Business item popularity ranking method and device, computer equipment and storage medium

Abstract

The invention discloses a business item popularity ranking method and device, computer equipment and a storage medium, and belongs to the technical field of big data. The method comprises the following steps: firstly, obtaining structured and unstructured business data from a database, converting the structured data into two-dimensional coordinates through a space mapping technology, and extracting key business labels in the unstructured data by utilizing a text vectorization technology; and then, combining the two types of information to construct an initial popularity map so as to visually display the potential popularity of the business project. Thirdly, a pre-trained popularity prediction model is introduced, the initial popularity map is optimized, weight parameters are accurately adjusted, and a more accurate business item popularity map is generated; and finally, sorting the business items according to the heat map. The invention further relates to the technical field of the block chain, and the business data is stored on the block chain node. According to the method, the business data is deeply mined, and the popularity map is adjusted and optimized by using the machine learning method, so that accurate evaluation and sorting of business item popularity are realized.

Description

Technical Field

[0001] The present application belongs to the field of big data technology, and specifically relates to a method, device, computer equipment and storage medium for ranking the popularity of business items. Background Art

[0002] Business project popularity ranking refers to the collection and analysis of data related to projects or business activities (such as visit volume, transaction volume, user feedback, social media attention, etc.), and the use of certain algorithms or models to evaluate and rank the popularity of projects or business activities. Its purpose is to help companies or individuals quickly identify popular projects or business activities in order to better meet market demand and enhance competitiveness. Business project popularity ranking has a wide range of application scenarios in many fields, such as hot fund rankings, product recommendations on e-commerce platforms, hot topic rankings on social media, news rankings on news websites, etc. Through popularity ranking, companies or individuals can more accurately push content or products that users are interested in, thereby improving user satisfaction and loyalty.

[0003] Traditional popularity sorting methods, such as those based on simple counts (such as clicks, views) or fixed rules (such as release time, ratings), lack the ability to deeply mine and analyze data. These methods can only capture surface popularity indicators, but cannot deeply analyze the motivations behind user behavior and the actual value of the project, and thus cannot accurately reflect the subtle changes in user needs and the dynamic fluctuations in project popularity. In addition, traditional popularity sorting methods are also susceptible to human intervention and bias. For example, artificial adjustments to sorting rules or data, as well as subjective judgments based on personal preferences or interests, may lead to unfair and objective sorting results. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a method, device, computer equipment and storage medium for ranking the popularity of business projects, so as to solve the technical problems that traditional popularity ranking methods lack the ability to deeply mine and analyze data, and are affected by human intervention and bias, resulting in popularity ranking results that are not fair and objective.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a method for ranking the popularity of business items, which adopts the following technical solution:

[0006] A method for ranking business project popularity, comprising:

[0007] Acquire business data to be processed from a database, wherein the business data includes structured data and unstructured data;

[0008] 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 the 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] Construct an initial heat map based on 2D coordinate information and key business tags;

[0011] Use the pre-trained heat prediction model to update the weight parameters of the initial heat map to obtain the business project heat map;

[0012] The business projects are heat sorted according to the business project heat map to obtain a heat sorting result.

[0013] Furthermore, the structured data includes a plurality of data points, and 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, including:

[0014] Perform dimensionality reduction processing on each data point in the structured data in turn to obtain several dimensionality reduction data points;

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

[0016] Integrate the projection coordinates of each dimension-reduced data point to obtain two-dimensional coordinate information.

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

[0018] Extract text data from unstructured data and perform word segmentation on the text data to obtain several text word segments;

[0019] Use the bag-of-words model to vectorize each text word segmentation to obtain several text word segmentation vectors;

[0020] Count the word frequencies of each text segmentation, and determine the key business segmentation based on the word frequency statistics.

[0021] Determine the business tag corresponding to the key business word from the preset business tag library to obtain the key business tag.

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

[0023] Determine the two-dimensional coordinate information matching the business object and obtain the target two-dimensional coordinate information;

[0024] Determine the key business tag that matches the business object and obtain the target key business tag;

[0025] Obtain a preset heat map template, wherein the heat map template includes a plurality of grids;

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

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

[0028] Marking the attribute data of the business object correspondingly at the initial position of the business object;

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

[0030] Determine the color information of each grid using color gradient mapping based on the heat value of each grid;

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

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

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

[0034] Draw a predicted heat map based on the heat prediction results;

[0035] Calculate the heat map deviation value between the initial heat map and the predicted heat map;

[0036] Determine whether the heat map deviation value is greater than or equal to the 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 to obtain the business project heat map.

[0037] Furthermore, the heat map deviation value between the initial heat map and the predicted heat map is calculated, including:

[0038] Determine the corresponding grids in the initial heat map and the predicted heat map to obtain the target grid;

[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 heat map and the predicted heat map is calculated based on the heat difference matrix to obtain the heat map deviation value.

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

[0042] Step 1, obtaining initial weight parameters of an initial heat map, wherein the initial heat map includes multiple sets of initial weight parameters;

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

[0044] Step 3, calculating the fitness value of each chromosome based on a preset fitness function;

[0045] Step 4, select the target chromosome based on the fitness value of the chromosome, and perform crossover and mutation operations on the genes of the target chromosome to obtain a new chromosome;

[0046] Step 5, obtaining weight parameters corresponding to the new chromosomes, obtaining multiple sets of updated weight parameters, and updating the weight parameters of the initial heat map based on the multiple sets of updated weight parameters;

[0047] Step 6, calculating the heat map deviation value between the updated initial heat map and the predicted heat map;

[0048] Repeat steps 3 to 6 until the heat map deviation value is less than the deviation threshold, and obtain the business project heat map.

[0049] In order to solve the above technical problems, the embodiment of the present application further provides a business item popularity ranking device, which adopts the following technical solution:

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

[0051] A data acquisition module, used to acquire the business data to be processed from the database, wherein the business data includes structured data and unstructured data;

[0052] A 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 label acquisition module is used to obtain text data in unstructured data, convert the text data into vector representation, and extract key business labels from the text data vector;

[0054] A heat map construction module is used to construct an initial heat map based on two-dimensional coordinate information and key business tags;

[0055] A 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;

[0056] The heat sorting module is used to heat sort the business projects according to the business project heat map to obtain the heat sorting result.

[0057] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0058] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the business project heat ranking method as described in any one of the above items when executing the computer-readable instructions.

[0059] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0060] A computer-readable storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by a processor, implement the steps of the business project heat ranking method as described in any one of the above.

[0061] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0062] The present application discloses a method, device, computer equipment and storage medium for ranking the heat of business projects, which belongs to the field of big data technology. First, structured and unstructured business data are obtained from a database, and the structured data is converted into two-dimensional coordinates through spatial mapping technology, and the key business tags in the unstructured data are extracted using text vectorization technology. Subsequently, an initial heat map is constructed by combining these two types of information to intuitively display the potential heat of the business project. Next, a pre-trained heat prediction model is introduced to optimize the initial heat map, accurately adjust the weight parameters, and generate a more accurate heat map of business projects. Finally, the business projects are ranked according to this heat map. The present application also relates to the field of blockchain technology, and business data is stored on blockchain nodes. The present application automatically processes structured and unstructured data, deeply explores the inherent correlation of business data, avoids human intervention and prejudice, ensures the fairness and objectivity of heat ranking, and uses a pre-trained model to intelligently optimize the heat map weight, further improves the accuracy of the ranking results, solves the problems of insufficient data mining and excessive subjectivity in traditional methods, and provides more reliable data support for business decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

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

[0065] Figure 2 A flow chart showing an embodiment of a method for ranking the popularity of business items according to the present application is shown;

[0066] Figure 3 A schematic diagram showing the structure of an embodiment of a device for ranking the popularity of business items according to the present application is shown;

[0067] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0068] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0069] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

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

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

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

[0073] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0074] Server 105 can be a server that provides various services, such as a background server that provides support for pages displayed on terminal devices 101, 102, and 103. The server can be an independent 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 communications, middleware services, domain name services, security services, content distribution networks (CDNs), and big data and artificial intelligence platforms.

[0075] It should be noted that the business item heat ranking method provided in the embodiment of the present application is generally executed by a server, and accordingly, the business item heat ranking device is generally set in the server.

[0076] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0077] Continue to refer Figure 2, showing a flow chart of an embodiment of the business project heat ranking method according to the present application. The present application embodiment can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the 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 knowledge to obtain the best results.

[0078] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning. The business project popularity ranking method includes the following steps:

[0079] S201, obtaining business data to be processed from a database, wherein the business data includes structured data and unstructured data.

[0080] Specifically, the business data to be processed is obtained from the database. In view of the complex and ever-changing business environment and the wide variety of business data, the structured and unstructured data of the business to be processed are obtained from the database, including quantitative indicators such as sales and user volume, and text information such as user comments and market reports.

[0081] Structured data usually has a fixed format and type, such as tabular data in a database, where each field has a clear meaning and data type. Structured data is easy to store, query, and analyze because they follow strict rules and structures. For structured data, it can usually be extracted directly 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 visual analysis on a two-dimensional plane.

[0082] Unstructured data has no fixed format or structure, such as text, images, audio, etc. Unstructured data contains rich semantic information and contextual information, but it is difficult to use directly for numerical calculations or statistical analysis. For unstructured data (such as text), preprocessing is first required, including word segmentation, removal of stop words, stemming, etc., in order to convert the text into a computer-processable format. Then, word embedding technology (such as Word2Vec, BERT, etc.) is used to convert the text into a vector representation, which can facilitate subsequent machine learning processing while maintaining the semantic information of the text. Next, a convolutional neural network (CNN) or other deep learning models can be used to extract features from the text vector to extract key business tags or features.

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

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

[0085] Specifically, mapping structured data to two-dimensional space greatly simplifies the process of data analysis and visualization by converting complex multi-dimensional structured data into intuitive and easy-to-understand two-dimensional coordinate representations. The mapping process requires calculating the coordinate position of each data point of the structured data in two-dimensional space, and also requires ensuring that the mapping process can retain the key features and relationships of the original data. Through this data mapping method, the originally abstract and difficult to intuitively perceive structured data becomes visualized and measurable, which facilitates subsequent data fusion, pattern recognition, and heat assessment operations.

[0086] Structured data usually contains information in multiple dimensions, and there are complex relationships and redundancy between these dimensions. It is not feasible to directly display these multidimensional data on a two-dimensional plane, because two-dimensional space cannot accommodate all dimensional information. In order to more intuitively display the distribution and relationship of structured data, it is necessary to map it from a high-dimensional space to a low-dimensional space (such as a two-dimensional plane). In this way, business personnel can quickly obtain valuable information by observing the location, density, and distribution of points (representing business items) on a two-dimensional plane.

[0087] The dimensionality reduction techniques used in the mapping process (such as principal component analysis PCA) can effectively retain the main information in the data (i.e. the direction with the largest 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 retaining the original characteristics of the data as much as possible.

[0088] S203, obtaining text data in the unstructured data, converting the text data into vector representation, and extracting key business tags from the text data vector.

[0089] Specifically, the text data is converted into vector representation, and the text information is mined using machine learning technology. The words, sentences, and even the entire document in the text are converted into vectors in a high-dimensional space through mathematical models, so that the computer can understand and process the text content. Subsequently, key business tags are extracted from the text data vector. Based on the semantic features and business relevance of the text vector, the words or phrases that are important for business analysis are automatically identified and labeled, which not only improves the processing efficiency of text data, but also ensures the accurate extraction of key information.

[0090] Unstructured data (such as text) usually contains a lot of semantic information and contextual information, which is difficult to extract directly through numerical calculations or statistical analysis. Therefore, more complex natural language processing techniques are needed to extract key information. In business analysis, unstructured data is often used to extract key business tags, sentiment tendencies, topics and other information from texts. This information is important for understanding business needs, assessing business risks, and formulating business strategies.

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

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

[0093] Specifically, by combining the two-dimensional coordinate information of structured data with the key business tags of unstructured data, an initial heat map is drawn based on a preset heat map template. The initial heat map shows the heat distribution of business projects in a visual way. Among them, the two-dimensional coordinate information provides spatial dimension support for the heat map, so that different business projects can be clearly distinguished and located in the heat map; and the key business tags serve as a measure of heat, and intuitively reflect the importance and attention of each project through visual elements such as color and size. This initial heat map that integrates structured and unstructured data not only improves the depth and breadth of data analysis, but also provides an intuitive and easy-to-understand visual reference for subsequent heat prediction and optimization.

[0094] When constructing the initial heat map model, the combined use of structured data and unstructured data makes the analysis more comprehensive and in-depth. The coordinate position on the two-dimensional plane provides a visual display of spatial distribution and correlation, while key business tags enhance the semantic depth and explanatory power of the analysis. The two complement each other and provide strong support for business analysis and decision-making.

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

[0096] Specifically, the pre-trained heat prediction model is used to update the weight parameters of the initial heat map to improve the accuracy and intelligence of heat sorting. The pre-trained model is trained based on a large amount of historical data and business rules, and can automatically learn and identify the key factors and patterns that affect the heat of business projects. The heat prediction model can generate heat prediction results based on the input business data, and a predicted heat map can be drawn based on the heat prediction results. The weight parameters of the initial heat map are updated by comparing the deviation between the initial heat map and the predicted heat map. By fine-tuning and optimizing the weight parameters of the initial heat map, the model can reduce the impact of human intervention and bias, and ensure the fairness and objectivity of heat evaluation. At the same time, the heat prediction model can also capture market dynamics and trend changes, and provide strong support for the real-time update and dynamic adjustment of the heat map of business projects, which not only improves the accuracy of heat sorting, but also enhances the company's responsiveness and competitiveness to market changes.

[0097] S206, performing heat sorting on the business items according to the business item heat map to obtain a heat sorting result.

[0098] Specifically, the heat ranking is carried out according to the heat map of business projects. The heat map quantifies the degree of attention of each business project into specific heat values ​​through intuitive visual display, providing a solid data foundation for sorting. During the sorting process, the system will automatically sort the business projects according to the heat values ​​to ensure that the ranking results are objective and fair. It 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 sustainable and healthy business development.

[0099] In the above embodiments, the present application automatically processes structured and unstructured data, deeply explores the intrinsic correlation of business data, avoids human intervention and bias, ensures the fairness and objectivity of heat sorting, and uses pre-trained models to intelligently optimize the heat map weights, further improving the accuracy of the sorting results, solving the problems of insufficient data mining and excessive subjectivity in traditional methods, and providing more reliable data support for business decisions.

[0100] Furthermore, the structured data includes a plurality of data points, and 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, including:

[0101] Perform dimensionality reduction processing on each data point in the structured data in turn to obtain several dimensionality reduction data points;

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

[0103] Integrate the projection coordinates of each dimension-reduced data point to obtain two-dimensional coordinate information.

[0104] In this embodiment, the process of mapping structured data to two-dimensional space is essentially a technical processing process for dimensionality reduction and visualization of high-dimensional data. First, by implementing dimensionality reduction processing on each data point in the structured data, such as using the principal component analysis (PCA) method, the complexity of the data is effectively reduced while retaining the main features of the data. Subsequently, the reduced-dimensional data points are mapped one by one to the two-dimensional plane, and the accurate projection 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 relationship of the data clear at a glance. Finally, the two-dimensional projection coordinates of all reduced-dimensional 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 that converts multiple variables that may be correlated into a few linearly uncorrelated variables through orthogonal transformation. These linearly uncorrelated variables can retain most of the information in the original data. The PCA method helps to reduce the complexity of data and improve the efficiency of data processing and analysis. It is widely used in data compression, image processing, pattern recognition and other fields.

[0106] In the above embodiment, the principal component analysis (PCA) dimensionality reduction technology is used to effectively simplify the structured data into coordinate points in a two-dimensional space. This process not only retains the main features of the data, but also significantly reduces the complexity of data processing. The mapped two-dimensional coordinate information intuitively displays the relationship between the data.

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

[0108] Extract text data from unstructured data and perform word segmentation on the text data to obtain several text word segments;

[0109] Use the bag-of-words model to vectorize each text word segmentation to obtain several text word segmentation vectors;

[0110] Count the word frequencies of each text segmentation, and determine the key business segmentation based on the word frequency statistics.

[0111] Determine the business tag corresponding to the key business word from the preset business tag library to obtain the key business tag.

[0112] In this embodiment, the text information in the unstructured data is effectively converted into a structured vector representation through a series of processing flows. First, the text data in the unstructured data is accurately extracted and segmented, and converted into operable text segmentations. Subsequently, using the bag-of-words model, these segmentations are mapped to points in the vector space, realizing the numerical expression of the text data. Next, based on word frequency statistics, key business segmentations are identified from the text segmentations, and key business segmentations are often closely related to the core of the business. Finally, by comparing the preset business tag library, the key business segmentations are assigned corresponding business tags, realizing a direct mapping from text to business knowledge, which 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 words based on word frequency statistics, the text words are first traversed to count the number of times each text word appears. Then, a word frequency threshold is set according to the business background. As long as the number of times a text word appears exceeds the threshold, the text word is considered a potential key business word. For example, in the text analysis of the e-commerce field, if words such as "commodity", "price", and "discount" appear frequently, they will be identified as key business words. By sorting these high-frequency words and further filtering them in combination with business logic, such as removing common words or insignificant words, the word set closely related to the core of the business is finally determined.

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

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

[0116] Determine the two-dimensional coordinate information matching the business object and obtain the target two-dimensional coordinate information;

[0117] Determine the key business tag that matches the business object and obtain the target key business tag;

[0118] Obtain a preset heat map template, wherein the heat map template includes a plurality of grids;

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

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

[0121] Marking the attribute data of the business object correspondingly at the initial position of the business object;

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

[0123] Determine the color information of each grid using color gradient mapping based on the heat value of each grid;

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

[0125] In this embodiment, in the business project analysis, the process of constructing the initial heat map by integrating two-dimensional coordinate information and key business tags demonstrates the deep integration of data visualization and business insights. First, the corresponding two-dimensional coordinates and key business tags are accurately matched for each business object to ensure the dual accuracy of the data in the spatial dimension and the business dimension. Subsequently, the preset heat map template is used as the display framework, which provides a flexible data display space through grid division. The initial position of the business object in the template is located by coordinate information, and its attribute data is obtained and marked according to the key business tags. This process realizes a direct mapping from data to visualization elements.

[0126] Furthermore, the Gaussian kernel function is used to calculate the grid heat value, converting the attribute data of the business object into intuitive heat information, and mapping it into color information through color gradient, which enhances the information expression ability and visual appeal of the heat map. Finally, the template is dynamically updated based on the heat value and color information to generate the initial heat map, which not only intuitively shows the heat difference of the business objects in spatial distribution, but also deeply reveals the patterns and trends behind the business data, providing strong data support for decision makers.

[0127] When constructing the initial heat map, the Gaussian kernel function calculates the heat contribution of each business object to its surrounding grids, that is, according to the location and attribute data of the business object, the heat is diffused to the surrounding grids in a Gaussian distribution, thereby ensuring that the heat map can smoothly and accurately reflect the influence range and intensity of the business object in space, providing a more delicate and precise visual expression for business analysis.

[0128] In the above embodiment, by combining two-dimensional coordinates with key business tags, this technology effectively converts business project data into an intuitive initial heat map. The Gaussian kernel function ensures that the heat distribution is smooth and accurate, and the color gradient mapping enhances the visual expression, which not only improves the depth of data analysis, but also enhances decision makers' insight into the overall and detailed aspects of business projects.

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

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

[0131] Draw a predicted heat map based on the heat prediction results;

[0132] Calculate the heat map deviation value between the initial heat map and the predicted heat map;

[0133] Determine whether the heat map deviation value is greater than or equal to the 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 to obtain the business project heat map.

[0134] In this embodiment, by introducing a pre-trained heat prediction model and combining it with genetic algorithm optimization, fine adjustment of the initial heat map weight parameters is achieved. First, the model is used to predict the heat distribution of business data, draw a predicted heat map, compare it with the initial heat map, and quantify the heat map deviation. If the deviation exceeds the preset threshold, the genetic algorithm is started to iteratively optimize the weight parameters. The genetic algorithm simulates the biological evolution mechanism and continuously screens and combines the optimal solution until the deviation is reduced to an acceptable range. In the end, the generated business project heat map is not only closer to the actual business situation, 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. It searches for the optimal solution in the solution space through operations such as selection, crossover, and mutation. In the solution of building a heat map of business projects, the core role of the genetic algorithm is to optimize the weight parameters of the initial heat map. When there is a large deviation between the predicted heat map and the initial heat map, the genetic algorithm can iteratively update the weight parameters, continuously screen and combine the optimal solutions, reduce the deviation, and finally obtain a heat map that is closer to the actual business situation, thereby improving the accuracy of data analysis and decision-making.

[0136] The popularity prediction model can be trained based on a variety of machine learning models, such as logistic regression, support vector machine (SVM), random forest, gradient boosting tree (GBDT) and deep learning models such as recurrent neural network (RNN), convolutional neural network (CNN), etc. When training a popularity prediction model, first of all, a large amount of historical data needs to be collected. These data should include information that can reflect the popularity of the content, such as text content, release time, user interaction (such as likes, comments, and sharing). Then, the data is preprocessed by cleaning, denoising, and feature extraction for subsequent model training. Features useful for popularity prediction are extracted from the preprocessed data. These features may include word frequency, TF-IDF value, release time, author influence, etc. of the text content. According to the characteristics of the problem, a suitable machine learning model or deep learning model is selected, and the extracted features are used as input data to train the model. During the training process, the parameters of the model need to be continuously adjusted to optimize the prediction performance of the model. Use the validation set or test set to evaluate the trained model, check the model's prediction accuracy, recall rate, F1 score and other indicators, and tune the model according to the evaluation results to improve the model's prediction performance.

[0137] In the above embodiment, the accuracy of the business project heat map is effectively optimized by combining the pre-trained heat prediction model with the genetic algorithm. The prediction model provides accurate heat prediction, and the genetic algorithm iteratively optimizes the deviation to ensure that the final heat map closely fits the actual business situation.

[0138] Furthermore, the heat map deviation value between the initial heat map and the predicted heat map is calculated, including:

[0139] Determine the corresponding grids in the initial heat map and the predicted heat map to obtain the target grid;

[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 heat map and the predicted heat map is calculated based on the heat difference matrix to obtain the heat map deviation value.

[0142] In this embodiment, when calculating the deviation value between the initial heat map and the predicted heat map, the grids corresponding to the two maps are first accurately matched to ensure the accuracy of the comparison. Subsequently, a heat difference matrix is ​​constructed by calculating the heat difference between each corresponding grid, which intuitively shows the specific differences in the heat distribution between the two. Then, the average deviation is calculated based on the matrix to obtain a quantitative heat map deviation value, which reflects the degree of deviation between the two in the overall heat distribution. The heat deviation value is calculated with a high degree of attention to data details and accurate quantification of deviations.

[0143] The heat difference matrix is ​​a tool used to quantify the difference between the initial heat map and the predicted heat map. It calculates the heat difference between the corresponding grids of the two and constructs them into a matrix form, thereby intuitively showing the specific differences in heat distribution between the two.

[0144] In the above embodiment, the pre-trained heat prediction model is combined with the genetic algorithm to accurately adjust the initial heat map 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 heat map until the heat map deviation value is less than the deviation threshold, thereby obtaining a business project heat map, including:

[0146] Step 1, obtaining initial weight parameters of an initial heat map, wherein the initial heat map includes multiple sets of initial weight parameters;

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

[0148] Step 3, calculating the fitness value of each chromosome based on a preset fitness function;

[0149] Step 4, select the target chromosome based on the fitness value of the chromosome, and perform crossover and mutation operations on the genes of the target chromosome to obtain a new chromosome;

[0150] Step 5, obtaining weight parameters corresponding to the new chromosomes, obtaining multiple sets of updated weight parameters, and updating the weight parameters of the initial heat map based on the multiple sets of updated weight parameters;

[0151] Step 6, calculating the heat map deviation value between the updated initial heat map and the predicted heat map;

[0152] Repeat steps 3 to 6 until the heat map deviation value is less than the deviation threshold, and obtain the business project heat map.

[0153] In this embodiment, first, the genetic algorithm maps each set of weight parameters of the initial heat map to a chromosome. Subsequently, the advantages and disadvantages of each chromosome are evaluated by a preset fitness function to ensure that the algorithm can evolve in the direction of reducing the deviation of the heat map. After the target chromosome is screened, crossover and mutation operations are further performed. These operations simulate gene recombination and mutation in biological evolution, introduce new solutions to the search space, and increase the possibility of finding a global optimal solution. As the iteration proceeds, new chromosomes are continuously generated, and their corresponding weight parameters gradually approach the optimal solution, so that the deviation value between the updated initial heat map and the predicted heat map gradually decreases. Finally, when the deviation value drops below the preset threshold, the algorithm stops iterating and outputs the optimized business project heat map.

[0154] Specifically, n chromosomes are randomly generated, each chromosome represents the encoding of a set of weight parameters (the initial heat map has n sets of weight parameters), and the n chromosomes are taken as a population 1. The fitness value of each chromosome in population 1 is calculated based on the preset fitness function, and some individuals are selected from population 1 as parents according to the fitness value. The selected parent individuals will undergo a crossover operation, that is, some bits in their chromosomes (chromosome genes) will be exchanged, and the offspring individuals generated after the crossover will undergo a mutation operation, that is, some bits in their chromosomes will be randomly changed. Through the crossover operation and mutation operation, a new population 2 is formed, and population 2 also contains n chromosomes. The n sets of weight parameters corresponding to the initial heat map are n (at least 2 chromosomes among the n chromosomes of population 2 have undergone crossover and mutation operations), indicating that the initial heat map has been updated. At this time, the heat map deviation value between the updated initial heat map and the predicted heat map is calculated, and it is determined whether the heat map deviation value calculated after the update is greater than or equal to the preset deviation threshold. If the heat map deviation value calculated after the update is still greater than or equal to the deviation threshold, the genetic algorithm is continued to be used to iteratively update the weight parameters of the heat map according to the above chromosome gene crossover and mutation operations until the heat map deviation value is less than the deviation threshold, and the business project heat map is obtained.

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

[0156] In this embodiment, the electronic device (eg Figure 1The server shown in the figure) can receive instructions or obtain data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

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

[0158] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0159] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0160] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0161] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a device for ranking the popularity of business items. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

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

[0163] The data acquisition module 301 is used to acquire the 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 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;

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

[0166] A heat map construction module 304 is used to construct an initial heat map based on the two-dimensional coordinate information and key business tags;

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

[0168] The heat ranking module 306 is used to heat-rank the business items according to the business item heat map to obtain a heat ranking result.

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

[0170] Perform dimensionality reduction processing on each data point in the structured data in turn to obtain a number of reduced-dimensionality data points; map each reduced-dimensionality data point to a two-dimensional space, and obtain the projection coordinates of each reduced-dimensionality data point in the two-dimensional space; integrate the projection coordinates of each reduced-dimensionality data point to obtain two-dimensional coordinate information.

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

[0172] Extract text data from unstructured data and perform word segmentation on the text data to obtain several text word segments; use the bag-of-words model to vectorize each text word segment to obtain several text word segmentation vectors; count the word frequency of each text word segmentation, and determine the key business word segmentation based on the word frequency statistics; determine the business tag corresponding to the key business word segmentation from the preset business tag library to obtain the key business tag.

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

[0174] Determine the two-dimensional coordinate information that matches the business object and obtain the target two-dimensional coordinate information; determine the key business tag that matches the business object and obtain the target key business tag; obtain a preset heat map template, wherein the heat map template includes a plurality of grids; determine the initial position of the business object in the heat map template based on the target two-dimensional coordinate information; obtain the attribute data of the business object based on the target key business tag; mark the attribute data of the business object at the initial position of the business object; calculate the heat value of each grid in the heat map template through a Gaussian kernel function; determine the color information of each grid based on the heat value of each grid using color gradient mapping; update the data of the heat map template based on the heat value and color information to obtain an initial heat map.

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

[0176] Import the business data into the pre-trained heat prediction model to obtain the heat prediction results; draw the 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 the 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, thereby obtaining the business project heat map.

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

[0178] Determine the corresponding grids in the initial heat map and the predicted heat map to obtain the target grid; calculate the heat difference between the target grids, and construct a heat difference matrix based on the heat difference; calculate the average deviation between the initial heat map and the predicted heat map based on the heat difference matrix to obtain the heat map deviation value.

[0179] Furthermore, the weight updating module 305 is further configured to perform the following steps:

[0180] Step 1, obtaining initial weight parameters of an initial heat map, wherein the initial heat map includes multiple sets of initial weight parameters;

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

[0182] Step 3, calculating the fitness value of each chromosome based on a preset fitness function;

[0183] Step 4, select the target chromosome based on the fitness value of the chromosome, and perform crossover and mutation operations on the genes of the target chromosome to obtain a new chromosome;

[0184] Step 5, obtaining weight parameters corresponding to the new chromosomes, obtaining multiple sets of updated weight parameters, and updating the weight parameters of the initial heat map based on the multiple sets of updated weight parameters;

[0185] Step 6, calculating the heat map deviation value between the updated initial heat map and the predicted heat map;

[0186] Repeat steps 3 to 6 until the heat map deviation value is less than the deviation threshold, and obtain the business project heat map.

[0187] In the above embodiment, the present application discloses a business project heat ranking device, which belongs to the field of big data technology. First, structured and unstructured business data are obtained from the database, and the structured data is converted into two-dimensional coordinates through spatial mapping technology, and the key business tags in the unstructured data are extracted using text vectorization technology. Subsequently, the initial heat map is constructed by combining these two types of information to intuitively display the potential heat of the business project. Next, a pre-trained heat prediction model is introduced to optimize the initial heat map, accurately adjust the weight parameters, and generate a more accurate business project heat map. Finally, the business projects are sorted according to this heat map. The present application also relates to the field of blockchain technology, and business data is stored on blockchain nodes. The present application automatically processes structured and unstructured data, deeply explores the inherent correlation of business data, avoids human intervention and prejudice, ensures the fairness and objectivity of heat sorting, and uses a pre-trained model to intelligently optimize the heat map weight, further improves the accuracy of the sorting results, solves the problems of insufficient data mining and excessive subjectivity in traditional methods, and provides more reliable data support for business decision-making.

[0188] To solve the above technical problems, the present application also provides a computer device. 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 through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmab l eGate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0190] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0191] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), 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, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the business project heat ranking method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

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

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

[0194] In the above embodiment, the present application discloses a computer device, which belongs to the field of big data technology. First, structured and unstructured business data are obtained from the database, and the structured data is converted into two-dimensional coordinates through spatial mapping technology, and the key business tags in the unstructured data are extracted using text vectorization technology. Subsequently, the initial heat map is constructed by combining these two types of information to intuitively display the potential heat of the business project. Next, a pre-trained heat prediction model is introduced to optimize the initial heat map, accurately adjust the weight parameters, and generate a more accurate heat map of the business project. Finally, the business projects are sorted according to this heat map. The present application also relates to the field of blockchain technology, and the business data is stored on the blockchain node. The present application automatically processes structured and unstructured data, deeply explores the inherent correlation of business data, avoids human intervention and prejudice, ensures the fairness and objectivity of heat sorting, and uses the pre-trained model to intelligently optimize the heat map weight, further improves the accuracy of the sorting results, solves the problems of insufficient data mining and excessive subjectivity in traditional methods, and provides more reliable data support for business decision-making.

[0195] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the business project heat ranking method as described above.

[0196] In the above embodiment, the present application discloses a computer-readable storage medium, which belongs to the field of big data technology. First, structured and unstructured business data are obtained from the database, and the structured data is converted into two-dimensional coordinates through spatial mapping technology, and the key business tags in the unstructured data are extracted using text vectorization technology. Subsequently, the initial heat map is constructed by combining these two types of information to intuitively display the potential heat of the business project. Next, a pre-trained heat prediction model is introduced to optimize the initial heat map, accurately adjust the weight parameters, and generate a more accurate heat map of the business project. Finally, the business projects are sorted according to this heat map. The present application also relates to the field of blockchain technology, and business data is stored on blockchain nodes. The present application automatically processes structured and unstructured data, deeply explores the inherent correlation of business data, avoids human intervention and prejudice, ensures the fairness and objectivity of heat sorting, and uses a pre-trained model to intelligently optimize the heat map weight, further improves the accuracy of the sorting results, solves the problems of insufficient data mining and excessive subjectivity in traditional methods, and provides more reliable data support for business decision-making.

[0197] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0198] The present application can be used in many general or special computer system environments or configurations. For example: 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, distributed computing environments including any of the above systems or devices, etc. The present 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. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0199] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for ranking the popularity of business items, characterized in that: include: Acquire business data to be processed from a database, wherein the business data includes structured data and unstructured data; Mapping the structured data to a two-dimensional space, and calculating the coordinate position of the structured data in the two-dimensional space to obtain two-dimensional coordinate information; Acquire text data in the unstructured data, convert the text data into vector representation, and extract key business tags from the text data vector; Constructing an initial heat map based on the two-dimensional coordinate information and the key business tags; Using a pre-trained heat prediction model to update the weight parameters of the initial heat map to obtain a business project heat map; The business items are heat sorted according to the business item heat map to obtain a heat sorting result.

2. The method for ranking business items according to claim 1, characterized in that: The structured data includes a plurality of data points. 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, including: Performing dimensionality reduction processing on each data point in the structured data in turn to obtain a plurality of dimensionality reduction data points; Mapping each of the reduced-dimensionality data points to the two-dimensional space, and obtaining the projection coordinates of each of the reduced-dimensionality data points in the two-dimensional space; The projection coordinates of each of the reduced-dimensionality data points are integrated to obtain the two-dimensional coordinate information.

3. The method for ranking business items by popularity as claimed in claim 2, characterized in that: Acquiring text data from the unstructured data, converting the text data into a vector representation, and extracting key business tags from the text data vector, including: Extracting text data from the unstructured data, and performing word segmentation processing on the text data to obtain a plurality of text word segments; Using a bag-of-words model to vectorize each of the text segmentation words, to obtain a number of text segmentation vectors; Counting the word frequencies of each of the text segmentations, and determining key business segmentations based on the word frequency statistics; The business tag corresponding to the key business word is determined from a preset business tag library to obtain the key business tag.

4. The method for ranking business items by popularity as claimed in claim 3, characterized in that: The business project includes several business objects, and an initial heat map is constructed based on the two-dimensional coordinate information and the key business tags, including: Determine the two-dimensional coordinate information matching the business object, and obtain the target two-dimensional coordinate information; Determine a key business tag that matches the business object, and obtain a target key business tag; Obtain a preset heat map template, wherein the heat map template includes a plurality of grids; Determining an initial position of the business object in the heat map template based on the target two-dimensional coordinate information; Acquire attribute data of the business object based on the target key business tag; Marking the attribute data of the business object correspondingly at the initial position of the business object; Calculate the heat value of each grid in the heat map template by using a Gaussian kernel function; Determine the color information of each grid 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 method for ranking business items by popularity as claimed in claim 4, characterized in that: The weight parameters of the initial heat map are updated using the pre-trained heat prediction model to obtain a business project heat map, including: Importing the business data into the pre-trained popularity prediction model to obtain a popularity prediction result; Draw a predicted heat map based on the heat prediction result; Calculating a 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, a genetic algorithm is used to iteratively update the weight parameters of the initial heat map until the heat map deviation value is less than the deviation threshold, thereby obtaining the business item heat map.

6. The method for ranking business items by popularity as claimed in claim 5, characterized in that: Calculating a heat map deviation value between the initial heat map and the predicted heat map includes: Determine the grids corresponding to each other in the initial heat map and the predicted heat map to obtain a target grid; Calculating the heat difference between the target grids, and constructing a heat difference matrix based on the heat difference; The average deviation between the initial heat map and the predicted heat map is calculated based on the heat difference matrix to obtain the heat map deviation value.

7. The method for ranking business items by popularity according to claim 5, characterized in that: Iteratively updating the weight parameters of the initial heat map using a genetic algorithm until the heat map deviation value is less than the deviation threshold, thereby obtaining the business item heat map, including: Step 1, obtaining initial weight parameters of the initial heat map, wherein the initial heat map includes multiple groups of initial weight parameters; Step 2, generating a corresponding chromosome for each set of the initial weight parameters; Step 3, calculating the fitness value of each chromosome based on a preset fitness function; Step 4, selecting a target chromosome based on the fitness value of the chromosome, and performing a crossover operation and a mutation operation on the gene of the target chromosome to obtain a new chromosome; Step 5, obtaining weight parameters corresponding to the new chromosomes, obtaining multiple sets of updated weight parameters, and updating the weight parameters of the initial heat map based on the multiple sets of updated weight parameters; Step 6, calculating a heat map deviation value between the updated initial heat map and the predicted heat map; Repeat steps 3 to 6 until the heat map deviation value is less than the deviation threshold, thereby obtaining the business item heat map.

8. A device for ranking the popularity of business items, characterized in that: include: A data acquisition module, used to acquire the business data to be processed from the database, wherein the business data includes structured data and unstructured data; A data mapping module, 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; A label acquisition module, used to acquire text data in the unstructured data, convert the text data into a vector representation, and extract key business labels from the text data vector; A heat map construction module, used to construct an initial heat map based on the two-dimensional coordinate information and the key business tags; A weight updating module, 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 heat sorting module is used to heat sort the business items according to the business item heat map to obtain a heat sorting result.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the business item heat ranking method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the business item heat ranking method according to any one of claims 1 to 7 are implemented.

Images