Business item heat ranking method and device, computer device, and storage medium

Abstract

The application discloses a business item heat ranking method and device, computer equipment and a storage medium, and belongs to the technical field of big data. First, structured and unstructured business data is obtained from a database, the structured data is converted into two-dimensional coordinates through a space mapping technology, and meanwhile, key business labels in the unstructured data are extracted by using a text vectorization technology. Then, an initial heat map is constructed in combination with the two types of information to intuitively display the potential heat of the business items. Next, a pre-trained heat prediction model is introduced to optimize the initial heat map, accurately adjust weight parameters, and generate a more accurate business item heat map. Finally, the business items are ranked according to the heat map. The application also relates to the technical field of blockchains, and business data is stored on a blockchain node. The application realizes accurate evaluation and ranking of the heat of business items by deeply mining business data and using a machine learning method to optimize the heat map.

Description

Technical Field

[0001] This application belongs to the field of big data technology, specifically relating to a method, apparatus, computer equipment, and storage medium for ranking business items by popularity. Background Technology

[0002] Business project popularity ranking refers to the process of collecting and analyzing data related to projects or business activities (such as website traffic, transaction volume, user feedback, and social media engagement), and then using specific algorithms or models to evaluate and rank the popularity of these projects or activities. Its purpose is to help businesses or individuals quickly identify popular projects or business activities to better meet market demands and enhance competitiveness. Business project popularity ranking has wide applications in various fields, such as ranking popular funds, product recommendations on e-commerce platforms, ranking trending topics on social media, and ranking news on news websites. Through popularity ranking, businesses or individuals can more accurately push content or products that users are interested in, improving user satisfaction and loyalty.

[0003] Traditional popularity ranking methods, such as those based on simple counts (like clicks and views) or fixed rules (like publication time and ratings), lack the ability to deeply mine and analyze data. These methods often only capture superficial popularity metrics and fail to delve into the underlying motivations of user behavior and the actual value of projects, thus failing to accurately reflect subtle changes in user needs and dynamic fluctuations in project popularity. Furthermore, traditional popularity ranking methods are susceptible to human intervention and bias. For example, manually adjusting ranking rules or data, as well as subjective judgments based on personal preferences or interests, can lead to ranking results that are neither fair nor objective. Summary of the Invention

[0004] The purpose of this application is to propose a method, apparatus, computer equipment, and storage medium for ranking business items by popularity, in order to solve the technical problems of traditional popularity ranking methods, such as the lack of in-depth data mining and analysis capabilities, and the influence of human intervention and bias, which leads to unfair and unobjective popularity ranking results.

[0005] To address the aforementioned technical problems, this application provides a method for ranking business items by popularity, employing the following technical solution:

[0006] A method for ranking business projects by popularity includes:

[0007] Retrieve business data to be processed from the database, including structured and unstructured data;

[0008] Structured data is mapped to a two-dimensional space, and the coordinates of the structured data in the two-dimensional space are calculated to obtain two-dimensional coordinate information;

[0009] Obtain text data from unstructured data, convert the text data into vector representation, and extract key business tags from the text data vector;

[0010] An initial heat map is constructed based on two-dimensional coordinate information and key business tags;

[0011] The weight parameters of the initial heatmap are updated using a pre-trained heatmap prediction model to obtain a heatmap of business projects.

[0012] The business projects are ranked by popularity based on the business project heat map, and the ranking results are obtained.

[0013] Furthermore, the structured data includes several data points. The structured data is mapped to a two-dimensional space, and the coordinates of the structured data in the two-dimensional space are calculated to obtain two-dimensional coordinate information, including:

[0014] Each data point in the structured data is sequentially subjected to dimensionality reduction processing to obtain several dimensionality-reduced data points;

[0015] Map each dimensionality-reduced data point to a two-dimensional space and obtain the projected coordinates of each dimensionality-reduced data point in the two-dimensional space;

[0016] By integrating the projected coordinates of each dimensionality-reduced data point, two-dimensional coordinate information is obtained.

[0017] Furthermore, text data is obtained from unstructured data, converted into vector representation, and key business tags are extracted from the text data vectors, including:

[0018] Text data is extracted from unstructured data, and the text data is segmented to obtain several text words;

[0019] The bag-of-words model is used to vectorize each text segment, resulting in several text segment vectors;

[0020] Calculate the word frequency of each text segment and use the word frequency statistics to determine the key business word segmentation.

[0021] The key business tags are obtained by determining the business tags corresponding to the key business words from the preset business tag library.

[0022] Furthermore, the business project includes several business objects. An initial heatmap is constructed based on two-dimensional coordinate information and key business tags, including:

[0023] Determine the two-dimensional coordinate information that matches the business object to obtain the target two-dimensional coordinate information;

[0024] Identify the key business tags that match the business objects to obtain the target key business tags;

[0025] Obtain a preset heatmap template, which includes several grids;

[0026] Determine the initial position of the business object in the heatmap template based on the target's two-dimensional coordinate information;

[0027] Obtain attribute data of business objects based on target key business tags;

[0028] Mark the attribute data of the business object at its initial position;

[0029] The heat value of each grid in the heatmap template is calculated using the Gaussian kernel function.

[0030] The color information of each grid is determined by using color gradient mapping based on the heat value of each grid.

[0031] The heatmap template is updated based on the heat value and color information to obtain the initial heatmap.

[0032] Furthermore, the weight parameters of the initial heatmap are updated using a pre-trained heatmap prediction model to obtain a business project heatmap, including:

[0033] Import business data into a pre-trained popularity prediction model to obtain popularity prediction results;

[0034] A predicted heat map is drawn based on the heat prediction results;

[0035] Calculate the heatmap deviation between the initial heatmap and the predicted heatmap;

[0036] Determine whether the heatmap deviation value is greater than or equal to the preset deviation threshold. When the heatmap deviation value is greater than or equal to the deviation threshold, use a genetic algorithm to iteratively update the weight parameters of the initial heatmap until the heatmap deviation value is less than the deviation threshold, and then obtain the business project heatmap.

[0037] Further, the heatmap deviation value between the initial heatmap and the predicted heatmap is calculated, including:

[0038] The target grid is obtained by determining the corresponding grids in the initial heatmap and the predicted heatmap;

[0039] Calculate the heat difference between target grids and construct a heat difference matrix based on the heat difference;

[0040] The average deviation between the initial heatmap and the predicted heatmap is calculated based on the heatmap difference matrix to obtain the heatmap deviation value.

[0041] Furthermore, a genetic algorithm is used to iteratively update the weight parameters of the initial heatmap until the heatmap deviation value is less than the deviation threshold, thus obtaining the business project heatmap, including:

[0042] Step 1: Obtain the initial weight parameters of the initial heatmap, where the initial heatmap contains multiple sets of initial weight parameters;

[0043] Step 2: Generate a corresponding chromosome for each set of initial weight parameters;

[0044] Step 3: Calculate the fitness value of each chromosome based on the preset fitness function;

[0045] Step 4: Select target chromosomes based on their fitness values, and perform crossover and mutation operations on the genes of the target chromosomes to obtain new chromosomes;

[0046] Step 5: Obtain the weight parameters corresponding to the new chromosome, obtain multiple sets of updated weight parameters, and update the weight parameters of the initial heatmap based on the multiple sets of updated weight parameters;

[0047] Step 6: Calculate the heatmap deviation between the updated initial heatmap and the predicted heatmap;

[0048] Repeat steps 3 through 6 until the heatmap deviation value is less than the deviation threshold to obtain the business project heatmap.

[0049] To address the aforementioned technical problems, this application also provides a business item popularity ranking device, which employs the following technical solution:

[0050] A business item popularity ranking device, comprising:

[0051] The data acquisition module is used to acquire business data to be processed from the database, including structured data and unstructured data.

[0052] The data mapping module is used to map structured data to a two-dimensional space and calculate the coordinate position of the structured data in the two-dimensional space to obtain two-dimensional coordinate information.

[0053] The tag acquisition module is used to acquire text data from unstructured data, convert the text data into vector representation, and extract key business tags from the text data vector.

[0054] The heatmap construction module is used to build an initial heatmap based on two-dimensional coordinate information and key business tags.

[0055] The weight update module is used to update the weight parameters of the initial heatmap using a pre-trained heatmap prediction model to obtain a heatmap of business projects.

[0056] The popularity ranking module is used to rank business projects based on the popularity map and obtain the popularity ranking results.

[0057] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0058] A computer device includes a memory and a processor, the memory storing computer-readable instructions, the processor executing the computer-readable instructions to implement the steps of the business item popularity ranking method as described in any of the preceding claims.

[0059] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0060] A computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the steps of the business item popularity ranking method as described in any one of the above.

[0061] Compared with the prior art, the embodiments of this application have the following main advantages:

[0062] This application discloses a method, apparatus, computer equipment, and storage medium for ranking business projects by popularity, belonging to the field of big data technology. First, structured and unstructured business data are obtained from a database. The structured data is transformed into two-dimensional coordinates using spatial mapping technology, while key business tags are extracted from the unstructured data using text vectorization technology. Then, an initial popularity map is constructed by combining these two types of information to visually display the potential popularity of business projects. Next, a pre-trained popularity prediction model is introduced to optimize the initial popularity map, precisely adjusting the weight parameters to generate a more accurate popularity map for business projects. Finally, the business projects are ranked based on this popularity map. This application also relates to the field of blockchain technology, where business data is stored on blockchain nodes. This application automates the processing of structured and unstructured data, deeply mining the inherent relationships within the business data, avoiding human intervention and bias, ensuring the fairness and objectivity of the popularity ranking, and using a pre-trained model to intelligently optimize the weights of the popularity map, further improving the accuracy of the ranking results. It solves the problems of insufficient data mining and excessive subjectivity in traditional methods, providing more reliable data support for business decisions. Attached Figure Description

[0063] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 An exemplary system architecture diagram is shown, in which this application can be applied;

[0065] Figure 2 A flowchart is shown as an embodiment of the business item popularity ranking method according to this application;

[0066] Figure 3 A schematic diagram of a structure of an embodiment of the business item popularity sorting device according to this application is shown;

[0067] Figure 4 A schematic diagram of the structure of one embodiment of a computer device according to this application is shown. Detailed Implementation

[0068] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0069] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0070] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0071] like Figure 1As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0072] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0073] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.

[0074] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103. The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0075] It should be noted that the business item popularity ranking method provided in this application embodiment is generally executed by the server, and correspondingly, the business item popularity ranking device is generally set in the server.

[0076] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0077] Continue to refer to Figure 2The diagram illustrates a flowchart of an embodiment of the business project popularity ranking method according to this application. This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0078] Artificial intelligence (AI) foundational technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly include computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning. The aforementioned method for ranking business project popularity includes the following steps:

[0079] S201: Obtain the business data to be processed from the database. The business data includes structured data and unstructured data.

[0080] Specifically, the process involves retrieving business data from the database. Given the complex and ever-changing business environment and the diverse types of business data, the process retrieves both structured and unstructured data from the database. Structured data includes quantitative metrics such as sales revenue and user volume, while unstructured data includes textual information such as user reviews and market reports.

[0081] Structured data typically has a fixed format and type, such as tabular data in a database, where each field has a clearly defined meaning and data type. Structured data is easy to store, query, and analyze because it follows strict rules and structures. For structured data, it can often be directly extracted from the database and normalized to eliminate dimensional differences. Then, statistical methods (such as Principal Component Analysis (PCA)) can be used to reduce the dimensionality of the data for visualization analysis in a two-dimensional plane.

[0082] Unstructured data, such as text, images, and audio, lacks a fixed format or structure. While it contains rich semantic and contextual information, it is difficult to use directly for numerical computation or statistical analysis. For unstructured data (like text), preprocessing is necessary, including word segmentation, stop word removal, and stemming, to transform the text into a computer-processable format. Then, word embedding techniques (such as Word2Vec and BERT) are used to convert the text into vector representations, preserving semantic information while facilitating subsequent machine learning processing. Finally, convolutional neural networks (CNNs) or other deep learning models can be used to extract features from the text vectors, revealing key business labels or features.

[0083] Different processing methods are used for structured and unstructured data in order to better leverage their respective advantages and improve the accuracy and efficiency of business analysis.

[0084] S202 maps the structured data to a two-dimensional space and calculates the coordinate position of the structured data in the two-dimensional space to obtain two-dimensional coordinate information.

[0085] Specifically, mapping structured data to a two-dimensional space greatly simplifies data analysis and visualization by transforming complex, multi-dimensional structured data into an intuitive and easy-to-understand two-dimensional coordinate representation. The mapping process requires calculating the coordinates of each data point in the structured data within the two-dimensional space, while also ensuring that the mapping preserves the key features and relationships of the original data. Through this data mapping method, previously abstract and difficult-to-perceive structured data becomes visualized and measurable, facilitating subsequent operations such as data fusion, pattern recognition, and popularity assessment.

[0086] Structured data typically contains information across multiple dimensions, with complex relationships and redundancy among them. Directly displaying this multidimensional data on a two-dimensional plane is impractical because two-dimensional space cannot accommodate all dimensional information. To more intuitively illustrate the distribution and relationships of structured data, it needs to be mapped from a high-dimensional space to a low-dimensional space (such as a two-dimensional plane). This allows business personnel to quickly extract valuable information by observing the location, density, and distribution of points (representing business items) on the two-dimensional plane.

[0087] Dimensionality reduction techniques used in the mapping process (such as Principal Component Analysis (PCA)) can effectively preserve the main information in the data (i.e., the direction of maximum variance) while removing redundant information. Through dimensionality reduction methods such as PCA, structured data can be reduced from a high-dimensional space to a two-dimensional plane while preserving as many of the original features of the data as possible.

[0088] S203: Obtain text data from unstructured data, convert the text data into a vector representation, and extract key business tags from the text data vector.

[0089] Specifically, text data is transformed into vector representations, and machine learning techniques are used to extract information from the text. Mathematical models convert words, sentences, and even entire documents into vectors in a high-dimensional space, enabling computers to understand and process the text content. Subsequently, key business tags are extracted from the text data vectors. Based on the semantic features and business relevance of the text vectors, words or phrases that are important for business analysis are automatically identified and labeled. This not only improves the efficiency of text data processing but also ensures the accurate extraction of key information.

[0090] Unstructured data (such as text) typically contains a wealth of semantic and contextual information, which is difficult to extract directly through numerical calculations or statistical analysis. Therefore, more sophisticated natural language processing techniques are needed to extract key information. In business analysis, unstructured data is often used to extract key business tags, sentiment, and themes from text. This information is crucial for understanding business needs, assessing business risks, and developing business strategies.

[0091] Word embedding techniques (such as Word2Vec, BERT, etc.) and deep learning models (such as convolutional neural networks CNN) can effectively process unstructured data and transform text into vector representations. By further processing these vector representations, key business labels or features can be extracted.

[0092] S204, construct an initial heat map based on two-dimensional coordinate information and key business labels.

[0093] Specifically, by combining the two-dimensional coordinate information of structured data with the key business tags of unstructured data, an initial heatmap is generated based on a pre-set heatmap template. This initial heatmap visually displays the distribution of popularity among business projects. The two-dimensional coordinate information provides spatial support for the heatmap, allowing different business projects to be clearly distinguished and located within it. The key business tags serve as a measure of popularity, using visual elements such as color and size to intuitively reflect the importance and level of attention received by each project. This initial heatmap, which integrates structured and unstructured data, not only enhances the depth and breadth of data analysis but also provides an intuitive and easily understood visual reference for subsequent popularity prediction and optimization.

[0094] When building the initial heatmap model, the combined use of structured and unstructured data makes the analysis more comprehensive and in-depth. The coordinate positions on the two-dimensional plane provide a visual representation of spatial distribution and correlation, while key business tags enhance the semantic depth and interpretability of the analysis. The two complement each other and generate strong support for business analysis and decision-making.

[0095] S205, use the pre-trained heat prediction model to update the weight parameters of the initial heat map to obtain the business project heat map.

[0096] Specifically, a pre-trained popularity prediction model is used to update the weight parameters of the initial popularity map, improving the accuracy and intelligence of popularity ranking. The pre-trained model is trained on a large amount of historical data and business rules, enabling it to automatically learn and identify key factors and patterns affecting the popularity of business projects. The popularity prediction model can generate popularity prediction results based on the input business data, and a predicted popularity map can be drawn based on these results. The weight parameters of the initial popularity map are updated by comparing the deviation between the initial and predicted popularity maps. Through fine-tuning and optimizing the weight parameters of the initial popularity map, the model can reduce the influence of human intervention and bias, ensuring the fairness and objectivity of popularity assessment. Simultaneously, the popularity prediction model can also capture market dynamics and trend changes, providing strong support for the real-time updating and dynamic adjustment of business project popularity maps. This not only improves the accuracy of popularity ranking but also enhances the company's responsiveness and competitiveness to market changes.

[0097] S206, Sort the business projects by popularity based on the business project popularity map to obtain the popularity ranking results.

[0098] Specifically, the system ranks business projects based on a heatmap. This heatmap, through intuitive visual presentation, quantifies the level of attention received by each business project into a specific heat value, providing a solid data foundation for the ranking. During the ranking process, the system automatically sorts business projects according to their heat values, ensuring objective and fair results. This not only simplifies the traditional manual evaluation process and improves work efficiency but also reveals the true performance and market potential of business projects through the power of data. The heat ranking results not only provide strong data support for corporate decision-making but also help companies better understand market dynamics, optimize resource allocation, and promote the continuous and healthy development of their businesses.

[0099] In the above embodiments, this application automates the processing of structured and unstructured data, deeply explores the inherent relationships in business data, avoids human intervention and bias, ensures the fairness and objectivity of the popularity ranking, and uses a pre-trained model to intelligently optimize the weights of the popularity map, further improving the accuracy of the ranking results. This solves the problems of insufficient data mining and excessive subjectivity in traditional methods, and provides more reliable data support for business decisions.

[0100] Furthermore, the structured data includes several data points. The structured data is mapped to a two-dimensional space, and the coordinates of the structured data in the two-dimensional space are calculated to obtain two-dimensional coordinate information, including:

[0101] Each data point in the structured data is sequentially subjected to dimensionality reduction processing to obtain several dimensionality-reduced data points;

[0102] Map each dimensionality-reduced data point to a two-dimensional space and obtain the projected coordinates of each dimensionality-reduced data point in the two-dimensional space;

[0103] By integrating the projected coordinates of each dimensionality-reduced data point, two-dimensional coordinate information is obtained.

[0104] In this embodiment, the process of mapping structured data to a two-dimensional space is essentially a technical process of dimensionality reduction and visualization of high-dimensional data. First, by performing dimensionality reduction on each data point in the structured data, such as using Principal Component Analysis (PCA), the complexity of the data is effectively reduced while retaining its main features. Then, the dimensionality-reduced data points are mapped one by one onto a two-dimensional plane, and the accurate projected coordinates of the data points in the two-dimensional space are calculated and obtained. This process not only simplifies the representation of the data but also makes the spatial distribution of the data readily apparent. Finally, the two-dimensional projected coordinates of all the dimensionality-reduced data points are integrated to obtain the complete coordinate information of the structured data in the two-dimensional space.

[0105] Principal Component Analysis (PCA) is a commonly used data dimensionality reduction method. It transforms multiple potentially correlated variables into a few linearly uncorrelated variables through orthogonal transformation. These linearly uncorrelated variables retain most of the information in the original data. PCA helps reduce data complexity and improves the efficiency of data processing and analysis, and is widely used in fields such as data compression, image processing, and pattern recognition.

[0106] In the above embodiments, the structured data is effectively simplified into coordinate points in a two-dimensional space by using principal component analysis (PCA) dimensionality reduction technology. This process not only preserves the main features of the data, but also significantly reduces the complexity of data processing. The mapped two-dimensional coordinate information intuitively shows the interrelationships between the data.

[0107] Furthermore, text data is obtained from unstructured data, converted into vector representation, and key business tags are extracted from the text data vectors, including:

[0108] Text data is extracted from unstructured data, and the text data is segmented to obtain several text words;

[0109] The bag-of-words model is used to vectorize each text segment, resulting in several text segment vectors;

[0110] Calculate the word frequency of each text segment and use the word frequency statistics to determine the key business word segmentation.

[0111] The key business tags are obtained by determining the business tags corresponding to the key business words from the preset business tag library.

[0112] In this embodiment, text information in unstructured data is effectively transformed into a structured vector representation through a series of processing steps. First, the text data in the unstructured data is accurately extracted and segmented into operable text segments. Then, using the bag-of-words model, these segments are mapped to points in a vector space, realizing the numerical representation of the text data. Next, based on word frequency statistics, key business segments are identified from the text segments, as these key business segments are often closely related to the core business. Finally, by comparing with a pre-set business tag library, key business segments are assigned corresponding business tags, realizing a direct mapping from text to business knowledge. This not only improves the efficiency of data processing but also significantly enhances the data's ability to support business decisions.

[0113] In the process of identifying key business-related word segmentation based on word frequency statistics, the first step is to traverse the text segmentation and count the frequency of each word. Then, a word frequency threshold is set based on the business context; if the frequency of a text segmentation exceeds this threshold, it is considered a potential key business word. For example, in e-commerce text analysis, words such as "product," "price," and "discount" that appear frequently will be identified as key business words. By ranking these high-frequency words and further filtering them in conjunction with business logic, such as removing generic or irrelevant words, the final set of word segments closely related to the core business is determined.

[0114] In the above embodiments, by extracting and converting unstructured text into vector representation, combining word frequency statistics to identify key business words, and finally matching the business tag library, the automated extraction of business knowledge from text is realized. This not only improves the intelligence level of data processing, but also enhances the practical value of text data for business decision-making, helping enterprises to quickly understand market trends and customer needs.

[0115] Furthermore, the business project includes several business objects. An initial heatmap is constructed based on two-dimensional coordinate information and key business tags, including:

[0116] Determine the two-dimensional coordinate information that matches the business object to obtain the target two-dimensional coordinate information;

[0117] Identify the key business tags that match the business objects to obtain the target key business tags;

[0118] Obtain a preset heatmap template, which includes several grids;

[0119] Determine the initial position of the business object in the heatmap template based on the target's two-dimensional coordinate information;

[0120] Obtain attribute data of business objects based on target key business tags;

[0121] Mark the attribute data of the business object at its initial position;

[0122] The heat value of each grid in the heatmap template is calculated using the Gaussian kernel function.

[0123] The color information of each grid is determined by using color gradient mapping based on the heat value of each grid.

[0124] The heatmap template is updated based on the heat value and color information to obtain the initial heatmap.

[0125] In this embodiment, the process of constructing an initial heatmap by integrating two-dimensional coordinate information and key business tags in business project analysis demonstrates the deep integration of data visualization and business insights. First, each business object is precisely matched with its corresponding two-dimensional coordinates and key business tags, ensuring data accuracy in both spatial and business dimensions. Then, a preset heatmap template is used as the display framework, providing a flexible data display space through grid division. The initial position of the business object within the template is located using coordinate information, and its attribute data is obtained and labeled based on the key business tags. This process achieves a direct mapping from data to visualization elements.

[0126] Furthermore, a Gaussian kernel function is used to calculate grid heat values, transforming the attribute data of business objects into intuitive heat information. This heat map is then mapped to color information via color gradients, enhancing its informational power and visual appeal. Finally, the template is dynamically updated based on the heat values ​​and color information to generate an initial heat map. This not only visually displays the spatial distribution differences in heat values ​​of business objects but also reveals the patterns and trends behind the business data, providing strong data support for decision-makers.

[0127] When constructing the initial heatmap, the Gaussian kernel function calculates the heat contribution of each business object to its surrounding grid. That is, based on the location and attribute data of the business object, it diffuses heat to the surrounding grid in a Gaussian distribution, thereby ensuring that the heatmap can smoothly and accurately reflect the influence range and intensity of the business object in space, providing a more delicate and precise visualization for business analysis.

[0128] In the above embodiments, by combining two-dimensional coordinates with key business labels, this technology effectively transforms business project data into an intuitive initial heatmap. The Gaussian kernel function ensures that the heat distribution is smooth and accurate, while the color gradient mapping enhances the visual expressiveness. This not only improves the depth of data analysis but also enhances decision-makers' ability to gain insight into the overall picture and details of business projects.

[0129] Furthermore, the weight parameters of the initial heatmap are updated using a pre-trained heatmap prediction model to obtain a business project heatmap, including:

[0130] Import business data into a pre-trained popularity prediction model to obtain popularity prediction results;

[0131] A predicted heat map is drawn based on the heat prediction results;

[0132] Calculate the heatmap deviation between the initial heatmap and the predicted heatmap;

[0133] Determine whether the heatmap deviation value is greater than or equal to the preset deviation threshold. When the heatmap deviation value is greater than or equal to the deviation threshold, use a genetic algorithm to iteratively update the weight parameters of the initial heatmap until the heatmap deviation value is less than the deviation threshold, and then obtain the business project heatmap.

[0134] In this embodiment, a pre-trained heat map prediction model is introduced and optimized using a genetic algorithm to achieve fine-tuning of the initial heat map's weight parameters. First, the model predicts the heat distribution of business data, generates a predicted heat map, and compares it with the initial heat map, quantifying the deviation. If the deviation exceeds a preset threshold, the genetic algorithm is activated to iteratively optimize the weight parameters. The genetic algorithm, simulating a biological evolution mechanism, continuously filters and combines optimal solutions until the deviation is reduced to an acceptable range. Ultimately, the generated business project heat map not only more closely reflects actual business conditions but also improves the accuracy and efficiency of data analysis and decision-making.

[0135] Genetic Algorithm (GA) is a computational model that simulates the biological evolution process in nature. Through operations such as selection, crossover, and mutation, it searches for the optimal solution in the solution space. In constructing heatmaps for business projects, the core role of the genetic algorithm is to optimize the weight parameters of the initial heatmap. When there is a significant deviation between the predicted heatmap and the initial heatmap, the genetic algorithm can iteratively update the weight parameters, continuously selecting and combining optimal solutions to reduce the deviation, ultimately obtaining a heatmap that more closely reflects the actual business situation, thus improving the accuracy of data analysis and decision-making.

[0136] Popularity prediction models can be trained using various machine learning models, such as logistic regression, support vector machines (SVM), random forests, gradient boosting trees (GBDT), and deep learning models like recurrent neural networks (RNN) and convolutional neural networks (CNN). Training a popularity prediction model first requires collecting a large amount of historical data, including text content, publication time, and user interactions (such as likes, comments, and shares) that reflect content popularity. Then, the data undergoes preprocessing such as cleaning, noise reduction, and feature extraction to facilitate subsequent model training. Features useful for popularity prediction are extracted from the preprocessed data; these features may include word frequency, TF-IDF value, publication time, and author influence. A suitable machine learning or deep learning model is selected based on the characteristics of the problem, and the extracted features are used as input data to train the model. During training, the model parameters need to be continuously adjusted to optimize predictive performance. The trained model is evaluated using a validation or test set to check metrics such as prediction accuracy, recall, and F1 score. Based on the evaluation results, the model is fine-tuned to improve its predictive performance.

[0137] In the above embodiments, the accuracy of the business project heatmap is effectively optimized by combining a pre-trained heatmap prediction model with a genetic algorithm. The prediction model provides accurate heatmap predictions, while the genetic algorithm iteratively optimizes for deviations, ensuring that the final heatmap closely reflects the actual business situation.

[0138] Further, the heatmap deviation value between the initial heatmap and the predicted heatmap is calculated, including:

[0139] The target grid is obtained by determining the corresponding grids in the initial heatmap and the predicted heatmap;

[0140] Calculate the heat difference between target grids and construct a heat difference matrix based on the heat difference;

[0141] The average deviation between the initial heatmap and the predicted heatmap is calculated based on the heatmap difference matrix to obtain the heatmap deviation value.

[0142] In this embodiment, when calculating the deviation between the initial heatmap and the predicted heatmap, the grids corresponding to the two maps are first precisely matched to ensure the accuracy of the comparison. Then, a heatmap difference matrix is ​​constructed by calculating the heatmap difference between each corresponding grid. This matrix visually displays the specific differences in heatmap distribution between the two maps. Next, the average deviation is calculated based on this matrix to obtain a quantified heatmap deviation value. This value reflects the degree of deviation between the two maps in the overall heatmap distribution. The calculation of the heatmap deviation value demonstrates a high degree of attention to data details and precise quantification of deviation.

[0143] The heat difference matrix is ​​a tool used to quantify the difference between an initial heat map and a predicted heat map. By calculating the heat difference between the corresponding grids of the two and constructing it into a matrix, it can intuitively show the specific differences between the two in terms of heat distribution.

[0144] In the above embodiments, by combining a pre-trained heat prediction model with a genetic algorithm, the initial heat map is precisely adjusted to ensure that the final business project heat map is highly consistent with reality, effectively reducing the deviation between prediction and reality and improving the accuracy of data-driven decision-making.

[0145] Furthermore, a genetic algorithm is used to iteratively update the weight parameters of the initial heatmap until the heatmap deviation value is less than the deviation threshold, thus obtaining the business project heatmap, including:

[0146] Step 1: Obtain the initial weight parameters of the initial heatmap, where the initial heatmap contains multiple sets of initial weight parameters;

[0147] Step 2: Generate a corresponding chromosome for each set of initial weight parameters;

[0148] Step 3: Calculate the fitness value of each chromosome based on the preset fitness function;

[0149] Step 4: Select target chromosomes based on their fitness values, and perform crossover and mutation operations on the genes of the target chromosomes to obtain new chromosomes;

[0150] Step 5: Obtain the weight parameters corresponding to the new chromosome, obtain multiple sets of updated weight parameters, and update the weight parameters of the initial heatmap based on the multiple sets of updated weight parameters;

[0151] Step 6: Calculate the heatmap deviation between the updated initial heatmap and the predicted heatmap;

[0152] Repeat steps 3 through 6 until the heatmap deviation value is less than the deviation threshold to obtain the business project heatmap.

[0153] In this embodiment, firstly, the genetic algorithm maps each set of weight parameters in the initial heatmap to a chromosome. Then, the quality of each chromosome is evaluated using a preset fitness function to ensure the algorithm evolves in a direction that reduces heatmap bias. After selecting target chromosomes, crossover and mutation operations are further performed. These operations simulate gene recombination and mutation in biological evolution, introducing new solutions to the search space and increasing the likelihood of finding the global optimum. As iteration progresses, new chromosomes are continuously generated, and their corresponding weight parameters gradually approach the optimal solution, causing the deviation between the updated initial heatmap and the predicted heatmap to gradually decrease. Finally, when the deviation drops below a preset threshold, the algorithm stops iterating and outputs the optimized business project heatmap.

[0154] Specifically, n chromosomes are randomly generated, each representing a set of weight parameters (the initial heatmap has n sets of weight parameters). These n chromosomes form a population 1. The fitness value of each chromosome in population 1 is calculated based on a preset fitness function. Individuals are selected from population 1 as parents based on their fitness values. Crossover occurs between the selected parents, exchanging certain positions (genes) on their chromosomes. The offspring produced after crossover undergo mutation, randomly altering certain positions on their chromosomes. Through crossover and mutation, a new population 2 is formed, which also contains n chromosomes. The population (at least two chromosomes out of n chromosomes in population 2 have undergone crossover and mutation operations) corresponds to the n sets of weight parameters of the initial heatmap, indicating that the initial heatmap has been updated. At this time, the heatmap deviation value between the updated initial heatmap and the predicted heatmap is calculated. It is determined whether the heatmap deviation value calculated after the update is greater than or equal to the preset deviation threshold. If the heatmap deviation value calculated after the update is still greater than or equal to the deviation threshold, the genetic algorithm is used to iteratively update the weight parameters of the heatmap according to the chromosome gene crossover and mutation operations above, until the heatmap deviation value is less than the deviation threshold, and the business project heatmap is obtained.

[0155] In the above embodiments, the weight parameters of the initial heatmap are iteratively optimized by a genetic algorithm, which significantly reduces the deviation between the predicted and actual heatmaps, ensures the high accuracy of the final business project heatmap, and improves the accuracy of data-driven decision-making.

[0156] In this embodiment, the business item popularity ranking method runs on electronic devices (e.g., Figure 1The server shown can receive instructions or acquire data via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wideband) connections, and other currently known or future wireless connection methods.

[0157] It should be emphasized that, to further ensure the privacy and security of the aforementioned business data, the data can also be stored in a blockchain node.

[0158] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0159] 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 instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When executed, the computer-readable instructions can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0160] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures 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, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0161] Further reference Figure 3 As a response to the above Figure 2 The implementation of the method shown in this application provides an embodiment of a business item popularity ranking device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0162] like Figure 3 As shown, the business item popularity ranking device 300 described in this embodiment includes:

[0163] The data acquisition module 301 is used to acquire business data to be processed from the database, wherein the business data includes structured data and unstructured data;

[0164] The data mapping module 302 is used to map structured data to a two-dimensional space and calculate the coordinate position of the structured data in the two-dimensional space to obtain two-dimensional coordinate information.

[0165] The tag acquisition module 303 is used to acquire text data in unstructured data, convert the text data into vector representation, and extract key business tags from the text data vector.

[0166] The heatmap construction module 304 is used to construct an initial heatmap based on two-dimensional coordinate information and key business tags.

[0167] The weight update module 305 is used to update the weight parameters of the initial heat map using a pre-trained heat prediction model to obtain a heat map of business projects.

[0168] The popularity ranking module 306 is used to rank business projects based on the popularity map and obtain the popularity ranking results.

[0169] Furthermore, the structured data includes several data points, and the data mapping module 302 is specifically used for:

[0170] Each data point in the structured data is sequentially subjected to dimensionality reduction processing to obtain several dimensionality-reduced data points; each dimensionality-reduced data point is mapped to a two-dimensional space, and the projection coordinates of each dimensionality-reduced data point in the two-dimensional space are obtained; the projection coordinates of each dimensionality-reduced data point are integrated to obtain two-dimensional coordinate information.

[0171] Furthermore, the tag acquisition module 303 is specifically used for:

[0172] Text data is extracted from unstructured data and segmented into words to obtain several text segments; each text segment is vectorized using the bag-of-words model to obtain several text segment vectors; the word frequency of each text segment is counted, and the word frequency statistics result is used to determine key business segments; the business tags corresponding to the key business segments are determined from the preset business tag library to obtain key business tags.

[0173] Furthermore, the business project includes several business objects, and the heatmap construction module 304 is specifically used for:

[0174] The process involves: determining the two-dimensional coordinates of the business object to obtain the target two-dimensional coordinates; determining the key business tags of the business object to obtain the target key business tags; obtaining a preset heatmap template, which includes several grids; determining the initial position of the business object in the heatmap template based on the target two-dimensional coordinates; obtaining the attribute data of the business object based on the target key business tags; marking the attribute data of the business object at its initial position; calculating the heat value of each grid in the heatmap template using a Gaussian kernel function; determining the color information of each grid using color gradient mapping based on its heat value; and updating the heatmap template based on the heat value and color information to obtain the initial heatmap.

[0175] Furthermore, the weight update module 305 is specifically used for:

[0176] Import business data into a pre-trained heat prediction model to obtain heat prediction results; draw a predicted heat map based on the heat prediction results; calculate the heat map deviation value between the initial heat map and the predicted heat map; determine whether the heat map deviation value is greater than or equal to a preset deviation threshold. When the heat map deviation value is greater than or equal to the deviation threshold, use a genetic algorithm to iteratively update the weight parameters of the initial heat map until the heat map deviation value is less than the deviation threshold, thus obtaining the business project heat map.

[0177] Furthermore, the weight update module 305 is also used for:

[0178] The corresponding grids in the initial heatmap and the predicted heatmap are determined to obtain the target grids; the heat difference between the target grids is calculated, and a heat difference matrix is ​​constructed based on the heat difference; the average deviation between the initial heatmap and the predicted heatmap is calculated based on the heat difference matrix to obtain the heatmap deviation value.

[0179] Furthermore, the weight update module 305 is also used to perform the following steps:

[0180] Step 1: Obtain the initial weight parameters of the initial heatmap, where the initial heatmap contains multiple sets of initial weight parameters;

[0181] Step 2: Generate a corresponding chromosome for each set of initial weight parameters;

[0182] Step 3: Calculate the fitness value of each chromosome based on the preset fitness function;

[0183] Step 4: Select target chromosomes based on their fitness values, and perform crossover and mutation operations on the genes of the target chromosomes to obtain new chromosomes;

[0184] Step 5: Obtain the weight parameters corresponding to the new chromosome, obtain multiple sets of updated weight parameters, and update the weight parameters of the initial heatmap based on the multiple sets of updated weight parameters;

[0185] Step 6: Calculate the heatmap deviation between the updated initial heatmap and the predicted heatmap;

[0186] Repeat steps 3 through 6 until the heatmap deviation value is less than the deviation threshold to obtain the business project heatmap.

[0187] In the above embodiments, this application discloses a business project popularity ranking device, belonging to the field of big data technology. First, structured and unstructured business data are obtained from a database. The structured data is transformed into two-dimensional coordinates using spatial mapping technology, while key business tags are extracted from the unstructured data using text vectorization technology. Then, an initial popularity map is constructed by combining these two types of information to visually display the potential popularity of business projects. Next, a pre-trained popularity prediction model is introduced to optimize the initial popularity map, precisely adjusting the weight parameters to generate a more accurate business project popularity map. Finally, the business projects are ranked based on this popularity map. This application also relates to the field of blockchain technology, where business data is stored on blockchain nodes. This application automates the processing of structured and unstructured data, deeply mining the inherent relationships within the business data, avoiding human intervention and bias, ensuring the fairness and objectivity of the popularity ranking, and using a pre-trained model to intelligently optimize the weights of the popularity map, further improving the accuracy of the ranking results. It solves the problems of insufficient data mining and excessive subjectivity in traditional methods, providing more reliable data support for business decisions.

[0188] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0189] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0190] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0191] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for business project popularity ranking methods. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0192] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, for example, to execute computer-readable instructions for the business item popularity ranking method.

[0193] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0194] In the above embodiments, this application discloses a computer device belonging to the field of big data technology. First, structured and unstructured business data are obtained from a database. The structured data is transformed into two-dimensional coordinates using spatial mapping technology, while key business tags are extracted from the unstructured data using text vectorization technology. Then, an initial heatmap is constructed by combining these two types of information to visually display the potential popularity of business projects. Next, a pre-trained heatmap prediction model is introduced to optimize the initial heatmap, precisely adjusting the weight parameters to generate a more accurate heatmap of business projects. Finally, the business projects are ranked based on this heatmap. This application also relates to the field of blockchain technology, where business data is stored on blockchain nodes. This application automates the processing of structured and unstructured data, deeply mining the inherent relationships within business data, avoiding human intervention and bias, ensuring the fairness and objectivity of the heatmap ranking, and intelligently optimizing the heatmap weights using a pre-trained model to further improve the accuracy of the ranking results. This solves the problems of insufficient data mining and excessive subjectivity in traditional methods, providing more reliable data support for business decisions.

[0195] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the business item popularity ranking method described above.

[0196] In the above embodiments, this application discloses a computer-readable storage medium belonging to the field of big data technology. First, structured and unstructured business data are obtained from a database. The structured data is transformed into two-dimensional coordinates using spatial mapping technology, while key business tags are extracted from the unstructured data using text vectorization technology. Then, an initial heatmap is constructed by combining these two types of information to visually display the potential popularity of business projects. Next, a pre-trained heatmap prediction model is introduced to optimize the initial heatmap, precisely adjusting weight parameters to generate a more accurate heatmap of business projects. Finally, business projects are ranked based on this heatmap. This application also relates to the field of blockchain technology, where business data is stored on blockchain nodes. This application automates the processing of structured and unstructured data, deeply mining the inherent relationships within business data, avoiding human intervention and bias, ensuring the fairness and objectivity of heatmap ranking, and intelligently optimizing heatmap weights using a pre-trained model to further improve the accuracy of the ranking results. It solves the problems of insufficient data mining and excessive subjectivity in traditional methods, providing more reliable data support for business decisions.

[0197] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0198] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0199] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A method for ranking business projects by popularity, characterized in that, include: Retrieve business data to be processed from the database, wherein the business data includes structured data and unstructured data; The structured data is mapped to a two-dimensional space, and the coordinate position of the structured data in the two-dimensional space is calculated to obtain two-dimensional coordinate information; Obtain text data from the unstructured data, convert the text data into a vector representation, and extract key business tags from the text data vector; An initial heat map is constructed based on the two-dimensional coordinate information and the key business tags; The weight parameters of the initial heatmap are updated using a pre-trained heatmap prediction model to obtain a business project heatmap. Specifically, the business data is imported into the pre-trained heatmap prediction model to obtain heatmap prediction results. A predicted heatmap is drawn based on the heatmap prediction results. The heatmap deviation between the initial heatmap and the predicted heatmap is calculated. It is determined whether the heatmap deviation is greater than or equal to a preset deviation threshold. If the heatmap deviation is greater than or equal to the deviation threshold, a genetic algorithm is used to iteratively update the weight parameters of the initial heatmap until the heatmap deviation is less than the deviation threshold, thus obtaining the business project heatmap. Corresponding grids in the initial heatmap and the predicted heatmap are determined to obtain target grids. The heatmap difference between the target grids is calculated, and a heatmap difference matrix is ​​constructed based on the heatmap difference. The average deviation between the initial heatmap and the predicted heatmap is calculated based on the heatmap difference matrix, thus obtaining the heatmap deviation value. The business projects are ranked by popularity based on the aforementioned business project heat map, and the ranking results are obtained.

2. The business item popularity ranking method as described in claim 1, characterized in that, The structured data includes several data points. The structured data is mapped to a two-dimensional space, and the coordinate positions of the structured data in the two-dimensional space are calculated to obtain two-dimensional coordinate information, including: Each data point in the structured data is sequentially subjected to dimensionality reduction processing to obtain several dimensionality-reduced data points; Map each of the dimensionality-reduced data points to the two-dimensional space, and obtain the projected coordinates of each of the dimensionality-reduced data points in the two-dimensional space; By integrating the projected coordinates of each of the dimensionality-reduced data points, the two-dimensional coordinate information is obtained.

3. The business item popularity ranking method as described in claim 2, characterized in that, Obtain text data from the unstructured data, convert the text data into a vector representation, and extract key business tags from the text data vector, including: Text data is extracted from the unstructured data, and the text data is segmented to obtain several text segments; The bag-of-words model is used to vectorize each of the text segments, resulting in several text segment vectors; Calculate the word frequency of each segmented text and use the word frequency statistics to determine the key business word segmentation. The key business tags are obtained by determining the business tags corresponding to the key business words from the preset business tag library.

4. The business item popularity ranking method as described in claim 3, characterized in that, The business project includes several business objects. An initial heatmap is constructed based on the two-dimensional coordinate information and the key business tags, including: Determine the two-dimensional coordinate information that matches the business object to obtain the target two-dimensional coordinate information; Identify the key business tags that match the business object to obtain the target key business tags; Obtain a preset heatmap template, wherein the heatmap template includes several grids; The initial position of the business object in the heatmap template is determined based on the target two-dimensional coordinate information; Obtain the attribute data of the business object based on the target key business tags; The attribute data of the business object is marked at its initial position. The heat value of each grid in the heatmap template is calculated using a Gaussian kernel function. The color information of each grid is determined by using color gradient mapping based on the heat value of each grid. The heat map template is updated based on the heat value and the color information to obtain the initial heat map.

5. The business item popularity ranking method as described in claim 1, characterized in that, The weight parameters of the initial heatmap are iteratively updated using a genetic algorithm until the deviation value of the heatmap is less than the deviation threshold, thereby obtaining the business project heatmap, including: Step 1: Obtain the initial weight parameters of the initial heatmap, wherein the initial heatmap contains multiple sets of initial weight parameters; Step 2: Generate a corresponding chromosome for each set of initial weight parameters; Step 3: Calculate the fitness value of each chromosome based on the preset fitness function; Step 4: Select target chromosomes based on their fitness values, and perform crossover and mutation operations on the genes of the target chromosomes to obtain new chromosomes; Step 5: Obtain the weight parameters corresponding to the new chromosome, obtain multiple sets of updated weight parameters, and update the weight parameters of the initial heatmap based on the multiple sets of updated weight parameters; Step 6: Calculate the heatmap deviation value between the updated initial heatmap and the predicted heatmap; Repeat steps 3 to 6 until the deviation value of the heat map is less than the deviation threshold to obtain the heat map of the business project.

6. A business item popularity ranking device, characterized in that, The business item popularity ranking device implements the steps of the business item popularity ranking method as described in any one of claims 1 to 5, and the business item popularity ranking device includes: The data acquisition module is used to acquire business data to be processed from the database, wherein the business data includes structured data and unstructured data; The data mapping module is used to map the structured data to a two-dimensional space and calculate the coordinate position of the structured data in the two-dimensional space to obtain two-dimensional coordinate information. The tag acquisition module is used to acquire text data from the unstructured data, convert the text data into a vector representation, and extract key business tags from the text data vector. A heatmap construction module is used to construct an initial heatmap based on the two-dimensional coordinate information and the key business tags; The weight update module is used to update the weight parameters of the initial heat map using a pre-trained heat prediction model to obtain a business project heat map. The popularity ranking module is used to rank business projects based on the popularity map of the business projects and obtain the popularity ranking result.

7. A computer device, characterized in that, The device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the business item popularity ranking method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the business item popularity ranking method as described in any one of claims 1 to 5.

Images