Control method, food delivery robot and computer readable storage medium

Through the voice control system, the existing food delivery robots are solved, and the delivery accuracy and work efficiency of food delivery robots are improved, and the risks of operators' contact with robots are reduced. , improving the safety and efficiency of restaurant services.

CN113936653BActive Publication Date: 2024-11-15KEENON ROBOTICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111091350.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-17
Publication Date
2024-11-15
Estimated Expiration
2041-09-17

AI Technical Summary

Technical Problem

The existing food delivery robot is low in intelligence and cumbersome in operation. Operators need to manually select delivery destinations, which poses a sanitary and safety hazard and is inconvenient to use in large-scale restaurants.

Method used

The voice control system is used to control the food delivery robot, identify the food delivery command through voice input, update the task list, and automatically execute the food delivery tasks, improve the delivery accuracy and work efficiency, and reduce the operator's direct contact with the robot.

Benefits of technology

It simplifies the operation process, improves the delivery accuracy and work efficiency of the food delivery robot, reduces the risk of operators' contact with the food delivery robot, and improves the efficiency and safety of restaurant services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113936653B_ABST
    Figure CN113936653B_ABST
Patent Text Reader

Abstract

The present invention provides a control method for a food delivery robot, the food delivery robot includes a voice control system and multiple food storage layers, the food delivery robot has a current task list, and the control method includes: receiving a food delivery instruction issued by an operator; performing voice recognition on the food delivery instruction through the voice control system to determine the content of the food delivery instruction, the content of the food delivery instruction includes one or more food delivery tasks, each food delivery task includes at least a food storage layer number and a target point; updating the current task list according to the food delivery task; when the number of tasks in the current task list is not less than the number of the food storage layers, controlling the food delivery robot to execute the tasks in the current task list. The embodiment of the present invention can control the food delivery robot through voice input, and also provides a control method when the food delivery robot executes multiple food delivery tasks at the same time, which improves the delivery accuracy and work efficiency of the food delivery robot without the operator having to directly contact the food delivery robot.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention generally relates to the technical field of intelligent devices, and in particular to a control method of a food delivery robot, a food delivery robot and a computer-readable storage medium. Background Art

[0002] Smart devices are widely used in many industries due to their advantages such as intelligence, high efficiency and low cost. For example, food delivery robots used in restaurants and canteens execute commands to deliver food dishes from the food outlet to customers, replacing part of manual labor and saving operating costs. Currently, more and more restaurants and canteens are trying to use food delivery robots.

[0003] Figure 1 Figure 1 shows a typical implementation of user ordering and food delivery in a restaurant. Figure 1 As shown, after the user sits down in the restaurant, he or she starts ordering food using the mini program by scanning the QR code on the desktop. After scanning the QR code on the desktop, the mini program will transmit the user's membership information to the food delivery robot and / or management server in the background. After the dishes are ready, the restaurant waiter places the dishes on the internal tray of the food delivery robot, and then enters the designated destination, such as the user's table number, on the user interface of the food delivery robot. The food delivery robot then goes to the destination to deliver the food. After the robot arrives at the target table, it can notify the customer through voice to remind the customer to pick up the food. After the customer has finished picking up the food, the food delivery robot automatically returns to the food outlet and waits for the next delivery task and instructions.

[0004] However, existing food delivery robots can only complete food delivery actions, and their intelligence level is not high. Operators are required to manually select the delivery destination through the operation interface after placing the food to be delivered. If the restaurant is large, different partitions or floors need to be determined before selecting and confirming the delivery destination, which makes the whole process more cumbersome. In addition, existing food delivery robots usually require operators to enter specific instructions or click specific buttons before confirming that the delivery destination has been entered and can be started. Otherwise, the food delivery robot will continue to wait for the operator to enter the delivery instruction, which also makes the existing food delivery robots inconvenient to use. Moreover, the operator controls the food delivery robot by manually clicking on the operation interface, which still poses health and safety risks in places that provide catering services such as restaurants and canteens.

[0005] The contents of the background technology section are merely the technologies known to the inventors and do not necessarily represent the prior art in the field. Summary of the invention

[0006] In view of one or more defects in the prior art, the present invention provides an embodiment of a control method, which controls a food delivery robot through voice input, and also provides a control method for a food delivery robot to perform multiple food delivery tasks at the same time, thereby improving the delivery accuracy and work efficiency of the food delivery robot without the operator having to directly contact the food delivery robot. The embodiments of the present invention also provide a food delivery robot and a computer-readable storage medium, which can execute the food delivery robot control method provided in the embodiments of the present invention.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0008] A control method for a food delivery robot, the food delivery robot comprising a voice control system and a plurality of food storage layers, the food delivery robot having a current task list, the control method comprising:

[0009] Receive meal delivery instructions from operators;

[0010] Performing voice recognition on the meal delivery instruction through the voice control system to determine the content of the meal delivery instruction, wherein the content of the meal delivery instruction includes one or more meal delivery tasks, and each meal delivery task includes at least a food storage layer number and a target point;

[0011] Update the current task list according to the meal delivery task; and

[0012] When the number of tasks in the current task list is not less than the number of the food containing layers, the food delivery robot is controlled to execute the tasks in the current task list.

[0013] According to one aspect of the present invention, the control method of the food delivery robot further includes:

[0014] determining the number of food containing layers in which food is placed among the plurality of food containing layers; and

[0015] When the number of tasks in the current task list is equal to the number of food containing layers on which food is placed, the food delivery robot is controlled to execute the tasks in the current task list.

[0016] According to one aspect of the present invention, the control method of the food delivery robot further includes: when the number of tasks in the current task list is less than the number of the food containing layers, repeatedly performing the following steps:

[0017] Receive meal delivery instructions from operators;

[0018] Performing voice recognition on the meal delivery instruction by the voice control system to determine the content of the meal delivery instruction; and

[0019] Update the current task list according to the meal delivery task;

[0020] Until the number of tasks in the current task list is equal to the number of the food storage layers or it is confirmed that the user has no further food delivery instructions, the food delivery robot is controlled to execute the tasks in the current task list.

[0021] According to one aspect of the present invention, when the number of tasks in the current task list is less than the total number of food storage layers, the food delivery robot is controlled to play a first preset audio, and the first preset audio is used to prompt the user to give further operation instructions.

[0022] According to one aspect of the present invention, after playing the first preset audio, when no meal delivery instruction is received from the operator within a first preset time, it is confirmed that the user has no further meal delivery instruction.

[0023] According to one aspect of the present invention, the control method of the food delivery robot also includes: before the step of controlling the food delivery robot to execute a task in the current task list, controlling the food delivery robot to play a second preset audio, wherein the second preset audio includes at least the number of delivery instructions currently received by the food delivery robot.

[0024] According to one aspect of the present invention, when the number of meal delivery tasks in the current task list is greater than the number of the food containing layers, the meal delivery tasks exceeding the number of the food containing layers are not executed.

[0025] According to one aspect of the present invention, the voice control system includes a voice collection unit, an audio processing unit and a background control unit, wherein the step of receiving the meal delivery instruction issued by the operator is performed by the voice collection unit, and the step of performing voice recognition on the meal delivery instruction by the voice control system to determine the content of the meal delivery instruction includes:

[0026] The audio processing unit digitally processes the meal delivery instruction acquired by the voice acquisition unit to acquire a digital signal;

[0027] Performing speech recognition based on the digital signal by the audio processing unit to obtain text information corresponding to the meal delivery instruction; and

[0028] The food storage layer number and target point information are obtained according to the text information through the background control module.

[0029] According to one aspect of the present invention, the step of obtaining the food storage layer number and target point information according to the text information through the background control module further includes:

[0030] Identifying food delivery intent keywords from the text information; and

[0031] According to the meal delivery intention keyword, the food storage layer number and target point information are obtained.

[0032] According to one aspect of the present invention, there is provided a food delivery robot, comprising:

[0033] A main body, wherein a plurality of food containing layers are arranged on the main body;

[0034] a driving system, the driving system being arranged on the main body and being controllable to drive the food delivery robot to move; and

[0035] A voice control system is provided on the main body and is configured to execute the control method as described above.

[0036] According to one aspect of the present invention, the food delivery robot also includes a graphical user interface, which communicates with the voice control system, and the voice control system is configured to control the graphical user interface to render and display the food storage layer number and target point.

[0037] According to one aspect of the present invention, a computer-readable storage medium is provided, comprising computer-executable commands stored thereon, wherein the executable commands implement the control method as described above when executed by a processor.

[0038] Compared with the prior art, the embodiments of the present invention provide a control method for a food delivery robot, which uses voice to control the food delivery robot, and does not require an operator to manually input a delivery destination. The food delivery robot can recognize the food delivery instruction by simply receiving the operator's voice instruction, thereby simplifying the operation process, improving work efficiency, and avoiding direct contact between the operator and the food delivery robot. The embodiments of the present invention also provide a food delivery robot and a computer-readable storage medium, which can execute the aforementioned control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0040] Figure 1 A typical implementation method of user ordering and food delivery in a restaurant is shown;

[0041] Figure 2 is a flow chart of one embodiment of the present invention;

[0042] Figure 3 It is a schematic diagram of a flow chart for determining the relationship between the number of meal delivery tasks and the number of food storage layers in one embodiment of the present invention;

[0043] Figure 4 is a schematic diagram of a complete process of controlling a food delivery robot to execute a food delivery command in one embodiment of the present invention;

[0044] Figure 5 is a schematic diagram of a process for identifying a meal delivery instruction in one embodiment of the present invention;

[0045] Figure 6 is a complete flow chart of identifying a meal delivery instruction in one embodiment of the present invention;

[0046] Figure 7 is a schematic diagram of the structure of a food delivery robot in one embodiment of the present invention; and

[0047] Figure 8 1 is a system schematic diagram of a food delivery robot in one embodiment of the present invention. DETAILED DESCRIPTION

[0048] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0049] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0050] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or can communicate with each other; it can be directly connected, or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply means that the first feature is lower in level than the second feature.

[0052] The disclosure below provides many different embodiments or examples to realize different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or reference letters in different examples, and this repetition is for the purpose of simplicity and clarity, which itself does not indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides various specific examples of processes and materials, but those of ordinary skill in the art can be aware of the application of other processes and / or the use of other materials.

[0053] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0054] Figure 2 A flow chart of a control method 100 of a food delivery robot 10 according to an embodiment of the present invention is shown, which will be described in detail below with reference to the accompanying drawings.

[0055] like Figure 7 As shown, the food delivery robot 10 includes a voice control system 11 and a plurality of food storage layers 12. Figure 2 As shown, the control method 100 of the food delivery robot 10 includes:

[0056] In step S101, a meal delivery instruction issued by an operator is received, where the meal delivery instruction is a voice instruction, for example, directly spoken by the operator. The voice control system 11 of the meal delivery robot 10 may include a voice acquisition unit, such as a microphone, for acquiring the meal delivery instruction of the operator and converting the sound signal into an electrical signal. In addition, the voice control system 11 may also include an audio processing unit for necessary processing of the electrical signal, including but not limited to filtering, AD conversion, etc.

[0057] In step S102, the voice control system 11 performs voice recognition on the meal delivery instruction to determine the content of the meal delivery instruction, where the content of the meal delivery instruction includes one or more meal delivery tasks, and each meal delivery task includes at least a food storage layer number and a target point.

[0058] The audio processing unit of the voice control system 11 may include voice recognition software or hardware for voice recognition of meal delivery instructions. For example, the meal delivery instruction may be recognized and text information may be generated, and then the content of the meal delivery instruction may be parsed from the text information. The meal delivery task in the meal delivery instruction includes at least the number and target point of the food storage layer 12. When the meal delivery task in the meal delivery instruction is recognized, the number of the food storage layer 12 in the meal delivery task corresponds to the target point that appears in the meal delivery task. For example, the meal delivery instruction issued by the operator includes a meal delivery task, and the meal delivery task is to deliver the first layer to table number one, where the first layer that appears is a pre-set serial number in the food storage layer, and may also be other coding forms, such as "A, B, C...", etc. Table number one is a table number code or a specific position code pre-set in the restaurant cafeteria. Different coding forms may also be used according to the specific circumstances of the restaurant cafeteria.

[0059] In addition, the meal delivery instruction issued by the operator may also include multiple meal delivery tasks, such as delivering the first layer to table one, delivering the second layer to table five, etc. The voice control system 11 can perform voice analysis on the result of voice recognition, and parse out each meal delivery task one by one, each meal delivery task including the food storage layer number and the corresponding target point.

[0060] In step S103, the current task list is updated according to the meal delivery task.

[0061] The current task list can be set and maintained in the control system of the food delivery robot, which can be implemented in the form of software, hardware or firmware. Each time a new food delivery task is assigned to the food delivery robot, the new food delivery task is added to the current task list; when the food delivery robot completes one of the food delivery tasks, the completed food delivery task is deleted from the current task list. After parsing one or more food delivery tasks in step S102, the parsed food delivery tasks are recorded in the current task list in a timely manner.

[0062] According to a preferred embodiment of the present invention, the current task list can be displayed in real time on a graphical user interface of the food delivery robot. When the operator issues multiple food delivery instructions, the current task list will accumulate and record the food delivery tasks one by one.

[0063] In step S104, it is determined whether the number of meal delivery tasks in the current task list is less than the number of food storage layers. The number of food storage layers of the meal delivery robot is known and can be set in advance to facilitate comparison with the number of meal delivery tasks in the current task list.

[0064] In step S105, when the number of meal delivery tasks in the current task list is not less than the number of food storage layers, the meal delivery robot 10 is controlled to execute the meal delivery tasks. For example, if the meal delivery robot 10 is provided with three food storage layers, and if three or more meal delivery tasks are recorded in the current task list, the meal delivery robot 10 is controlled to start executing the meal delivery tasks.

[0065] Reference above Figure 1 The control method of the food delivery robot according to an embodiment of the present invention is described. Through the above embodiment, the food delivery robot can be controlled by voice input, and a control method when the food delivery robot performs multiple food delivery tasks at the same time is also provided, which improves the delivery accuracy and work efficiency of the food delivery robot while the operator does not need to directly contact the food delivery robot.

[0066] According to one embodiment of the present invention, the control method of the food delivery robot 10 further includes:

[0067] Determine the number of food containing layers in which food is placed among the multiple food containing layers, and when the number of tasks in the current task list is equal to the number of food containing layers 12 in which food is placed, control the food delivery robot to execute the tasks in the current task list.

[0068] A weight sensor can be set on each food storage layer to detect whether there is food placed on it. Alternatively, it is also possible to determine whether there is food placed by acquiring an image in the food storage layer, and then determine the number of food storage layers with food placed. Before executing the food delivery task, judging whether there is food placed in the food storage layer can avoid delivery errors or omissions.

[0069] Figure 3 The control method 200 of the food delivery robot 10 according to an embodiment of the present invention is shown. The control method 200 includes a process of determining the relationship between the number of food delivery tasks and the number of food storage layers. Figure 3 Detailed description.

[0070] Steps S201, S202, S203 and S204 are substantially the same as steps S101, S102, S103 and S104, respectively. In step S201, a meal delivery instruction issued by an operator is received; in step S202, the meal delivery instruction is voice recognized to determine the content of the meal delivery instruction; in step S203, a meal delivery task is received and the current task list is updated; in step S204, it is determined whether the number of tasks in the current task list is not less than the number of food storage layers. When the number of tasks is equal to or greater than the number of food storage layers, step S205 is executed to control the meal delivery robot to complete the meal delivery task. Otherwise, step S206 is performed to determine whether the user has further meal delivery instructions. If not, it indicates that the user (operator) has issued all meal delivery instructions, so step S205 is performed to control the robot to complete the meal delivery task; otherwise, step S201 is returned to repeat steps S201, S202, S203 and S204.

[0071] Through Figure 3 The control method 200 shown in the figure controls the food delivery robot 10 to perform the food delivery task until the number of food delivery tasks in the current task list is equal to the number of food storage layers 12 or it is confirmed that the user has no further food delivery instructions. In this embodiment, when the number of food delivery tasks is less than the number of food storage layers 12, the above steps are executed in a loop.

[0072] like Figure 3 As shown, in step S206, it is determined whether the user has further delivery instructions. When a delivery instruction input by the user is received within the preset time, it returns to step S201. When no delivery instruction input by the user is received within the preset time (for example, 5 seconds or 10 seconds), it is determined by default that the user has no further delivery instructions. Or optionally, when a specific voice from the operator is received or a confirmation button is pressed, it is considered that there is no additional food that needs to be delivered at the moment, then it proceeds to step S205, and the delivery robot 10 executes the delivery task previously recorded in the current task list.

[0073] Figure 4 The control method 300 for controlling the food delivery robot 10 according to one embodiment of the present invention is shown. The control method 300 also includes a detailed process including waking up the food delivery robot 10. Figure 4 Detailed description.

[0074] In step S301, the food delivery robot is started and the control method 300 begins. Before receiving the food delivery instruction issued by the operator, the food delivery robot can be set to a dormant state to save power. In step S302, the food delivery robot is awakened by receiving a preset voice or preset behavior issued by the operator, for example, the operator awakens the food delivery robot by issuing a voice command of "Hello, Peanut" or "Start", or by activating a key switch.

[0075] After waking up, the food delivery robot will continue to monitor whether it has received food delivery instructions from the operator, such as Figure 4 As shown, in step S303, whether a meal delivery instruction is received within the second preset time, if a meal delivery instruction issued by the operator is received, step S304 is executed, if a meal delivery instruction issued by the operator is not received within the second preset time, it is confirmed that there is no meal delivery task to be executed, the control method 300 ends, and the meal delivery robot returns to the dormant state, wherein the second preset time can be set to 5 seconds. After receiving the meal delivery instruction issued by the operator, in step S304, the meal delivery instruction is identified by the voice control system 11, wherein the meal delivery instruction includes one or more meal delivery tasks, and after the meal delivery instruction is identified, the meal delivery task is obtained in step S305. In step S306, meal delivery tasks are received and the current task list is updated. The current task list accumulates and records the received meal delivery tasks one by one, and the number of meal delivery tasks in the current task list is also obtained. After obtaining the number of meal delivery tasks, in step S307, the number of meal delivery tasks in the current task list is compared with the number of food holding layers 12. If the number of meal delivery tasks is less than the number of food holding layers 12, step S309 is executed; if the number of meal delivery tasks is not less than the number of food holding layers 12, step S308 is executed to continue to determine whether the number of meal delivery tasks in the current task list is equal to the number of food holding layers 12. If the number of meal delivery tasks is equal to the number of food holding layers 12, step S314 is performed to play a second preset audio (described in detail later), and then step S315 is performed to execute the previously recorded meal delivery tasks in the current task list. If the number of meal delivery tasks is greater than the number of food holding layers 12, in step S313, the meal delivery tasks that exceed the number of food holding layers 12 are ignored. For example, the food delivery robot has three food storage layers 12. When receiving a food delivery task, a total of four food delivery instructions are recognized through the voice control system 11. At this time, the food delivery tasks exceeding three are considered invalid. At the same time, the food delivery tasks are accumulated and recorded one by one in the current task list. That is, the fourth food delivery task is directly discarded and not recorded in the current task list, and the three food delivery tasks recorded previously in the current task list are executed.

[0076] like Figure 4As shown, when the number of food delivery tasks in the current task list is less than the number of food holding layers 12, in step S309, the food delivery robot is controlled to play a first preset audio, and the first preset audio is used to prompt the operator to give further operating instructions. The first preset voice indicates that some food holding layers 12 are still unused, or asks the operator whether there are other instructions, such as "the third layer is still empty" or "are there any other tasks", etc., to make full use of each food holding layer 12 in the food delivery robot.

[0077] Further, after playing the first preset audio, the subsequent activities of the food delivery robot are controlled according to whether the user's food delivery instruction is received, wherein after playing the first preset audio, in step S310, within the first preset time, for example, the first preset time is 5 seconds, it is determined whether the food delivery instruction is received. If a new food delivery instruction is received, the process returns to step S304 to identify the newly received food delivery instruction. If no new food delivery instruction is received, the process continues to determine whether an instruction containing no subsequent task information is received in step S311. The failure to receive a new food delivery instruction here includes, for example, not receiving any voice within the preset time, or the received voice cannot be identified as a food delivery instruction, or receiving an instruction containing no subsequent task information issued by an operator, wherein the instruction containing no subsequent task information is, for example, "depart immediately", "no more", etc. If an instruction containing no subsequent task information is received, it is confirmed that the operator has no further food delivery instructions, and the process proceeds to step S314. In step S314, the food delivery robot is controlled to play a second preset audio, wherein the second preset audio at least includes the number of food delivery tasks recorded in the current task list of the food delivery robot. In this embodiment, before the food delivery robot executes the food delivery task in the current task list, a step of controlling the food delivery robot to play a second preset audio is added. The second preset audio includes the number of food delivery tasks recorded in the current task list of the food delivery robot, and may also include the number of the food storage layer 12 in the food delivery task and the corresponding target point. By playing the second preset audio, the operator is informed that the food delivery task is about to be executed, which is convenient for the operator to check the number of trees and the corresponding relationship in the food delivery task again to ensure the accuracy of the food delivery. Then proceed to step S315 to control the food delivery robot to execute the food delivery command. If it is determined in step S311 that no instruction containing no subsequent task information is received, that is, within the first preset time, neither a new food delivery instruction nor an instruction containing no subsequent task information is received, in step S312, a third preset audio is played, and the third preset audio can be a voice that prompts the operator that the food delivery robot is about to execute the food delivery task, and then steps S314 and S315 are executed to execute the food delivery task in the current task list.

[0078] According to one embodiment of the present invention, the food delivery robot 10 further includes a graphical user interface 13, such as a display screen. After receiving the food delivery task in step S306, Figure 4 As shown, in step S317, the meal delivery tasks in the current task list are displayed on the graphical user interface. Step S317 can be executed after receiving the meal delivery tasks and updating the current task list, and before executing the meal delivery tasks in the current task list. The meal delivery task information displayed in the graphical user interface 13 may include the number of the food storage layer 12 and the corresponding target point. By displaying the meal delivery tasks recorded in the current task list through the graphical user interface 13, the operator can clearly observe the corresponding relationship between the number of meal delivery tasks and the food storage layer 12, which is convenient for the operator to verify the meal delivery tasks, avoid voice recognition errors or omissions, further improve the accuracy of meal delivery, and avoid delivery errors.

[0079] Similarly, when it is determined in step S308 that the number of delivery tasks is greater than the number of food containing layers 12, in step S316, the delivery robot 10 is controlled to play a second preset voice, and then step S313 is executed, and no record is made for the delivery tasks that exceed the number of food containing layers 12.

[0080] According to one embodiment of the present invention, Figure 8 As shown, the voice control system 11 includes a voice collection unit 111, an audio processing unit 112 and a background control unit 113. Specifically, the voice collection unit 111 can be a microphone. The step of receiving the meal delivery instruction issued by the operator is performed by the voice collection unit 111. Figure 5 The step 400 of identifying a meal delivery instruction according to an embodiment of the present invention includes the following steps:

[0081] S401: Digitally process the meal delivery instruction acquired by the voice acquisition unit through the audio processing unit to acquire a digital signal;

[0082] S402: performing speech recognition based on the digital signal by the audio processing unit to obtain text information corresponding to the meal delivery instruction;

[0083] S403: Obtaining the food storage layer number and target point information according to the text information through the background control module.

[0084] Figure 6 FIG. 4 shows a method for speech recognition according to an embodiment of the present invention, which can be performed by the audio processing unit 112. Figure 6As shown, the audio processing unit 112 can perform preliminary processing on the meal delivery instruction obtained by the voice collection unit 101 before performing voice recognition. The processing methods include noise filtering, echo elimination, ultrasonic optimization and low-frequency enhancement, etc., to obtain more accurate meal delivery instructions and reduce interference with the meal delivery instructions, and then perform step S401.

[0085] According to an embodiment of the present invention, step S403 further includes:

[0086] Identifying food delivery intent keywords from the text information; and

[0087] The target point information is obtained according to the food delivery intention keyword.

[0088] Specifically, Figure 6 As shown, the speech acquisition unit 111 acquires the meal delivery instruction issued by the operator, and after preprocessing by the audio processing unit 112, the meal delivery instruction is digitized, and the digital signal of the meal delivery instruction is split into small waveforms and encoded. The audio processing unit 112 extracts features from the small waveforms, matches them in the acoustic model database, obtains the corresponding single words or Chinese characters, further calibrates the words or Chinese characters, matches the single words or Chinese characters in the speech model library, obtains the speech model of the words or Chinese characters, and performs language normalization and correction on the speech model through the audio processing unit 112 to obtain the speech recognition text information of the words or Chinese characters. The speech recognition text information is processed by the background control unit 113, such as word segmentation and stop word removal, and the word segmentation result is matched with preset delivery intention keywords, where the delivery intention keywords may include, for example, "deliver to", "deliver to", "deliver to", etc., and the information including the number and target point of the food holding layer 12 is identified. Finally, the delivery task in the delivery instruction is filtered out through methods such as homophonic correction, regular matching, and preset delivery point matching.

[0089] In addition, abnormal situations may be encountered during speech recognition, such as failure to recognize, invalid target point, etc. The background control unit 113 can preset corresponding processing methods for various abnormal situations, and when a specific abnormality occurs, the corresponding processing method is called. The subscripts list some abnormal processing methods according to embodiments of the present invention.

[0090]

[0091]

[0092] In this embodiment, the abnormal situations listed in the above table and the corresponding processing methods of the abnormal situations are provided, wherein the backend refers to the background control unit 113 of the voice control system 11. When the above abnormal situation occurs, the background control unit 113 calls the processing method corresponding to the abnormal situation, and directly controls the food delivery robot 10 to play the voice and perform the corresponding action according to the preset processing method. When the voice issued by the user cannot be recognized, for example, the voice is fuzzy or the voice collection is incomplete, the preset voice used to prompt the user of the abnormal situation is played at this time, and further, the recognizable voice example can also be played. When the food delivery instruction issued by the user contains a preset target point or a preset food storage layer number that does not belong to the preset target point or the preset food storage layer number, the food delivery robot is controlled to play the preset voice used to prompt the user that the target point or the food storage layer cannot be recognized, and the voice that cannot obtain the complete food delivery information is not recorded. The complete food delivery information includes the target point that can be recognized and the corresponding food storage layer number.

[0093] When multiple delivery instructions corresponding to the same food storage layer number are received, the task list is updated, and the target point corresponding to the food storage layer number is replaced with the target point in the latest delivery instruction received, overwriting the original task, and no preset voice prompt is performed.

[0094] The present invention also provides an embodiment of a food delivery robot, such as Figure 7 As shown, the food delivery robot comprises:

[0095] A main body 14, on which a plurality of food containing layers 12 are disposed, and the main body 14 is used to provide a bearing condition for other components of the food delivery robot 10;

[0096] A driving system 15, which is disposed on the main body 14 and can be controlled to drive the food delivery robot to move, such as electrically driven rollers, tracks or other walking mechanisms, so that the food delivery robot can move between the food outlet and the target point;

[0097] The voice control system 11 is arranged on the main body 14 and is configured to execute the control method as described above, receive the meal delivery instruction issued by the operator, and identify the meal delivery instruction, obtain the food storage layer 12 number and the corresponding target point in the meal delivery task, and control the meal delivery robot 10 to execute the meal delivery task in the current task list.

[0098] According to one embodiment of the present invention, the food delivery robot 10 further includes a graphical user interface 13, such as Figure 2As shown, the graphical user interface 13 can be fixedly arranged on the main body 14, and the graphical user interface 13 communicates with the voice control system 11, and the voice control system 11 is configured to control the graphical user interface 13 to render and display the target point. The graphical user interface 13 can display the meal delivery tasks in the current task list, including the number of meal delivery tasks, the correspondence between the number of the food storage layer 12 and the target point, for the operator to verify the recognition of the meal delivery instruction.

[0099] The present invention also provides an embodiment of a computer-readable storage medium, wherein the computer-readable storage medium includes computer-executable instructions stored thereon, and the executable instructions implement the control method as described above when executed by a processor.

[0100] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. 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 control method for a food delivery robot, the food delivery robot comprising a voice control system and a plurality of food storage layers, the food delivery robot having a current task list, the control method comprising: Receive meal delivery instructions from operators; Performing voice recognition on the meal delivery instruction by the voice control system to determine the content of the meal delivery instruction, wherein the content of the meal delivery instruction includes one or more meal delivery tasks, and each meal delivery task includes at least a food storage layer number and a target point; Update the current task list according to the meal delivery task; and When the number of tasks in the current task list is not less than the number of the food containing layers, controlling the food delivery robot to execute the tasks in the current task list; When the number of tasks in the current task list is less than the number of food containing layers, the following steps are repeatedly performed: Receive meal delivery instructions from operators; performing voice recognition on the meal delivery instruction by the voice control system to determine the content of the meal delivery instruction; and Update the current task list according to the meal delivery task; until the number of tasks in the current task list is equal to the number of the food containing layers or it is confirmed that the user has no further food delivery instructions, controlling the food delivery robot to execute the tasks in the current task list; When multiple meal delivery instructions including the same food storage layer number are received, the task list is updated, and the target point corresponding to the food storage layer number is replaced with the target point in the latest received meal delivery instruction.

2. The control method according to claim 1, further comprising: determining the number of food containing layers in which food is placed among the plurality of food containing layers; and When the number of tasks in the current task list is equal to the number of food containing layers on which food is placed, the food delivery robot is controlled to execute the tasks in the current task list.

3. According to the control method of claim 1, when the number of tasks in the current task list is less than the total number of food storage layers, the food delivery robot is controlled to play a first preset audio, and the first preset audio is used to prompt the user to give further operation instructions.

4. The control method according to claim 3, wherein after playing the first preset audio, when no meal delivery instruction is received from the operator within a first preset time, it is confirmed that the user has no further meal delivery instruction.

5. The control method according to any one of claims 1 to 4, further comprising: Before the step of controlling the food delivery robot to execute the task in the current task list, the food delivery robot is controlled to play a second preset audio, wherein the second preset audio at least includes the number of food delivery instructions currently received by the food delivery robot.

6. According to the control method described in any one of claims 1 to 4, when the number of meal delivery tasks in the current task list is greater than the number of the food storage layers, the meal delivery tasks exceeding the number of the food storage layers are not executed.

7. The control method according to any one of claims 1 to 4, wherein the voice control system comprises a voice collection unit, an audio processing unit and a background control unit, wherein the step of receiving the meal delivery instruction issued by the operator is performed by the voice collection unit, and the step of performing voice recognition on the meal delivery instruction by the voice control system to determine the content of the meal delivery instruction comprises: The audio processing unit digitally processes the meal delivery instruction acquired by the voice acquisition unit to acquire a digital signal; Performing speech recognition based on the digital signal by the audio processing unit to obtain text information corresponding to the meal delivery instruction; and The background control unit obtains the food storage layer number and target point information according to the text information.

8. The control method according to claim 7, wherein the step of obtaining the food storage layer number and target point information according to the text information by the background control unit further comprises: identifying a food delivery intention keyword from the text information; and According to the meal delivery intention keyword, the food storage layer number and target point information are obtained.

9. A food delivery robot, comprising: A main body, wherein a plurality of food containing layers are arranged on the main body; A driving system, which is disposed on the main body and can be controlled to drive the food delivery robot to move; and A voice control system, which is arranged on the main body and is configured to execute the control method according to any one of claims 1 to 8.

10. The food delivery robot according to claim 9, further comprising a graphical user interface, wherein the graphical user interface communicates with the voice control system, and the voice control system is configured to control the graphical user interface to render and display the food storage layer number and target point.

11. A computer-readable storage medium, comprising computer executable commands stored thereon, wherein the executable commands implement the control method according to any one of claims 1 to 8 when executed by a processor.