Intelligent interaction method, equipment and storage medium based on AI big model logistics data

Abstract

The present application relates to an intelligent interaction method, device and storage medium based on AI large-scale model logistics data. The method includes: obtaining business data in the logistics system and converting the business data into standard business data; parsing and identifying system functions in the logistics system to generate structured description information; in response to receiving a business query request, performing semantic recognition on the business query request to generate prompt information; based on at least one of standard business data, structured description information and prompt information, obtaining a target prediction result. The present application integrates multi-dimensional data such as standardized business data, structured description information and prompt information, which can cover all elements of logistics, achieve accurate demand forecasting, assist users in making quick decisions, and meet the query, calculation and / or scheduling needs in the entire logistics scenario.

Description

Technical Field

[0001] The present application relates to the field of logistics management technology, and in particular to an intelligent interaction method, device and storage medium based on AI large model logistics data. Background Art

[0002] Against the backdrop of today's rapid global digitalization and logistics development, research into intelligent logistics processing methods has become crucial. With the growth of e-commerce and supply chain management, the logistics industry faces increasingly complex challenges, such as rapidly increasing orders, inventory management, and logistics route optimization. Effectively allocating resources across various logistics hubs and planning routes have become key to improving logistics efficiency, ensuring the smooth flow of goods, and maintaining customer satisfaction.

[0003] However, traditional logistics management and scheduling methods are often limited by human resources and time costs, and cannot meet the growing demand. Therefore, how to efficiently and accurately query / calculate logistics data to meet logistics scheduling needs is an urgent problem that needs to be solved. Summary of the Invention

[0004] Based on this, it is necessary to provide an intelligent interaction method, equipment and storage medium based on AI large model logistics data to address the above technical problems.

[0005] In a first aspect, the present application provides an intelligent interaction method based on AI large model logistics data, the method comprising:

[0006] Acquire business data in the logistics system and convert the business data into standard business data;

[0007] Analyze and identify system functions in the logistics system to generate structured description information;

[0008] In response to receiving a service query request, performing semantic recognition on the service query request and generating prompt information;

[0009] A target prediction result is obtained based on at least one of the standard business data, the structured description information and the prompt information.

[0010] In one embodiment, converting the business data into standard business data includes:

[0011] Performing semantic recognition on the business data to extract target entities; wherein the target entities include at least one of order entities, transportation entities, inventory entities, and equipment entities;

[0012] Creating a data view that matches the entity type of the target entity according to the target entity; wherein the data view includes at least one of a global inventory view, a risk warning view, and a real-time transportation capacity view;

[0013] The data views are associated based on foreign key constraints to obtain the standard business data.

[0014] In one embodiment, parsing and identifying system functions in the logistics system to generate structured description information includes:

[0015] Parsing and identifying the code corresponding to the system function to obtain function description information; wherein the system function includes at least one of a route optimization function, an inventory forecasting function, and a transportation capacity scheduling function; the function description information includes a function name, input parameters, and functional logic;

[0016] The function description information is standardized to obtain the structured description information; wherein the structured description information includes a function name, input requirements, and processing logic.

[0017] In one embodiment, obtaining a target prediction result based on at least one of the standard business data, the structured description information, and the prompt information includes:

[0018] Matching the prompt information with the structured description information to obtain a matching result;

[0019] If the matching result is successful, the prompt information, the standard business data matching the prompt information, and the structured description information are input into the AI ​​big model to obtain a candidate result;

[0020] The system function matching the prompt information is executed, and combined with the candidate results to obtain the target prediction result.

[0021] In one embodiment, the method further comprises:

[0022] In the case where the matching result is a matching failure, the prompt information and the standard business data matching the prompt information are input into the AI ​​big model to obtain the target prediction result.

[0023] In one embodiment, executing the system function that matches the prompt information and combining the candidate results to obtain the target prediction result includes at least one of the following:

[0024] The first method is to obtain a predicted path set based on an improved ant colony algorithm when executing the path optimization function that matches the prompt information; and obtain the target predicted result based on the predicted path set and the candidate result;

[0025] The second method is to obtain an inventory forecast result based on the Prophet model when executing the inventory forecast function that matches the prompt information; and obtain the target forecast result based on the inventory forecast result and the candidate result;

[0026] The third method is to obtain a matching matrix between vehicles and cargoes based on a mixed integer programming algorithm when executing a transportation scheduling function that matches the prompt information; and obtain the target prediction result based on the matching matrix and the candidate results.

[0027] In one embodiment, the method further comprises:

[0028] In response to receiving feedback information of the target prediction result, if the evaluation score included in the feedback information is less than a qualified threshold, obtaining modification information of the prompt information;

[0029] Updating the prompt information based on the modification information to obtain updated prompt information;

[0030] An updated target prediction result is obtained based on at least one of the standard business data, the structured description information and the updated prompt information.

[0031] In a second aspect, the present application further provides an intelligent interactive device based on AI large model logistics data, the device comprising:

[0032] A conversion module, used to obtain business data in the logistics system and convert the business data into standard business data;

[0033] A first generating module is used to parse and identify system functions in the logistics system and generate structured description information;

[0034] A second generating module is configured to, in response to receiving a service query request, perform semantic recognition on the service query request and generate prompt information;

[0035] A determination module is used to obtain a target prediction result based on at least one of the standard business data, the structured description information and the prompt information.

[0036] In a third aspect, the present application also provides a computer device comprising a processor and a memory for storing a computer program of the processor; wherein the processor is configured to: when executing the computer program, implement the steps of the method execution described in any embodiment of the present application.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method execution described in any embodiment of the present application.

[0038] In the above-mentioned intelligent interaction method based on AI large-scale logistics data, by standardizing business data, data differences between different systems (corresponding to different application scenarios), platforms or devices can be eliminated, facilitating subsequent processing and analysis of business data; parsing system functions and generating structured description information can help to automatically understand and call related functional modules, and improve the intelligent scheduling capabilities of the logistics system; integrating multi-dimensional data such as standardized business data (such as historical sales, supply chain delivery time, etc.), structured description information (such as promotion rules, vehicle scheduling algorithms, etc.) and prompt information can cover all logistics elements, achieve accurate demand forecasting, assist users in making quick decisions, and meet the query, calculation and / or scheduling needs in the entire logistics scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a diagram illustrating an application environment of an intelligent interaction method based on AI large-scale model logistics data according to an exemplary embodiment;

[0040] Figure 2 This is a flow chart illustrating an intelligent interaction method based on AI large model logistics data according to an exemplary embodiment;

[0041] Figure 3 1 is a structural block diagram of an intelligent interactive device based on AI large model logistics data according to an exemplary embodiment;

[0042] Figure 4 The figure shows the internal structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0044] The terms "first", "second" and "third" in the embodiments of the present application are only used for descriptive purposes and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, method, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally also include steps or units that are not listed, or may optionally also include other steps or units inherent to these processes, methods, products or devices.

[0045] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0046] In some embodiments, the intelligent interaction method based on AI large model logistics data provided in the embodiments of the present application can be applied to Figure 1 In the illustrated application environment, a computer device 102 communicates with a server 104 via a network, and the server 104 communicates with a database 106 via a network. The computer device 102 can obtain business data to be processed from the database 106 in real time via the server 104. The computer device 102 can be any mobile terminal or a fixed terminal. A terminal can be a device that provides voice and / or data connectivity to a user. Exemplarily, the terminal can be an IoT terminal, such as a sensor device, a mobile phone or so-called "cellular" phone, and a computer with an IoT terminal, for example, a fixed, portable, pocket-sized, handheld, or computer-built-in device.

[0047] In some embodiments, the intelligent interaction method based on AI large model logistics data provided in the embodiments of the present application can be applied to a computer device.

[0048] In some embodiments, as Figure 2 As shown, an intelligent interaction method based on AI large model logistics data is provided, and the method includes the following steps:

[0049] S201, acquiring business data in the logistics system and converting the business data into standard business data.

[0050] In the embodiment of the present application, the logistics system may include but is not limited to at least one of an order management system, a transportation management system, and a warehouse management system.

[0051] In the embodiment of the present application, business data may include but is not limited to at least one of order data, inventory data, transportation data, vehicle and equipment data, personnel data and customer service data.

[0052] In some embodiments, computer equipment can standardize original business data from different systems and formats and convert them into standard business data with a unified standard structure / format (such as standardized encoding, consistent naming rules, etc.) to facilitate effective storage, sharing, analysis and application of data.

[0053] S202: Analyze and identify system functions in the logistics system to generate structured description information.

[0054] In the embodiment of the present application, the system function in the logistics system may include at least one of a route optimization function, an inventory forecasting function, and a transportation capacity scheduling function. Different logistics systems may include one or more system functions; and the system functions included in different logistics systems may be the same or different.

[0055] In some embodiments, parsing and identifying system functions in the logistics system to generate structured description information includes:

[0056] Parsing and identifying the code corresponding to the system function to obtain function description information; wherein the system function includes at least one of a route optimization function, an inventory forecasting function, and a transportation capacity scheduling function; the function description information includes a function name, input parameters, and functional logic;

[0057] The function description information is standardized to obtain the structured description information; wherein the structured description information includes a function name, input requirements, and processing logic.

[0058] In the embodiment of the present application, the function name is used to characterize the purpose or function of the function (such as "generate a shipping cost quotation").

[0059] In the embodiment of the present application, the input requirements are used to clarify the parameter type (e.g., the parameter type corresponding to weight is a number) and the value range (e.g., the mode of transportation includes truck / lorry / airplane).

[0060] In the embodiment of the present application, the processing logic is used to indicate the calculation rules described through natural language (such as basic cost = weight × distance × unit price).

[0061] In some embodiments, the computer device can parse the system code through the abstract syntax tree, identify the input / output of the system function, and generate preliminary description information in combination with Javadoc / annotations; associate the system function with the corresponding business document, supplement the business logic description, and obtain function description information.

[0062] In some embodiments, the computer device automatically identifies the function name, input parameters and functional logic by analyzing the code corresponding to the system function; for example, it extracts the parameters of the freight calculation function (cargo weight, distance, transportation method / speed) and the corresponding pricing rules (such as a 30% surcharge for cold chain); and standardizes the function description information to obtain structured description information.

[0063] In one embodiment, the computer device can configure processing logic with a complexity greater than a predetermined threshold (such as time-based freight, regional pricing strategies, etc.) as configurable parameters, so that system functions can flexibly respond to market / policy changes (such as a 10% increase in holiday freight rates).

[0064] S203 : In response to receiving the service query request, perform semantic recognition on the service query request and generate prompt information.

[0065] In some embodiments, a computer device uses an intent classification model in the field of natural language processing (NLP) to perform semantic recognition processing on voice data or text data corresponding to a business query request, obtains a semantic recognition result, and obtains an intent classification of the business query request, i.e., user needs, based on the semantic recognition result; based on the intent classification, generates prompt information including business background, data range, and operation options; for example, the prompt information may be "The user needs to inquire about the transportation status of fresh food from location A to location B."

[0066] In some embodiments, a computer device trains an intent classification model based on training sample data with labeled intent classification. For example, intent classification may include but is not limited to calculating transportation, AI costs, querying transportation status, etc.; during the training process, the cross-entropy loss function can be used to iteratively optimize the model, and the model parameters of the intent classification model can be updated through the back-propagation algorithm to improve the accuracy of intent classification.

[0067] S204: Obtain a target prediction result based on at least one of the standard business data, the structured description information, and the prompt information.

[0068] In some embodiments, a computer device may input one or more of standard business data, structured description information, and prompt information into an artificial intelligence (AI) large model to obtain target prediction results for prompt information (i.e., user needs) in real time.

[0069] In the above-mentioned intelligent interaction method based on AI large-scale logistics data, by standardizing business data, data differences between different systems (corresponding to different application scenarios), platforms or devices can be eliminated, facilitating subsequent processing and analysis of business data; parsing system functions and generating structured description information can help to automatically understand and call related functional modules, and improve the intelligent scheduling capabilities of the logistics system; integrating multi-dimensional data such as standardized business data (such as historical sales, supply chain delivery time, etc.), structured description information (such as promotion rules, vehicle scheduling algorithms, etc.) and prompt information can cover all logistics elements, achieve accurate demand forecasting, assist users in making quick decisions, and meet the query, calculation and / or scheduling needs in the entire logistics scenario.

[0070] In some embodiments, converting the business data into standard business data includes:

[0071] Performing semantic recognition on the business data to extract target entities; wherein the target entities include at least one of order entities, transportation entities, inventory entities, and equipment entities;

[0072] Creating a data view that matches the entity type of the target entity according to the target entity; wherein the data view includes at least one of a global inventory view, a risk warning view, and a real-time transportation capacity view;

[0073] Based on foreign key constraints, various data views are associated to obtain standard business data.

[0074] In the embodiment of the present application, a foreign key constraint is a mechanism used in a relational database to maintain referential integrity between different tables / data views.

[0075] In some embodiments, the computer device may input raw business data into a name recognition model, capture contextual information of the business data through a multi-layer Transformer encoder, and use a conditional random field (CRF) in the output layer to predict and label target entities and categories.

[0076] Optionally, the order entity may include but is not limited to at least one field of order number, customer information, goods details and timeliness requirements.

[0077] Optionally, the transport entity may include but is not limited to at least one field of waybill number, carrier, vehicle information, personnel information and positioning information.

[0078] Optionally, the inventory entity may include but is not limited to at least one field of a storage location code, a minimum stock keeping unit (SKU), a batch, an expiration date, an inventory quantity, and temperature / humidity data.

[0079] Optionally, the device entity may include but is not limited to at least one field of a device tag, a device load capacity, and a shelf radio frequency identification (RFID) tag.

[0080] In one embodiment, the computer device can use data modeling technology to perform entity-relationship analysis on data tables in the logistics system to extract target entities; and generate data views based on the target entities and database view creation technology.

[0081] In one embodiment, if the target entity is an inventory entity, the data view that matches the entity type of the inventory entity is the global inventory view. The global inventory view can be linked to reservation records in the order tracking view using fields such as the available quantity, in-transit quantity, and locked quantity of the smallest stock keeping unit (SKU) using foreign keys.

[0082] In one embodiment, if the target entity is a transportation entity, the data view that matches the entity type of the transportation entity is a real-time capacity view. The real-time capacity view can use foreign keys to constrain the allocation status of the transportation task table based on fields such as vehicle location, remaining load, route planning, and driver work hours.

[0083] In one embodiment, when the target entity includes an inventory entity, a transportation entity, and an equipment entity, the data view that matches the entity type of the target entity can be a risk warning view. The risk warning view can incorporate fields such as inventory expiration date, transportation delay records, and equipment failure history.

[0084] In an embodiment of the present application, by performing semantic recognition on the original business data and extracting the target entities, and then converting these entities into data frames in a unified format, the business data from different sources can be logically consistent, which is convenient for subsequent analysis and integration; by creating and displaying data views, the visualization ability of business data can be improved, and after the new function, new module or new data source is connected, it can be quickly integrated with the existing part, which can enhance the scalability of the system.

[0085] In some embodiments, obtaining a target prediction result based on at least one of the standard business data, the structured description information, and the prompt information includes:

[0086] Matching the prompt information with the structured description information to obtain a matching result;

[0087] If the matching result is successful, the prompt information, the standard business data matching the prompt information, and the structured description information are input into the AI ​​big model to obtain a candidate result;

[0088] The system function matching the prompt information is executed, and combined with the candidate results to obtain the target prediction result.

[0089] In some embodiments, the computer device matches the intent classification corresponding to the prompt information with the function name field in the structured description information to determine whether the matching result is a successful match; when the intent classification and the function name field are successfully matched, the prompt information, the standard business data (i.e., the data view) matching the prompt information, and the structured description information matching the prompt information are input into the AI ​​big model to obtain a candidate result; the AI ​​big model is used to call the system function matching the prompt information to obtain a second result; based on the candidate result and the second result, the target prediction result is obtained.

[0090] In the embodiments of the present application, by matching prompt information with structured description information, both can be input into the AI ​​large model, providing more accurate input for the AI ​​large model, making the output candidate results more consistent with the actual situation, thereby improving the accuracy of the target prediction results. In the case of a successful match, the corresponding system function is executed to make appropriate responses to different scenarios, enhancing the flexibility of the logistics system and its adaptability to diverse needs. Furthermore, by determining the target prediction result based on the candidate results and the second result (dual result), the accuracy of the target prediction result can be further improved compared to a single input and single output.

[0091] In some embodiments, the method further comprises:

[0092] In the case where the matching result is a matching failure, the prompt information and the standard business data matching the prompt information are input into the AI ​​big model to obtain the target prediction result.

[0093] In some embodiments, when the matching result is a match failure, the computer device can directly input the prompt information and the data view matching the prompt information into the AI ​​big model, and the model output result is the target prediction result.

[0094] In an embodiment of the present application, when the matching result is a matching failure, even if the structured description information and the system function fail to match successfully, the prompt information and standard business data still contain valuable information; inputting this information into the AI ​​big model can reduce the information waste caused by matching failure, and the AI ​​big model can still make reasonable and accurate predictions based on the prompt information and standard business data, providing a guarantee for the user's experience.

[0095] In some embodiments, executing the system function that matches the prompt information and combining the candidate results to obtain the target prediction result includes at least one of the following:

[0096] The first method is to obtain a predicted path set based on an improved ant colony algorithm when executing the path optimization function that matches the prompt information; and obtain the target predicted result based on the predicted path set and the candidate result;

[0097] The second method is to obtain an inventory forecast result based on the Prophet model when executing the inventory forecast function that matches the prompt information; and obtain the target forecast result based on the inventory forecast result and the candidate result;

[0098] The third method is to obtain a matching matrix between vehicles and cargoes based on a mixed integer programming algorithm when executing a transportation scheduling function that matches the prompt information; and obtain the target prediction result based on the matching matrix and the candidate results.

[0099] In the embodiment of the present application, the path optimization function may include but is not limited to at least one parameter of the starting point coordinates, the destination list, the vehicle load, the traffic conditions and the cost model (fuel consumption / time consumption).

[0100] In some embodiments, the computer device can obtain dynamic road condition data through the traffic condition API, build a road network status time series database, and update the road section travel time according to the interval time; take the cost of the path (including fuel consumption, road and bridge fees, and driver wages, etc.) and time (estimated arrival time) as the optimization target, and each path as a function solution (including the sequence of nodes passed through and the corresponding transportation cost and time); calculate the probability of selecting the next node j at node i, and retain non-dominated solutions in each round of probability calculation iteration based on the Pareto (Pareto Dominance) dominance relationship to form a dynamically updated solution set, that is, the predicted path set.

[0101] Exemplarily, the computer device calculates the probability of selecting the next node j at node i using the ant colony algorithm as follows:

[0102]

[0103] in, Indicates the concentration of cost-related information accumulated on edge (road segment) i to j, reflecting the pros and cons of the economic cost of this road segment in historical path selection; Indicates the time-related factor concentration accumulated on edge (road segment) i to j, reflecting the time efficiency of this road segment in historical path selection (such as travel speed, etc.); Indicates the heuristic factor for edge (road segment) i to j, determined by the current road conditions; indicates the hyperparameter that controls the cost pheromone weight; indicates the hyperparameter used to control the temporal pheromone weight; Indicates the hyperparameter that controls the heuristic factor weights.

[0104] In one embodiment, when a computer device receives a new order, it parses the order, extracts the order's pickup point, delivery point, time window, and cargo attributes (volume / weight); traverses the paths in the existing solution set and identifies vehicles that conflict with the new order (e.g., paths overlap and capacity is insufficient); finds the best insertion point in the path so that the cost and time changes after the new path / stop are minimized; if the target value is improved after the new path is inserted (e.g., cost is reduced or time is shortened), the pheromone of the related edge is enhanced, or, for the path that is overloaded or timed out due to the insertion of the order, its pheromone is evaporated to reduce the probability of subsequent selection.

[0105] In the embodiment of the present application, the inventory forecasting function may include but is not limited to at least one parameter selected from historical sales volume (time series), supply chain delivery time, seasonal factors, and promotional factors.

[0106] In some embodiments, the computer device can extract historical sales data from the business system, align it at a daily / weekly granularity, and clean outliers (such as smoothing out abnormal peaks during promotions); obtain promotion plan data within a preset time, and label the promotion plan data with promotion type, covered SKU, and expected traffic growth, etc.; obtain the supplier's historical delivery on-time rate, and dynamically calculate the number of safety stock buffer days in combination with current production capacity and logistics timeliness; fit historical data through Fourier series to extract annual periodicity (such as holidays) and monthly fluctuations (such as the impact of the rainy season on commodities); based on growth trends, periodic items, and holiday effects, combine piecewise linear or logistic growth curves to establish a Prophet model to simulate trend changes and automatically identify mutation points; and calculate inventory forecast results based on the Prophet model.

[0107] In an embodiment of the present application, the capacity scheduling function may include but is not limited to at least one parameter of the volume / weight of the goods to be transported, the vehicle type (cold chain transportation / ordinary transportation) and the delivery time window.

[0108] In one embodiment, a computer device obtains cargo attribute data, standardizes the cargo attribute data, unifies transport units, and marks special cargo (such as cold chain cargo and vibration-sensitive cargo); synchronizes vehicle location, remaining capacity, and cold chain status in real time, and verifies driver compliance; establishes a mixed-integer programming (MIP) model based on fixed costs (vehicle basic fees), variable costs (fuel consumption, road and bridge fees, refrigeration energy consumption), and penalty costs (time window deviation, customer priority adjustment) in combination with constraints; calculates a matching matrix between vehicles and cargo based on the MIP model; the constraints may include capacity constraints, time constraints, and regulatory constraints, for example, a vehicle load must reserve 8% emergency space as a capacity buffer; or a driver must drive less than or equal to eight hours a day, etc.

[0109] In the embodiments of this application, an improved ant colony algorithm can effectively solve complex path planning problems. The Prophet model can accurately predict future inventory demand based on historical data, meeting the processing requirements of datasets with seasonal or trending changes. A mixed integer programming algorithm can accurately calculate the optimal vehicle and cargo matching solution, ensuring efficient resource utilization. Different types of prediction tasks require different algorithms / functions. The algorithm that best suits the current scenario is determined based on prompt information, improving the accuracy, reliability, and flexibility of the target prediction results.

[0110] In some embodiments, the method further comprises:

[0111] In response to receiving feedback information of the target prediction result, if the evaluation score included in the feedback information is less than a qualified threshold, obtaining modification information of the prompt information;

[0112] Updating the prompt information based on the modification information to obtain updated prompt information;

[0113] An updated target prediction result is obtained based on at least one of the standard business data, the structured description information and the updated prompt information.

[0114] In the embodiment of the present application, the evaluation score may include but is not limited to at least one of an accuracy evaluation score, a timeliness evaluation score, and a completeness evaluation score.

[0115] In one embodiment, the qualification thresholds corresponding to different evaluation scores may be the same or different. The computer device may use a sliding window algorithm to automatically adjust the qualification threshold based on historical feedback information over a predetermined period of time (eg, seven days).

[0116] In some embodiments, after outputting the target prediction result, the computer device can obtain user feedback information on the target detection result, and the feedback information includes the evaluation score of each indicator; when the evaluation score of any indicator is less than the qualified threshold, the user's modification information on the prompt information can be obtained or corresponding modification information can be generated based on the indicator whose evaluation score is less than the qualified threshold; the modification information may include but is not limited to at least one of parameter adjustment, model replacement and data correction; the prompt information is updated based on the modification information to obtain updated prompt information.

[0117] For example, the feedback information is "the predicted capacity is 5, the capacity is insufficient, and the accuracy assessment score is 70"; the qualified threshold value corresponding to the accuracy assessment score in the current scenario is 80, and the accuracy assessment score is less than the qualified threshold value 80, then the modification information "it is recommended to increase the number of transport vehicles parameter, but do not modify the time window" can be generated based on the feedback information; the number of transport vehicles parameter is adjusted based on the modification information, and other parameters remain unchanged to obtain the updated prompt information.

[0118] In the embodiment of the present application, a closed-loop feedback mechanism is formed by receiving feedback information on the target prediction results and making corrections based on the feedback information. When the target prediction results are not ideal, the prompt information can be automatically or assisted by the user to optimize according to the feedback information, thereby guiding the AI ​​large model to output results that are more in line with actual needs and increase its adaptability to complex scenarios. In addition, the same type of prediction task may require different processing logic in different business scenarios. Through feedback-driven prompt optimization, different business needs can be met. For example, in logistics scheduling, some are more concerned about timeliness, while others are more concerned about cost. Feedback can be used to adjust prompt information to highlight priorities and prompt user experience.

[0119] In the embodiments of the present application, the following provides specific examples in combination with any of the above embodiments:

[0120] Specific Example 1: This application provides an example process for a computer device to implement an intelligent interaction method based on AI large model logistics data; when a processor in the computer device executes a computer program, the following steps are implemented:

[0121] Use data modeling technology to perform entity-relationship analysis on the business data tables in the logistics system and extract the target entities; use database view creation technology to generate data views from the target entities; use foreign key constraint technology to establish relationships between views and obtain standard business data.

[0122] Structured description information is generated for the system functions in the logistics system, and the structured description information includes function name, input requirements and processing logic.

[0123] In response to receiving a business query request, the voice data or text data input by the user is analyzed through the intent classification model to determine the corresponding intent classification; based on the intent classification, a prompt word representing the user's needs is generated.

[0124] Standard business data, structured description information and prompt information are synchronously input into the AI ​​big model to obtain candidate results; the prompt information is matched with the system function, and if the match is successful, the matched system function is executed to obtain the function result; based on the function result and the candidate result, the target prediction result is obtained; if the match fails, the candidate result output by the AI ​​big model is determined to be the target prediction result.

[0125] In the embodiment of the present application, by standardizing business data, data differences between different systems (corresponding to different application scenarios), platforms or devices can be eliminated, which facilitates subsequent processing and analysis of business data; parsing system functions and generating structured description information helps to automatically understand and call related functional modules, and improve the intelligent scheduling capabilities of the logistics system; integrating multi-dimensional data such as standardized business data (such as historical sales, supply chain delivery time, etc.), structured description information (such as promotion rules, vehicle scheduling algorithms, etc.) and prompt information can cover all elements of logistics, achieve accurate demand forecasting, assist users in making quick decisions, and meet the query, calculation and / or scheduling needs in the entire logistics scenario.

[0126] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0127] Based on the same inventive concept, the embodiments of the present application also provide an intelligent interaction device based on AI large model logistics data for implementing the aforementioned intelligent interaction method based on AI large model logistics data. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more intelligent interaction embodiments based on AI large model logistics data provided below can be found in the above limitations of the intelligent interaction method based on AI large model logistics data, and will not be repeated here.

[0128] In one embodiment, Figure 3 As shown, an intelligent interactive device based on AI large model logistics data is provided, the device comprising:

[0129] A conversion module 10 is used to obtain business data in the logistics system and convert the business data into standard business data;

[0130] A first generating module 20 is used to analyze and identify system functions in the logistics system and generate structured description information;

[0131] The second generating module 30 is configured to perform semantic recognition on the business query request in response to receiving the business query request and generate prompt information;

[0132] The determination module 40 is configured to obtain a target prediction result based on at least one of the standard business data, the structured description information, and the prompt information.

[0133] In one embodiment, the conversion module 10 is configured to perform the following steps:

[0134] Performing semantic recognition on the business data to extract target entities; wherein the target entities include at least one of order entities, transportation entities, inventory entities, and equipment entities;

[0135] Creating a data view that matches the entity type of the target entity according to the target entity; wherein the data view includes at least one of a global inventory view, a risk warning view, and a real-time transportation capacity view;

[0136] The data views are associated based on foreign key constraints to obtain the standard business data.

[0137] In one embodiment, the first generating module 20 is configured to perform the following steps:

[0138] Parsing and identifying the code corresponding to the system function to obtain function description information; wherein the system function includes at least one of a route optimization function, an inventory forecasting function, and a transportation capacity scheduling function; the function description information includes a function name, input parameters, and functional logic;

[0139] The function description information is standardized to obtain the structured description information; wherein the structured description information includes a function name, input requirements, and processing logic.

[0140] In one embodiment, the determining module 40 includes:

[0141] a matching unit, configured to match the prompt information with the structured description information to obtain a matching result;

[0142] A first processing unit is configured to, when the matching result is successful, input the prompt information, the standard business data matching the prompt information, and the structured description information into an AI big model to obtain a candidate result;

[0143] The second processing unit is used to execute the system function that matches the prompt information and obtain the target prediction result in combination with the candidate results.

[0144] In one embodiment, the determining module 40 is further configured to perform the following steps:

[0145] In the case where the matching result is a matching failure, the prompt information and the standard business data matching the prompt information are input into the AI ​​big model to obtain the target prediction result.

[0146] In one embodiment, the second processing unit is configured to perform at least one of the following steps:

[0147] The first method is to obtain a predicted path set based on an improved ant colony algorithm when executing the path optimization function that matches the prompt information; and obtain the target predicted result based on the predicted path set and the candidate result;

[0148] The second method is to obtain an inventory forecast result based on the Prophet model when executing the inventory forecast function that matches the prompt information; and obtain the target forecast result based on the inventory forecast result and the candidate result;

[0149] The third method is to obtain a matching matrix between vehicles and cargoes based on a mixed integer programming algorithm when executing a transportation scheduling function that matches the prompt information; and obtain the target prediction result based on the matching matrix and the candidate results.

[0150] In one embodiment, the apparatus further comprises:

[0151] an acquisition module, configured to, in response to receiving feedback information of the target prediction result, acquire modification information of the prompt information if the evaluation score included in the feedback information is less than a qualified threshold;

[0152] The second generating module 30 is configured to update the prompt information based on the modification information to obtain updated prompt information;

[0153] The determination module 40 is configured to obtain an updated target prediction result based on at least one of the standard business data, the structured description information, and the updated prompt information.

[0154] Each module in the above-mentioned intelligent interactive device based on AI large model logistics data can be fully or partially implemented through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor of the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above modules.

[0155] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, memory, a communication interface, a display unit, and an input device connected via a method bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating method and a computer program. The internal memory provides an environment for the operation of the operating method and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal via wired or wireless communication. The wireless communication method can be achieved through Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements an image processing method. The display screen of the computer device can be a liquid crystal display or an electronic ink display. The input device of the computer device can be a touch layer covering the display screen, or keys, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse.

[0156] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0157] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0158] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps performed by a processor of a computer device when the computer program is executed by a processor.

[0159] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0160] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0161] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0162] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. An intelligent interaction method based on AI large model logistics data, characterized by: The method comprises: Acquire business data in the logistics system and convert the business data into standard business data; Parsing and identifying system functions in the logistics system to generate structured description information; wherein, parsing and identifying system functions in the logistics system to generate structured description information includes: parsing and identifying codes corresponding to the system functions to obtain function description information; wherein, the system functions include at least one of a route optimization function, an inventory forecasting function, and a transportation scheduling function; the function description information includes a function name, input parameters, and functional logic; and standardizing the function description information to obtain the structured description information; wherein, the structured description information includes a function name, input requirements, and processing logic; In response to receiving a service query request, performing semantic recognition on the service query request and generating prompt information; Based on at least one of the standard business data, the structured description information and the prompt information, a target prediction result is obtained; wherein, the target prediction result is obtained based on at least one of the standard business data, the structured description information and the prompt information, including: matching the prompt information with the structured description information to obtain a matching result; when the matching result is a successful match, inputting the prompt information, the standard business data matching the prompt information and the structured description information into the AI ​​big model to obtain a candidate result; executing the system function matching the prompt information, and combining the candidate result to obtain the target prediction result.

2. The method according to claim 1, characterized in that The converting the business data into standard business data includes: Performing semantic recognition on the business data to extract target entities; wherein the target entities include at least one of order entities, transportation entities, inventory entities, and equipment entities; Creating a data view that matches the entity type of the target entity according to the target entity; wherein the data view includes at least one of a global inventory view, a risk warning view, and a real-time transportation capacity view; The data views are associated based on foreign key constraints to obtain the standard business data.

3. The method according to claim 1, characterized in that The method further comprises: In the case where the matching result is a matching failure, the prompt information and the standard business data matching the prompt information are input into the AI ​​big model to obtain the target prediction result.

4. The method according to claim 1, wherein The executing the system function matching the prompt information and combining the candidate results to obtain the target prediction result includes at least one of the following: The first method is to obtain a predicted path set based on an improved ant colony algorithm when executing the path optimization function that matches the prompt information; and obtain the target predicted result based on the predicted path set and the candidate result; The second method is to obtain an inventory forecast result based on the Prophet model when executing the inventory forecast function that matches the prompt information; and obtain the target forecast result based on the inventory forecast result and the candidate result; The third method is to obtain a matching matrix between vehicles and cargo based on a mixed integer programming model when executing a capacity scheduling function that matches the prompt information; The target prediction result is obtained based on the matching matrix and the candidate results.

5. The method according to claim 1, wherein The method further comprises: In response to receiving feedback information of the target prediction result, if the evaluation score included in the feedback information is less than a qualified threshold, obtaining modification information of the prompt information; Updating the prompt information based on the modification information to obtain updated prompt information; An updated target prediction result is obtained based on at least one of the standard business data, the structured description information and the updated prompt information.

6. An intelligent interactive device based on AI large model logistics data, characterized in that: The device comprises: A conversion module, used to obtain business data in the logistics system and convert the business data into standard business data; A first generation module is configured to parse and identify system functions in the logistics system to generate structured description information; wherein the parse and identify system functions in the logistics system to generate structured description information includes: parsing and identifying codes corresponding to the system functions to obtain function description information; wherein the system functions include at least one of a route optimization function, an inventory forecasting function, and a transportation scheduling function; wherein the function description information includes a function name, input parameters, and functional logic; and performing standardization processing on the function description information to obtain the structured description information; wherein the structured description information includes a function name, input requirements, and processing logic; A second generating module is configured to, in response to receiving a service query request, perform semantic recognition on the service query request and generate prompt information; A determination module is used to obtain a target prediction result based on at least one of the standard business data, the structured description information and the prompt information; wherein, obtaining the target prediction result based on at least one of the standard business data, the structured description information and the prompt information includes: matching the prompt information with the structured description information to obtain a matching result; when the matching result is a successful match, inputting the prompt information, the standard business data matching the prompt information and the structured description information into the AI ​​big model to obtain a candidate result; executing the system function that matches the prompt information, and combining the candidate result to obtain the target prediction result.

7. A computer device, characterized in that: The method comprises a processor and a memory; wherein the memory is used to store a computer program; and the processor is configured to implement the method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images