A production portal information recommendation method and system based on large model drive

Abstract

The present invention provides a large-model-driven production portal information recommendation method and system, relating to the field of data processing technology. The method comprises: obtaining a user's current consultation data; performing word segmentation processing on the current consultation data; constructing a word embedding vector sequence; analyzing the user's current consultation intention using a large-model based on multi-layer stacked gated recurrent units; determining, based on the current consultation intention, multiple production portal information matching the current consultation data using a multi-layer perceptron; obtaining a consultation intention summary formed by the user during historical consultations, the consultation intention summary including multiple typical consultation intentions of the user during historical consultations; updating the user's consultation intention summary based on the similarity between the current consultation intention and each typical consultation intention in the consultation intention summary; sorting multiple successfully matched production portal information based on the updated consultation intention summary; and recommending the sorted multiple production portal information to the user.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a production portal information recommendation method and system based on large model driving. Background Art

[0002] In today's digital age, users are faced with a vast amount of information, and manually filtering out valuable information has become extremely difficult. Currently, users can simply type in keywords or input voice data to clarify their needs. The recommendation system automatically filters and provides the most relevant information based on the user's needs, helping users save time and effort.

[0003] Current recommendation systems primarily use keyword matching to make recommendations. However, the same keyword can have different meanings in different contexts, and there are many pieces of content with similar meanings but different expressions. Keyword-based recommendations ignore contextual relevance, which can lead to recommendations that differ significantly from customer needs. This leads to overly simplistic recommendations, low personalization, and a failure to meet diverse user needs. Summary of the Invention

[0004] In order to solve the technical problems that the existing technology performs recommendations based on keyword matching, ignores contextual relevance, easily leads to a large difference between recommended content and customer needs, and the recommended content is too single and has a low degree of personalization, which cannot meet the diverse needs of users, the present invention provides a production portal information recommendation method and system based on a large model drive.

[0005] The technical solutions provided by the embodiments of the present invention are as follows:

[0006] First aspect

[0007] An embodiment of the present invention provides a production portal information recommendation method based on a large model drive, comprising:

[0008] S1: Get the user's current consultation data;

[0009] S2: performing word segmentation processing on the current consultation data;

[0010] S3: Construct word embedding vectors for each word segment and form a word embedding vector sequence;

[0011] S4: Analyze the user's current consultation intention based on the word embedding vector sequence through a large model based on multi-layer stacked gated recurrent units;

[0012] S5: Determine, based on the current consultation intention, multiple pieces of production portal information matching the current consultation data using a multi-layer perceptron;

[0013] S6: Obtain a consultation intention summary formed by the user in the historical consultation process, wherein the consultation intention summary includes multiple typical consultation intentions of the user in the historical consultation process;

[0014] S7: updating the user's consultation intention summary according to the similarity between the current consultation intention and each typical consultation intention in the consultation intention summary;

[0015] S8: sorting the multiple successfully matched production portal information according to the updated consultation intent summary;

[0016] S9: Recommending multiple sorted production portal information to the user.

[0017] Second aspect

[0018] An embodiment of the present invention provides a large-model driven production portal information recommendation system, comprising:

[0019] processor;

[0020] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for recommending production portal information based on large model driving as described in the first aspect is implemented.

[0021] The third aspect

[0022] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for recommending production portal information based on large model driving as described in the first aspect is implemented.

[0023] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0024] In the present invention, a large model based on multi-layer stacked gated recurrent units is used to effectively capture the user's contextual information and analyze the user's deep consulting intention. At the same time, by continuously updating the user's consulting intention summary, the user's interest changes are dynamically captured. A multi-layer perceptron is used to perform multi-level feature extraction and matching processing on the current consulting intention, which helps to find the production portal information that best meets the user's needs, improve the accuracy and quality of the recommended content, and make the recommendation results more in line with the user's long-term preferences and have a higher degree of personalization. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A flowchart of a method for recommending production portal information based on a large model drive provided by an embodiment of the present invention;

[0027] Figure 2 A schematic diagram of the structure of a production portal information recommendation method based on a large model drive provided by an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of the structure of a production portal information recommendation system driven by a large model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0030] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0031] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0032] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0033] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0034] Reference Manual Figure 1 , which shows a flow chart of a production portal information recommendation method based on a large model drive provided by an embodiment of the present invention.

[0035] Reference Manual Figure 2 , which shows a structural diagram of a production portal information recommendation method based on a large model drive provided by an embodiment of the present invention.

[0036] An embodiment of the present invention provides a method for recommending production portal information based on a large model. This method can be implemented by a device for recommending production portal information based on a large model, which can be a terminal or a server. The process flow of the method for recommending production portal information based on a large model can include the following steps:

[0037] S1: Get the user's current consultation data.

[0038] Alternatively, the consultation data may be text data typed by the user or voice data used for input.

[0039] Furthermore, voice data can be converted into text data through a voice recognition algorithm.

[0040] S2: Perform word segmentation on the current consultation data.

[0041] In a possible implementation, S2 specifically includes: performing word segmentation processing on the current consultation data through regular expressions, maximum matching method, bidirectional maximum matching method, hidden Markov model and / or conditional random field.

[0042] Regular expressions are a tool for matching strings. By defining character patterns, you can find and process specific text fragments. They can be used to identify word boundaries, punctuation marks, numbers, etc., and then perform word segmentation.

[0043] The maximum match method is a dictionary-based word segmentation method, also known as the forward maximum match method. It starts at the beginning of the text and tries to match the longest word possible. At each step, it starts from the current position and attempts to match the longest possible word until no further matches are found.

[0044] The bidirectional maximum matching method combines the forward maximum matching method and the reverse maximum matching method (matching from right to left), improving the accuracy of word segmentation by executing both methods simultaneously and comparing the results. If the word segmentation results obtained by the two methods differ, the result with fewer segmented words is usually selected, or a decision is made based on other strategies.

[0045] The Hidden Markov Model (HMM) is a probabilistic model that generates observation sequences (words) from state sequences (usually parts of speech) and uses statistical learning to address word segmentation. During word segmentation, each word is treated as an observation state, and the optimal segmentation result is determined by maximizing the overall probability.

[0046] Conditional Random Field (CRF) is an undirected graph model commonly used in sequence labeling tasks, such as word segmentation. CRF learns the interdependencies between features and predicts the label of each character (such as the beginning, middle, or end of a word) given the context, thereby achieving word segmentation.

[0047] It's important to note that each of the above word segmentation methods has its own advantages and disadvantages. In practice, the appropriate method is often selected based on specific needs and scenarios. Regular expressions and maximum matching methods are suitable for simple scenarios, while hidden Markov models and conditional random fields are suitable for complex scenarios requiring high-precision word segmentation. Bidirectional maximum matching methods offer a certain compromise in both simple and complex scenarios.

[0048] S3: Construct word embedding vectors for each word segment and form a word embedding vector sequence.

[0049] In a possible implementation, S3 specifically includes: constructing word embedding vectors for each word segment through Word2Vec, GloVe, and / or FastText, and forming a word embedding vector sequence.

[0050] Among them, Word2Vec is a word embedding technology based on neural networks. The core idea is to predict target words through context words (Skip-gram) or predict context words through target words (CBOW, Continuous Bag of Words), thereby learning the vector representation of words.

[0051] GloVe is a global word embedding method. Unlike Word2Vec's local context prediction, GloVe generates word embeddings through factorization based on a global co-occurrence matrix. GloVe utilizes global statistical information to better capture the co-occurrence relationship between words.

[0052] Among them, FastText is different from Word2Vec and GloVe. FastText decomposes words into character n-grams, thereby capturing the morphological information within the words, enabling FastText to generate more fine-grained word embeddings and handle unregistered words.

[0053] In practical applications, you can choose appropriate word embedding technology according to specific needs, or combine these methods to achieve the best effect.

[0054] S4: Based on the word embedding vector sequence, a large model based on multi-layer stacked gated recurrent units is used to analyze the user's current consultation intention.

[0055] The Gated Recurrent Unit (GRU) is an improved recurrent neural network (RNN) architecture designed to address the vanishing and exploding gradient problems that occur in standard RNNs when processing long sequences of data. The basic unit of a GRU consists of two gates: a reset gate and an update gate, which control how information flows at each time step. By simplifying the gating mechanism, the GRU retains its ability to remember long-term dependencies while reducing computational complexity.

[0056] Optionally, the multi-layer stacked gated recurrent unit includes a stacked multi-layer gated recurrent unit. The input layer of the first layer of gated recurrent units is used to obtain a weighted word embedding vector sequence, the candidate layer of the previous layer of gated recurrent units is connected to the input layer of the next layer of gated recurrent units, the output layers of each layer of gated recurrent units are connected to a fully connected layer, and the fully connected layer is used to fuse the hidden states in the candidate layers of the gated recurrent units in each layer to obtain a comprehensive hidden state representing the consultation intention.

[0057] It's important to note that by stacking multiple layers of GRU units, each layer can further abstract and process data based on the features extracted by the previous layer, thereby capturing more complex temporal dependencies and semantic information. The first layer may focus on local, short-term dependencies, while subsequent layers can capture dependencies over longer time spans and higher-level semantic features. By fusing the hidden states of each GRU layer in the fully connected layer, the model can integrate features from different levels, preventing the excessive influence of features from a single level on the final result. This enhances the model's robustness and generalization capabilities, making it more stable when processing input sequences of different types and lengths.

[0058] In a possible implementation, S4 specifically includes sub-steps S401 to S403:

[0059] S401: Input the word embedding vector sequence into the first-layer gated recurrent unit to obtain the hidden state of the first-layer gated recurrent unit:

[0060]

[0061]

[0062]

[0063]

[0064] Among them, z t represents the output vector of the update gate at time t, σ() represents the activation function, W uz represents the weight matrix between the input layer and the update gate, x tRepresents the input data at time t (weighted word embedding vector sequence), W hz Represents the self-connection weight matrix of the update gate between time t and time t-1, represents the hidden state of the first layer gated recurrent unit at time t-1, b z represents the bias term of the update gate, r t Represents the output vector of the reset gate at time t, W ur Represents the weight matrix between the input layer and the reset gate, W hr Represents the self-connection weight matrix of the reset gate between time t and time t-1, b r represents the bias term of the reset gate, c t Represents the output vector of the candidate layer at time t, W uc Represents the weight matrix between the input layer and the candidate layer, W hc represents the self-connection weight matrix between the candidate layer at time t and time t-1, b c represents the bias term of the candidate layer, ⊙ represents the element-wise product operation, Represents the hidden state of the first layer gated recurrent unit at time t.

[0065] It should be noted that by resetting the gate and updating the gate, the model can effectively selectively remember or forget past information, thereby enhancing the model's ability to remember important information.

[0066] S402: Input the hidden state of the i-1th gated recurrent unit into the i-th gated recurrent unit to obtain the hidden state of the i-th gated recurrent unit:

[0067]

[0068]

[0069]

[0070]

[0071] in, represents the hidden state of the i-1th layer gated recurrent unit at time t-1, represents the hidden state of the i-th layer gated recurrent unit at time t-1, represents the hidden state of the i-th layer gated recurrent unit at time t, i ≥ 2.

[0072] It's important to note that in a multi-layer GRU, each layer processes the output of the previous layer, accumulating multiple levels of information. This approach can better capture both short-term and long-term dependencies in time series, enhancing the model's expressive power and enabling it to better comprehensively consider various information when faced with complex input data.

[0073] S403: The hidden states in the candidate layers of the gated recurrent units at each layer are fused through the fully connected layer to obtain a comprehensive hidden state to analyze the user's current consultation intention:

[0074]

[0075] Among them, H represents the comprehensive latent state that represents the current consultation intention, β i Represents the fusion coefficient of the gated recurrent unit in the i-th layer.

[0076] It's important to note that the GRU hidden state is updated gradually over time, accumulating and reflecting dynamic changes in the input sequence. Therefore, the combined hidden state dynamically reflects the entire sequence of user input, capturing the changes and trends expressed throughout the conversation, which is crucial for understanding the current consultation intent.

[0077] In this invention, the features and information captured by GRU hidden states at different levels may differ. Lower-level GRUs may capture more basic, local features, while higher-level GRUs may capture more abstract, global features. By fusing this information from different levels, we can comprehensively consider features from different levels, thereby forming a more comprehensive and richer integrated hidden state.

[0078] S5: Based on the current consultation intention, a multi-layer perceptron is used to determine multiple production portal information that matches the current consultation data.

[0079] The Multi-Layer Perceptron (MLP) is a fundamental and widely used feedforward neural network model. It consists of multiple layers of neurons (or nodes), typically including an input layer, a hidden layer, and an output layer. The neurons in each layer are fully connected to the neurons in the next layer, forming a nonlinear mapping that can be used for classification, regression, and other prediction tasks.

[0080] In a possible implementation, S5 specifically includes sub-steps S501 to S506:

[0081] S501: Encode each piece of production portal information using a one-hot encoding method to form a production portal information feature vector.

[0082] Among them, One-Hot Encoding is a commonly used encoding technology, which is mainly used to convert categorical data into numerical data that can be processed by machine learning models.

[0083] It's important to note that one-hot encoding generates a unique feature vector for each piece of production portal information. This encoding method is simple and effective, ensuring that all production portal information is uniquely identified, and it can avoid interference between features, especially when there are many categorical data.

[0084] S502: Map the production portal information feature vector to a latent factor vector through the latent factor matrix:

[0085]

[0086] Among them, q j represents the potential factor vector corresponding to the j-th production portal information, Q j represents the potential factor matrix corresponding to the j-th production portal information, T Represents the transpose operation of the matrix, v j Represents the j-th production portal information feature vector.

[0087] It's important to note that mapping high-dimensional one-hot encoded vectors to a latent factor space using a latent factor matrix effectively reduces the dimensionality of the data and captures the underlying semantic relationships of the production portal information. The latent factor vector retains more useful information at a lower dimensionality, helping to better characterize the characteristics of the production portal information.

[0088] S503: Concatenate the latent factor vector corresponding to each piece of production portal information with the comprehensive latent state used to represent the current consultation intention to obtain a concatenated vector:

[0089] p j =H,q j

[0090] Among them, p j represents the concatenated vector corresponding to the j-th production portal information, and H represents the comprehensive latent state that represents the current consultation intention.

[0091] It's important to note that concatenating the comprehensive latent state of the current inquiry intent with the latent factor vectors of each piece of production portal information helps combine the semantic information of user needs with the characteristic information of the production portal information. This concatenated vector more comprehensively expresses the correlation between user needs and portal information, providing a stronger foundation for subsequent matching calculations.

[0092] S504: Determine the interaction vector between each production portal information and the current consultation intention through a multi-layer perceptron:

[0093] z 1,j =ReLU(W1p j +b1)

[0094] z 2,j=ReLU(W2z 1,j +b2)

[0095]

[0096] z l,j =ReLU(W l z l-1,j +b l )

[0097] Among them, z l,j represents the interaction vector between the j-th production portal information and the current consultation intention, representing the output of the l-th layer, z l-1,j represents the interaction vector between the j-th production portal information and the current consultation intention, ReLU represents the ReLU activation function, and W l represents the weight matrix of the lth layer, b l Represents the bias term of the lth layer, l = 1, 2,, L, and L represents the total number of layers of the multilayer perceptron.

[0098] It should be noted that a multi-layer perceptron (MLP) is used to process the concatenated vectors, extracting the complex relationship between the user's consultation intent and the production portal information layer by layer through nonlinear transformations of multiple hidden layers. MLP can learn deeper feature interactions, especially when dealing with nonlinear relationships. At the same time, the ReLU activation function can effectively prevent the gradient vanishing problem while providing the model with nonlinear capabilities, allowing the model to fit more complex data patterns. Ultimately, the output vector of the MLP (interaction vector) can accurately reflect the degree of match between user intent and portal information.

[0099] S505: Calculate the matching degree between each production portal information and the current consultation intention based on the interaction vector between each production portal information and the current consultation intention:

[0100] r j =Sigmoid(W r z l,j +b r )

[0101] Among them, r j represents the matching degree between the j-th production portal information and the current consultation intention, Sigmoid represents the Sigmoid activation function, and W r represents the matching layer weight matrix, b r represents the matching layer bias term.

[0102] It should be noted that the matching degree is obtained by inputting the interaction vector into the matching layer and mapping the output value to the range [0, 1] using the Sigmoid function. This step compresses the high-dimensional interaction information into a matching degree score, which facilitates direct comparison of the degree of fit between information from different production portals and user intent.

[0103] S506: sorting the various production portal information in descending order of matching degree, and selecting a preset number of production portal information with the highest sorting scores.

[0104] Among them, those skilled in the art can set the size of the preset number according to actual conditions, and the present invention does not limit it. Optionally, the preset number is specifically 10.

[0105] This method not only effectively combines the user's current inquiry intent with the characteristics of the production portal information, but also captures complex feature interactions through deep learning models, ultimately achieving accurate personalized recommendations. This design can significantly improve the accuracy of the recommendation system and user experience.

[0106] S6: Obtain a summary of the user's consultation intentions formed during the historical consultation process.

[0107] The consultation intention summary includes multiple typical consultation intentions of the user in the historical consultation process.

[0108] It's important to note that a user's historical consulting behavior can reflect their long-term interests and preferences. By summarizing these behaviors into typical consulting intentions, the system can more accurately understand the user's long-term interests and use them as a basis for recommendations and matching. This approach allows the recommendation system to not only base its recommendations on the user's current behavior but also fully utilize past behavioral data to provide more targeted recommendations.

[0109] S7: Update the user's consultation intention summary based on the similarity between the current consultation intention and each typical consultation intention in the consultation intention summary.

[0110] In a possible implementation, S7 specifically includes sub-steps S701 and S702:

[0111] S701: Calculate the cosine similarity between the current consultation intention and each typical consultation intention in the consultation intention summary:

[0112]

[0113] Among them, sim k represents the cosine similarity between the kth typical consulting intention in the consulting intention summary and the current consulting intention, H represents the comprehensive latent state that characterizes the current consulting intention, and H kRepresents the comprehensive hidden state representing the k-th typical consultation intention and represents the vector modular operation.

[0114] S702: When the cosine similarity between a certain target typical consulting intention and the current consulting intention is lower than a preset similarity, the target typical consulting intention is replaced with the current consulting intention, and the consulting intention summary is updated.

[0115] When the cosine similarity between multiple typical consulting intentions and the current consulting intention is lower than the preset similarity, the current consulting intention is used to replace the typical consulting intention with the lowest similarity, and the consulting intention summary is updated.

[0116] It's important to note that replacement occurs only when the current inquiry intent has a low degree of similarity with some older intents. This approach ensures that the intent retained in the summary is always the most representative of the user's interests. As user interests diversify or change, this strategy enables the system to respond promptly, preventing older, irrelevant intents from taking up space and thus maintaining the representativeness of the summary. Through this update mechanism, the system can gradually remove content that the user is no longer interested in, reducing the risk of recommending irrelevant content and improving the accuracy of recommendation results. This allows the recommendation system to better match users' actual needs and enhance the user experience.

[0117] In this invention, the system dynamically updates the user's interest model by calculating the similarity between the current inquiry intent and historical typical inquiry intents, and replacing older, less similar intents with the current one. This means that a user's historical interests are not static, but are constantly adapting to new behaviors and inquiries, allowing the system to more accurately reflect the user's current needs and preferences. This enhances the accuracy and relevance of recommendations while controlling the size of summaries to maintain computational efficiency.

[0118] S8: Based on the updated consultation intent summary, the multiple successfully matched production portal information are sorted and processed.

[0119] In a possible implementation, S8 specifically includes sub-steps S801 to S803:

[0120] S801: Calculate the matching degree between the successfully matched production portal information and each updated typical consulting intention through a multi-layer perceptron.

[0121] Specifically, how to calculate the matching degree by using the multi-layer perceptron can refer to the contents of S503 to S505 above, and to avoid repetition, the present invention will not go into details.

[0122] S802: Calculate the average matching degree between the successfully matched production portal information and the updated consultation intent summary:

[0123]

[0124] Among them, R j represents the average matching degree between the jth production portal information that is successfully matched and the updated consultation intent summary, r kj It represents the matching degree between the successfully matched j-th production portal information and the updated k-th typical consulting intent, and K represents the total number of typical consulting intents contained in the consulting intent summary.

[0125] S803: Sort the production portal information in descending order of average matching degree.

[0126] In this invention, portal information is sorted in descending order of average matching scores, ensuring that users see the most relevant recommendations that best meet their current needs. This sorting method significantly improves user satisfaction and the effectiveness of the recommendation system by prioritizing the most matching content.

[0127] S9: Recommending multiple sorted production portal information to the user.

[0128] It should be noted that by sorting by average matching scores, the system ensures that users first see the production portal information that is most relevant to their current consultation intentions and historical interests. This approach can maximize user needs and improve the accuracy and effectiveness of recommendations.

[0129] In one possible implementation, the training method of a large model based on multi-layer stacked gated recurrent units specifically includes:

[0130] Construct the mean square error loss function:

[0131]

[0132] Among them, f represents the mean square error loss function, r j It represents the matching degree between the j-th production portal information calculated by the model and the current consultation intention, It represents the actual matching degree between the j-th production portal information and the current consultation intention, and m represents the total number of production portal information samples.

[0133] According to the mean square error loss function, the Adam optimizer is used to adaptively adjust the learning rate and acceleration parameters to train a large model based on multi-layer stacked gated recurrent units:

[0134]

[0135]

[0136]

[0137]

[0138]

[0139] m t =β1m t-1 +(1-β1)g t

[0140] Among them, θ t represents the model parameters at the tth iteration, θ t-1 represents the model parameters at the t-1th iteration, α represents the basic learning rate, represents the second-order moment estimate after correction of the deviation at the t-th iteration, ε represents the hyperparameter used for numerical stability, represents the first-order moment estimate after the deviation correction at the tth iteration, v t represents the second-order moment estimate at the t-th iteration, β2 represents the second-order moment estimate attenuation coefficient, v t-1 represents the second-order moment estimate at the t-1th iteration, g t represents the gradient at the tth iteration, ▽ represents the gradient operation, f represents the loss function, ▽ θ f t (θ t-1 ) indicates that the loss function performs gradient calculation on the model parameters at the tth iteration, m t represents the first-order moment estimate at the t-th iteration, β1 represents the first-order moment estimate attenuation coefficient, m t-1 Represents the first-order moment estimate at the t-1th iteration.

[0141] It's important to note that the Adam optimizer adaptively adjusts the learning rate of each parameter based on its historical gradient information. For parameters with drastic gradient changes, Adam reduces the learning rate, while for parameters with gentle gradient changes, it increases the learning rate. This adaptability enables faster model convergence while reducing training issues caused by improper learning rate selection.

[0142] In this paper, by using the Adam optimizer, the model training process can adaptively adjust the learning rate and acceleration parameters, effectively handle sparse gradients, improve numerical stability, accelerate convergence, and reduce sensitivity to hyperparameters. This optimization method is particularly suitable for complex multi-layer stacked GRUs and multi-layer perceptrons, and can improve the model's training efficiency, stability, and generalization ability, ultimately achieving better predictive performance.

[0143] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0144] In the present invention, a large model based on multi-layer stacked gated recurrent units is used to effectively capture the user's contextual information and analyze the user's deep consulting intention. At the same time, by continuously updating the user's consulting intention summary, the user's interest changes are dynamically captured. A multi-layer perceptron is used to perform multi-level feature extraction and matching processing on the current consulting intention, which helps to find the production portal information that best meets the user's needs, improve the accuracy and quality of the recommended content, and make the recommendation results more in line with the user's long-term preferences and have a higher degree of personalization.

[0145] Reference Manual Figure 3 , which shows a structural diagram of a production portal information recommendation system driven by a large model provided by the present invention.

[0146] The present invention further provides a large-model driven production portal information recommendation system 20, which is applied to the above-mentioned large-model driven production portal information recommendation method, comprising:

[0147] Processor 201.

[0148] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201 , the method for recommending production portal information based on a large model drive as described in the method embodiment is implemented.

[0149] The large model-driven production portal information recommendation system 20 provided by the present invention can execute the above-mentioned large model-driven production portal information recommendation method and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0150] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0151] In the present invention, a large model based on multi-layer stacked gated recurrent units is used to effectively capture the user's contextual information and analyze the user's deep consulting intention. At the same time, by continuously updating the user's consulting intention summary, the user's interest changes are dynamically captured. A multi-layer perceptron is used to perform multi-level feature extraction and matching processing on the current consulting intention, which helps to find the production portal information that best meets the user's needs, improve the accuracy and quality of the recommended content, and make the recommendation results more in line with the user's long-term preferences and have a higher degree of personalization.

[0152] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be 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, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0153] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0154] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0155] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0156] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0157] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0158] 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. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0159] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0160] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0161] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0162] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0163] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0164] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for recommending production portal information based on a large model drive as described in the method embodiment is implemented.

[0165] The computer-readable storage medium provided by the present invention can implement the steps and effects of the large model-driven production portal information recommendation method of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0166] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0167] In the present invention, a large model based on multi-layer stacked gated recurrent units is used to effectively capture the user's contextual information and analyze the user's deep consulting intention. At the same time, by continuously updating the user's consulting intention summary, the user's interest changes are dynamically captured. A multi-layer perceptron is used to perform multi-level feature extraction and matching processing on the current consulting intention, which helps to find the production portal information that best meets the user's needs, improve the accuracy and quality of the recommended content, and make the recommendation results more in line with the user's long-term preferences and have a higher degree of personalization.

[0168] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0169] There are a few points to note:

[0170] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0171] (2) For the sake of clarity, the thickness of layers or regions in the drawings used to describe the embodiments of the present invention are exaggerated or reduced, that is, these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or intervening elements may be present.

[0172] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to form new embodiments.

[0173] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A production portal information recommendation method based on large model driving, characterized in that: include: S1: Get the user's current consultation data; S2: performing word segmentation processing on the current consultation data; S3: Construct word embedding vectors for each word segment and form a word embedding vector sequence; S4: Analyze the user's current consultation intention based on the word embedding vector sequence through a large model based on multi-layer stacked gated recurrent units; S5: Determine, based on the current consultation intention, multiple pieces of production portal information matching the current consultation data using a multi-layer perceptron; S6: Obtain a consultation intention summary formed by the user in the historical consultation process, wherein the consultation intention summary includes multiple typical consultation intentions of the user in the historical consultation process; S7: updating the user's consultation intention summary according to the similarity between the current consultation intention and each typical consultation intention in the consultation intention summary; S8: sorting the multiple successfully matched production portal information according to the updated consultation intent summary; S9: Recommending multiple sorted production portal information to the user.

2. The method for recommending production portal information based on large model drive according to claim 1, characterized in that: The S2 is specifically: The current consultation data is segmented using regular expressions, maximum matching method, bidirectional maximum matching method, hidden Markov model and / or conditional random field.

3. The method for recommending production portal information based on large model drive according to claim 1, characterized in that: The S3 is specifically: Build word embedding vectors for each word segment through Word2Vec, GloVe, and / or FastText, and form a word embedding vector sequence.

4. The method for recommending production portal information based on large model driving according to claim 1, characterized in that: The multi-layer stacked gated recurrent unit includes a multi-layer gated recurrent unit in a stacked arrangement; the input layer of the first layer of gated recurrent units is used to obtain a weighted word embedding vector sequence, the candidate layer of the previous layer of gated recurrent units is connected to the input layer of the next layer of gated recurrent units, and the output layers of the gated recurrent units in each layer are connected to the fully connected layer, and the fully connected layer is used to fuse the hidden states in the candidate layers of the gated recurrent units in each layer to obtain a comprehensive hidden state that represents the consultation intention.

5. The method for recommending production portal information based on large model drive according to claim 4, characterized in that: The S4 specifically includes: S401: Input the word embedding vector sequence into the first-layer gated recurrent unit to obtain the hidden state of the first-layer gated recurrent unit: Among them, z t represents the output vector of the update gate at time t, σ() represents the activation function, W uz represents the weight matrix between the input layer and the update gate, x t Represents the input data at time t (weighted word embedding vector sequence), W hz Represents the self-connection weight matrix of the update gate between time t and time t-1, represents the hidden state of the first layer gated recurrent unit at time t-1, b z represents the bias term of the update gate, r t Represents the output vector of the reset gate at time t, W ur Represents the weight matrix between the input layer and the reset gate, W hr Represents the self-connection weight matrix of the reset gate between time t and time t-1, b r represents the bias term of the reset gate, c t Represents the output vector of the candidate layer at time t, W uc Represents the weight matrix between the input layer and the candidate layer, W hc represents the self-connection weight matrix between the candidate layer at time t and time t-1, b c represents the bias term of the candidate layer, ⊙ represents the element-wise product operation, Represents the hidden state of the first layer gated recurrent unit at time t; S402: Input the hidden state of the i-1th gated recurrent unit into the i-th gated recurrent unit to obtain the hidden state of the i-th gated recurrent unit: in, represents the hidden state of the i-1th layer gated recurrent unit at time t-1, represents the hidden state of the i-th layer gated recurrent unit at time t-1, represents the hidden state of the i-th layer gated recurrent unit at time t, i ≥ 2; S403: The hidden states in the candidate layers of the gated recurrent units at each layer are fused through the fully connected layer to obtain a comprehensive hidden state to analyze the user's current consultation intention: Among them, H represents the comprehensive latent state that represents the current consultation intention, β i Represents the fusion coefficient of the gated recurrent unit in the i-th layer.

6. The method for recommending production portal information based on large model drive according to claim 5, characterized in that: The S5 specifically includes: S501: Encode each piece of production portal information using a one-hot encoding method to form a production portal information feature vector; S502: Mapping the production portal information feature vector to a latent factor vector through a latent factor matrix: Among them, q j represents the potential factor vector corresponding to the j-th production portal information, Q j represents the potential factor matrix corresponding to the j-th production portal information, T Represents the transpose operation of the matrix, v j represents the feature vector of the j-th production portal information; S503: Concatenate the latent factor vector corresponding to each piece of production portal information with the comprehensive latent state used to represent the current consultation intention to obtain a concatenated vector: p j =<H,q j Among them, p j represents the concatenated vector corresponding to the j-th production portal information, and H represents the comprehensive latent state representing the current consultation intention; S504: Determine the interaction vector between each production portal information and the current consultation intention through a multi-layer perceptron: Among them, z l,j represents the interaction vector between the j-th production portal information and the current consultation intention, representing the output of the l-th layer, z l-1,j represents the interaction vector between the j-th production portal information and the current consultation intention, ReLU represents the ReLU activation function, and W l represents the weight matrix of the lth layer, b l Represents the bias term of the lth layer, l = 1, 2, ..., L, L represents the total number of layers of the multilayer perceptron; S505: Calculate the matching degree between each production portal information and the current consultation intention based on the interaction vector between each production portal information and the current consultation intention: r j =Sigmoid(W r z l,j +b r ) Among them, r j represents the matching degree between the j-th production portal information and the current consultation intention, Sigmoid represents the Sigmoid activation function, and W r represents the matching layer weight matrix, b r represents the matching layer bias term; S506: sorting the various production portal information in descending order of matching degree, and selecting a preset number of production portal information with the highest sorting scores.

7. The method for recommending production portal information based on large model drive according to claim 1, characterized in that: The S7 specifically includes: S701: Calculate the cosine similarity between the current consultation intention and each typical consultation intention in the consultation intention summary: Among them, sim k represents the cosine similarity between the kth typical consulting intention in the consulting intention summary and the current consulting intention, H represents the comprehensive latent state that characterizes the current consulting intention, and H k represents the comprehensive hidden state representing the k-th typical consultation intention, || || represents the vector modulus operation; S702: When the cosine similarity between a target typical consulting intent and the current consulting intent is lower than a preset similarity, the target typical consulting intent is replaced with the current consulting intent, and the consulting intent summary is updated; When the cosine similarities between multiple typical consulting intentions and the current consulting intention are lower than a preset similarity, the current consulting intention is used to replace the typical consulting intention with the lowest similarity, and the consulting intention summary is updated.

8. The method for recommending production portal information based on large model driving according to claim 1, characterized in that: The S8 specifically includes: S801: Calculate the matching degree between the successfully matched production portal information and each updated typical consultation intention through a multi-layer perceptron; S802: Calculate the average matching degree between the successfully matched production portal information and the updated consultation intent summary: Among them, R j represents the average matching degree between the jth production portal information that is successfully matched and the updated consultation intent summary, r kj represents the matching degree between the successfully matched j-th production portal information and the updated k-th typical consulting intent, and K represents the total number of typical consulting intents contained in the consulting intent summary; S803: Sort the production portal information in descending order of average matching degree.

9. The method for recommending production portal information based on large model driving according to claim 1, characterized in that: The training method of the large model based on multi-layer stacked gated recurrent units specifically includes: Construct the mean square error loss function; According to the mean square error loss function, the Adam optimizer is used to adaptively adjust the learning rate and acceleration parameters to train the large model based on multi-layer stacked gated recurrent units.

10. A production portal information recommendation system based on large model drive, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for recommending production portal information based on large model driving according to any one of claims 1 to 6 is implemented.

Images