Tour guide system, method, equipment and medium

Abstract

The invention provides a tour guide system, method, equipment and medium, and relates to the technical field of scenic spot tour guide, and the system comprises an interaction module which is used for obtaining explanation demand information and sending the explanation demand information to a data processing module; the preset information acquisition module is used for acquiring at least one piece of preset information and sending the at least one piece of preset information to the data processing module, and the at least one piece of preset information comprises the current position information; the data processing module is used for determining target explanation information according to the explanation demand information and / or at least one piece of preset information and sending the target explanation information to the interaction module; and the interaction module is used for playing the target explanation information. According to the invention, personalized and interactive intelligent explanation is provided for users in scenic spots.

Description

Technical Field

[0001] The present invention relates to the technical field of scenic area tour guides, and more particularly, to a tour guide system, method, device, and medium. Background Art

[0002] In order to enhance the user's visiting experience, some scenic areas are equipped with interpretation services, which are currently mainly realized through manual interpretation or rental of broadcasting equipment. However, most of the existing interpretation devices can only output interpretation content unidirectionally, lacking interactivity with users, making it difficult to fully meet the personalized needs of users. Moreover, the current interpretation devices cannot integrate with park services. When users need park services, they can only query through other devices. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to overcome the deficiencies in the prior art and provide a tour guide system, method, device, and medium. The present invention provides the following technical solutions:

[0004] In a first aspect, the present invention provides a tour guide system, which includes: an interaction module, a preset information acquisition module, and a data processing module;

[0005] The interaction module is used to obtain interpretation requirement information and send the interpretation requirement information to the data processing module;

[0006] The preset information acquisition module is used to obtain at least one preset information and send the at least one preset information to the data processing module. The at least one preset information includes: current location information;

[0007] The data processing module is used to determine target interpretation information according to the interpretation requirement information and / or the at least one preset information, and send the target interpretation information to the interaction module;

[0008] The interaction module is further used to play the target interpretation information.

[0009] In an embodiment, the interpretation requirement information includes: voice information and / or video information. The data processing module is used to determine interpretation information according to the voice information and / or the video information, and determine the target interpretation information according to the interpretation information and / or the at least one preset information.

[0010] In an embodiment, the data processing module includes:

[0011] A voice processing unit, which is used to obtain the voice information and convert the voice information into text information;

[0012] Perform semantic understanding on the text information through a preset language model to obtain a semantic understanding result;

[0013] Search a preset knowledge base according to the semantic understanding result to obtain the corresponding explanation information;

[0014] Obtain the at least one preset information, and determine the target explanation information according to the corresponding explanation information and the at least one preset information.

[0015] In one embodiment, the data processing module further includes:

[0016] A visual processing unit, configured to obtain the image information, perform object recognition and content understanding on the image information through a preset visual model, and obtain an object recognition result and a content understanding result;

[0017] Search a preset knowledge base according to the object recognition result and the content understanding result to obtain the corresponding explanation information;

[0018] Obtain the at least one preset information, and determine the target explanation information according to the corresponding explanation information and the at least one preset information.

[0019] In one embodiment, the speech processing unit is further configured to send the semantic understanding result to the visual processing unit; the visual processing unit is further configured to perform multi-modal fusion on the semantic understanding result, the object recognition result, and the content understanding result to obtain a fusion result; search the preset knowledge base according to the fusion result to obtain the corresponding explanation information; obtain the at least one preset information, and determine the target explanation information according to the corresponding explanation information and the at least one preset information.

[0020] In one embodiment, the system further includes: a plurality of scenic area service modules;

[0021] The speech processing unit is further configured to judge the user's intention according to the semantic understanding result;

[0022] Determine at least one target scenic area service module from the plurality of scenic area service modules according to the user's intention;

[0023] Call the at least one target scenic area service module, and input the semantic understanding result and the at least one preset information into the target scenic area service module to obtain a feedback result;

[0024] Send the feedback result to the interaction module;

[0025] The visual processing unit is further configured to judge the user's intention according to the fusion result;

[0026] Determine at least one of the target scenic area service modules from the plurality of scenic area service modules according to the user's intention;

[0027] Call the at least one target scenic area service module, and input the fusion result and the at least one preset information into the target scenic area service module to obtain the feedback result;

[0028] Send the feedback result to the interaction module.

[0029] In one embodiment, the system further includes: a model training module;

[0030] The model training module is configured to obtain a training data set, where the training data set includes: a plurality of the semantic understanding results and user intention labels respectively corresponding to the semantic understanding results;

[0031] Obtain an initial language model, where the initial language model includes a plurality of training weights;

[0032] Determine a plurality of target training weights that meet preset conditions from the plurality of training weights, freeze each of the target training weights, and determine the unfrozen training weights as the weights to be trained;

[0033] Based on the training data set, train the initial language model, and fine-tune each of the weights to be trained during the training process to obtain the preset language model.

[0034] In a second aspect, the present invention provides a tour guide method, which is applied to the tour guide system described in the first aspect. The method includes:

[0035] The interaction module obtains the explanation requirement information and sends the explanation requirement information to the data processing module;

[0036] The preset information acquisition module obtains at least one preset information and sends the at least one preset information to the data processing module. The at least one preset information includes: current location information;

[0037] The data processing module determines the target explanation information according to the explanation requirement information and / or the at least one preset information, and sends the target explanation information to the interaction module;

[0038] The interaction module plays the target explanation information.

[0039] In a third aspect, the present invention provides a tour guide device, including a memory and a processor. The memory stores a computer program, and when the computer program runs on the processor, it executes the tour guide method described in the second aspect.

[0040] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the tour guide method described in the second aspect.

[0041] The tour guide system, method, device and medium provided by the embodiments of the present application, the system includes: an interaction module, a preset information acquisition module and a data processing module; the interaction module is configured to acquire explanation requirement information and send the explanation requirement information to the data processing module; the preset information acquisition module is configured to acquire at least one preset information and send the at least one preset information to the data processing module, the at least one preset information includes: current location information; the data processing module is configured to determine target explanation information according to the explanation requirement information and / or the at least one preset information and send the target explanation information to the interaction module; the interaction module is configured to play the target explanation information. The present application realizes providing personalized and interactive intelligent explanations for scenic area users. In addition, by integrating multiple scenic area service modules, the present application further improves the convenience and satisfaction of users.

[0042] To make the above objects, features and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0044] Figure 1 Shows a schematic structural diagram of the tour guide system provided by the embodiments of the present application;

[0045] Figure 2 Shows another schematic structural diagram of the tour guide system provided by the embodiments of the present application;

[0046] Figure 3 Shows a schematic flow diagram of the tour guide method provided by the embodiments of the present application;

[0047] Figure 4 Shows a schematic structural diagram of the tour guide device provided by the embodiments of the present application.

[0048] MAIN ELEMENT SYMBOL DESCRIPTION:

[0049] 100 - Tour guide system; 110 - Interaction module; 120 - Preset information acquisition module; 130 - Data processing module; 140 - Scenic area service module; 400 - Tour guide device; 401 - Transceiver; 402 - Processor; 403 - Memory. Detailed implementation manner

[0050] The embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0051] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used in the description of the template herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0053] Embodiment 1

[0054] Currently, the explanation services provided by scenic areas are mainly realized in the following ways: (1) Headphones and a host device that communicates with the headphones. Staff members communicate through the host device, and users receive the communication information through the headphones to achieve guided tour explanations; (2) Multiple wireless signal transmitters are pre - arranged in multiple scenic areas. After the user holds the automatic trigger player and enters the corresponding scenic area, the automatic trigger player receives the corresponding wireless signal and then plays the pre - recorded explanation information; (3) QR codes are posted in multiple scenic areas, and users scan the QR codes through terminal devices to obtain explanation information. The intelligent level of the explanation devices used in these existing technologies is relatively low. Most of them can only output the explanation content unidirectionally, lack interactivity with users, and are difficult to meet the personalized needs of users.

[0055] For this, please refer to Figure 1, this application provides a tour guide system 100, including: an interaction module 110, a preset information acquisition module 120, and a data processing module 130; the interaction module 110 is used to acquire explanation requirement information and send the explanation requirement information to the data processing module 130; the preset information acquisition module 120 is used to acquire at least one preset information and send the at least one preset information to the data processing module 130, and the at least one preset information includes: current location information; the data processing module 130 is used to determine target explanation information according to the explanation requirement information and / or the at least one preset information, and send the target explanation information to the interaction module 110; the interaction module 110 is used to play the target explanation information.

[0056] In this embodiment, the interaction module 110 and the data processing module 130 are connected through a mobile communication network. Specifically, at least one signal base station is set in the scenic area. As the infrastructure of the mobile communication network, the signal base station connects the interaction module 110 and the data processing module 130 to realize data transmission and interaction between the interaction module 110 and the data processing module 130. The preset information acquisition module 120 is used to acquire at least one preset information, where the at least one preset information includes but is not limited to: user information, environmental temperature, weather, current location information, and the number of people in the scenic area, etc. Among them, user information, such as user name, age, personality, etc., can be uploaded through the interaction module 110 and sent by the interaction module 110 to the preset information acquisition module 120; environmental temperature and weather can be obtained by the preset information acquisition module 120 by calling meteorological data; the current location information can be obtained by acquiring the positioning information sent by at least one positioning base station. Please refer to Figure 1 , Figure 1 Multiple positioning base stations are shown in, and each positioning base station respectively conducts data interaction with the preset information acquisition module 120; the scenic area population information can be obtained by the preset information acquisition module 120 by calling scenic area data; specifically, the type of preset information acquired by the preset information acquisition module 120 and the acquisition method corresponding to the preset information type can be determined according to the actual situation, and only examples are given here without limitation.

[0057] In one embodiment, the explanation requirement information includes: voice information and / or video information. The data processing module 130 is used to determine explanation information according to the voice information and / or the video information, and determine the target explanation information according to the explanation information and / or the at least one preset information.

[0058] It should be noted that the explanatory requirement information includes: voice information and / or video information. The interaction module 110 includes: a voice acquisition unit and a video acquisition unit. Among them, the voice acquisition unit is used to acquire voice information and send the voice information to the data processing module 130; the video acquisition unit is used to acquire video information and send the video information to the data processing module 130. The data processing module 130 processes the acquired voice information and / or video information, obtains the corresponding explanatory information, and then converts the corresponding explanatory information into a natural language form to obtain the target explanatory information; or combines the corresponding explanatory information with at least one preset information and then converts it into a natural language form to obtain the target explanatory information; or converts at least one preset information into a natural language form to obtain the target explanatory information.

[0059] In one embodiment, the data processing module 130 includes: a voice processing unit, which is used to acquire the voice information, convert the voice information into text information, perform semantic understanding on the text information through a preset language model to obtain a semantic understanding result, search a preset knowledge base according to the semantic understanding result to obtain the corresponding explanatory information, acquire the at least one preset information, and determine the target explanatory information according to the corresponding explanatory information and the at least one preset information.

[0060] The preset language model is an artificial intelligence model constructed based on deep learning technology, and is used to understand and generate natural language text.

[0061] In this embodiment, the voice processing unit is used to acquire voice information from the interaction module 110, convert the voice information into text information, and input the obtained text information into the preset language model for semantic understanding. For example: the voice processing unit acquires voice information from the interaction module 110, performs text conversion on the voice information to obtain the following text information "Please recommend a venue that is most suitable for viewing?", after inputting the text information into the preset language model to obtain the corresponding semantic understanding result, searches the preset knowledge base according to the semantic understanding result to obtain the corresponding explanatory information. Further, the voice processing unit will acquire at least one preset information from the preset information acquisition module 120, such as weather information and venue information, etc., combine the explanatory information and the at least one preset information, and convert it into a natural language form to obtain the target explanatory information, such as "The tropical rainforest pavilion in Area A may be a good choice because the water lilies are in full bloom today!".

[0062] In other embodiments, after the speech processing unit processes the speech information to obtain the corresponding semantic understanding result, it can further obtain at least one preset information from the preset information acquisition module 120 according to the semantic understanding result, and then query the preset knowledge base based on the semantic understanding result and the at least one preset information to obtain the corresponding explanation information. For example, the speech processing unit obtains the speech information from the interaction module 110, converts the speech information into text, and obtains the following text information: "What was this famous person doing at my age?" After obtaining the corresponding semantic understanding result by inputting the text into the preset language model, according to the semantic understanding result, the user information, such as age, is obtained from the preset information acquisition module. Then, based on the user information and the semantic understanding result, the preset knowledge base is queried to obtain the corresponding explanation information. Further, if the corresponding preset information is not obtained, after the speech processing unit queries the preset knowledge base, the following explanation information will be obtained: "May I ask how old you are now?" It can be understood that the corresponding explanation information in different scenarios is pre-stored in the preset knowledge base.

[0063] It should be noted that a plurality of information related to the scenic area is pre-stored in the preset knowledge base, such as: flower species, venue introduction, exhibit background, etc. It can be understood that the preset knowledge base will be continuously updated and iterated according to the update of the scenic area and user needs to supplement new scenic area information.

[0064] In one embodiment, the data processing module 130 further includes: a visual processing unit, configured to obtain the image information, perform object recognition and content understanding on the image information through a preset visual model to obtain an object recognition result and a content understanding result; search the preset knowledge base according to the object recognition result and the content understanding result to obtain the corresponding explanation information; obtain the at least one preset information, and determine the target explanation information according to the corresponding explanation information and the at least one preset information.

[0065] The preset visual model is an artificial intelligence model constructed based on deep learning technology, and is used to recognize and understand image or video content.

[0066] In this embodiment, the visual processing unit is used to obtain image information from the interaction module 110, and perform object recognition and content understanding on the image information through a preset visual model. For example: The visual processing unit obtains the image information taken by the user from the interaction module 110, analyzes the image information, and identifies the target objects and scene content in the image. Suppose the user takes a picture of a flower, and the visual processing unit identifies through the preset visual model that this is a "Diana rose" and understands that the scene where it is located is a flower exhibition area. Subsequently, according to the object recognition result and content understanding result, the preset knowledge base is queried to obtain the corresponding explanation information. For example: The Diana rose is native to China and symbolizes good wishes and yearning for love. Further, the visual processing unit obtains at least one preset information from the preset information acquisition module 120, such as weather and temperature, etc., combines the explanation information with the at least one preset information, and after converting it into a natural language form, obtains the target explanation information. For example: "This is a Diana rose. It is native to China and symbolizes good wishes and yearning for love. On this sunny day, it is a good choice to admire this flower."

[0067] In one embodiment, the speech processing unit is further configured to send the semantic understanding result to the visual processing unit; the visual processing unit is further configured to perform multi-modal fusion on the semantic understanding result, the object recognition result, and the content understanding result to obtain a fusion result; search the preset knowledge base according to the fusion result to obtain the corresponding explanation information; obtain the at least one preset information, and determine the target explanation information according to the corresponding explanation information and the at least one preset information.

[0068] In this embodiment, the explanation requirement information includes both: voice information (such as the voice input by the user) and image information (such as the picture or video taken by the user). The speech processing unit and the visual processing unit in the data processing module 130 work together to achieve the comprehensive processing of multi-modal information. The speech processing unit is responsible for converting the user's voice information into a semantic understanding result and transmitting it to the visual processing unit; the visual processing unit then uses deep learning algorithms to perform object recognition and content understanding on the image information to obtain the object recognition result and the content understanding result. Subsequently, the visual processing unit fuses the semantic understanding result, the object recognition result, and the content understanding result to form a multi-modal fusion result. Based on this fusion result, the corresponding explanation information is searched in the preset knowledge base. Further, the visual processing unit obtains at least one preset information from the preset information acquisition module 120, such as weather and temperature, etc., combines the explanation information with the at least one preset information, and after converting it into a natural language form, obtains the target explanation information.

[0069] For example, the interaction module 110 obtains a piece of video information: a 15 - second video, and voice information: "What kind of flower is this?" and sends them to the data processing module 130. The voice processing unit in the data processing module 130 obtains the voice information and processes it to obtain a semantic understanding result, and sends the semantic understanding result to the video processing unit; the video processing unit processes the video information to obtain a target recognition result and a content understanding result; the semantic understanding result, the target recognition result, and the content understanding result are multi - modality fused to obtain a fusion result, and according to the fusion result, the preset knowledge base is searched to obtain the corresponding explanation information, and according to the corresponding explanation information and the at least one preset information, the target explanation information is determined, for example: "Today's weather is a bit gloomy, but with the company of Diana roses, our mood will still be happy."

[0070] In one embodiment, please refer to Figure 2 , the tour guide system 100 further includes: a plurality of scenic area service modules 140; the voice processing unit is further configured to judge the user's intention according to the semantic understanding result; determine at least one target scenic area service module from the plurality of scenic area service modules 140 according to the user's intention; call the at least one target scenic area service module, and input the semantic understanding result and the at least one preset information into the target scenic area service module to obtain a feedback result; send the feedback result to the interaction module 110;

[0071] The visual processing unit is further configured to judge the user's intention according to the fusion result; determine at least one of the target scenic area service modules from the plurality of scenic area service modules 140 according to the user's intention; call the at least one target scenic area service module, and input the fusion result and the at least one preset information into the target scenic area service module to obtain the feedback result; send the feedback result to the interaction module 110.

[0072] In this embodiment, the tour guide system 100 also integrates a plurality of scenic area service modules 140 to meet the diverse needs of users. Specifically, after the voice processing unit performs semantic understanding on the voice information, it will judge the user's intention according to the semantic understanding result. For example, the user may want to query the shuttle bus time or nearby catering services. The voice processing unit selects at least one target scenic area service module that matches it from the plurality of scenic area service modules 140 according to the user's intention. Call the target scenic area service module, and input the semantic understanding result and the at least one preset information obtained into it, so as to obtain the corresponding feedback result. For example, when the user wants to query the shuttle bus time, the voice processing unit will call the shuttle bus service module according to the semantic processing result, and input the user's query intention and at least one preset information, such as the current location, into the shuttle bus service module, and finally obtain the specific shuttle bus time information as the feedback.

[0073] It can be understood that the semantic understanding result usually contains multiple keywords. Based on multiple keywords, the user intention can be determined, and then the target scenic area service module can be determined according to the user intention. For example, if the voice information is "I want to go to the nearest restaurant", the keywords may be "nearest" and "restaurant". The voice processing unit inputs these keywords and at least one preset information, such as location information, passenger flow information, etc. into the positioning module, and finally obtains the positioning result of the restaurant near the user's current location;

[0074] Furthermore, the visual processing unit can judge the user intention according to the fusion result. For example, imagine that the user takes a photo of a park restaurant through the interaction module 110 and says: I want to book a seat in this restaurant. After the voice processing unit processes the voice information, it sends the semantic understanding result to the visual processing unit. After the visual processing unit processes the image data to obtain the corresponding target recognition result and content understanding result, it performs multi-modal fusion on the semantic understanding result, the target recognition result and the content understanding result to obtain the fusion result, and makes a graph determination according to the fusion result.

[0075] In one embodiment, the tour guide system 100 further includes: a model training module; the model training module is used to obtain a training data set, and the training data set includes: a plurality of the semantic understanding results and the user intention labels respectively corresponding to the semantic understanding results; obtain an initial language model, and the initial language model includes a plurality of training weights; determine a plurality of target training weights that meet the preset conditions from the plurality of training weights, freeze each of the target training weights, and determine the unfrozen training weights as the weights to be trained; based on the training data set, train the initial language model, and fine-tune each of the weights to be trained during the training process to obtain the preset language model.

[0076] In this embodiment, the model training module is further used to optimize the initial language model to improve its semantic understanding ability, and then obtain the preset language model. Specifically, the model training module first obtains a training data set including semantic understanding results and their corresponding user intention labels, and then obtains an initial language model, which includes a plurality of trainable weight parameters. Then, the model training module screens out the key weights that meet the preset conditions from these weights and freezes them, while determining the remaining weights as the weights to be trained. During the training process, the initial language model is fine-tuned using the training data set, and only the weights to be trained are adjusted. Finally, the optimized preset language model is obtained. This process improves the recognition accuracy of the preset language model for user intentions in a data-driven manner, so as to provide more accurate services for users.

[0077] The tour guide system provided by the embodiments of the present application includes: an interaction module 110, a preset information acquisition module 120, and a data processing module 130; the interaction module 110 is configured to acquire explanation requirement information and send the explanation requirement information to the data processing module 130; the preset information acquisition module 120 is configured to acquire at least one preset information and send the at least one preset information to the data processing module 130, where the at least one preset information includes: current location information; the data processing module 130 is configured to determine target explanation information according to the explanation requirement information and / or the at least one preset information, and send the target explanation information to the interaction module 110; the interaction module 110 is configured to play the target explanation information. The present application realizes providing personalized and interactive intelligent explanations for scenic area users. In addition, by integrating multiple scenic area service modules 140, the present application further improves the convenience and satisfaction of users.

[0078] Embodiment 2

[0079] In addition, please refer to Figure 3 , the embodiments of the present application also provide a tour guide method, which is applied to the tour guide system 100 described in Embodiment 1, and the method includes: steps S310 to S330.

[0080] S310, the interaction module 110 acquires explanation requirement information and sends the explanation requirement information to the data processing module 130.

[0081] S320, the preset information acquisition module acquires at least one preset information and sends the at least one preset information to the data processing module, where the at least one preset information includes: current location information;

[0082] S330, the data processing module 130 determines target explanation information according to the explanation requirement information and sends the target explanation information to the interaction module 110.

[0083] S340, the interaction module 110 plays the target explanation information.

[0084] The tour guide method provided by the embodiments of the present invention, which is applied to the tour guide system 100 described in Embodiment 1, will not be repeated here to avoid redundancy.

[0085] The guiding method provided by the embodiment of the present application obtains the explanation requirement information through the interaction module 110 and sends the explanation requirement information to the data processing module 130; the preset information obtaining module 120 obtains at least one preset information and sends the at least one preset information to the data processing module 130, and the at least one preset information includes: the current location information; the data processing module 130 determines the target explanation information according to the explanation requirement information and / or the at least one preset information, and sends the target explanation information to the interaction module 110; the interaction module 110 plays the target explanation information, realizing personalized and interactive intelligent explanation for scenic area users. In addition, by integrating multiple scenic area service modules 140, the present application further improves the convenience and satisfaction of users.

[0086] Embodiment 3

[0087] In addition, the embodiment of the present invention provides a guiding device 400, including a memory 403 and a processor 402. The memory 403 stores a computer program, and when the computer program runs on the processor 402, it executes the guiding method provided in Embodiment 2.

[0088] Specifically, please refer to Figure 4 , the guiding device 400 includes: a transceiver 401, a bus interface and a processor 402. The processor 402 is used for the interaction module 110 to obtain the explanation requirement information and send the explanation requirement information to the data processing module 130; the preset information obtaining module 120 obtains at least one preset information and sends the at least one preset information to the data processing module 130, and the at least one preset information includes: the current location information; the data processing module 130 determines the target explanation information according to the explanation requirement information and / or the at least one preset information, and sends the target explanation information to the interaction module 110; the interaction module 110 plays the target explanation information. In the embodiment of the present invention, the guiding device 400 further includes: a memory 403. In Figure 4 , the bus architecture may include any number of interconnected buses and bridges. Specifically, various circuits of one or more processors 402 represented by the processor 402 and the memory 403 represented by the memory 403 are linked together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators and power management circuits, which are well known in the art, so they will not be further described herein. The bus interface provides an interface. The transceiver 401 may be multiple elements, that is, including a transmitter and a receiver, and provides a unit for communicating with various other devices on the transmission medium. The processor 402 is responsible for managing the bus architecture and general processing, and the memory 403 can store the data used by the processor 402 when performing operations.

[0089] The guiding device 400 provided by an embodiment of the present invention can execute the guiding method provided in Embodiment 2 of the above method embodiment. To avoid repetition, it will not be described herein again.

[0090] Embodiment 4

[0091] In addition, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the guiding method provided in Embodiment 2 is implemented.

[0092] In this embodiment, the computer-readable storage medium may be a read-only memory 403 (Read-Only Memory, abbreviated as ROM), a random access memory (Random Access Memory, abbreviated as RAM), a magnetic disk, an optical disk, or the like.

[0093] The computer-readable storage medium provided in this embodiment can implement the guiding method provided in Embodiment 2. To avoid repetition, it will not be described herein again.

[0094] In all the examples shown and described here, any specific value should be construed as merely exemplary, not as a limitation. Therefore, other examples of the exemplary embodiments may have different values.

[0095] It should be noted that like reference numerals and letters denote like items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0096] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can be made, and these all belong to the protection scope of the present invention.

Claims

1. A tour guide system, characterized in that: The system comprises: an interaction module, a preset information acquisition module and a data processing module; The interaction module is used to obtain explanation requirement information and send the explanation requirement information to the data processing module; The preset information acquisition module is used to acquire at least one preset information and send the at least one preset information to the data processing module, wherein the at least one preset information includes: current location information; The data processing module is used to determine target explanation information according to the explanation requirement information and / or the at least one preset information, and send the target explanation information to the interaction module; The interactive module is also used to play the target explanation information.

2. The tour guide system according to claim 1, characterized in that: The explanation requirement information includes: voice information and / or image information. The data processing module is used to determine the explanation information according to the voice information and / or the image information, and determine the target explanation information according to the explanation information and / or the at least one preset information.

3. The tour guide system according to claim 2, characterized in that: The data processing module comprises: A voice processing unit, used to obtain the voice information and convert the voice information into text information; Performing semantic understanding on the text information through a preset language model to obtain a semantic understanding result; Searching a preset knowledge base according to the semantic understanding result to obtain the corresponding explanation information; The at least one preset information is acquired, and the target explanation information is determined according to the corresponding explanation information and the at least one preset information.

4. The tour guide system according to claim 3, characterized in that: The data processing module also includes: A visual processing unit, used to obtain the image information, perform target recognition and content understanding on the image information through a preset visual model, and obtain a target recognition result and a content understanding result; Searching a preset knowledge base according to the target recognition result and the content understanding result to obtain the corresponding explanation information; The at least one preset information is acquired, and the target explanation information is determined according to the corresponding explanation information and the at least one preset information.

5. The guide system according to claim 4, characterized in that: The speech processing unit is further used to send the semantic understanding result to the visual processing unit; The visual processing unit is further used to perform multimodal fusion on the semantic understanding result, the target recognition result and the content understanding result to obtain a fusion result; Search the preset knowledge base according to the fusion result to obtain the corresponding explanation information; The at least one preset information is acquired, and the target explanation information is determined according to the corresponding explanation information and the at least one preset information.

6. The guide system according to claim 5, characterized in that: The system also includes: a plurality of scenic area service modules; The speech processing unit is further used to determine the user intention according to the semantic understanding result; Determining at least one target scenic spot service module from the plurality of scenic spot service modules according to the user intention; Calling the at least one target scenic spot service module, and inputting the semantic understanding result and the at least one preset information into the target scenic spot service module to obtain a feedback result; Sending the feedback result to the interaction module; The visual processing unit is further used to determine the user intention according to the fusion result; Determining at least one target scenic spot service module from the plurality of scenic spot service modules according to the user intention; calling the at least one target scenic spot service module, and inputting the fusion result and the at least one preset information into the target scenic spot service module to obtain the feedback result; Send the feedback result to the interaction module.

7. The tour guide system according to claim 3, characterized in that: The system also includes: a model training module; The model training module is used to obtain a training data set, wherein the training data set includes: a plurality of the semantic understanding results and user intention labels corresponding to the semantic understanding results; Acquire an initial language model, wherein the initial language model includes a plurality of training weights; Determining a plurality of target training weights satisfying a preset condition from the plurality of training weights, freezing each of the target training weights, and determining each of the unfrozen training weights as a weight to be trained; Based on the training data set, the initial language model is trained, and during the training process, each weight to be trained is fine-tuned to obtain the preset language model.

8. A tour guide method, characterized in that: The tour guide system applied to any one of claims 1 to 7, the method comprising: The interactive module obtains the explanation requirement information and sends the explanation requirement information to the data processing module; The preset information acquisition module acquires at least one preset information and sends the at least one preset information to the data processing module, wherein the at least one preset information includes: current location information; The data processing module determines target explanation information according to the explanation requirement information and / or the at least one preset information, and sends the target explanation information to the interaction module; The interactive module plays the target explanation information.

9. A tour guide device, characterized in that: The system comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is run on the processor, the tour guide method according to claim 8 is executed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the tour guide method according to claim 8 is implemented.

Images