Data product intelligent recommendation method, system, equipment and medium

Abstract

The invention relates to a data product intelligent recommendation method, system and device and a medium, and relates to the technical field of artificial intelligence and big data. The method comprises the following steps: acquiring a structured feature vector; constructing a dynamic preference model, inputting the structured feature vector, and outputting a preference score; a filtering recommendation model deployed based on a distributed architecture is constructed, and a recommendation module takes the preference score, the current training task index parameter and the recommended data product set as a state space, performs calculation through a reward function and outputs a first recommendation score; the collaborative filtering module performs collaborative filtering calculation according to the preference score and outputs a second recommendation score; performing weighted fusion on the first recommendation score and the second recommendation score to generate a data product recommendation list; and dynamically updating related parameters of the dynamic preference model and the filtering recommendation model according to feedback information of a decision maker to the data product recommendation list. The method can accurately capture the dynamic preference of the decision maker, and has efficient parallel processing capability.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence and big data technology, and in particular to a method, system, device and medium for intelligent recommendation of data products. Background Technology

[0002] In emergency training management, decision-makers need to process massive amounts of training data, resource information, and task indicators to formulate scientific and reasonable training plans and decisions. However, existing information systems in the field of training management still have many problems that urgently need to be solved in terms of data product recommendation.

[0003] Current data product recommendations generally lack specificity, relying heavily on static rules or simple collaborative filtering algorithms. This makes it difficult to accurately match the personalized needs of different decision-makers in diverse emergency training scenarios, and also hinders real-time adaptation to dynamic changes in training tasks and adjustments to decision-makers' preferences. Furthermore, existing recommendation technologies fail to effectively integrate professional knowledge graphs within the emergency training domain, resulting in recommendations that often deviate from the professional logic of emergency training, leading to a large number of invalid recommendations and increasing the cost for decision-makers to select effective data products. In addition, facing the demands of multi-user, multi-scenario parallel processing in large-scale emergency training management scenarios, existing systems lack efficient parallel recommendation service architectures, struggling to handle concurrent recommendation requests, resulting in low recommendation efficiency and failing to meet the high timeliness requirements of emergency training management. These problems prevent the full utilization of data resources in emergency training management, limiting decision-making efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a data product intelligent recommendation method, system, device, and medium that can accurately capture decision-makers' dynamic preferences, deeply integrate domain knowledge, and have efficient parallel processing capabilities to address the above-mentioned technical problems.

[0005] A method for intelligent recommendation of data products, the method comprising: Acquire behavioral data, personalized tags, emergency domain knowledge graph, and current training task indicator parameters of decision-makers in emergency training management scenarios, and preprocess them to obtain structured feature vectors; A dynamic preference model is constructed, and the structured feature vector is input into the dynamic preference model for processing, and preference scores for various data products are output. Construct a filtering recommendation model based on a distributed architecture deployment, the filtering recommendation model including a recommendation module and a collaborative filtering module; The recommendation module uses the preference score, the current training task indicator parameters, and the set of recommended data products as the state space, and calculates the first recommendation score using a reward function that includes behavioral feedback and task matching degree. The collaborative filtering module performs collaborative filtering calculations based on the preference scores of the data products and outputs a second recommendation score. The first recommendation score and the second recommendation score are weighted and fused to output a fused recommendation score; a data product recommendation list is generated based on the fused recommendation score. Based on the decision-makers' feedback on the data product recommendation list, the relevant parameters of the dynamic preference model and the filtering recommendation model are dynamically updated, and parallel recommendation services are provided based on a distributed architecture.

[0006] On the other hand, a data product intelligent recommendation system is also provided, including: The data preprocessing module is used to acquire and preprocess decision-makers' behavioral data, personalized tags, emergency domain knowledge graphs, and current training task indicator parameters in emergency training management scenarios to obtain structured feature vectors. The preference score calculation module is used to construct a dynamic preference model, input the structured feature vector into the dynamic preference model for processing, and output the preference scores of various data products. A filtering recommendation model building module is used to build a filtering recommendation model based on a distributed architecture. The filtering recommendation model includes a recommendation module and a collaborative filtering module. The first recommendation score calculation module is used in the recommendation module to calculate and output the first recommendation score using the preference score, the current training task indicator parameters, and the set of recommended data products as the state space, through a reward function that includes behavioral feedback and task matching degree. The second recommendation score calculation module is used in the collaborative filtering module to perform collaborative filtering calculation based on the preference score of the data product and output the second recommendation score. The data product recommendation list generation module is used to perform weighted fusion of the first recommendation score and the second recommendation score, and output a fused recommendation score; and generate a data product recommendation list based on the fused recommendation score. The feedback update module is used to dynamically update the relevant parameters of the dynamic preference model and the filtering recommendation model based on the decision-maker's feedback information on the data product recommendation list, and to provide parallel recommendation services based on a distributed architecture.

[0007] In another aspect, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-mentioned intelligent recommendation method for data products.

[0008] Furthermore, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the aforementioned intelligent recommendation method for data products.

[0009] Compared with existing technologies, the intelligent recommendation method, system, device, and medium for data products provided by this invention have the following beneficial effects: 1. By integrating knowledge graphs in the emergency response field, decision-maker behavior data, and training task indicators to construct a dynamic preference model, and combining the dual computational logic of reinforcement learning and collaborative filtering, the recommendation results not only match the personalized preferences of decision-makers but also meet the needs of professional emergency training scenarios, significantly reducing the proportion of invalid recommendations, accurately capturing the dynamic preferences of decision-makers, and significantly improving the accuracy of recommendations.

[0010] 2. Based on the decision-maker's feedback on the recommendation list, the relevant parameters of the dynamic preference model and the filtering recommendation model are updated in real time, which can quickly respond to changes in training tasks and adjustments in decision-makers' preferences, and has stronger dynamic adaptability.

[0011] 3. Through automated data preprocessing, preference modeling, and precise recommendations, it replaces decision-makers in completing tedious data screening and solution comparison processes, reducing the time cost of finding effective data products and significantly improving decision-making efficiency.

[0012] 4. Based on a distributed architecture, the filtering recommendation model is deployed to support parallel recommendation services for multiple users and multiple scenarios. It can efficiently handle concurrent recommendation requests in large-scale emergency training management and meet the needs of simultaneous advancement of training tasks in multiple locations and of multiple types.

[0013] 5. By accurately matching preferences and integrating professional logic, we can break down the silos of scattered data resources, avoid resource waste caused by data product mismatch, improve the utilization rate of emergency training-related data resources, and reduce management costs. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention, and those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart illustrating an intelligent recommendation method for data products in one embodiment; Figure 2 This is a structural block diagram of a data product intelligent recommendation system in one embodiment; Figure 3 This is an internal structural diagram of a computer device in one embodiment.

[0016] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] It should be noted that in this invention, the use of terms such as "first," "second," etc., is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0019] It is understood that the technical solutions of the various embodiments of the present invention can be combined with each other, but only if they are based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0020] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0021] Example 1 like Figure 1 As shown, the intelligent recommendation method for data products provided in this embodiment includes the following steps: Step 201: Obtain the behavioral data, personalized tags, emergency domain knowledge graph, and current training task indicator parameters of decision-makers in the emergency training management scenario, and perform preprocessing to obtain a structured feature vector.

[0022] Step 202: Construct a dynamic preference model. Input the structured feature vector into the dynamic preference model for processing and output the preference scores of various data products.

[0023] Step 203: Construct a filtering recommendation model based on a distributed architecture. The filtering recommendation model includes a recommendation module and a collaborative filtering module.

[0024] Step 204: The recommendation module uses the preference score, the current training task indicator parameters, and the set of recommended data products as the state space, and calculates the first recommendation score using a reward function that includes behavioral feedback and task matching degree.

[0025] Step 205: The collaborative filtering module performs collaborative filtering calculations based on the preference scores of the data products and outputs the second recommendation score.

[0026] Step 206: Perform a weighted fusion of the first recommendation score and the second recommendation score to output the fused recommendation score; generate a data product recommendation list based on the fused recommendation score.

[0027] Step 207: Based on the decision-makers' feedback on the data product recommendation list, dynamically update the relevant parameters of the dynamic preference model and the filtering recommendation model, and provide parallel recommendation services based on a distributed architecture.

[0028] In the specific implementation of step 201, multi-dimensional data of decision-makers in the emergency training management process are collected, including behavioral data and static data.

[0029] Behavioral data includes operation logs, historical data retrieval records, and command issuance preferences. The operation logs contain the type, time, and object of each operation. The historical data retrieval records contain the data type, time, and frequency of each retrieval. The command issuance preferences contain the style, frequency, and object of various commands.

[0030] Static data includes personalized tags, an emergency response domain knowledge graph, and current training task metrics. Personalized tags are labels actively input by decision-makers; the emergency response domain knowledge graph... , For entities in the emergency response field, This refers to the relationships between entities; the current training task metrics include training type, scale, objective, and environmental parameters.

[0031] During preprocessing, unstructured data (such as log text) is converted into structured feature vectors using log template extraction and TF-IDF methods. For example, feature extraction is performed on operation logs to obtain behavioral feature vectors. The personalized tags are encoded to obtain the tag feature vector. Knowledge graph feature vectors are extracted from emergency domain knowledge graphs using graph embedding algorithms. The task feature vector is obtained by performing feature processing on the current training task index parameters. .

[0032] This step, through multi-dimensional data collection and structured processing, provides comprehensive and standardized input data for subsequent model building, breaking the limitations of a single data type and ensuring that the data accurately reflects the needs of decision-makers and the characteristics of the scenario.

[0033] In the specific implementation of step 202, the structured feature vector includes behavioral feature vectors, label feature vectors, knowledge graph feature vectors, and task feature vectors. These four types of vectors are fused to obtain a fused feature vector. The calculation expression for the fused feature vector is as follows: ; In the formula, Represents the fused feature vector; Represents a behavioral feature vector; Represents the label feature vector; Represents the feature vector of a knowledge graph; Represents the task feature vector; , , , This indicates the fusion weight.

[0034] Dynamic preference model Implemented using deep neural networks, such as Attention-LSTM, the feature vectors are fused. Input the dynamic preference model, and map the relationship between the models. Output decision-makers' preference score vectors for various data products Preference score vector Each element corresponds to a quantitative value representing the degree of preference for a particular data product.

[0035] This step, through multi-feature fusion and deep neural network modeling, can accurately capture the decision-maker's personalized preferences, while incorporating emergency domain knowledge and task requirements, making the preference scores more aligned with the professional logic of emergency training and management scenarios.

[0036] In the specific implementation of step 203, the distributed architecture can be implemented using the MapReduce framework. This architecture splits the recommendation task of multiple users into independent subtasks, which are then distributed to different computing nodes for parallel execution, providing a foundation for subsequent parallel recommendations of multiple users and multiple scenarios.

[0037] The filtering recommendation model consists of two main modules. The recommendation module focuses on calculating the fit between the dynamic preferences of individual decision-makers and the current task, while the collaborative filtering module supplements the recommendation basis by leveraging the common preferences of group decision-makers. The combination of the two forms a dual recommendation logic of personalization and group, which ensures the relevance of the recommendation and improves the reliability of the recommendation results.

[0038] In the specific implementation of step 204, the recommendation module employs a reinforcement learning algorithm to model the recommendation process as a Markov decision process (MDP). Its state space... ,in, The preference score vector output in step 202 This is the current task feature vector. This is a collection of recommended data products.

[0039] Action space This refers to the collection of all available data products in an emergency training management scenario (such as training progress visualization dashboards, risk warning analysis reports, etc.); the reward function expression is: ; In the formula, Represents the reward function; Representing the state space; Indicates data products; Indicates the weight of the reward function; This indicates policymakers' attitude towards data products. Behavioral feedback includes usage duration, click frequency, and quantitative scores corresponding to accepting or rejecting instructions; Indicates data products With task feature vector The degree of matching.

[0040] Reinforcement learning agents use reinforcement strategies The goal of selecting data products is to maximize cumulative rewards and ultimately output the top referral score. Score based on first recommendation It quantifies the degree to which data products are adapted to decision-makers' dynamic preferences and current tasks.

[0041] The expression for maximizing the cumulative reward is: ; In the formula, Indicates reinforcement strategy Corresponding cumulative expected reward; This represents the mathematical expectation operation; Indicates a time step; Indicates the discount factor; Indicates at time step Below, in a state Choose action The instant rewards received; Indicates time step The corresponding state space; Indicates time step The chosen data product.

[0042] In the specific implementation of step 205, the collaborative filtering module first calculates the similarity value based on the current decision-maker's preference score for the data product and the preference scores of other decision-makers for the data product. The expression is: ; In the formula, Indicates the similarity value; Indicates the current decision-maker; Indicates other decision-makers; This represents the current decision-maker's preference score vector for data products; This represents the preference score vector of other decision-makers for data products; This indicates the current decision-maker's preference score for data products; This indicates other decision-makers' preference scores for data products.

[0043] Then, based on the similarity value, the second recommendation score for the current decision-maker is calculated, expressed as: ; In the formula, This indicates the second recommended score; Indicates and Similar sets of decision-makers; Indicates other decision-makers For data products The rating.

[0044] In the specific implementation of steps 203 to 205, the design of the two main modules of the filtering recommendation model achieves the integration of reinforcement learning and collaborative filtering algorithms. This allows reinforcement learning to capture the dynamic preferences and task suitability of decision-makers, while collaborative filtering draws on the choices of other decision-makers, making the recommendation logic more comprehensive and effectively improving the accuracy and reliability of the recommendation results. Simultaneously, the deployment of the distributed architecture lays the foundation for subsequent parallel recommendation services, solving the recommendation efficiency problem in large-scale scenarios.

[0045] In the specific implementation of step 206, the first recommendation score and the second recommendation score are weighted and fused, and the calculation expression is as follows: ; In the formula, Indicates the fusion recommendation score; This represents the score fusion coefficient, used to balance the dynamic adaptability of reinforcement learning with the group reference value of collaborative filtering.

[0046] Then, based on the fusion recommendation score Sort all available data products in descending order and select the top ones. Data products ( Generate a list of recommended data products (based on a preset recommendation threshold) and recommend it to the current decision-maker.

[0047] This step integrates the recommendation advantages of the two modules through a reasonable weighted fusion strategy, so that the recommendation results not only meet the individual needs of decision-makers, but also have the acceptance of the group. At the same time, the quality of the recommendation list is ensured through sorting and filtering.

[0048] In the specific implementation of step 207, the feedback information includes the decision-maker's acceptance or rejection instructions for the recommendation results, the duration of data product usage, and human ratings. These feedback information are converted into the basis for parameter adjustment through preset quantitative rules.

[0049] The relevant parameters for dynamic updates include: the fusion weights of the dynamic preference model. , , , Reward function weights in reinforcement learning The score fusion coefficient of the filter recommendation model After the parameters are updated, independent computing resources are allocated to multiple users based on a distributed architecture. Each computing node independently completes the data preprocessing, model inference, and data product recommendation list generation process. The consistency of model parameter updates is ensured through a distributed synchronization mechanism, supporting parallel recommendation requests from multiple users and multiple scenarios per second, meeting the needs of large-scale training management scenarios.

[0050] This step achieves model self-optimization through feedback-driven parameter updates, enabling the recommendation system to adapt to the dynamic changes in decision-makers' preferences and training tasks in real time. At the same time, it leverages the parallel processing capabilities of the distributed architecture to meet the concurrent recommendation needs of large-scale emergency training management scenarios.

[0051] In one embodiment, taking a fire rescue training management scenario as an example, the implementation process of the present invention is described in detail: First, data collection and preprocessing are performed. This includes collecting the fire commander's (decision-making) operation logs (e.g., viewing training videos, adjusting training parameters), historical retrieval records (e.g., simulation training data from the past 3 months), and command issuance preferences (e.g., preference for detailed or summary commands); the commander inputs personalized tags: {"Rescue," "Command Decision," "Resource Allocation"}; loading a fire rescue domain knowledge graph (containing entities and relationships such as rescue types, rescue equipment, and tactical methods); obtaining current training task indicators: {"Training Type = High-Rise Building Rescue," "Number of Trainees = 50," "Training Objective = Improve Initial Control Capability"}; and preprocessing the above data to generate behavioral feature vectors. Label feature vector Knowledge feature vector Task feature vector .

[0052] Then construct a dynamic preference model. According to the formula... Calculate the fused feature vector (weights set empirically), and train a dynamic preference model using a deep neural network. Output the commander's preference score vector for various data products. .

[0053] In the process of calculating the filtering recommendation model, the recommendation module uses... Current task feature vector and the recommended data product set as the state space According to the state space Choose data products Such as the "High-Rise Building Rescue Resource Allocation Prediction Model"; based on the commander's usage time. Task matching degree Calculate reward value This will be used as the first recommended score output.

[0054] The collaborative filtering module calculates the similarity between the commander and other rescue commanders, discovers that similar users frequently use the "Risk Warning Analysis Report," and generates a collaborative filtering score. ; Calculate the fusion recommendation score according to the fusion formula: .

[0055] Then, recommendation and feedback optimization are performed. A list of recommended data products is generated based on the fusion recommendation scores and pushed to the commander. If the commander accepts and frequently uses the recommended products, the relevant parameters of the dynamic preference model and the filtering recommendation model are dynamically updated to increase the weight of relevant features.

[0056] Finally, a distributed architecture is used to provide recommendation services in parallel for multiple commanders in this fire and rescue scenario.

[0057] It should be understood that, although this embodiment Figure 1 The steps are shown sequentially as indicated by the arrows, but they are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order in which these steps are performed; they can be executed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0058] Example 2 Based on the intelligent recommendation method for data products in Embodiment 1, this embodiment discloses an intelligent recommendation system for data products, such as... Figure 2 As shown, the intelligent recommendation system for data products includes: a data preprocessing module 401, a preference score calculation module 402, a filtering recommendation model construction module 403, a first recommendation score calculation module 404, a second recommendation score calculation module 405, a data product recommendation list generation module 406, and a feedback update module 407, wherein: The data preprocessing module 401 is used to acquire and preprocess the decision-maker's behavioral data, personalized tags, emergency domain knowledge graph and current training task indicator parameters in the emergency training management scenario to obtain structured feature vectors.

[0059] The preference score calculation module 402 is used to construct a dynamic preference model. It inputs the structured feature vector into the dynamic preference model for processing and outputs the preference scores of various data products.

[0060] The filtering recommendation model building module 403 is used to build a filtering recommendation model based on a distributed architecture. The filtering recommendation model includes a recommendation module and a collaborative filtering module.

[0061] The first recommendation score calculation module 404 is used in the recommendation module to calculate and output the first recommendation score using the preference score, the current training task indicator parameters, and the set of recommended data products as the state space, through a reward function that includes behavioral feedback and task matching degree.

[0062] The second recommendation score calculation module 405 is used in the collaborative filtering module to perform collaborative filtering calculations based on the preference scores of the data products and output the second recommendation score.

[0063] The data product recommendation list generation module 406 is used to perform weighted fusion of the first recommendation score and the second recommendation score, and output the fused recommendation score; and generate a data product recommendation list based on the fused recommendation score.

[0064] The feedback update module 407 is used to dynamically update the relevant parameters of the dynamic preference model and the filtering recommendation model based on the decision-maker's feedback on the data product recommendation list, and to provide parallel recommendation services based on a distributed architecture.

[0065] In this embodiment, the specific working process and working principle of the data preprocessing module 401, preference score calculation module 402, filtering recommendation model construction module 403, first recommendation score calculation module 404, second recommendation score calculation module 405, data product recommendation list generation module 406, and feedback update module 407 are the same as those in Embodiment 1, and therefore will not be described again in this embodiment. Each unit module can be implemented entirely or partially through software, hardware, or a combination thereof. Each unit module can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above unit modules.

[0066] Example 3 like Figure 3 The diagram illustrates a computer device disclosed in this embodiment, including a transmitter, a receiver, a memory, and a processor. The transmitter is used to send instructions and data, the receiver is used to receive instructions and data, the memory is used to store computer execution instructions, and the processor is used to execute the computer execution instructions stored in the memory to implement the method in Embodiment 1 above.

[0067] It is important to note that the aforementioned memory can be either standalone or integrated with the processor. When the memory is set up independently, the computer device also includes a bus for connecting the memory and the processor.

[0068] Example 4 This embodiment discloses a computer-readable storage medium storing computer-executable instructions. When a processor executes the computer-executable instructions, it implements the method in Embodiment 1 above.

[0069] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0070] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0071] The embodiments described above are merely examples of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention.

Claims

1. A method for intelligent recommendation of data products, characterized in that, The method comprises: acquiring behavior data of a decision maker in an emergency training management scenario, personalized labels, an emergency domain knowledge graph, and current training task index parameters, and preprocessing to obtain a structured feature vector; constructing a dynamic preference model, inputting the structured feature vector into the dynamic preference model for processing, and outputting preference scores of various data products; constructing a filtering recommendation model deployed based on a distributed architecture, the filtering recommendation model comprising a recommendation module and a collaborative filtering module; the recommendation module taking the preference scores, the current training task index parameters, and a set of recommended data products as a state space, calculating through a reward function comprising behavior feedback and task matching degree, and outputting a first recommendation score; the collaborative filtering module performing collaborative filtering calculation according to the preference scores of data products, and outputting a second recommendation score; weighting and fusing the first recommendation score and the second recommendation score to output a fused recommendation score, and generating a data product recommendation list according to the fused recommendation score; dynamically updating related parameters of the dynamic preference model and the filtering recommendation model based on feedback information of the decision maker on the data product recommendation list, and performing parallel recommendation services based on the distributed architecture.

2. The method of claim 1, wherein, The structured feature vector comprises a behavior feature vector, a label feature vector, a knowledge graph feature vector, and a task feature vector; performing fusion processing on the behavior feature vector, the label feature vector, the knowledge graph feature vector, and the task feature vector to obtain a fused feature vector; inputting the fused feature vector into the dynamic preference model for processing to output preference scores of various data products by the decision maker.

3. The method of claim 2, wherein, The calculation expression of the fused feature vector is: ； In the formula, denotes a fusion feature vector; denotes a behavior feature vector; denotes a label feature vector; denotes a knowledge graph feature vector; denotes a task feature vector; , , , denotes a fusion weight.

4. The method of claim 1, wherein, In the recommendation module, the reward function expression is: ； wherein, represents a reward function; represents a state space; represents a data product; represents a reward function weight; represents a decision maker's behavioral feedback on a data product ; represents a matching degree of a data product to a task feature vector .

5. The method of claim 4, wherein, The collaborative filtering module performs collaborative filtering calculation according to the preference scores of data products, and outputs a second recommendation score, comprising: In the collaborative filtering module, a similarity value is calculated according to the preference score of the current decision maker on the data product and the preference scores of other decision makers on the data product; the second recommendation score of the current decision maker is calculated based on the similarity value.

6. The method of claim 5, wherein, The similarity value is calculated according to the preference score of the current decision maker on the data product and the preference scores of other decision makers on the data product, and the expression is: ； wherein, represents a similarity value; represents a current decision maker; represents other decision makers; represents a preference score vector of the current decision maker for the data product; represents a preference score vector of the other decision makers for the data product; represents a preference score of the current decision maker for the data product; represents a preference score of the other decision makers for the data product.

7. The method of claim 6, wherein, The second recommendation score of the current decision maker is calculated based on the similarity value, and the expression is: ； wherein, represents a second recommendation score; represents a set of decision makers similar to represents other decision makers scored the data product.​​ 8. A data product intelligent recommendation system, characterized in that, The system comprises: a data preprocessing module configured to acquire behavior data of a decision maker in an emergency training management scenario, personalized labels, an emergency domain knowledge graph, and current training task index parameters, and preprocess to obtain a structured feature vector; a preference score calculation module configured to construct a dynamic preference model, input the structured feature vector into the dynamic preference model for processing, and output preference scores of various data products; a filtering recommendation model construction module configured to construct a filtering recommendation model deployed based on a distributed architecture, the filtering recommendation model comprising a recommendation module and a collaborative filtering module; The first recommendation score calculation module is configured to, in the recommendation module, take the preference score, the current training task index parameter and the recommended data product set as a state space, and calculate a first recommendation score by using a reward function containing behavior feedback and task matching degree. The second recommendation score calculation module is configured to, in the collaborative filtering module, perform collaborative filtering calculation according to the preference score of the data product, and output a second recommendation score. The data product recommendation list generation module is configured to perform weighted fusion on the first recommendation score and the second recommendation score, output a fused recommendation score, and generate a data product recommendation list according to the fused recommendation score. The feedback update module is configured to dynamically update related parameters of the dynamic preference model and the filtering recommendation model according to feedback information of the decision maker on the data product recommendation list, and perform parallel recommendation services based on a distributed architecture. 9.A computer device, comprising a memory and a processor, and characterized in that, The memory stores a computer program, and the processor implements the steps of the data product intelligent recommendation method in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer program is stored on the memory and is executed by the processor to implement the steps of the data product intelligent recommendation method in any one of claims 1 to 7.

Images