Cleaning planning method and device, electronic equipment and storage medium
By collecting information on cleaning resources and environmental monitoring data, and using neural network models to predict the level of sanitation status, a cleaning plan is generated, and resources are allocated rationally. This solves the problem of low waste collection efficiency caused by unreasonable cleaning planning, and achieves efficient waste collection and environmental cleanliness.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-25
- Publication Date
- 2026-03-27
AI Technical Summary
Existing cleaning planning methods result in poor waste collection efficiency, uneven distribution of cleaning resources, and inability to promptly empty trash cans that are nearly full or already full.
By collecting information on cleaning resources and environmental monitoring data, a neural network model is used to predict the sanitation status level of the area to be cleaned, generate a cleaning plan, rationally allocate cleaning resources, and prioritize the cleaning of areas with more serious sanitation conditions.
It improved garbage collection efficiency, ensured environmental cleanliness, rationally allocated cleaning resources, prioritized the treatment of severely polluted areas, and solved the problem of low garbage collection efficiency caused by unreasonable cleaning planning.
Smart Images
Figure CN121746142A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of smart city technology and relates to a cleaning planning method, device, electronic device and storage medium. Background Technology
[0002] In order to maintain the cleanliness of the urban environment, the health of residents, and the hygiene of public spaces, it is especially important to clean up garbage in a timely and efficient manner.
[0003] In related technologies, sweepers often collect garbage according to fixed routes and times. However, this method can lead to uneven distribution of cleaning resources, resulting in poor garbage collection efficiency. For example, when traveling along a fixed route and time, the sweeper may first reach garbage bins with less garbage before proceeding to full bins. This unreasonable cleaning plan will result in garbage in bins that are close to full or already full not being emptied in a timely manner. Summary of the Invention
[0004] In view of the above, it is necessary to provide a cleaning planning method, device, electronic equipment and storage medium that can solve the technical problem of poor waste collection efficiency caused by unreasonable cleaning planning.
[0005] On the one hand, this application provides a cleaning planning method, the method comprising: collecting cleaning resource information and environmental monitoring data of multiple areas to be cleaned; predicting the sanitary status level of each area to be cleaned based on the environmental monitoring data of each area to be cleaned; and generating a cleaning plan corresponding to the multiple areas to be cleaned based on the cleaning resource information and the sanitary status level of the multiple areas to be cleaned.
[0006] In some embodiments of this application, the environmental monitoring data for each area to be cleaned includes one or more of the following: environmental image data of the street in each area to be cleaned, real-time status data of garbage at the garbage collection location on the street, and historical status data.
[0007] In some embodiments of this application, predicting the sanitary status level of each area to be cleaned based on environmental monitoring data includes: extracting features from the environmental monitoring data of each area to be cleaned using a neural network model to obtain multiple features; determining a feature vector based on the multiple features; predicting the feature vector to obtain a confidence level for each area to be cleaned corresponding to multiple preset sanitary levels; and determining the sanitary status level from the multiple preset sanitary levels based on the confidence level.
[0008] In some embodiments of this application, the training of the neural network model includes: acquiring multiple environmental sample data and a label corresponding to each environmental sample data, wherein the label is used to indicate a preset hygiene level of each environmental sample data, and training a preset neural network based on the multiple environmental sample data and the label corresponding to each environmental sample data to obtain a neural network model.
[0009] In some embodiments of this application, generating a cleaning plan corresponding to the plurality of areas to be cleaned based on the cleaning resource information and the sanitary status levels of the plurality of areas to be cleaned includes: generating a cleaning planning task based on preset prompt information, the cleaning resource information and the sanitary status levels of the plurality of areas to be cleaned, wherein the prompt information is used to prompt the generation of the cleaning plan based on the cleaning resource information and the sanitary status levels of the plurality of areas to be cleaned, and inputting the cleaning planning task into a language model to obtain the cleaning plan.
[0010] In some embodiments of this application, the step of inputting the cleaning planning task into a language model to obtain the cleaning plan includes: determining cleaning planning information based on semantic analysis of the cleaning planning task, wherein the cleaning planning information includes the cleaning order of the plurality of areas to be cleaned, the cleaning resource information required for each area to be cleaned, and / or the cleaning time information for each area to be cleaned; generating the cleaning plan based on the cleaning planning information, wherein the cleaning resource information required for each area to be cleaned includes human resource information and / or tool resource information.
[0011] In some embodiments of this application, the method further includes: if there are multiple cleaning schemes, determining a target cleaning scheme from the multiple cleaning schemes, and sending the target cleaning scheme to a terminal device.
[0012] On the other hand, this application provides a cleaning planning device, the device comprising: a data acquisition module for acquiring cleaning resource information and environmental monitoring data of multiple areas to be cleaned; a prediction module for predicting the sanitary status level of each area to be cleaned based on the environmental monitoring data of each area to be cleaned; and a generation module for generating a cleaning plan corresponding to the multiple areas to be cleaned based on the cleaning resource information and the sanitary status level of the multiple areas to be cleaned.
[0013] On the other hand, this application provides an electronic device, the electronic device comprising: a memory storing at least one instruction; and a processor executing the at least one instruction to implement the cleaning planning method.
[0014] On the other hand, this application provides a computer-readable storage medium storing at least one instruction that, when executed by a processor in an electronic device, implements the cleaning planning method.
[0015] In the cleaning planning scheme provided in this application embodiment, environmental monitoring data of the area to be cleaned can reflect the sanitary status of the area. Therefore, the sanitary status level of each area to be cleaned can be predicted through environmental monitoring data, and the sanitary status level can reflect the severity of the sanitary status of the area to be cleaned. Since cleaning resource information can reflect the available cleaning resources, a cleaning plan can be generated by comprehensively considering the cleaning resource information and the sanitary status level. This not only allows for the rational allocation of cleaning resources to each area to be cleaned, but also prioritizes the cleaning of areas with more serious sanitary status, thereby improving waste collection efficiency and solving the technical problem of poor waste collection efficiency due to unreasonable cleaning planning. Attached Figure Description
[0016] Figure 1 This is a schematic diagram of a cleaning planning system provided in an embodiment of this application.
[0017] Figure 2 This is a flowchart of a cleaning planning method provided in an embodiment of this application.
[0018] Figure 3 This is a functional block diagram of a cleaning planning device provided in one embodiment of this application.
[0019] Figure 4 This is a schematic diagram of the structure of a cloud server provided in one embodiment of this application. Detailed Implementation
[0020] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.
[0021] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner. Unless otherwise specified, the following embodiments and features described herein can be combined with each other.
[0022] This application provides a cleaning planning method that can improve waste collection efficiency and ensure environmental cleanliness. The cleaning planning method provided in this application can be applied to one or more electronic devices, such as servers, laptops, mobile phones, and computers. The server can be a cloud server or a server cluster. This application does not limit the type of electronic device.
[0023] To facilitate the explanation of the cleaning planning method provided in the embodiments of this application, the following description will use a cloud server as an example.
[0024] like Figure 1 The diagram shown is a schematic representation of a cleaning planning system provided in an embodiment of this application. Figure 1 The cleaning planning system includes a data acquisition device 10, a cloud server 20, and a terminal device 30.
[0025] In some embodiments of this application, the data acquisition device 10 is used to collect cleaning resource information and environmental monitoring data of multiple areas to be cleaned, and to send the collected cleaning resource information and environmental monitoring data to the cloud server 20.
[0026] The cleaning resource information collected by the data acquisition device 10 may include human resource information and / or tool resource information. For example, human resource information may include information such as the number of cleaning personnel on duty, and tool resource information may include information such as the location, status, and quantity of idle cleaning tools. Cleaning tools include, but are not limited to: the location of cleaning carts, brooms, high-pressure water guns, dustpans, and pick-up clips.
[0027] Environmental monitoring data for each area to be cleaned includes one or more of the following: street environmental image data, real-time status data of garbage at garbage collection locations on the street, and historical status data. The garbage collection location can be the coordinates or coordinate range of a garbage collection device, which can be a garbage can, garbage bin, etc. Real-time garbage status data can include one or more of the following: real-time garbage weight, real-time garbage volume, and real-time garbage height. Historical garbage status data can include one or more of the following: historical garbage weight, historical garbage volume, and historical garbage height.
[0028] The data acquisition device 10 may include a collection of devices for collecting cleaning resource information and environmental monitoring data. For example, the data acquisition device 10 may include an attendance machine for recording the attendance of cleaning personnel, a visual sensor (e.g., a camera and monitor) for collecting environmental image data, a position sensor for acquiring information such as the location of cleaning tools like cleaning vehicles, an ultrasonic sensor for acquiring the height of trash, and a weight sensor for acquiring the weight of trash. The position sensor may be a Global Positioning System (GPS) and may be located inside the cleaning vehicle, while the ultrasonic sensor and weight sensor may be located inside the trash collection device. The location of the cleaning tools may be their coordinates or a range of coordinates. The above examples of methods for acquiring cleaning resource information and environmental monitoring data are merely illustrative and are not limited to practical applications.
[0029] In some embodiments of this application, the cloud server 20 is used to generate a cleaning plan for cleaning multiple areas to be cleaned based on cleaning resource information and environmental monitoring data, and to send the cleaning plan to the terminal device 30.
[0030] The cloud server 20 can determine the number of cleaning staff present and other information based on the received attendance records. By analyzing the locations of the cleaning tools, the cloud server 20 can determine the number, location, and status of idle cleaning tools. For example, by analyzing the locations of the cleaning tools, the cloud server 20 can identify cleaning tools that are stationary within a preset time period as idle cleaning tools, thereby determining the number and location of idle cleaning tools. The preset time period can be customized. The above examples of methods for determining the number of cleaning staff present and the number, location, and status of idle cleaning tools are merely illustrative and are not limited to practical applications.
[0031] In other embodiments of this application, the cloud server 20 can also obtain information such as the quantity, location, and status of idle cleaning tools such as brooms, dustpans, and / or high-pressure water guns as cleaning resource information. For example, the cloud server 20 can obtain information such as the quantity, location, and status of cleaning tools from an inventory management system for cleaning materials in various areas to be cleaned, thereby determining the quantity, location, and status of idle cleaning vehicles, brooms, dustpans, and / or high-pressure water guns. Alternatively, radio frequency identification (RFID) tags can be affixed to the cleaning tools, and the cloud server 20 can track various cleaning materials through these RFID tags to determine the quantity, location, and status of idle cleaning vehicles, brooms, dustpans, and / or high-pressure water guns.
[0032] In some embodiments of this application, the cloud server 20 can store the received cleaning resource information and environmental monitoring data in a database. The processor of the cloud server 20 can generate a cleaning plan by retrieving the cleaning resource information and environmental monitoring data from the database. The database may include a historical database for storing historical data; when new cleaning resource information and environmental monitoring data are received, historical cleaning resource information and environmental monitoring data can be stored in the historical database.
[0033] In some embodiments of this application, the terminal device 30 may be a screen display, workstation, or server of the environmental protection bureau of each area to be cleaned. For example, the screen display, workstation, or server may display the cleaning plan on a visualization panel for user viewing. Alternatively, the terminal device 30 may also be a mobile phone or computer used by environmental protection workers. The above examples of the terminal device 30 are merely illustrative and are not limited to these in practical applications.
[0034] The data acquisition device 10 and the cloud server 20, as well as the cloud server 20 and the terminal device 30, can be connected via a communication module. The communication module can be a wired communication module and / or a wireless communication module. This application does not limit the type of communication module.
[0035] In other embodiments of this application, the data acquisition device 10 can send cleaning resource information and environmental monitoring data of multiple areas to be cleaned to an external device that communicates with the cloud server 20 for storage, so that the cloud server 20 can obtain cleaning resource information and environmental monitoring data of multiple areas to be cleaned from the external device, generate a cleaning plan based on the cleaning resource information and environmental monitoring data, and send the cleaning plan to the terminal device 30.
[0036] like Figure 2 The diagram shown is a flowchart of a cleaning planning method provided in one embodiment of this application. Depending on different needs, the order of the steps in this flowchart can be adjusted according to actual requirements, and some steps can be omitted. The method is applied to a cloud server, for example... Figure 4 The cloud server 20 shown.
[0037] S11 collects information on cleaning resources and environmental monitoring data for multiple areas to be cleaned.
[0038] In some embodiments of this application, the cleaning resource information may include human resource information and / or tool resource information, and the environmental monitoring data for each area to be cleaned includes one or more of the following: environmental image data of the streets in each area to be cleaned, real-time status data of garbage at garbage collection locations on the streets, and historical status data. The historical status data of the garbage can be obtained from a historical database.
[0039] For example, the environmental monitoring data for each area to be cleaned may include street environmental image data and real-time status data of garbage, or the environmental monitoring data for each area to be cleaned may include real-time status data and historical status data of garbage.
[0040] For details regarding cleanup resource information and environmental monitoring data, please refer to the description above; this application will not repeat the description.
[0041] In this embodiment, environmental monitoring data of the area to be cleaned can reflect the sanitary status of the area, and cleaning resource information can reflect the available cleaning resources.
[0042] S12, based on the environmental monitoring data of each area to be cleaned, predict the sanitary status level of each area to be cleaned.
[0043] In some embodiments of this application, the cloud server can extract features from the environmental monitoring data of each area to be cleaned based on a neural network model to obtain multiple features, determine a feature vector based on the multiple features, predict the feature vector to obtain the confidence level of each area to be cleaned corresponding to multiple preset hygiene levels, and determine the hygiene status level of each area to be cleaned from the multiple preset hygiene levels based on the confidence level.
[0044] The preset hygiene level can represent the degree of dirtiness or disorder in the hygiene status. Multiple preset hygiene levels can be customized, and this application does not limit this. For example, multiple preset hygiene levels may include no dirtiness, low dirtiness, medium dirtiness, and extreme dirtiness, where the degree of dirtiness corresponding to no dirtiness, low dirtiness, medium dirtiness, and extreme dirtiness can increase sequentially. The hygiene status level of each area to be cleaned can have a corresponding preset time period. For example, the preset time period can be the next day.
[0045] The neural network model can include a feature extraction module and a classification module. The feature extraction module can include, but is not limited to, network layers such as convolutional layers, pooling layers, fully connected layers, batch normalization layers, and activation function layers. Parameters such as the kernel size, stride, and padding in the convolutional layers, and the weight matrix and bias vector in the fully connected layers, can be customized. The classification module can include fully connected layers and activation functions. The fully connected layers can include a weight matrix and bias vectors, where each row or column of the weight matrix corresponds to a preset hygiene level.
[0046] If the environmental monitoring data for each area to be cleaned includes street environmental image data and real-time garbage status data, the multiple features can include features corresponding to the environmental image data and features corresponding to the real-time status data. Alternatively, if the environmental monitoring data for each area to be cleaned includes real-time garbage status data and historical garbage status data, the multiple features can include features corresponding to the real-time garbage status data and features corresponding to the historical garbage status data. The features corresponding to the environmental image data can be extracted using network layers such as convolutional layers, while the features corresponding to the real-time and historical status data can be extracted using network layers such as fully connected layers.
[0047] For example, the cloud server can concatenate the multiple features to obtain a feature vector. The cloud server can multiply the feature vector with the weight matrix in the classification layer to obtain a multiplied vector. Adding this multiplied vector to the bias vector in the classification layer yields the original score corresponding to each preset hygiene level. Calculating the original score for each preset hygiene level using the activation function formula, the confidence / probability of each area to be cleaned corresponding to each preset hygiene level can be obtained. Each confidence level can be in the range of 0 to 1.
[0048] For example, the method for calculating the confidence / probability of each area to be cleaned corresponding to each preset hygiene level can refer to formula (1):
[0049]
[0050] Among them, P i This represents the confidence / probability of each area to be cleaned corresponding to the i-th preset hygiene level, z. i This represents the original score of each area to be cleaned corresponding to the i-th preset hygiene level, where C represents the number of preset hygiene levels, and z j This indicates that each area to be cleaned corresponds to the original score of the j-th preset hygiene level.
[0051] Based on the confidence level of each area to be cleaned corresponding to each preset hygiene level, multiple confidence levels can be obtained for each area to be cleaned. Among the multiple confidence levels for each area to be cleaned, the cloud server can determine the preset hygiene level corresponding to the highest confidence level as the hygiene status level of each area to be cleaned.
[0052] In some embodiments of this application, the cloud server can obtain a neural network model by training a neural network, wherein the neural network may include, but is not limited to, deep learning networks such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). The Convolutional Neural Network may be networks such as LeNet, AlexNet, and ResNet, and this application does not impose any limitations on this.
[0053] The training of the neural network model includes: obtaining multiple environmental sample data and corresponding labels for each environmental sample data from a cloud server. The labels are used to indicate the preset hygiene level of each environmental sample data. Based on the multiple environmental sample data and the corresponding labels for each environmental sample data, the preset neural network is trained to obtain the neural network model.
[0054] For an explanation of the environmental sample data, please refer to the description of the environmental monitoring data above.
[0055] The cloud server can encode the labels corresponding to each environmental sample data based on multiple preset hygiene levels to obtain an encoding vector corresponding to each environmental sample data. This application does not limit the encoding method. For example, the cloud server can encode the labels corresponding to each environmental sample data based on multiple preset hygiene levels. In the encoding vector corresponding to each environmental sample data, the encoding value corresponding to the preset hygiene level indicated by the label corresponding to each environmental sample data can be the value 1, and the encoding values corresponding to other preset hygiene levels besides the preset hygiene level indicated by the label corresponding to each environmental sample data can be the value 0.
[0056] By inputting multiple environmental sample data into a neural network for prediction, the confidence level of each environmental sample data corresponding to multiple preset hygiene levels can be obtained, thereby obtaining multiple confidence levels corresponding to each environmental sample data. The prediction loss of the neural network is calculated based on the encoding vector corresponding to each environmental sample data and multiple confidence levels using a preset loss function. The network parameters of the neural network are adjusted according to the prediction loss until the loss value is within a preset range, thus obtaining the neural network model.
[0057] The preset loss function can be cross-entropy loss, and this application does not restrict the type of preset loss function. The network parameters of the neural network can be learning rate, weights, and biases, etc. The preset range can be customized. For example, the preset range can be 0 to 1.
[0058] For example, the calculation method for predicted loss can refer to the following formula (2):
[0059]
[0060] Where L represents the predicted loss, N can represent the number of multiple environmental sample data, C represents the number of multiple preset hygiene levels, and y in P represents the encoded value of the nth environmental sample data corresponding to the i-th preset hygiene level in the encoded vector of the nth environmental sample data. in This represents the confidence level of the nth environmental sample data corresponding to the i-th preset hygiene level.
[0061] In this embodiment, the sanitation status level reflects the severity / dirtiness of the sanitation status of the area to be cleaned. By using a neural network to predict environmental monitoring data, the sanitation status level of each area to be cleaned can be accurately determined.
[0062] S13: Based on the cleaning resource information and the sanitary status level of multiple areas to be cleaned, generate cleaning plans corresponding to multiple areas to be cleaned.
[0063] In some embodiments of this application, the cloud server generates cleaning plans corresponding to multiple areas to be cleaned based on cleaning resource information and the hygiene status levels of multiple areas to be cleaned. This includes: generating a cleaning planning task based on preset prompt information, cleaning resource information, and the hygiene status levels of multiple areas to be cleaned; the prompt information is used to prompt the generation of cleaning plans based on cleaning resource information and the hygiene status levels of multiple areas to be cleaned; and inputting the cleaning planning task into a language model to obtain the cleaning plan.
[0064] The prompt message can be customized, and this application does not impose any restrictions on it.
[0065] This application does not limit the type of language model. For example, the language model can be GPT4, ChatGLM, BERT, Qwen-14B, Baichuan-7B, and Qwen-7B, etc.
[0066] For example, the cloud server can determine cleaning planning information based on semantic analysis of the cleaning planning task. The cleaning planning information includes, but is not limited to: the cleaning order of multiple areas to be cleaned, the cleaning resource information required for each area to be cleaned, and / or the cleaning time information for each area to be cleaned. Based on the cleaning planning information, a cleaning plan is generated.
[0067] For example, the cleaning order for areas with higher levels of dirt and disorder can take precedence over the cleaning order for areas with lower levels of dirt and disorder. The cleaning resource information required for each area to be cleaned may include the number of cleaning personnel, cleaning vehicles, and cleaning tools such as brooms required for each area. The cleaning time information for each area to be cleaned may include the start time and estimated cleaning duration.
[0068] For example, if the areas to be cleaned include A, B, and C, a neural network model is used to predict the sanitation status levels of areas A, B, and C based on the environmental image data of the streets in areas A, B, and C, as well as the real-time weight, volume, and height of trash cans. If the sanitation status level of area A is "no dirt or disorder," the sanitation status level of area B is "low dirt or disorder," and the sanitation status level of area C is "extremely dirty or disorderly," a cleaning plan task is generated based on the available cleaning personnel, cleaning vehicles, and the sanitation status levels of areas A, B, and C. The cleaning plan task is then input into a language model, resulting in a cleaning plan that requires dispatching two cleaning personnel and one cleaning vehicle to areas C, B, and A in sequence to collect and empty the trash cans.
[0069] For example, if the areas to be cleaned include D, E, and F, a neural network model is used to predict the historical and real-time garbage weight, historical and real-time garbage volume, historical and real-time garbage height of the trash cans on the streets of areas D, E, and F, respectively, to obtain the sanitation status level of areas D, E, and F. If the sanitation status level of area D is extremely dirty, that of area E is moderately dirty, and that of area F is not dirty, a cleaning plan task is generated based on the available cleaning personnel, cleaning vehicles, garbage shovels, and the sanitation status levels of areas D, E, and F. The cleaning plan task is then input into a language model, resulting in a cleaning plan that requires dispatching 6 cleaning personnel, 2 cleaning vehicles, and tools such as pick-up clips and brooms to sequentially clean the street garbage in areas D, E, and F.
[0070] In some embodiments of this application, if the cleaning plan is a single one, the cloud server can send the cleaning plan to the terminal device (e.g., [device name]) that is connected to the cloud server. Figure 1 (See terminal device 30). If there are multiple cleaning schemes, the cloud server can determine the target cleaning scheme from among them and send the target cleaning scheme to the terminal device. For example, the cloud server can randomly select one cleaning scheme from among the multiple cleaning schemes as the target cleaning scheme, or the cloud server can determine the cleaning scheme with the shortest cleaning time as the target cleaning scheme. The above example of the method for selecting the target cleaning scheme is only an example, and it is not limited to this in actual applications.
[0071] In this embodiment, by using a language model to make decisions on cleaning planning tasks, it is possible not only to rationally allocate cleaning resources to each area to be cleaned, but also to prioritize cleaning areas with more serious sanitation conditions. This can improve garbage collection efficiency and solve the technical problem of poor garbage collection efficiency caused by unreasonable cleaning planning.
[0072] In the cleaning planning scheme provided in this application embodiment, environmental monitoring data of the area to be cleaned can reflect the sanitary status of the area. Therefore, the sanitary status level of each area to be cleaned can be predicted through environmental monitoring data, and the sanitary status level can reflect the severity of the sanitary status of the area to be cleaned. Since cleaning resource information can reflect the available cleaning resources, a cleaning plan can be generated by comprehensively considering the cleaning resource information and the sanitary status level. This not only allows for the rational allocation of cleaning resources to each area to be cleaned, but also prioritizes the cleaning of areas with more serious sanitary status, thereby improving waste collection efficiency and solving the technical problem of poor waste collection efficiency due to unreasonable cleaning planning.
[0073] like Figure 3 The diagram shown is a functional block diagram of a cleaning planning device provided in an embodiment of this application. The cleaning planning device 206 includes a data acquisition module 2060, a prediction module 2061, a generation module 2062, and a push module 2063. The module / unit referred to in this application refers to a type of module / unit that can be... Figure 4 The processor 203 in the middle acquires a series of computer-readable instruction segments that are capable of performing a fixed function, which are stored in Figure 4 The memory 202 is used for this purpose. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.
[0074] The data acquisition module 2060 is used to collect information on cleaning resources and environmental monitoring data from multiple areas to be cleaned.
[0075] In some embodiments of this application, the environmental monitoring data for each area to be cleaned includes one or more of the following: environmental image data of the street in each area to be cleaned, real-time status data of garbage at the garbage collection location on the street, and historical status data.
[0076] The prediction module 2061 is used to predict the sanitary status level of each area to be cleaned based on the environmental monitoring data of each area to be cleaned.
[0077] In some embodiments of this application, the prediction module 2061 is further configured to extract features from the environmental monitoring data of each area to be cleaned based on a neural network model, obtain multiple features, determine a feature vector based on the multiple features, predict the feature vector to obtain the confidence level of each area to be cleaned corresponding to multiple preset hygiene levels, and determine the hygiene status level from the multiple preset hygiene levels based on the confidence level.
[0078] In some embodiments of this application, the prediction module 2061 is further configured to acquire multiple environmental sample data and a label corresponding to each environmental sample data, wherein the label is used to indicate a preset hygiene level of each environmental sample data, and to train a preset neural network based on the multiple environmental sample data and the label corresponding to each environmental sample data to obtain a neural network model.
[0079] The generation module 2062 is used to generate a cleaning plan corresponding to the multiple areas to be cleaned based on the cleaning resource information and the sanitary status level of the multiple areas to be cleaned.
[0080] In some embodiments of this application, the generation module 2062 is further configured to generate a cleaning plan task based on preset prompt information, the cleaning resource information, and the sanitary status levels of the multiple areas to be cleaned. The prompt information is used to prompt the generation of the cleaning plan based on the cleaning resource information and the sanitary status levels of the multiple areas to be cleaned. The cleaning plan task is input into a language model to obtain the cleaning plan.
[0081] In some embodiments of this application, the generation module 2062 is further configured to determine cleaning planning information based on semantic analysis of the cleaning planning task, wherein the cleaning planning information includes the cleaning order of the plurality of areas to be cleaned, the cleaning resource information required for each area to be cleaned, and / or the cleaning time information for each area to be cleaned, and generate the cleaning plan based on the cleaning planning information, wherein the cleaning resource information required for each area to be cleaned includes human resource information and / or tool resource information.
[0082] In some embodiments of this application, the push module 2063 is used to determine a target cleaning plan from multiple cleaning plans if there are multiple cleaning plans, and send the target cleaning plan to the terminal device.
[0083] like Figure 4 The diagram shown is a schematic representation of a cloud server provided in one embodiment of this application. The cloud server 20 can be a mobile phone, tablet computer, laptop computer, computer, or other cloud server. This embodiment of the application does not impose any restrictions on the specific type of cloud server.
[0084] like Figure 4 As shown, the cloud server 20 may include a communication module 201, a memory 202, a processor 203, an input / output (I / O) interface 204, and a bus 205. The processor 203 is coupled to the communication module 201, the memory 202, and the input / output interface 204 via the bus 205.
[0085] Communication module 201 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more wired communication solutions such as Universal Serial Bus (USB) and Controller Area Network (CAN). The wireless communication module may provide one or more wireless communication solutions such as Wireless Fidelity (Wi-Fi), Bluetooth (BT), mobile communication networks, Frequency Modulation (FM), Near Field Communication (NFC), and Infrared (IR).
[0086] Memory 202 may include one or more random access memory (RAM) and one or more non-volatile memory (NVM). The RAM can be directly read and written by the processor 203, and can be used to store executable programs (e.g., machine instructions) of other running programs, as well as user and application data. The RAM may include static random-access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.
[0087] Non-volatile memory can also store executable programs and user and application data, and can be pre-loaded into random access memory for direct reading and writing by the processor 203. Non-volatile memory can include disk storage devices and flash memory. For example, flash memory can be Nand Flash.
[0088] Memory 202 is used to store one or more computer programs. The one or more computer programs are configured to be executed by processor 203. The one or more computer programs include multiple instructions that, when executed by processor 203, enable a cleaning planning method to be executed on cloud server 20.
[0089] In other embodiments, such as Figure 4 The cloud server 20 shown also includes an external storage interface for connecting to external storage devices to expand the storage capacity of the cloud server 20.
[0090] Processor 203 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.
[0091] The processor 203 provides computing and control capabilities; for example, the processor 203 is used to execute computer programs stored in the memory 202 to implement the cleaning planning method described above.
[0092] The input / output interface 204 is used to provide a channel for user input or output. For example, the input / output interface 204 can be used to connect various input / output devices, such as a mouse, keyboard, touch device, display screen, etc., so that users can enter information or visualize information.
[0093] Bus 205 is used at least to provide a channel for communication between the communication module 201, memory 202, processor 203, and input / output interface 204 in the cloud server 20.
[0094] It is understood that the structure illustrated in the embodiments of this application does not constitute a specific limitation on the cloud server 20. In other embodiments of this application, the cloud server 20 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
[0095] This application also provides a computer-readable storage medium storing a computer program, which includes program instructions. When the program instructions are executed, the method implemented can refer to the methods in the above embodiments of this application.
[0096] The computer-readable storage medium can be the internal memory of the electronic device described in the above embodiments, such as the hard disk or memory of the electronic device. Alternatively, the computer-readable storage medium can be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., installed on the electronic device.
[0097] In some embodiments, a computer-readable storage medium may include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of the electronic device, etc.
[0098] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.
[0099] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0100] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.
[0101] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No appended diagram markings in the claims should be construed as limiting the scope of the claims.
[0102] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in this application may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.
[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.
Claims
1. A cleaning planning method, characterized in that, The method includes: Collect information on cleaning resources and environmental monitoring data from multiple areas awaiting cleaning; Based on the environmental monitoring data of each area to be cleaned, the sanitary status level of each area to be cleaned is predicted; Based on the cleaning resource information and the sanitary status level of the multiple areas to be cleaned, a cleaning plan is generated for each of the multiple areas to be cleaned.
2. The cleaning planning method as described in claim 1, characterized in that, The environmental monitoring data for each area to be cleaned includes one or more of the following: environmental image data of the street in each area to be cleaned, real-time status data of garbage at the garbage collection location on the street, and historical status data.
3. The cleaning planning method as described in claim 1, characterized in that, The prediction of the sanitary status level of each area to be cleaned based on environmental monitoring data includes: Based on the neural network model, feature extraction is performed on the environmental monitoring data of each area to be cleaned to obtain multiple features; Determine the feature vector based on the multiple features; The feature vector is predicted to obtain the confidence level of each area to be cleaned corresponding to multiple preset hygiene levels; The hygiene status level is determined from the plurality of preset hygiene levels based on the confidence level.
4. The cleaning planning method as described in claim 3, characterized in that, The training of the neural network model includes: Acquire multiple environmental sample data and a label corresponding to each environmental sample data, wherein the label is used to indicate the preset hygiene level of each environmental sample data; Based on the multiple environmental sample data and the corresponding labels for each environmental sample data, a preset neural network is trained to obtain a neural network model.
5. The cleaning planning method as described in claim 1, characterized in that, The step of generating cleaning plans for the multiple areas to be cleaned based on the cleaning resource information and the sanitary status levels of the multiple areas to be cleaned includes: Based on the preset prompt information, the cleaning resource information, and the sanitary status levels of the multiple areas to be cleaned, a cleaning plan task is generated. The prompt information is used to prompt the generation of the cleaning plan based on the cleaning resource information and the sanitary status levels of the multiple areas to be cleaned. The cleaning planning task is input into the language model to obtain the cleaning solution.
6. The cleaning planning method as described in claim 5, characterized in that, The step of inputting the cleaning planning task into the language model to obtain the cleaning solution includes: Based on the semantic analysis of the cleaning planning task, cleaning planning information is determined, wherein the cleaning planning information includes the cleaning order of the multiple areas to be cleaned, the cleaning resource information required for each area to be cleaned, and / or the cleaning time information for each area to be cleaned. Based on the cleaning planning information, the cleaning plan is generated, wherein the cleaning resource information required for each area to be cleaned includes human resource information and / or tool resource information.
7. The cleaning planning method as described in claim 1, characterized in that, The method further includes: If there are multiple cleaning schemes, a target cleaning scheme is determined from the multiple cleaning schemes and the target cleaning scheme is sent to the terminal device.
8. A cleaning planning device, characterized in that, The device includes: The data acquisition module is used to collect information on cleaning resources and environmental monitoring data from multiple areas to be cleaned. The prediction module is used to predict the sanitary status level of each area to be cleaned based on the environmental monitoring data of each area. The generation module is used to generate cleaning plans corresponding to the multiple areas to be cleaned based on the cleaning resource information and the sanitary status level of the multiple areas to be cleaned.
9. An electronic device, characterized in that, The electronic device includes: Memory, storing at least one instruction; and The processor executes the at least one instruction to implement the cleaning planning method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, which, when executed by a processor in an electronic device, implements the cleaning planning method as described in any one of claims 1 to 7.