Human-computer interaction method based on AI assistant in digital audio-visual place, medium and equipment

Abstract

The invention discloses a man-machine interaction method based on an AI assistant in a digital audio-visual place, a medium and equipment, and the method comprises the steps: receiving an identification instruction of a user side identification code, and obtaining user information which comprises user identification information and position information of the digital audio-visual place where a current user is located; and receiving demand content input by the user side, performing semantic analysis on the demand content by the AI assistant, outputting response content, and executing a corresponding operation instruction according to the response content. According to the scheme, the AI assistant is introduced to interact with the user, the response content can be output after semantic analysis is conducted on the demand content input by the user in real time, the response content comprises the user information, timely service can be provided for the current user according to the user information and the response content, and the user experience is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent interaction in digital audio-visual venues, and specifically to a human-computer interaction method, medium and device based on an AI assistant in a digital audio-visual venue. Background Art

[0002] At present, singing in digital audio-visual venues has become a part of people's leisure and entertainment life. In digital audio-visual venues, people can order songs according to their preferences or call the front desk for merchandise services. However, currently, adding songs to sing requires users to operate one by one, and calling the front desk service also requires users to manually press the service bell before the front desk responds. When the user's needs are vague, the existing equipment in digital audio-visual venues cannot provide users with corresponding customized services, which brings a bad experience to users. Summary of the invention

[0003] In view of the above problems, the present application provides a technical solution for human-computer interaction based on AI assistant in digital audio-visual venues to solve the technical problem that the equipment in existing digital audio-visual venues cannot provide users with corresponding customized services, giving users a poor experience.

[0004] To achieve the above-mentioned purpose, in a first aspect, the present application provides a human-computer interaction method based on an AI assistant in a digital audio-visual place, wherein an identification code is provided in the digital audio-visual place, and the method comprises:

[0005] Receiving an identification instruction of the identification code from the user terminal, and acquiring user information, wherein the user information includes user identification information and location information of the digital audio-visual place where the current user is located;

[0006] Receiving the demand content input by the user end, the AI ​​assistant performs semantic analysis on the demand content and outputs response content, wherein the response content includes the user information;

[0007] Execute corresponding operation instructions according to the response content.

[0008] Furthermore, the demand content is inputted in voice or text form;

[0009] The receiving demand content input by the user end, the AI ​​assistant performs semantic analysis on the demand content, and outputs the response content including:

[0010] When the user inputs the required content by voice, the AI ​​assistant converts the voice information into text information after receiving it, and then performs semantic analysis on the text information and outputs the response content.

[0011] Furthermore, before receiving the demand content input by the user, the method further includes:

[0012] When it is detected that the acceleration of the user terminal is greater than a preset acceleration, the AI ​​assistant is started.

[0013] Furthermore, the demand content includes a budget amount and shopping demand, and the location information of the digital audio-visual venue where the current user is located includes box ID information;

[0014] The AI ​​assistant performs semantic analysis on the demand content, outputs response content, and executes corresponding operation instructions according to the response content, including:

[0015] The AI ​​assistant calls the product recommendation engine to recommend a product combination to the user terminal according to the shopping needs and the budget amount, and after receiving the product confirmation instruction from the user terminal, adds the product confirmed by the user terminal to the list to be paid;

[0016] After receiving the payment completion instruction from the user terminal for the goods in the to-be-paid list, all the goods information in the list and the box ID information are sent to the front desk terminal.

[0017] Furthermore, the method comprises:

[0018] The AI ​​assistant displays the total amount of goods in the current list to be paid in real time, and issues a first prompt message when the difference between the total amount of goods and the budget amount is within a preset error range.

[0019] Furthermore, the method further comprises:

[0020] Synchronize the box ID information and shopping order number to the food delivery robot;

[0021] After the food delivery robot verifies the shopping order number, it transports the goods placed on the food delivery robot to the digital audio-visual place corresponding to the box ID information. After the food delivery robot arrives at the destination, it sends a second prompt message to the relevant equipment in the corresponding digital audio-visual place. The second prompt message is used to prompt that the shopping goods have arrived.

[0022] Further, the demand content includes location information;

[0023] The AI ​​assistant performs semantic analysis of the demand content including:

[0024] The AI ​​assistant performs semantic analysis on the demand content, and determines the box ID information to which the user's shopping items will be delivered based on the box ID information of the current user and the location information contained in the demand content.

[0025] Furthermore, the AI ​​assistant performs semantic analysis on the demand content, outputs response content, and executes corresponding operation instructions according to the response content, including:

[0026] The AI ​​assistant receives the user's demand content for adjusting the operating parameters of relevant equipment in the current digital audio-visual venue, generates corresponding operation instructions according to the demand content, and stores the operation instructions in the message queue;

[0027] The AI ​​assistant sends the operation instructions in the message queue to the relevant equipment in the current digital audio-visual venue through the API gateway, so that the relevant equipment in the current digital audio-visual venue adjusts the operating parameters according to the operation instructions.

[0028] In a second aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the human-computer interaction method based on an AI assistant in a digital audio-visual venue as described in the first aspect of the present application.

[0029] In a third aspect, the present application provides an electronic device having a computer program stored thereon, including a processor and a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by the processor, the human-computer interaction method based on an AI assistant in a digital audio-visual venue as described in the first aspect of the present application is implemented.

[0030] Different from the prior art, the above technical solution involves a human-computer interaction method, medium and device based on an AI assistant in a digital audio-visual venue. The method includes: receiving an identification instruction of a user-side identification code, obtaining user information, and the user information includes user identification information and location information of the digital audio-visual venue where the current user is located; receiving the demand content input by the user, the AI ​​assistant performs semantic analysis on the demand content, outputs response content, and executes corresponding operation instructions according to the response content. By introducing an AI assistant to interact with the user, the above solution can perform semantic analysis on the demand content input by the user in real time, and output response content, and the response content contains user information, and can provide timely services to the current user according to the user information and response content, effectively improving the user experience.

[0031] The above-mentioned records related to the invention content are only an overview of the technical solution of the present application. In order to enable ordinary technicians in the field to more clearly understand the technical solution of the present application, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned purpose and other purposes, features and advantages of the present application easier to understand, the following is an explanation in combination with the specific implementation mode and drawings of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The drawings are only used to illustrate the principles, implementation methods, applications, characteristics and effects of the specific embodiments of the present invention and other related contents, and shall not be considered as limiting the present application.

[0033] In the drawings of the specification:

[0034] Figure 1 This is a flow chart of the human-computer interaction method based on an AI assistant in a digital audio-visual venue described in the first exemplary embodiment of the present application;

[0035] Figure 2 This is a flow chart of a human-computer interaction method based on an AI assistant in a digital audio-visual venue according to a second exemplary embodiment of the present application;

[0036] Figure 3 This is a flow chart of a human-computer interaction method based on an AI assistant in a digital audio-visual venue as described in the third exemplary embodiment of the present application;

[0037] Figure 4 This is a flow chart of a human-computer interaction method based on an AI assistant in a digital audio-visual venue as described in the fourth exemplary embodiment of the present application;

[0038] Figure 5 This is a flow chart of a human-computer interaction method based on an AI assistant in a digital audio-visual venue as described in the sixth exemplary embodiment of the present application;

[0039] Figure 6 A schematic diagram of the location of a box involved in an exemplary embodiment of the present application;

[0040] Figure 7 A schematic diagram of an electronic device according to an exemplary embodiment of the present application;

[0041] The reference numerals in the above drawings are described as follows:

[0042] 10. Electronic equipment;

[0043] 101. Processor;

[0044] 102. Storage medium. DETAILED DESCRIPTION

[0045] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0046] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0047] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0048] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0049] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0050] Without further limitations, in this application, the words "include", "comprises", "has" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0051] In this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0052] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0053] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms such as "install", "connect", "connect", "fix", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For technicians in the technical field to which the present application belongs, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0054] In a first aspect, the present application provides a human-computer interaction method based on an AI assistant in a digital audio-visual venue, such as Figure 1 As shown, the digital audio-visual venue is provided with an identification code, and the method comprises:

[0055] Step S101: receiving an identification instruction of the identification code from the user terminal, and acquiring user information, wherein the user information includes user identification information and location information of the digital audio-visual place where the current user is located;

[0056] Step S102: receiving the demand content input by the user end, the AI ​​assistant performs semantic analysis on the demand content, and outputs response content, wherein the response content includes the user information;

[0057] Step S103: executing corresponding operation instructions according to the response content.

[0058] In step S101, the digital audio-visual place may be a KTV, a karaoke room, a home karaoke machine, etc. The identification code may be presented in the form of a barcode, a QR code, or a mini-program identification code. Specifically, the identification code may be placed at any location in the digital audio-visual place, such as a table, a door, a display device, etc. In other embodiments, the digital audio-visual place involved in the present application may also be applied to an electronic music DJ box, a script-killing box, or a cinema hall, etc. In short, as long as it is a box that can support offline playback of video streaming data, it is applicable to the method involved in the present application.

[0059] The user terminal can be a mobile phone, tablet, etc. of the user. The user terminal can identify the identification code by scanning. When the identification code is identified, in addition to establishing a communication connection with the system, the system can also collect user information corresponding to the user terminal. The user's identification information may include the user's name, bound mobile phone number, whether the user is a member (if so, the member number may also be included), ID number, etc. The location information of the digital audio-visual venue where the current user is located may be the room number (such as the box ID) or the geographic coordinate location of the digital audio-visual venue where the current user is located.

[0060] In step S102, the demand content input by the user can be a clear demand, such as "I need xx", or a more vague demand, such as "I want xx now, can you recommend it to me?". The AI ​​assistant is an AI robot that can understand the user's intention and interact with the user. It can be implemented using an AI big model. The AI ​​assistant performs semantic analysis on the demand content input by the user and outputs the response content.

[0061] In step S103, for example, when the user expresses a need for a service ring, the corresponding operation instruction is to automatically call a service ring in the digital audio-visual place where the current user is located.

[0062] The above solution introduces an AI assistant to interact with users. It can perform semantic analysis on the user's input content in real time and output response content, which contains user information. The AI ​​assistant can directly connect to the offline service system and package and transmit user needs, box ID, user identification information, etc. directly to the server. The server and the user are in the same area (for example, the server is at the front desk, and the user is in the box). Therefore, it can directly provide services to the user according to the user's needs, effectively improving the user experience.

[0063] In some embodiments, the demand content is inputted by voice or text. The receiving of the demand content inputted by the user terminal, the AI ​​assistant performing semantic analysis on the demand content, and outputting the response content comprises: when the user terminal inputs the demand content by voice, the AI ​​assistant converts the voice information into text information after receiving it, and then performs semantic analysis on the text information and outputs the response content.

[0064] In short, the user's demand content can be input in text or voice. When the user inputs the demand content in voice, the AI ​​assistant will first convert the user's voice information into text information and then analyze it, and then output the response content according to the analysis results. By setting the voice interaction method, user operation can be facilitated.

[0065] In some embodiments, before receiving the required content input by the user terminal, it also includes: when it is detected that the acceleration of the user terminal is greater than a preset acceleration, starting the AI ​​assistant.

[0066] In short, in order to prevent users from operating incorrectly, after recognizing the identification code, they can also wake up the AI ​​assistant through the "shake" function. Taking the user end as a mobile phone as an example, when the user shakes the phone, the built-in acceleration sensor of the mobile phone will collect the acceleration data of the mobile phone in three-dimensional space in real time. These data include acceleration values ​​in the three directions of x-axis, y-axis, and z-axis, which represent the horizontal movement, vertical movement, and vertical movement of the mobile phone in space. When it is detected that the acceleration of the user end is greater than the preset acceleration, the AI ​​assistant is started.

[0067] In some embodiments, the demand content includes a budget amount and shopping needs, and the location information of the digital audio-visual venue where the current user is located includes box ID information.

[0068] like Figure 2 As shown, the AI ​​assistant performs semantic analysis on the demand content, outputs response content, and executes corresponding operation instructions according to the response content, including:

[0069] Step S201: the AI ​​assistant calls the product recommendation engine to recommend a product combination to the user terminal according to the shopping demand and the budget amount, and after receiving the product confirmation instruction from the user terminal, adds the product confirmed by the user terminal to the list to be paid;

[0070] Step S202: after receiving the payment completion instruction from the user terminal for the goods in the to-be-paid list, all the goods information in the list and the box ID information are sent to the front-end terminal.

[0071] In this embodiment, the front desk terminal is the merchant service end operating the current digital audio-visual venue. Usually, snack and alcohol shops are set up at the front desk of the digital audio-visual venue to facilitate consumers to buy and improve the business efficiency. However, the existing business model relies on users to go to the front desk shop to buy after they have clear needs. When many users do not want to leave the box or the needs are unclear, this part of the consumption potential will be suppressed. If the solution of this application is adopted, the user only needs to talk to the AI ​​assistant, and the AI ​​assistant is interconnected with the product recommendation engine. The corresponding products will be presented directly to the user in the dialog box, and after the user completes the payment, the AI ​​assistant can send the product information and user information purchased by the user (including the user ID of the order and the box ID) directly to the front desk, so that the front desk can prepare the goods in time, thereby providing users with better and timely services.

[0072] And because it is an AI assistant that interacts with the user, it can not only place orders for the drinks and meals specified by the user and have them delivered to the box, but also make product recommendations for the user's specific needs when the user's needs are unclear.

[0073] In some embodiments, the method includes: the AI ​​assistant displays the total amount of goods in the current list to be paid in real time, and issues a first prompt message when the difference between the total amount of goods and the budget amount is within a preset error range.

[0074] For example, the user input requirement may be "My budget today is about 800, please help me order some drinks, fruit plates and hot dishes", then when the AI ​​assistant recommends products to the user, it can recommend some drinks, fruit plates and hot dishes in combination, or recommend drinks, fruit plates and hot dishes to the user one by one according to the category. When each item is added to the current list to be paid, the total price of the item to be paid will be displayed in real time to give the user a psychological expectation. When the total price is detected to be close to 800, the first prompt message will be issued to let the user know that the current number of added items is sufficient and remind the user to pay.

[0075] Furthermore, the AI ​​assistant can also be interconnected with the equipment in the box, so the first prompt information can also be presented in the display device in the box, and can also be presented through different effects such as lighting equipment, audio equipment, etc. in the box.

[0076] In some embodiments, Figure 3 As shown, the method also includes:

[0077] Step S301: Synchronize the box ID information and the shopping order number to the food delivery robot;

[0078] Step S302: After the food delivery robot verifies the shopping order number, it transports the goods placed on the food delivery robot to the digital audio-visual place corresponding to the box ID information, and after the food delivery robot arrives at the destination, it sends a second prompt message to the relevant equipment in the corresponding digital audio-visual place, and the second prompt message is used to prompt that the shopping goods have arrived.

[0079] In short, in order to further liberate manual labor and improve meal delivery efficiency and user experience, after the front desk prepares the goods purchased by the user, the food delivery robot can deliver the goods purchased by the user. The food delivery robot can directly obtain the destination box location corresponding to the goods to be transported through the AI ​​assistant. When a food delivery robot has multiple destination box locations for the goods to be transported, these locations can be stored in the message queue in sequence, and then the goods can be delivered in sequence according to the number of times. You can also scan the QR code on the shopping receipt to verify the user's order number and user information, and deliver the goods after the verification is correct. Specifically, after each user payment is completed, a unique order number for this transaction will be generated, and the order number is also bound to the box ID. The food delivery robot can scan the shopping receipt to compare the scanned box ID and order number with the box ID and order number previously received from the AI ​​assistant. If the match is successful, the goods will be delivered.

[0080] The second prompt information can also be presented on a display device in the box, or can be presented by displaying different effects through lighting equipment, audio equipment, etc. in the box.

[0081] In some embodiments, the demand content includes location information; the AI ​​assistant performs semantic analysis on the demand content, including: the AI ​​assistant performs semantic analysis on the demand content, and determines the box ID information to which the shopping goods of the user terminal are to be delivered based on the box ID information of the current user terminal and the location information contained in the demand content.

[0082] In short, through the AI ​​assistant, users can not only purchase goods for the digital audio-visual venue where they are currently located, but also a user can use the AI ​​assistant to purchase goods for the user in the next box. For example, the user can specify "order a box of drinks for the box to the left of the current box", and the front desk terminal will respond after the user completes the payment. In order to avoid user operation errors, taking KTV as an example, when the user inputs the demand content containing direction information, the user can also be presented with the current KTV box guide map in the dialog box, and the box where the current user is located can be specially marked.

[0083] like Figure 6As shown, the current box is box-6. When maintaining the box information, you can add the box information in the four directions of A, B, C, and D of a certain floor to save the box space layout in the KTV. For example, the D direction of box-1 is box-2, and the other directions are empty; the A direction of box-2 is box-1, the B direction is empty, the C direction is box-5, the D direction is box-3, and so on. When the user inputs the demand content including "adjacent boxes", the AI ​​assistant will give priority to recommending the most adjacent boxes, namely box-3, box-5 and box-7, followed by box-1, box-2, box-4,

[0084] In some embodiments, Figure 4 As shown, the AI ​​assistant performs semantic analysis on the demand content, outputs response content, and executes corresponding operation instructions according to the response content, including:

[0085] Step S401: The AI ​​assistant receives the user's demand content for adjusting the operating parameters of relevant equipment in the current digital audio-visual venue, generates corresponding operation instructions according to the demand content, and stores the operation instructions in the message queue;

[0086] Step S402: The AI ​​assistant sends the operation instructions in the message queue to the relevant equipment in the current digital audio-visual venue through the API gateway, so that the relevant equipment in the current digital audio-visual venue adjusts the operating parameters according to the operation instructions.

[0087] For example, user A enters the box and scans the mini program code (i.e., identification code) in the box. After the scan is successful, the system will obtain the user information and box information. Then user A can shake the phone to wake up the AI ​​assistant and use text or voice to input the required content. For example, you can send a command to the AI ​​assistant: "Help me turn on the headlights." The AI ​​assistant understands the command entered by the user and sends it to the box lighting control system through the API gateway and message queue. The box lighting control system executes the corresponding command and turns on the box headlights. Through the interaction between the AI ​​assistant and the user, it is convenient for the user to adjust the operating parameters of the relevant equipment in the current box, thereby improving the user experience. The relevant equipment may be a song request machine (the user can directly interact with the AI ​​assistant to request or change songs), air conditioning (the user can directly interact with the AI ​​assistant to adjust the temperature), audio equipment (the user can directly interact with the AI ​​assistant to adjust the volume or sound effects), lighting equipment (the user can directly interact with the AI ​​assistant to adjust the lighting effects), etc.

[0088] like Figure 5 As shown, one of the purposes of this application is to encourage users to complete consumption through AI assistants and realize a closed loop from intelligent product recommendations to user consumption.

[0089] For example, a user can place an order and obtain a product by sending a fuzzy command to an AI assistant. The specific steps include the following:

[0090] (1) User A enters the box and scans the mini program code in the box (the system obtains user information and box information at this time);

[0091] (2) Shake the phone to wake up the AI ​​assistant, and send a vague instruction to the AI ​​assistant using text or voice: "My budget for ordering today is 500 yuan. Please help me choose a few items."

[0092] (3) The AI ​​assistant understands the instructions input by the user and, based on the instructions and the product recommendation engine, recommends single products or combination packages to the user;

[0093] (4) The user selects the item or set meal they like from the recommendation list in the AI ​​assistant dialog box and adds it to the shopping cart with one click. The assistant calculates the order amount in the shopping cart in real time and reminds the user;

[0094] (5) After the user completes the product selection, the assistant confirms the product box to the user, and the user confirms the order and pays;

[0095] (6) The order information is sent to the offline management system through the API gateway and message queue. After receiving the information, the offline management system delivers the ordered goods to the corresponding box and notifies the offline supermarket to ship the goods;

[0096] (7) Offline supermarkets sort goods and have waiters / robots deliver the goods to the private rooms, and ring a service bell or a TV screen to remind customers that the food has arrived.

[0097] In a second aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the human-computer interaction method based on an AI assistant in a digital audio-visual venue as described in the first aspect of the present invention.

[0098] The computer-readable storage medium may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories.

[0099] The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD ROM); the magnetic surface memory can be a disk memory or a tape memory.

[0100] The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), direct memory bus random access memory (DRRAM). The computer-readable storage medium described in the embodiments of the present invention is intended to include these and any other suitable types of memory.

[0101] like Figure 7 As shown, in a third aspect, the present invention provides an electronic device 10, comprising a processor 101 and a storage medium 102, on which a computer program is stored, and when the computer program is executed by the processor, the human-computer interaction method based on an AI assistant in a digital audio-visual place as described in the first aspect of the present invention is implemented.

[0102] In some embodiments, the processor can be implemented by software, hardware, firmware or a combination thereof, and can use circuits, single or multiple application specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processors (Digital Signal Processor, DSP), digital signal processing devices (Digital Signal Processing Device, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), central processing units (Central Processing Unit, CPU), controllers, microcontrollers, microprocessors, at least one of which, so that the processor can execute some or all of the steps or any combination of the steps in the human-computer interaction method based on AI assistant in the digital audio-visual place described in the various embodiments of the present application.

[0103] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A human-computer interaction method based on an AI assistant in a digital audio-visual venue, characterized in that: The digital audio-visual venue is provided with an identification code, and the method comprises: Receiving an identification instruction of the identification code from the user terminal, and acquiring user information, wherein the user information includes user identification information and location information of the digital audio-visual place where the current user is located; Receiving the demand content input by the user end, the AI ​​assistant performs semantic analysis on the demand content and outputs response content, wherein the response content includes the user information; Execute corresponding operation instructions according to the response content.

2. The human-computer interaction method based on an AI assistant in a digital audio-visual venue as claimed in claim 1, characterized in that: The demand content includes the budget amount and shopping demand, and the location information of the digital audio-visual venue where the current user is located includes the box ID information; The AI ​​assistant performs semantic analysis on the demand content, outputs response content, and executes corresponding operation instructions according to the response content, including: The AI ​​assistant calls the product recommendation engine to recommend a product combination to the user terminal according to the shopping needs and the budget amount, and after receiving the product confirmation instruction from the user terminal, adds the product confirmed by the user terminal to the list to be paid; After receiving the payment completion instruction from the user terminal for the goods in the to-be-paid list, all the goods information in the list and the box ID information are sent to the front-end terminal.

3. The human-computer interaction method based on AI assistant in a digital audio-visual place according to claim 2, characterized in that: The method comprises: The AI ​​assistant displays the total amount of the goods in the current list to be paid in real time, and issues a first prompt message when the difference between the total amount of the goods and the budget amount is within a preset error range.

4. The human-computer interaction method based on AI assistant in a digital audio-visual place according to claim 2, characterized in that: The method further comprises: Synchronize the box ID information and shopping order number to the food delivery robot; After the food delivery robot verifies the shopping order number, it transports the goods placed on the food delivery robot to the digital audio-visual place corresponding to the box ID information. After the food delivery robot arrives at the destination, it sends a second prompt message to the relevant equipment in the corresponding digital audio-visual place. The second prompt message is used to prompt that the shopping goods have arrived.

5. The human-computer interaction method based on AI assistant in a digital audio-visual venue as claimed in claim 2, characterized in that: The demand content includes location information; The AI ​​assistant performs semantic analysis of the demand content including: The AI ​​assistant performs semantic analysis on the demand content, and determines the box ID information to which the user's shopping items will be delivered based on the box ID information of the current user and the location information contained in the demand content.

6. The human-computer interaction method based on AI assistant in a digital audio-visual place according to claim 1, characterized in that: The AI ​​assistant performs semantic analysis on the demand content, outputs response content, and executes corresponding operation instructions according to the response content, including: The AI ​​assistant receives the user's demand content for adjusting the operating parameters of relevant equipment in the current digital audio-visual venue, generates corresponding operation instructions according to the demand content, and stores the operation instructions in the message queue; The AI ​​assistant sends the operation instructions in the message queue to the relevant equipment in the current digital audio-visual venue through the API gateway, so that the relevant equipment in the current digital audio-visual venue adjusts the operating parameters according to the operation instructions.

7. The human-computer interaction method based on AI assistant in a digital audio-visual place according to claim 1, characterized in that: The demand content is inputted in voice or text form; The receiving demand content input by the user end, the AI ​​assistant performs semantic analysis on the demand content, and outputs the response content including: When the user inputs the required content by voice, the AI ​​assistant converts the voice information into text information after receiving it, and then performs semantic analysis on the text information and outputs the response content.

8. The human-computer interaction method based on AI assistant in a digital audio-visual venue as claimed in claim 1, characterized in that: Before receiving the required content input by the user, it also includes: When it is detected that the acceleration of the user terminal is greater than a preset acceleration, the AI ​​assistant is started.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the human-computer interaction method based on an AI assistant in a digital audio-visual venue as described in any one of claims 1 to 8 is implemented.

10. An electronic device having a computer program stored thereon, characterized in that: It includes a processor and a storage medium, wherein a computer program is stored on the storage medium, and when the computer program is executed by the processor, the human-computer interaction method based on an AI assistant in a digital audio-visual place as described in any one of claims 1 to 8 is implemented.

Images