Logistics simulation method and device

Abstract

The invention discloses a logistics simulation method and device, and relates to the technical field of computers. One specific embodiment of the method comprises the following steps: receiving logistics information input by a user, wherein the logistics information comprises a current logistics state and a prompt statement; determining input information according to the current logistics state and the prompt statement; and determining output information corresponding to the logistics information according to the input information and the logistics simulation model so as to make a decision according to the output information. According to the logistics simulation method based on the large language model, the logistics simulation model is adopted to automatically deduce the logistics state, so that the output result is closer to reality, the simulation efficiency is high, the knowledge graph of logistics simulation is established by using the large language model, and reuse of knowledge of a logistics scene in simulation is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for logistics simulation. Background Art

[0002] Simulation is a commonly used technical means in the operation of logistics systems. Due to the complexity of logistics systems and the large number of uncontrollable factors, the effects of decisions made on logistics systems in actual execution are often uncontrollable. Therefore, decisions can be input into the simulation system to observe the results and the impact on various aspects, and then applied in actual scenarios after confirming that the results meet expectations.

[0003] Among the related technologies, one simulation technology mainly relies on manual experience, which requires manual setting of the behavior patterns of each role in the simulation system and the generation logic of random factors, so as to evaluate the effects of the superposition of these logics. However, this method is easily affected by the limitations of manual experience. The other is to simulate the work of the simulation system through machine learning, input the decision logic into the machine learning model, and observe the corresponding output. However, this method requires separate fitting of the relevant model for each scenario and cannot be reused in other scenarios. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and device for logistics simulation, and provides a logistics simulation method based on a large language model. The logistics simulation model is used to automatically deduce the logistics status, so that the output result is closer to reality and the simulation efficiency is high. The knowledge graph of logistics simulation is established using a large language model, which is conducive to the reuse of knowledge of logistics scenarios in simulation.

[0005] To achieve the above object, according to one aspect of an embodiment of the present invention, a logistics simulation method is provided, comprising:

[0006] Receive logistics information input by the user, the logistics information including the current logistics status and prompt statement;

[0007] Determine input information according to the current logistics status and prompt statement;

[0008] Output information corresponding to the logistics information is determined according to the input information and the logistics simulation model, so as to make a decision according to the output information.

[0009] Optionally, determining output information corresponding to the logistics information according to the input information and the logistics simulation model includes:

[0010] Encrypting the input information according to the constructed logistics dictionary to obtain encrypted input information;

[0011] The encrypted input information is input into the logistics simulation model to obtain the output information.

[0012] Optionally, before encrypting the input information according to the constructed logistics dictionary, the method further includes:

[0013] The names of various elements and various event words corresponding to the logistics scenario are obtained, and the logistics dictionary is constructed according to the names of various elements and various event words.

[0014] Optionally, the prompt statement includes a decision prompt and a specific prompt; and the input information is determined according to the current logistics status and the prompt statement, including:

[0015] The current logistics status, the decision prompt and the specific prompt are spliced ​​to obtain direct input, and the direct input is used as the input information. The output information corresponds to the direct input at the current moment.

[0016] Optionally, the prompt statement includes a decision prompt and a specific prompt; and the input information is determined according to the current logistics status and the prompt statement, including:

[0017] splicing according to the current logistics status and the decision prompt to obtain indirect input;

[0018] According to the indirect input and the logistics simulation model, an indirect output corresponding to the indirect input is obtained; the indirect output indicates the logistics status at the next moment;

[0019] The indirect output and the specific prompt are used as the input information.

[0020] Optionally, before determining output information corresponding to the logistics information according to the input information and the logistics simulation model, the method further includes:

[0021] Acquire multiple historical logistics states and historical prompt statements corresponding to each of the historical logistics states;

[0022] The logistics simulation model is trained based on multiple historical logistics states and historical prompt statements corresponding to each of the historical logistics states.

[0023] Optionally, the logistics simulation model is trained according to a plurality of historical logistics states and historical prompt statements corresponding to each of the historical logistics states, including:

[0024] The constructed logistics dictionary is used to encrypt the historical logistics status and the historical prompt statements respectively;

[0025] The logistics simulation model is obtained by using the encrypted historical logistics status and historical prompt sentences for training.

[0026] Wherein, the logistics simulation model is a large language model.

[0027] According to another aspect of an embodiment of the present invention, there is provided a logistics simulation device, comprising:

[0028] A receiving module receives logistics information input by a user, wherein the logistics information includes a current logistics status and a prompt statement;

[0029] A first determination module determines input information according to the current logistics status and prompt statement;

[0030] The second determination module determines output information corresponding to the logistics information according to the input information and the logistics simulation model, so as to make a decision according to the output information.

[0031] According to another aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0032] one or more processors;

[0033] a storage device for storing one or more programs,

[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the logistics simulation method provided by the present invention.

[0035] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for logistics simulation provided by the present invention is implemented.

[0036] One embodiment of the above invention has the following advantages or beneficial effects: the logistics simulation method provided by the embodiment of the present invention determines the input information according to the current logistics status and prompt statement after receiving the logistics information input by the user, and then calls the logistics simulation model to obtain the output information to make decisions on logistics operations. The method establishes a logistics simulation tool based on a large language model, and uses the logistics simulation model to automatically deduce the future logistics status; by summarizing the names of various elements and event vocabulary in the logistics scene, a logistics dictionary is formed, and the logistics dictionary is used to encrypt the input and output of the logistics simulation model; the large language model is used to establish a knowledge graph for logistics simulation, so as to facilitate the reuse of the knowledge of the logistics scene in the simulation, so that the output results obtained are closer to reality and the simulation efficiency is high.

[0037] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0039] Figure 1 is a schematic diagram of the main process of a logistics simulation method according to an embodiment of the present invention;

[0040] Figure 2 is a schematic diagram of the main process of another logistics simulation method according to an embodiment of the present invention;

[0041] Figure 3 It is a flow chart of a logistics simulation method according to an embodiment of the present invention;

[0042] Figure 4 is a schematic diagram of main modules of a logistics simulation device according to an embodiment of the present invention;

[0043] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0044] Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0046] Figure 1 FIG. 1 is a schematic diagram of the main process of a logistics simulation method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0047] Step S101: receiving logistics information input by a user, the logistics information including the current logistics status and prompt statements;

[0048] Step S102: Determine input information according to the current logistics status and prompt statement;

[0049] Step S103: Determine output information corresponding to the logistics information based on the input information and the logistics simulation model, so as to make a decision based on the output information.

[0050] In the embodiment of the present invention, the logistics information input by the user is first received. The logistics information includes the current logistics status and prompt statements. The current logistics status is used to describe the current resource situation and requirements of the scenario described in the simulation system, and the prompt statement is used to describe the current decision input, or the user's requirements for output information. For example, the current logistics status can be: "10 shelves, 1 sku per shelf, 10 pickers, 10,000 orders, 10 items per order, 1 hour of picking time, and 10 items per person per minute." The prompt statement can be: "Will there be a delay?" or "Add 10 pickers," where "Will there be a delay?" indicates that the user wants to evaluate the potential risk of delay, and "Add 10 pickers" indicates that adding 10 pickers is used as a decision input.

[0051] In the embodiment of the present invention, the prompt statement can be one or more, and multiple prompt statements can be input at the same time; the prompt statement includes a decision prompt and a specific prompt, the decision prompt is used to describe the current decision input, and the specific prompt is used for the user's requirements for output information, such as "add 10 pickers" is a decision prompt, and "whether there will be a delay" is a specific prompt. At the same time, the prompt statement can also be empty, indicating that the user hopes to output all states of the system without inputting any decision.

[0052] In an embodiment of the present invention, the input information is determined according to the current logistics status and the prompt statement, and further can include: splicing the current logistics status, decision prompts and specific prompts to obtain direct input, using the direct input as input information, and the output information corresponds to the direct input at the current moment. That is, the direct input obtained by splicing the current logistics status, decision prompts and specific prompts is the input information, and the corresponding output information can be obtained through the direct input at the current moment. Among them, the input information can be in json format, that is, the current logistics status, decision prompts and specific prompts can be spliced ​​into json format to obtain input information.

[0053] For example, the user input is:

[0054] Current logistics status: "10 shelves, 1 sku per shelf, 10 pickers, 10,000 orders, 10 items per order, 1 hour of picking time, and a picking speed of 10 items per person per minute."

[0055] Decision prompt: "Add 10 pickers."

[0056] Specific prompt: "Will it be delayed?"

[0057] The current logistics status, decision prompts, and specific prompts are spliced ​​into a JSON format and directly input "{status: "10 shelves, 1 sku per shelf, 10 pickers, 10,000 orders, 10 items per order, 1 hour picking time, and a picking speed of 10 items per person per minute." Prompt: "Add 10 pickers. Will there be a delay?"}", which is the input information.

[0058] In the embodiment of the present invention, Figure 2 As shown, the input information is determined according to the current logistics status and prompt statements, including:

[0059] Step S201: splicing according to the current logistics status and decision prompts to obtain indirect input;

[0060] Step S202: obtaining an indirect output corresponding to the indirect input according to the indirect input and the logistics simulation model; the indirect output indicates the logistics status at the next moment;

[0061] Step S203: taking the indirect output and the specific prompt as input information.

[0062] In an embodiment of the present invention, the current logistics status and decision prompts can be spliced ​​to obtain indirect input, which is an intermediate state and is not displayed to the user; the indirect input is then input into the logistics simulation model to obtain an indirect output, that is, the logistics status at the next moment, and then the logistics status at the next moment and the specific prompt are used as input information, or the logistics status at the next moment and the decision prompt input by the user at the next moment are spliced ​​to obtain input information, or new indirect input can be spliced ​​to obtain a new indirect output, that is, the user can input multiple rounds of decision prompts to obtain corresponding output information.

[0063] For example, based on the user's input in the previous text, the indirect input is spliced: "{Status: "10 shelves, 1 sku per shelf, 10 pickers, 10,000 orders, 10 items per order, 1 hour picking time, and a picking speed of 10 items per person per minute." Prompt: "Add 10 pickers."}", and the logistics simulation model is called to obtain the logistics status at the next moment, which can be expressed as "XXXXXX". The user may enter a new decision prompt again at the next moment, such as "10 more pickers have been added." The interactive interface will splice out new input information "{Status: "XXXXXX", Prompt: "10 more pickers have been added"}", and after entering the logistics simulation model, new output information is obtained.

[0064] In an embodiment of the present invention, output information corresponding to logistics information is determined based on input information and a logistics simulation model, including: encrypting the input information according to a constructed logistics dictionary to obtain encrypted input information; inputting the encrypted input information into the logistics simulation model to obtain output information.

[0065] In an embodiment of the present invention, after the input information is determined according to the current logistics status and the prompt statement, the constructed logistics dictionary is used to encrypt the input information to obtain the encrypted input information. That is, the input information can be converted into the language in the logistics dictionary through the constructed logistics dictionary to realize the encryption of the input information, and then the encrypted input information is input into the logistics simulation model to obtain the output information.

[0066] In an embodiment of the present invention, before encrypting the input information according to the constructed logistics dictionary, it also includes: obtaining the names of each element and each event vocabulary corresponding to the logistics scene, and constructing a logistics dictionary according to each element name and each event vocabulary. That is, construct a logistics dictionary corresponding to the logistics scene, and then use the logistics dictionary to encrypt the input information. The logistics dictionary includes the names of elements involved in the logistics scene, such as warehouses, vehicles, distribution stations, packages, cargo volume, etc.; it also includes event vocabulary in the logistics scene, such as warehouse explosion, delay, etc.; it can also include letters, numbers and mathematical symbols, etc., and then form the language in the logistics dictionary according to the names of each element and event vocabulary, as well as letters, numbers and mathematical symbols, etc., and construct a logistics dictionary. The constructed logistics dictionary can enable the input information and output information to express the events that may occur in the logistics scene.

[0067] In the embodiment of the present invention, before determining the output information corresponding to the logistics information according to the input information and the logistics simulation model, the method further includes:

[0068] Obtain multiple historical logistics states and historical prompt statements corresponding to each historical logistics state;

[0069] A logistics simulation model is trained based on multiple historical logistics states and historical prompt sentences corresponding to each historical logistics state.

[0070] In the embodiment of the present invention, before determining the output information corresponding to the logistics information according to the input information and the logistics simulation model, it is necessary to train the logistics simulation model, and perform model training by obtaining multiple historical logistics states and historical prompt statements of each historical logistics state to obtain the logistics simulation model. That is, obtain multiple historical logistics states at the previous and next moments from the database, convert the historical logistics state of the previous moment and the historical logistics state of the next moment into language descriptions, respectively, as the input logistics state and output; at the same time, convert the decision executed at the previous moment into language descriptions, as the input historical prompt statements; if no decision was executed at the previous moment, the historical prompt statement is empty, and each input and output is used as a matching pair to obtain a large amount of training data, that is, the historical logistics state, prompt statement and output are used as training data, and the json file of the training data is converted into text format and input into the model for training to obtain the logistics simulation model.

[0071] In an embodiment of the present invention, processing of specific prompts in historical prompt statements can also be added. For example, assuming that the description language of the system status is "10 shelves, 1 sku on each shelf, 10 pickers, 10,000 orders, 10 items on each order, 1 hour picking time, and a picking speed of 10 items per person per minute." Then, specific prompts can be added, such as "will there be a delay?", "are there enough pickers?", etc., and then outputs that conform to the actual situation are given according to the specific prompt language to obtain a matching pair of input and output.

[0072] After the logistics simulation model is trained, it can be packaged in the logistics system and called by the user through the interactive interface. The user can call the logistics simulation model in a single round or multiple rounds in the interactive interface. The single round call is to input the spliced ​​direct input into the logistics simulation model to obtain the output information corresponding to the direct input. The multiple round call is to input the spliced ​​indirect input into the logistics simulation model to obtain the logistics status at the next moment. Then the user inputs a new decision prompt again, inputs it into the logistics simulation model, and obtains the output information. The user can input new decision prompts multiple times, and the interactive interface retains the indirect input format in each round.

[0073] In an embodiment of the present invention, a logistics simulation model is trained based on a plurality of historical logistics states and historical prompt statements corresponding to each historical logistics state, including:

[0074] The constructed logistics dictionary is used to encrypt the historical logistics status and historical prompt sentences respectively;

[0075] The encrypted historical logistics status and historical prompt statements are used for training to obtain a logistics simulation model.

[0076] Among them, the logistics simulation model is a large language model.

[0077] In an embodiment of the present invention, when training a logistics simulation model, the constructed logistics field is used to encrypt the historical logistics status and historical prompt sentences, and convert them into the language of the logistics dictionary respectively, that is, the encrypted historical logistics status and historical prompt sentences are obtained, and then the encrypted historical logistics status and historical prompt sentences are used for training to obtain a logistics simulation model. The structure of the logistics simulation model is a large language model structure, such as the open source GPT-2, GPT-J and other model structures.

[0078] Figure 3 The flowchart of a logistics simulation method of an embodiment of the present invention is shown in FIG. A large language model structure is used to construct the model, and the input format and output format of the model are determined; the model input includes the logistics status and the corresponding prompt statement, and the model output corresponds to the model input, which is the response result obtained by analyzing the model input; then data preparation is performed, that is, the historical logistics status at multiple moments and the prompt statement corresponding to each historical logistics status are obtained from the database to obtain training data; the model is trained using the training data to obtain a logistics simulation model; the logistics simulation model can be called by the interactive interface according to the user's input; the interactive interface provides a dialog box for the user's input of the logistics status, decision prompts and specific prompts, and outputs the output result of the model on the interactive interface. After receiving the current logistics status, decision prompts and specific prompts input by the user, the interactive interface splices the current logistics status, decision prompts and specific prompts into direct input, and splices the current logistics status and decision prompts into indirect input; the direct input calls the logistics simulation model to obtain the output at the current moment, and displays it in the output box of the interactive interface; the indirect input calls the logistics simulation model, outputs the logistics status at the next moment, and splices it with the decision prompts input by the user in the next round as the indirect input for the next round, and the cycle continues until the user no longer inputs new decision prompts, and the corresponding output is obtained, which is displayed in the output box of the interactive interface.

[0079] The logistics simulation method provided by the embodiment of the present invention determines the input information according to the current logistics status and prompt statement after receiving the logistics information input by the user, and then calls the logistics simulation model to obtain the output information to make a decision on logistics operation. The method establishes a logistics simulation tool based on a large language model, and uses the logistics simulation model to automatically deduce the future logistics status; by summarizing the names of various elements and event vocabulary in the logistics scene, a logistics dictionary is formed, and the logistics dictionary is used to encrypt the input and output of the logistics simulation model; the large language model is used to establish a knowledge graph of logistics simulation, so as to facilitate the reuse of the knowledge of the logistics scene in the simulation, so that the output result is closer to reality and the simulation efficiency is high.

[0080] According to another aspect of the embodiment of the present invention, Figure 4As shown, a logistics simulation device 400 is provided, comprising:

[0081] The receiving module 401 receives the logistics information input by the user, and the logistics information includes the current logistics status and prompt statements;

[0082] The first determination module 402 determines input information according to the current logistics status and the prompt statement;

[0083] The second determination module 403 determines output information corresponding to the logistics information according to the input information and the logistics simulation model, so as to make a decision according to the output information.

[0084] In the embodiment of the present invention, the second determination module 403 is further used to: encrypt the input information according to the constructed logistics dictionary to obtain encrypted input information; input the encrypted input information into the logistics simulation model to obtain output information.

[0085] In an embodiment of the present invention, the second determination module 403 is also used to: before encrypting the input information according to the constructed logistics dictionary, obtain the names of each element and each event vocabulary corresponding to the logistics scenario, and construct a logistics dictionary according to the names of each element and each event vocabulary.

[0086] In an embodiment of the present invention, the prompt statement includes a decision prompt and a specific prompt; the first determination module 402 is further used to: splice the current logistics status, decision prompt and specific prompt to obtain direct input, use the direct input as input information, and the output information corresponds to the direct input at the current moment.

[0087] In an embodiment of the present invention, the prompt statement includes a decision prompt and a specific prompt; the first determination module 402 is further used to: obtain indirect input according to the current logistics status and the decision prompt; obtain an indirect output corresponding to the indirect input according to the indirect input and the logistics simulation model; the indirect output indicates the logistics status at the next moment; and use the indirect output and the specific prompt as input information.

[0088] In an embodiment of the present invention, the second determination module 403 is also used to: obtain multiple historical logistics states and historical prompt statements corresponding to each historical logistics state before determining the output information corresponding to the logistics information based on the input information and the logistics simulation model; and train the logistics simulation model based on the multiple historical logistics states and the historical prompt statements corresponding to each historical logistics state.

[0089] In an embodiment of the present invention, the second determination module 403 is further used to: use the constructed logistics dictionary to encrypt the historical logistics status and the historical prompt sentences respectively; use the encrypted historical logistics status and historical prompt sentences for training to obtain a logistics simulation model, wherein the logistics simulation model is a large language model.

[0090] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the logistics simulation method provided by the present invention.

[0091] According to another aspect of an embodiment of the present invention, a computer readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for logistics simulation provided by the present invention is implemented.

[0092] Figure 5 An exemplary system architecture 500 is shown to which the method or apparatus for logistics simulation according to an embodiment of the present invention may be applied.

[0093] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0094] Users can use terminal devices 501, 502, 503 to interact with server 505 through network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0095] The terminal devices 501 , 502 , and 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0096] The server 505 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 501, 502, and 503. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0097] It should be noted that the logistics simulation method provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the logistics simulation device is generally set in the server 505 .

[0098] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0099] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device suitable for implementing an embodiment of the present invention. Figure 6 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0100] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0101] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0102] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0103] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0104] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0105] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor, for example, it may be described as: a processor includes a receiving module, a first determination module, and a second determination module. The names of these modules do not constitute a limitation on the modules themselves in some cases, for example, the receiving module may also be described as a "module for receiving logistics information input by a user".

[0106] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: receiving logistics information input by a user, the logistics information includes the current logistics status and prompt statements; determining the input information according to the current logistics status and prompt statements; determining the output information corresponding to the logistics information according to the input information and the logistics simulation model, so as to make a decision according to the output information.

[0107] According to the technical solution of the embodiment of the present invention, the logistics simulation method provided by the embodiment of the present invention determines the input information according to the current logistics status and prompt statement after receiving the logistics information input by the user, and then calls the logistics simulation model to obtain the output information to make decisions on logistics operations. The method establishes a logistics simulation tool based on a large language model, and uses the logistics simulation model to automatically deduce the future logistics status; by summarizing the names of various elements and event vocabulary in the logistics scene, a logistics dictionary is formed, and the logistics dictionary is used to encrypt the input and output of the logistics simulation model; the large language model is used to establish a knowledge graph for logistics simulation, so as to facilitate the reuse of the knowledge of the logistics scene in the simulation, so that the output results obtained are closer to reality and the simulation efficiency is high.

[0108] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A logistics simulation method, characterized in that: include: Receive logistics information input by the user, the logistics information including the current logistics status and prompt statement; Determine input information according to the current logistics status and prompt statement; Output information corresponding to the logistics information is determined according to the input information and the logistics simulation model, so as to make a decision according to the output information.

2. The method according to claim 1, characterized in that Determining output information corresponding to the logistics information according to the input information and the logistics simulation model includes: Encrypting the input information according to the constructed logistics dictionary to obtain encrypted input information; The encrypted input information is input into the logistics simulation model to obtain the output information.

3. The method according to claim 2, characterized in that Before encrypting the input information according to the constructed logistics dictionary, it also includes: The names of various elements and various event words corresponding to the logistics scenario are obtained, and the logistics dictionary is constructed according to the names of various elements and various event words.

4. The method according to claim 1, characterized in that The prompt sentences include decision prompts and specific prompts; Determining input information according to the current logistics status and the prompt statement includes: The current logistics status, the decision prompt and the specific prompt are spliced ​​to obtain direct input, and the direct input is used as the input information. The output information corresponds to the direct input at the current moment.

5. The method according to claim 1, characterized in that The prompt sentences include decision prompts and specific prompts; Determining input information according to the current logistics status and the prompt statement includes: splicing according to the current logistics status and the decision prompt to obtain indirect input; According to the indirect input and the logistics simulation model, an indirect output corresponding to the indirect input is obtained; the indirect output indicates the logistics status at the next moment; The indirect output and the specific prompt are used as the input information.

6. The method according to claim 1, characterized in that Before determining the output information corresponding to the logistics information according to the input information and the logistics simulation model, the method further includes: Acquire multiple historical logistics states and historical prompt statements corresponding to each of the historical logistics states; The logistics simulation model is trained based on multiple historical logistics states and historical prompt statements corresponding to each of the historical logistics states.

7. The method according to claim 1, characterized in that The logistics simulation model is trained according to a plurality of historical logistics states and historical prompt statements corresponding to each of the historical logistics states, including: The constructed logistics dictionary is used to encrypt the historical logistics status and the historical prompt statements respectively; The logistics simulation model is obtained by using the encrypted historical logistics status and historical prompt sentences for training. Wherein, the logistics simulation model is a large language model.

8. A logistics simulation device, characterized in that: include: A receiving module receives logistics information input by a user, wherein the logistics information includes a current logistics status and a prompt statement; A first determination module determines input information according to the current logistics status and prompt statement; The second determination module determines output information corresponding to the logistics information according to the input information and the logistics simulation model, so as to make a decision according to the output information.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images