A kind of intelligent management method of hotel guest room

Abstract

The invention discloses an intelligent management method for hotel guest rooms, which relates to the technical field of hotel management. After adopting the method, customers staying in hotel guest rooms have a better experience, and customers can communicate and dialogue with intelligent robots through voice throughout the whole process to complete the control of the system itself, applications in the system, and intelligent devices in the room; at the same time, the original menu navigation interaction mode and the full intelligent robot mode are supported, and the user can switch the interaction mode arbitrarily by issuing instructions. It is very friendly to users of all ages and reduces the learning cost of users; the innovative approximate sound analysis mode and instruction analysis mode help the intelligent robot to better understand the user's intention, so as to achieve accurate recognition of the user's voice and intention identification; the intelligent robot replaces the hotel waiter to respond to the user's needs in time, improves the hotel service efficiency, and saves labor costs.

Description

Technical Field

[0001] The present invention relates to the technical field of hotel management, and in particular to an intelligent management method for hotel guest rooms. Background Art

[0002] At present, most smart hotels on the market are equipped with smart devices to achieve intelligent control of hotel equipment and a simple smart hotel living experience through voice control. Consumers have higher and higher requirements for travel experience, and simple smart control can no longer meet people's requirements for hotel comfort and convenience. A large number of hotels have begun to use smart speakers + smart devices + multi-channel content delivery to meet consumers' comfort and convenience requirements. However, this requires hotels to introduce more equipment, which increases costs, and ultimately they can only pass on the costs to consumers by raising room prices. Summary of the invention

[0003] The present invention provides a method for intelligent management of hotel guest rooms, which collects user voices through a microphone array of a television remote control and issues instructions to an intelligent voice library, and finally a virtual robot completes the service. The system integrates the intelligent voice library and the virtual robot into the television screen, solving the problem that the original smart hotel needs to purchase a large number of smart speakers, large-screen televisions, smart robots and other multiple terminals, greatly reducing the cost of hotel intelligent transformation, achieving user comfort experience while improving convenience.

[0004] The technical solution adopted by the present invention is as follows:

[0005] The present invention provides a hotel room intelligent management method, comprising: when a customer enters a hotel room, a television terminal automatically senses and starts, and a television screen displays a virtual animation robot interacting with the customer by voice; the voice interaction comprises at least the following steps:

[0006] S1. The customer inputs voice information into the voice command library through the remote control microphone array;

[0007] S2, the voice instruction library parses the voice information into a text string through a voice parsing module;

[0008] S3, the voice instruction library determines the type of the text string;

[0009] S4. If the type of the text string is a question-and-answer type, the virtual animation robot matches the answer information piece from the question-and-answer library and feeds back the answer information piece to the customer in the form of voice; if the type of the text string is an instruction type, the virtual animation robot matches the instruction information piece from the instruction library;

[0010] S5. If the instruction information bar is an end instruction, there is no need to enter the sub-process, and the virtual animation robot ends the current voice interaction; if the instruction information bar is a device control sub-process call instruction, the virtual animation robot calls the corresponding device control sub-process, controls the corresponding device according to the instruction, and then ends the current voice interaction; if the instruction information bar is an application software sub-process call instruction, the virtual animation robot calls the corresponding application software sub-process, opens the corresponding application software, and after the internal process of the application software is executed, the virtual animation robot ends the current voice interaction.

[0011] In a preferred embodiment of the present invention, when a customer enters a hotel room and inserts a room card into a room card slot, the television terminal automatically identifies the customer's check-in information.

[0012] In a preferred embodiment of the present invention, the voice instruction library has a Mandarin accent recognition function to ensure that the pinyin of the text string is correct.

[0013] In a preferred embodiment of the present invention, the speech analysis module has word slot groups obtained by grouping according to parts of speech, and the word slot lexicon under all word slot groups stores Chinese text strings and full pinyin spellings respectively.

[0014] In a preferred embodiment of the present invention, during the speech analysis process, the speech information obtained by approximate sound recognition needs to be compared with the word slot lexicon under different part-of-speech groups in the order of verb->scenario mode->noun, and then compared twice in the order of Chinese text string->pinyin full spelling.

[0015] In a preferred embodiment of the present invention, when the customer is required to specify multiple parameters based on the acquired voice information, the virtual animation robot pushes the equipment and parameter information supported by the system to the customer as dialogue information.

[0016] In a preferred embodiment of the present invention, the television terminal automatically memorizes the context of the customer's communication and dialogue with the virtual animation robot at the same time, and extracts the instruction operation object, operation parameters, and operation behavior specific information therefrom, and combines them to obtain the final complete execution instruction.

[0017] In a preferred embodiment of the present invention, the execution status of all instructions extracted from the user voice information is recorded, and more basic word slots are supplemented and learned based on the maintenance of the system user feedback module and the knowledge base management module.

[0018] In a preferred embodiment of the present invention, when the corresponding device executes instructions and the corresponding application software executes internal processes, the virtual animation robot feeds back all links of the execution process to the customer in the form of voice.

[0019] Compared with the prior art, the beneficial effects of the present invention are: customers can communicate with the intelligent robot through voice throughout the whole process, and complete the control of the system itself, applications within the system, and smart devices in the room; it supports the original menu navigation interaction mode and the full intelligent robot mode at the same time, and users can switch the interaction mode at will by issuing commands. It is very friendly to users of all ages and reduces user learning costs; the innovative approximate sound analysis mode and command analysis mode help the intelligent robot better understand the user's intentions, so as to achieve accurate recognition of the user's voice and intention identification; the intelligent robot replaces the hotel waiter to respond to user needs in a timely manner, improve hotel service efficiency, and save labor costs.

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the embodiments of the present invention are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is a schematic diagram of the process of the hotel room intelligent management method of the present invention;

[0023] Figure 2 It is a system schematic block diagram of the hotel room intelligent management method of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Please refer to Figure 1 and Figure 2 The present invention provides a hotel room intelligent management method, comprising: when a customer enters a hotel room, a TV terminal automatically senses and starts, and a TV screen displays a virtual animation robot interacting with the customer by voice; the voice interaction comprises at least the following steps:

[0027] S1. The customer inputs voice information into the voice command library through the remote control microphone array;

[0028] S2, the voice instruction library parses the voice information into a text string through a voice parsing module;

[0029] S3, the voice instruction library determines the type of the text string;

[0030] S4. If the type of the text string is a question-and-answer type, the virtual animation robot matches the answer information piece from the question-and-answer library and feeds back the answer information piece to the customer in the form of voice; if the type of the text string is an instruction type, the virtual animation robot matches the instruction information piece from the instruction library;

[0031] S5. If the instruction information bar is an end instruction, there is no need to enter the sub-process, and the virtual animation robot ends the current voice interaction; if the instruction information bar is a device control sub-process call instruction, the virtual animation robot calls the corresponding device control sub-process, controls the corresponding device according to the instruction, and then ends the current voice interaction; if the instruction information bar is an application software sub-process call instruction, the virtual animation robot calls the corresponding application software sub-process, opens the corresponding application software, and after the internal process of the application software is executed, the virtual animation robot ends the current voice interaction.

[0032] In the present invention, the TV screen is used as the display medium, and the voice library is used to analyze the user's voice through the voice library and fully convey it to the virtual character. The virtual butler is controlled to accurately understand the user's intention and communicate with the user in real time. At the same time, the user's demand response is completed, the instant response speed of hotel services is improved, and the customer's one-to-one butler-style intimate service living experience is completed. The present invention integrates a microphone array (far and near field sound collection), a proprietary voice library, an intelligent robot animation library, a cloud server, system applications (including copyrighted audio and video APK and proprietary online mall applications), and intelligent devices. It realizes the collection of user voice needs through a microphone array, the recognition of user intentions through the cloud server operation voice library, and the complete communication to the intelligent robot. The intelligent robot has a self-learning function, and the intelligent butler responds and guides the user's needs through voice and animation. After communicating with the user's voice response, the user's intention is fully understood and conveyed to the corresponding device or application to complete the response.

[0033] In the present invention, the system determines the command type of the voice according to the received voice string information through the command matching rules of its own voice library. For example, if the voice information is "I am hungry", the full spelling "wo e le" is obtained. Then the text strings "I am hungry" and "wo e le" are used to match with different part-of-speech word slots in the system knowledge base. The word "hungry" is found to be successfully matched in the scene mode part-of-speech word slot library. According to the established rules, the voice operation object is obtained as the ordering section of the system.

[0034] In the present invention, the proprietary voice library includes: a word slot management platform, an audio approximation management API program, an instruction composition analysis API program, a question and answer knowledge base management platform, etc. The word slot management platform stores and manages different types of vocabulary and the meanings of vocabulary; the audio approximation management processes and analyzes different pronunciation habits of different groups of people to obtain the real intention audio information; the instruction composition analysis program arranges and combines the user audio string according to the rules to obtain the intention instruction; the question and answer knowledge base management platform maintains the commonly used scenario questions and answers and the self-learning user's voice information.

[0035] The intelligent animation library includes: hotel room scene library, intelligent robot animation library, and intelligent robot related instruction library. The intelligent robot compares the instructions transmitted by the voice library with the related instruction library to determine the relevant scenes. At the same time, according to the specific instructions and scenes, it analyzes whether it needs to communicate with the user, completes the call of the animation library and controls the system applications and smart devices.

[0036] In the present invention, the audio similarity recognition process of speech information is as follows:

[0037] 1) Convert user voice information into text strings through third-party tools;

[0038] 2) Convert the text string of the voice information into the full pinyin;

[0039] 3) According to the pronunciation rules of various dialects, the full pinyin of the text is expanded to obtain the full pinyin of different dialect pronunciation habits, such as the pronunciation of H and F in some areas;

[0040] 4) Compare the full pinyin spelling of the dialect pronunciation habits with the pinyin word slot library to obtain the user's possible pronunciation combinations.

[0041] In the present invention, the voice command composition analysis includes:

[0042] 1) Group word slots in full scene mode according to part of speech

[0043] 2) The word slot word library under all word slot groups stores Chinese text strings and pinyin spellings respectively

[0044] 3) Compare the user pronunciation combinations obtained by approximate sound recognition with the word slot lexicon under different parts of speech groups in the order of verb -> scenario mode -> noun. Perform two comparisons in the order of Chinese text string -> full pinyin.

[0045] 4) If the comparison result is obtained in step 3), the command nature of the user's voice can be obtained according to the existing rules. If the comparison does not obtain a matching result, it means that the obtained user voice information does not belong to a voice command.

[0046] In the present invention, the user intention recognition function and the robot dialogue self-learning process are specifically as follows:

[0047] 1) To obtain the voice information of command nature, analyze and obtain the user's actual intention according to the operating devices and operating parameters corresponding to the word slots in the system knowledge base.

[0048] 2) When the user is required to specify multiple parameters based on the acquired voice information, the robot pushes the device and parameter information supported by the system to the user as dialogue information.

[0049] 3) Automatically memorize the context of the user's communication with the robot during the same conversation, and extract the device and specific parameter information from it to obtain the final execution instructions.

[0050] 4) The execution status of all instructions extracted from user voice is recorded, and more basic word slots are supplemented and learned based on the maintenance of the system user feedback module and the knowledge base management module.

[0051] In an optional embodiment of the present invention, the television terminal senses and identifies the customer through a thermal infrared human body sensor.

[0052] In an optional embodiment of the present invention, when the corresponding device executes instructions and the corresponding application software executes internal processes, the virtual animation robot feeds back all links of the execution process to the customer in the form of voice.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A hotel room intelligent management method, characterized in that: include: When a customer enters a hotel room and inserts the room card into the room card slot, the TV terminal automatically recognizes the customer's check-in information, the TV terminal automatically senses and starts, and the TV screen displays a virtual animation robot interacting with the customer by voice; the voice interaction includes at least the following steps: S1. The customer inputs voice information into the voice command library through the remote control microphone array; S2, the voice instruction library parses the voice information into a text string through a voice parsing module, the voice parsing module has a word slot group obtained after grouping according to parts of speech, and the word slot word library under all word slot groups stores Chinese text strings and pinyin full spelling respectively; S3, the voice instruction library determines the type of the text string; S4. If the type of the text string is a question-and-answer type, the virtual animation robot matches a response information piece from the question-and-answer library and feeds back the response information piece to the customer in the form of voice; if the type of the text string is an instruction type, the virtual animation robot matches an instruction information piece from the instruction library; S5. If the instruction information bar is an end instruction, there is no need to enter the sub-process, and the virtual animation robot ends the current voice interaction; if the instruction information bar is a device control sub-process call instruction, the virtual animation robot calls the corresponding device control sub-process, controls the corresponding device according to the instruction, and then ends the current voice interaction; if the instruction information bar is an application software sub-process call instruction, the virtual animation robot calls the corresponding application software sub-process, opens the corresponding application software, and after the internal process of the application software is executed, the virtual animation robot ends the current voice interaction.

2. The hotel room intelligent management method according to claim 1, characterized in that: The voice instruction library has a Mandarin accent recognition function to ensure that the pinyin of the text string is correct.

3. The hotel room intelligent management method according to claim 2, characterized in that: During speech analysis, the speech information obtained by approximate sound recognition needs to be compared with the word slot lexicon under different part-of-speech groups in the order of verb->scenario mode->noun, and then compared twice in the order of Chinese text string->pinyin full spelling.

4. The hotel room intelligent management method according to claim 3, characterized in that: When the customer needs to specify multiple parameters according to the acquired voice information, the virtual animation robot pushes the device and parameter information supported by the system to the customer as dialogue information.

5. The hotel room intelligent management method according to claim 4, characterized in that: The television terminal automatically memorizes the context of the client's communication and dialogue with the virtual animation robot at the same time, and extracts the instruction operation object, operation parameters, and specific information of the operation behavior therefrom, and combines them to obtain the final complete execution instruction.

6. The hotel room intelligent management method according to claim 5, characterized in that: The execution status of all instructions extracted from user voice information is recorded, and more basic word slots are supplemented and learned based on the maintenance of the system user feedback module and the knowledge base management module.

7. The hotel room intelligent management method according to claim 1, characterized in that: When the corresponding device executes instructions and the corresponding application software executes internal processes, the virtual animation robot will feedback all links of the execution process to the customer in the form of voice.

Images