Method, apparatus, device and readable medium for data processing

Abstract

Embodiments of this disclosure provide a method, apparatus, device, and readable medium for data processing. The method includes: acquiring a set of data related to a bidding task; determining a set of candidate data based on the set of data related to the bidding task using a trained large language model, wherein the large language model is trained based on training samples formed by aggregating multiple sets of sample data related to the bidding task; determining at least one set of necessary information associated with the bidding task based on the set of candidate data; and sending the at least one set of necessary information associated with the bidding task to a corresponding terminal device. In this manner, the accuracy and speed of acquiring at least one set of necessary information associated with the bidding task can be improved.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computer technology, and more specifically, to methods, apparatus, devices, and computer-readable storage media for data processing. Background Technology

[0002] With the continuous development of the social economy, various industries are generating a large number of projects and demands. To address these projects and demands, companies can select suitable service providers through bidding. Therefore, people expect to obtain timely and accurate information related to the bidding process (e.g., bidding requirements in a specific field, the types of bidding requirements within that field, and whether the bidding period is currently open). Summary of the Invention

[0003] In a first aspect of this disclosure, a method for data processing is provided. The method includes: acquiring a set of data related to a bidding task; determining a set of candidate data based on the set of data related to the bidding task using a trained large language model, wherein the large language model is trained based on training samples formed by aggregating multiple sets of sample data related to the bidding task; determining at least one set of at least one necessary piece of information associated with the bidding task based on the set of candidate data; and sending the at least one set of at least one necessary piece of information associated with the bidding task to a corresponding terminal device.

[0004] In a second aspect of this disclosure, an apparatus for data processing is provided. The apparatus includes: an acquisition module configured to acquire a set of data related to a bidding task; a first determination module configured to determine a set of candidate data based on the set of data related to the bidding task using a trained large language model, wherein the large language model is trained based on training samples formed by aggregating multiple sets of sample data related to the bidding task; a second determination module configured to determine at least one set of at least one necessary piece of information associated with the bidding task based on the set of candidate data; and a sending module configured to send at least one set of at least one necessary piece of information associated with the bidding task to a corresponding terminal device.

[0005] In a third aspect of this disclosure, an electronic device is provided. The electronic device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method of the first aspect of this disclosure when executed by the at least one processing unit.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program that can be executed by a processor to perform the method according to a first aspect of this disclosure.

[0007] In a fifth aspect of this disclosure, a computer program product is provided, including computer-executable instructions, wherein the computer-executable instructions can be executed by a processor to perform a method according to a first aspect of this disclosure.

[0008] It should be understood that the description in the Summary of the Invention section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of various implementations of this disclosure will become more apparent in the following detailed description, taken in conjunction with the accompanying drawings. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0011] Figure 2 A schematic diagram illustrating a process for generating tender leads according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A flowchart of a data processing procedure according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A block diagram of an apparatus for data processing according to some embodiments of the present disclosure is shown; and

[0014] Figure 5 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. Detailed Implementation

[0015] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0016] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0017] It should be noted that the acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0018] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and user authorization should be obtained.

[0019] For example, in response to receiving a user's active request, a prompt message is sent to the user to clearly inform the user that the requested operation will require the acquisition and use of the user's personal information, thereby enabling the user to choose whether to provide personal information to the software or hardware such as electronic devices, applications, servers or storage media that perform the operation of the technical solution disclosed herein, based on the prompt message.

[0020] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, for example, via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose whether to "agree" or "disagree" to provide personal information to the electronic device.

[0021] As used in this paper, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably.

[0022] A neural network is a machine learning network based on deep learning. A neural network processes input and provides a corresponding output, typically consisting of an input layer, an output layer, and one or more hidden layers between the input and output layers. Neural networks used in deep learning applications often include many hidden layers, thus increasing the network's depth. The layers of a neural network are connected sequentially, so that the output of the previous layer is provided as the input to the next layer. The input layer receives the input to the neural network, while the output layer's output serves as the final output. Each layer of a neural network includes one or more nodes (also called processing nodes or neurons), each node processing the input from the layer above.

[0023] Machine learning typically comprises three phases: training, testing, and application (also known as inference). In the training phase, a given model is trained using a large amount of training data, iteratively updating parameter values ​​until the model can consistently generate inferences that meet the expected goals from the training data. Through training, the model can be considered to have learned the relationship between inputs and outputs (also known as an input-output mapping) from the training data. The parameter values ​​of the trained model are determined. In the testing phase, test inputs are applied to the trained model to test whether it can provide the correct output, thus determining the model's performance. The testing phase can sometimes be integrated into the training phase. In the application or inference phase, the trained model can be used to process actual model inputs based on the trained parameter values ​​to determine the corresponding model output.

[0024] As briefly mentioned above, companies can select suitable service providers through bidding. However, the sources of data related to bidding tasks are diverse, and the amount of data is quite large. Therefore, how to quickly and accurately identify bidding needs in a certain field, the type of bidding needs in that field, and whether it is within the bidding period are urgent problems to be solved.

[0025] In some solutions, data related to the bidding task can be obtained manually. However, manual processing can only obtain a limited amount of data, and under the premise of ensuring the quantity, it often leads to a series of problems such as slow processing speed and decreased accuracy.

[0026] In other solutions, Natural Language Processing (NLP) algorithms can be used to extract relevant information from data related to the bidding task. Algorithms such as FastText and slot pattern recognition are then employed to identify the necessary information associated with the bidding task. However, in such solutions, multiple NLP models are often required to clarify information such as the type of bidding requirement, the issuance date, the deadline, related requirements, contact person, and contact information. Each NLP model requires a large number of labeled samples for training, resulting in a lengthy training process. Even when using trained NLP models to obtain the necessary information related to the bidding task, the accuracy rate remains relatively low.

[0027] To at least partially address the aforementioned problems and other potential issues in traditional solutions, this disclosure provides a data processing scheme. According to various embodiments of this disclosure, a set of data related to a bidding task is first acquired. Further, a set of candidate data is determined based on the set of data related to the bidding task using a trained large language model, where the large language model is trained on training samples formed by aggregating multiple sets of sample data related to the bidding task. Further, based on the set of candidate data, at least one set of at least one necessary piece of information associated with the bidding task is determined. Finally, at least one set of at least one necessary piece of information associated with the bidding task is sent to a corresponding terminal device. In this manner, candidate data is determined in batches from the data related to the bidding task using a trained large language model, thereby obtaining at least one necessary piece of information associated with the bidding task, thus improving the accuracy and speed of obtaining at least one necessary piece of information associated with the bidding task.

[0028] The following description will focus on exemplary embodiments of the present disclosure with reference to the accompanying drawings.

[0029] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. For example... Figure 1 As shown, the example environment 100 may include server 110 and terminal devices 120-1, 120-2, ..., 120-N. For ease of discussion, terminal devices 120-1, 120-2, ..., 120-N may be collectively referred to as terminal device 120 or individually referred to as terminal device 120.

[0030] In example environment 100, a database 130 is deployed on server 110, which stores data related to the bidding project. Server 110 can determine at least one set of necessary information associated with the bidding project based on the data related to the bidding project obtained from database 130, and send at least one set of necessary information associated with the bidding project to the corresponding terminal device 120.

[0031] Server 110 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 110 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0032] Terminal device 120 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof.

[0033] A communication connection can be established between server 110 and terminal device 120. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 110 and terminal device 120 can achieve signaling interaction through the communication connection between them.

[0034] It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0035] Figure 2 A schematic diagram of a process 200 for generating tender leads according to some embodiments of the present disclosure is shown. Process 200 can be implemented in server 110. The following is in conjunction with... Figure 1 A detailed description of process 200 is provided.

[0036] In some embodiments, database 130 stores data related to the bidding task, which may include, but is not limited to, bidding data, visit feedback, user profiles, etc. This disclosure is not intended to limit the type of data related to the bidding task. In some embodiments, server 110 may also acquire data related to the bidding task in real time and store the acquired data in database 130.

[0037] In box 210, server 110 can obtain a set of sample data related to the bidding task from database 130, and perform feature engineering on the obtained sample data to obtain training samples for training a Large Language Model (LLM). In some embodiments, the training samples for training the LLM may include task description information (Instruction), input samples, and output samples.

[0038] In some embodiments, the task description information is content extracted from a set of data related to the bidding task and the format of a set of data related to the bidding task that is input into a large language model, described in natural language.

[0039] It should be understood that feature engineering involves constructing task description information, input samples, and output samples for training large language models. The construction of task description information, input samples, and output samples will be described below.

[0040] Taking logistics as an example, the types of logistics services can include, for example, transportation, express delivery, freight, full truckload (FTL), supply chain, cold chain, and less-than-truckload (LTL). This disclosure is not intended to limit the target business or the types of target businesses.

[0041] For example, the content extracted from a set of data related to a bidding task, described in natural language, can be constructed as follows:

[0042]

[0043]

[0044] In some embodiments, the input sample can be in the format "id":"data related to the bidding task". For example, server 110 can construct the following input sample:

[0045]

[0046]

[0047]

[0048]

[0049]

[0050]

[0051] The content of the output sample can be configured according to actual needs. In some embodiments, the output sample may include a unique identifier, tender type, announcement title related to the tender task, announcement details related to the tender task, attachments related to the tender task, and license information related to the tender task. In some embodiments, the output sample may be in comma-separated value CSV format.

[0052] For example, the following output sample can be constructed:

[0053]

[0054] In box 220, server 110 trains a large language model based on training samples obtained by feature engineering to obtain a multi-target recognition model.

[0055] Before training a large language model, the first step is to select a base for the model, such as chatglm, qwen, or llama, and download the parameters for that base. Then, the algorithm for fine-tuning the large language model needs to be determined. For example, the lora-ga algorithm can be used.

[0056] Optimizing large language models mainly involves two parts: model training optimization and model fine-tuning. Model training optimization involves adjusting parameters such as step size and learning rate. For example, a grid search method can be used to optimize model training. Model fine-tuning involves adjusting parameters such as LoRa.

[0057] In some embodiments, when tuning and training a large language model, the input samples can be divided into multiple groups, each group including one or more data related to bidding. Multiple groups of input samples are then fed into the large language model for tuning and training. For example, a MapReduce Multi Process approach can be used to tune and train the large language model.

[0058] In box 230, server 110 can perform offline evaluation of the trained large language model.

[0059] For example, lead accuracy can be used as an evaluation metric to assess large language models. Specifically, lead accuracy can be calculated using the following formula: Lead Accuracy = Number of Leads Followed Up / Number of Leads Issued.

[0060] In box 240, server 110 identifies data related to the bidding task based on a multi-target recognition model to obtain multi-category recognition information.

[0061] Server 110 can acquire a set of data related to the bidding task and, using a multi-object recognition model (i.e., a trained large language model), determine multi-category recognition information (i.e., a set of candidate data) based on this set of data. For example, a set of candidate data can be shown in Table 1 below:

[0062] Table 1

[0063]

[0064] During the identification process, a set of data related to the bidding task can be directly input into the multi-target identification model, so that the multi-target identification model can simultaneously identify each piece of data related to the bidding task in a set of data related to the bidding task.

[0065] In box 250, server 110 can mine logistics bidding clues based on the multi-category identification information obtained from the identification.

[0066] In some embodiments, server 110 may determine at least one set of necessary information associated with the bidding task based on the identified multi-category identification information. For example, the data associated with the bidding task includes the bidding type and time information related to the bidding task (e.g., deadline, registration time, etc.). Server 110 may filter at least one set of candidate necessary information associated with the bidding task from a set of candidate data based on the bidding type, and filter at least one set of necessary information associated with the bidding project from at least one set of candidate necessary information associated with the bidding task based on the time information.

[0067] For example, at least one necessary piece of information (i.e., a logistics bidding lead) related to the bidding project, obtained by server 110, can be as follows:

[0068]

[0069] In box 260, server 110 distributes logistics bidding leads. In some embodiments, server 110 may send at least one set of necessary information associated with the bidding task to the corresponding terminal device 120.

[0070] Specifically, server 110 can add corresponding tags to at least one set of necessary information associated with the bidding task based on the bidding type, and send at least one set of necessary information associated with the bidding task to the corresponding terminal device 120 based on the corresponding tags.

[0071] For example, at least one set of at least one necessary piece of information (logistics bidding clue) associated with a bidding task, sent to terminal device 120, can be represented as follows:

[0072]

[0073] Based on this, compared with ordinary NLP algorithms, the data processing method provided in this disclosure can increase the lead conversion rate from 12.2% to 15.7%. Online, the difference between sales is eliminated through PSM, and the sales data is split into experimental and control groups. A / B experiments are conducted with a total of 2,000 sales in each group, as shown in Table 2 below. The P value shows that there is no significant difference in lead processing rate between the two groups of sales.

[0074] Table 2

[0075]

[0076] The experimental group used a large model combined with MRMP technology to generate logistics bidding leads, while the control group used a common NLP algorithm for lead generation. The final lead-to-business conversion rate was 12.2% in the experimental group and 15.7% in the control group. The experimental group showed a significant improvement (p=0.0023) of 28.69% compared to the control group, as shown in Table 3 below.

[0077] Table 3

[0078]

[0079] As shown in Table 4 below, in terms of processing speed, the experimental group showed a relative improvement of 128.48% compared to the control group:

[0080] Table 4

[0081]

[0082] In summary, this disclosure can identify candidate data in batches from data related to bidding tasks using a trained large language model, thereby obtaining at least one necessary piece of information associated with the bidding task, and thus improving the accuracy and speed of obtaining at least one necessary piece of information associated with the bidding task.

[0083] Figure 3 A flowchart of a process 300 for data processing according to some embodiments of the present disclosure is shown. For example, process 300 may be performed by... Figure 1 The server 110 in the middle is executing.

[0084] In box 310, server 110 obtains a set of data related to the bidding task.

[0085] In box 320, server 110 uses a trained large language model to determine a set of candidate data based on a set of data related to the bidding task. The large language model is trained based on training samples formed by aggregating multiple sets of sample data related to the bidding task.

[0086] In box 330, server 110 determines at least one set of necessary information associated with the bidding task based on a set of candidate data.

[0087] In box 340, server 110 sends at least one set of necessary information associated with the bidding task to the corresponding terminal device 120.

[0088] In some embodiments, the training samples also include task description information, which is a natural language description of the content extracted from a set of data related to the bidding task and the format of the set of data related to the bidding task input into the large language model.

[0089] In some embodiments, each set of data related to the bidding task input into the large language model has a unique identifier.

[0090] In some embodiments, the training samples also include output samples, which include a unique identifier, tender type, announcement title related to the tender task, announcement details related to the tender task, attachment content related to the tender task, and certificate information related to the tender task.

[0091] In some embodiments, the output samples are in comma-separated value CSV format.

[0092] In some embodiments, the announcement details related to the bidding task include time information, and wherein determining at least one set of at least one necessary information associated with the bidding task includes: selecting at least one set of candidate necessary information associated with the bidding task from a set of candidate data based on the bidding type; and selecting at least one set of at least one necessary information associated with the bidding project from at least one set of candidate necessary information associated with the bidding task based on time information.

[0093] In some embodiments, sending at least one set of necessary information associated with a bidding task to a corresponding terminal device includes: adding corresponding tags to at least one set of necessary information associated with a bidding task based on the bidding type; and sending at least one set of necessary information associated with a bidding task to a corresponding terminal device based on the corresponding tags.

[0094] Figure 4A block diagram of an apparatus 400 for data processing according to some embodiments of the present disclosure is shown. The apparatus 400 may be implemented in a server 110. Various modules / components in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0095] The device 400 includes an acquisition module 410 configured to acquire a set of data related to the bidding task. The device 400 also includes a first determination module 420 configured to determine a set of candidate data based on the set of data related to the bidding task using a trained large language model, wherein the large language model is trained based on training samples formed by aggregating multiple sets of sample data related to the bidding task. The device 400 also includes a second determination module 430 configured to determine at least one set of necessary information associated with the bidding task based on the set of candidate data. The device 400 further includes a sending module 440 configured to send at least one set of necessary information associated with the bidding task to a corresponding terminal device.

[0096] In some embodiments, the training samples also include task description information, which is a natural language description of the content extracted from a set of data related to the bidding task and the format of the set of data related to the bidding task input into the large language model.

[0097] In some embodiments, each set of data related to the bidding task input into the large language model has a unique identifier.

[0098] In some embodiments, the training samples also include output samples, which include a unique identifier, tender type, announcement title related to the tender task, announcement details related to the tender task, attachment content related to the tender task, and certificate information related to the tender task.

[0099] In some embodiments, the output samples are in comma-separated value CSV format.

[0100] In some embodiments, the announcement details related to the bidding task include time information, and the second determining module 430 is further configured to filter at least one set of candidate necessary information associated with the bidding task from a set of candidate data based on the bidding type; and to filter at least one set of necessary information associated with the bidding project from at least one set of candidate necessary information associated with the bidding task based on time information.

[0101] In some embodiments, the sending module 440 is further configured to add corresponding tags to at least one set of necessary information associated with the bidding task based on the bidding type; and to send at least one set of necessary information associated with the bidding task to the corresponding terminal device based on the corresponding tags.

[0102] The units included in device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units may be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 400 may be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0103] Figure 5 A block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 5 The electronic device 500 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown can be used to achieve Figure 1 The first server 110, the second server 120 and / or the client 110.

[0104] like Figure 5 As shown, electronic device 500 is in the form of a general-purpose electronic device. Components of electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. Processing unit 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 500.

[0105] Electronic device 500 typically includes multiple computer storage media. Such media can be any available media accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be a removable or non-removable medium and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data (e.g., training data for training) and can be accessed within electronic device 500.

[0106] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 5 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0107] Communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0108] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0109] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores one or more computer instructions, wherein the one or more computer instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transient computer-readable medium and includes computer-executable instructions that are executed by a processor to implement the methods described above.

[0110] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0111] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0112] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0113] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0114] Various implementations of this disclosure have been described above. The foregoing description is exemplary and not exhaustive, nor is it limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the implementations disclosed herein.

Claims

1. A method for data processing, comprising: Obtain a set of data related to the bidding task; Using a trained large language model, a set of candidate data is determined based on the set of data related to the bidding task. The large language model is trained based on training samples formed by aggregating multiple sets of sample data related to the bidding task. Based on the aforementioned set of candidate data, at least one set of necessary information associated with the bidding task is determined; as well as Send at least one set of necessary information associated with the bidding task to the corresponding terminal device.

2. The method according to claim 1, wherein the training samples further include task description information, the task description information being content extracted from the set of data related to the bidding task and the format of the set of data related to the bidding task input into the large language model, described in natural language.

3. The method according to claim 2, wherein each set of data related to the bidding task input into the large language model has a unique identifier.

4. The method according to claim 3, wherein the training samples further include output samples, the output samples including the unique identifier, the tender type, the announcement title related to the tender task, the announcement details related to the tender task, the attachment content related to the tender task, and the certificate information related to the tender task.

5. The method according to claim 4, wherein the output sample is in comma-separated value CSV format.

6. The method of claim 4, wherein the announcement details related to the bidding task include time information, and wherein determining at least one set of at least one essential piece of information associated with the bidding task includes: Based on the bidding type, at least one set of candidate necessary information related to the bidding task is selected from the set of candidate data; as well as Based on the time information, at least one set of necessary information associated with the bidding project is selected from at least one set of candidate necessary information associated with the bidding task.

7. The method of claim 6, wherein sending the at least one set of necessary information associated with the bidding task to the corresponding terminal device comprises: Based on the tender type, add corresponding tags to at least one set of necessary information associated with the tender task; as well as Based on the corresponding tags, at least one set of necessary information associated with the bidding task is sent to the corresponding terminal device.

8. An apparatus for data processing, comprising: The acquisition module is configured to acquire a set of data related to the bidding task. The first determining module is configured to determine a set of candidate data based on the set of data related to the bidding task using a trained large language model, wherein the large language model is trained based on training samples formed by aggregating multiple sets of sample data related to the bidding task. The second determining module is configured to determine at least one set of necessary information associated with the bidding task based on the set of candidate data. as well as The sending module is configured to send at least one set of necessary information associated with the bidding task to the corresponding terminal device.

9. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 7 when executed by the at least one processing unit.

10. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 7.

11. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 7.

Images