A cleaning system and method, apparatus

Abstract

The application provides a cleaning system and method and device. The method comprises: obtaining cleaning request information from a terminal device, the cleaning request information comprising information of a target to be cleaned or information of the target to be cleaned and a target position; inputting the cleaning request information into a trained large language model to obtain cleaning instructions output by the trained large language model, the cleaning instructions comprising information of a target cleaning device, a cleaning task and information of a task position; and sending the cleaning instructions to the target cleaning device according to the information of the target cleaning device. The application uses the trained large language model to generate cleaning instructions recognizable by the cleaning device according to cleaning requirements, so as to instruct the cleaning device to perform a specified task and reduce the demand for manual labor, thereby reducing labor costs.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of computers, and particularly relates to a cleaning system and method and device. BACKGROUND

[0002] In large places, such as shopping malls, office buildings, and airports, cleaning work, including dumping garbage and cleaning dirt, is a task with a large workload and high manpower demand. For example, a 100,000 square meter shopping mall requires at least 20 cleaning workers per day, and the annual labor cost can reach hundreds of thousands of yuan. Such cleaning tasks require a large number of cleaning personnel, resulting in high labor costs. SUMMARY

[0003] The embodiments of the present application provide a cleaning system and method, device, computer readable storage medium, and computer program product, which can solve the problem of high labor cost in cleaning large places.

[0004] In a first aspect, the embodiments of the present application provide a cleaning method, comprising:

[0005] receiving cleaning request information from a terminal device, the cleaning request information comprising information of a target to be cleaned or the information of the target to be cleaned and a target position;

[0006] inputting the cleaning request information into a trained large language model to obtain a cleaning instruction output by the trained large language model, the cleaning instruction comprising information of a target cleaning device, a cleaning task, and information of a task position;

[0007] sending the cleaning instruction to the target cleaning device according to the information of the target cleaning device, the cleaning instruction being used to instruct the target cleaning device to move to the task position and execute the cleaning task;

[0008] When the cleaning request information comprises information of a target to be cleaned, the trained large language model is used to determine the target cleaning device, the cleaning task, and the task position according to the information of the target to be cleaned, and output the cleaning instruction.

[0009] When the cleaning request information comprises information of a target to be cleaned and a target position, the trained large language model is used to determine the target cleaning device and the cleaning task according to the information of the target to be cleaned, and determine the task position according to the target position, and output the cleaning instruction.

[0010] In one embodiment, the cleaning request information is information generated by the terminal device when receiving user input work content and obtaining the position of the user, and the work content comprises information of the target to be cleaned.

[0011] The cleaning request information is information generated by the terminal device after receiving an image collected by a first camera device and obtaining a position of the first camera device, the image including an imaging area of the target to be cleaned, each first camera device being installed at each place of a site;

[0012] The cleaning request information is generated by the terminal device according to a task triggered automatically at a preset time, the task including information of the target to be cleaned;

[0013] The target position includes a position of the user and a position of the first camera device.

[0014] In an embodiment, the method further includes:

[0015] inputting the cleaning request information into a trained large language model to obtain an unprocessable instruction output by the trained large language model;

[0016] sending the unprocessable instruction to the terminal device, the unprocessable instruction being used to instruct the terminal device to send the cleaning request information to a device of a cleaning personnel;

[0017] The trained large language model is used to determine that a size of the target to be cleaned is greater than a preset size according to the information of the target to be cleaned or determine that the target position is empty, and output the unprocessable instruction.

[0018] In an embodiment, the cleaning device includes a first cleaning robot and a second cleaning robot, the first cleaning robot including a moving base and a clamp, a container, and a second camera device arranged on the moving base, and the second cleaning robot being a full-automatic cleaning robot.

[0019] In an embodiment, the information of the task position includes information of a target area and identification information representing the target position.

[0020] In an embodiment, before the cleaning request information is input into the trained large language model, the method further includes:

[0021] obtaining training data and labels, the training data including first data, second data, and third data, the first data including a position of the user and work content, the second data including a position of a first camera device and a collected image, and the third data including a task triggered automatically at a preset time;

[0022] fine-tuning a large language model using the training data until a value of a loss function of the large language model is less than a preset loss value, the loss function being used to calculate a difference value between an output result of the large language model and the labels.

[0023] When the value of the loss function is less than the preset loss value, the trained large language model is obtained.

[0024] In a second aspect, an embodiment of the present application provides a cleaning device, comprising:

[0025] A communication module is configured to receive cleaning request information from a terminal device, wherein the cleaning request information comprises information of a target to be cleaned or information of the target to be cleaned and a target position;

[0026] The communication module is further configured to send the cleaning instruction to the target cleaning device according to the information of the target cleaning device, wherein the cleaning instruction is used to instruct the target cleaning device to perform the cleaning task after moving to the target position.

[0027] A prediction module is configured to input the cleaning request information into a trained large language model to obtain a cleaning instruction output by the trained large language model, wherein the cleaning instruction comprises information of a target cleaning device, a cleaning task and a target position.

[0028] When the cleaning request information comprises information of a target to be cleaned, the trained large language model is configured to determine the target cleaning device, the cleaning task and the target position according to the information of the target to be cleaned, and output the cleaning instruction.

[0029] When the cleaning request information comprises the information of the target to be cleaned and the target position, the trained large language model is configured to determine the target cleaning device and the cleaning task according to the information of the target to be cleaned, determine the target position according to the target position, and output the cleaning instruction.

[0030] In an embodiment, the device further comprises:

[0031] An acquisition module is configured to acquire training data and labels, wherein the training data comprises first data, second data and third data, the first data comprises a position and a work content of a user, the second data comprises a position of a first camera device and an image collected by the first camera device, and the third data comprises a task triggered automatically at a preset time.

[0032] A training module is configured to fine-tune a large language model by using the training data until a value of a loss function of the large language model is less than a preset loss value, wherein the loss function is used to calculate a difference value between an output result of the large language model and the labels.

[0033] The training module is further configured to obtain the trained large language model when the value of the loss function is less than the preset loss value.

[0034] In a third aspect, the embodiments of the present application provide a cleaning system, comprising a server, a terminal device and at least one cleaning device;

[0035] The terminal device is configured to send the cleaning request information to the server after obtaining the cleaning request information;

[0036] The server is configured to receive the cleaning request information from the terminal device, wherein the cleaning request information comprises information of a target to be cleaned or information of the target to be cleaned and a target position; input the cleaning request information into a trained large language model to obtain a cleaning instruction output by the trained large language model; and send the cleaning instruction to the target cleaning device according to information of the target cleaning device, wherein the cleaning instruction comprises information of the target cleaning device, a cleaning task and information of a task position;

[0037] The target cleaning device is configured to move to the task position and perform the cleaning task according to the cleaning instruction after receiving the cleaning instruction from the server;

[0038] When the cleaning request information comprises information of the target to be cleaned, the trained large language model is configured to determine the target cleaning device, the cleaning task and the task position according to the information of the target to be cleaned, and output the cleaning instruction.

[0039] When the cleaning request information comprises information of the target to be cleaned and the target position, the trained large language model is configured to determine the target cleaning device and the cleaning task according to the information of the target to be cleaned, determine the task position according to the target position, and output the cleaning instruction.

[0040] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method in any one of the first aspect.

[0041] In a fifth aspect, the embodiments of the present application provide a computer program product, which, when executed on a server, causes the server to perform the method in any one of the first aspect.

[0042] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0043] The embodiment of the application obtains cleaning request information from a terminal device, the cleaning request information including information of a target to be cleaned or information of the target to be cleaned and a target position; inputs the cleaning request information into a trained large language model to obtain a cleaning instruction output by the trained large language model, the cleaning instruction including information of a target cleaning device, a cleaning task, and information of a task position; and sends the cleaning instruction to the target cleaning device according to the information of the target cleaning device, the cleaning instruction being used to instruct the target cleaning device to move to the task position and then perform the cleaning task; when the cleaning request information includes information of the target to be cleaned, the trained large language model is used to determine the target cleaning device, the cleaning task, and the task position according to the information of the target to be cleaned, and output the cleaning instruction; and when the cleaning request information includes information of the target to be cleaned and the target position, the trained large language model is used to determine the target cleaning device and the cleaning task according to the information of the target to be cleaned, determine the task position according to the target position, and output the cleaning instruction. The trained large language model can be used to generate a cleaning instruction recognizable by a cleaning device according to a cleaning requirement, instruct the cleaning device to perform a specified task, and reduce the demand for manual work, thereby reducing the labor cost.

[0044] It can be understood that the beneficial effects of the second aspect to the fifth aspect can be referred to the related description in the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0046] Figure 1 is a schematic diagram of a cleaning system provided by an embodiment of the present application;

[0047] Figure 2 is a schematic diagram of a first cleaning robot provided by an embodiment of the present application;

[0048] Figure 3 is a first flowchart of a cleaning method provided by an embodiment of the present application;

[0049] Figure 4 is a second flowchart of a cleaning method provided by an embodiment of the present application;

[0050] Figure 5 is a third flowchart of a cleaning method provided by an embodiment of the present application;

[0051] Figure 6FIG. 1 is a structural schematic diagram of a cleaning device according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular sequences of acts, techniques, etc., in order to provide a thorough understanding of the embodiments of the application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0053] It will be understood that the terms "comprises" and / or "comprising," when used in this specification, include the presence of one or more features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0054] It is also to be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items, and that the term "at least one of" followed by a list of two or more items means any single one of the items in the list, and that the term "one or more of" followed by a list of two or more items means any single one or plurality of two or more of the items in the list.

[0055] As used in the description of the application and the appended claims, the term "if' can be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon [the described condition or event] being detected" or "in response to [the described condition or event] being detected", depending on the context.

[0056] In addition, the terms "first", "second", "third", etc. as used in the description of the application and the appended claims are not used to denote or imply relative importance but are used to distinguish one element from another.

[0057] Reference throughout this specification to "one embodiment", "an embodiment", or "a specific embodiment", means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment", "in an embodiment", "in some embodiments", "in other embodiments", "in additional embodiments", etc. in various places in the specification are not necessarily all referring to the same embodiment, unless otherwise specifically stated. The terms "comprise", "comprising", "has", "having", "includes", "including", "contain", "containing" and variants thereof are all meant to encompass the terms "including", "including but not limited to", "consisting of" and "consisting essentially of" unless otherwise specifically indicated.

[0058] In large places, such as shopping malls, office buildings, airports, cleaning work, including dumping garbage, cleaning dirty, is a heavy workload, high demand for manpower task. For example: a 100,000 square meters of shopping mall, at least 20 cleaning workers per day, annual labor costs can reach hundreds of thousands of yuan. Such cleaning tasks make the demand for cleaning personnel, resulting in high labor costs.

[0059] In addition, there may be various emergencies in large places, such as beverages spilled on the ground, wall skin falling, etc., which need to be handled by cleaning personnel in time, but the manual cleaning method may not be able to clean up in time. And the manual cleaning method may have inconsistent cleaning quality due to differences between people.

[0060] To solve the above problems, the embodiments of the present application provide a cleaning system and method, device, readable storage medium, computer program product.

[0061] In one embodiment, Figure 1 is a schematic diagram of a cleaning system provided by an embodiment of the present application. As Figure 1 shown, the system includes a terminal device 10, a server 11 and at least one cleaning device 12.

[0062] Among them, the cleaning device includes a first cleaning robot and a second cleaning robot. Figure 2 is a schematic diagram of a first cleaning robot provided by an embodiment of the present application. As Figure 2 shown, the first cleaning robot includes a mobile base 20 and a clamp 21 (not labeled in the figure) disposed on the mobile base 20, a container 22, and a second camera device 23. The clamp 21 includes a clamping jaw 211 and a mechanical arm 212, one end of the mechanical arm 212 is connected to the mobile base 20, the other end of the mechanical arm 212 is connected to the clamping jaw 211, and the container 22 can be a garbage can. It can be understood that the first cleaning robot is provided with a signal receiver integrated in the interior.

[0063] The second cleaning robot is a full-automatic cleaning robot. The full-automatic cleaning robot can be a remotely controlled sweeping and mopping integrated robot. It can be understood that the second cleaning robot is provided with a signal receiver integrated in the interior.

[0064] The terminal device 10 is configured to send cleaning request information to the server after obtaining the cleaning request information.

[0065] Among them, the cleaning request information includes information of a target to be cleaned or information of a target to be cleaned and a target position.

[0066] In application, the terminal device can install a software system to realize information processing.

[0067] In a possible implementation, the cleaning request information is generated by the terminal device after receiving the work content input by the user and obtaining the location of the user, the work content including information of the target to be cleaned.

[0068] For example, each terminal device is installed at a work station of each user. The user finds that there is sewage on the ground and inputs the work content on the terminal device: there is sewage on the ground in area 1 of the site, please assign a cleaning device to clean. The work content includes the target to be cleaned: sewage. The terminal device receives the work content input by the user and obtains the location of the user: the coordinates of the work station through the software system.

[0069] The user finds that the garbage can is full of garbage and inputs the work content on the terminal device: the garbage can is full, please assign a cleaning device to clean. The work content includes the target to be cleaned: the garbage can. The terminal device receives the work content input by the user and obtains the location of the user: the coordinates of the work station through the software system.

[0070] The terminal device generates the cleaning request information according to the work content and the location of the user through the software system. The cleaning request information can include the work content and the location of the user, and further include information of the target to be cleaned and the location of the target.

[0071] The cleaning device includes a first cleaning robot and a second cleaning robot. The work content input by the user can also be: there is sewage on the ground in area 1 of the site, please assign the second cleaning robot to clean, and the garbage can is full, please assign the first cleaning robot to clean.

[0072] In a possible implementation, the cleaning request information is generated by the terminal device after receiving the image captured by the first camera device and obtaining the location of the first camera device, the image including an imaging area of the target to be cleaned, and each first camera device is installed at each place of the site.

[0073] For example, the first camera device finds that there is sewage on the ground and captures an image containing the sewage. The image includes an imaging area of the target to be cleaned: the sewage. After receiving the image, the terminal device obtains the location of the first camera device through the software system, and the location of the first camera device is used to determine the location of the stain or the cleaning area.

[0074] The terminal device generates the cleaning request information according to the image and the location of the first camera device through the software system. The cleaning request information includes the image and the location of the first camera device, and further includes information of the target to be cleaned and the location of the target.

[0075] Correspondingly, the location of the target includes the location of the user and the location of the first camera device.

[0076] In a possible implementation, the cleaning request information is generated by the terminal device according to a task triggered automatically at a preset time.

[0077] For example, the preset time is set as 5:00 pm, and the task is to clean all garbage cans in the place. The terminal device generates a cleaning request information according to the automatic triggering of cleaning all garbage cans in the place at 5:00 pm through the software system. The cleaning request information includes the information of the task, and further includes the information of the target to be cleaned.

[0078] The server 11 is configured to receive the cleaning request information from the terminal device, input the cleaning request information into the trained large language model, obtain a cleaning instruction output by the trained large language model, and send the cleaning instruction to the target cleaning device according to the information of the target cleaning device.

[0079] When the cleaning request information includes the information of the target to be cleaned, the trained large language model is configured to determine the target cleaning device, the cleaning task and the task location according to the information of the target to be cleaned, and output the cleaning instruction. When the cleaning request information includes the information of the target to be cleaned and the target location, the trained large language model is configured to determine the target cleaning device and the cleaning task according to the information of the target to be cleaned, determine the task location according to the target location, and output the cleaning instruction. The cleaning instruction includes the information of the target cleaning device, the information of the cleaning task and the information of the task location.

[0080] For example, the cleaning task can be to clean the garbage can, to clean the floor, to clean the liquid on the floor, or to pick up the garbage on the floor.

[0081] In a possible implementation, the information of the task location includes the information of the target area and the identification information representing the target location.

[0082] In an application, the trained large language model is integrated in the server. The large language model can be set as an LLAVA model (Large Language and Vision Assistant, a new type of large multi-modal model).

[0083] For example, the cleaning request information can include the work content and the location of the user. The work content is that the garbage can is full, please assign the first cleaning robot to clean up, and the location of the user is 23 workstations. The trained large language model determines the target cleaning device according to the garbage can: the first cleaning robot, and the cleaning task: cleaning the garbage can, and determines the task location according to the location of the user: 1 area 23 workstations. The cleaning instruction includes the number of the first cleaning robot, 1 area 23 workstations, and cleaning the garbage can.

[0084] It can be understood that the information of the task location includes the information of the target area and the identification information representing the target location, which can provide accurate positioning for the target robot.

[0085] In order for the target cleaning device to better identify the cleaning instruction, the server processes the cleaning instruction to obtain a new cleaning instruction: robot: 1; position: block1, no45; task: clean the trash can.

[0086] The target cleaning device 12, after receiving the cleaning instruction from the server, moves to the task position according to the cleaning instruction and performs the cleaning task.

[0087] For example, the cleaning instruction is: robot: 1; position: block1, no45; task: clean the trash can. After the first cleaning robot receives the cleaning instruction, it moves to the 1st area 23 work station, uses the clamp to pick up the garbage can at the work station through the positioning of the second camera device, and pours the garbage in the garbage can into the container.

[0088] It can be understood that the cleaning request information is input to the trained large language model through the server to obtain the cleaning instruction output by the trained large language model; the cleaning instruction is sent to the target cleaning device according to the information of the target cleaning device, and the target cleaning device receives the cleaning instruction from the server, moves to the task position according to the cleaning instruction, and performs the cleaning task, so that the cleaning device can be assigned in time to clean up. At the same time, since the cleaning device is used to perform the task, the consistency of the cleaning quality can be ensured.

[0089] And through the trained large language model, accurate cleaning tasks can be generated to realize the scheduling of the cleaning device and cope with complex and variable cleaning demands.

[0090] In this embodiment, the terminal device obtains the cleaning request information and sends the cleaning request information to the server; the server receives the cleaning request information from the terminal device, and the cleaning request information includes the information of the target to be cleaned or the information of the target to be cleaned and the target position; the cleaning request information is input to the trained large language model to obtain the cleaning instruction output by the trained large language model; the cleaning instruction is sent to the target cleaning device according to the information of the target cleaning device, wherein the cleaning instruction includes the information of the target cleaning device, the cleaning task and the information of the task position; the target cleaning device receives the cleaning instruction from the server, moves to the task position according to the cleaning instruction, and performs the cleaning task, so that the trained large language model can be used to generate a cleaning instruction recognizable by the cleaning device according to the cleaning demand, to realize the indication of the cleaning device to perform the specified task, reduce the demand for manual work, and reduce the labor cost.

[0091] In one embodiment, Figure 3 is a first flowchart of a cleaning method provided by an embodiment of the present application. As Figure 3 shown, the method is applied to a server and includes:

[0092] S11: receiving cleaning request information from a terminal device.

[0093] The cleaning request information includes information of a target to be cleaned or information of the target to be cleaned and a target position.

[0094] S12: inputting the cleaning request information into a trained large language model to obtain a cleaning instruction output by the trained large language model.

[0095] The cleaning instruction includes information of a target cleaning device, a cleaning task, and information of a task position.

[0096] S13: sending the cleaning instruction to the target cleaning device according to the information of the target cleaning device.

[0097] The cleaning instruction is used to instruct the target cleaning device to perform the cleaning task after moving to the task position. When the cleaning request information includes information of a target to be cleaned, the trained large language model is used to determine the target cleaning device, the cleaning task, and the task position according to the information of the target to be cleaned, and output the cleaning instruction. When the cleaning request information includes information of a target to be cleaned and a target position, the trained large language model is used to determine the target cleaning device and the cleaning task according to the information of the target to be cleaned, and determine the task position according to the target position, and output the cleaning instruction.

[0098] The embodiment of the present application obtains cleaning request information from a terminal device, the cleaning request information includes information of a target to be cleaned or information of the target to be cleaned and a target position. The cleaning request information is input into a trained large language model to obtain a cleaning instruction output by the trained large language model, the cleaning instruction includes information of a target cleaning device, a cleaning task, and information of a task position. The cleaning instruction is sent to the target cleaning device according to the information of the target cleaning device, and the cleaning instruction is used to instruct the target cleaning device to perform the cleaning task after moving to the task position. When the cleaning request information includes information of a target to be cleaned, the trained large language model is used to determine the target cleaning device, the cleaning task, and the task position according to the information of the target to be cleaned, and output the cleaning instruction. When the cleaning request information includes information of a target to be cleaned and a target position, the trained large language model is used to determine the target cleaning device and the cleaning task according to the information of the target to be cleaned, and determine the task position according to the target position, and output the cleaning instruction. The trained large language model is used to generate a cleaning instruction recognizable by a cleaning device according to a cleaning requirement, to instruct the cleaning device to perform a specified task, and to reduce the demand for manual work, thereby reducing the labor cost.

[0099] In one embodiment, Figure 4 is a second flowchart of a cleaning method provided by an embodiment of the present application. As shown in Figure 4As shown, the method further comprises:

[0100] S14: input the cleaning request information into the trained large language model to obtain an unprocessable instruction output by the trained large language model.

[0101] The trained large language model is configured to determine that the size of the target to be cleaned is greater than a preset size according to the information of the target to be cleaned, or determine an empty position according to the target position, and output the unprocessable instruction.

[0102] In application, when the cleaning request information represents a complex situation, the trained large language model outputs an unprocessable instruction. Specifically, the complex situation includes that the size of the target to be cleaned is greater than a preset size, or the target position cannot be determined according to the target position, an empty position is obtained, and the target cleaning device cannot process the specified task.

[0103] For example, the size of the cleaning target is greater than the preset size, such as too much sewage on the ground or too large garbage volume.

[0104] S15: send the unprocessable instruction to the terminal device.

[0105] The unprocessable instruction is used to instruct the terminal device to send the cleaning request information to the device of the cleaning personnel.

[0106] In application, the terminal device sends the cleaning request information to the device of the cleaning personnel through a software system, so that the cleaning personnel can complete the request demand.

[0107] The embodiment inputs the cleaning request information into the trained large language model, obtains the unprocessable instruction output by the trained large language model, and sends the unprocessable instruction to the terminal device. When the cleaning situation is complex and the cleaning device cannot be completed, the cleaning personnel can be informed to complete the task, so that the cleaning task can be completed.

[0108] In one embodiment, Figure 5 is a third flowchart of the cleaning method provided by an embodiment of the present application. As shown in Figure 5 Before step S12, the method further comprises:

[0109] S21: obtain training data and labels.

[0110] The training data includes first data, second data and third data, the first data includes the position and work content of the user, the second data includes the position of the first camera device and the collected image, and the third data includes a task triggered automatically at a preset time.

[0111] For example, the work content can be cleaning a garbage can. Or the work content includes the position and type of the target.

[0112] S22: fine-tuning the large language model by using the training data until a value of a loss function of the large language model is less than a preset loss value.

[0113] The loss function is used to calculate a difference value between an output result of the large language model and a label.

[0114] S23: obtaining the trained large language model when the value of the loss function is less than the preset loss value.

[0115] The embodiment fine-tunes the large language model by using the training data, the first data includes the position and the work content of the user, the second data includes the position of the first camera device and the collected image, and the third data includes the task triggered automatically at the preset time, so as to ensure that the trained large language model can recognize the cleaning demand to output the cleaning instruction recognizable by the cleaning device.

[0116] In one embodiment, when the target cleaning device cannot complete the cleaning instruction, the target cleaning device sends the terminal device the unhandled information, and the unhandled information is used to instruct the terminal device to send the cleaning request information to the device of the cleaning personnel.

[0117] The embodiment sends the terminal device the unhandled information when the target cleaning device cannot complete the cleaning instruction, so that the terminal device sends the cleaning request information to the device of the cleaning personnel, so that the cleaning personnel can understand the task to be completed, and ensure that the cleaning task can be completed.

[0118] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the application. The data collection in the above embodiment is in compliance, and its use or implementation does not involve hindering the public interest.

[0119] Corresponding to the method described in the above embodiment, only the part related to the embodiment of the application is shown for ease of description.

[0120] In one embodiment, Figure 6 is a structural schematic diagram of a cleaning device provided by an embodiment of the application.

[0121] As Figure 6 shown, the device comprises:

[0122] The communication module 30 is configured to receive the cleaning request information from the terminal device, and the cleaning request information comprises the information of the target to be cleaned or the information of the target to be cleaned and the target position.

[0123] Also used for sending cleaning instructions to the target cleaning device according to the information of the target cleaning device, the cleaning instructions being used to instruct the target cleaning device to move to the task position and then execute the cleaning task;

[0124] The prediction module 31 is configured to input the cleaning request information into the trained large language model, and obtain cleaning instructions output by the trained large language model, the cleaning instructions including information of the target cleaning device, the cleaning task, and the task position;

[0125] When the cleaning request information includes information of a target to be cleaned, the trained large language model is configured to determine the target cleaning device, the cleaning task, and the task position according to the information of the target to be cleaned, and output the cleaning instructions; when the cleaning request information includes information of a target to be cleaned and a target position, the trained large language model is configured to determine the target cleaning device and the cleaning task according to the information of the target to be cleaned, and determine the task position according to the target position, and output the cleaning instructions.

[0126] In one embodiment, the apparatus further comprises:

[0127] The acquisition module is further configured to acquire training data and labels, the training data including first data, second data, and third data, the first data including a position and a work content of a user, the second data including a position of the first camera device and an image collected by the first camera device, and the third data including a task triggered automatically at a preset time;

[0128] The training module is configured to fine-tune the large language model by using the training data until a value of a loss function of the large language model is less than a preset loss value, the loss function being used to calculate a difference value between an output result of the large language model and the labels;

[0129] Also used for obtaining the trained large language model when the value of the loss function is less than the preset loss value.

[0130] In one embodiment, the prediction module is further configured to input the cleaning request information into the trained large language model, and obtain an unprocessable instruction output by the trained large language model;

[0131] The communication module is further configured to send the unprocessable instruction to the terminal device, the unprocessable instruction being used to instruct the terminal device to send the cleaning request information to a device of a cleaning personnel;

[0132] The trained large language model is configured to determine that a size of the target to be cleaned is greater than a preset size according to the information of the target to be cleaned, or determine that the target position is empty according to the target position, and output the unprocessable instruction.

[0133] It should be noted that the information interaction, execution process and the like between the above apparatuses / units are based on the same concept as the method embodiments of the present application, and the specific functions and the technical effects brought by the same can be referred to the method embodiments part, and will not be repeated here.

[0134] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific name of each functional unit and module is only for convenient distinction, and does not limit the protection scope of the present application. The specific working process of the unit and module in the system can refer to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0135] The embodiment of the present application further provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps in each method embodiment.

[0136] The embodiment of the present application provides a computer program product, when the computer program product runs on an electronic device, the electronic device executes the steps in each method embodiment.

[0137] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the present application can implement all or part of the processes in the above-mentioned embodiment methods through a computer program to instruct relevant hardware to complete, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some cases, the computer readable medium can not be an electrical carrier signal and a telecommunication signal.

[0138] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0139] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0140] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / network device and method can be implemented in other ways. For example, the apparatus / network device embodiments described above are only schematic, for example, the division of the modules or units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection between each other can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0141] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may also be distributed to multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiment scheme according to actual needs.

[0142] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A cleaning method, characterized in that, include: Receive cleaning request information from a terminal device, the cleaning request information including information about the target to be cleaned and the target location; The cleaning request information is input into a trained large language model to obtain the cleaning instructions output by the trained large language model. The cleaning instructions include information about the target cleaning equipment, the cleaning task, and the task location. Based on the information of the target cleaning device, a cleaning instruction is sent to the target cleaning device. The cleaning instruction is used to instruct the target cleaning device to move to the task location and then execute the cleaning task. Wherein, when the cleaning request information includes information about the target to be cleaned and the target location, the trained large language model is used to determine the target cleaning equipment and the cleaning task based on the information about the target to be cleaned, and to determine the task location based on the target location, and to output the cleaning instruction; The cleaning request information is generated by the terminal device after receiving the work content input by the user and obtaining the user's location. The work content includes information about the target to be cleaned. The cleaning request information is generated by the terminal device after receiving the image captured by the first camera device and obtaining the location of the first camera device. The image includes the imaging area of ​​the target to be cleaned, and each of the first cameras is installed in a different location. The target location includes the user's location and the location of the first camera device.

2. The method according to claim 1, characterized in that, Also includes: The cleaning request information is input into the trained large language model to obtain the unprocessable instruction output by the trained large language model. Send the unprocessable instruction to the terminal device, the unprocessable instruction being used to instruct the terminal device to send the cleaning request information to the cleaning personnel's equipment; The trained large language model is used to determine, based on the information of the target to be cleaned, that the size of the target to be cleaned is greater than a preset size, or to determine an empty position based on the target position, and to output the instruction that it cannot be processed.

3. The method according to any one of claims 1 to 2, characterized in that, The cleaning equipment includes a first cleaning robot and a second cleaning robot. The first cleaning robot includes a mobile base and a clamp, a container, and a second camera device disposed on the mobile base. The second cleaning robot is a fully automatic cleaning robot.

4. The method according to claim 3, characterized in that, The information about the mission location includes information about the target area and identification information representing the target location.

5. The method according to claim 4, characterized in that, Before inputting the cleaning request information into the trained large language model, the method further includes: Acquire training data and labels. The training data includes first data, second data and third data. The first data includes the user's location and work content. The second data includes the location of the first camera device and the captured images. The third data includes tasks that are automatically triggered at a preset time. Using the training data, the large language model is fine-tuned until the value of the loss function of the large language model is less than a preset loss value. The loss function is used to calculate the difference between the output of the large language model and the label. When the value of the loss function is less than the preset loss value, the trained large language model is obtained.

6. A cleaning device, characterized in that, include: The communication module is used to receive cleaning request information from the terminal device, the cleaning request information including information about the target to be cleaned and the target location; It is also used to send a cleaning instruction to the target cleaning device based on the information of the target cleaning device, the cleaning instruction being used to instruct the target cleaning device to move to the task position and then perform the cleaning task; The prediction module is used to input the cleaning request information into a trained large language model to obtain the cleaning instructions output by the trained large language model. The cleaning instructions include information about the target cleaning equipment, the cleaning task, and the task location. Wherein, when the cleaning request information includes information about the target to be cleaned and the target location, the trained large language model is used to determine the target cleaning equipment and the cleaning task based on the information about the target to be cleaned, and to determine the task location based on the target location, and to output the cleaning instruction; The cleaning request information is generated by the terminal device after receiving the work content input by the user and obtaining the user's location. The work content includes information about the target to be cleaned. The cleaning request information is generated by the terminal device after receiving the image captured by the first camera device and obtaining the location of the first camera device. The image includes the imaging area of ​​the target to be cleaned, and each of the first cameras is installed in a different location. The target location includes the user's location and the location of the first camera device.

7. The apparatus according to claim 6, characterized in that, Also includes: The acquisition module is used to acquire training data and labels. The training data includes first data, second data and third data. The first data includes the user's location and work content. The second data includes the location of the first camera device and the captured images. The third data includes tasks that are automatically triggered at a preset time. The training module is used to fine-tune the large language model using the training data until the value of the loss function of the large language model is less than a preset loss value. The loss function is used to calculate the difference between the output of the large language model and the label. It is also used to obtain the trained large language model when the value of the loss function is less than the preset loss value.

8. A cleaning system, characterized in that, Includes servers, terminal equipment, and at least one cleaning device; The terminal device is used to send the cleaning request information to the server after obtaining the cleaning request information; The server is configured to receive the cleaning request information from the terminal device, the cleaning request information including information about the target to be cleaned and the target location; The cleaning request information is input into the trained large language model to obtain the cleaning instructions output by the trained large language model. Based on the information of the target cleaning equipment, a cleaning instruction is sent to the target cleaning equipment, the cleaning instruction including information about the target cleaning equipment, the cleaning task, and the task location; The target cleaning device is used to receive a cleaning instruction from the server, move to the task location according to the cleaning instruction, and perform the cleaning task. Wherein, when the cleaning request information includes information about the target to be cleaned and the target location, the trained large language model is used to determine the target cleaning equipment and the cleaning task based on the information about the target to be cleaned, and to determine the task location based on the target location, and to output the cleaning instruction; The cleaning request information is generated by the terminal device after receiving the work content input by the user and obtaining the user's location. The work content includes information about the target to be cleaned. The cleaning request information is generated by the terminal device after receiving the image captured by the first camera device and obtaining the location of the first camera device. The image includes the imaging area of ​​the target to be cleaned, and each of the first cameras is installed in a different location. The target location includes the user's location and the location of the first camera device.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images