback priority.

[0059] Step S205: Generate target explanation actions for the robot based on the target explanation words and the relationship between candidate actions and candidate explanation words.

[0060] Specifically, based on the correspondence between candidate actions and various explanatory segments in the candidate explanatory text, a target candidate action corresponding to the target explanatory segment is determined; the target explanatory segment constitutes the target explanatory text; and a target explanatory action is generated for the robot based on the target candidate action. When the robot outputs the target explanatory text to visitors, it can coordinate with outputting actions that match the content of the explanatory text, thereby improving the emotional resonance and communication effect of human-computer interaction.

[0061] Through steps S201 to S205 above, an action knowledge base is established based on the robot's candidate actions and their interactive intentions. An exhibition hall scene knowledge base is also established for the target exhibition hall scene. This knowledge base stores candidate explanation phrases. A correlation is established between the candidate actions in the action knowledge base and the candidate explanation phrases in the exhibition hall scene knowledge base. Based on the visitor's characteristics and the preset explanation duration requirements, a target explanation phrase is determined from the candidate explanation phrases. Based on the target explanation phrase and the correlation between the candidate actions and the candidate explanation phrases, a target explanation action is generated for the robot. After basic explanation settings are configured for the robot, this embodiment can generate personalized explanation phrases and configure corresponding explanation actions based on the characteristics of specific visitors during each explanation, eliminating the need for manual customization of explanation phrases. Therefore, it solves the problem of low efficiency in setting up explanations for robots in related technologies and improves the efficiency of robot explanation settings.

[0062] In some embodiments, according to step S201 above, an action knowledge base is established based on the robot's candidate actions and the interaction intent of the candidate actions, which may specifically include:

[0063] Identify the interaction intent for each candidate action and generate an action knowledge base for candidate actions and interaction intents; candidate actions and interaction intents Figure 1 One-to-one correspondence. The robot's candidate actions can include basic actions such as shaking hands, nodding, and pointing; demonstration actions such as showing a certain action or skill; facial expressions such as smiling; and so on. Each candidate action corresponds to an interaction intent. Through the above methods, the action knowledge base can be better organized and managed.

[0064] Furthermore, in some embodiments, according to step S202 above, establishing an exhibition hall scene knowledge base for the target exhibition hall scene may specifically include:

[0065] Obtain candidate explanatory words for the target explanatory scenario; divide the candidate explanatory words into segments to obtain each explanatory segment, and set the explanatory duration for each explanatory segment; establish an exhibition hall scenario knowledge base based on the explanatory information; the explanatory information includes at least the explanatory segment and the explanatory duration.

[0066] The aforementioned segmentation can be based on various segmentation rules. Candidate explanatory words can be divided into single-sentence segments, or they can be divided into paragraphs containing multiple sentences based on semantics and preset semantic segmentation standards. No specific limitations are specified here. The explanatory information may also include the location of each exhibit in the exhibition hall, related images, videos, or other multimedia materials. Natural language processing technology and multimedia content management technology can be used to establish a scene knowledge base for the exhibition hall.

[0067] Furthermore, in some embodiments, according to step S203 above, establishing the association between candidate actions in the action knowledge base and candidate explanatory terms in the exhibition hall scene knowledge base specifically includes:

[0068] The semantics of the explanatory segments are analyzed and categorized. Based on the classification results and the interactive intent of candidate actions, the explanatory segments are linked to the interactive intent. Figure 1 First, match; based on the matching results of the explanation segment and the interaction intent, establish the correspondence between candidate actions and explanation segments; based on the correspondence between candidate actions and explanation segments, determine the association between candidate actions and candidate explanation words.

[0069] Furthermore, in some embodiments, according to step S204 above, the target explanation word is determined from the candidate explanation words based on the characteristics of the visitor and the preset explanation duration requirement, which may specifically include:

[0070] Based on the matching degree between visitor characteristics and explanation segments, the playback priority of explanation segments is determined; based on the playback priority and explanation duration requirements, the target explanation words are determined through combinatorial optimization.

[0071] Visitor characteristics can include information such as age, occupation, cultural background, personal hobbies, and language preferences. Information such as visitors' body posture and facial expressions can also be obtained through sensors, cameras, and other devices to analyze visitors' real-time emotional state and obtain more visitor feedback as information reference.

[0072] This embodiment uses semantic matching technology to calculate the matching degree between the visitor's features and each explanation segment. The higher the matching degree, the higher the playback priority of the corresponding explanation segment. Preferably, the importance of each visitor's features can be evaluated based on pre-set evaluation indicators, and different weight values ​​can be assigned to different features according to the evaluation results. These weighted values ​​are then calculated with the matching degree to obtain the playback priority score of each explanation segment. In the target explanation scenario, the playback priority score S(j) of the j-th explanation segment among the robot's candidate explanation words can be calculated using the following formula:

[0073] S(j)=∑[C(i,j)*W(i)]

[0074] Where C(i,j) represents the matching degree between the i-th visitor feature and the j-th explanation word, and W(i) represents the weight of the i-th visitor feature.

[0075] Furthermore, based on the aforementioned playback priority and preset explanation duration requirements, target explanation terms are determined using a combination optimization solution. This combination optimization solution involves identifying a set of target explanation segments, forming target explanation terms based on this set of segments, maximizing the number of explanation segments included in the target explanation terms, ensuring the total explanation duration of this set of segmented explanations does not exceed the preset explanation duration requirement, and simultaneously satisfying the needs of visitors as much as possible, i.e., maximizing the matching degree between the target explanation segments and the characteristics of the visitors. This combination optimization solution can be implemented using a dynamic programming algorithm. Assuming there are m explanation segments, these segments are arranged in descending order of playback priority. A two-dimensional array DP is defined, where D[i][j] represents the optimal combination solution among the first i explanation segments when the explanation duration requirement is j. The recursive formula can then be obtained:

[0076] DP[i][j]=max(DP[i-1][j],DP[i-1][jT(i)]+S(i))

[0077] Here, S(i) represents the playback priority score of the i-th sentence. By filling the above DP array, the optimal combination of explanation segments can be obtained, and the target explanation words can be formed based on this optimal combination of explanation segments. In addition, the above formula and algorithm can also be adjusted and optimized according to specific circumstances to adapt to the needs of practical applications.

[0078] Furthermore, in some embodiments, according to step S205 above, based on the target explanation words and the correlation between candidate actions and candidate explanation words, a target explanation action is generated for the robot, which may specifically include:

[0079] Based on the correspondence between candidate actions and various explanatory segments in the candidate explanatory text, the target candidate action corresponding to the target explanatory segment is determined; the target explanatory segment forms the target explanatory text; and the target explanatory action is generated for the robot based on the target candidate action.

[0080] In this embodiment, based on the correspondence between candidate actions in the action knowledge base and each target explanation segment, corresponding target candidate actions are determined for each target explanation segment in the already determined target explanation text. Target explanation actions are then generated based on the combination of these target candidate actions. This embodiment can generate more personalized and flexible explanation texts tailored to the characteristics of different visitors. Combined with natural language generation technology, it achieves natural and fluent speech output. Simultaneously with the output of the explanation text, it also outputs explanation actions that match the content of the explanation text and the needs of the visitors, thereby improving the human-computer interaction experience for visitors.

[0081] The present embodiment will now be described and illustrated through preferred embodiments.

[0082] Figure 3 This is a flowchart of the robot showroom explanation method according to a preferred embodiment, such as... Figure 3 As shown, the process includes the following steps:

[0083] Step S301: Based on the robot's candidate actions and the interaction intent of the candidate actions, establish an action knowledge base;

[0084] Step S302: Establish an exhibition hall scene knowledge base for the target exhibition hall scene; the exhibition hall scene knowledge base stores candidate explanatory words;

[0085] Step S303: Establish the association between the candidate actions in the action knowledge base and the candidate explanatory words in the exhibition hall scene knowledge base;

[0086] Step S304: Sort the explanation segments according to the matching degree between the characteristics of the visitors and the explanation segments in the candidate explanation text;

[0087] Step S305: Select a preset number of explanation segments as target explanation segments;

[0088] Step S306: Calculate the total duration of the explanation segments of the target;

[0089] Step S307: Determine whether the total explanation time exceeds the preset explanation time; if it exceeds, proceed to step S308; if it does not exceed, proceed to step S309.

[0090] Step S308: Remove the explanation segment with the lowest matching degree with the visitor's characteristics from the target explanation segment, and proceed to step S306.

[0091] Step S309: Generate target explanation text based on the target explanation segment;

[0092] Step S310: Generate target explanation actions for the robot based on the target explanation words and the relationship between candidate actions and candidate explanation words.

[0093] This embodiment also provides a robot exhibition hall explanation device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. The terms "module," "unit," "subunit," etc., used below refer to combinations of software and / or hardware that achieve a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0094] Figure 4 This is a structural block diagram of the robot's exhibition hall explanation device in this embodiment, as shown below. Figure 4As shown, the device includes: a first creation module 41, a second creation module 42, an association module 43, a first generation module 44, and a second generation module 45, wherein:

[0095] The first creation module 41 is used to create an action knowledge base based on the robot's candidate actions and their interactive intentions; the second creation module 42 is used to create an exhibition hall scene knowledge base for the target exhibition hall scene; the exhibition hall scene knowledge base stores candidate explanatory words; the association module 43 is used to create an association relationship between the candidate actions in the action knowledge base and the candidate explanatory words in the exhibition hall scene knowledge base; the first generation module 44 is used to determine the target explanatory word from the candidate explanatory words according to the characteristics of the visitors and the preset explanation duration requirements; the second generation module 45 is used to generate the target explanation action for the robot according to the target explanatory word and the association relationship between the candidate actions and the candidate explanatory words.

[0096] Figure 5 This is a preferred structural block diagram of the robot's exhibition hall explanation device in this embodiment, such as... Figure 5 As shown, in Figure 4 In addition, it also includes a perception module 46, which is used to acquire the visitor's body posture information and facial expression information.

[0097] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0098] This embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0099] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0100] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0101] S1. Based on the robot's candidate actions and the interaction intentions of the candidate actions, establish an action knowledge base;

[0102] S2, establish an exhibition hall scene knowledge base for the target exhibition hall scene; the exhibition hall scene knowledge base stores candidate explanatory words;

[0103] S3, establish the association between candidate actions in the action knowledge base and candidate explanatory words in the exhibition hall scene knowledge base;

[0104] S4. Based on the characteristics of the visitors and the preset explanation time requirements, determine the target explanation words from the candidate explanation words;

[0105] S5 generates target explanation actions for the robot based on the target explanation words and the relationship between candidate actions and candidate explanation words.

[0106] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0107] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, a network interface, a display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for explaining a robot in an exhibition hall. The display screen may be an LCD screen or an e-ink screen. The input devices may be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0108] Furthermore, in conjunction with the robot exhibition hall explanation methods provided in the above embodiments, this embodiment can also provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the robot exhibition hall explanation methods described in the above embodiments.

[0109] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0110] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0111] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0112] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method for explaining a robot in an exhibition hall, characterized in that, include: An action knowledge base is established based on the robot's candidate actions and the interaction intent of the candidate actions; Establish an exhibition hall scene knowledge base for the target exhibition hall scene; The exhibition hall scene knowledge base stores candidate explanatory terms; Establish the association between the candidate actions in the action knowledge base and the candidate explanatory words in the exhibition hall scene knowledge base; The establishment of the association between the candidate actions in the action knowledge base and the candidate explanatory terms in the exhibition hall scene knowledge base includes: The semantics of the explanatory segments in the candidate explanatory words are analyzed and classified. Based on the classification results and the interactive intent of the candidate actions, the explanatory segments are matched with the interactive intents one by one. Based on the matching results between the explanation segment and the interaction intent, a correspondence between the candidate action and the explanation segment is established; Based on the correspondence between the candidate actions and the explanatory segments, the association between the candidate actions and the candidate explanatory words is determined; Based on the characteristics of the visitors and the preset duration of the explanation, the target explanation word is determined from the candidate explanation words; Based on the target explanation words and the relationship between the candidate actions and the candidate explanation words, a target explanation action is generated for the robot.

2. The method for explaining a robot in an exhibition hall according to claim 1, characterized in that, The robot-based candidate actions and their interaction intentions are used to establish an action knowledge base, including: Identify the interaction intent of each candidate action and generate an action knowledge base for the candidate actions and the interaction intents; the candidate actions and the interaction intents correspond one-to-one.

3. The method for explaining a robot in an exhibition hall according to claim 2, characterized in that, The establishment of an exhibition hall scene knowledge base for the target exhibition hall scene includes: Obtain candidate explanatory words for the target explanatory scenario; The candidate explanatory words are divided into segments to obtain each explanatory segment in the candidate explanatory words, and an explanation duration is set for each explanatory segment; A knowledge base for the exhibition hall scene is established based on the explanation information; the explanation information includes at least the explanation segment and the explanation duration.

4. The method for explaining a robot in an exhibition hall according to claim 3, characterized in that, The process of determining the target explanation word from the candidate explanation words based on the characteristics of the visitors and the preset explanation duration requirements includes: The playback priority of the explanation segment is determined based on the matching degree between the characteristics of the visitor and the explanation segment; Based on the playback priority and the required explanation duration, the target explanation words are determined using a combination optimization solution.

5. The method for explaining a robot in an exhibition hall according to claim 4, characterized in that, The step of generating a target explanation action for the robot based on the target explanation word and the association between the candidate action and the candidate explanation word includes: Based on the correspondence between the candidate actions and the various explanatory segments in the candidate explanatory text, the target candidate action corresponding to the target explanatory segment is determined; the target explanatory segment constitutes the target explanatory text; Based on the target candidate actions, generate the target explanation actions for the robot.

6. A robot exhibition hall explanation device, characterized in that, It includes a first creation module, a second creation module, an association module, a first generation module, and a second generation module, wherein: The first establishment module is used to establish an action knowledge base based on the robot's candidate actions and the interaction intent of the candidate actions; The second module is used to establish a knowledge base for the target exhibition hall scene; the knowledge base stores candidate explanatory terms. The association module is used to establish the association relationship between the candidate actions in the action knowledge base and the candidate explanatory words in the exhibition hall scene knowledge base; The establishment of the association between the candidate actions in the action knowledge base and the candidate explanatory terms in the exhibition hall scene knowledge base includes: The semantics of the explanatory segments in the candidate explanatory words are analyzed and classified. Based on the classification results and the interactive intent of the candidate actions, the explanatory segments are matched with the interactive intents one by one. Based on the matching results between the explanation segment and the interaction intent, a correspondence between the candidate action and the explanation segment is established; Based on the correspondence between the candidate actions and the explanatory segments, the association between the candidate actions and the candidate explanatory words is determined; The first generation module is used to determine the target explanation word from the candidate explanation words based on the characteristics of the visitors and the preset explanation duration requirements; The second generation module is used to generate a target explanation action for the robot based on the target explanation word and the relationship between the candidate action and the candidate explanation word.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the exhibition hall explanation method for the robot according to any one of claims 1 to 5.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the exhibition hall explanation method for the robot according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the exhibition hall explanation method for the robot as described in any one of claims 1 to 5.

Images