Prompt information generation method and apparatus, terminal device, and storage medium

Abstract

The present application is applicable to the technical field of automobiles, and provides a prompt information generation method and apparatus, a terminal device, and a storage medium. The method comprises: acquiring vehicle information of a target fleet, fleet operation information, behavior information of drivers, and a prompt keyword for the target fleet; and inputting the vehicle information, the fleet operation information, the behavior information and the prompt keyword into a trained prompt information generation model for processing, to obtain prompt information corresponding to the prompt keyword. Compared with existing technologies that merely generate corresponding prompt information on the basis of vehicle information, such as wheel statuses and fuel level statuses, this method can generate more comprehensive prompt information by integrating vehicle information, fleet operation information, and behavior information of drivers, and additionally, by further integrating a prompt keyword and a prompt information generation model, this method can generate, in a targeted manner, prompt information that better meets actual needs and is more accurate, thereby improving the generation accuracy of prompt information, and also enhancing the practicability of the generated prompt information.

Description

Prompt information generation method, device, terminal device and storage medium Technical Field

[0001] The present application relates to the field of automobile technology, and in particular to a method, apparatus, terminal device, and storage medium for generating prompt information. Background Art

[0002] Fleet management is a critical task in modern transportation. Effective fleet management can improve transportation efficiency, reduce costs, and ensure safety. Generating real-time fleet management recommendations and prompts is a key means of improving the efficiency and accuracy of fleet management.

[0003] However, existing prompt information generation methods usually only generate corresponding prompt information based on vehicle information, such as wheel status and fuel level status, which is not comprehensive enough, thereby reducing the accuracy of prompt information generation and the practicality of the generated prompt information. Technical issues

[0004] One of the purposes of the embodiments of the present application is to provide a prompt information generation method, apparatus, terminal device and storage medium to solve the technical problems in the prior art of low accuracy in generating prompt information and low practicality of the generated prompt information. Technical Solutions

[0005] The technical solution adopted in the embodiment of this application is:

[0006] In a first aspect, a method for generating prompt information is provided, comprising:

[0007] Obtaining fleet data of a target fleet and prompt keywords of the target fleet; wherein the fleet data includes vehicle information, fleet operation information, and driver behavior information;

[0008] The vehicle information, the fleet operation information, the behavior information and the prompt keyword are input into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword; wherein, the prompt information generation model is trained by a pre-built large language model.

[0009] In one embodiment, the prompt keywords are obtained in the following manner:

[0010] Obtaining mission information, fleet data, and historical fleet management information of the target fleet;

[0011] Determining demand information of the target fleet based on the fleet data and the historical fleet management information;

[0012] The prompt keywords are generated based on the task information and the requirement information.

[0013] In one embodiment, the prompt information generation model includes a semantic analysis layer and a prompt information generation layer; the vehicle information, the fleet operation information, the behavior information, and the prompt keyword are input into the trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword, including:

[0014] Inputting the vehicle information, the fleet operation information, and the behavior information into the semantic analysis layer for processing to obtain the current status information of the target fleet;

[0015] The prompt keyword and the current state information are input into the prompt information generation layer for processing to obtain the prompt information.

[0016] In one embodiment, the step of inputting the prompt keyword and the current state information into the prompt information generation layer for processing to obtain the prompt information includes:

[0017] Determining, based on the prompt keyword, a plurality of prompt elements corresponding to the prompt information;

[0018] The prompt information is generated based on the plurality of prompt elements and the current state information.

[0019] In one embodiment, determining the plurality of prompt elements corresponding to the prompt information according to the prompt keyword includes:

[0020] Determining candidate words associated with the prompt keyword;

[0021] Performing causal analysis on the prompt keyword and the candidate words respectively to obtain a first analysis result corresponding to the prompt keyword and a second analysis result corresponding to the candidate words;

[0022] A plurality of the prompt elements are determined based on the first analysis result and the second analysis result.

[0023] In one embodiment, the vehicle information, the fleet operation information, and the behavior information are all structured data; before inputting the vehicle information, the fleet operation information, the behavior information, and the prompt keyword into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword, the method further includes:

[0024] performing data preprocessing on the vehicle information, the fleet operation information, and the behavior information in sequence to obtain first data corresponding to the vehicle information, second data corresponding to the fleet operation information, and third data corresponding to the behavior information;

[0025] Converting the first data, the second data, and the third data in sequence based on natural language processing technology to obtain first text information corresponding to the first data, second text information corresponding to the second data, and third text information corresponding to the third data;

[0026] generating target text information corresponding to the fleet data according to the first text information, the second text information, and the third text information;

[0027] Accordingly, the vehicle information, the fleet operation information, the behavior information, and the prompt keyword are input into the trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword, including:

[0028] The target text information and the prompt keyword are input into the prompt information generation model for processing to obtain the prompt information.

[0029] In one embodiment, before inputting the vehicle information, the fleet operation information, the behavior information, and the prompt keyword into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword, the method further includes:

[0030] Obtaining historical fleet data and historical fleet management information of the target fleet within a historical time period;

[0031] The large language model is pre-trained according to the historical fleet data and the historical fleet management information to obtain the prompt information generation model.

[0032] In a second aspect, a prompt information generating device is provided, comprising:

[0033] a first acquiring unit, configured to acquire fleet data of a target fleet and prompt keywords of the target fleet; wherein the fleet data includes vehicle information, fleet operation information, and driver behavior information;

[0034] The first processing unit is used to input the vehicle information, the fleet operation information, the behavior information and the prompt keyword into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword; wherein the prompt information generation model is trained by a pre-built large language model.

[0035] In a third aspect, a terminal device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the prompt information generation method as described in any one of the first aspects when executing the computer program.

[0036] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by a processor, the prompt information generating method as described in any one of the first aspects is implemented.

[0037] In a fifth aspect, a computer program product is provided. When the computer program product is run on a terminal device, the terminal device can execute the prompt information generation method described in any one of the above-mentioned first aspects. Beneficial effects

[0038] The target fleet's fleet data and prompt keywords are obtained; the fleet data includes vehicle information, fleet operation information, and driver behavior information; the vehicle information, fleet operation information, behavior information, and prompt keywords are input into a trained prompt information generation model for processing to generate prompt information corresponding to the prompt keywords; the prompt information generation model is trained using a pre-built large-scale language model. Compared to existing technologies that generate prompt information based solely on vehicle information, such as wheel status and fuel level, this method combines vehicle information, fleet operation information, and driver behavior information to generate richer prompt information. Furthermore, by combining prompt keywords with the prompt information generation model, it can generate more targeted and accurate prompt information that better meets actual needs, thereby improving the accuracy and practicality of the generated prompt information. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or exemplary technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0040] FIG1 is a flowchart of a method for generating prompt information according to an embodiment of the present application;

[0041] FIG2 is a flowchart of a method for generating prompt information according to another embodiment of the present application;

[0042] FIG3 is a flowchart of a method for generating prompt information according to another embodiment of the present application;

[0043] FIG4 is a flowchart of a method for generating prompt information according to another embodiment of the present application;

[0044] FIG5 is a schematic diagram of the structure of a prompt information generating device provided in an embodiment of the present application;

[0045] FIG6 is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application. Modes for Carrying Out the Invention

[0046] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit this application.

[0047] It should be noted that when a component is referred to as being "fixed on" or "disposed on" another component, it may be directly on the other component or indirectly on the other component. When a component is referred to as being "connected to" another component, it may be directly or indirectly connected to the other component. The terms "upper", "lower", "left", "right", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of description and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on this application. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances. The terms "first" and "second" are only used for the purpose of convenience of description and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0048] Fleet management is a critical task in modern transportation. Effective fleet management can improve transportation efficiency, reduce costs, and ensure safety. However, traditional fleet management methods typically rely on experience and manual decision-making to output fleet management suggestions and prompts, lacking intelligent and automated support. Furthermore, existing methods for generating prompt information typically only generate corresponding prompt information based on vehicle information, such as wheel status and fuel level. This lacks comprehensive consideration, reducing the accuracy and practicality of the generated prompt information.

[0049] Based on this, in all embodiments of this application, a method for generating prompt information is provided to achieve intelligent and automated generation of prompt information, while also improving the accuracy of prompt information generation and the practicality of the generated prompt information. The specific implementation process of the above prompt information generation method can be found in the corresponding embodiment of the figure below, and will not be repeated here.

[0050] FIG1 is a flowchart of a method for generating prompt information provided by an embodiment of the present application. As shown in FIG1 , the method for generating prompt information may include the following steps:

[0051] In S101 , fleet data of a target fleet and prompt keywords of the target fleet are obtained; wherein the fleet data includes vehicle information, fleet operation information, and driver behavior information.

[0052] In actual applications, in order to generate accurate prompt information, the manager can send a prompt information generation request to the terminal device. The manager specifically refers to the decision-maker or manager of the target fleet.

[0053] In an embodiment of the present application, the terminal device detecting a prompt information generation request may include: detecting a preset operation for the terminal device. The preset operation may be determined according to actual needs and is not limited here. Exemplarily, the preset operation may be: the preset control of the terminal device is triggered. Based on this, when the terminal device detects that its own preset control is triggered, it indicates that the preset operation is detected, that is, the above-mentioned prompt information generation request is detected; of course, the preset operation may also be a time-triggered operation, and the terminal device may be configured with a corresponding operation process during operation, and the operation process includes trigger nodes for multiple key events, and the above-mentioned key events include prompt information generation events. In this case, if the terminal device detects that the trigger node associated with the prompt information generation event has been reached, the operations of S101~S102 are executed to perform the prompt generation operation.

[0054] After detecting the prompt information generation request, the terminal device can obtain the fleet data of the target fleet and the prompt keywords of the target fleet; wherein the fleet data includes vehicle information, fleet operation information and driver behavior information.

[0055] It should be noted that the target fleet can be an engineering fleet or a logistics and transportation fleet, and there is no restriction here.

[0056] Vehicle information includes but is not limited to: license plate number, model, driving time, speed and fuel level of each vehicle in the target fleet.

[0057] Fleet operation information includes, but is not limited to, fleet size, average vehicle utilization, transport efficiency, transport costs, vehicle maintenance rate, and service quality score. Fleet size represents the total number of vehicles in the target fleet. Average vehicle utilization refers to the percentage between the number of vehicles currently in use and the total number of vehicles in the target fleet. Transport efficiency refers to the percentage between the actual duration and theoretical duration of a transport mission performed by the target fleet. Vehicle maintenance rate refers to the percentage between the number of vehicles repaired and the total number of vehicles in the target fleet. The service quality score specifically refers to customer satisfaction and on-time delivery rates.

[0058] The driver's behavior information includes but is not limited to: the performance of the driver of each vehicle in the target fleet during the driving process, such as whether the driver is fatigued or driving in violation of regulations.

[0059] In the embodiment of the present application, the prompt keywords of the target fleet specifically refer to the key points of the fleet management suggestions for the target fleet.

[0060] It should be noted that the prompt keyword can be one or more.

[0061] In one embodiment of the present application, the manager can input the prompt keyword of the target fleet on the display interface of the terminal device, based on which the terminal device can obtain the prompt keyword of the target fleet.

[0062] In another embodiment of the present application, in order to improve the accuracy of obtaining the prompt keyword so that the prompt keyword is more consistent with the current status and specific needs of the target fleet, the terminal device can specifically obtain the prompt keyword according to the following steps, which are detailed as follows:

[0063] Obtaining mission information, fleet data, and historical fleet management information of the target fleet;

[0064] Determining demand information of the target fleet based on the fleet data and the historical fleet management information;

[0065] The prompt keywords are generated based on the task information and the requirement information.

[0066] In this embodiment, the historical fleet management information refers to the fleet management records of the target fleet within a historical time period. The historical time period can be determined according to actual needs and is not limited here.

[0067] It should be noted that the above-mentioned fleet management records include historical fleet operation status, historical fleet demand and historical fleet prompt information corresponding to each transportation task of the target fleet within the historical time period.

[0068] The historical fleet operation status includes but is not limited to vehicle information, fleet operation information, and driver behavior information for each transport mission of the target fleet within a historical time period.

[0069] Historical fleet prompts specifically refer to fleet management recommendations for each transport mission within a historical time period. These include, but are not limited to, first prompts related to route optimization, second prompts related to resource allocation, third prompts related to vehicle maintenance, and fourth prompts related to drivers.

[0070] In this embodiment, after obtaining the fleet data and historical fleet management information of the target fleet, the terminal device can compare the fleet data with the historical fleet operating conditions in the historical fleet management information one by one, determine the historical fleet operating conditions whose similarity with the fleet data is greater than or equal to a set threshold, and obtain the historical fleet demand corresponding to the historical fleet operating conditions whose similarity with the fleet data is greater than or equal to the set threshold.

[0071] Afterwards, the terminal device can determine the current operating status of the target fleet based on the fleet data of the target fleet. Finally, the terminal device can predict problems or challenges that may arise in the target fleet based on the current operating status, and determine the current needs of the target fleet based on the predicted problems or challenges that may arise in the target fleet.

[0072] Finally, the terminal device can determine the final demand of the target fleet, that is, the demand information of the target fleet, based on the current demand and the historical fleet demand obtained above.

[0073] In this embodiment, after obtaining the demand information of the target vehicle fleet, the terminal device may generate prompt keywords of the target vehicle fleet according to the demand information and task information.

[0074] In S102, the vehicle information, the fleet operation information, the behavior information and the prompt keyword are input into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword; wherein, the prompt information generation model is trained by a pre-built large language model.

[0075] In this embodiment of the present application, a terminal device can input vehicle information, fleet operation information, behavior information, and prompt keywords into a trained prompt information generation model for processing, thereby obtaining prompt information corresponding to the prompt keywords. The prompt information generation model is trained on a pre-built large-scale language model based on sample data. The sample data includes historical fleet data and historical fleet management information for the target fleet within a historical time period.

[0076] Based on this, the terminal device can obtain the prompt information generation model according to the following steps, which are detailed as follows:

[0077] Obtaining historical fleet data and historical fleet management information of the target fleet within a historical time period;

[0078] The large language model is pre-trained according to the historical fleet data and the historical fleet management information to obtain the prompt information generation model.

[0079] In practical applications, large language models (LLMs) are deep learning models trained on massive amounts of text data. They can not only generate natural language text but also deeply understand the meaning of the text and handle various natural language tasks such as text summarization, question answering, and translation.

[0080] Large language models include but are not limited to: Llama2 model and Chatgpt model.

[0081] It's important to note that large-scale language models employ a multi-layered neural network architecture, with each layer consisting of multiple neurons. The input text sequence is processed and transformed through a series of network layers, ultimately resulting in the model's output. Large-scale language models can employ the Transformer architecture as their neural network structure. This Transformer architecture incorporates a self-attention mechanism.

[0082] In large language models, the self-attention mechanism is implemented by performing matrix multiplication and softmax activation on the input text sequence. For each position, the large language model calculates the similarity between it and other positions and takes a weighted average of the sequence based on the weight of the similarity. In this way, at different network layers, the large language model can learn different relationships in the sequence, such as those between words and sentences.

[0083] It should be noted that the training process for the aforementioned large-scale language model consists of two phases: pre-training and fine-tuning. During the pre-training phase, the large-scale language model uses a large amount of text corpus (historical fleet data of the target fleet within the sample dataset over a historical period) for unsupervised learning, learning the linguistic patterns and semantic relationships within the text sequences. During the fine-tuning phase, the large-scale language model uses a small amount of labeled data (such as prompt keywords and historical fleet management information) for supervised learning to optimize the model parameters.

[0084] Based on this, in this embodiment, when training a pre-built large language model, the terminal device can input a sample data set into the large language model for pre-training and fine-tuning to obtain a trained prompt information generation model.

[0085] In one embodiment of the present application, since the prompt information generation model includes a semantic analysis layer and a prompt information generation layer, the terminal device can specifically obtain prompt information corresponding to the prompt keyword through steps S201 to S202 as shown in FIG. 2 , as detailed below:

[0086] In S201 , the vehicle information, the fleet operation information, and the behavior information are input into a semantic analysis layer for processing to obtain current status information of the target fleet.

[0087] In S202, the prompt keyword and the current state information are input into the prompt information generation layer for processing to obtain the prompt information.

[0088] In this embodiment, the terminal device can input vehicle information, fleet operation information and driver behavior information into the semantic analysis layer for analysis, so that the prompt information generation model can understand the current operating status of the target fleet based on the above vehicle information, fleet operation information and driver behavior information, thereby obtaining the current status information of the target fleet.

[0089] Afterwards, the terminal device can input the prompt keyword and current status information into the prompt information generation layer for processing, that is, determine the alternative prompt information corresponding to the target fleet based on the prompt keyword, and then select the target prompt information matching the current status information from the alternative prompt information in combination with the current status information of the target fleet, thereby obtaining the prompt information corresponding to the prompt keyword.

[0090] It should be noted that the prompt information can be one or more.

[0091] In one embodiment of the present application, in order to further improve the accuracy of generating prompt information, the terminal device can specifically generate prompt information corresponding to the prompt keyword through steps S301 to S302 as shown in FIG3 , as detailed below:

[0092] In S301, a plurality of prompt elements corresponding to the prompt information are determined according to the prompt keyword.

[0093] In this embodiment, the terminal device can determine multiple prompt elements corresponding to the prompt information according to the prompt keyword, wherein the prompt element is used to represent the specific prompt direction of the prompt information.

[0094] In one embodiment of the present application, the terminal device may specifically determine multiple prompt elements corresponding to the prompt information according to the following steps, which are detailed as follows:

[0095] Determining candidate words associated with the prompt keyword;

[0096] Performing causal analysis on the prompt keyword and the candidate words respectively to obtain a first analysis result corresponding to the prompt keyword and a second analysis result corresponding to the candidate words;

[0097] A plurality of the prompt elements are determined based on the first analysis result and the second analysis result.

[0098] In this embodiment, in order to enrich the specific content of the prompt information as much as possible, the terminal device can obtain candidate words that are similar to the prompt keyword, that is, candidate words associated with the prompt keyword, from a preset dictionary.

[0099] It is understandable that the candidate words are synonyms of the prompt keyword.

[0100] After obtaining the candidate words, the terminal device may perform causal analysis on the prompt keyword and the candidate words respectively to obtain a first analysis result corresponding to the prompt keyword and a second analysis result corresponding to the candidate words.

[0101] In practical applications, causal analysis aims to identify the causes of changes in a phenomenon, primarily addressing the question of "why." Causal analysis distinguishes the phenomenon that is the cause from other non-causal phenomena in the antecedent state of the research object, or distinguishes the phenomenon that is the result from other phenomena in the subsequent state of the research object.

[0102] For example, assuming that the prompt keyword is "route optimization", the terminal device can perform a cause-effect analysis on the prompt keyword "route optimization", analyze the reasons why route optimization is needed, and analyze the results of route optimization.

[0103] It should be noted that the first analysis result includes the generation reason and result corresponding to the specific content of the prompt keyword, and the second analysis result includes the generation reason and result corresponding to the specific content of the candidate word.

[0104] In this embodiment, after obtaining the first analysis result and the second analysis result, the terminal device may determine a plurality of prompt elements according to the first analysis result and the second analysis result.

[0105] For example, when the keyword "route optimization" is displayed, the corresponding first analysis result may include: the reason for the route optimization is that the target fleet is about to enter a congested area, and the result of the route optimization is that the travel time can be shortened and energy consumption can be reduced. Based on this, the terminal device may determine that the multiple prompt elements corresponding to the keyword "route optimization" include, but are not limited to: optimal route, avoiding congested areas, reducing transportation time, and fuel consumption.

[0106] When the keyword "resource allocation" is displayed, the corresponding first analysis result includes: the resource allocation is generated because the target fleet includes a large number of vehicles and a large number of drivers. The result of resource allocation is to reasonably distribute the number of vehicle usages and to balance the working hours of each driver as much as possible. Based on this, the terminal device can determine that the multiple prompt elements corresponding to the keyword "resource allocation" include but are not limited to: reasonable allocation of vehicles and reasonable allocation of drivers.

[0107] When the keyword prompt is "vehicle maintenance," the corresponding first analysis result includes: the cause of vehicle maintenance is a vehicle failure, and the route optimization result can avoid the vehicle failure. Based on this, the terminal device can determine that the multiple prompt elements corresponding to the keyword "vehicle maintenance" include, but are not limited to: regular vehicle maintenance plan, failure prediction, and preventive maintenance.

[0108] When the prompt keyword is "driver," the corresponding first analysis result includes: the driver's generation reason is the driver's illegal behavior or poor performance while driving the vehicle, and the driver's result is that the driver's behavior can be improved while driving the vehicle. Based on this, the terminal device can determine that the multiple prompt elements corresponding to the prompt keyword "driver" include but are not limited to: driver training plan, safe driving reminders, and performance evaluation indicators.

[0109] In S302, the prompt information is generated based on the plurality of prompt elements and the current state information.

[0110] In this embodiment, the terminal device can input multiple prompt elements and current status information into the prompt information generation layer for processing, that is, determine multiple alternative prompt information corresponding to the target fleet based on the multiple prompt elements, and then select at least one target prompt information that matches the current status information from the multiple alternative prompt information in combination with the current status information of the target fleet, thereby obtaining prompt information corresponding to the prompt keyword.

[0111] As can be seen from the above, the prompt information generation method provided in the embodiment of the present application obtains fleet data and prompt keywords of the target fleet; wherein the fleet data includes vehicle information, fleet operation information, and driver behavior information; the vehicle information, fleet operation information, behavior information, and prompt keywords are input into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keywords; wherein the prompt information generation model is trained by a pre-built large-scale language model. Compared with the existing technology that only generates corresponding prompt information based on vehicle information, such as wheel status and oil level status, this method combines vehicle information, fleet operation information, and driver behavior information to generate richer prompt information. At the same time, combined with prompt keywords and prompt information generation models, it can generate more targeted prompt information that is more in line with actual needs and more accurate, thereby improving the accuracy of prompt information generation and the practicality of the generated prompt information.

[0112] In one embodiment of the present application, since vehicle information, fleet operation information, and behavior information are all structured data, and the input requirement of the large language model is natural language, when these structured data are input into the prompt information generation model for processing, the prompt information generation model cannot fully understand the above structured data, resulting in the prompt information generation model being unable to generate accurate prompt information. Therefore, please refer to Figure 4, which is a flowchart of the implementation of the prompt information generation method provided by another embodiment of the present application. Compared with the embodiment corresponding to Figure 1, the prompt information generation method provided by this embodiment may also include S401 to S403 as shown in Figure 4 before step S102. Accordingly, step S102 may specifically include step S404, which is detailed as follows:

[0113] In S401, data preprocessing is performed on the vehicle information, the fleet operation information, and the behavior information in sequence to obtain first data corresponding to the vehicle information, second data corresponding to the fleet operation information, and third data corresponding to the behavior information.

[0114] It should be noted that data preprocessing includes, but is not limited to, data cleaning, data format conversion, and data normalization. Data cleaning is used to remove invalid or erroneous data to ensure data accuracy and completeness. Data format conversion converts raw data into a format suitable for processing by the conversion module, such as converting numeric data to text or percentages. Data normalization is used to bring data of different ranges and units into the same scale for subsequent conversion and comparison.

[0115] In this embodiment, the terminal device can perform data preprocessing on the vehicle information, fleet operation information and behavior information in sequence to obtain first data corresponding to the vehicle information, second data corresponding to the fleet operation information and third data corresponding to the behavior information.

[0116] It should be noted that the first data, the second data and the third data are still structured data.

[0117] In S402, the first data, the second data and the third data are converted in sequence based on natural language processing technology to obtain first text information corresponding to the first data, second text information corresponding to the second data and third text information corresponding to the third data.

[0118] In this embodiment, after obtaining the first data, the second data and the third data, the terminal device can respectively perform data conversion on the first data, the second data and the third data to obtain the first text information of the first data in natural language form, the second text information of the second data in natural language form and the third text information of the third data in natural language form.

[0119] Specifically, the terminal device may perform data conversion on the first data, the second data, and the third data based on natural language processing technology and setting rules, wherein the setting rules may be set according to actual needs and are not limited here.

[0120] For example, the terminal device may convert the fleet size figure into a textual description of the number of vehicles.

[0121] In S403 , target text information corresponding to the fleet data is generated according to the first text information, the second text information, and the third text information.

[0122] In this embodiment, after obtaining the first text information, the second text information and the third text information, in order to achieve a comprehensive overview of the current operating status of the target fleet in natural language form, the terminal device can combine and generate target text information corresponding to the fleet data based on the first text information, the second text information and the third text information.

[0123] For example, assume that the structured data corresponding to the fleet data is shown in Table 1:

[0124] Table 1

[0125] License plate number, vehicle type, driver, operating time: Guangdong A00001, small truck, Zhang San, 3 hours; Guangdong A00002, medium truck, Li Si, 4 hours

[0126] The converted target text information is: Zhang San, the small truck driver with license plate number Yue A00001, has been driving for 3 hours, and Zhang San, the medium truck driver with license plate number Yue A00002, has been driving for 4 hours.

[0127] In S404, the target text information and the prompt keyword are input into the prompt information generation model for processing to obtain the prompt information.

[0128] In this embodiment, the terminal device may input the target text information and the prompt keyword into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword.

[0129] It can be seen from the above that the prompt information generation method provided by this embodiment improves the processing accuracy of the prompt information generation model, thereby further improving the generation accuracy of the prompt information.

[0130] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0131] Corresponding to the prompt information generation method described in the above embodiment, FIG5 shows a schematic diagram of the structure of a prompt information generation device provided by the embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown. Referring to FIG5, the prompt information generation device 500 includes: a first acquisition unit 51 and a first processing unit 52. In particular:

[0132] The first acquisition unit 51 is used to acquire fleet data of a target fleet and prompt keywords of the target fleet; wherein the fleet data includes vehicle information, fleet operation information, and driver behavior information.

[0133] The first processing unit 52 is used to input the vehicle information, the fleet operation information, the behavior information and the prompt keyword into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword; wherein, the prompt information generation model is trained by a pre-built large language model.

[0134] In one embodiment of the present application, the first acquisition unit 51 specifically includes: a second acquisition unit, an information determination unit, and a first generation unit.

[0135] The second acquisition unit is used to acquire the mission information, fleet data and historical fleet management information of the target fleet.

[0136] The information determination unit is used to determine the demand information of the target fleet based on the fleet data and the historical fleet management information.

[0137] The first generating unit is configured to generate the prompt keyword based on the task information and the requirement information.

[0138] In one embodiment of the present application, the prompt information generation model includes a semantic analysis layer and a prompt information generation layer; the first processing unit 52 specifically includes: a second processing unit and a third processing unit.

[0139] The second processing unit is used to input the vehicle information, the fleet operation information and the behavior information into the semantic analysis layer for processing to obtain the current status information of the target fleet.

[0140] The third processing unit is used to input the prompt keyword and the current state information into the prompt information generation layer for processing to obtain the prompt information.

[0141] In one embodiment of the present application, the third processing unit specifically includes: a first factor determination unit and a second generation unit.

[0142] The first element determining unit is configured to determine a plurality of prompt elements corresponding to the prompt information according to the prompt keyword.

[0143] The second generating unit is configured to generate the prompt information based on the plurality of prompt elements and the current state information.

[0144] In one embodiment of the present application, the first factor determination unit specifically includes: a word determination unit, an analysis unit, and a second factor determination unit.

[0145] The word determination unit is used to determine candidate words associated with the prompt keyword.

[0146] The analyzing unit is configured to perform causal analysis on the prompt keyword and the candidate words respectively, to obtain a first analysis result corresponding to the prompt keyword and a second analysis result corresponding to the candidate words.

[0147] The second element determination unit is configured to determine a plurality of the prompt elements according to the first analysis result and the second analysis result.

[0148] In one embodiment of the present application, the vehicle information, the fleet operation information, and the behavior information are all structured data; the prompt information generating device 500 further includes: a pre-processing unit, a conversion unit, and a third generating unit; accordingly, the first processing unit 52 specifically includes: a fourth processing unit.

[0149] The preprocessing unit is used to perform data preprocessing on the vehicle information, the fleet operation information and the behavior information in sequence to obtain first data corresponding to the vehicle information, second data corresponding to the fleet operation information and third data corresponding to the behavior information.

[0150] The conversion unit is used to convert the first data, the second data and the third data in sequence based on natural language processing technology to obtain first text information corresponding to the first data, second text information corresponding to the second data and third text information corresponding to the third data.

[0151] The third generating unit is configured to generate target text information corresponding to the fleet data according to the first text information, the second text information, and the third text information.

[0152] The fourth processing unit is used to input the target text information and the prompt keyword into the prompt information generation model for processing to obtain the prompt information.

[0153] In one embodiment of the present application, the prompt information generating device 500 further includes: a third acquisition unit and a pre-training unit.

[0154] The third acquisition unit is used to acquire historical fleet data and historical fleet management information of the target fleet within a historical time period.

[0155] The pre-training unit is used to pre-train the large language model according to the historical fleet data and the historical fleet management information to obtain the prompt information generation model.

[0156] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0157] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0158] Figure 6 is a schematic diagram of the structure of a terminal device provided in one embodiment of the present application. As shown in Figure 6, the terminal device 6 in this embodiment includes: at least one processor 60 (only one is shown in Figure 6), a memory 61, and a computer program 62 stored in the memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, it implements the steps of any of the above-mentioned prompt information generation method embodiments.

[0159] The terminal device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will appreciate that FIG6 is merely an example of the terminal device 6 and does not limit the terminal device 6. The terminal device 6 may include more or fewer components than shown in the figure, or may combine certain components or different components. For example, the terminal device 6 may also include input and output devices, network access devices, etc.

[0160] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0161] In some embodiments, the memory 61 may be an internal storage unit of the terminal device 6, such as the internal memory of the terminal device 6. In other embodiments, the memory 61 may also be an external storage device of the terminal device 6, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped with the terminal device 6. Furthermore, the memory 61 may include both the internal storage unit of the terminal device 6 and an external storage device. The memory 61 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or is about to be output.

[0162] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0163] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0164] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process steps in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0165] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0166] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for generating prompt information, characterized in that: include: Obtaining fleet data of a target fleet and prompt keywords of the target fleet; wherein the fleet data includes vehicle information, fleet operation information, and driver behavior information; The vehicle information, the fleet operation information, the behavior information and the prompt keyword are input into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword; wherein, the prompt information generation model is trained by a pre-built large language model.

2. The method for generating prompt information according to claim 1, wherein: The prompt keywords are obtained in the following way: Obtaining mission information, fleet data, and historical fleet management information of the target fleet; Determining demand information of the target fleet based on the fleet data and the historical fleet management information; The prompt keywords are generated based on the task information and the requirement information.

3. The prompt information generating method according to claim 1, characterized in that: The prompt information generation model includes a semantic analysis layer and a prompt information generation layer; the vehicle information, the fleet operation information, the behavior information, and the prompt keyword are input into the trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword, including: Inputting the vehicle information, the fleet operation information, and the behavior information into the semantic analysis layer for processing to obtain the current status information of the target fleet; The prompt keyword and the current state information are input into the prompt information generation layer for processing to obtain the prompt information.

4. The method for generating prompt information according to claim 3, wherein: The step of inputting the prompt keyword and the current state information into the prompt information generation layer for processing to obtain the prompt information includes: Determining, based on the prompt keyword, a plurality of prompt elements corresponding to the prompt information; The prompt information is generated based on the plurality of prompt elements and the current state information.

5. The method for generating prompt information according to claim 4, wherein: The step of determining, based on the prompt keyword, a plurality of prompt elements corresponding to the prompt information includes: Determining candidate words associated with the prompt keyword; Performing causal analysis on the prompt keyword and the candidate words respectively to obtain a first analysis result corresponding to the prompt keyword and a second analysis result corresponding to the candidate words; A plurality of the prompt elements are determined based on the first analysis result and the second analysis result.

6. The prompt information generating method according to claim 1, characterized in that: The vehicle information, the fleet operation information, and the behavior information are all structured data; Before inputting the vehicle information, the fleet operation information, the behavior information, and the prompt keyword into the trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword, the method further includes: performing data preprocessing on the vehicle information, the fleet operation information, and the behavior information in sequence to obtain first data corresponding to the vehicle information, second data corresponding to the fleet operation information, and third data corresponding to the behavior information; Converting the first data, the second data, and the third data in sequence based on natural language processing technology to obtain first text information corresponding to the first data, second text information corresponding to the second data, and third text information corresponding to the third data; generating target text information corresponding to the fleet data according to the first text information, the second text information, and the third text information; Accordingly, the vehicle information, the fleet operation information, the behavior information, and the prompt keyword are input into the trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword, including: The target text information and the prompt keyword are input into the prompt information generation model for processing to obtain the prompt information.

7. The method for generating prompt information according to any one of claims 1 to 6, characterized in that: Before inputting the vehicle information, the fleet operation information, the behavior information, and the prompt keyword into the trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword, the method further includes: Obtaining historical fleet data and historical fleet management information of the target fleet within a historical time period; The large language model is pre-trained according to the historical fleet data and the historical fleet management information to obtain the prompt information generation model.

8. A prompt information generating device, characterized in that: include: a first acquiring unit, configured to acquire fleet data of a target fleet and prompt keywords of the target fleet; wherein the fleet data includes vehicle information, fleet operation information, and driver behavior information; The first processing unit is used to input the vehicle information, the fleet operation information, the behavior information and the prompt keyword into a trained prompt information generation model for processing to obtain prompt information corresponding to the prompt keyword; wherein the prompt information generation model is trained by a pre-built large language model.

9. The prompt information generating device according to claim 8, characterized in that: The first acquiring unit specifically includes: A second acquisition unit is used to acquire the task information, fleet data and historical fleet management information of the target fleet; an information determining unit, configured to determine demand information of the target fleet based on the fleet data and the historical fleet management information; The first generating unit is configured to generate the prompt keyword based on the task information and the requirement information.

10. The prompt information generating device according to claim 8, characterized in that: The prompt information generation model includes a semantic analysis layer and a prompt information generation layer; The first processing unit specifically includes: A second processing unit is configured to input the vehicle information, the fleet operation information, and the behavior information into a semantic analysis layer for processing to obtain current status information of the target fleet; The third processing unit is configured to input the prompt keyword and the current state information into the prompt information generation layer for processing to obtain the prompt information.

11. The prompt information generating device according to claim 10, characterized in that: The third processing unit specifically includes: A first element determining unit, configured to determine a plurality of prompt elements corresponding to the prompt information according to the prompt keyword; The second generating unit is configured to generate the prompt information based on the plurality of prompt elements and the current state information.

12. The prompt information generating device according to claim 11, characterized in that: The first factor determination unit specifically includes: a word determination unit, configured to determine candidate words associated with the prompt keyword; an analysis unit, configured to perform causal analysis on the prompt keyword and the candidate words respectively, to obtain a first analysis result corresponding to the prompt keyword and a second analysis result corresponding to the candidate words; The second element determination unit is configured to determine a plurality of the prompt elements according to the first analysis result and the second analysis result.

13. The prompt information generating device according to claim 8, characterized in that: The vehicle information, the fleet operation information, and the behavior information are all structured data; The prompt information generating device further includes: a preprocessing unit, configured to perform data preprocessing on the vehicle information, the fleet operation information, and the behavior information in sequence to obtain first data corresponding to the vehicle information, second data corresponding to the fleet operation information, and third data corresponding to the behavior information; a conversion unit, configured to convert the first data, the second data, and the third data in sequence based on a natural language processing technology to obtain first text information corresponding to the first data, second text information corresponding to the second data, and third text information corresponding to the third data; a third generating unit, configured to generate target text information corresponding to the fleet data according to the first text information, the second text information, and the third text information; Accordingly, the first processing unit specifically includes: The fourth processing unit is configured to input the target text information and the prompt keyword into the prompt information generation model for processing to obtain the prompt information.

14. The prompt information generating device according to any one of claims 8 to 13, characterized in that: The prompt information generating device further includes: a third acquiring unit, configured to acquire historical fleet data and historical fleet management information of the target fleet within a historical time period; A pre-training unit is used to pre-train the large language model based on the historical fleet data and the historical fleet management information to obtain the prompt information generation model.

15. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the prompt information generating method according to any one of claims 1 to 7 are implemented.

16. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the prompt information generating method according to any one of claims 1 to 7 are implemented.

Images