Plant polysaccharide data query method and device, electronic equipment and storage medium

Abstract

The invention provides a plant polysaccharide data query method and device, electronic equipment and a storage medium, and relates to the technical field of biologication.The method comprises the steps that a target keyword is determined; querying each data table in a plant polysaccharide database based on the target keyword to obtain a data record corresponding to the target keyword; the plant polysaccharide database stores the plant polysaccharide data based on the data table; the data table comprises a plant information table, a polysaccharide information table and an experiment data table; the plant polysaccharide data comprises a polysaccharide name, a molecular structure, biological activity, a plant source and an extraction mode; the plant information table and the polysaccharide information table are associated based on plant names corresponding to plant sources; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name. According to the method and the device provided by the invention, systematic integration of the plant functional polysaccharide data is realized, and the utilization rate of the plant functional polysaccharide data is improved.

Description

Technical Field

[0001] The present invention relates to the field of biotechnology, and in particular to a plant polysaccharide data query method, device, electronic equipment and storage medium. Background Art

[0002] In recent years, with the advancement of medicine and biotechnology, plant functional polysaccharides have gradually attracted widespread attention as important bioactive ingredients. Many plants are rich in functional polysaccharides, and these substances show promising application prospects in antioxidant, anti-tumor, and immune regulation. Currently, researchers have systematically studied the extraction, chemical structure, and bioactivity of some plant functional polysaccharides, and have achieved certain results in the fields of drug development and health foods.

[0003] However, existing information and data on plant functional polysaccharides are often scattered across various literature and research reports. Statistics and analysis of this information remain insufficient, lacking both professionalism and specificity. These limitations limit researchers' systematic understanding and application of plant polysaccharides, hindering R&D efficiency and innovation in related fields.

[0004] Therefore, how to systematically integrate plant functional polysaccharide data and improve the utilization rate of plant functional polysaccharide data has become a technical problem that needs to be urgently solved in the industry. Summary of the Invention

[0005] The present invention provides a plant polysaccharide data query method, device, electronic device and storage medium, which are used to solve the technical problem of how to systematically integrate plant functional polysaccharide data and improve the utilization rate of plant functional polysaccharide data.

[0006] The present invention provides a plant polysaccharide data query method, comprising: Determining target keywords; the target keywords are determined based on at least one of the polysaccharide name, molecular structure, plant origin, biological activity, and extraction method of the plant polysaccharide to be queried; Querying each data table in the plant polysaccharide database based on the target keyword to obtain data records corresponding to the target keyword; Among them, the plant polysaccharide database stores plant polysaccharide data based on a data table; the data table includes a plant information table, a polysaccharide information table and an experimental data table; the plant polysaccharide data includes the polysaccharide name, molecular structure, biological activity, plant source and extraction method; the plant information table and the polysaccharide information table are associated based on the plant name corresponding to the plant source; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name.

[0007] In some embodiments, the plant polysaccharide database is established based on the following steps: Obtaining the plant polysaccharide data based on public databases and / or plant polysaccharide experimental data; Generate a plant information table based on the plant sources in each plant polysaccharide data, as well as the plant families and plant names corresponding to the plant sources; Generate a polysaccharide information table based on the polysaccharide name, molecular structure, biological activity, plant source, and plant name corresponding to the plant source in each plant polysaccharide data; Generate an experimental data table based on the polysaccharide name, extraction method, and experimental process and experimental parameters corresponding to the extraction method in each plant polysaccharide data; establishing a first inter-table relationship between the polysaccharide information table and the plant information table based on the plant name; Establishing a second inter-table relationship between the polysaccharide information table and the experimental data table based on the polysaccharide name; The plant polysaccharide database is established based on the plant information table, the polysaccharide information table, the experimental data table, the first inter-table relationship, and the second inter-table relationship.

[0008] In some embodiments, obtaining the plant polysaccharide data based on a public database and / or plant polysaccharide experimental data includes: Based on the public database, obtain multiple plant polysaccharide research documents; Perform word segmentation on each plant polysaccharide research document, and determine the high-frequency word segmentation in each plant polysaccharide research document and the text position of the high-frequency word segmentation based on the frequency of occurrence of each word segmentation in the corresponding plant polysaccharide research document; the high-frequency word segmentation is a word segmentation whose frequency of occurrence is greater than a preset frequency; Based on the high-frequency segmented words and the text positions of the high-frequency segmented words, information is extracted from various plant polysaccharide research documents to obtain plant polysaccharide data in each plant polysaccharide research document.

[0009] In some embodiments, after performing word segmentation on each plant polysaccharide research document and determining the high-frequency word segmentation in each plant polysaccharide research document based on the frequency of occurrence of each word segmentation in the corresponding plant polysaccharide research document, and the text position of the high-frequency word segmentation, the method further includes: Determine the high-frequency segmented words as candidate target keywords and add them to the keyword library; The keyword library is used to determine target keywords based on user selection input.

[0010] In some embodiments, the plant polysaccharide database is updated based on the following steps: Determine the data update time interval; Based on the data update time interval, obtaining new plant polysaccharide research literature and new plant polysaccharide experimental data from various public databases; Performing text analysis on the newly added plant polysaccharide research literature to obtain first newly added plant polysaccharide data; Processing the newly added plant polysaccharide experimental data to obtain second newly added plant polysaccharide data; The first newly added plant polysaccharide data and the second newly added plant polysaccharide data are stored in the plant polysaccharide database.

[0011] In some embodiments, determining the target keyword includes: Get initial keywords; Inputting the initial keyword into a query recommendation model to obtain a plurality of recommended keywords output by the query recommendation model; determining the initial keyword and the recommended keyword as target keywords; Among them, the query recommendation model is trained based on sample initial keywords and sample recommended keywords corresponding to the sample initial keywords; the sample initial keywords are historical initial keywords input by each user, and the sample recommended keywords are determined based on the query history records corresponding to the historical initial keywords.

[0012] In some embodiments, the method further comprises: Deploying the plant polysaccharide database to a cloud platform; Alternatively, the plant polysaccharide database is deployed to a distributed system; the distributed system includes edge computing nodes and central computing nodes; multiple plant polysaccharide data obtained by each edge computing node are stored in each edge settlement node; based on the central computing node, the plant information table, polysaccharide information table and experimental data table in each edge computing node are summarized.

[0013] The present invention provides a plant polysaccharide data query device, comprising: a determination unit, configured to determine a target keyword; the target keyword being determined based on at least one of the polysaccharide name, molecular structure, plant origin, biological activity, and extraction method of the plant polysaccharide to be queried; A query unit, configured to query each data table in the plant polysaccharide database based on the target keyword to obtain data records corresponding to the target keyword; Among them, the plant polysaccharide database stores plant polysaccharide data based on a data table; the data table includes a plant information table, a polysaccharide information table and an experimental data table; the plant polysaccharide data includes the polysaccharide name, molecular structure, biological activity, plant source and extraction method; the plant information table and the polysaccharide information table are associated based on the plant name corresponding to the plant source; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name.

[0014] The present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the plant polysaccharide data query method is implemented when the processor executes the computer program.

[0015] The present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the plant polysaccharide data query method is implemented.

[0016] The plant polysaccharide data query method, device, electronic device and storage medium provided by the present invention determine target keywords; query each data table in the plant polysaccharide database based on the target keywords to obtain data records corresponding to the target keywords; because the plant polysaccharide data includes multidimensional data such as polysaccharide name, molecular structure, biological activity, plant source and extraction method, the plant polysaccharide data can be stored comprehensively and systematically, and can be conveniently queried using the target keywords; because the plant polysaccharide database stores the plant polysaccharide data through data tables, the data tables include a plant information table, a polysaccharide information table and an experimental data table; the plant information table and the polysaccharide information table are associated based on the plant name corresponding to the plant source; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name; structured storage of plant polysaccharide data is achieved, which facilitates the storage and query of plant polysaccharide data; systematic integration of plant functional polysaccharide data is achieved, and the utilization rate of plant functional polysaccharide data is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1It is a schematic flow chart of the plant polysaccharide data query method provided by the present invention.

[0020] Figure 2 It is a structural schematic diagram of the plant polysaccharide data query device provided by the present invention.

[0021] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only 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 ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first," "second," and the like in the present invention are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps, units, or modules is not necessarily limited to those steps, units, or modules that are explicitly listed, but may include other steps, units, or modules that are not explicitly listed or that are inherent to these processes, methods, products, or apparatuses.

[0024] Plant polysaccharides, also known as plant polysaccharides, are a class of macromolecular compounds found in plants, composed of multiple monosaccharide molecules linked by glycosidic bonds. Several public databases exist that collect information on plant polysaccharides, such as the Carbohydrate-Active Enzymes Database, PubChem (Organic Small Molecule Bioactivity Data), the Natural Product Database, and related research findings. However, data on plant polysaccharides in these databases and research findings is fragmented, lacks systematicity, is infrequently updated, and lacks sufficient research on the correlation between the bioactivity of polysaccharides and their chemical structure.

[0025] In order to solve the shortcomings of related technologies, Figure 1 This is a flow chart of the plant polysaccharide data query method provided by the present invention, such as Figure 1As shown, the method includes step 110 and step 120.

[0026] Step 110 , determining target keywords; the target keywords are determined based on at least one of the polysaccharide name, molecular structure, plant origin, biological activity, and extraction method of the plant polysaccharide to be queried.

[0027] Specifically, the plant polysaccharide data query method provided in the embodiments of the present invention is implemented by a plant polysaccharide data query device. The device can be implemented by software, such as a plant polysaccharide data query program, or by hardware, such as a processor, computer, or server that executes the plant polysaccharide data query method.

[0028] The plant polysaccharide to be queried is the plant polysaccharide to be queried. The target keyword is used to query the plant polysaccharide to be queried. The target keyword can be determined based on at least one of the polysaccharide name, molecular structure, plant origin, biological activity, and extraction method of the plant polysaccharide to be queried.

[0029] The term "polysaccharide name" refers to the name of the plant polysaccharide, which may include the Chinese name, English name, full name, or abbreviation. Molecular structure refers to information such as the type of monosaccharide units, glycosidic bond type, branching structure, molecular weight, and chain length within the plant polysaccharide. Plant source refers to the plant from which the plant polysaccharide can be extracted. Biological activity refers to the effects or effects of plant polysaccharides on organisms (such as the human body), including antioxidant, anti-aging, enzyme inhibition, biostimulation, immunomodulatory, and anti-inflammatory properties. Extraction method refers to the method used to extract the plant polysaccharide from the plant, including solvent extraction, ultrasonic extraction, and enzymatic hydrolysis.

[0030] Step 120: query each data table in the plant polysaccharide database based on the target keyword to obtain data records corresponding to the target keyword; wherein the plant polysaccharide database stores plant polysaccharide data based on the data table; the data table includes a plant information table, a polysaccharide information table and an experimental data table; the plant polysaccharide data includes the polysaccharide name, molecular structure, biological activity, plant source and extraction method; the plant information table and the polysaccharide information table are associated based on the plant name corresponding to the plant source; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name.

[0031] Specifically, a large amount of plant polysaccharide data can be collected in advance. These plant polysaccharide data include at least the polysaccharide name, molecular structure, biological activity, plant source and extraction method. A plant polysaccharide database can be set up to store the plant polysaccharide data. Three data tables can be set up in the plant polysaccharide database, namely the plant information table, the polysaccharide information table and the experimental data table. The plant information table is mainly used to store relevant information of the plant, which may include the plant name, plant family, Latin name, etc. The polysaccharide information table is mainly used to store relevant information of the plant polysaccharide, which may include the polysaccharide name, plant source, molecular structure, biological activity and extraction method, etc. The experimental data table is mainly used to store relevant information of the plant polysaccharide extraction method, which may include monosaccharide composition, extraction method and experimental conditions (temperature, humidity and enzyme type), etc.

[0032] The plant information table and the polysaccharide information table can be linked using the plant name as a foreign key; the polysaccharide information table and the experimental data table can be linked using the polysaccharide name as a foreign key. This allows for establishing relationships between the three tables. Generally, the plant information table and the polysaccharide information table can have a one-to-many relationship, meaning a single plant may contain multiple polysaccharides; and the polysaccharide information table and the experimental data table can have a one-to-many relationship, meaning a single plant polysaccharide can have experimental conditions corresponding to multiple extraction methods. Relational modeling can accommodate complex query requirements.

[0033] Based on this, we can match target keywords with fields in various data tables within the plant polysaccharide database, querying each table to ultimately obtain data records matching the target keywords. For example, the plant polysaccharide database dynamically generates SQL statements to filter database records based on conditional joins. This data record can be a single record in a single table or related records across three tables. These data records represent structured storage of plant polysaccharide data.

[0034] The plant polysaccharide data query method provided by the embodiment of the present invention determines the target keyword; based on the target keyword, each data table in the plant polysaccharide database is queried to obtain the data record corresponding to the target keyword; since the plant polysaccharide data includes multidimensional data such as polysaccharide name, molecular structure, biological activity, plant source and extraction method, the plant polysaccharide data can be stored comprehensively and systematically, and can be conveniently queried using the target keyword; since the plant polysaccharide database stores the plant polysaccharide data through data tables, the data tables include a plant information table, a polysaccharide information table and an experimental data table; the plant information table and the polysaccharide information table are associated based on the plant name corresponding to the plant source; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name; structured storage of plant polysaccharide data is achieved, which facilitates the storage and query of plant polysaccharide data; systematic integration of plant functional polysaccharide data is achieved, and the utilization rate of plant functional polysaccharide data is improved.

[0035] It should be noted that each embodiment of the present invention can be freely combined, the order can be changed, or it can be executed separately, and does not need to rely on or depend on a fixed execution order.

[0036] In some embodiments, the plant polysaccharide database is established based on the following steps: Obtain plant polysaccharide data based on public databases and / or plant polysaccharide experimental data; Generate a plant information table based on the plant sources in each plant polysaccharide data, as well as the plant families and plant names corresponding to the plant sources; Generate a polysaccharide information table based on the polysaccharide name, molecular structure, biological activity, plant source, and plant name corresponding to the plant source in each plant polysaccharide data; Generate an experimental data table based on the polysaccharide name, extraction method, and experimental process and experimental parameters corresponding to the extraction method in the data of each plant polysaccharide; Establishing a first inter-table relationship between the polysaccharide information table and the plant information table based on the plant name; Establishing a second inter-table relationship between the polysaccharide information table and the experimental data table based on the polysaccharide name; A plant polysaccharide database is established based on the plant information table, the polysaccharide information table, the experimental data table, the first inter-table relationship and the second inter-table relationship.

[0037] Specifically, plant polysaccharide data exists in standard documents, phytochemical textbooks, research papers, and other literature. Plant polysaccharide data can be obtained through literature mining and laboratory research. Literature mining primarily involves extracting relevant literature from existing public databases and performing text parsing on these documents to obtain plant polysaccharide data. Laboratory research primarily involves obtaining plant polysaccharide data from existing experimental reports or data.

[0038] A plant information table can be generated using the plant source, the corresponding plant family, and the plant name in each plant polysaccharide data as the main fields. A polysaccharide information table can be generated using the polysaccharide name, molecular structure, biological activity, plant source, and the corresponding plant name in each plant polysaccharide data as the main fields. An experimental data table can be generated using the polysaccharide name, extraction method, and the corresponding experimental process and experimental parameters in each plant polysaccharide data as the main fields.

[0039] Inter-table relationships refer to the associations between data tables, which can be established using foreign keys. For example, you can use the plant name as the foreign key to establish a first inter-table relationship between the polysaccharide information table and the plant information table. You can also use the polysaccharide name as the foreign key to establish a second inter-table relationship between the polysaccharide information table and the experimental data table.

[0040] Finally, a plant polysaccharide database is established based on the plant information table, the polysaccharide information table, the experimental data table, the first inter-table relationship and the second inter-table relationship. The plant polysaccharide database can be implemented using the MySQL database management system.

[0041] The plant polysaccharide data query method provided in an embodiment of the present invention constructs a plant polysaccharide database through a plant information table, a polysaccharide information table, an experimental data table, a first inter-table relationship and a second inter-table relationship, thereby realizing structured storage of plant polysaccharide data and facilitating the storage and query of plant polysaccharide data.

[0042] In some embodiments, obtaining plant polysaccharide data based on public databases and / or plant polysaccharide experimental data includes: Based on public databases, obtain multiple plant polysaccharide research papers; Perform word segmentation on each plant polysaccharide research literature, and determine the high-frequency word segmentation and the text position of each high-frequency word segmentation in each plant polysaccharide research literature based on the frequency of each word segmentation in the corresponding plant polysaccharide research literature; high-frequency word segmentation refers to the word segmentation whose frequency of occurrence is greater than the preset frequency; Based on high-frequency segmentation words and the text positions of high-frequency segmentation words, information extraction is performed in various plant polysaccharide research documents to obtain the plant polysaccharide data in each plant polysaccharide research document.

[0043] Specifically, multiple plant polysaccharide research papers can be obtained from public databases, such as the KEGG database, the CABI plant database, and the PubChem database. After collecting the plant polysaccharide research papers, they can be preprocessed, including removing irrelevant content, removing stop words, and ensuring that each paper is divided into paragraphs or chapters to facilitate subsequent analysis of the specific location of each word in the text.

[0044] Perform word segmentation on each plant polysaccharide research literature. The purpose of word segmentation is to convert the text from a long string of characters into smaller units that can be understood and processed by machines, so as to facilitate subsequent text analysis and word frequency statistics and other tasks. The frequency of occurrence of each word in the corresponding plant polysaccharide research literature can be determined by word frequency statistics or word frequency-inverse document frequency (TF-IDF) statistics. Words with a frequency greater than the preset frequency are determined as high-frequency words. These high-frequency words may be closely related to the polysaccharide name, molecular structure, plant origin, biological activity and extraction method of plant polysaccharides, such as "antioxidant" and "immunomodulatory". The preset frequency can be set as needed. Determine the text position of the high-frequency word by regular expression positioning or position annotation.

[0045] According to the high-frequency segmented words and the text position of the high-frequency segmented words, information is extracted from various plant polysaccharide research documents to obtain the plant polysaccharide data in each plant polysaccharide research document.

[0046] In the above process, optical character recognition (OCR) can be used to process the chart information in the plant polysaccharide research literature to obtain editable text. Natural language processing tools can be used to perform word segmentation and word frequency statistics on the text, such as scripts written in Python.

[0047] The plant polysaccharide data query method provided by the embodiment of the present invention processes the plant polysaccharide research literature in the public database, and can obtain plant polysaccharide data more comprehensively.

[0048] In some embodiments, after performing word segmentation on each plant polysaccharide research document and determining the high-frequency word segmentation and the text position of the high-frequency word segmentation in each plant polysaccharide research document based on the frequency of occurrence of each word segmentation in the corresponding plant polysaccharide research document, the method further includes: Identify high-frequency segmented words as candidate target keywords and add them to the keyword library; The keyword library is used to determine target keywords based on user selection input.

[0049] Specifically, an embodiment of the present invention further provides a method for dynamically generating keywords, wherein high-frequency segmented words from the latest plant polysaccharide research literature in a public database can be used as candidate target keywords and added to a keyword library to achieve dynamic updating of the keyword library.

[0050] The user can select and input in the keyword library to determine the final target keyword from multiple candidate target keywords.

[0051] The plant polysaccharide data query method provided by the embodiment of the present invention can dynamically generate keywords based on high-frequency word segmentations in the latest plant polysaccharide research literature in the public database, making it easier for users to query and use them.

[0052] In some embodiments, the plant polysaccharide database is updated based on the following steps: Determine the data update time interval; Based on the data update time interval, new plant polysaccharide research literature and new plant polysaccharide experimental data are obtained from various public databases; Perform text analysis on newly added plant polysaccharide research literature to obtain the first newly added plant polysaccharide data; Processing the newly added plant polysaccharide experimental data to obtain second newly added plant polysaccharide data; The first newly added plant polysaccharide data and the second newly added plant polysaccharide data are stored in the plant polysaccharide database.

[0053] Specifically, a dynamic update mechanism can be established to regularly collect the latest research data and literature to ensure the timeliness of the database.

[0054] The data update time interval may be determined, such as one month or one quarter, etc. According to the data update time interval, newly added plant polysaccharide research literature and newly added plant polysaccharide experimental data are obtained from various public databases.

[0055] By performing text analysis on the newly added plant polysaccharide research literature, the first newly added plant polysaccharide data can be obtained. By performing data processing on the newly added plant polysaccharide experimental data, the second newly added plant polysaccharide data can be obtained.

[0056] The first newly added plant polysaccharide data and the second newly added plant polysaccharide data may be reviewed by the administrator of the database, and on the basis of ensuring the accuracy of the content, the first newly added plant polysaccharide data and the second newly added plant polysaccharide data may be stored in the plant polysaccharide database.

[0057] The plant polysaccharide data query method provided by the embodiment of the present invention obtains new plant polysaccharide research literature and new plant polysaccharide experimental data from various public databases, dynamically updates the plant polysaccharide database, and improves the timeliness and comprehensiveness of plant functional polysaccharide data.

[0058] In some embodiments, determining target keywords includes: Get initial keywords; Inputting the initial keywords into the query recommendation model to obtain multiple recommended keywords output by the query recommendation model; Identify initial keywords and recommended keywords as target keywords; Among them, the query recommendation model is trained based on sample initial keywords and sample recommended keywords corresponding to the sample initial keywords; the sample initial keywords are the historical initial keywords input by each user, and the sample recommended keywords are determined based on the query history records corresponding to the historical initial keywords.

[0059] Specifically, the plant polysaccharide database provided by the embodiment of the present invention can also recommend relevant target keywords based on the user's search history or behavioral preferences.

[0060] The user enters an initial keyword in the database query interface. The query interface can input the initial keyword into the query recommendation model, and obtain multiple recommended keywords output by the query recommendation model. After confirmation by the user, the initial keyword and the recommended keywords can be determined as the target keywords to be searched.

[0061] The query recommendation model is obtained by training a neural network model as the initial model. The specific training process is as follows: First, a large number of sample initial keywords and sample recommended keywords corresponding to the sample initial keywords are collected. Sample initial keywords are historical initial keywords entered by each user (initial keywords entered in the query history). For example, a user may enter the plant name "Plant A" in a query. Sample recommended keywords are determined based on the query history corresponding to the historical initial keywords, or based on the user's query preferences. For example, after the user enters "Plant A," their query history contains content related to the plant's "antioxidant" biological activity. Therefore, the sample recommended keywords corresponding to the "antioxidant" sample initial keyword "Plant A" can be used. The initial model is then trained using the sample initial keywords and the sample recommended keywords corresponding to the sample initial keywords (as sample labels) to improve the initial model's predictive ability for sample recommended keywords. Ultimately, the query recommendation model is obtained.

[0062] Sample recommendation keywords can also be configured based on individual user query preferences. Users can set query preferences for specific data content within the database, such as biological activity or extraction methods. The query recommendation model can then prioritize keywords related to biological activity or extraction methods in its output.

[0063] The plant polysaccharide data query method provided by the embodiment of the present invention determines the sample initial keywords and the sample recommended keywords corresponding to the sample initial keywords based on the user's query history records, and trains a query recommendation model, which can more conveniently determine the recommended keywords so that users can conduct more comprehensive and intelligent queries.

[0064] In some embodiments, the method further comprises: Deploy the plant polysaccharide database to the cloud platform; Alternatively, the plant polysaccharide database is deployed to a distributed system; the distributed system includes edge computing nodes and central computing nodes; multiple plant polysaccharide data obtained by each edge computing node are stored in each edge settlement node; based on the central computing node, the plant information table, polysaccharide information table and experimental data table in each edge computing node are summarized.

[0065] Specifically, the plant polysaccharide database provided in the embodiments of the present invention can be deployed on a cloud platform or on a distributed system, as described below.

[0066] The first deployment method is to deploy the plant polysaccharide database based on the cloud platform.

[0067] This example builds a cloud-based plant functional polysaccharide database system suitable for large-scale data storage, real-time updates, high-concurrency queries, and deep learning model training and prediction. The system supports real-time data collection, storage, analysis, and intelligent recommendations for plant functional polysaccharides, comprehensively improving data processing capabilities and user experience.

[0068] The cloud platform can store both structured and unstructured data (literature, experimental data, etc.). It also provides elastic computing resources for running deep learning models, improving model training and prediction efficiency. This deep learning model can be the query recommendation model mentioned in the previous example, or other models used to process plant polysaccharide data in the database. The cloud platform also supports big data processing and distributed parallel computing for handling large datasets. Automated crawlers and scheduled tasks can be set up within the cloud platform to automatically capture the latest literature and experimental data from the literature library weekly, ensuring real-time data updates. The cloud platform also utilizes natural language processing services for literature content analysis, providing intelligent recommendations based on user query history.

[0069] For example, cloud platforms like AWS can be chosen. Amazon RDS is used as a MySQL database to store plant polysaccharide data, with an initial storage capacity of 100GB (gigabytes) and automatic expansion up to 1TB (terabytes). Amazon S3 is used to store literature data, with an initial capacity of 50GB and an increase of approximately 10GB per month. Amazon EC2 is used for deep learning training, and the resulting models can be used to predict the bioactivity of plant polysaccharides. Using the Apache Spark computing engine, each data processing task supports up to 500GB of data, with parallel computing time limited to 20 minutes.

[0070] Monthly literature collection: Approximately 1,000 articles; Weekly literature updates: 200 articles, including experimental data. Data update frequency: Automatically updated every 24 hours to ensure data keeps pace with scientific research progress.

[0071] The bioactivity prediction model can be trained on the cloud platform. Input data includes polysaccharide molecular weight (100kDa-500kDa, kDa represents kilodaltons) and monosaccharide composition (e.g., arabinose, glucose, galactose, etc.). Output is antioxidant activity (IC50 value). The training dataset contains 700 polysaccharide samples and the test set contains 300 samples, achieving an accuracy rate of 92%. A comparison of the above scheme with related technical solutions is shown in Table 1.

[0072] Table 1 Comparison of plant polysaccharide database deployment based on cloud platform and related technologies

[0073] The second deployment method is to deploy the plant polysaccharide database based on a distributed system.

[0074] In this solution, the plant polysaccharide database is deployed to a distributed system; the distributed system includes edge computing nodes and central computing nodes.

[0075] Multiple plant polysaccharide data acquired by each edge computing node is stored in each edge settlement node. By offloading data collection, preliminary processing, and some model inference tasks to edge computing nodes close to the data source, data transmission latency is reduced. This approach is suitable for field laboratories, scientific research field sites, or research scenarios requiring distributed collaboration.

[0076] Based on the central computing node, the plant information table, polysaccharide information table and experimental data table in each edge computing node are summarized.

[0077] A lightweight database and inference model are deployed on edge computing nodes (such as laboratory workstations) within the distributed system to enable local data collection, preliminary cleaning, and rapid processing. The edge computing nodes record experimental conditions, extraction rates, activity data, and other data in real time, performing data cleaning and structuring, such as removing outliers and standardizing fields. A TinyML model is deployed to predict polysaccharide antioxidant activity (IC50 values), with inference time under 1 second. The optimized lightweight machine learning model deployed on the edge computing nodes processes experimental data in real time and provides preliminary predictions, significantly reducing the computational burden of data transmission to the central computing nodes.

[0078] A distributed file system is used to synchronize data across multiple nodes, enabling distributed collaborative storage and ensuring data consistency and efficient sharing. Using a distributed file system (such as Ceph), an efficient data transmission channel is established between edge nodes and central nodes, supporting real-time synchronization across multiple nodes. Automatic synchronization is implemented every two hours, supporting data retransmission after network interruptions. The master database is stored in the central node, and new data is backed up daily from the edge nodes to the central node, stored as time-series versions.

[0079] Central computing nodes aggregate data from edge computing nodes and perform highly complex deep learning training and advanced data analysis. Central computing nodes can store literature data, experimental data, and prediction results uploaded by edge nodes. The storage architecture can combine MySQL (structured data) and Ceph (unstructured data). Central nodes utilize high-performance graphics processors for model optimization, including graph neural network (GNN) and multi-task learning modules.

[0080] Edge computing nodes can store data when the network is unstable. When the edge computing node is offline, the data can be stored locally and automatically synchronized after the network is restored to ensure data integrity. After the network is restored, the data will be automatically synchronized to the central computing node.

[0081] The comparison between the above scheme and related technical solutions is shown in Table 2.

[0082] Table 2 Comparison of plant polysaccharide database deployment based on distributed systems and related technologies

[0083] Comparing the above two solutions: The advantages of the cloud platform solution are high scalability and flexibility, efficient parallel computing and storage integration, efficient user experience, and reduced system operating costs; the advantages of the distributed solution are real-time and efficient response, reduced pressure on central nodes, support for distributed collaborative research, adaptability to offline or network-restricted environments, data security and privacy protection, as well as flexible expansion and high fault tolerance.

[0084] In some embodiments, a graph database (such as Neo4j) can also be used to construct a knowledge graph to show the deep relationship between polysaccharides and biological activities.

[0085] In some embodiments, an analysis function module can also be embedded in the database, for example, supporting the invocation of random forest or support vector machine algorithms to directly predict the bioactivity results of polysaccharides.

[0086] In some embodiments, the search process can be intelligently designed, combining natural language processing (NLP) and recommendation algorithms to dynamically optimize the ranking of search results and improve the relevance of results. This includes adding an intelligent recommendation module based on polysaccharide characteristics, for example, recommending polysaccharides with similar molecular weights or biological activities and their corresponding literature.

[0087] In some embodiments, deep learning techniques (such as convolutional neural networks (CNNs) and graph neural networks (GNNs)) can be used to model the complex relationship between polysaccharide molecular structure and bioactivity. This can be combined with protein databases and pathway databases (such as Reactome) to analyze the mechanisms of action of polysaccharides on specific targets. The application of deep learning techniques to predict polysaccharide bioactivity shifts data analysis from qualitative to quantitative, supporting the discovery of potentially highly active polysaccharides.

[0088] In some embodiments, real-time updated heatmaps, relationship graphs, and trend graphs can also be provided to support dynamic filtering, scaling, and exporting by users. A prediction data visualization module can be added, for example, to display the confidence interval of the deep learning model's prediction results for the bioactivity of a certain polysaccharide.

[0089] In some embodiments, the database can also add a built-in feedback function, allowing users to directly mark data errors or make feature suggestions in the interface. A feedback priority sorting mechanism can be established to automatically adjust the development plan based on the frequency of user feedback.

[0090] The following describes an apparatus provided by an embodiment of the present invention. The apparatus described below and the method described above can refer to each other.

[0091] Figure 2 This is a schematic diagram of the structure of the plant polysaccharide data query device provided by the present invention. Figure 2 As shown, the device includes: A determination unit 210 is configured to determine a target keyword; the target keyword is determined based on at least one of the polysaccharide name, molecular structure, plant origin, biological activity, and extraction method of the plant polysaccharide to be queried; A query unit 220 is configured to query each data table in the plant polysaccharide database based on the target keyword to obtain data records corresponding to the target keyword; Among them, the plant polysaccharide database stores plant polysaccharide data based on data tables; the data tables include plant information tables, polysaccharide information tables and experimental data tables; plant polysaccharide data include polysaccharide names, molecular structures, biological activities, plant sources and extraction methods; the plant information table and the polysaccharide information table are associated based on the plant names corresponding to the plant sources; the polysaccharide information table and the experimental data table are associated based on the polysaccharide names.

[0092] The plant polysaccharide data query device provided by the embodiment of the present invention determines the target keyword; queries each data table in the plant polysaccharide database based on the target keyword to obtain the data record corresponding to the target keyword; since the plant polysaccharide data includes multidimensional data such as polysaccharide name, molecular structure, biological activity, plant source and extraction method, the plant polysaccharide data can be stored comprehensively and systematically, and can be conveniently queried using the target keyword; since the plant polysaccharide database stores the plant polysaccharide data through data tables, the data tables include a plant information table, a polysaccharide information table and an experimental data table; the plant information table and the polysaccharide information table are associated based on the plant name corresponding to the plant source; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name; structured storage of plant polysaccharide data is achieved, which facilitates the storage and query of plant polysaccharide data; systematic integration of plant functional polysaccharide data is achieved, and the utilization rate of plant functional polysaccharide data is improved.

[0093] Based on the above embodiments, the present invention combines advanced cloud computing, big data, and deep learning processing technologies on the basis of the basic solution to propose an optimal implementation plan, including: 1. Adopt cloud computing architecture and distributed computing By migrating the plant polysaccharide database to the cloud platform, and leveraging the elastic scalability of cloud computing and the powerful capabilities of distributed computing, we can achieve efficient storage, management, and analysis of large-scale data while supporting high concurrent access.

[0094] Select mainstream cloud service platforms (such as AWS, Azure, or Google Cloud), and employ cloud databases (such as Amazon RDS) and distributed storage (such as Amazon S3) to store large amounts of literature data, experimental data, and analysis results. Employ distributed computing frameworks (such as Hadoop and Spark) for rapid big data processing and analysis, supporting multi-task parallel computing to reduce data analysis latency. Automatically adjust cloud computing resources based on access volume and computing demand to ensure efficient system operation during peak periods while reducing computing resource consumption and operating costs during off-peak periods.

[0095] Leveraging cloud platform support, the database easily scales to multi-terabyte data storage and can handle 2,000 new articles and experimental data daily. Distributed computing can process and analyze 100GB of data in a matter of hours, providing reliable support for in-depth analysis and real-time recommendations. Elastic computing resources ensure response times of less than one second even during high-concurrency queries (such as during periods of concentrated scientific research access).

[0096] 2. Use big data analysis and data mining Utilizing big data analysis technology, we deeply explore the potential relationships between data from dimensions such as polysaccharides and plant sources, extraction methods, and biological activities, discover new research trends, and support precise scientific research and decision-making.

[0097] Deeply integrating data from various sources, including literature, experiments, and open databases, the system uses multi-dimensional analyses (such as cluster analysis and association rule analysis) to reveal relationships between different plants and polysaccharides. Integrating big data technologies, the system automatically analyzes newly added literature and experimental data in real time, ensuring the database is always updated with the latest scientific research findings and data. Using big data models (such as random forests, XGBoost, and Gradient Boosting), the system trains polysaccharide bioactivity prediction models based on existing data, enabling accurate prediction of the bioactivity of different polysaccharides.

[0098] Using big data analysis tools, we can extract promising new functional polysaccharides and, through cluster analysis, identify unique structural features associated with anti-tumor activity. Real-time data analysis ensures that 2,000 monthly updated articles and experimental data are immediately reflected in the database, supporting researchers in making timely decisions. Predictive model accuracy has increased to 95%, providing precise bioactivity data support for drug development and reducing experimental costs.

[0099] 3. Integrated application of deep learning and artificial intelligence algorithms Through deep learning and artificial intelligence (AI) algorithms, complex analysis of polysaccharide data is carried out, especially in the prediction of biological activity and modeling of the relationship between molecular structure and activity, to achieve more accurate scientific research predictions and recommendations.

[0100] Deep learning technologies such as convolutional neural networks (CNNs) and graph neural networks (GNNs) are used to model the complex relationship between polysaccharide molecular structure and its biological activity. Deep learning frameworks such as TensorFlow and PyTorch are used on cloud platforms to train large amounts of polysaccharide data. GPU-accelerated computing improves model training efficiency and prediction accuracy. Combined with multi-task learning (MTL), a single model simultaneously performs multiple tasks (such as bioactivity prediction, target prediction, and toxicity prediction), significantly improving model efficiency and accuracy.

[0101] Deep learning models can accurately identify the relationship between subtle changes in polysaccharide molecular structure and their biological activity, increasing prediction accuracy to 95%. Especially in predicting antioxidant and anti-tumor activity, the error is controlled within ±5μg / mL (micrograms per milliliter). Using AI algorithms, researchers can recommend promising medicinal polysaccharides from a vast polysaccharide database, reducing experimental costs and increasing the success rate of drug development.

[0102] 4. Adopt intelligent user experience and recommendation systems Through intelligent recommendations and personalized search functions, the efficiency and satisfaction of users in the query, analysis and data screening processes are greatly improved.

[0103] Combining collaborative filtering with content recommendation algorithms, it recommends relevant literature, experimental data, and information on similar functional polysaccharides based on users' past queries and interests. Machine learning models optimize search rankings, supporting semantic search and natural language processing, allowing users to conduct precise searches using natural language queries (e.g., "Search for anti-tumor plant polysaccharides"). Integrating tools like D3.js and Plotly, it provides interactive data visualization, allowing users to flexibly view and compare the characteristics, activities, and experimental data of different polysaccharides through dragging, dropping, and zooming.

[0104] The system provides "personalized recommendations" based on the user's search history and preferences, recommending relevant literature and functional polysaccharides, which has increased the click-through rate to 85%, significantly improving the user experience. The multidimensional data visualization function provides intuitive heat maps, trend charts, and relationship diagrams, allowing users to clearly see the performance of different polysaccharides in different areas of activity, improving the efficiency and accuracy of data analysis. The query system based on natural language processing supports users to enter "anti-tumor polysaccharides". The system can automatically interpret the user's intent and return relevant data, improving the convenience of operation.

[0105] 5. System maintenance and data update Through the intelligent data update and feedback system, real-time data update, automatic error correction and timely response to user needs can be achieved, thereby improving the system's operating efficiency and user satisfaction.

[0106] The automated crawler, combined with the data update module, automatically captures new literature and experimental data weekly. Machine learning models are then used to automatically detect and delete redundant or erroneous data. User feedback is received in real time, analyzed, and system functionality is rapidly adjusted and updated to ensure continuous system optimization. Machine learning combined with rule-based validation automatically detects and corrects data anomalies in the database, such as biological activity data that deviates from normal ranges.

[0107] 50-100 articles are automatically updated monthly, with 2,000 new entries added each week. User feedback processing time has been reduced to 24 hours, and common issues are fixed through automated systems, improving user satisfaction. Automatic error correction mechanisms have reduced the database error rate to 0.5%, significantly improving data accuracy and reliability.

[0108] The best implementation has the following advantages: 1. Large-scale data support and flexible expansion: The combination of cloud computing and distributed computing enables the system to maintain efficient processing and analysis capabilities even when data volumes increase dramatically. It supports data storage and computing from several GB to several TB levels, ensuring the long-term sustainability of the system.

[0109] 2. Accurate bioactivity prediction and intelligent recommendation: Supported by deep learning and big data analysis, this invention can not only accurately predict the bioactivity of polysaccharides, but also help researchers discover potential research directions and new application values ​​through an intelligent recommendation system, greatly reducing the cost and time of drug development.

[0110] 3. Real-time data updates and intelligent feedback: The combination of automated crawlers and feedback mechanisms enables the system to obtain the latest scientific research results in real time and update the database in a timely manner, providing a smoother user experience. It can also quickly respond to user feedback and optimize system functions.

[0111] 4. Multidimensional data interaction and visualization: The multidimensional data visualization function enables users to more intuitively understand and analyze the characteristics and activity distribution of polysaccharides, supports users to conduct multi-angle analysis, and enhances the research value of the data.

[0112] 5. Efficient resource utilization and cost reduction: The elastic scalability of cloud computing and the parallel computing capabilities of deep learning models greatly improve system processing efficiency while reducing hardware and operation and maintenance costs, providing a cost-effective solution.

[0113] Figure 3 Schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 3 As shown, the electronic device may include: a processor (Processor) 310, a communication interface (Communications Interface) 320, a memory (Memory) 330 and a communication bus (Communications Bus) 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call the logic commands in the memory 330 to execute the method described in the above embodiments, for example: Determine target keywords; the target keywords are determined based on at least one of the polysaccharide name, molecular structure, plant source, biological activity and extraction method of the plant polysaccharide to be queried; query each data table in the plant polysaccharide database based on the target keywords to obtain data records corresponding to the target keywords; wherein the plant polysaccharide database stores plant polysaccharide data based on data tables; the data tables include plant information tables, polysaccharide information tables and experimental data tables; plant polysaccharide data include polysaccharide name, molecular structure, biological activity, plant source and extraction method; the plant information table and the polysaccharide information table are associated based on the plant name corresponding to the plant source; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name.

[0114] Furthermore, the logical commands in the aforementioned memory can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several commands for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0115] The processor in the electronic device provided by the embodiment of the present invention can call the logic instructions in the memory to implement the above method. Its specific implementation method is consistent with the implementation method of the above method and can achieve the same beneficial effects, which will not be repeated here.

[0116] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method provided in the above embodiments is implemented.

[0117] Its specific implementation is consistent with the aforementioned method implementation and can achieve the same beneficial effects, so it will not be repeated here.

[0118] An embodiment of the present invention provides a computer program product, including a computer program. When the computer program is executed by a processor, the method described above is implemented.

[0119] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0120] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A plant polysaccharide data query method, characterized in that: include: Determine target keywords; the target keywords are determined based on at least one of the polysaccharide name, molecular structure, plant source, biological activity and extraction method of the plant polysaccharide to be queried; Based on the target keyword, query each data table in the plant polysaccharide database to obtain the data record corresponding to the target keyword; Among them, the plant polysaccharide database stores plant polysaccharide data based on a data table; the data table includes a plant information table, a polysaccharide information table and an experimental data table; the plant polysaccharide data includes polysaccharide name, molecular structure, biological activity, plant source and extraction method; the plant information table and the polysaccharide information table are associated based on the plant name corresponding to the plant source; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name.

2. The plant polysaccharide data query method according to claim 1, characterized in that: The plant polysaccharide database is established based on the following steps: Based on public databases and / or plant polysaccharide experimental data, obtaining the plant polysaccharide data; Generate a plant information table based on the plant sources in each plant polysaccharide data, and the plant family and plant name corresponding to the plant source; Generate a polysaccharide information table based on the polysaccharide name, molecular structure, biological activity, plant source and plant name corresponding to the plant source in each plant polysaccharide data; Generate an experimental data table based on the polysaccharide name, extraction method, and experimental process and experimental parameters corresponding to the extraction method in each plant polysaccharide data; Establishing a first inter-table relationship between the polysaccharide information table and the plant information table based on the plant name; Establishing a second inter-table relationship between the polysaccharide information table and the experimental data table based on the polysaccharide name; The plant polysaccharide database is established based on the plant information table, the polysaccharide information table, the experimental data table, the first inter-table relationship and the second inter-table relationship.

3. The plant polysaccharide data query method according to claim 2, characterized in that: The obtaining of the plant polysaccharide data based on the public database and / or the plant polysaccharide experimental data includes: Based on the public database, obtain multiple plant polysaccharide research documents; Segment each plant polysaccharide research document, and determine the high-frequency segmentation in each plant polysaccharide research document and the text position of the high-frequency segmentation based on the frequency of occurrence of each segmentation in the corresponding plant polysaccharide research document; the high-frequency segmentation is a segmentation whose frequency of occurrence is greater than a preset frequency; Based on the high-frequency segmented words and the text positions of the high-frequency segmented words, information extraction is performed in various plant polysaccharide research documents to obtain the plant polysaccharide data in each plant polysaccharide research document.

4. The plant polysaccharide data query method according to claim 3, characterized in that: After segmenting each plant polysaccharide research document, and determining the high-frequency segmentation in each plant polysaccharide research document based on the frequency of occurrence of each segmentation in the corresponding plant polysaccharide research document, and the text position of the high-frequency segmentation, the method further includes: Determine the high-frequency segmented words as candidate target keywords and add them to the keyword library; The keyword library is used to determine target keywords based on user selection input.

5. The plant polysaccharide data query method according to claim 2, characterized in that: The plant polysaccharide database is updated based on the following steps: Determine the data update time interval; Based on the data update time interval, obtaining new plant polysaccharide research literature and new plant polysaccharide experimental data from various public databases; Performing text analysis on the newly added plant polysaccharide research literature to obtain the first newly added plant polysaccharide data; Processing the newly added plant polysaccharide experimental data to obtain second newly added plant polysaccharide data; The first newly added plant polysaccharide data and the second newly added plant polysaccharide data are stored in the plant polysaccharide database.

6. The plant polysaccharide data query method according to claim 1, characterized in that: Determining the target keywords includes: Get initial keywords; Inputting the initial keyword into a query recommendation model to obtain a plurality of recommended keywords output by the query recommendation model; determining the initial keyword and the recommended keyword as target keywords; Among them, the query recommendation model is trained based on sample initial keywords and sample recommended keywords corresponding to the sample initial keywords; the sample initial keywords are historical initial keywords input by each user, and the sample recommended keywords are determined based on the query history records corresponding to the historical initial keywords.

7. The plant polysaccharide data query method according to claim 1, characterized in that: The method further comprises: Deploying the plant polysaccharide database to a cloud platform; Alternatively, the plant polysaccharide database is deployed to a distributed system; the distributed system includes edge computing nodes and central computing nodes; multiple plant polysaccharide data obtained by each edge computing node are stored in each edge settlement node; based on the central computing node, the plant information table, polysaccharide information table and experimental data table in each edge computing node are summarized.

8. A plant polysaccharide data query device, characterized in that: include: A determination unit, used to determine target keywords; The target keyword is determined based on at least one of the polysaccharide name, molecular structure, plant source, biological activity and extraction method of the plant polysaccharide to be queried; A query unit, used to query each data table in the plant polysaccharide database based on the target keyword to obtain data records corresponding to the target keyword; Among them, the plant polysaccharide database stores plant polysaccharide data based on a data table; the data table includes a plant information table, a polysaccharide information table and an experimental data table; the plant polysaccharide data includes polysaccharide name, molecular structure, biological activity, plant source and extraction method; the plant information table and the polysaccharide information table are associated based on the plant name corresponding to the plant source; the polysaccharide information table and the experimental data table are associated based on the polysaccharide name.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the plant polysaccharide data query method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the plant polysaccharide data query method according to any one of claims 1 to 7 is implemented.

Images