A data collection method and system based on Internet takeaway information

Abstract

The present invention relates to the field of intelligent data collection technology, and in particular to a data collection method and system based on Internet takeaway information. The method comprises the following steps: obtaining takeaway platform information data; semantically standardizing the takeaway platform information data to generate a semantically normalized data set of takeaway information; associating the semantically normalized data set of takeaway information with geographic data, thereby generating geographic location associated data of takeaway information; using the geographic location associated data of takeaway information to perform entity relationship mapping on the semantically normalized data set of takeaway information to generate an entity relationship mapping graph of takeaway information; calculating the relevance of takeaway information on the entity relationship mapping graph of takeaway information to obtain a relevance coefficient of takeaway information. The present invention improves the efficiency and quality of takeaway information data collection by performing semantic standardization, geographic association, intelligent reasoning and data storage optimization on the data collected from takeaway information.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent data collection, and in particular to a data collection method and system based on Internet takeaway information. Background Art

[0002] The collection of takeaway information mainly relies on manual input and crawling of web page information. However, this method is inefficient and prone to errors, and cannot cope with the growing amount of takeaway platforms and information. With the advancement of technology, an automated data collection system based on web crawlers has emerged. Web crawlers simulate human browser behavior, automatically access takeaway platform websites, crawl and extract required information, and achieve rapid collection of large-scale data. This method improves efficiency, but still faces challenges such as website anti-crawler mechanisms and data structure changes. With the development of machine learning and artificial intelligence technology, new data collection systems are gradually emerging. The data crawling system based on machine learning can automatically adjust the crawling strategy by analyzing the change patterns and rules of the takeaway platform pages, thereby improving the accuracy and stability of data collection. However, when processing massive data, it is difficult to establish effective entity relationship mapping and measure relevance. At the same time, it is often impossible to perform deep reasoning and intelligent completion on missing collected data, resulting in low integrity and accuracy of the collection. Summary of the invention

[0003] Based on this, it is necessary to provide a data collection method and system based on Internet takeaway information to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a data collection method based on Internet takeaway information is provided, the method comprising the following steps:

[0005] Step S1: Acquire food delivery platform information data; perform semantic standardization on the food delivery platform information data to generate a food delivery information semantic standardization data set; perform geographic data association on the food delivery information semantic standardization data set to generate food delivery information geographic location association data;

[0006] Step S2: Use the geographic location-related data of takeaway information to perform entity relationship mapping on the semantic normalized data set of takeaway information to generate an entity relationship mapping graph of takeaway information; calculate the relevance of takeaway information on the entity relationship mapping graph of takeaway information to obtain a relevance coefficient of takeaway information; compare the relevance coefficient of takeaway information with a preset standard relevance threshold to generate strongly-related takeaway information data and weakly-related takeaway information data; perform data update control on the strongly-related takeaway information data and the weakly-related takeaway information data to generate takeaway information collection control data;

[0007] Step S3: Based on the takeaway information collection and control data, knowledge reasoning is performed on the takeaway information entity relationship mapping graph to generate takeaway information collection reasoning data; uncertainty processing is performed on the takeaway information collection and control data using the takeaway information collection reasoning data to generate takeaway information collection completion data; intelligent collection completion and optimization are performed on the takeaway information collection and control data based on the takeaway information collection completion data and the takeaway information collection inference data to generate takeaway information collection optimization data;

[0008] Step S4: Optimize the data collected by takeaway information by storing a cache cluster to generate takeaway information cache data; standardize the data backup of the takeaway information cache data to generate standard takeaway information collection backup data; set up interfaces for the standard takeaway information collection backup data to generate takeaway information collection format conversion data; perform interface integration testing on the takeaway information collection format conversion data to generate a takeaway information collection module to execute takeaway information data collection.

[0009] The present invention ensures the consistency of data through semantic standardization, and the association of geographic data improves the accuracy of takeaway information, making subsequent analysis more reliable. Geographic location-related data makes takeaway information more regional, which helps merchants to make more targeted marketing strategies in specific areas. Geographic location-related data provides a basis for subsequent multi-dimensional analysis, such as making in-depth research on food preferences, delivery time, etc. in specific areas possible. Through entity relationship mapping and association calculation, the degree of association between takeaway information can be more accurately understood, so that data can be processed more finely. Dividing data into strongly associated and weakly associated parts can help better process different data and improve the accuracy and effectiveness of data analysis. According to the classification of association, data can be regulated in a targeted manner, making the data more instructive and practical, and improving the value of subsequent analysis and application. Through knowledge reasoning, the entity relationship mapping map of takeaway information can be enriched to make it more in-depth and broad, providing more useful information for subsequent analysis and application. Uncertainty processing helps to reduce uncertainty in data, improve the credibility of data, and make subsequent decision-making and application more confident. By completing and optimizing the data collected from takeout information, the integrity and accuracy of the data can be improved, making it more suitable for various analysis and application scenarios. Storing data in a cache cluster improves the access speed and efficiency of the data, making the real-time acquisition and processing of takeout information faster. Through backup, standardization and format conversion, the integrity and reliability of the backup data of the takeout information are ensured, and the risk of data loss is reduced. Through interface setting and integration testing, the stability of the takeout information collection module and its interoperability with other systems are guaranteed, making the collection process of takeout information more reliable and smooth. Therefore, the present invention improves the efficiency and quality of takeout information data collection by performing semantic standardization, geographic association, intelligent reasoning and data storage optimization on the data collected from takeout information.

[0010] In this specification, a data collection system based on Internet takeaway information is provided, which is used to execute the above-mentioned data collection method based on Internet takeaway information. The data collection system based on Internet takeaway information includes:

[0011] The geographic association module is used to obtain the information data of the food delivery platform; perform semantic standardization on the information data of the food delivery platform to generate a semantically normalized data set of food delivery information; perform geographic data association on the semantically normalized data set of food delivery information to generate geographic location association data of food delivery information;

[0012] The information association judgment module is used to use the geographical location association data of takeout information to perform entity relationship mapping on the semantic normalized data set of takeout information to generate an entity relationship mapping map of takeout information; calculate the association degree of takeout information on the entity relationship mapping map of takeout information to obtain the association coefficient of takeout information; compare the association coefficient of takeout information with a preset standard association threshold to generate strongly associated takeout information data and weakly associated takeout information data; perform data update regulation on the strongly associated takeout information data and the weakly associated takeout information data to generate takeout information collection regulation data;

[0013] The information missing inference module is used to perform knowledge reasoning on the takeaway information entity relationship mapping graph based on the takeaway information collection and control data to generate takeaway information collection reasoning data; use the takeaway information collection reasoning data to process the uncertainty of the takeaway information collection and control data to generate takeaway information collection completion data; based on the takeaway information collection completion data and the takeaway information collection inference data, the takeaway information collection control data is intelligently completed and optimized to generate takeaway information collection optimization data;

[0014] The interface integration module is used to store and cache clusters for takeout information collection optimization data to generate takeout information cache data; to standardize data backup of takeout information cache data to generate standard takeout information collection backup data; to set interfaces for standard takeout information collection backup data to generate takeout information collection format conversion data; to perform interface integration testing on takeout information collection format conversion data, thereby generating a takeout information collection module to execute takeout information data collection.

[0015] The beneficial effect of the present invention is that semantic standardization of takeaway platform information data helps unify data formats and improve data consistency and comprehensibility. By associating geographic data, takeaway information can be associated with specific geographic locations, which is helpful for subsequent geographic information analysis. Generating a takeaway information entity relationship mapping map helps understand the relationship between takeaway information, so as to better perform subsequent analysis and reasoning. By calculating the degree of association, the degree of association between takeaway information can be quantified, which helps to identify information with high correlation. Knowledge reasoning on the takeaway information entity relationship mapping map helps to discover potential relationships and laws, and improve the depth of data analysis. Dealing with the uncertainty of takeaway information collection and regulation data helps to improve the credibility and stability of data. Using reasoning data to complete and optimize information collection and regulation data can improve the integrity and accuracy of information. Generating takeaway information cache data helps to improve data access speed and system responsiveness. The generation of standard takeaway information collection backup data helps data security and recoverability. By converting data in the takeaway information collection format, data interaction and integration with different systems or platforms can be achieved. Through steps such as standardization, association and intelligent completion, the quality and consistency of takeaway information are improved, thereby enhancing the credibility of data. Through the steps of entity relationship mapping, knowledge reasoning, etc., the relationship between takeout information can be analyzed more deeply and more information can be mined. Through the steps of caching and format conversion, the performance and efficiency of the system can be improved, and the data access and processing process can be accelerated. Therefore, the present invention improves the efficiency and quality of takeout information data collection by performing semantic standardization, geographic association, intelligent reasoning and data storage optimization on the data collected from takeout information. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the steps of a data collection method based on Internet takeaway information;

[0017] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0018] Figure 3 for Figure 1 Detailed implementation steps of step S25;

[0019] Figure 4 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0022] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0023] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0024] To achieve this, please refer to Figures 1 to 4 , a data collection method based on Internet takeaway information, the method comprising the following steps:

[0025] Step S1: Acquire food delivery platform information data; perform semantic standardization on the food delivery platform information data to generate a food delivery information semantic standardization data set; perform geographic data association on the food delivery information semantic standardization data set to generate food delivery information geographic location association data;

[0026] Step S2: Use the geographic location-related data of takeaway information to perform entity relationship mapping on the semantic normalized data set of takeaway information to generate an entity relationship mapping graph of takeaway information; calculate the relevance of takeaway information on the entity relationship mapping graph of takeaway information to obtain a relevance coefficient of takeaway information; compare the relevance coefficient of takeaway information with a preset standard relevance threshold to generate strongly-related takeaway information data and weakly-related takeaway information data; perform data update control on the strongly-related takeaway information data and the weakly-related takeaway information data to generate takeaway information collection control data;

[0027] Step S3: Based on the takeaway information collection and control data, knowledge reasoning is performed on the takeaway information entity relationship mapping graph to generate takeaway information collection reasoning data; uncertainty processing is performed on the takeaway information collection and control data using the takeaway information collection reasoning data to generate takeaway information collection completion data; intelligent collection completion and optimization are performed on the takeaway information collection and control data based on the takeaway information collection completion data and the takeaway information collection inference data to generate takeaway information collection optimization data;

[0028] Step S4: Optimize the data collected by takeaway information by storing a cache cluster to generate takeaway information cache data; standardize the data backup of the takeaway information cache data to generate standard takeaway information collection backup data; set up interfaces for the standard takeaway information collection backup data to generate takeaway information collection format conversion data; perform interface integration testing on the takeaway information collection format conversion data to generate a takeaway information collection module to execute takeaway information data collection.

[0029] The present invention ensures the consistency of data through semantic standardization, and the association of geographic data improves the accuracy of takeaway information, making subsequent analysis more reliable. Geographic location-related data makes takeaway information more regional, which helps merchants to make more targeted marketing strategies in specific areas. Geographic location-related data provides a basis for subsequent multi-dimensional analysis, such as making in-depth research on food preferences, delivery time, etc. in specific areas possible. Through entity relationship mapping and association calculation, the degree of association between takeaway information can be more accurately understood, so that data can be processed more finely. Dividing data into strongly associated and weakly associated parts can help better process different data and improve the accuracy and effectiveness of data analysis. According to the classification of association, data can be regulated in a targeted manner, making the data more instructive and practical, and improving the value of subsequent analysis and application. Through knowledge reasoning, the entity relationship mapping map of takeaway information can be enriched to make it more in-depth and broad, providing more useful information for subsequent analysis and application. Uncertainty processing helps to reduce uncertainty in data, improve the credibility of data, and make subsequent decision-making and application more confident. By completing and optimizing the data collected from takeout information, the integrity and accuracy of the data can be improved, making it more suitable for various analysis and application scenarios. Storing data in a cache cluster improves the access speed and efficiency of the data, making the real-time acquisition and processing of takeout information faster. Through backup, standardization and format conversion, the integrity and reliability of the backup data of the takeout information are ensured, and the risk of data loss is reduced. Through interface setting and integration testing, the stability of the takeout information collection module and its interoperability with other systems are guaranteed, making the collection process of takeout information more reliable and smooth. Therefore, the present invention improves the efficiency and quality of takeout information data collection by performing semantic standardization, geographic association, intelligent reasoning and data storage optimization on the data collected from takeout information.

[0030] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for collecting data based on Internet takeaway information of the present invention. In this example, the method for collecting data based on Internet takeaway information includes the following steps:

[0031] Step S1: Acquire food delivery platform information data; perform semantic standardization on the food delivery platform information data to generate a food delivery information semantic standardization data set; perform geographic data association on the food delivery information semantic standardization data set to generate food delivery information geographic location association data;

[0032] In an embodiment of the present invention, information data of the food delivery platform is obtained by using an open interface (API) or crawler technology provided by the food delivery platform. Ensure compliance with relevant laws and regulations and the platform's usage policy. Develop semantic standardization specifications to define the various attributes and fields of food delivery information to ensure data consistency. Clean the acquired food delivery information data, including removing duplicates, processing missing data, processing outliers, etc. Organize the cleaned data according to the semantic standardization specifications to generate a semantically normalized data set. Use the address or longitude and latitude information in the food delivery information to associate with a geographic information service (such as a map API) to obtain specific geographic location information. Associate the geographic location information with the food delivery information data set to generate food delivery information geographic location association data.

[0033] Step S2: Use the geographic location-related data of takeaway information to perform entity relationship mapping on the semantic normalized data set of takeaway information to generate an entity relationship mapping graph of takeaway information; calculate the relevance of takeaway information on the entity relationship mapping graph of takeaway information to obtain a relevance coefficient of takeaway information; compare the relevance coefficient of takeaway information with a preset standard relevance threshold to generate strongly-related takeaway information data and weakly-related takeaway information data; perform data update control on the strongly-related takeaway information data and the weakly-related takeaway information data to generate takeaway information collection control data;

[0034] In an embodiment of the present invention, the data quality is ensured by cleaning, deduplication and standardization of takeaway information. Relationships between entities are established according to different attributes in the takeaway information (such as merchants, dishes, prices, etc.). A graph database or other relational database can be used to store these relationships. The established entity relationship is represented as a graph structure to form a takeaway information entity relationship mapping map. According to business needs and data characteristics, a calculation method for the correlation between takeaway information is defined. Cosine similarity, Jaccard similarity or other similarity measurement methods can be considered. For each pair of takeaway information, its correlation coefficient is calculated. Based on business needs or statistical analysis, a preset standard correlation threshold is set. The calculated correlation coefficient is compared with the threshold, and the takeaway information is classified into two categories: strong correlation and weak correlation. According to the classification results of the previous step, the takeaway information with strong correlation and weak correlation is identified. For the takeaway information with strong correlation and weak correlation, corresponding data updates and adjustments are performed. For example, certain attributes can be added or reduced, prices or recommendation strategies can be adjusted, etc., to generate takeaway information collection and regulation data.

[0035] Step S3: Based on the takeaway information collection and control data, knowledge reasoning is performed on the takeaway information entity relationship mapping graph to generate takeaway information collection reasoning data; uncertainty processing is performed on the takeaway information collection and control data using the takeaway information collection reasoning data to generate takeaway information collection completion data; intelligent collection completion and optimization are performed on the takeaway information collection and control data based on the takeaway information collection completion data and the takeaway information collection inference data to generate takeaway information collection optimization data;

[0036] In an embodiment of the present invention, an entity relationship mapping graph is constructed by using takeaway information collection and regulation data. This can be achieved through a graph database or similar data storage method to ensure that the relationship between data can be effectively represented. A rule engine is used to define and execute knowledge reasoning rules. Rules can be used to infer the relationship between entities and discover potential patterns and laws based on previous experience, domain knowledge and data analysis results. Probabilistic models are used to handle uncertainty in takeaway information collection and regulation data. Tools such as probabilistic graph models and Bayesian networks can be used to model and handle uncertainty, enabling the system to better understand and respond to data changes. Fusion of data from different sources combined with probabilistic inference methods can more accurately estimate the credibility and uncertainty of entity relationships. Machine learning models are used to complete and optimize takeaway information collection and regulation data. This can include using supervised learning, unsupervised learning or semi-supervised learning methods to train models based on existing data, and then use them to predict missing or incomplete information. Use effective feature engineering in machine learning models to improve the performance of the model. Feature engineering can convert data into more useful representations based on domain knowledge and actual conditions. Introduce a feedback loop to continuously adjust and optimize the model based on user feedback and data changes in actual application scenarios to ensure the robustness and adaptability of the model.

[0037] Step S4: Optimize the data collected by takeaway information by storing a cache cluster to generate takeaway information cache data; standardize the data backup of the takeaway information cache data to generate standard takeaway information collection backup data; set up interfaces for the standard takeaway information collection backup data to generate takeaway information collection format conversion data; perform interface integration testing on the takeaway information collection format conversion data to generate a takeaway information collection module to execute takeaway information data collection.

[0038] In the embodiment of the present invention, by selecting a suitable storage solution, such as a distributed cache system (such as Redis, Memcached) or a distributed file system (such as Hadoop HDFS), etc., the requirements of high concurrency, high availability and scalability are met. The optimized data of takeaway information collection is stored in the cache cluster, and data synchronization and update can be performed on demand to ensure the real-time and accuracy of the data. Design a backup strategy to determine the backup frequency, storage location and backup type (full backup, incremental backup, etc.). Standardize the cache data of takeaway information to ensure that the format of the backup data is unified, easy to manage and restore. Design and define the interface specifications for the backup data of takeaway information collection, including data format, field meaning and access method. Develop a data conversion module to convert the standard takeaway information collection backup data into a format that meets the requirements according to the defined interface specifications to ensure data consistency and compatibility. Perform integration testing on the interface to verify whether the data transmission and conversion process meets expectations and ensure the reliability and stability of the interface. Integrate the interface, data conversion module, storage cache cluster and other components into a unified takeaway information collection module. Perform system testing on the entire takeaway information collection module to verify its functions and performance, including the accuracy, stability and performance indicators of data collection.

[0039] Preferably, step S1 comprises the following steps:

[0040] Step S11: using the cloud platform to obtain food delivery platform information data, wherein the food delivery platform information data includes food delivery platform structure data and food delivery platform format data; classifying and identifying the data sources of the food delivery platform structure data and the food delivery platform format data, thereby generating food delivery platform classification list data;

[0041] Step S12: performing data cleaning on the food delivery platform classification list data to generate food delivery platform classification list cleaning data; performing feature extraction on the food delivery platform classification list data to generate food delivery platform feature extraction data; performing data mapping on the food delivery platform feature extraction data to generate a food delivery information feature mapping table;

[0042] Step S13: Filling missing values ​​in the takeaway information feature mapping table to obtain a takeaway information feature-filled dataset; performing semantic standardization on the takeaway information feature-filled dataset to generate a takeaway information semantically normalized dataset;

[0043] Step S14: map-encode the semantically normalized dataset of takeout information using map coding technology to generate a takeout geographic information coding dataset; associate the takeout geographic information coding dataset with geographic data using geographic information technology to generate takeout information geographic location association data.

[0044] The present invention obtains food delivery platform information data, including structure and format data, through a cloud platform, which helps to establish a comprehensive food delivery platform classification list, covering the organizations and data formats of different food delivery platforms. It improves the comprehensiveness and comprehensiveness of food delivery platform data and provides a basis for subsequent data processing. Cleaning data, extracting features, and performing data mapping help to normalize and structure data, providing high-quality data for subsequent analysis and processing. It improves the consistency and availability of data, simplifies the complexity of data, and provides a better basis for further data analysis and mining. Missing value filling and semantic standardization help to process incomplete or non-standard data and improve the integrity and accuracy of data. By filling missing values ​​and standardizing semantics, the data is made more consistent, and errors caused by missing or non-standard data in subsequent analysis are reduced. Map coding and geographic location association associate food delivery information with geographic location, providing support for geospatial analysis and visualization. It makes the data more meaningful, helps to analyze the distribution of food delivery services in different geographic areas, and provides a data basis for geographic information system (GIS) analysis.

[0045] In an embodiment of the present invention, by utilizing the API or tool of the cloud platform, the structural data and format data are obtained through the interface provided by the takeaway platform. The acquired data is classified and identified by using machine learning or data mining technology to identify the organization data and format data of the takeaway platform. According to the results of the classification identification, the classification list data of the takeaway platform is generated, including the organization data and format data. The classification list data is cleaned, and duplicates, missing values ​​and abnormal data are processed. The feature engineering technology is used to extract key features from the cleaned data for subsequent analysis. The extracted features are mapped to the corresponding data table to generate a takeaway information feature mapping table. The missing values ​​in the takeaway information feature mapping table are filled using an interpolation method or a machine learning algorithm. Standardization rules are formulated to semantically standardize the takeaway information feature filling data set to ensure data consistency. The semantically normalized data set is map-encoded using geographic information system (GIS) technology, and the address information is converted into geographic coordinates. Using geographic information technology, the map-encoded data set is associated with geographic information to generate takeaway information geographic location associated data.

[0046] Preferably, step S2 comprises the following steps:

[0047] Step S21: performing information entity recognition on the semantically normalized data set of takeaway information to generate takeaway entity information data, wherein the takeaway entity information data includes takeaway restaurant data and takeaway dish data; performing time series merging of the takeaway restaurant data, takeaway dish data, and takeaway information geographic location associated data to generate takeaway information entity recognition data;

[0048] Step S22: extracting relations from the takeaway information entity recognition data to generate takeaway information entity association data; performing takeaway semantic mapping based on the takeaway information entity association data to generate a takeaway information entity relationship mapping graph;

[0049] Step S23: constructing a graph database for the takeaway information entity relationship mapping graph using graph database technology to generate a relational graph database; using the relational graph database to perform relational storage on the takeaway information entity relationship mapping graph to generate a takeaway relationship graph database to store data;

[0050] Step S24: Calculate the takeout information relevance of the data stored in the takeout relationship graph database using the takeout information relevance calculation formula to obtain the takeout information relevance coefficient; compare the takeout information relevance coefficient with the preset standard relevance threshold, and when the takeout information relevance coefficient is greater than or equal to the preset standard relevance threshold, mark the data stored in the takeout relationship graph database as strongly-related takeout information data; when the takeout information relevance coefficient is less than the preset standard relevance threshold, mark the data stored in the takeout relationship graph database as weakly-related takeout information data;

[0051] Step S25: performing data update and regulation on the strongly associated takeaway information data and the weakly associated takeaway information data to generate takeaway information collection and regulation data.

[0052] The present invention performs entity recognition through a semantically normalized data set to identify entity information such as takeaway restaurants and dishes. Combined with geographic location data, takeaway entity recognition data is created, which may include restaurant, dish information and their geographic locations, which helps to better understand the spatial and temporal distribution of the takeaway business. Extracting relationships from entity recognition data may help to discover the correlation between restaurants and dishes, geographic locations, etc. Based on these relationship data, a takeaway information entity relationship mapping map is established, which helps to understand the semantic association between various entities. Using graph database technology, the entity relationship mapping map is converted into a relational graph database, and this database structure is more suitable for processing complex associations between entities. Storing entity relationship graph data in a relational graph database is conducive to more efficient storage and query of entity relationships. By calculating the takeaway information correlation coefficient, the data stored in the takeaway relationship graph database is evaluated, which helps to understand the degree of correlation between entities. According to the preset standard correlation threshold, marking the data as strongly associated or weakly associated may help to identify and distinguish takeaway information with different degrees of association. Updating and adjusting the strongly and weakly correlated takeout information data may include information completion, error correction, or data quality improvement, which will help optimize the collection and management of takeout information.

[0053] As an example of the present invention, refer to Figure 2As shown, in this example, step S2 includes:

[0054] Step S21: performing information entity recognition on the semantically normalized data set of takeaway information to generate takeaway entity information data, wherein the takeaway entity information data includes takeaway restaurant data and takeaway dish data; performing time series merging of the takeaway restaurant data, takeaway dish data, and takeaway information geographic location associated data to generate takeaway information entity recognition data;

[0055] In an embodiment of the present invention, by selecting or constructing a semantically normalized data set, it may include information, menus, user comments and other data on the takeaway platform. Clean the data, remove duplicates, missing values ​​and noise data, and ensure data quality. Use natural language processing (NLP) technology for text mining and entity recognition. Use NER technology to identify takeaway entities, such as restaurant names, dishes, etc., and classify and organize them. If the data contains geographic location information, a geographic information system (GIS) or a corresponding geographic location processing tool may be used to associate the geographic location with restaurant / dish information. Combined with timestamps or time information, the restaurant, dish data and geographic location data are merged in chronological order to create takeaway information entity recognition data. The sorted entity information data is stored in a suitable database, which may use a relational database or a graph database, and a suitable storage method is selected according to the characteristics of the data. Design a suitable index structure to improve data query efficiency, especially for entity association and geographic location retrieval. Design an automated process to process large-scale data to ensure that entity recognition and association processing can be effectively applied to the entire data set. After the implementation is completed, data verification and debugging are performed to ensure the quality and accuracy of the generated takeaway information entity recognition data.

[0056] Step S22: extracting relations from the takeaway information entity recognition data to generate takeaway information entity association data; performing takeaway semantic mapping based on the takeaway information entity association data to generate a takeaway information entity relationship mapping graph;

[0057] In an embodiment of the present invention, by using a dependency syntactic analysis tool, the dependency relationship between each word in the sentence is analyzed to find the grammatical dependency relationship between entities. A machine learning or deep learning algorithm is used to train a model to extract the relationship between entities. Existing relationship extraction models such as RE-BERT, OpenIE, etc. can be used. On the basis of entity recognition, the relationship between entities is annotated, such as the inclusion relationship between restaurants and dishes, the ordering relationship between users and restaurants, etc. The annotated relationship is integrated with the entity recognition data to generate takeaway information entity association data. Word embedding technology such as Word2Vec and GloVe is used to map the vocabulary to a high-dimensional space to capture the semantic relationship between vocabulary. If there is an external knowledge graph, the knowledge graph embedding algorithm such as TransE and TransR can be used to embed and learn entity relationships. Entity association data is stored using a graph database and an entity relationship graph is established. Databases such as Neo4j can easily represent entities and their relationships. Use visualization tools such as Gephi or D3.js to visualize the graph to better understand the relationship between entities. Design an automated process to handle the large amount of data generated by relationship extraction and mapping to ensure the reliability and efficiency of the process. Verify the generated entity association data and relationship graph to ensure the accuracy of relationship extraction and mapping.

[0058] Step S23: constructing a graph database for the takeaway information entity relationship mapping graph using graph database technology to generate a relational graph database; using the relational graph database to perform relational storage on the takeaway information entity relationship mapping graph to generate a takeaway relationship graph database to store data;

[0059] In the embodiment of the present invention, by selecting a graph database that suits the requirements, common graph databases include Neo4j, Amazon Neptune, ArangoDB, etc. In this scenario, Neo4j is a common choice because it focuses on the graph data model and provides powerful graph database functions. Design the data model of the graph database to ensure that the entity-relationship mapping graph of the takeaway information can be accurately represented. In Neo4j, the data model is usually composed of nodes and relationships. For example, the following node types can be defined:

[0060] Restaurant node; dish node; user node. Define the following relationship types: containment relationship (restaurant contains dishes); ordering relationship (user orders restaurant). Import the generated takeaway information entity relationship mapping graph data into the graph database. Neo4j supports the Cypher query language. You can use LOAD CSV or other appropriate import tools to import data from files or other data sources into the database. In order to improve query performance, create indexes according to actual needs. Neo4j supports creating indexes on nodes and relationships for faster data retrieval. Use the query language of the graph database (such as Cypher) to execute queries and explore the takeaway information entity relationship mapping graph. The graph can be intuitively displayed and analyzed through the visualization tools provided by the graph database or other visualization libraries (such as D3.js).

[0061] Step S24: Calculate the takeout information relevance of the data stored in the takeout relationship graph database using the takeout information relevance calculation formula to obtain the takeout information relevance coefficient; compare the takeout information relevance coefficient with the preset standard relevance threshold, and when the takeout information relevance coefficient is greater than or equal to the preset standard relevance threshold, mark the data stored in the takeout relationship graph database as strongly-related takeout information data; when the takeout information relevance coefficient is less than the preset standard relevance threshold, mark the data stored in the takeout relationship graph database as weakly-related takeout information data;

[0062] In an embodiment of the present invention, a correlation calculation formula is designed, which should take into account the attributes of the nodes and relationships in the takeout relationship graph database, as well as the connections between them. This formula can be customized according to actual needs and business logic. For each data in the takeout relationship graph database, the correlation coefficient is calculated using the defined correlation calculation formula. A preset standard correlation threshold is set according to business needs and actual conditions. This threshold will be used to determine whether the correlation of the takeout information meets the standard of strong correlation. The calculated correlation coefficient is compared with the preset standard correlation threshold, and then the data stored in the takeout relationship graph database is marked as strongly correlated or weakly correlated. The above-mentioned correlation calculation and marking process is applied to all data in the takeout relationship graph database to ensure the consistency and accuracy of the data.

[0063] Step S25: performing data update and regulation on the strongly associated takeaway information data and the weakly associated takeaway information data to generate takeaway information collection and regulation data.

[0064] In the embodiment of the present invention, by determining the update control rules, a set of rules are formulated according to the business requirements and system goals to determine the specific update method of the strongly associated and weakly associated takeaway information data. This may include the update frequency, data processing, extraction of key information, etc. Design an algorithm to implement the update control rules. This may involve querying, filtering, aggregating and transforming the data in the database. The specific update algorithm depends on the business logic and the database system used. According to the designed update algorithm, the actual data update control is performed on the strongly associated and weakly associated takeaway information data. This may include: updating attribute values: updating the attribute values ​​of the takeaway information data according to the rules to ensure that they reflect the latest information. Adding additional information: adding additional information or tags to enhance the richness of the takeaway information. Deleting redundant information: deleting or marking no longer needed information according to the rules to ensure the cleanliness of the data. Performing association operations: performing association operations to associate the strongly associated and weakly associated takeaway information with other related data. While performing data update control, takeaway information collection control data is generated. This can be a log recording the update operation, which contains information such as the time of each update, the data status before and after the update, etc. This helps monitor system performance and ensure data traceability, generating takeaway information collection and regulation data.

[0065] Preferably, the formula for calculating the relevance of takeaway information in step S24 is as follows:

[0066]

[0067] In the formula, R(u,i) represents the relevance of user u to takeaway item i, and w k Expressed as the weights of different takeaway features, f k (u,i) represents the similarity coefficient between user u and food delivery item i on the kth feature, T represents the change of food delivery association over time, h(t) represents the influence coefficient of association at time t, h j It is represented as the coefficient of variation of takeout association with spatial position, a represents the influence weight of regulating spatial variables, J represents the upper limit of the number of spatial variables, and K represents the upper limit of takeout characteristics.

[0068] The present invention analyzes and integrates a production optimization target formula, and adjusts the relevance of user u to takeaway item i in the formula, which is a value between 0 and 1, indicating the relevance of the user to the takeaway item. The logical function is used in the formula To map the association degree to the range of 0 to 1. Different takeaway features may have different effects on the user's association degree. By adjusting the weight, the contribution of each feature to the association degree can be controlled. The similarity coefficient between user u and takeaway item i on the kth feature. This coefficient can be calculated based on the feature vector or feature space of the user and the takeaway item, and is used to measure their similarity on this feature. The association degree of takeaway information may change over time. By introducing time-varying data, the impact of time on the association degree can be considered. The influence coefficient on the association degree at time t. This function is used to adjust the weight of time on the association degree. Different function forms can be designed according to actual needs, such as exponential decay function or linear decay function. The association degree of takeaway information may be affected by spatial position. By introducing spatial variation coefficient, the impact of spatial position on the association degree can be considered. Adjust the influence weight α of spatial variables. This parameter is used to adjust the contribution degree of spatial variables to the association degree. It can be adjusted according to actual needs. The upper limit of the number of spatial variables J. By limiting the number of spatial variables, the influence degree of spatial variables on the association degree can be controlled. By limiting the number of takeaway features, the influence degree of takeaway features on the association degree can be controlled. When using the conventional takeaway information association calculation formula in the art, the association between user u and takeaway item i can be obtained. By applying the takeaway information association calculation formula provided by the present invention, the association between user u and takeaway item i can be calculated more accurately. The formula comprehensively considers factors such as user characteristics, takeaway characteristics, time changes, and spatial location, so as to calculate the user's association with the takeaway item. By adjusting the value of the parameters, the contribution of different factors to the association can be flexibly controlled, so as to obtain an association calculation result that meets actual needs. In this way, personalized recommendations and rankings can be provided to users, improving the user experience and commercial benefits of the takeaway platform.

[0069] Preferably, step S25 comprises the following steps:

[0070] Step S251: when it is confirmed that the data stored in the takeout relationship graph database is strongly associated takeout information data, restaurant takeout information is collected based on the strongly associated takeout information data to obtain restaurant takeout menu information data and restaurant business hours information data; timing time is set based on the restaurant business hours information data, thereby generating a strongly associated timing collection timestamp;

[0071] Step S252: Real-time monitoring of restaurant takeaway menu information data is performed according to the strongly associated timed collection timestamp to generate strongly associated restaurant takeaway real-time monitoring data; dynamic data capture is performed on the strongly associated restaurant takeaway real-time monitoring data to generate strongly associated restaurant dynamic change data and strongly associated restaurant static change data;

[0072] Step S253: incrementally updating the dynamic change data of strongly associated restaurants by using the incremental update technology to generate the incremental update data of strongly associated restaurants; using the incremental update data of strongly associated restaurants to package and push the static change data of strongly associated restaurants to generate the information collection and control data of strongly associated restaurants;

[0073] Step S254: when it is confirmed that the data stored in the takeout relationship graph database is strongly associated takeout information data, takeout after-sales information is collected based on the weakly associated takeout information data to obtain restaurant takeout review data and restaurant takeout rating data; interaction frequency analysis is performed on the restaurant takeout review data and the restaurant takeout rating data to generate restaurant takeout interaction frequency data;

[0074] Step S255: performing a periodic information collection timestamp setting based on the restaurant takeaway interaction frequency data to generate a weakly correlated timed collection timestamp; performing a change comparison on the restaurant takeaway interaction frequency data according to the weakly correlated timed collection timestamp to generate restaurant takeaway interaction comparison verification data;

[0075] Step S256: Use the support vector machine algorithm to perform information prediction on the restaurant takeaway interaction comparison and verification data, thereby generating weakly correlated restaurant information collection and regulation data; perform data fusion on the strongly correlated restaurant information collection and regulation data and the weakly correlated restaurant information collection and regulation data, thereby generating takeaway information collection and regulation data.

[0076] The present invention collects restaurant takeout information, including menu information and business hours information, based on the strongly associated takeout information data when confirming that the data stored in the takeout relationship graph database is strongly associated takeout information. Ensure that the most relevant and accurate data is used for subsequent processing, and improve the quality and practicality of takeout information. Use the timed acquisition timestamp to monitor the restaurant takeout menu information in real time, and capture dynamic changes and static changes data. Provide real-time restaurant takeout information monitoring, allowing the system to adapt to changes in takeout information more quickly, thereby enhancing the real-time performance of the system. Incrementally update the dynamically changing data through the incremental update technology, generate incremental update data, which is used to package and push static change data, and generate information collection and control data. Reduce the overhead of data update, improve efficiency, and ensure the consistency of static change data. Collect takeout after-sales information based on weakly associated takeout information data, including comment data and rating data; analyze the interaction frequency. Provide feedback on the quality of restaurant takeout service, which can be used to improve and optimize services, and the interaction frequency analysis helps to understand the degree of interaction between users and takeout information. Set a regular information collection timestamp according to the interaction frequency data, and perform a change comparison to generate interaction comparison verification data. Increased sensitivity to changes in takeout information, allowing the system to capture changes in user interaction behavior more timely. Information prediction is performed on interactive comparison verification data through the support vector machine algorithm to generate weakly correlated restaurant information collection and regulation data. Using machine learning algorithms for prediction can more accurately understand user behavior and trends, thereby better adjusting and optimizing takeout information collection strategies. Data fusion is performed on strongly correlated and weakly correlated restaurant information collection and regulation data. Comprehensive use of strongly correlated and weakly correlated data provides more comprehensive and accurate takeout information, enhancing the system's comprehensive capabilities and decision-making level.

[0077] As an example of the present invention, refer to Figure 3 As shown, in this example, step S25 includes:

[0078] Step S251: when it is confirmed that the data stored in the takeout relationship graph database is strongly associated takeout information data, restaurant takeout information is collected based on the strongly associated takeout information data to obtain restaurant takeout menu information data and restaurant business hours information data; timing time is set based on the restaurant business hours information data, thereby generating a strongly associated timing collection timestamp;

[0079] In an embodiment of the present invention, by confirming the data structure and content stored in the takeout relationship graph database, it is ensured that the database contains restaurant takeout information. To verify the existence and consistency of strongly associated takeout information data, a data review and verification process may be required. Design a program or script to extract strongly associated restaurant takeout information data from the database. Implement a data extraction process to obtain restaurant takeout menu information and restaurant business hours information. Clean and preprocess the extracted data to ensure the accuracy and completeness of the data. Data format conversion or standardization may be required to meet the format requirements within the system. Set a scheduled collection strategy based on restaurant business hours information. Create or configure a scheduled task to ensure that the latest takeout information data is extracted from the database at a specified time. Implement logical or programmatic operations to generate a strongly associated scheduled collection timestamp. Ensure that the timestamp matches the time sensitivity of the takeout information so that it can accurately reflect the time of the most recent data collection.

[0080] Step S252: Real-time monitoring of restaurant takeaway menu information data is performed according to the strongly associated timed collection timestamp to generate strongly associated restaurant takeaway real-time monitoring data; dynamic data capture is performed on the strongly associated restaurant takeaway real-time monitoring data to generate strongly associated restaurant dynamic change data and strongly associated restaurant static change data;

[0081] In an embodiment of the present invention, a real-time monitoring system is established to regularly check the update of restaurant takeaway menu information data. A timed acquisition timestamp is used for comparison to determine whether there is new takeaway menu information data. When there is an update, the corresponding data capture and processing process is triggered. According to the trigger of the real-time monitoring system, new takeaway menu information data is collected. The collected data is organized into strongly associated restaurant takeaway real-time monitoring data. The accuracy and timeliness of the real-time monitoring data are ensured. The dynamic changes of takeaway menu information data are captured using a comparison algorithm or a difference detection technology. New, updated or deleted menu items are identified, and related change information is recorded. This may include changes in dish prices, additions of new dishes or deletions of existing dishes, etc. Strongly associated restaurant dynamic change data is generated based on the dynamically captured change information. The data format may include information such as timestamp, dish ID, change type (new, updated, deleted), etc. If necessary, data related to static changes is generated, such as basic restaurant information, changes in cuisine, etc. It is ensured that static change data is correlated with dynamic change data to provide a complete view of takeaway menu information changes.

[0082] Step S253: incrementally updating the dynamic change data of strongly associated restaurants by using the incremental update technology to generate the incremental update data of strongly associated restaurants; using the incremental update data of strongly associated restaurants to package and push the static change data of strongly associated restaurants to generate the information collection and control data of strongly associated restaurants;

[0083] In an embodiment of the present invention, by using appropriate incremental update technologies, such as incremental extraction, Change Data Capture (CDC), etc., the dynamically changing data of strongly associated restaurants is incrementally updated. This can reduce the overhead of data transmission and processing, and only the changed data is transmitted and processed. Based on the incremental update technology, the changed parts of the dynamically changing data are identified. These changed parts are organized into the incremental update data of strongly associated restaurants. The data format may include timestamp, change type, dish ID, etc. A data packaging strategy is formulated to package the incremental update data and static change data of strongly associated restaurants. Consider using standard data formats, such as JSON or XML, to facilitate data transmission and parsing. Configure a push channel to transmit the packaged data to the target system. Data push can be performed using message queues, HTTP interfaces, etc. After the target system receives the data, it is parsed and processed. According to the incremental update data, the corresponding dynamic change and static change information is updated. Generate strongly associated restaurant information collection and control data, including updated menu information, change time, etc. Implement a data verification mechanism to ensure the integrity and correctness of the pushed data. For possible error situations, a rollback mechanism is designed to ensure the consistency of system data and generate strongly associated restaurant information collection and control data.

[0084] Step S254: when it is confirmed that the data stored in the takeout relationship graph database is strongly associated takeout information data, takeout after-sales information is collected based on the weakly associated takeout information data to obtain restaurant takeout review data and restaurant takeout rating data; interaction frequency analysis is performed on the restaurant takeout review data and the restaurant takeout rating data to generate restaurant takeout interaction frequency data;

[0085] In an embodiment of the present invention, relevant data such as order information, user comments, and ratings are screened from weakly correlated takeaway information data. The required information is extracted from the takeaway relationship graph database using a data extraction tool or script. User comments and rating data are extracted from the collected takeaway information data. Natural language processing (NLP) technology can be used to process the comment text and extract key information, such as sentiment analysis and topic analysis. The restaurant takeaway comment data is analyzed to understand the user's evaluation and feedback on the takeaway. The rating data is used to evaluate user satisfaction. The interaction frequency is counted, including the frequency of user comments, the frequency of restaurant replies, etc. The noise in the comment data is cleaned and processed, such as spelling errors, invalid characters, etc. The comment data is preprocessed, such as word segmentation, stop word removal, stemming, etc., for subsequent analysis. An interaction frequency model is established based on the comment data and the rating data. Machine learning algorithms such as regression analysis and cluster analysis can be used to predict the interaction frequency of restaurant takeaways. Visualization tools such as charts and dashboards are used to display the analysis results of restaurant takeaway comment data, rating data, and interaction frequency data. Through intuitive charts, it helps business decision makers better understand user interactions and generate restaurant takeaway interaction frequency data.

[0086] Step S255: performing a periodic information collection timestamp setting based on the restaurant takeaway interaction frequency data to generate a weakly correlated timed collection timestamp; performing a change comparison on the restaurant takeaway interaction frequency data according to the weakly correlated timed collection timestamp to generate restaurant takeaway interaction comparison verification data;

[0087] In an embodiment of the present invention, by determining the time interval for regular information collection, such as daily, weekly or monthly. Generate a weakly correlated timed collection timestamp to record the time point of each data collection. Develop a data collection plan to ensure that the takeaway interaction frequency data is collected regularly according to the set timestamp. Use automated tools, scripts or data pipelines to perform data collection tasks. Generate a weakly correlated timed collection timestamp based on the regular information collection timestamp. Associate the timestamp with the takeaway interaction frequency data of each data collection to establish a relationship between time and data. Store the collected takeaway interaction frequency data in a suitable database for subsequent analysis and comparison. Ensure the consistency of the data storage structure and format for subsequent data processing. Compare two or more consecutive takeaway interaction frequency data based on the weakly correlated timed collection timestamp. Calculate the change ratio to determine the change trend of the interaction frequency data. Generate restaurant takeaway interaction comparison verification data based on the results of the change comparison. The comparison data can be displayed in the form of tables, charts, etc., so that business decision makers can more intuitively understand the changes in the interaction frequency.

[0088] Step S256: Use the support vector machine algorithm to perform information prediction on the restaurant takeaway interaction comparison and verification data, thereby generating weakly correlated restaurant information collection and regulation data; perform data fusion on the strongly correlated restaurant information collection and regulation data and the weakly correlated restaurant information collection and regulation data, thereby generating takeaway information collection and regulation data.

[0089] In an embodiment of the present invention, weakly associated restaurant information collection and control data is used as a training set, including timestamps, interaction frequency comparison verification data and other relevant features. The data set is divided into a training set and a test set. Feature selection and transformation are performed on the data to ensure that the input features are suitable for the SVM model. Time-related features, historical interaction frequency data, etc. can be considered. The support vector machine algorithm is used to train the model on the training set. Select appropriate hyperparameters such as kernel functions and regularization parameters. Use the test set to evaluate the model performance, considering indicators such as accuracy and recall. Adjust the model parameters to improve performance. Use the trained SVM model to predict the restaurant takeaway interaction comparison verification data to generate weakly associated restaurant information collection and control data. Integrate the strongly associated restaurant information collection and control data and the weakly associated restaurant information collection and control data. Clean the integrated data to handle missing values, outliers, etc. Merge the two parts of data according to common identifiers (such as restaurant ID and timestamp). Further process the merged data to ensure that the data format is consistent and subsequent analysis can be performed. Perform a comprehensive analysis on the merged data, considering the weights and influencing factors of the strongly associated and weakly associated data. Generate takeaway information collection and control data based on the analysis results, including possible optimization suggestions, adjustment of interaction strategies, etc. Verify the generated takeaway information collection and control data to ensure its rationality and feasibility.

[0090] Preferably, step S3 comprises the following steps:

[0091] Step S31: perform entity linking on the takeaway information entity relationship mapping graph based on the takeaway information collection control data to generate a takeaway information collection entity relationship graph; perform knowledge reasoning on the takeaway information collection entity relationship graph based on a logical reasoning algorithm to generate takeaway information collection reasoning data;

[0092] Step S32: using the takeaway information collection inference data to perform data collection logic filling on the takeaway information collection control data to generate takeaway information collection filling data; performing information association on the takeaway information collection filling data to generate takeaway information collection associated data; performing inference verification on the takeaway information collection associated data to generate takeaway information collection inference data;

[0093] Step S33: Probabilize the inference data of takeaway information collection by using a probabilistic inference method to generate takeaway information collection inference probability data; perform uncertainty processing on the takeaway information collection inference probability data to generate takeaway information collection completion data;

[0094] Step S34: intelligently complete and optimize the takeaway information collection and regulation data based on the takeaway information collection completion data and the takeaway information collection inference data to generate takeaway information collection optimization data.

[0095] The present invention generates an entity relationship map of takeaway information through entity linking, which can more clearly understand the relationship between takeaway information and improve the efficiency of information organization and management. Using logical reasoning algorithms to perform knowledge reasoning on entity relationship maps helps to discover potential associations and rules, and improve the ability to understand and analyze takeaway information. Using reasoning data to logically fill in the control data, make up for possible missing or incomplete information, and improve the integrity and accuracy of the data. By filling in the data through association, a more complete data set is formed, which helps to identify deeper relationships between takeaway information and improve the dimension and richness of the data. Inferring and verifying the associated data can infer unknown information and provide more reliable basis for decision-making. Through probabilistic reasoning methods, probability is given to inferred data to improve the credibility and interpretability of the data. Dealing with uncertainty, generating more robust and reliable data, and improving the quality and availability of data. Using collected and completed data and inferred data to intelligently complete and optimize the control data, the accuracy and practicality of the data are improved.

[0096] As an example of the present invention, refer to Figure 4 As shown, in this example, step S3 includes:

[0097] Step S31: perform entity linking on the takeaway information entity relationship mapping graph based on the takeaway information collection control data to generate a takeaway information collection entity relationship graph; perform knowledge reasoning on the takeaway information collection entity relationship graph based on a logical reasoning algorithm to generate takeaway information collection reasoning data;

[0098] In the embodiment of the present invention, data quality and consistency are ensured by collecting and regulating data for takeout information collection. Entities, such as restaurants, dishes, addresses, etc., are extracted from the takeout information. The extracted entities are standardized to ensure that the same entities have a consistent representation. Entity matching is performed using an external knowledge base (such as an encyclopedia, a commercial database, etc.) to link entities in the takeout information to corresponding entities in the knowledge base. Relationships between entities, such as the location of the restaurant, the classification of dishes, etc., are extracted from the takeout information. An entity relationship graph is constructed to represent entities and relationships in the form of a graph. The entity relationship graph is represented in a logically inferable form, such as using triples to represent entity relationships. Logical rules are designed to describe the logical relationships between entities, such as "A is the upstream node of B", "If C occurs, then D will also occur", etc. The rules are executed using a logical reasoning algorithm to infer new knowledge and fill in possible missing relationships in the graph. New relationships and information are extracted from the execution results of the logical reasoning algorithm. The reasoning results are formatted into a data structure for subsequent processing, such as triples, graph updates, etc., to generate takeout information collection reasoning data.

[0099] Step S32: using the takeaway information collection inference data to perform data collection logic filling on the takeaway information collection control data to generate takeaway information collection filling data; performing information association on the takeaway information collection filling data to generate takeaway information collection associated data; performing inference verification on the takeaway information collection associated data to generate takeaway information collection inference data;

[0100] In an embodiment of the present invention, the takeaway information collection reasoning data generated in step S31 is used. The takeaway information collection control data is analyzed to determine the missing data or incomplete information. Based on the reasoning data, the identified missing data is logically filled to fill the missing information. The filled data is associated with the original data to ensure the consistency of the filled data with the original data. The filled data and the original data are integrated to generate a complete data set to form the takeaway information collection related data. The takeaway information collection related data is analyzed to verify the consistency and logical relationship between the filled data and the original data. Verification methods (such as logical verification, statistical analysis, etc.) are used to verify the accuracy and logical rationality of the filled data. Possible abnormal data or inference results are detected for further investigation and processing. The final inference data is extracted from the verification results and data completion status obtained in the inference verification process. The verified inference data is formatted into a suitable data structure to facilitate storage and subsequent analysis. According to the feedback of the inference results, the logic and relevance of the filled data are evaluated, and the data filling and verification process is improved as needed.

[0101] Step S33: Probabilize the inference data of takeaway information collection by using a probabilistic inference method to generate takeaway information collection inference probability data; perform uncertainty processing on the takeaway information collection inference probability data to generate takeaway information collection completion data;

[0102] In the embodiment of the present invention, by selecting an appropriate probability model, such as a Bayesian network, a probability graph model, etc., according to data characteristics and reasoning requirements. The takeaway information collection inference data is converted into a probability form to represent the possibility distribution of each variable, and the dependency between different variables is considered. If a probability model is used, parameter learning is performed to learn the parameters of the model through existing data. The probability data is analyzed to understand the probability distribution of each variable and identify the source of uncertainty. An uncertainty model is established, and factors such as randomness and measurement error are considered, and these factors are introduced into the probability distribution to form more comprehensive uncertainty probability data. The probability fusion method is used to integrate uncertainties from different sources to ensure that the final probability data can accurately reflect the uncertainty of takeaway information collection. The probability model is used to infer unknown data to generate takeaway information collection inference probability data. A suitable probability threshold is set, and the confidence level of the inference result is judged according to the threshold to determine whether to complete the data. According to the inference probability data, a suitable completion method is selected, which can be a probability-based interpolation, fusion, etc. method to generate takeaway information collection completion data. Considering the transmission of uncertainty between different variables, a model is established to describe the transmission path of uncertainty. Set the rules for uncertainty transmission and determine how to transmit and accumulate uncertainty based on the model and data characteristics. During the reasoning process, ensure that uncertainty information can be effectively transmitted so that the final takeaway information collection and completion data can reflect the comprehensive uncertainty situation.

[0103] Step S34: intelligently complete and optimize the takeaway information collection and regulation data based on the takeaway information collection completion data and the takeaway information collection inference data to generate takeaway information collection optimization data.

[0104] In the embodiment of the present invention, the data quality is ensured by cleaning the takeaway information collection and control data, processing outliers, missing values, etc. The takeaway information collection and completion data, the takeaway information collection and inference data and the original control data are integrated to establish a comprehensive data set. Use machine learning algorithms, such as regression, decision tree, random forest, etc., to train the model for intelligent completion based on the existing data features. Select appropriate features, which may include the takeaway order volume, time period, geographical location, etc., to improve the completion accuracy of the model. Use the existing takeaway information collection and completion data as a training set, and use the validation set to tune the model parameters to ensure the generalization performance of the model. Consider using optimization algorithms, such as genetic algorithms, simulated annealing, etc., to optimize the takeaway information collection and control data. Define the optimization objective function, which may include minimizing delivery time, maximizing delivery efficiency, etc., determined according to business needs. Adjust the parameters of the optimization algorithm according to actual conditions to obtain better optimization results. Establish an intelligent decision model, and integrate the takeaway information collection and control data, intelligent completion data and optimization data into the decision model. Build a real-time decision-making system that can respond to changes in takeout information in real time, perform scheduling and decision optimization, and generate takeout information collection optimization data.

[0105] Preferably, step S33 includes the following steps:

[0106] Step S331: Probabilizing the takeaway information collection and inference data through a Bayesian network to generate takeaway information collection and inference probability data;

[0107] Step S332: quantify the uncertainty of the takeaway information collection and reasoning probability data using the data accuracy quantification formula to generate collection and reasoning probability confidence data; compare the collection and reasoning probability confidence data with the preset standard confidence threshold, and when the collection and reasoning probability confidence data is greater than or equal to the preset standard confidence threshold, generate collection and reasoning normal data; when the collection and reasoning probability confidence data is greater than or equal to the preset standard confidence threshold, generate collection and reasoning abnormal data;

[0108] Step S333: performing abnormal data detection on the collected reasoning abnormal data to generate collected reasoning abnormal detection data; performing data filling on the collected reasoning abnormal detection data until the collected reasoning normal data is generated;

[0109] Step S334: Perform a posteriori inference on the collected and inferred normal data based on the probability model to generate a posteriori data for the collection of takeaway information; perform information collection correction on the takeaway information collection inference data based on the a posteriori data for the collection of takeaway information to generate complete data for the collection of takeaway information.

[0110] The present invention converts the inference data collected from takeaway information into probability data through a Bayesian network, so as to more comprehensively understand the uncertainty and possibility of the data. Improving the expressiveness of the data helps to more accurately quantify the inference results of the takeaway information. The uncertainty of the inference probability data is quantified using the data accuracy quantification formula, and compared with the preset standard confidence threshold. Through the determination of the confidence, information with high credibility in data accuracy can be filtered out, which helps to improve the accuracy of subsequent analysis. Anomaly detection is performed on the inference data that does not meet the standard confidence threshold, and data filling is performed to make it close to normal data. Through the detection and processing of abnormal data, the quality of the collected data is ensured to be higher, and the influence of uncertainty and anomalies on subsequent analysis is reduced. Posterior inference is performed based on the probability model to generate posterior data of the takeaway information collection, and use it to correct the inference data. Through posterior inference, the true situation of the takeaway information can be better understood, and the accuracy and completeness of the collected information can be improved by correcting the inference data.

[0111] In an embodiment of the present invention, the takeaway information collection inference data is converted into a probability distribution by using a Bayesian network model. The Bayesian inference algorithm is used to calculate the takeaway information collection inference probability data in combination with prior knowledge and observation data. Formulate a data precision quantification formula, which may involve statistical methods, error analysis, etc. Input the probability data into the precision quantification formula to generate the collection inference probability confidence data. Compare the collection inference probability confidence data with the preset standard confidence threshold. Design an abnormal data detection algorithm, which may use statistical methods, machine learning models or professional field knowledge. According to the abnormal detection results, the abnormal data is processed, which may include eliminating, replacing or filling missing values. Repeat the abnormal detection and processing until the collection inference normal data is generated. Use a probability model for posterior inference, which may include Bayesian inference, Markov chain Monte Carlo method, etc. Generate takeaway information collection posterior data, which represents a more accurate estimate of the actual situation. According to the posterior data, the inferred data is corrected, which may include adjusting weights, correcting errors, etc., to generate takeaway information collection completion data.

[0112] Preferably, the data accuracy quantification formula in step S332 is as follows:

[0113]

[0114] Where P(X|Y) is the probability of event X given observation data Y, P(Y|X) is the probability of observation data Y given event X, P(X) is the probability of event X before observation data Y, P(Y) is the probability of observation data Y, and μ is the data precision quantification anomaly adjustment value.

[0115] The present invention analyzes and integrates a data precision quantification formula, the principle of which is based on the relationship between conditional probability and joint probability. It uses observed data to update the estimate of the probability of an event. Specifically, the Bayesian formula shows that the posterior probability is proportional to the product of the prior probability and the likelihood, and is normalized by dividing by the marginal probability to obtain the posterior probability. Among them, the prior probability P(X) represents the estimate of the probability of an event before any data is observed. It provides prior basic knowledge or beliefs. By introducing the prior probability, previous experience or knowledge can be integrated into the probability reasoning, thereby affecting the calculation of the posterior probability. The likelihood P(Y|X) represents the probability of observing specific data given the occurrence of an event. It measures the degree of support of the observed data for the occurrence of the event. Through the likelihood, the estimate of the probability of an event can be updated based on the information of the observed data. The marginal probability P(Y) represents the probability of observing specific data. It is obtained by comprehensively considering the observed data and all possible events. The marginal probability is used in the Bayesian formula to normalize the posterior probability to ensure that the sum of the posterior probabilities is 1. The data precision quantification abnormal adjustment value μ is used to correct errors and deviations caused by the complexity and non-ideality of the actual system. It can correct the difference between the theoretical assumptions in the formula and the actual system, improve the accuracy and reliability of data precision quantification, and more accurately generate the probability P(X|Y) of event X given the observation data Y. At the same time, the data precision quantification abnormal adjustment value in the formula, the probability of occurrence of observation data Y and other parameters can be adjusted according to the actual situation, so as to adapt to different data precision quantification scenarios, and improve the applicability and flexibility of the algorithm. When using the conventional data precision quantification formula in the art, the probability of event X given the observation data Y can be obtained. By applying the data precision quantification formula provided by the present invention, the probability of event X given the observation data Y can be more accurately calculated. By combining prior probability, likelihood and marginal probability, the Bayesian formula provides a method for updating and adjusting the estimation of the probability of event occurrence based on observation data. It allows more accurate and reliable probabilistic reasoning and decision-making through the interaction between previous beliefs and new observation data. The interaction between these parameters produces a more accurate quantitative formula, which provides uncertainty quantification and confidence assessment for the probability data of takeaway information collection reasoning.

[0116] Preferably, step S4 comprises the following steps:

[0117] Step S41: Perform data sharding storage on the takeaway information collection optimization data through distributed storage technology to generate a takeaway information sharding storage cluster; perform index structure design on the takeaway information sharding storage cluster to generate takeaway information index structure data; perform cache optimization on the takeaway information index structure data through distributed cache technology to generate takeaway information cache data;

[0118] Step S42: performing load balancing analysis on the takeaway information cache data to generate takeaway information load balancing data; using the takeaway information load balancing data to perform data backup on the takeaway information cache data to generate takeaway information backup data; performing data standardization on the takeaway information backup data to generate standard takeaway information collection backup data, wherein data standardization includes data cleaning, data missing value filling and data standardization;

[0119] Step S43: setting interface specifications for the standard takeaway information collection backup data based on a preset API design method to generate takeaway information API data; performing format conversion on the standard takeaway information collection backup data using the takeaway information API data to generate takeaway information collection format conversion data;

[0120] Step S44: Perform security verification settings on the takeaway information collection format conversion data to generate takeaway information security authentication data; perform permission control on the takeaway information collection format conversion data to generate takeaway information permission control data; import the takeaway information security authentication data and the takeaway information permission control data into the takeaway information API for interface integration testing, thereby generating a takeaway information collection module to execute takeaway information data collection.

[0121] The present invention can realize horizontal expansion and efficient retrieval of data through distributed storage through data sharding storage and index structure design, and adapt to the processing requirements of large-scale data. Through caching technology, frequently accessed data can be stored in memory, reducing the access pressure on the storage system and accelerating data reading. Load balancing ensures that system resources are evenly distributed and avoids overload of a single node. Data backup can cope with hardware failure or data loss and ensure data integrity. Data standardization includes cleaning, filling missing values ​​and standardization, which helps to eliminate errors and inconsistencies in data and improve the reliability of subsequent processing and analysis. Preset API design and specifications can make the system interface clearer and easier to use, and help the collaboration between different modules. Through format conversion, data can be converted into the format required by different systems, which promotes the circulation and sharing of data. Security verification and permission control ensure that only authenticated users can access sensitive data, effectively preventing potential security risks. Integration testing can verify the collaboration between various components and ensure the stability and consistency of the system in practical applications.

[0122] In the embodiment of the present invention, by selecting an appropriate distributed storage system, such as Hadoop Distributed FileSystem (HDFS), Amazon S3, etc., data sharding is performed on the takeaway information to ensure uniform data distribution. A takeaway information sharding storage cluster is established to achieve high availability and scalability through distributed storage technology. A suitable index structure, such as B-tree, Hash index, etc., is designed according to the query requirements of the takeaway information. The performance and storage efficiency of the index structure are ensured. Distributed cache systems, such as Redis, Memcached, etc., are used. The takeaway information index structure data is cached to accelerate data access. Appropriate cache strategies, such as LRU (least recently used) or TTL (time to live) are implemented. Load balancing technologies, such as Nginx, HAProxy, etc., are used to distribute takeaway information requests to different server nodes. Load balancing analysis is performed to ensure load balance of each node. Load balancing data is backed up to ensure system reliability. Data backup can be performed by master-slave replication, redundant storage, etc. Data cleaning is performed to handle abnormal or erroneous data. Missing data values ​​are filled to ensure data integrity. Data standardization is performed to make the data format consistent. Define the interface specifications of the takeout information API based on the preset API design method. Use standards such as RESTful or GraphQL to develop the API design. Use the designed API specifications to convert the standard takeout information collection backup data. You can use data conversion tools or write custom scripts to achieve format conversion. Perform security verification on the takeout information collection format conversion data to ensure that only authorized users can access it. Use secure transmission protocols such as HTTPS to prevent data from being maliciously intercepted. Implement permission control to limit access to the takeout information collection format conversion data. Use authentication mechanisms such as OAuth and JWT to ensure the permissions of legitimate users. Import the takeout information security authentication data and permission control data into the takeout information API. Perform interface integration testing to verify the functionality and performance of the API. Ensure that the takeout information collection module can perform the takeout information data collection task normally.

[0123] In this specification, a data collection system based on Internet takeaway information is provided, which is used to execute the above-mentioned data collection method based on Internet takeaway information. The data collection system based on Internet takeaway information includes:

[0124] The geographic association module is used to obtain the information data of the food delivery platform; perform semantic standardization on the information data of the food delivery platform to generate a semantically normalized data set of food delivery information; perform geographic data association on the semantically normalized data set of food delivery information to generate geographic location association data of food delivery information;

[0125] The information association judgment module is used to use the geographical location association data of takeout information to perform entity relationship mapping on the semantic normalized data set of takeout information to generate an entity relationship mapping map of takeout information; calculate the association degree of takeout information on the entity relationship mapping map of takeout information to obtain the association coefficient of takeout information; compare the association coefficient of takeout information with a preset standard association threshold to generate strongly associated takeout information data and weakly associated takeout information data; perform data update regulation on the strongly associated takeout information data and the weakly associated takeout information data to generate takeout information collection regulation data;

[0126] The information missing inference module is used to perform knowledge reasoning on the takeaway information entity relationship mapping graph based on the takeaway information collection and control data to generate takeaway information collection reasoning data; use the takeaway information collection reasoning data to process the uncertainty of the takeaway information collection and control data to generate takeaway information collection completion data; based on the takeaway information collection completion data and the takeaway information collection inference data, the takeaway information collection control data is intelligently completed and optimized to generate takeaway information collection optimization data;

[0127] The interface integration module is used to store and cache clusters for takeout information collection optimization data to generate takeout information cache data; to standardize data backup of takeout information cache data to generate standard takeout information collection backup data; to set interfaces for standard takeout information collection backup data to generate takeout information collection format conversion data; to perform interface integration testing on takeout information collection format conversion data, thereby generating a takeout information collection module to execute takeout information data collection.

[0128] The beneficial effect of the present invention is that semantic standardization of takeaway platform information data helps unify data formats and improve data consistency and comprehensibility. By associating geographic data, takeaway information can be associated with specific geographic locations, which is helpful for subsequent geographic information analysis. Generating a takeaway information entity relationship mapping map helps understand the relationship between takeaway information, so as to better perform subsequent analysis and reasoning. By calculating the degree of association, the degree of association between takeaway information can be quantified, which helps to identify information with high correlation. Knowledge reasoning on the takeaway information entity relationship mapping map helps to discover potential relationships and laws, and improve the depth of data analysis. Dealing with the uncertainty of takeaway information collection and regulation data helps to improve the credibility and stability of data. Using reasoning data to complete and optimize information collection and regulation data can improve the integrity and accuracy of information. Generating takeaway information cache data helps to improve data access speed and system responsiveness. The generation of standard takeaway information collection backup data helps data security and recoverability. By converting data in the takeaway information collection format, data interaction and integration with different systems or platforms can be achieved. Through steps such as standardization, association and intelligent completion, the quality and consistency of takeaway information are improved, thereby enhancing the credibility of data. Through the steps of entity relationship mapping, knowledge reasoning, etc., the relationship between takeout information can be analyzed more deeply and more information can be mined. Through the steps of caching and format conversion, the performance and efficiency of the system can be improved, and the data access and processing process can be accelerated. Therefore, the present invention improves the efficiency and quality of takeout information data collection by performing semantic standardization, geographic association, intelligent reasoning and data storage optimization on the data collected from takeout information.

[0129] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0130] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A data collection method based on Internet takeaway information, characterized in that: The following steps are involved: Step S1: Acquire food delivery platform information data; perform semantic standardization on the food delivery platform information data to generate a semantic standardization data set of food delivery information; Perform geographic data association on the semantically normalized dataset of takeaway information to generate geographic location association data of takeaway information; Step S2: Use the geographic location associated data of takeout information to perform entity relationship mapping on the semantic normalized data set of takeout information to generate an entity relationship mapping graph of takeout information; calculate the takeout information relevance on the takeout information entity relationship mapping graph to obtain the takeout information relevance coefficient, wherein the takeout information relevance calculation formula is as follows: In the formula, Represented as user For takeaway items The correlation degree, Represented as the weights of different takeaway features, Represented as user and takeaway items In the The similarity coefficient on the features, It is represented by the change of takeaway relevance over time. Expressed as time The influence coefficient on the correlation degree, It is expressed as the coefficient of variation of takeaway association with spatial location, Expressed as the influence weight of the adjustment space variable, Expressed as an upper limit on the number of spatial variables, It is expressed as the upper limit of the takeaway feature; Compare the takeaway information correlation coefficient with a preset standard correlation threshold to generate strongly correlated takeaway information data and weakly correlated takeaway information data; Data updating and regulating are performed on the strongly associated takeaway information data and the weakly associated takeaway information data to generate takeaway information collection and regulation data, wherein the data updating and regulating are performed on the strongly associated takeaway information data and the weakly associated takeaway information data including the following steps: Step S251: when it is confirmed that the data stored in the takeout relationship graph database is strongly associated takeout information data, restaurant takeout information is collected based on the strongly associated takeout information data to obtain restaurant takeout menu information data and restaurant business hours information data; timing time is set based on the restaurant business hours information data, thereby generating a strongly associated timing collection timestamp; Step S252: Real-time monitoring of restaurant takeaway menu information data is performed according to the strongly associated timed collection timestamp to generate strongly associated restaurant takeaway real-time monitoring data; dynamic data capture is performed on the strongly associated restaurant takeaway real-time monitoring data to generate strongly associated restaurant dynamic change data and strongly associated restaurant static change data; Step S253: incrementally updating the dynamic change data of strongly associated restaurants by using the incremental update technology to generate the incremental update data of strongly associated restaurants; using the incremental update data of strongly associated restaurants to package and push the static change data of strongly associated restaurants to generate the information collection and control data of strongly associated restaurants; Step S254: when it is confirmed that the data stored in the takeout relationship graph database is strongly associated takeout information data, takeout after-sales information is collected based on the weakly associated takeout information data to obtain restaurant takeout review data and restaurant takeout rating data; interaction frequency analysis is performed on the restaurant takeout review data and the restaurant takeout rating data to generate restaurant takeout interaction frequency data; Step S255: performing a periodic information collection timestamp setting based on the restaurant takeaway interaction frequency data to generate a weakly correlated timed collection timestamp; performing a change comparison on the restaurant takeaway interaction frequency data according to the weakly correlated timed collection timestamp to generate restaurant takeaway interaction comparison verification data; Step S256: performing information prediction on the restaurant takeaway interactive comparison verification data by using a support vector machine algorithm, thereby generating weakly correlated restaurant information collection and regulation data; performing data fusion on the strongly correlated restaurant information collection and regulation data and the weakly correlated restaurant information collection and regulation data, thereby generating takeaway information collection and regulation data; Step S3: Based on the takeaway information collection and control data, knowledge reasoning is performed on the takeaway information entity relationship mapping graph to generate takeaway information collection reasoning data; uncertainty processing is performed on the takeaway information collection and control data using the takeaway information collection reasoning data to generate takeaway information collection completion data; intelligent collection completion and optimization are performed on the takeaway information collection and control data according to the takeaway information collection completion data and the takeaway information collection inference data to generate takeaway information collection optimization data; Step S3 includes the following steps: Step S31: perform entity linking on the takeaway information entity relationship mapping graph based on the takeaway information collection control data to generate a takeaway information collection entity relationship graph; perform knowledge reasoning on the takeaway information collection entity relationship graph based on a logical reasoning algorithm to generate takeaway information collection reasoning data; Step S32: using the takeaway information collection inference data to perform data collection logic filling on the takeaway information collection control data to generate takeaway information collection filling data; performing information association on the takeaway information collection filling data to generate takeaway information collection associated data; performing inference verification on the takeaway information collection associated data to generate takeaway information collection inference data; Step S33: Probabilize the inference data of takeaway information collection by using a probabilistic inference method to generate takeaway information collection inference probability data; perform uncertainty processing on the takeaway information collection inference probability data to generate takeaway information collection completion data; Step S34: intelligently complete and optimize the takeaway information collection and control data according to the takeaway information collection and completion data and the takeaway information collection and inference data, and generate takeaway information collection and optimization data; Step S4: Optimize the data collected by takeaway information by storing a cache cluster to generate takeaway information cache data; standardize the data backup of the takeaway information cache data to generate standard takeaway information collection backup data; set up interfaces for the standard takeaway information collection backup data to generate takeaway information collection format conversion data; perform interface integration testing on the takeaway information collection format conversion data to generate a takeaway information collection module to execute takeaway information data collection.

2. The data collection method based on Internet takeaway information according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: using the cloud platform to obtain food delivery platform information data, wherein the food delivery platform information data includes food delivery platform structure data and food delivery platform format data; classifying and identifying the data sources of the food delivery platform structure data and the food delivery platform format data, thereby generating food delivery platform classification list data; Step S12: performing data cleaning on the food delivery platform classification list data to generate food delivery platform classification list cleaning data; performing feature extraction on the food delivery platform classification list data to generate food delivery platform feature extraction data; performing data mapping on the food delivery platform feature extraction data to generate a food delivery information feature mapping table; Step S13: Filling missing values ​​in the takeaway information feature mapping table to obtain a takeaway information feature-filled dataset; performing semantic standardization on the takeaway information feature-filled dataset to generate a takeaway information semantically normalized dataset; Step S14: map-encode the semantically normalized dataset of takeout information using map coding technology to generate a takeout geographic information coding dataset; associate the takeout geographic information coding dataset with geographic data using geographic information technology to generate takeout information geographic location association data.

3. The data collection method based on Internet takeaway information according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing information entity recognition on the semantically normalized data set of takeaway information to generate takeaway entity information data, wherein the takeaway entity information data includes takeaway restaurant data and takeaway dish data; performing time series merging of the takeaway restaurant data, takeaway dish data, and takeaway information geographic location associated data to generate takeaway information entity recognition data; Step S22: extracting relations from the takeaway information entity recognition data to generate takeaway information entity association data; performing takeaway semantic mapping based on the takeaway information entity association data to generate a takeaway information entity relationship mapping graph; Step S23: constructing a graph database for the takeaway information entity relationship mapping graph using graph database technology to generate a relational graph database; using the relational graph database to perform relational storage on the takeaway information entity relationship mapping graph to generate a takeaway relationship graph database to store data; Step S24: Calculate the takeout information relevance of the data stored in the takeout relationship graph database using the takeout information relevance calculation formula to obtain the takeout information relevance coefficient; compare the takeout information relevance coefficient with the preset standard relevance threshold, and when the takeout information relevance coefficient is greater than or equal to the preset standard relevance threshold, mark the data stored in the takeout relationship graph database as strongly-related takeout information data; when the takeout information relevance coefficient is less than the preset standard relevance threshold, mark the data stored in the takeout relationship graph database as weakly-related takeout information data; Step S25: performing data update and regulation on the strongly associated takeaway information data and the weakly associated takeaway information data to generate takeaway information collection and regulation data.

4. The data collection method based on Internet takeaway information according to claim 1 is characterized in that: Step S33 includes the following steps: Step S331: Probabilizing the takeaway information collection and inference data through a Bayesian network to generate takeaway information collection and inference probability data; Step S332: quantify the uncertainty of the takeaway information collection and reasoning probability data using the data accuracy quantification formula to generate collection and reasoning probability confidence data; compare the collection and reasoning probability confidence data with the preset standard confidence threshold, and when the collection and reasoning probability confidence data is greater than or equal to the preset standard confidence threshold, generate collection and reasoning normal data; when the collection and reasoning probability confidence data is greater than or equal to the preset standard confidence threshold, generate collection and reasoning abnormal data; Step S333: performing abnormal data detection on the collected reasoning abnormal data to generate collected reasoning abnormal detection data; performing data filling on the collected reasoning abnormal detection data until the collected reasoning normal data is generated; Step S334: Perform a posteriori inference on the collected and inferred normal data based on the probability model to generate a posteriori data for the collection of takeaway information; perform information collection correction on the takeaway information collection inference data based on the a posteriori data for the collection of takeaway information to generate complete data for the collection of takeaway information.

5. The data collection method based on Internet takeaway information according to claim 4 is characterized in that: The data accuracy quantification formula in step S332 is as follows: In the formula, Represented as a given observation data Cases, events The probability of occurrence, Indicated as an event In the event of a The probability of occurrence, Represented as an event In the observation data The probability before it appears, Represented as observed data The probability of occurrence, Expressed as a quantitative anomaly adjustment value for data precision.

6. The method for collecting data based on Internet takeaway information according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Perform data sharding storage on the takeaway information collection optimization data through distributed storage technology to generate a takeaway information sharding storage cluster; perform index structure design on the takeaway information sharding storage cluster to generate takeaway information index structure data; perform cache optimization on the takeaway information index structure data through distributed cache technology to generate takeaway information cache data; Step S42: performing load balancing analysis on the takeaway information cache data to generate takeaway information load balancing data; using the takeaway information load balancing data to perform data backup on the takeaway information cache data to generate takeaway information backup data; performing data standardization on the takeaway information backup data to generate standard takeaway information collection backup data, wherein data standardization includes data cleaning, data missing value filling and data standardization; Step S43: setting interface specifications for the standard takeaway information collection backup data based on a preset API design method to generate takeaway information API data; performing format conversion on the standard takeaway information collection backup data using the takeaway information API data to generate takeaway information collection format conversion data; Step S44: Perform security verification settings on the takeaway information collection format conversion data to generate takeaway information security authentication data; perform permission control on the takeaway information collection format conversion data to generate takeaway information permission control data; import the takeaway information security authentication data and the takeaway information permission control data into the takeaway information API for interface integration testing, thereby generating a takeaway information collection module to execute takeaway information data collection.

7. A data collection method system based on Internet takeaway information, characterized in that: Used to execute the data collection method based on Internet takeaway information as claimed in claim 1, the data collection system based on Internet takeaway information comprises: The geographic association module is used to obtain the information data of the food delivery platform; perform semantic standardization on the information data of the food delivery platform to generate a semantically normalized data set of food delivery information; perform geographic data association on the semantically normalized data set of food delivery information to generate geographic location association data of food delivery information; The information association judgment module is used to use the geographical location association data of takeout information to perform entity relationship mapping on the semantic normalized data set of takeout information to generate an entity relationship mapping map of takeout information; calculate the association degree of takeout information on the entity relationship mapping map of takeout information to obtain the association coefficient of takeout information; compare the association coefficient of takeout information with a preset standard association threshold to generate strongly associated takeout information data and weakly associated takeout information data; perform data update regulation on the strongly associated takeout information data and the weakly associated takeout information data to generate takeout information collection regulation data; The information missing inference module is used to perform knowledge reasoning on the takeaway information entity relationship mapping graph based on the takeaway information collection and control data to generate takeaway information collection reasoning data; use the takeaway information collection reasoning data to process the uncertainty of the takeaway information collection and control data to generate takeaway information collection completion data; based on the takeaway information collection completion data and the takeaway information collection inference data, the takeaway information collection control data is intelligently completed and optimized to generate takeaway information collection optimization data; The interface integration module is used to store and cache clusters for takeout information collection optimization data to generate takeout information cache data; to standardize data backup of takeout information cache data to generate standard takeout information collection backup data; to set interfaces for standard takeout information collection backup data to generate takeout information collection format conversion data; to perform interface integration testing on takeout information collection format conversion data, thereby generating a takeout information collection module to execute takeout information data collection.

Images