Method for extracting spatial distribution characteristics of different types of enterprises in combination with large model
By constructing a basic information table and a large model operating environment, combining the company's introduction and text summary of business scope, two large model search methods are used to dynamically adjust the data volume, solving the speed and accuracy of the large model in enterprise type identification, and achieving rapid and accurate extraction and visualization of the spatial distribution feature of the enterprise.
Patent Information
- Application Number
- CN202510445896.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-10
- Publication Date
- 2025-08-15
AI Technical Summary
The prior art is difficult to quickly and accurately extract the spatial distribution characteristics of different types of enterprises, especially when large models are slow to calculate and have high error rates, which cannot effectively support actual production needs.
By constructing basic information tables and spatial information fields, establishing a large-scale operation environment, using two large-scale model search methods, combining the company's introduction and text summary of business scope, batch data processing is carried out, and spatial distribution characteristics are drawn through latitude and longitude information, and the data volume is dynamically adjusted to improve processing efficiency.
It realizes the rapid and accurate extraction of different types of enterprise data and performs spatial visualization, improving the processing speed and accuracy of large models in enterprise type identification.
Smart Images
Figure CN120492881A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to technical fields such as urban planning, smart cities, natural language processing and geographic information systems, and in particular to a method for extracting spatial distribution features of different types of enterprises combined with a large model. Background Art
[0002] Extracting and analyzing the spatial distribution characteristics of different types of enterprises is a crucial foundation for innovative spatial analysis and industrial research. While current enterprise data provides basic classifications based on industry or sector types, it lacks the flexibility to adapt to the specific enterprise classifications required for specific applications. For example, enterprises in the elderly care industry or urban planning sectors require this type of classification. Therefore, it is necessary to extract enterprise types based on information such as their business scope and profile. Due to the large number of enterprises, manual identification of enterprise types is labor-intensive and impractical for practical application.
[0003] With the rapid development of large-scale model technology, it's now possible to use large models to identify business types through their ability to recognize text semantics. However, privately deployed large models lack the computing power to support many practical applications, resulting in slow computational speeds. Therefore, algorithms are needed to accelerate the process of large-scale model recognition of business types to better serve real-world production needs. Currently, large models may experience errors and reduced accuracy when processing batches of data, necessitating the ability to dynamically adjust the amount of data processed at a time. Summary of the Invention
[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing technology and provide a method for extracting spatial distribution characteristics of different types of enterprises combined with a large model. The present invention can effectively and quickly extract different types of enterprise data through a large model and perform spatial visualization of the enterprise data.
[0005] The present invention adopts the following technical solutions to solve the above technical problems:
[0006] In a first aspect, a method for extracting spatial distribution features of different types of enterprises combined with a large model according to the present invention includes:
[0007] Step 1: Create basic information tables and spatial information fields for enterprise data and store them in the database;
[0008] Step 2: Establish a large model operating environment;
[0009] Step 3: Using the large model retrieval method twice, extract enterprise data of different enterprise types using the large model; wherein the process of extracting enterprise data of each enterprise type is shown in steps 3.1 to 3.3;
[0010] Step 3.1: For each enterprise type t to be extracted, construct a batch enterprise type judgment statement and pass it to the large model to extract enterprise data from the database in batches multiple times; the enterprise data extracted in each batch is recorded as e;
[0011] Step 3.2: Perform the following operations on the enterprise data extracted in batches in step 3.1:
[0012] For each batch of extracted enterprise data e, determine whether there are enterprises belonging to enterprise type t in e. If so, record the batch of extracted enterprise data e as enterprise data E for single enterprise type determination;
[0013] Step 3.3: Construct a statement for determining the type of a single enterprise based on all E obtained in step 3.2, and pass the statement to the large model for determining the enterprise type, thereby extracting enterprise data for enterprise type t.
[0014] Step 4: The user draws the spatial distribution characteristics of different types of enterprise data.
[0015] As a further optimization scheme of the method for extracting spatial distribution features of different types of enterprises in combination with a large model according to the present invention, in step 1, a basic information table is constructed for each enterprise in the enterprise data. The basic information table includes data on the enterprise profile and the enterprise's business scope that can be used to determine the enterprise type;
[0016] Each enterprise includes a longitude and latitude information.
[0017] As a further optimization scheme of the method for extracting spatial distribution features of different types of enterprises combined with a large model according to the present invention, step 2 includes:
[0018] According to the characteristics of different types of enterprises, large model prompt word databases are constructed respectively; among them, the large model prompt word database is set according to the content of the enterprise profile and the enterprise business scope.
[0019] As a further optimization scheme of the method for extracting spatial distribution features of different types of enterprises combined with a large model described in the present invention, constructing batches of enterprise type judgment statements in step 3.1 refers to: textually summarizing the data of the corporate profiles and business scopes of multiple enterprises, and writing enterprise type judgment statements for the textually summarized data.
[0020] As a further optimization scheme of the method for extracting spatial distribution characteristics of different types of enterprises combined with a large model described in the present invention, in step 3.2, if there are no enterprises belonging to enterprise type t in the enterprise data extracted in batches from the i-th to the i+M-1th times, the number of enterprise data extracted from the database in each batch is reduced; wherein M is a preset specified number of times, and i is an integer greater than 0.
[0021] As a further optimization scheme of the method for extracting spatial distribution characteristics of different types of enterprises combined with a large model described in the present invention, in step 4, spatial distribution characteristics of different types of enterprise data are mapped using the longitude and latitude information of the enterprises.
[0022] In a second aspect, an embodiment of the present invention further provides a computer device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, the steps of the method for extracting spatial distribution features of different types of enterprises combined with a large model as described in the first aspect above or any corresponding embodiment thereof are implemented.
[0023] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for extracting spatial distribution features of different types of enterprises combined with a large model as described in the first aspect above or any corresponding embodiment thereof are implemented.
[0024] Compared with the prior art, the present invention adopts the above technical solution and has the following technical effects:
[0025] (1) The present invention provides a method for extracting spatial distribution features of different types of enterprises in combination with a large model, which can quickly extract different types of enterprise data from the enterprise's text information and characterize spatial distribution features;
[0026] (2) Based on the intelligent recognition of enterprise text-related information by the big model and the configuration of an improvement strategy to improve the data analysis speed of the big model, the present invention proposes a method for extracting spatial distribution features of different types of enterprises combined with the big model. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 It is a schematic diagram of the overall process of the present invention.
[0028] Figure 2 This is a schematic diagram of the secondary search processing flow.
[0029] Figure 3 It is a schematic diagram of the adjustment of the number of enterprises in batch processing. DETAILED DESCRIPTION
[0030] The technical solution of the present invention is further described in detail below with reference to the accompanying drawings:
[0031] A method for extracting spatial distribution features of different types of enterprises combined with a large model, including:
[0032] Step 1, see attached Figure 1 , which is the overall technical roadmap of this invention. This invention first constructs a basic enterprise information table and a spatial information field. The basic enterprise information table contains a large amount of textual descriptive information about the enterprise. The spatial information field table is used to store spatial location information. All of this information is stored in a spatial database.
[0033] In this step, a basic information table is constructed for each enterprise in the enterprise data. The basic information table includes data such as the company profile and business scope, which can be used to determine the company type. The company profile and business scope data are generally text data and are unstructured, requiring manual or other methods to determine the company type.
[0034] Each enterprise entry includes a latitude and longitude information. The latitude and longitude information included in each enterprise entry is mainly used for spatial visualization of the enterprise.
[0035] Step 2: Establish a large model operating environment; build a large model prompt word corpus based on the characteristics of different types of enterprises. Currently, establishing a large model operating environment is relatively easy. For example, you can install the DeepSeek large model locally for free.
[0036] The large model prompt word database is designed based on the company profile and business scope. The large model prompt word database is key to extracting company types, but this invention focuses on extracting company types based on the company profile and business scope. Therefore, the prompt word database needs to be designed based on the company profile and business scope.
[0037] Step 3, see attached Figure 2 , through the two-step large model retrieval method, the large model is used to extract enterprise data of different enterprise types. The present invention focuses on the use of the two-step large model retrieval method, mainly to solve the problem of high error rate that may occur when the large model parses large amounts of text into structured data. The output of structured text for a small amount of data each time may cause a job to take a lot of time. This poses a certain barrier to the widespread promotion of large models in practical applications. To this end, the present invention sets up a large model processing of batch enterprise information. If the enterprise text information content that meets the conditions is found during a batch processing, the batch processed information will be processed in strips and in sequence. This will greatly improve the efficiency of large model processing.
[0038] The process of extracting enterprise data for each enterprise type is shown in steps 3.1 to 3.3;
[0039] Step 3.1: For each type of enterprise to be extracted, construct batch enterprise type judgment statements and pass them to the large model, extracting enterprise data from the database in batches. Each batch of extracted enterprise data is denoted as e. Constructing batch enterprise type judgment statements in this step involves aggregating the company profiles and business scope data of multiple enterprises and then writing enterprise type judgment statements based on this aggregated data. The purpose of this step is to process enterprise information in batches to reduce the number of calls to the large model.
[0040] The amount of enterprise data extracted in each batch in this step is determined based on the results of the continuous judgments in step 3.2. If no enterprise data is found for a specific enterprise type in the specified number of consecutive judgments, the amount of data extracted will be reduced. The purpose of this step is to repeatedly find that the batch processing results do not contain the information required for analysis, which may indicate that the batch processing data volume is too large. Therefore, the size of the batch processing text information needs to be reduced.
[0041] Step 3.2: Perform the following operations on the enterprise data extracted in batches in step 3.1:
[0042] For each batch of extracted enterprise data e, determine whether there are enterprises belonging to enterprise type t in e. If so, record the batch of extracted enterprise data e as enterprise data E for single enterprise type determination;
[0043] Also, see the attached Figure 3 If there is no enterprise belonging to enterprise type t in the enterprise data extracted in batches from the i-th to the i+M-1th time, the number of enterprise data extracted from the database in each batch is reduced; where M is the preset specified number of times and i is an integer greater than 0.
[0044] Step 3.2 is a judgment process: if relevant information is found in a batch process, the information of each enterprise is checked one by one. Otherwise, the batch process is continued to improve the speed.
[0045] Step 3.3: Construct a statement for determining the type of a single enterprise based on all E obtained in step 3.2, and pass the statement to the large model for determining the enterprise type, thereby extracting enterprise data for enterprise type t.
[0046] Step 4: The user plots the spatial distribution characteristics of different types of enterprise data. In this step, the spatial distribution characteristics of different types of enterprise data are plotted using the longitude and latitude information of the enterprises.
[0047] An embodiment of the present invention also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, it implements the steps of the method for extracting spatial distribution features of different types of enterprises combined with a large model as described in the first aspect above or any corresponding embodiment thereof.
[0048] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method for extracting spatial distribution features of different types of enterprises combined with a large model as described in the first aspect above or any corresponding embodiment thereof.
[0049] It will be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, the object-oriented programming language Java and the interpreted scripting language JavaScript.
[0050] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0051] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.
[0052] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0053] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0054] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.
Claims
1. A method for extracting spatial distribution features of different types of enterprises combined with a large model, characterized by: include: Step 1: Create basic information tables and spatial information fields for enterprise data and store them in the database; Step 2: Establish a large model operating environment; Step 3: Using the large model retrieval method twice, extract enterprise data of different enterprise types using the large model; wherein the process of extracting enterprise data of each enterprise type is shown in steps 3.1 to 3.3; Step 3.1: For each enterprise type t to be extracted, construct a batch enterprise type judgment statement and pass it to the large model to extract enterprise data from the database in batches multiple times; the enterprise data extracted in each batch is recorded as e; Step 3.2: Perform the following operations on the enterprise data extracted in batches in step 3.1: For each batch of extracted enterprise data e, determine whether there are enterprises belonging to enterprise type t in e. If so, record the batch of extracted enterprise data e as enterprise data E for single enterprise type determination; Step 3.3: Construct a statement for determining the type of a single enterprise based on all E obtained in step 3.2, and pass the statement to the large model for determining the enterprise type, thereby extracting enterprise data for enterprise type t. Step 4: The user draws the spatial distribution characteristics of different types of enterprise data.
2. The method for extracting spatial distribution features of different types of enterprises combined with a large model according to claim 1 is characterized in that: In step 1, a basic information table is constructed for each enterprise in the enterprise data. The basic information table includes the enterprise profile and business scope data that can be used to determine the enterprise type; Each enterprise includes a longitude and latitude information.
3. The method for extracting spatial distribution features of different types of enterprises combined with a large model according to claim 2 is characterized in that: Step 2 includes: According to the characteristics of different types of enterprises, large model prompt word databases are constructed respectively; among them, the large model prompt word database is set according to the content of the enterprise profile and the enterprise business scope.
4. The method for extracting spatial distribution features of different types of enterprises combined with a large model according to claim 2 is characterized in that: Constructing batches of enterprise type judgment statements in step 3.1 means: aggregating the data of the enterprise profiles and business scopes of multiple enterprises into text, and writing enterprise type judgment statements based on the aggregating data.
5. The method for extracting spatial distribution features of different types of enterprises combined with a large model according to claim 1 is characterized in that: In step 3.2, if there is no enterprise belonging to enterprise type t in the enterprise data extracted in batches from the i-th to the i+M-1th time, the number of enterprise data extracted from the database in each batch is reduced; where M is a preset specified number of times and i is an integer greater than 0.
6. The method for extracting spatial distribution features of different types of enterprises combined with a large model according to claim 1 is characterized in that: In step 4, the spatial distribution characteristics of different types of enterprise data are drawn using the longitude and latitude information of the enterprises.
7. A computer device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for extracting spatial distribution features of different types of enterprises combined with a large model are implemented as described in any one of claims 1 to 6.
8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for extracting spatial distribution features of different types of enterprises combined with a large model are implemented as described in any one of claims 1 to 6.