Book packaging method and device based on readable fields, server and medium

Abstract

The invention provides a book packaging method and device based on a read-suitable field, a server and a medium. The method comprises the following steps: receiving book order information; identifying a read-suitable field corresponding to each book category in the to-be-packaged book list; generating a first book distribution strategy based on the read-suitable fields and the stored book lists corresponding to the book warehouses; for each target book storehouse, dividing the to-be-packaged book sub-list corresponding to the target book storehouse into a plurality of picking lists based on the read-suitable fields, and generating a second book distribution strategy based on the dispatchable robot number range and the current state information of each book sorting robot in the target book storehouse; and according to the second book distribution strategy, the target book sorting robot is controlled to execute a book packaging action according to the corresponding picking list. The book sorting efficiency and the automation degree can be remarkably improved, and the experience of sells, purchasers and warehouse management can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of book packaging, and in particular, to a book packaging method, device, server, and medium based on suitable reading fields. Background Art

[0003] The deficiencies of traditional book management software systems in the classification of the extracurricular reading system of the Chinese New Curriculum Standard. Specifically, with the implementation of the Chinese New Curriculum Standard, the classification of the extracurricular reading system has gradually become an important part of primary and secondary education. However, traditional book management software systems have not been updated in a timely manner and have failed to cover this new classification system, resulting in the inability to accurately identify the suitable school age segments for book products in the system. This defect has brought many inconveniences to the sales side, the purchasing side, and the warehouse management. In addition, the current common method for book sorting is for warehouse management personnel to manually sort and package the corresponding books according to the sales order, resulting in low book sorting efficiency and low automation. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a book packaging method, device, server, and medium based on suitable reading fields, which can significantly improve the efficiency and automation of book sorting, and also help to improve the experience of the sales side, the purchasing side, and the warehouse management.

[0005] In a first aspect, the present invention provides a book packaging method based on suitable reading fields. The method is applied to a server in a book storage system, and the book storage system further includes book sorting robots deployed in each book warehouse. The server is communicatively connected to the book sorting robots. The method includes: Receiving book order information, where the book order information at least includes a list of books to be packaged, and the list of books to be packaged is used to describe the book categories corresponding to each school age segment and their quantity information; Identifying the suitable reading fields corresponding to each book category in the list of books to be packaged, where the suitable reading fields are used to describe the suitability of the book category for its corresponding school age segment; Based on the suitable reading fields and the list of books already in stock corresponding to each book warehouse, with the goal of minimizing the number of allocated book warehouses and the number of book sorting robots scheduled in each book warehouse, generating a first book allocation strategy, where the first book allocation strategy is used to describe at least one target book warehouse and its corresponding sub-list of books to be packaged and the range of the number of schedulable robots; For each target book storage, divide the sub-list of books to be packed corresponding to the target book storage into multiple picking lists based on the suitable-for-reading fields, and generate a second book allocation strategy based on the range of the number of schedulable robots and the current status information of each book sorting robot in the target book storage. The second book allocation strategy is used to describe the target book sorting robots to be scheduled in the target book storage and their corresponding picking lists. According to the second book allocation strategy, control the target book sorting robots to perform book packing actions according to their corresponding picking lists.

[0006] In one implementation, based on the suitable-for-reading fields and the list of books already in storage corresponding to each book storage, with the goal of minimizing the number of allocated book storages and the number of book sorting robots scheduled in each book storage, generate a first book allocation strategy, including: According to the suitability constraint, based on the suitable-for-reading fields corresponding to each book category in the list of books to be packed and the list of books already in storage corresponding to each book storage, generate an initial set of book allocation strategies. The suitability constraint is that book categories corresponding to the same school age segment and the same suitable-for-reading fields are preferentially allocated to the same book storage. For any alternative book allocation strategy in the set of book allocation strategies, generate the fitness value corresponding to the alternative book allocation strategy with the goals of minimizing the number of book storages, minimizing the number of book sorting robots scheduled in each book storage, and maximizing the concentration of suitable-for-reading fields. Screen multiple alternative book allocation strategies from the set of book allocation strategies based on the fitness value, and perform crossover and mutation operations on the selected book allocation strategies to obtain new alternative book allocation strategies, so as to form a new set of book allocation strategies. Until the iteration stop condition is met, take the alternative book allocation strategy corresponding to the maximum fitness value in the set of book allocation strategies at this time as the first book allocation strategy.

[0007] In one implementation, the end of the robotic arm of each book sorting robot is equipped with a whole-pack book gripper and a single-book gripper; based on the range of the number of schedulable robots and the current status information of each book sorting robot in the target book storage, generate a second book allocation strategy, including: Publish the book packing tasks of the picking lists to the task pool. For any book packing task in the task pool, receive the competition requests initiated by each book sorting robot in the target book warehouse for this book packing task, determine the task cost corresponding to each book sorting robot based on the current status information carried in the competition request, determine the target book sorting robot corresponding to the picking list of this book packing task according to the task cost corresponding to each book sorting robot and the range of the number of schedulable robots, and remove this book packing task from the task pool; where the current status information includes the distance between the current position of the book sorting robot and the position information corresponding to this book packing task, the type of gripper currently used by the book sorting robot, and the power information of the book sorting robot. Continue to determine the target book sorting robot corresponding to the picking list of the next book packing task until the task pool is empty, and obtain the second book allocation strategy.

[0008] In one implementation, according to the second book allocation strategy, control the target book sorting robot to perform the book packing action according to its corresponding picking list, including: Obtain the warehouse grid model corresponding to the target book warehouse, and the warehouse grid model describes the occupancy status of each grid in the target book warehouse through specified markers; Based on the warehouse grid model, the current position of the target book sorting robot and its corresponding picking list, plan the picking path corresponding to the target book sorting robot; Predict the time when the target book sorting robot reaches each grid in the target book warehouse based on the picking path to determine whether there is a situation where multiple target book sorting robots occupy the same grid at the same time; If so, perform pause control or obstacle avoidance control on the target book sorting robots that occupy the same grid at the same time, so that the target book sorting robot can successfully reach the grid corresponding to the picking list and perform the book packing action according to its corresponding picking list.

[0009] In one implementation, a vision device is mounted on the book sorting robot; performing the book packing action according to its corresponding picking list includes: After the target book sorting robot successfully reaches the grid corresponding to the picking list, obtain the shelf image data collected by the vision device; Locate the book to be grabbed based on the shelf image data and the position information described in the picking list, and identify whether the type of gripper currently used by the target book sorting robot matches the book to be grabbed based on the shelf image data; If not, switch the type of gripper currently used by the target book sorting robot, and use the switched gripper to perform the grabbing action and the book packing action on the book to be grabbed.

[0010] In one embodiment, the book storage system further includes a book monitoring device communicatively connected to the server. The book monitoring device includes a pressure sensor network and a camera network deployed on each shelf in the book warehouse. The camera network includes a top-layer fisheye lens, a middle-layer wide-angle lens, and a bottom-layer depth camera. The method further includes: Perceiving the pressure changes corresponding to each shelf board in the shelf through the pressure sensor network to monitor whether a book-in event or a book-out event occurs on the shelf based on the pressure changes; If so, locating the target shelf and shelf board where the book-in event or the book-out event occurs, activating the camera network corresponding to the target shelf and shelf board, and acquiring a book image set collected by the activated camera network for the target shelf and shelf board. The book image set includes an occupancy heat map collected by the top-layer fisheye lens, book image data collected by the middle-layer wide-angle lens, and book point cloud data collected by the bottom-layer depth camera; Updating the list of books already stored corresponding to the book warehouse according to the book image set.

[0011] In one embodiment, updating the list of books already stored corresponding to the book warehouse according to the book image set includes: In the case of a book-in event, perform the following operations: Identifying the in-storage event area of the target shelf and shelf board where the book-in event occurs based on the occupancy heat map; Cropping the first sub-image data corresponding to the in-storage event area from the book image data, and identifying the book spine data and book ISBN data corresponding to the newly stored book based on the first sub-image data; Determining the position information corresponding to the newly stored book according to the book spine data and the book point cloud data; Updating the list of books already stored based on the book ISBN data and position information corresponding to the newly stored book; In the case of a book-out event, perform the following operations: Identifying the out-storage event area of the target shelf and shelf board where the book-out event occurs based on the occupancy heat map; Cropping the second sub-image area corresponding to the out-storage event area from the book image data, and identifying the book ISBN data and position information corresponding to the already-out-stored book based on the second sub-image area and the previous frame of the second sub-image area; Updating the list of books already stored based on the book ISBN data and position information corresponding to the already-out-stored book.

[0012] In a second aspect, the present invention further provides a book packing device based on a suitable reading field. The device is applied to the server in the book storage system. The book storage system further includes book sorting robots deployed inside each book warehouse. The server is communicatively connected to the book sorting robots. The device includes: An order receiving module, configured to receive book order information, where the book order information at least includes a list of books to be packed, and the list of books to be packed is used to describe the book categories corresponding to each school age segment and their quantity information; A suitable reading recognition module, configured to recognize the suitable reading fields corresponding to each book category in the list of books to be packed, and the suitable reading fields are used to describe the suitability of the book category for its corresponding school age segment; A first allocation module, configured to generate a first book allocation strategy with the goal of minimizing the number of allocated book warehouses and the number of book sorting robots scheduled in each book warehouse based on the suitable reading fields and the list of books already stored in each book warehouse. The first book allocation strategy is used to describe at least one target book warehouse and its corresponding sub - list of books to be packed and the range of the number of schedulable robots; A second allocation module, for each target book warehouse, configured to divide the sub - list of books to be packed corresponding to the target book warehouse into multiple picking lists based on the suitable reading fields, and generate a second book allocation strategy based on the range of the number of schedulable robots and the current status information of each book sorting robot in the target book warehouse. The second book allocation strategy is used to describe the target book sorting robots scheduled in the target book warehouse and their corresponding picking lists; A book packing module, configured to control the target book sorting robots to perform book packing actions according to their corresponding picking lists according to the second book allocation strategy.

[0013] In a third aspect, the present invention further provides a server, including a processor and a memory. The memory stores computer - executable instructions that can be executed by the processor, and the processor executes the computer - executable instructions to implement the method according to any one of the first aspect.

[0014] In a fourth aspect, the present invention further provides a computer - readable storage medium, which stores computer - executable instructions. When the computer - executable instructions are called and executed by a processor, the computer - executable instructions cause the processor to implement the method according to any one of the first aspect.

[0015] The present invention provides a book packaging method, device, server and medium based on suitable-reading fields, which are applied to the server in the book storage system. The book storage system also includes a book sorting robot deployed in each book warehouse, and the server is in communication with the book sorting robot. First, the book order information is received. The book order information includes at least a list of books to be packaged. The list of books to be packaged is used to describe the book categories and quantity information corresponding to each school age group; then, the suitable-reading field corresponding to each book category in the list of books to be packaged is identified. The suitable-reading field is used to describe the readability of the book category relative to the school age group to which it belongs; on this basis, based on the suitable-reading field and the list of books already in the warehouse corresponding to each book warehouse, with the goal of minimizing the number of allocated book warehouses and minimizing the number of book sorting robots scheduled in each book warehouse, a first book allocation strategy is generated. The first book allocation strategy is used to describe at least one target The method identifies a target library warehouse and its corresponding sub-list of books to be packaged and the range of dispatchable robots. Then, for each target library warehouse, the sub-list of books to be packaged corresponding to the target library warehouse is divided into multiple picking lists based on the appropriate reading field. A second book allocation strategy is generated based on the range of dispatchable robots and the current status information of each book sorting robot in the target library warehouse. The second book allocation strategy is used to describe the target book sorting robots to be scheduled in the target library warehouse and their corresponding picking lists. Finally, according to the second book allocation strategy, the target book sorting robots are controlled to perform book packaging according to their corresponding picking lists. The method identifies the appropriate reading field corresponding to each book category in the list of books to be packaged, and then, based on the appropriate reading field, generates a first book allocation strategy with the library warehouse as the research object and a second book allocation strategy with the book sorting robot as the research object. This method controls the book sorting robots to perform book packaging according to the picking lists. The present invention not only significantly improves the efficiency and automation of book sorting, but also helps improve the experience of sellers, buyers, and warehouse management by packaging the book packages based on the appropriate reading field.

[0016] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 Schematic flow chart of a book packaging method based on suitable reading fields provided by an embodiment of the present invention; Figure 2 Schematic diagram of the core picking strategy of a book packaging method based on suitable reading fields provided by an embodiment of the present invention; Figure 3 Schematic diagram of the structure of a book packaging device based on suitable reading fields provided by an embodiment of the present invention; Figure 4 Schematic diagram of the structure of a server provided by an embodiment of the present invention. Specific embodiments

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0021] (1) Inconvenience for salesperson of the selling party: The salesperson of the selling party cannot accurately divide the suitable reading ranges for each grade in primary and secondary schools, so it is impossible to make accurate book recommendations for each school age segment. Therefore, the following problems exist: inaccurate recommendations: When the salesperson recommends books to schools, libraries, or parents, they cannot provide accurate recommendations based on the specific school age segment of the students, resulting in poor recommendation effects; low sales efficiency: Due to the lack of clear suitable reading segment information, the salesperson needs to spend more time on manual screening and recommendation, reducing the sales efficiency; decreased customer satisfaction: Inaccurate recommendations may lead to doubts about the professional ability of the selling party by customers, affecting customer satisfaction and long-term cooperation relationships.

[0022] (2) Inconveniences for the purchasers: Purchasers (such as schools, libraries, parents) cannot precisely know which school age group a book is suitable for reading, nor can they precisely know which books should be read by a certain school age group. Therefore, the following problems exist: Difficult selection: When parents select books for their children, they cannot accurately judge whether the books are suitable for their children's school age group, which may lead to inappropriate selection and affect their children's reading interest and effect; Chaotic management: After schools or libraries purchase books in batches, they need to screen and select each book variety one by one before they can distribute the books to the corresponding grades or borrowing shelves, increasing the management difficulty and workload; Resource waste: Due to the inability to accurately classify, some books may be wrongly assigned to inappropriate school age groups, resulting in resource waste.

[0023] (3) Inconveniences for the book warehouses: The warehouses cannot pack books according to the reading suitability classification requirements of schools or libraries. Therefore, the following problems exist: Low packing efficiency: When packing books, the warehouses cannot quickly and accurately pack according to the reading suitability classification requirements of schools or libraries, increasing the packing time and cost; Wrong distribution: Due to the lack of clear information on the suitable reading segments, books may be wrongly distributed to inappropriate schools or grades, affecting the distribution efficiency and customer satisfaction; Complex inventory management: Unable to manage the inventory according to the suitable reading segments, increasing the complexity and error rate of inventory management.

[0024] Based on this, the embodiments of the present invention provide a book packing method, device, server and medium based on suitable reading fields, which can significantly improve the efficiency and automation degree of book sorting, and also help to improve the experience of sellers, purchasers and warehouse management.

[0025] For the convenience of understanding this embodiment, first, a book packing method based on suitable reading fields disclosed in the embodiments of the present invention is introduced in detail. This method is applied to the server in the book warehousing system. The book warehousing system also includes book sorting robots deployed inside each book warehouse. The server is communicatively connected to the book sorting robots. Refer to Figure 1 the flow schematic diagram of a book packing method based on suitable reading fields shown in the figure. This method mainly includes the following steps S102 to step S110: Step S102, receive book order information.

[0026] Book order information includes at least a list of books to be packaged. This list describes the book categories and quantities for each school-age group. Books with the same title and publisher are considered to belong to the same category, for example, "How the Steel Was Tempered" published by the People's Education Press. Additionally, book order information may include customer information (such as company name, contact person, phone number, address, credit limit, total outstanding balance, etc.), auxiliary information (such as packaging requirements and shipping methods), and platform information (such as platform store name and platform order number).

[0027] Step S104: identifying the appropriate reading field corresponding to each book category in the list of books to be packaged.

[0028] The "suitable reading" field is used to describe the suitability of a book category relative to the school age group to which it belongs. In one example, the server pre-stores the "suitable reading" field corresponding to each book category. By reading the book categories included in the list of books to be packaged, the "suitable reading" field corresponding to each book category in the list of books to be packaged can be identified. For example, the "suitable reading" field can be divided into "first suitable reading," "second suitable reading," "third suitable reading," "teacher suitable reading," and so on. Different "suitable reading" fields can be set based on actual needs, and this is not limited in this embodiment of the present invention.

[0029] Step S106 , based on the read-only field and the list of stored books corresponding to each library, a first book allocation strategy is generated with the goal of minimizing the number of allocated library stores and the number of book sorting robots scheduled in each library.

[0030] The "in-stocked book list" describes the book categories, quantities, and locations of the books already in stock at the library. The first book allocation strategy describes at least one target library, its corresponding sub-list of books to be packaged, and the range of dispatchable robots. The sub-list of books to be packaged represents the book categories and quantities for which the target library needs to perform the packaging operation, while the range of dispatchable robots represents the range of book sorting robots that can be dispatched by the target library when performing the packaging operation.

[0031] In one example, an initial set of book allocation strategies can be generated based on the pre-configured readability constraints, the readability fields corresponding to each book category in the list of books to be packaged, and the list of books already in stock corresponding to each book warehouse. The book allocation strategy set includes multiple alternative book allocation strategies, which are used to describe at least one alternative book warehouse and its corresponding sub-list of books to be packaged and the range of the number of dispatchable robots; the fitness value corresponding to each alternative book allocation strategy is calculated by taking into account the number of book warehouses, the number of book sorting robots dispatched in each book warehouse, and the concentration of readability fields. The concentration of readability fields is used to describe the readability of books in the same school age group and the same readability. The book category corresponding to the read field is assigned to as few book warehouses as possible. The fewer the number of book warehouses assigned to it, the higher the value of the appropriate field concentration. Based on the fitness value, the alternative book allocation strategies are screened, crossed, mutated, and other operations are performed to form a new book allocation strategy set. After eliminating the alternative book allocation strategies that do not meet the readability constraint in the new book allocation strategy set, the fitness value corresponding to each alternative book allocation strategy in the new book allocation strategy set is recalculated. This process is repeated until the iteration stop condition is met (such as reaching a preset number of iterations). The alternative book allocation strategy with the highest fitness value in the book allocation strategy set at this time is selected as the first book allocation strategy.

[0032] Step S108: For each target library warehouse, the sub-list of books to be packaged corresponding to the target library warehouse is divided into multiple picking lists based on the read-appropriate field, and a second book allocation strategy is generated based on the range of the number of dispatchable robots and the current status information of each book sorting robot in the target library warehouse.

[0033] The current state information includes the distance between the book sorting robot's current location and the location corresponding to the book packaging task, the gripper type currently used by the book sorting robot, and the book sorting robot's battery level. The second book allocation strategy describes the target book sorting robot to be dispatched within the target library and its corresponding picking list. The picking list describes the number of book categories to be sorted by the target book sorting robot and their locations. Specifically, the location of a book category can be described by the shelf, the level within the shelf, and the specific coordinates within the level.

[0034] In one example, for each target library warehouse, the same book category is prioritized and assigned to the same picking list. If the quantity of a certain book category is greater than the preset packaging quantity, it can be divided into two or more picking lists; if the quantity of a certain book category is less than the preset packaging quantity, book categories of the same school age group and the same reading field can be assigned to the same picking list.

[0035] On this basis, the book sorting tasks corresponding to the picking lists can be published to the task pool. For each book sorting task in the task pool, competition requests uploaded by each book sorting robot in the target book warehouse for this book sorting task can be received. Then, according to the current status information of each book sorting robot, the corresponding target book sorting robot can be assigned to this book sorting task, and this book sorting task can be removed from the task pool. Next, continue to determine the target book sorting robot corresponding to the next book sorting task in the task pool, and repeat this process until the task pool is empty, then the second book allocation strategy can be obtained.

[0036] Step S110, according to the second book allocation strategy, control the target book sorting robot to perform the book packing action according to its corresponding picking list.

[0037] In one example, each target book sorting robot moves in the target book warehouse according to its corresponding picking list, performs conflict detection during the movement, and in the case of conflicts between two or more target book sorting robots, control the relevant target book sorting robots to pause or avoid obstacles, so that each target book sorting robot can safely reach the position described in its corresponding picking list; after the target book sorting robot reaches the position described in its corresponding picking list, it can use the vision device carried on it to locate the book to be grabbed, determine whether to switch the gripper it is currently using, etc., so as to realize the grabbing and packing of the book to be grabbed.

[0038] The book packing method based on the suitable reading field provided by the embodiments of the present invention, by identifying the suitable reading fields corresponding to each book category in the list of books to be packed, and then on the basis of this suitable reading field, generating the first book allocation strategy with the book warehouse as the research object and generating the second book allocation strategy with the book sorting robot as the research object, so as to control the book sorting robot to perform the book packing action according to the picking list. The present invention not only significantly improves the efficiency and automation degree of book sorting, but also the book packages obtained by packing based on the suitable reading field are helpful to improve the experience of the seller, the buyer and the warehouse management.

[0039] On the basis of the foregoing embodiments, the embodiments of the present invention provide a core picking strategy for the book packing method based on the suitable reading field. See Figure 2The core picking strategy diagram of a book packaging method based on the readability field is shown, including: (1) first determining the target library warehouse according to the range priority order of the designated library warehouse and whether the library warehouse has sufficient inventory; (2) under a target library warehouse, splitting the picking list according to the readability field (such as the 1st / 2nd / 3rd readability and teacher applicable); (3) calculating the optimal picking path for the target library warehouse based on the picking list, including each target book picking robot and its corresponding picking list and picking path. Among them, when there are too many book categories, one picking list is formed for every 200 categories to facilitate parallel picking.

[0040] Based on the above core picking strategy, an embodiment of the present invention provides a specific implementation of a book packaging method based on readable fields.

[0041] In one embodiment, the book storage system also includes a book monitoring device that is communicatively connected to the server. The book monitoring device includes a pressure sensor network and a camera network deployed on each shelf in the book warehouse. The camera network includes a top-level fisheye lens, a middle-level wide-angle lens, and a bottom-level depth camera.

[0042] In one example, 3 to 5 sensors can be installed at the bottom of each shelf of each rack, the distance between two adjacent sensors can be less than or equal to 30 cm, and the sensors can be high-precision thin film pressure sensors.

[0043] In one example, the "top," "middle," and "bottom" layers in the top fisheye lens, middle wide-angle lens, and bottom depth camera do not describe the height of each device, but rather the logical order of the data collected by each device during the update of the inventory list. For example, the top fisheye lens is used to capture images to locate a specific area, the middle wide-angle lens is used to identify the book's spine data and ISBN (International Standard Book Number) data, and finally the bottom depth camera is used to determine the book's location information. In a specific embodiment, the top fisheye lens can be a Dahua DH-IPC-EW4831-AS fisheye lens, the middle wide-angle lens can be a Hikvision DS-2CD3347G2 wide-angle lens, and the bottom depth camera can be an Intel RealSense L515 depth camera.

[0044] Based on this structure, the embodiment of the present invention provides a specific implementation method for updating the list of stored books, see (1.1) to (1.3) below: (1.1) The pressure sensor network senses the pressure changes corresponding to each shelf in the shelf, and monitors whether a book entry or exit event occurs on the shelf based on the pressure changes.

[0045] In one example, for any pressure sensor in the pressure sensor network, the pressure change at its location can be sensed by the pressure sensor. If the pressure change value is greater than a preset pressure threshold (for example, the weight of the taken-out book is less than 50g), it is determined that a book-in event or a book-out event has occurred on the shelf, and the pressure sensor sends a signal to the server. Among them, the positive or negative nature of the pressure change value can be used to describe the event type. For example, if the pressure change value is positive, it indicates that a book-in event has occurred; on the contrary, if the pressure change value is negative, it indicates that a book-out event has occurred.

[0046] (1.2) If so, locate the target shelf and shelf board where the book-in event or book-out event has occurred, activate the camera network corresponding to the target shelf and shelf board, and obtain the book image set collected by the activated camera network for the target shelf and shelf board.

[0047] Among them, the book image set includes the occupancy heat map collected by the top-layer fisheye lens, the book image data collected by the middle-layer wide-angle lens, and the book point cloud data collected by the bottom-layer depth camera.

[0048] In one example, the server can identify the specific location of the pressure sensor in the book warehouse (i.e., the target shelf and shelf board) according to the identifier of the carried pressure sensor, and then only activate the camera network corresponding to the target shelf and shelf board, trigger the camera network corresponding to the target shelf and shelf board to perform the image acquisition action, so as to reduce the computing load.

[0049] Optionally, a camera network can be set for each shelf. When it is detected that a book-in event or a book-out event has occurred at a certain shelf board, the camera network corresponding to the shelf to which the shelf board belongs can be activated to collect the book image set; or a camera network can be jointly set for each or multiple shelf boards in the shelf. When it is detected that a book-in event or a book-out event has occurred at a certain shelf board, the corresponding camera network can be activated to collect the book image set.

[0050] (1.3) Update the list of books already in stock corresponding to the book warehouse according to the book image set. In specific implementation, an implementation method for updating the list of books already in stock can be provided for the book-in event and the book-out event respectively.

[0051] (1.31) In the case of a book-in event, perform the following operations: Based on the occupancy heat map, the target shelves and shelves where the book entry event occurs are identified; the first sub-image data corresponding to the entry event area is intercepted from the book image data, and the book spine data and book ISBN data corresponding to the newly entered book are identified based on the first sub-image data; the location information corresponding to the newly entered book is determined based on the book spine data and book point cloud data; and the list of books already in storage is updated based on the book ISBN data and location information corresponding to the newly entered book.

[0052] In its implementation, the top-layer fisheye lens rapidly scans the entire row of shelves, generating an occupancy heat map and marking areas of potential change (e.g., from "high occupancy" to "low occupancy"). The middle-layer wide-angle lens performs high-resolution scans of the positioning shelves. The YOLOv8-Tiny model detects the location of book spines, and CRNN-OCR recognizes spine text. The bottom-layer depth camera scans the stacked books, generating a 3D point cloud. The Heberson algorithm extracts the outlines and calculates the 3D coordinates of each book, enabling updates to the inventory list in the book arrival scenario.

[0053] (1.32) In the event of a book out of the library, perform the following operations: Based on the occupancy heat map, the target shelf and shelf where the book outbound event occurred are identified; the second sub-image area corresponding to the outbound event area is cut out from the book image data, and based on the second sub-image area and the second sub-image area of the previous frame, the book ISBN data and location information corresponding to the outbound book are identified; based on the book ISBN data and location information corresponding to the outbound book, the list of books in the library is updated. In the specific implementation, the top fisheye lens: quickly scans the entire row of shelves, generates an occupancy heat map, and marks the areas that may change (such as from "high occupancy" to "low occupancy"). The middle wide-angle lens: performs high-resolution scanning on the positioning shelf, compares the obtained second sub-image area with the second sub-image area of the previous frame, and identifies the book ISBN data and location information corresponding to the books that have been outbound in the area, thereby realizing the update of the list of books in the library in the book outbound scenario.

[0054] Furthermore, after the list of books in the library is updated, the above-mentioned book image set can be sent to the associated terminal so that the updated list of books in the library can be calibrated and supplemented through the graphical user interface of the associated terminal. Calibration means calibrating the updated incorrect book information, and supplementation means supplementing the unpacking status of the updated books (whole package or single book), which is helpful for subsequent automatic grabbing by book sorting robots.

[0055] Based on the above embodiment, the embodiment of the present invention further explains the above steps S102 to S110.

[0056] For the aforementioned step S102, receive book order information, including a list of books to be packed, customer information, auxiliary information, platform information, etc.

[0057] For the aforementioned step S104, identify the suitable reading fields corresponding to each book category in the list of books to be packed. The book categories included in the list of books to be packed can be directly read. For each book category, based on the mapping relationship between the preset book category and the suitable reading fields, determine its corresponding book category. Optionally, the mapping relationship between the book category and the suitable reading fields can be determined based on the extracurricular reading guidance list provided by the relevant department. For book categories not included in the extracurricular reading guidance list, the extracurricular reading guidance list can be used to train a neural network so that the neural network learns the mapping relationship between the school age segment, the suitable reading fields, and the book category. Furthermore, the trained neural network model can be used to output the suitable reading fields corresponding to the book categories not included in the extracurricular reading guidance list.

[0058] For the aforementioned step S106, based on the suitable reading fields and the list of books already in stock in each book warehouse, with the goal of minimizing the number of allocated book warehouses and the number of book sorting robots scheduled in each book warehouse, the specific process of generating the first book allocation strategy is as follows: (2.1) According to the suitability constraint, based on the suitable reading fields corresponding to each book category in the list of books to be packed and the list of books already in stock in each book warehouse, generate an initial set of book allocation strategies.

[0059] Among them, the suitability constraint is that book categories corresponding to the same school age segment and the same suitable reading fields are preferentially allocated to the same book warehouse. In specific implementation, the same warehouse is preferentially allocated. That is, if a certain warehouse has already been allocated a certain book category under the same "school age segment - suitable field", then other book categories in the same group should be preferentially allocated to this warehouse. For example, if warehouse 1 has already been allocated book A of "grade 3 - textbooks", then book C belonging to the same "grade 3 - textbooks" should also be preferentially allocated to warehouse 1. Further, for each (grade, suitable field, category) combination, screen out a list of alternative book warehouses with sufficient inventory to cover the demand. Preferably, if a certain alternative book warehouse has already been allocated other book categories with the same "grade - suitable field", then its priority is raised to the top of the feasible list.

[0060] In one example, each individual (i.e., alternative book allocation strategy) is represented as an array of length N, where N is the total number of combinations of (grade, moderation field, category). Each element represents the warehouse ID assigned to that combination and must belong to its set of feasible warehouses. Example: Combination 1 (Grade 3 - Textbook - Book A) is assigned to Warehouse 1; Combination 2 (Grade 3 - Supplementary Teaching Material - Book B) is assigned to Warehouse 2. Based on this, an initial set of book allocation strategies can be generated as follows: First, group each (grade, moderation field), and try to allocate all book categories within the group to the same book warehouse (if the inventory of the book warehouse is sufficient); if it cannot be satisfied, randomly select from the feasible book warehouses, but preferentially select the book warehouse that already contains other categories in the same group. Example: If Book A and Book C of "Grade 3 - Textbook" need to be allocated to the same book warehouse, and Warehouse 1 can meet the requirements of both, then both will be allocated to Warehouse 1 in the initial solution.

[0061] (2.2) For any alternative book allocation strategy within the set of book allocation strategies, with the goal of minimizing the number of book warehouses, minimizing the number of book sorting robots scheduled in each book warehouse, and maximizing the concentration of the suitable reading field, generate the fitness value corresponding to this alternative book allocation strategy.

[0062] In specific implementation, the embodiments of the present invention mainly consider the following goals in the process of determining the fitness value corresponding to the alternative book allocation strategy: Goal 1: Minimize the number of warehouses (the number of unique warehouses); Goal 2: Minimize the number of robots (i.e., the total number of packages, the number of packages = ⌈demand / 200⌉); Goal 3: Maximize the concentration of the "school age segment - moderation field" group in the warehouses (reduce the number of warehouses with scattered categories within the group).

[0063] Based on the above goals, the embodiments of the present invention provide an expression for the fitness function: Fitness function = number of warehouses * W1 + number of robots * W2 + dispersion penalty term * W3; Among them, the dispersion penalty term is: count the number of categories within each "school age segment - moderation field" group that are allocated to different warehouses, and the higher the total sum, the higher the penalty. Weight setting: W1 >> W3 > W2, ensuring that the number of warehouses is prioritized, followed by the concentration within the group, and finally the number of robots.

[0064] (2.3) Select multiple alternative book allocation strategies from the set of book allocation strategies based on the fitness value, and perform crossover and mutation operations on the selected book allocation strategies to obtain new alternative book allocation strategies, so as to form a new set of book allocation strategies. When the iteration stop condition is met, the alternative book allocation strategy corresponding to the maximum fitness value in the set of book allocation strategies at this time is used as the first book allocation strategy.

[0065] Optionally, select: Select multiple optimal alternative book allocation strategies from the alternative book allocation strategies in descending order of fitness value. Group crossover: Cut the chromosome by grouping according to "school age segment - moderation field", exchange the warehouse allocations of the same group of the parents, and retain the within-group consistency. Example: Parent 1 allocates the "Grade 3 - teaching materials" group to Book Warehouse 1, and Parent 2 allocates it to Book Warehouse 2. After exchange, the offspring may inherit the allocation of the entire group. Mutation: Intra-group mutation: With a certain probability, migrate all book categories of a "school age segment - moderation field" group to another feasible book warehouse; Single-point mutation: Randomly select a combination of (grade, moderation field, category), and switch it to another book warehouse in its feasible warehouse list (preferably select a book warehouse that already contains the same group).

[0066] Form a new set of book allocation strategies through the above selection, crossover, and mutation operations, and continue to determine the fitness value corresponding to each alternative book allocation strategy in the new set of book allocation strategies according to (2.2). Repeat this process until the iteration stop condition is met, and use the alternative book allocation strategy corresponding to the maximum fitness value as the first book allocation strategy.

[0067] Exemplarily, the first book allocation strategy is as follows: (I) Target warehouse list: All target book warehouses assigned tasks; (II) The corresponding sub-list of books to be packed and the range of schedulable robot numbers for each target book warehouse: For each target book warehouse, list the combinations of (grade, moderation field, category), demand quantity, and number of packages (number of robots) assigned to it. Example: Warehouse 1: Grade 3 | Moderation field "First suitable for reading" | Book A (500 copies → 3 packages); Grade 3 | Moderation field "First suitable for reading" | Book C (200 copies → 1 package); Range of schedulable robot numbers = 4 ( )

[0068] Furthermore, the end of the robotic arm of the book sorting robot is equipped with a whole - pack book gripper and a single - book gripper. The whole - pack book gripper is suitable for grasping unopened whole packs of books (for example, each pack contains 10 books), and the single - book gripper is suitable for grasping single books that have been unpacked. Based on this, for the aforementioned step S108, the specific process of generating the second book distribution strategy based on the range of schedulable robot numbers and the current status information of each book sorting robot in the target book warehouse is as follows: (3.1) Publish the book packing tasks of the picking list to the task pool, and mark each book packing task as "unassigned". The book packing task describes the book category (book name, publisher) corresponding to the picking list, the shelf location (shelf and level in the warehouse), and the required gripper type (whole - pack gripper or single - book gripper).

[0069] For any book packing task in the task pool, receive the competition requests initiated by each book sorting robot in the target book warehouse for this book packing task, determine the task cost corresponding to each book sorting robot based on the current status information carried by the competition request, and determine the target book sorting robot corresponding to the picking list of this book packing task according to the task cost corresponding to each book sorting robot and the range of schedulable robot numbers, and remove this book packing task from the task pool.

[0070] In specific implementation, it is necessary to obtain the book category (book name, publisher) described in the book packing task, the shelf location (shelf and level in the warehouse), and the required gripper type (whole - pack gripper or single - book gripper), and it is also necessary to obtain the current status information of each book sorting robot. The current status information includes the distance between the current position of the book sorting robot and the position information corresponding to this book packing task, the gripper type currently used by the book sorting robot, and the power information of the book sorting robot.

[0071] Based on the above information, determine the task cost of each book sorting robot for the book packing task. The lower the task cost, the more suitable the book sorting robot is for executing this book sorting task. Among them, the calculation formula of the task cost is as follows: Task cost = path length weight × path distance+switching gripper weight × number of switches + power penalty term; Among them, path distance: the total distance from the current position of the robot to the shelf and then to the packing area; number of switches: if the required gripper for the task is different from the current one, the number is incremented by 1, otherwise it is 0; power penalty term: if the path distance exceeds the maximum distance supported by the remaining power, the cost is set to infinity (forbidden to be assigned).

[0072] In specific implementation, the book sorting robot with the lowest task cost can be bound to the book sorting task, and the book sorting task can be marked as "assigned" or removed from the task pool.

[0073] (3.3) Continue to determine the target book sorting robot corresponding to the picking list of the next book packing task until the task pool is empty, so as to obtain the second book allocation strategy. In specific implementation, repeat the aforementioned (3.2) until all the book sorting tasks in the task pool are marked as "assigned", or when the task pool does not contain book sorting tasks, then stop to obtain the final second book allocation strategy.

[0074] Exemplarily, assume that the task pool includes: Picking list 1: Book A (whole-package gripper, shelf S1, path distance 30 meters). Picking list 2: Book B (single-book gripper, shelf S2, path distance 50 meters). Among them, the robot status is: The battery of book sorting robot R1 supports 100 meters, the current gripper is a whole-package gripper, and it is located at the warehouse entrance. The battery of book sorting robot R2 supports 80 meters, the current gripper is a single-book gripper, and it is located in the middle of the shelf area. The auction process is as follows: Picking list 1: R1 cost = 30×1 (path) + 0 (no need to switch) = 30; R2 cost = 40×1 (path) + 1×10 (switch gripper) = 50, that is, book sorting robot R1 wins. Picking list 2: R1 cost = 55×1 (path) + 1×10 (switch gripper) = 65; R2 cost = 50×1 (path) + 0 = 50, that is, book sorting robot R2 wins. Based on this, the following second book allocation strategy is output: The book sorting task bound to book sorting robot R1 is picking list 1 (Book A, whole-package gripper); the book sorting task bound to book sorting robot R2 is picking list 2 (Book B, single-book gripper).

[0075] For the aforementioned step S110, according to the second book allocation strategy, the specific process of controlling the target book sorting robot to perform the book packing action according to its corresponding picking list is as follows: (4.1) Obtain the warehouse grid model corresponding to the target book warehouse.

[0076] Among them, the warehouse grid model describes the occupancy status of each grid in the target book warehouse through specified markings. Exemplarily, for the grid where the shelf is located, the grid is permanently marked as "1", that is, the grid is occupied; for other grids, if a book sorting robot is passing through the grid, the grid is marked as "1", that is, the grid is occupied, if there is no book sorting robot passing through the grid at this time, the grid is marked as "0", that is, the grid is idle (passable).

[0077] (4.2) Plan the picking path corresponding to the target book sorting robot based on the warehouse grid model, the current position of the target book sorting robot, and its corresponding picking list.

[0078] Exemplarily, the planning algorithm for the picking path can adopt the A* algorithm. The specific process is as follows: First, define the parameters of the A* algorithm, including: Define nodes: Each grid cell is a node, and the node attributes include: coordinates (x, y); actual cost g: the movement cost from the starting point to the current node (e.g., the cost per grid is 1); heuristic cost h: the estimated cost from the current node to the end point (Manhattan distance or Euclidean distance); total cost f = g + h. Define movement rules: Allow the robot to move in four directions: up, down, left, and right (four-neighborhood), or add diagonal movement (eight-neighborhood); the diagonal movement cost is set to √2 (closer to the actual distance); prohibit entering the grid marked as 1 (permanently or temporarily occupied).

[0079] Then, plan the picking path: (I) Input parameters: starting point (i.e., the grid coordinates corresponding to the current position of the robot), end point (i.e., the grid coordinates where the target shelf is located), and the real-time warehouse grid model (including all occupancy marks).

[0080] (II) Initialize the data structures: Open List: Store the nodes to be explored, sorted in ascending order of f value; Closed List: Store the explored nodes; Parent Map: Record the optimal predecessor node of each node for backtracking the path.

[0081] (III) Algorithm execution: Add the starting point to the open list, set its g = 0, calculate h heuristically, and f = g + h. Loop and execute the following steps: a. Select the current node: Take out the node with the smallest f value from the open list. b. Termination condition: If the current node is the end point, jump out of the loop and backtrack the path; if the open list is empty, the path does not exist. c. Generate adjacent nodes: Check the four-neighborhood / eight-neighborhood grids of the current node. d. Filter invalid nodes: Ignore the grids marked as 1 (occupied); ignore the nodes already in the closed list. e. Update the node cost: Calculate the g value of the adjacent node (the current node g + movement cost); if the adjacent node is not in the open list, or the new g value is lower, then update its g, h, f, and set the current node as the parent node; add the adjacent node to the open list (if it does not exist). f. Move the current node to the closed list.

[0082] (IV) Path backtracking: Trace back the parent nodes in reverse from the end point node until the starting point to generate the final path coordinate sequence.

[0083] It should be noted that the above-mentioned picking path planning algorithm is only an example, and those skilled in the art may select other path planning algorithms to generate a picking path corresponding to each target book sorting robot, and the embodiment of the present invention does not limit this.

[0084] (4.3) Predict the time it takes for the target book sorting robot to arrive at each grid in the target book warehouse based on the picking path to determine whether there are multiple target book sorting robots occupying the same grid at the same time.

[0085] (4.4) If yes, the target book sorting robot occupying the same grid at the same time is paused or controlled to avoid obstacles, so that the target book sorting robot can successfully reach the grid corresponding to the picking list and perform the book packing action according to its corresponding picking list.

[0086] When multiple target book sorting robots occupy the same grid at the same time, the priority of each target book sorting robot can be determined, and the target book sorting robot with the highest priority is given priority to pass through the grid so that it can successfully reach the grid corresponding to the picking list. In specific implementation, the priority of multiple target book sorting robots occupying the same grid at the same time can be determined according to the following formula: Priority = urgency of remaining task time × package priority coefficient + robot remaining battery weight; The remaining time urgency = 1 / the remaining time of the task deadline (the shorter the time, the higher the priority); the package priority coefficient is defined by business rules (for example, the first package to be read is limited).

[0087] In a specific embodiment, the target book sorting robot with a lower priority may be controlled to pause, and after the target book sorting robot with a higher priority passes through the grid, the target book sorting robot with a lower priority may be controlled to pass through the grid. In another specific embodiment, obstacle avoidance planning may be re-performed for the target book sorting robot with a lower priority. The path planning process can be found in the aforementioned (4.2), which will not be described in detail in this embodiment of the present invention.

[0088] Furthermore, the book sorting robot is equipped with a visual device. On this basis, the embodiment of the Northern Life further provides a specific implementation method for performing the book packing action according to the corresponding picking list, including: (I) After the target book sorting robot successfully reaches the grid corresponding to the picking list, obtain shelf image data captured by a visual device. In one example, the book sorting robot may be equipped with a visual device (such as a camera) to capture the shelf image data.

[0089] (II) Locate the book to be grabbed based on the shelf image data and the location information described in the picking list, and determine whether the gripper type currently used by the target book sorting robot matches the book to be grabbed based on the shelf image data. In one example, image processing can be performed on the shelf image data to extract the book bounding box contained in the picking list, and then a rough book position can be obtained. Combining the specific location information described in the picking list, the specific operation position for the book sorting robot to perform the grabbing action can be determined. Additionally, based on the recognition result of the shelf image data and the unpacking status (single book or whole package) of the book described in the list of books already stored in the warehouse (or the picking list), it can be judged whether it matches the gripper type currently used by the target book sorting robot.

[0090] (III) If not, then switch the gripper type currently used by the target book sorting robot, and use the switched gripper to perform the grabbing action and the book packing action on the book to be grabbed.

[0091] Furthermore, a rubber wheel type grabbing structure can be installed at the end of the book sorting robot. In a library, books are mostly placed upright in rows on the shelves, and books are placed closely together. It is impossible to directly use a mechanical claw to grab a single book. Considering that the force control of the robotic arm in the design imitating the human hand cannot reach the biological level of precision, and considering that hooks will damage the books, the embodiment of the present invention changes the idea and adopts a rubber wheel structure. A servo motor is used in cooperation with a disc with a rubber ring, which is installed at the head of the robotic arm to form an extraction structure, which can accurately separate the target book from the book stack and minimize the damage to the book. The setting of the rotation angle of the servo motor is the setting of the farthest and nearest distances for the book to be pulled out, which facilitates the subsequent clamping action of the mechanical claw.

[0092] Furthermore, to reduce the friction between the book and the shelf, the shelf can be made of a smoother material so that the rubber wheel type grabbing structure can more easily pull out the book. Further, to prevent the book from easily falling off the shelf due to too low friction between the book and the shelf, a partition made of a highly transparent material can be set on the shelf, and when it is detected that the book sorting robot is about to perform the grabbing action, the partition can be controlled to contract or lift, so that the books on the shelf are exposed, and then the book sorting robot can use the rubber wheel type grabbing structure to pull out the book and grab the book with the corresponding type of gripper.

[0093] In summary, the book packaging method based on the suitable reading fields provided by the embodiments of the present invention makes the information of book commodity materials more complete through this function. The specific number of copies can be obtained from the number of packages in the order-making link, and combined with the package specification adjustment form, it is convenient to query the package inventory of various package specifications of the books out of the warehouse, convenient to quickly query the number of packages without unpacking, and provides great convenience for links such as sales order-making. In addition, through the collaborative optimization of multiple algorithms, combined with business rules and automated scheduling strategies, under the constraint of the suitable reading fields (grade - textbook type), the automation degree and efficiency of book sorting are significantly improved, and it has at least the following characteristics: (1) Precise sorting and resource concentration driven by suitable reading fields: Based on the priority allocation mechanism of the genetic algorithm in the embodiments of the present invention, books with the same suitable reading field (such as "Grade 5 - Chinese textbook") are preferentially concentrated in the same book warehouse, reducing the need for cross-warehouse sorting and lowering the subsequent robot scheduling complexity. Example: All the textbooks for Grade 5 in a certain primary school are allocated to Warehouse A, avoiding path crossing and coordination costs caused by dispersion to multiple warehouses. (2) Full-process automation and intelligent decision-making: From warehouse selection to package generation (200 books per package) in the embodiments of the present invention, the whole process is automatically processed by algorithms without manual intervention. The genetic algorithm and the auction algorithm are linked to achieve the optimal matching of two-level resources of the warehouse - robot. Further, based on the conflict detection algorithm of the spatio-temporal grid in the embodiments of the present invention, path conflicts are predicted in real time, and low-priority robots automatically detour or pause. Combined with the dynamic reallocation mechanism, it ensures the continuous execution of tasks in high-load scenarios. (3) Efficiency improvement and cost optimization: Minimizing the sorting path, minimizing the number of gripper switches, maximizing resource utilization, minimizing the number of warehouses, and minimizing the number of robots comprehensively improve the book sorting efficiency and reduce the book sorting cost. (4) Enhanced dynamic adaptability and robustness: In the embodiments of the present invention, the robot battery power is real-time incorporated into the auction cost calculation, and low-battery robots are automatically assigned short-distance tasks, enhancing the dynamic adaptability and robustness.

[0094] On the basis of the foregoing embodiments, the embodiments of the present invention provide a book packaging device based on suitable reading fields. This device is applied to the server in the book warehousing system. The book warehousing system also includes book sorting robots deployed inside each book warehouse. The server is communicatively connected with the book sorting robots. Refer to Figure 3 the structural schematic diagram of a book packaging device based on suitable reading fields as shown, and this device mainly includes the following parts: An order receiving module 302, configured to receive book order information, where the book order information at least includes a list of books to be packaged, and the list of books to be packaged is used to describe the book categories and their quantity information corresponding to each school age segment; The suitable-reading recognition module 304 is used to recognize the suitable-reading fields corresponding to each book category in the list of books to be packed, and the suitable-reading fields are used to describe the suitability of the book category for its corresponding school-age segment; The first allocation module 306 is used to generate a first book allocation strategy with the goal of minimizing the number of allocated book warehouses and the number of book sorting robots scheduled in each book warehouse, based on the suitable-reading fields and the list of books already in stock corresponding to each book warehouse. The first book allocation strategy is used to describe at least one target book warehouse and its corresponding sub-list of books to be packed and the range of the number of schedulable robots; The second allocation module 308 is used for each target book warehouse to divide the sub-list of books to be packed corresponding to the target book warehouse into multiple picking lists based on the suitable-reading fields, and generate a second book allocation strategy based on the range of the number of schedulable robots and the current status information of each book sorting robot in the target book warehouse. The second book allocation strategy is used to describe the target book sorting robots scheduled in the target book warehouse and their corresponding picking lists; The book packing module 310 is used to control the target book sorting robots to perform book packing actions according to their corresponding picking lists in accordance with the second book allocation strategy.

[0095] The book packing device based on the suitable-reading fields provided by the embodiments of the present invention recognizes the suitable-reading fields corresponding to each book category in the list of books to be packed, and then, based on the suitable-reading fields, generates a first book allocation strategy with the book warehouse as the research object and a second book allocation strategy with the book sorting robot as the research object, so as to control the book sorting robots to perform book packing actions according to the picking lists. The present invention not only significantly improves the efficiency and automation degree of book sorting, but also the book packages obtained by packing based on the suitable-reading fields are helpful to improve the experience of the seller, the buyer and the warehouse management.

[0096] In one implementation manner, the first allocation module 306 is specifically used for: Generating an initial set of book allocation strategies according to the suitability constraint, based on the suitable-reading fields corresponding to each book category in the list of books to be packed and the list of books already in stock corresponding to each book warehouse. The suitability constraint is that book categories corresponding to the same school-age segment and the same suitable-reading field are preferentially allocated to the same book warehouse; For any alternative book allocation strategy in the set of book allocation strategies, generating the fitness value corresponding to the alternative book allocation strategy with the goal of minimizing the number of book warehouses, minimizing the number of book sorting robots scheduled in each book warehouse, and maximizing the concentration of suitable-reading fields; Filter multiple alternative book allocation strategies from the set of book allocation strategies based on fitness values, and perform crossover and mutation operations on the filtered book allocation strategies to obtain new alternative book allocation strategies, so as to form a new set of book allocation strategies. When the iteration stop condition is met, the alternative book allocation strategy corresponding to the maximum fitness value in the set of book allocation strategies at this time is used as the first book allocation strategy.

[0097] In one implementation, whole-package book grippers and single-book grippers are mounted at the ends of the robotic arms of the book sorting robots; the second allocation module 308 is specifically configured to: Publish the book packing task of the picking list to the task pool; For any book packing task in the task pool, receive the competition requests initiated by each book sorting robot in the target book warehouse for this book packing task, determine the task cost corresponding to each book sorting robot based on the current status information carried in the competition request, and determine the target book sorting robot corresponding to the picking list of this book packing task according to the task cost corresponding to each book sorting robot and the range of the number of schedulable robots, and remove this book packing task from the task pool; wherein, the current status information includes the distance between the current position of the book sorting robot and the position information corresponding to this book packing task, the type of gripper currently used by the book sorting robot, and the power information of the book sorting robot; Continue to determine the target book sorting robot corresponding to the picking list of the next book packing task until the task pool is empty, and obtain the second book allocation strategy.

[0098] In one implementation, the book packing module 310 is specifically configured to: Obtain the warehouse grid model corresponding to the target book warehouse, and the warehouse grid model describes the occupancy status of each grid in the target book warehouse through specified markers; Based on the warehouse grid model, the current position of the target book sorting robot and its corresponding picking list, plan the picking path corresponding to the target book sorting robot; Predict the time when the target book sorting robot reaches each grid in the target book warehouse based on the picking path to determine whether there is a situation where multiple target book sorting robots occupy the same grid at the same time; If so, perform pause control or obstacle avoidance control on the target book sorting robots that occupy the same grid at the same time, so that the target book sorting robots can successfully reach the grid corresponding to the picking list and perform book packing actions according to their corresponding picking lists.

[0099] In one implementation, the book packing module 310 is specifically configured to: After the target book sorting robot successfully reaches the grid corresponding to the picking list, obtain the shelf image data collected by the vision device; Locate the book to be grabbed based on the shelf image data and the location information described in the picking list, and identify whether the type of gripper currently used by the target book sorting robot matches the book to be grabbed based on the shelf image data; If not, switch the type of gripper currently used by the target book sorting robot, and use the switched gripper to perform the grabbing action and the book packing action on the book to be grabbed.

[0100] In one implementation, the book warehousing system further includes a book monitoring device communicatively connected to the server. The book monitoring device includes a pressure sensor network and a camera network deployed on each shelf in the book warehouse. The camera network includes a top-layer fisheye lens, a middle-layer wide-angle lens, and a bottom-layer depth camera; it also includes an inventory update module for: Sense the pressure change corresponding to each shelf board in the shelf through the pressure sensor network to monitor whether a book inbound event or a book outbound event occurs on the shelf based on the pressure change; If so, locate the target shelf and shelf board where the book inbound event or the book outbound event occurs, activate the camera network corresponding to the target shelf and shelf board, and obtain a book image set collected by the activated camera network for the target shelf and shelf board. The book image set includes an occupancy heat map collected by the top-layer fisheye lens, book image data collected by the middle-layer wide-angle lens, and book point cloud data collected by the bottom-layer depth camera; Update the list of books already in stock corresponding to the book warehouse according to the book image set.

[0101] In one implementation, the inventory update module is specifically used for: In the case of a book inbound event, perform the following operations: Identify the inbound event area of the target shelf and shelf board where the book inbound event occurs based on the occupancy heat map; Intercept the first sub-image data corresponding to the inbound event area from the book image data, and identify the book spine data and the book ISBN data corresponding to the newly inbound book based on the first sub-image data; Determine the location information corresponding to the newly inbound book according to the book spine data and the book point cloud data; Update the list of books already in stock based on the book ISBN data and the location information corresponding to the newly inbound book; In the case of a book outbound event, perform the following operations: Identify the outbound event area of the target shelf and shelf board where the book outbound event occurs based on the occupancy heat map; Intercept the second sub-image area corresponding to the outbound event area from the book image data, and identify the book ISBN data and the location information corresponding to the already-outbound book based on the second sub-image area and the previous frame of the second sub-image area; Update the list of books that have been put into storage based on the book ISBN data and location information corresponding to the books that have been shipped out.

[0102] The device provided by the embodiments of the present invention has the same implementation principle and technical effects as those of the foregoing method embodiments. For the sake of brief description, for the parts not mentioned in the device embodiments, reference may be made to the corresponding content in the foregoing method embodiments.

[0103] The embodiments of the present invention provide a server. Specifically, the server includes a processor and a storage device; a computer program is stored on the storage device, and when the computer program is run by the processor, it executes the method described in any one of the foregoing implementation manners.

[0104] Figure 4 FIG. 10 is a schematic structural diagram of a server provided by an embodiment of the present invention. The server 100 includes: a processor 40, a memory 41, a bus 42, and a communication interface 43. The processor 40, the communication interface 43, and the memory 41 are connected through the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0105] Among them, the memory 41 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 43 (which can be wired or wireless), a communication connection is realized between the system network element and at least one other network element, and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used.

[0106] The bus 42 may be an ISA bus, a PCI bus, an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 4 only a bidirectional arrow is used in FIG. 10, but it does not mean that there is only one bus or one type of bus.

[0107] Among them, the memory 41 is used to store a program. After receiving an execution instruction, the processor 40 executes the program. The method executed by the device defined by the flow process disclosed in any one of the foregoing embodiments of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0108] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 40 or the instructions in the form of software. The above-mentioned processor 40 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and combines its hardware to complete the steps of the above method.

[0109] The computer program product of the readable storage medium provided by the embodiments of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the foregoing method embodiments. For the specific implementation, reference can be made to the foregoing method embodiments and will not be elaborated here.

[0110] If the above-described functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0111] Finally, it should be noted that the above-described embodiments are only specific implementation manners of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A book packaging method based on readable fields, characterized in that, The method is applied to a server in a book storage system, which further includes book sorting robots deployed in each book warehouse. The server is communicatively connected to the book sorting robots. The method includes: Receiving book order information, where the book order information at least includes a list of books to be packed, and the list of books to be packed is used to describe the book categories corresponding to each school age segment and their quantity information; Identifying the appropriate reading fields corresponding to each of the book categories in the list of books to be packed, where the appropriate reading fields are used to describe the readability of the book categories relative to their respective school age segments; Based on the appropriate reading fields and the list of books already in stock corresponding to each book warehouse, with the goal of minimizing the number of allocated book warehouses and the number of book sorting robots scheduled in each book warehouse, generating a first book allocation strategy, which is used to describe at least one target book warehouse and its corresponding sub-list of books to be packed and the range of the number of schedulable robots; For each target book warehouse, based on the appropriate reading fields, dividing the sub-list of books to be packed corresponding to the target book warehouse into multiple picking lists, and based on the range of the number of schedulable robots and the current status information of each book sorting robot in the target book warehouse, generating a second book allocation strategy, which is used to describe the target book sorting robots to be scheduled in the target book warehouse and their corresponding picking lists; According to the second book allocation strategy, controlling the target book sorting robots to perform book packing actions according to their corresponding picking lists.

2. The book packaging method based on the suitable reading fields according to claim 1, wherein Based on the appropriate reading fields and the list of books already in stock corresponding to each book warehouse, with the goal of minimizing the number of allocated book warehouses and the number of book sorting robots scheduled in each book warehouse, generating a first book allocation strategy, including: According to the readability constraint, based on the appropriate reading fields corresponding to each of the book categories in the list of books to be packed and the list of books already in stock corresponding to each book warehouse, generating an initial set of book allocation strategies. The readability constraint is that for book categories corresponding to the same school age segment and the same appropriate reading field, they are preferentially allocated to the same book warehouse; For any alternative book allocation strategy in the set of book allocation strategies, with the goals of minimizing the number of book warehouses, minimizing the number of book sorting robots scheduled in each book warehouse, and maximizing the concentration of appropriate reading fields, generating the fitness value corresponding to the alternative book allocation strategy; Based on the fitness value, screening multiple alternative book allocation strategies from the set of book allocation strategies, and performing crossover and mutation operations on the selected book allocation strategies to obtain new alternative book allocation strategies, so as to form a new set of book allocation strategies. Until the iteration stop condition is met, the alternative book allocation strategy corresponding to the largest fitness value in the set of book allocation strategies at this time is used as the first book allocation strategy.

3. The book packaging method based on readable fields according to claim 1, wherein, The ends of the robotic arms of the book sorting robot are each equipped with a whole - package book gripper and a single - book gripper; Based on the range of the number of schedulable robots and the current status information of each book sorting robot in the target book storage, generate a second book allocation strategy, including: Publish the book packing task of the picking list to the task pool; For any one of the book packing tasks in the task pool, receive the competition requests initiated by each book sorting robot in the target book storage for this book packing task. Determine the task cost corresponding to each book sorting robot based on the current status information carried by the competition request. According to the task cost corresponding to each book sorting robot and the range of the number of schedulable robots, determine the target book sorting robot corresponding to the picking list of this book packing task, and remove this book packing task from the task pool; wherein, the current status information includes the distance between the current position of the book sorting robot and the position information corresponding to this book packing task, the type of gripper currently used by the book sorting robot, and the power information of the book sorting robot; Continue to determine the target book sorting robot corresponding to the picking list of the next book packing task until the task pool is empty, and obtain the second book allocation strategy.

4. The book packaging method based on the suitable reading fields according to claim 1, wherein According to the second book allocation strategy, control the target book sorting robot to perform the book packing action according to its corresponding picking list, including: Obtain the warehouse grid model corresponding to the target book storage, and the warehouse grid model describes the occupancy status of each grid in the target book storage through specified markers; Based on the warehouse grid model, the current position of the target book sorting robot, and its corresponding picking list, plan the picking path corresponding to the target book sorting robot; Predict the time when the target book sorting robot reaches each grid in the target book storage based on the picking path to determine whether there is a situation where multiple target book sorting robots occupy the same grid simultaneously; If so, perform pause control or obstacle - avoidance control on the target book sorting robots that simultaneously occupy the same grid, so that the target book sorting robot can successfully reach the grid corresponding to the picking list and perform the book packing action according to its corresponding picking list.

5. The book packaging method based on the suitable reading fields according to claim 4, wherein The book sorting robot is equipped with a vision device; performing the book packing action according to its corresponding picking list includes: After the target book sorting robot successfully reaches the grid corresponding to the picking list, obtain the shelf image data collected by the vision device; Locate the book to be grabbed based on the shelf image data and the position information described in the picking list, and identify whether the type of gripper currently used by the target book sorting robot matches the book to be grabbed based on the shelf image data; If not, switch the type of gripper currently used by the target book sorting robot, and use the switched gripper to perform the grabbing action and the book packing action on the book to be grabbed.

6. The method for packing books based on readable fields according to claim 1, wherein The book storage system further includes a book monitoring device in communication with the server, the book monitoring device including a pressure sensor network and a camera network deployed on each shelf in the book warehouse, the camera network including a top-layer fisheye lens, a middle-layer wide-angle lens, and a bottom-layer depth camera; the method further includes: Sensing pressure changes corresponding to each shelf in the shelf through the pressure sensor network, so as to monitor whether a book entry event or a book exit event occurs on the shelf based on the pressure changes; If yes, locate the target shelf and shelf where the book entry event or the book exit event occurs, activate the camera network corresponding to the target shelf and shelf, and obtain a book image set collected by the activated camera network for the target shelf and shelf, wherein the book image set includes an occupancy heat map collected by the top-layer fisheye lens, book image data collected by the middle-layer wide-angle lens, and book point cloud data collected by the bottom-layer depth camera; The stored book list corresponding to the book storeroom is updated according to the book image set.

7. The book packaging method based on readable fields according to claim 6, characterized in that, Updating the stored book list corresponding to the library according to the book image set includes: When the book storage event occurs, perform the following operations: Identify the target shelf and shelf entry event area where the book entry event occurs based on the occupancy heat map; Extracting first sub-image data corresponding to the storage event area from the book image data, and identifying book spine data and book ISBN data corresponding to the newly stored book based on the first sub-image data; Determining the location information corresponding to the newly-arrived book based on the book spine data and the book point cloud data; Update the list of books already in the library based on the book ISBN data and the location information corresponding to the newly-in-the-library book; When the book out-of-stock event occurs, perform the following operations: Identify the target shelf and shelf outbound event area where the book outbound event occurs based on the occupancy heat map; Extracting a second sub-image region corresponding to the outbound event region from the book image data, and identifying the book ISBN data and the location information corresponding to the outbound book based on the second sub-image region and the second sub-image region of the previous frame; Based on the ISBN data of the books corresponding to the shipped books and the location information, the list of the books in the warehouse is updated.

8. A book packaging device based on readable fields, characterized in that The device is applied to a server in a book storage system, which also includes a book sorting robot deployed in each book warehouse. The server is in communication connection with the book sorting robot. The device includes: An order receiving module is used to receive book order information, wherein the book order information includes at least a list of books to be packaged, wherein the list of books to be packaged is used to describe the book categories and quantity information corresponding to each school age group; a suitable reading identification module, configured to identify a suitable reading field corresponding to each book category in the list of books to be packaged, wherein the suitable reading field is used to describe the suitability of the book category relative to the school age group to which it belongs; The first allocation module is configured to generate a first book allocation strategy based on the suitable reading fields and the list of books already stored in each corresponding book storage, with the goal of minimizing the number of allocated book storages and the number of book sorting robots scheduled in each book storage. The first book allocation strategy is used to describe at least one target book storage and its corresponding sub-list of books to be packed and the range of the number of schedulable robots. The second allocation module is configured to, for each target book storage, divide the sub-list of books to be packed corresponding to the target book storage into multiple picking lists based on the suitable reading fields, and generate a second book allocation strategy based on the range of the number of schedulable robots and the current status information of each book sorting robot in the target book storage. The second book allocation strategy is used to describe the target book sorting robots scheduled in the target book storage and their corresponding picking lists. The book packing module is configured to control the target book sorting robots to perform book packing actions according to their corresponding picking lists in accordance with the second book allocation strategy.

9. A server, characterized in that, It includes a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor. The processor executes the computer-executable instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions cause the processor to implement the method according to any one of claims 1 to 7.

Images