Detailed Description
User information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in this disclosure are both user-authorized or fully authorized information and data by parties, and the collection, use and processing of relevant data requires compliance with relevant laws and regulations and standards of relevant countries and regions, and is provided with corresponding operation portals for user selection of authorization or denial.
Fig. 1 is a network architecture of a conventional wireless intercom system 100, and it can be seen that the intercom system is mainly characterized by allowing a plurality of users to access to a intercom host 20 for communication through intercom terminals (intercom terminals 10, intercom terminal 11..intercom terminal N) (intercom terminals may be, for example, a waist belt, an earphone, a microphone, a dispatcher station, an intercom, etc.). Wireless communication between each call terminal and the call host 20 is typically achieved by DECT technology (although other wireless lan communication technologies capable of implementing an intercom system, such as WIFI, bluetooth, etc., are not excluded). When the intercom system implements intercom by DECT technology, the usual intercom host 20 may be an RRU (Remote Radio Unit ).
In some scenarios, the call terminal may also be a device with only a wireless transceiver function, where the call terminal may be connected to a voice capturing and voice playing device, and configured to receive a voice signal captured by the voice capturing device, and then forward the voice signal to the call host 20, and be configured to receive a mixed signal sent by the call host 20, and play the mixed signal to a user through the voice playing device. For example, the call terminal may be a call waist pack, which may be connected to the headset. In other scenarios, the call terminal may be integrated with a microphone and an earphone, and the structure of the call terminal is not limited in this specification.
In general, a plurality of call terminals wirelessly connected with the call host 20 may be divided into one or more call packets, and a call may be implemented between call terminals within each call packet. Assuming that a call packet includes a call master 20 (BS) and 8 call terminals, since each call terminal only needs to hear the voice signals collected by other call terminals in the same call packet, it does not need to hear the voice signals collected by itself. Therefore, after each call terminal transmits the voice signal collected by itself to the call host, the call host 20 can mix the voice signals collected by other call terminals except the call terminal for each call terminal, and then issue the mixed voice signals to the call terminal. For example, the call host 20 receives the voice signal sent from the call terminal 10-call terminal 17, and for the call terminal 1, the voice signal sent from the call terminal 11-call terminal 17 may be subjected to a mixing process, and then the mixed signal is returned to the call terminal 10, so that the call terminal 10 plays the mixed signal through the microphone, that is, the user using the call terminal 10 can hear the speech of other users in the packet. Similarly, for other call terminals, the audio mixing signal of the call terminal can be obtained in a similar manner.
When the intercom system is applied to the scenario of the car restaurant, a conventional method may be described in connection with the car restaurant ordering system 2 of fig. 2, the intercom terminals in the intercom system may be divided into a plurality of communication groups according to lanes, and a plurality of dish makers and at least one ordering person may be bound to one lane. Each call terminal in the same group can receive the audio data collected by other call terminals in the group, so that the conversation between the ordering staff and the customer can be heard by the dishes making staff. The menu producer may also have a dialogue with the order taker.
After the customer 200 drives the car to the meal ordering point 202 of the lane 203, stopping running, sensing 201 by the underground sensor that the car is driven in, and sending prompt tones by headphones worn by the ordering person 204, the dish making person 205, the dish making person 206 and the dish making person 207;
the customer takes the microphone of the starting meal, and the ordering person 204 can talk with the customer 200 sitting in the car through the earphone to order the customer 200;
Dish maker 206 recommends order person 204 to promote xx dishes (which customer 200 cannot hear), and other staff turns off his microphone;
After the customer 200 has completed the order, the meal is taken away at meal order point 208.
It can be seen that current car restaurant ordering systems require the provision of specialized ordering personnel, and that each lane requires the provision of specialized ordering personnel when there is more than one lane. If the system can give various advantages of AI technology to the intercom system, the capability of the intercom system can be expanded, and the labor cost can be saved.
At present, AI (ARTIFICIAL INTELLIGENCE ) technology has been developed rapidly. AI may generally have learning, reasoning, self-correction, perception, language understanding, and problem solving capabilities. Artificial intelligence techniques have found wide application in a variety of fields including machine learning, natural language processing, computer vision, robotics, and the like. Communication with users through AI natural language processing techniques has been used in many applications. However, there is a technical obstacle in integrating the AI technology into the call terminal of the intercom system, and the call terminal of the intercom system is generally required to meet the requirement of low power consumption, while the function provided by the integrated AI technology has a higher requirement on the processing performance of the device, and the device cannot meet the requirement of low power consumption, so how to use the AI technology in the context of the intercom system is a problem to be solved urgently.
FIG. 3 is a network diagram of ordering system 30 of a car restaurant in one embodiment. The system comprises an intercom system 32 and an ordering device 31, wherein the intercom system 32 comprises at least one intercom terminal (an intercom terminal group 330 is shown in the figure as an example, and can be an intercom terminal 3331 and an intercom terminal 3322. The intercom terminal N) and at least one intercom host 321, the intercom system 32 and the ordering device 31 are communicated through the Internet 33, and the intercom terminals in the intercom system 32 and the intercom host 321 are communicated through a wireless local area network 34 (such as a local area network constructed by using a wireless protocol such as DECT and the like and are not enumerated here);
The processing chip installed on the ordering device 31 integrates an AI function, the ordering device 31 can perform voice interaction with a target object by using an AI technology, collect voice signals of the target object, generate audio data and order data based on the collected voice signals, send the audio data to the call host 321, and send the order data to the cloud server;
The call host 321 is a bridge for communicating between the devices located on the internet and the intercom system 32, and the call host 321 is connected to other devices outside the intercom system 32 through the internet 33, and is in internal communication with each call terminal or other call host inside the intercom system 32 through a wireless protocol of the intercom system 32. In order to transmit data from two different networks, the call host 321 transmits data from the internet 33 to each call terminal after protocol conversion when transmitting internet data to the intercom system 32, and transmits data from the intercom system 32 to the internet 33 after protocol conversion when transmitting data of the intercom system 32 to the internet. When there are a plurality of call hosts 321 in the intercom network, one of the call hosts 321 may act as a master and the other call hosts 321 may act as slaves.
Each call terminal in the intercom system 32 may collect local voice signals and generate audio data, send to the call host 321, and receive audio data from the call host 321.
As an example, ordering device 31 implements automatic speech recognition (Automatic Speech Recognition, ASR) and natural language processing (Natural Language Processing, NLP) using AI technology. The goal of ASR technology is to convert the lexical content in human speech into computer-readable input, while NLP technology aims at enabling computers to understand, interpret and generate human language. The ordering device automatically recognizes the collected voice signal of the customer into computer readable input through an ASR technology, so that the ordering device 31 can convert the voice signal into audio data capable of being transmitted through a network, and the ASR technology automatically recognizes the result to be used as a data source of NLP processing data, so that the ordering device 31 can understand the intention of the customer, such as inquiring a menu, ordering a menu and the like, and man-machine interaction is realized with the customer. The ordering device 31 in this specification can implement a multi-round conversation with a customer using NLP technology. The audio signals generated by the multiple rounds of conversations are sent to the conversation host 321, and then forwarded to other conversation terminals in the group by the conversation host 321, so that a user wearing the conversation terminal can perform voice interaction in time according to the heard voice.
Furthermore, based on some basic data (such as a user name, a license plate number, etc.) of the customer acquired by the ordering device 31, the historical data (such as dishes selected by the customer in a historical order, special tastes, order prices, etc.) of the customer can be analyzed by using a machine learning algorithm, user characteristic analysis can be performed on a target object, personalized data of the customer such as user preference, purchase history, etc. can be obtained, and based on the analysis result, personalized data such as recommending personalized dishes and packages to the customer can be pushed to the target object, so that user satisfaction and ordering efficiency can be improved. In addition, key indexes such as user behavior data and dish sales data can be collected and analyzed, and a dish recommendation algorithm is optimized, interface design is improved, system performance is improved and the like by utilizing a data analysis result. The function of analyzing the history data of the customer mentioned here may be integrated on the ordering device 31, or may be implemented by using a cloud server. When the function of analyzing the historical data of the user is implemented by the cloud server, the ordering device 31 may send audio data generated by one or more rounds of voice interaction to the cloud server through the call host 321, and then forward push data generated after the analysis by the cloud server to the ordering device 31.
The ordering device 31 can also be provided with an interactive interface for order payment, and the cloud server can also integrate order processing and payment functions, support various payment modes (such as code scanning payment, face recognition payment and the like) and facilitate a user to quickly complete payment. The order data can be sent to the cloud server, and the cloud server processes and completes order payment.
Since ordering device 31 and intercom system 32 are in communication established via internet 33, ordering device 31 and intercom host 321 may be provided with a wired or wireless network interface, as an example, through which both devices access the internet. In one embodiment, this network interface may be a POE (Power over Ethernet, intranet powered) network cable interface, which is a technology that enables simultaneous transmission of data signals and power over ethernet cables. This technology allows some IP-based devices to be supplied with dc power via a single ethernet cable, so that ordering device 31 may transmit audio data, order data, etc. and may also transmit a power signal via a POE cable interface, so that ordering device 31 may be powered without an external power source, and thus the placement position of ordering device 31 may not need to be considered as to whether it is close to the external power interface. Of course, powering of ordering device 31 by an external power source does not affect the implementation of the present invention.
In addition, the ordering device 31 may also include a detection unit, where the detection unit can sense whether a target object exists in the target area, and wake up or sleep the ordering device 31 based on whether the target object exists in the target area, so that power consumption of the ordering device can be saved. The type of the detection unit may be various, for example, may be a radar that senses whether a vehicle enters a target area, or may be an image pickup device that collects an image of the target area and determines whether a vehicle enters the target area through image recognition. The ordering device 31 may further have a dual microphone array including a main microphone and a sub-microphone, and the ordering device 31 may perform noise reduction processing on the voice signal based on the target voice collected by the main microphone and the environmental noise collected by the sub-microphone.
The ordering device 31 and the call host 321 can be directly connected, or can be connected through other relay devices. The embodiment of fig. 4 illustrates a car restaurant ordering system 30 further comprising a routing device 41 in communication with the ordering device 31 and the call host 321, respectively, via the internet 33. One of the functions of the routing device 41 is to expand the wiring distance between the ordering device 31 and the call hosts 321, and in addition, if more than one call host 321 is provided, if each call host 321 is connected with the routing device 41, the function of expanding the distance between the call hosts 321 can be achieved. The routing device may also function to forward data that the ordering device 31 interacts with the cloud server.
Another function is for the routing device 41 to assist in enabling roaming handoffs of individual telephony terminals between different telephony hosts 321. Since intercom system 32 may employ the DECT standard, DECT being a standard defined by ETSI, this technique is characterized by providing high quality, low delay voice services, supporting data communication services, supporting automatic lossless handover including carrier/slot switching due to deterioration of channel characteristics within the cell, and user mobility induced handoff. The call hosts 321 are limited in the number of connections based on the type of wireless technology used, so that a plurality of call hosts 321 may need to be disposed in the intercom system 32, each call host 321 may be networked in a cascade, daisy chain, or other manner, and in this scenario, the call hosts 321 are divided into master and slave devices. The call terminal can roam between different call hosts 321, and accurate clock synchronization between the master device and the slave device is required in order to achieve seamless roaming. Conventional intercom systems are generally based on bi-directional time synchronization of messages between a master device and a slave device. And the master device and the slave device calculate and obtain the total round trip time delay between the two devices according to the receiving and transmitting time stamps of the messages. In the present application, the routing device 41 may be connected to each call host 321 through the wired network interface 44, so as to expand the wiring distance between the call hosts 321, and simultaneously send a synchronous clock signal to each call host 321, thereby implementing roaming switching between different call hosts 321 for the call terminal.
It should be noted that in the context of film shots, stage shows, large-scale activities, etc., it is often necessary to utilize intercom system 32 to effect communication between on-site personnel to accomplish the organizational scheduling of the work. The technical idea of combining AI technology with intercom system 32 provided in the present specification is applicable not only in a car restaurant, but also in various intercom system 32, and thus fig. 5 of the present specification provides an example.
Fig. 5 is a schematic diagram of a call system 50 according to one embodiment of the present disclosure, where the intercom network 32 includes at least one call terminal (e.g., group of call terminals 330 shown in the figure) and at least one call host 321, and further includes a human-machine interaction device 51;
The man-machine interaction device 51 is capable of performing voice interaction with a target object by using an AI technology, collecting a voice signal of the target object, generating audio data based on the collected voice signal, and transmitting the audio data to the call host 321 through the internet 33;
The call host 321 may transmit data from the internet 33 to the call terminal after protocol conversion or transmit data from the internal call system 32 to the internet 33 after protocol conversion according to the data source and destination;
the call terminal may collect the voice signal and generate audio data, send the audio data to the call host 321, and receive the audio data sent by the call host 321.
The man-machine interaction device 51 may have functions to be equipped in various scenes according to different scenes applied, for example, for scenes requiring to be placed in an order, the man-machine interaction device 51 may generate order data based on the collected audio data, and send the order data to the cloud server through the internet 33. The order data may be generated in different scenarios, e.g., order data may include customer ordered dishes, quantity, special needs for the dishes, etc. For another example, in a medical facility such as a hospital, the man-machine interaction device 51 can interact with a patient to acquire a patient's voice signal, obtain data such as a dropping speed of infusion liquid medicine, feedback data of physical condition, and a remaining amount of liquid, and send the data to each call terminal group 330 through the call host 321, so as to realize quick communication between medical staff, and improve the efficiency and quality of patient nursing. The solution of generating orders in the scene similar to that of automobile restaurants can be realized by the patient through the man-machine interaction device 51.
Similarly, referring to the various solutions provided above for the application scenario of the car restaurant, the audio data generated by the voice interaction may enable the man-machine interaction device 51 or the cloud server to perform user feature analysis, and based on the analysis result, push personalized data to the target object. The order data in this specification is a generic term for data generated in different situations, and for example, real-time data when a patient feeds back infusion to a doctor may be considered as order data. The objective of user profiling and the personalized data pushed will also vary according to the type of order. Those skilled in the art can make and use the adaptive scene design in light of the embodiments disclosed in the present specification.
Similarly, to implement distance expansion, the call system may further include a routing device 41, which communicates with the man-machine interaction device 51 and the call host 321 through the internet 33, and the routing device 41 forwards data interacted by the man-machine interaction device 51 and the call host 321, and data interacted by the man-machine interaction device and the cloud server. In particular, in order to expand the layout distance between the respective call hosts 321, the routing device 41 may be connected to each call host 321. The routing device 41 and the call hosts 321, if connected through wired network interfaces (network interfaces 43, 44), the routing device 41 is also capable of implementing sending a synchronous clock signal to each call host 321, so that the call terminal roams and switches between different call hosts 321.
The man-machine interaction device 51 may also be connected to the routing device 41 or the call host 321 through a POE network cable interface (network interface 42 in the figure), so as to obtain a power supply signal without an external power supply.
In addition, the human-computer interaction device 51 may include a detection unit to wake up or sleep the human-computer interaction device 51 based on whether a target object exists in the target area or not, and the human-computer interaction device 51 may have a dual microphone array including a main microphone and a sub microphone to perform noise reduction processing on the voice signal based on the target voice collected by the main microphone and the environmental noise collected by the sub microphone.
In this specification, the call master 321 is a device in both the internet and the intercom system 32, and thus is different from the call master 321 of the conventional intercom system 32. The specific working principle of the device can be understood by referring to the technical schemes disclosed in the embodiments in the present specification, and the description thereof is omitted herein.
Embodiments of the present description are presented in greater detail below in conjunction with the application example of fig. 6.
In the communication system 60 in the figure, the man-machine interaction device 601, the routing device 602 and the plurality of communication hosts are all provided with wired network ports, the network interface 6014 of the man-machine interaction device 601 is a POE network port, the man-machine interaction device 601 is interconnected with the network interface 6021 of the routing device 602 through the POE network port (the network interface 6014 in the figure), and the routing device 602 is provided with a plurality of network ports, and besides being connected with the man-machine interaction device 601 in a wired manner, the man-machine interaction device is also connected with the network ports of the communication hosts through the network ports respectively. The master call master 603 is a master device, and the other call masters are slave devices (slave call master 606 in the figure). Each call host has a wireless module (wireless module 6032 and wireless module 6062 in the figure) to realize wireless connection with each call terminal, and an intercom system 611 is constructed.
The man-machine interaction device 601 is designed with a man-machine interaction interface GUI that is presented to the user through the display unit 6012. The man-machine interaction device 601 is provided with a processing chip 6013 integrated with a plurality of AI technologies, namely an ARM in the figure, and the man-machine interaction device 601 realizes the functions of collecting and playing voice signals through a microphone 6015 and an earphone 6011. In addition, the man-machine interaction device 601 is provided with a detection unit 6014, and the detection unit 6014 can be a radar device, a camera or the like, and whether the man-machine interaction device 601 needs to be awakened is determined by detecting whether a person exists in a target area. After the man-machine interaction device 601 is awakened, voice signals of a customer are collected, multiple rounds of interaction is carried out with the customer through an AI technology, order data are generated, and the interacted audio data and the order data are sent to the routing device 602 through a POE network port.
The routing device 602 sends the audio data to the master call host 603 and the slave call host 606 via the network interface 6022, and sends the order data to the cloud server via the network interface 6021. The master call host 603 distributes audio data to the locally bound talk terminal group 604 and the slave call host 606 distributes audio data to the locally bound talk terminal group 605. The routing device 602 may also send a clock synchronization signal to each connected call host, so as to implement seamless handover when the call terminal roams from the signal coverage area of the currently bound call host to the signal coverage area of another call host.
After receiving the order data, the cloud server processes the order data, for example, completes a payment transaction process and the like.
The ordering device or the man-machine interaction device in the present specification may be a computer device, and fig. 7 is a schematic diagram of a hardware structure of the computer device, where the computer device includes a processor 701 and a machine-readable storage medium 702 storing machine executable instructions. The processor 701 and the machine-readable storage medium 702 may communicate via a system bus 703. Also, by reading and executing machine-executable instructions corresponding to the supply and demand prediction logic in the machine-readable storage medium 702, the processor 701 may perform the functions of the ordering device or the human-machine interaction device described above.
The machine-readable storage medium 702 referred to in this disclosure may be any electronic, magnetic, optical, or other physical storage device that can contain or store information, such as executable instructions, data, or the like. For example, the machine-readable storage medium 702 may include both permanent and non-permanent, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of machine-readable storage media include, but are not limited to, phase-change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, read only compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage, quantum memory, graphene-based storage or other magnetic storage devices, or any other non-transmission medium, which may be used to store information that may be accessed by the computing device.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Where a description of "a specific example", or "some examples", etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present description. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Other embodiments of the present description will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This specification is intended to cover any variations, uses, or adaptations of the specification following, in general, the principles of the specification and including such departures from the present disclosure as come within known or customary practice within the art to which the specification pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the specification being indicated by the following claims.
It is to be understood that the present description is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.
The foregoing description of the preferred embodiments is provided for the purpose of illustration only, and is not intended to limit the scope of the disclosure, since any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the disclosure are intended to be included within the scope of the disclosure.