Industry attribute identification method and device, equipment, storage medium and product

Abstract

The invention discloses an industry attribute identification method and device, equipment, a storage medium and a product. The method comprises the following steps: acquiring enterprise trade data of a to-be-identified enterprise; inputting the enterprise trade data into a keyword extraction model obtained by pre-training to obtain at least one product keyword output by the model and the keyword quantity of each product keyword; screening each product keyword according to the keyword quantity of each product keyword, and determining a target keyword; determining a product industry category corresponding to the target keyword; and according to the product industry category, determining the industry attribute of the to-be-identified enterprise. According to the technical scheme, the industry identification efficiency and the identification accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an industry attribute identification method, device, equipment, storage medium and product. Background Art

[0002] In the global trade environment, accurately identifying the industry attributes of enterprises is of great significance for market analysis, enterprise evaluation and supply chain optimization. However, traditional industry attribute identification methods usually rely on manual labeling and classification for industry identification, which is inefficient, requires a lot of human resources and has low accuracy. Summary of the invention

[0003] The present invention provides an industry attribute recognition method, device, equipment, storage medium and product to improve industry recognition efficiency and recognition accuracy.

[0004] According to one aspect of the present invention, a method for identifying industry attributes is provided, the method comprising:

[0005] Obtaining corporate trade data of the enterprise to be identified;

[0006] Inputting the enterprise trade data into a pre-trained keyword extraction model to obtain at least one product keyword output by the model and the keyword quantity of each product keyword;

[0007] According to the keyword quantity of each product keyword, each product keyword is screened to determine the target keyword;

[0008] Determine the product industry category corresponding to the target keyword;

[0009] According to the product industry category, the industry attribute of the enterprise to be identified is determined.

[0010] According to another aspect of the present invention, there is provided an industry attribute identification device, the device comprising:

[0011] A trade data acquisition module, used to acquire the enterprise trade data of the enterprise to be identified;

[0012] A keyword extraction module is used to input the enterprise trade data into a pre-trained keyword extraction model to obtain at least one product keyword output by the model and the keyword quantity of each product keyword;

[0013] A keyword screening module, used to screen each of the product keywords according to the number of keywords of each of the product keywords, and determine the target keyword;

[0014] An industry category determination module, used to determine the product industry category corresponding to the target keyword;

[0015] The industry attribute determination module is used to determine the industry attribute of the enterprise to be identified according to the product industry category.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the industry attribute identification method described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the industry attribute identification method described in any embodiment of the present invention when executed.

[0021] According to another aspect of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the industry attribute identification method described in any embodiment of the present invention is implemented.

[0022] The technical solution of the embodiment of the present invention inputs the enterprise trade data into the pre-trained keyword extraction model to obtain at least one product keyword output by the model, as well as the keyword quantity of each product keyword; screens each product keyword according to the keyword quantity of each product keyword to determine the target keyword; determines the product industry category corresponding to the target keyword; and determines the industry attribute of the enterprise to be identified according to the product industry category. The above technical solution realizes the automatic prediction of industry attributes by extracting product keywords and determining the industry attributes based on the product industry category corresponding to the keywords, thereby improving the prediction efficiency and prediction accuracy of industry attributes.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 is a flow chart of an industry attribute identification method provided according to the first embodiment of the present invention;

[0026] Figure 2 is a flow chart of an industry attribute identification method provided according to Embodiment 2 of the present invention;

[0027] Figure 3 is a schematic diagram of the structure of an industry attribute identification device provided according to Embodiment 3 of the present invention;

[0028] Figure 4 It is a structural schematic diagram of an electronic device for implementing the industry attribute identification method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged 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" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1This is a flow chart of an industry attribute identification method provided in the first embodiment of the present invention. This embodiment is applicable to the case of identifying industry attributes of enterprise industries in a global trade environment. The method can be executed by an industry attribute identification device. The industry attribute identification device can be implemented in the form of hardware and / or software. The industry attribute identification device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0033] S110. Obtain the enterprise trade data of the enterprise to be identified.

[0034] The enterprise to be identified may be an enterprise to be identified by industry attributes in a global trade environment. Enterprise trade data may include product introduction data and product description data of related products developed or operated by the enterprise.

[0035] S120: Input the enterprise trade data into a pre-trained keyword extraction model to obtain at least one product keyword output by the model and the keyword quantity of each product keyword.

[0036] The keyword extraction model can be obtained by pre-training a preset text extraction network model for predicting product keywords and keyword quantity. For example, the text extraction network model can be BERT (Bidirectional Encoder Representations from Transformers), or GPT (Generative Pre-trained Transformer), which is not limited in this embodiment.

[0037] It should be noted that before inputting the enterprise trade data into the pre-trained keyword extraction model, the enterprise trade data can be pre-processed, including data deduplication, filling missing values ​​and special symbol processing.

[0038] The input of the keyword extraction model is the enterprise trade data, and the output is at least one product keyword obtained after keyword extraction of the enterprise trade data, and the number of keywords corresponding to each product keyword. For example, the output results include: product keyword A, the number of corresponding keywords is numA; product keyword B, the number of corresponding keywords is numB; product keyword C, the number of keywords is numC.

[0039] S130: Screen each product keyword according to the keyword quantity of each product keyword to determine the target keyword.

[0040] For example, the keyword quantity of each product keyword can be compared with a preset keyword quantity threshold, and if it is greater than the preset keyword quantity threshold, the product keyword is determined as the target keyword. The keyword quantity threshold can be preset by relevant technical personnel.

[0041] S140. Determine the product industry category corresponding to the target keyword.

[0042] For example, the target keyword can be input into the pre-trained industry category prediction model to perform industry category prediction to obtain the predicted product industry category. For example, if the target keyword is: home furnishing, carpet, floor covering, sofa cushion, etc., the predicted product industry category may be home furnishing trade category.

[0043] S150. Determine the industry attributes of the enterprise to be identified based on the product industry category.

[0044] For example, if the product industry category is home furnishing trade, then its corresponding industry attribute can be home furnishing retail. For another example, if the product industry category is lighting manufacturing, then its corresponding industry attribute can be home furnishing manufacturing.

[0045] The technical solution of the embodiment of the present invention inputs the enterprise trade data into the pre-trained keyword extraction model to obtain at least one product keyword output by the model, as well as the keyword quantity of each product keyword; screens each product keyword according to the keyword quantity of each product keyword to determine the target keyword; determines the product industry category corresponding to the target keyword; and determines the industry attribute of the enterprise to be identified according to the product industry category. The above technical solution realizes the automatic prediction of industry attributes by extracting product keywords and determining the industry attributes based on the product industry category corresponding to the keywords, thereby improving the prediction efficiency and prediction accuracy of industry attributes.

[0046] This embodiment also provides a method for constructing a keyword extraction model. In an optional embodiment, the keyword extraction model is constructed as follows: obtain trade sample data of enterprises belonging to different industries; generate sample label values ​​of the trade sample data; the sample label values ​​are standard keywords corresponding to the trade sample data; input the trade sample data with the sample label values ​​into a pre-constructed network model to obtain predicted keywords output by the model; perform model training on the network model according to the standard keywords and predicted keywords to obtain a trained keyword extraction model.

[0047] The trade sample data may include product introduction sample data and product description information sample data. The sample tag value is at least one standard keyword corresponding to the trade sample data.

[0048] Optionally, before inputting the trade sample data into the network model, the trade sample data may be cleaned, deduplicated, filled, and special characters processed.

[0049] The pre-processed trade sample data with sample label values ​​are input into the pre-built network model to obtain the predicted keywords output by the model. According to the standard keywords and predicted keywords, the loss value is determined based on the preset loss function; based on the loss value, the network model is iteratively trained until the iteration number judgment condition is met or the loss value tends to be stable, and a keyword extraction model that has completed training is obtained.

[0050] In the actual prediction process using the keyword extraction model, the accuracy of the results obtained by the model prediction can be verified, so that the trade sample data can be updated using data that meets the accuracy requirements.

[0051] Optionally, the target keywords corresponding to the enterprise trade data of the enterprise to be identified are subjected to accuracy verification to obtain a verification result; if the verification result passes, the enterprise trade data of the enterprise to be identified and its corresponding target keywords are used to update the trade sample data.

[0052] The accuracy check of the target keyword can be manually checked and corrected by relevant technical personnel, or it can be automatically checked. For example, the accuracy can be verified by determining the similarity between the target keyword and the industry attribute finally predicted. The higher the similarity, the higher the accuracy; the lower the similarity, the lower the accuracy. The seat check result with higher accuracy can be passed. If it passes the manual check or passes after manual correction, the enterprise trade data of the enterprise to be identified and its corresponding target keyword are used to update the trade sample data to improve the trade sample data.

[0053] Optionally, since some companies use products that fall into more detailed categories, for example, valves can be subdivided into water valves, air valves, and gas valves, etc., the categories that can be subdivided in the trade sample data can be subdivided into subcategories, thereby improving the trade sample data and reflecting its completeness, breadth, and comprehensiveness.

[0054] By continuously improving the trade sample data, we have achieved accurate construction of the sample data set, which makes the subsequent model learning process more accurate, and thus makes the model prediction accuracy of the trained keyword extraction model higher.

[0055] Embodiment 2

[0056] Figure 2 This is a flow chart of an industry attribute identification method provided in the second embodiment of the present invention. This embodiment is optimized and improved on the basis of the above technical solutions.

[0057] Further, the step of "screening each product keyword according to the number of keywords of each product keyword to determine the target keyword" is refined into "determining the total number of keywords according to the number of keywords of each product keyword; determining the keyword share of each product keyword according to the number of keywords of each product keyword and the total number of keywords; determining the target keyword according to the keyword share of each product keyword." to improve the method of determining the target keyword.

[0058] The step of "determining the product industry category corresponding to the target keyword" is refined into "obtaining standard industry classification data; the standard industry classification data includes at least one standard industry category; determining the matching similarity between the target keyword and each standard industry category; determining the product industry category corresponding to the target keyword based on the matching similarity." to improve the method of determining the product industry category.

[0059] It should be noted that for the parts not described in detail in the embodiments of the present invention, reference can be made to the descriptions of other embodiments. Figure 2 As shown, the method comprises the following specific steps:

[0060] S210: Obtain the enterprise trade data of the enterprise to be identified.

[0061] S220: Input the enterprise trade data into a pre-trained keyword extraction model to obtain at least one product keyword output by the model and the keyword quantity of each product keyword.

[0062] S230: Determine the total number of keywords according to the number of keywords of each product keyword.

[0063] For example, the sum of the keyword quantities of each product keyword can be determined as the total keyword quantity. For example, if the keyword quantity of product keyword A is 10, the keyword quantity of product keyword B is 20, and the keyword quantity of product keyword C is 30, then the total keyword quantity is 60.

[0064] S240: Determine the keyword proportion of each product keyword according to the keyword quantity and the total keyword quantity of each product keyword.

[0065] For example, continuing with the above example, the keyword share of product keyword A is 16.67%, the keyword share of product keyword B is 33.33%, and the keyword share of product keyword C is 50%.

[0066] S250. Determine target keywords based on the keyword proportion of each product keyword.

[0067] For example, a keyword whose proportion is greater than a preset proportion threshold can be determined as a target keyword. The preset proportion threshold can be preset by relevant technical personnel. It is understandable that in order to further improve the accuracy of determining the target keyword, the proportional relationship between the keyword proportions of the product keywords is comprehensively considered, and the target keyword can also be determined according to the proportion difference method.

[0068] In an optional embodiment, a target keyword is determined based on the keyword proportion of each product keyword, including: if there is a first product keyword whose keyword proportion meets the preset proportion threshold judgment condition, the first product keyword is determined as the target keyword; and if there is a second product keyword whose keyword proportion does not meet the preset proportion threshold judgment condition, and the number of second product keywords is at least two, the proportion difference between the keyword proportions corresponding to each second product keyword is determined; each second product keyword whose proportion difference meets the preset difference threshold judgment condition is determined as the target keyword.

[0069] The proportion threshold judgment condition may be preset by relevant technical personnel. Specifically, the proportion threshold judgment condition may be that the keyword proportion is greater than a preset proportion threshold. For example, the preset proportion threshold may be set to 95%.

[0070] Specifically, if the keyword proportion of product keyword A is 96%, which is greater than the preset proportion threshold, product keyword A is determined as the target keyword.

[0071] Among them, the difference threshold judgment condition can be pre-set by relevant technical personnel. For example, the difference threshold judgment condition can be that the difference between the keyword proportions of at least two product keywords is less than a preset difference threshold. For example, the preset difference threshold can be set to 10%.

[0072] Specifically, if product keyword A accounts for 53% of keywords, product keyword B accounts for 47% of keywords, and the difference between product keyword A and product keyword B is 6%, which is less than the preset difference threshold, then both product keyword A and product keyword B can be used as target keywords.

[0073] The above technical solution avoids the situation where products of different types are equally important in the enterprise by considering the difference in proportion in the process of determining the target keywords. When this situation occurs, keywords of each type of products should be considered as product keywords associated with the enterprise, thereby improving the subsequent prediction accuracy of the industry attributes of the enterprise.

[0074] S260. Obtain standard industry classification data; the standard industry classification data includes at least one standard industry category.

[0075] The industry standard classification data may be SIC8 (Standard Industrial Classification Code (Version 8)) industry classification data. The industry standard classification data includes at least one standard industry category and its corresponding industry code. For example, the standard industry category may include agriculture, forestry, fishery and mining, manufacturing, and construction.

[0076] S270: Determine the matching similarity between the target keyword and each standard industry category.

[0077] Exemplarily, similarities between the target keyword and each standard industry category may be determined respectively according to a similarity matching algorithm or a similarity matching model to obtain matching similarities between the target keyword and each standard industry category.

[0078] S280: Determine the product industry category corresponding to the target keyword based on the matching similarity.

[0079] The standard industry category with the highest matching similarity with the target keyword can be determined as the product industry category corresponding to the target keyword.

[0080] S290. Determine the industry attributes of the enterprise to be identified based on the product industry category.

[0081] If there is only one target keyword, the product industry category corresponding to the target keyword is determined as the industry attribute of the enterprise to be identified. If there are at least two target keywords, the product industry category of each target keyword is analyzed for commonality to determine whether it belongs to a similar industry category. If so, its upstream industry is used as the industry attribute of the enterprise to be identified. For example, if the product industry categories corresponding to the two target keywords are the home furnishing industry and the furniture industry, the home improvement industry is used as the industry attribute of the enterprise to be identified. If the product industry category is deployed in a similar industry category, it will be manually approved by relevant technical personnel and the industry attribute will be determined based on the approved results.

[0082] Optionally, the position of the enterprise to be identified in the industrial chain, as well as information such as its upstream and downstream enterprises, can be further determined.

[0083] Embodiment 3

[0084] Figure 3 The structure diagram of an industry attribute identification device provided in the third embodiment of the present invention is shown in FIG. The industry attribute identification device provided in the embodiment of the present invention can be applied to the case of identifying the industry attributes of the enterprise industry in the global trade environment. The industry attribute identification device can be implemented in the form of hardware and / or software, such as Figure 3As shown, the industry attribute identification device can be configured in an electronic device, and specifically includes: a trade data acquisition module 301, a keyword extraction module 302, a keyword screening module 303, an industry category determination module 304 and an industry attribute determination module 305.

[0085] in,

[0086] The trade data acquisition module 301 is used to acquire the enterprise trade data of the enterprise to be identified;

[0087] The keyword extraction module 302 is used to input the enterprise trade data into a pre-trained keyword extraction model to obtain at least one product keyword output by the model and the keyword quantity of each product keyword;

[0088] A keyword screening module 303 is used to screen each of the product keywords according to the keyword quantity of each of the product keywords to determine the target keyword;

[0089] An industry category determination module 304 is used to determine the product industry category corresponding to the target keyword;

[0090] The industry attribute determination module 305 is used to determine the industry attribute of the enterprise to be identified according to the product industry category.

[0091] The technical solution of the embodiment of the present invention inputs the enterprise trade data into the pre-trained keyword extraction model to obtain at least one product keyword output by the model, as well as the keyword quantity of each product keyword; screens each product keyword according to the keyword quantity of each product keyword to determine the target keyword; determines the product industry category corresponding to the target keyword; and determines the industry attribute of the enterprise to be identified according to the product industry category. The above technical solution realizes the automatic prediction of industry attributes by extracting product keywords and determining the industry attributes based on the product industry category corresponding to the keywords, thereby improving the prediction efficiency and prediction accuracy of industry attributes.

[0092] Optionally, the keyword screening module 303 includes:

[0093] A keyword total amount determination unit, used to determine the keyword total amount according to the keyword quantity of each of the product keywords;

[0094] A keyword proportion determination unit, used to determine the keyword proportion of each of the product keywords according to the keyword quantity of each of the product keywords and the total number of the keywords;

[0095] The target keyword determination unit is used to determine the target keyword according to the keyword proportion of each of the product keywords.

[0096] Optionally, a target keyword determination unit includes:

[0097] a first determination subunit, configured to determine the first product keyword as a target keyword if there is a first product keyword whose keyword proportion satisfies a preset proportion threshold judgment condition; and

[0098] a difference determination subunit, configured to determine a difference between the keyword proportions corresponding to the second product keywords if there are second product keywords whose keyword proportions do not meet the preset proportion threshold judgment condition, and the number of the second product keywords is at least two;

[0099] The second determination subunit is used to determine each second product keyword whose proportion difference meets a preset difference threshold judgment condition as a target keyword.

[0100] Optionally, the industry category determination module 304 includes:

[0101] A standard classification data acquisition unit, used to acquire standard industry classification data; the standard industry classification data includes at least one standard industry category;

[0102] A similarity determination unit, used to determine the matching similarity between the target keyword and each of the standard industry categories;

[0103] The industry category determination unit is used to determine the product industry category corresponding to the target keyword according to the matching similarity.

[0104] Optionally, the keyword extraction model is constructed as follows:

[0105] Obtain trade sample data for enterprises belonging to different industries;

[0106] Generate a sample tag value for the trade sample data; the sample tag value is a standard keyword corresponding to the trade sample data;

[0107] Inputting the trade sample data with the sample label value into the pre-built network model to obtain the predicted keywords output by the model;

[0108] The network model is trained according to the standard keywords and the predicted keywords to obtain a keyword extraction model that has completed the training.

[0109] Optionally, performing accuracy verification on target keywords corresponding to the enterprise trade data of the enterprise to be identified to obtain a verification result;

[0110] If the verification result passes, the trade sample data is updated using the enterprise trade data of the enterprise to be identified and its corresponding target keyword.

[0111] The industry attribute identification device provided in the embodiment of the present invention can execute the industry attribute identification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0112] Embodiment 4

[0113] Figure 4 A schematic diagram of the structure of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0114] like Figure 4 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0115] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0116] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the industry attribute recognition method.

[0117] In some embodiments, the industry attribute identification method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the industry attribute identification method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to perform the industry attribute identification method in any other appropriate manner (e.g., by means of firmware).

[0118] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0119] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0120] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0121] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0122] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0123] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0124] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0125] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying industry attributes, characterized in that: include: Obtaining corporate trade data of the enterprise to be identified; Inputting the enterprise trade data into a pre-trained keyword extraction model to obtain at least one product keyword output by the model and the keyword quantity of each product keyword; According to the keyword quantity of each product keyword, each product keyword is screened to determine the target keyword; Determine the product industry category corresponding to the target keyword; According to the product industry category, the industry attribute of the enterprise to be identified is determined.

2. The method according to claim 1, characterized in that The step of screening each of the product keywords according to the keyword quantity of each of the product keywords to determine the target keyword includes: Determine the total number of keywords based on the number of keywords for each of the product keywords; Determine the keyword proportion of each of the product keywords according to the keyword quantity of each of the product keywords and the total number of the keywords; Determine the target keywords based on the keyword proportion of each product keyword.

3. The method according to claim 2, characterized in that Determining the target keywords according to the keyword proportions of the product keywords includes: If there is a first product keyword whose keyword proportion meets the preset proportion threshold judgment condition, the first product keyword is determined as the target keyword; and, If there are second product keywords whose keyword proportions do not meet the preset proportion threshold judgment condition, and the number of the second product keywords is at least two, then determine the proportion difference between the keyword proportions corresponding to each of the second product keywords; Each second product keyword whose proportion difference satisfies a preset difference threshold judgment condition is determined as a target keyword.

4. The method according to claim 1, characterized in that Determining the product industry category corresponding to the target keyword includes: Acquire standard industry classification data; the standard industry classification data includes at least one standard industry category; Determine the matching similarity between the target keyword and each of the standard industry categories; According to the matching similarity, the product industry category corresponding to the target keyword is determined.

5. The method according to claim 1, characterized in that The keyword extraction model is constructed as follows: Obtain trade sample data for enterprises belonging to different industries; Generate a sample tag value for the trade sample data; the sample tag value is a standard keyword corresponding to the trade sample data; Inputting the trade sample data with the sample label value into the pre-built network model to obtain the predicted keywords output by the model; The network model is trained according to the standard keywords and the predicted keywords to obtain a keyword extraction model that has completed the training.

6. The method according to claim 5, characterized in that The method further comprises: Performing accuracy verification on target keywords corresponding to the enterprise trade data of the enterprise to be identified to obtain verification results; If the verification result passes, the trade sample data is updated using the enterprise trade data of the enterprise to be identified and its corresponding target keyword.

7. An industry attribute identification device, characterized in that: include: A trade data acquisition module, used to acquire the enterprise trade data of the enterprise to be identified; A keyword extraction module is used to input the enterprise trade data into a pre-trained keyword extraction model to obtain at least one product keyword output by the model and the keyword quantity of each product keyword; A keyword screening module, used to screen each of the product keywords according to the number of keywords of each of the product keywords, and determine the target keyword; An industry category determination module, used to determine the product industry category corresponding to the target keyword; The industry attribute determination module is used to determine the industry attribute of the enterprise to be identified according to the product industry category.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the industry attribute identification method described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the industry attribute identification method described in any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the industry attribute identification method according to any one of claims 1 to 6.

Images