Industry entity identification method, device, storage medium and electronic device

Abstract

The present invention discloses an industry entity recognition method, device, storage medium and electronic device, the method comprising: obtaining a target search term, recognizing the target search term, determining a primary font size recognition result in the target search term, extracting the last preset digits of the primary font size recognition result as a target entity, querying the target entity to determine company information associated with the target entity, the company information including business scope information, and when the business scope information includes the target entity, marking the target entity as an industry entity. The industry entity recognition method, device, storage medium and electronic device provided by the present invention can more accurately identify industry entity information in the search content, and effectively improve the recognition accuracy of entity categories.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an identification method, device, storage medium and electronic device for industry entities. Background Art

[0002] In the search scenario, in order to accurately identify the user's intention, it is necessary to perform a refined analysis of the search content entered by the user to obtain the corresponding address, font size, name and other information in the search content. When identifying named entities in the search content, due to insufficient data corresponding to industry entities in the training samples, the training model mistakenly identifies industry entities in the named entities as font size entities, resulting in inaccurate search results. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device, storage medium and electronic device for identifying industry entities to solve the technical problem of being unable to accurately identify industry words in a search field.

[0004] According to a first aspect of an embodiment of the present invention, a method for identifying an industry entity is provided, comprising:

[0005] Get the target search terms;

[0006] Identify the target search term and determine a primary font size recognition result in the target search term;

[0007] Extracting the last preset digit of the primary font size recognition result as the target entity;

[0008] Querying the target entity to determine company information associated with the target entity, wherein the company information includes business scope information;

[0009] When the target entity is included in the business scope information, the target entity is marked as an industry entity.

[0010] Optionally, querying the target entity to determine company information associated with the target entity includes:

[0011] Querying the target entity to obtain information of multiple companies associated with the target entity;

[0012] The multiple company information are sorted according to the strength of the correlation, and a preset number of company information are obtained in sequence.

[0013] Optionally, the step of sorting the plurality of company information according to the strength of the correlation and sequentially acquiring a preset number of the plurality of company information includes:

[0014] Obtaining a ranking of the plurality of company information according to the strength of the relationship between the plurality of company information and the target entity, wherein the stronger the relationship between the company information and the target entity, the higher the priority in the ranking;

[0015] A preset number of extracted company information is acquired in descending order of priority in the sorting to obtain a plurality of company information associated with the target entity.

[0016] Optionally, when the target entity is included in the business scope information, marking the target entity as an industry entity includes:

[0017] Verifying the target entity and the plurality of business scope information corresponding to the associated plurality of company information to determine the amount of business scope information including the target entity;

[0018] When the number reaches a preset number, the target entity is marked as an industry entity.

[0019] Optionally, obtaining a target search term from a preset database includes:

[0020] Obtain multiple historical search terms and corresponding search times within a preset time period;

[0021] When the number of searches reaches a preset number of searches, the corresponding historical search terms are used as target search terms.

[0022] Optionally, extracting the last preset digits of the primary font size recognition result as the target entity includes:

[0023] Determining the font size length of the primary font size recognition result;

[0024] When the font size length does not reach a preset length threshold, the last two digits of the font size of the primary font size recognition result are intercepted as the target entity;

[0025] When the font size length reaches a preset length threshold, the last three digits or more of the font size of the primary font size recognition result are intercepted as the target entity.

[0026] Optionally, when the target entity is included in the business scope information, marking the target entity as an industry entity includes:

[0027] Performing field identification on the business scope information according to the target entity;

[0028] When the number of fields related to the target entity in the business scope information reaches a preset number threshold, the target entity is marked as an industry entity.

[0029] According to a second aspect of an embodiment of the present invention, there is provided an identification device for an industry entity, comprising:

[0030] An acquisition module, used to acquire target search terms;

[0031] A first determination module is used to identify the target search term and determine a primary font size recognition result in the target search term;

[0032] A generating module, used for extracting the last preset digits of the primary font size recognition result as a target entity;

[0033] A second determination module is used to query the target entity to determine company information associated with the target entity, wherein the company information includes business scope information;

[0034] A marking module is used to mark the target entity as an industry entity when the target entity is included in the business scope information.

[0035] According to a third aspect of an embodiment of the present invention, there is provided a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for identifying an industry entity as described in any one of the first aspect of the present invention.

[0036] According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0037] a memory having a computer program stored thereon;

[0038] A processor is used to execute the computer program in the memory to implement the steps of the industry entity identification method described in any one of the first aspects of the present invention.

[0039] Through the above technical solution, the target search term is obtained, the target search term is identified, the primary font size recognition result in the target search term is determined, and the target entity is queried based on the preset number of digits at the end of the primary font size recognition result to determine the company information associated with the target entity. The company information includes business scope information. When the target entity is included in the business scope information, the target entity is marked as an industry entity. The industry entity identification method, device, storage medium and electronic device provided by the present invention obtain the corresponding target entity by intercepting the font size entity of the corresponding length, and then retrieve the target entity to obtain the associated company information, confirm whether the corresponding target entity exists in the business scope information of the company information, and determine whether the target entity is an industry entity, thereby effectively improving the recognition accuracy of the entity category.

[0040] Other features and advantages of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present invention but do not constitute a limitation of the present invention. In the accompanying drawings:

[0042] Figure 1 It is a schematic diagram of a method for identifying an industry entity proposed according to an exemplary embodiment.

[0043] Figure 2 The figure is a schematic diagram showing a method for determining company information according to an exemplary embodiment.

[0044] Figure 3 The present invention is a block diagram of an industry entity identification device according to an exemplary embodiment.

[0045] Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment.

[0046] Figure 5 is a block diagram of another electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0047] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0048] In order to solve the technical problem that the industry entity in the search content cannot be accurately identified in the prior art, resulting in inaccurate search results. The embodiment of the present invention provides an industry entity identification method. Figure 1 FIG. 1 is a schematic diagram of an industry entity identification method proposed according to an exemplary embodiment. It can be understood that the method is applied to a server to form a data processing platform. Figure 1 , the identification method of the industry entity comprises the following steps:

[0049] S11, obtaining target search terms.

[0050] It is understandable that this embodiment mainly identifies the industry entities in the search content entered by the user on the mobile terminal, so it is necessary to obtain the corresponding search terms (also referred to as search term information). Usually, in order to facilitate better analysis of user behavior, the server needs to store the search terms in a preset database to facilitate data calls in application scenarios such as user behavior analysis and model training.

[0051] The search terms in the preset database include multiple types of terms. For example, the search terms in the preset database include: person name terms for searching for person information, company name terms for searching for company information, and place terms for searching for place of origin information. Usually, the search terms in the preset database do not have industry entity information. Therefore, in this embodiment, the company name terms in the search terms are analyzed, and the company name terms in the preset database are determined as target search terms by screening the search terms.

[0052] Optionally, the above step S11 includes:

[0053] Get multiple historical search terms and corresponding search times within a preset time period.

[0054] When the number of searches reaches a preset number of searches, the corresponding historical search terms are used as target search terms.

[0055] It is understandable that the more users the server corresponds to, the larger the amount of search terms in the corresponding preset database. In order to obtain the target search terms in the preset database, it is necessary to identify the term type corresponding to each search term and determine the search terms of the corresponding type as the target search terms. Since the number of search terms is large, the search speed of the target search terms is reduced, affecting the user's search experience. Therefore, in this embodiment, it is necessary to set filtering conditions to filter the search terms in the preset database. Generally, the practicality of the search terms gradually decreases with the increase of time, and the more times the same search term appears in the preset database, the more important the search term is.

[0056] In this embodiment, the historical search terms and the corresponding search times within the preset time period are analyzed; when the search times corresponding to the historical search terms reach the preset search times, the historical search terms are used as the target search terms. For example, the preset time period is set to 3 months, and the historical search terms and the corresponding search times within 3 months are obtained; the preset search times are set to 5 times, and if the same historical search term has been searched by the user for more than 5 times within 3 months, the corresponding historical search term is determined to be the target search term.

[0057] S12, identifying the target search term and determining the primary font size recognition result in the target search term.

[0058] It can be understood that in this embodiment, the target search term is the search term corresponding to the company name entity input by the user. Usually, the target search term includes the company name information that needs to be queried, and the company name information usually includes the location information (or the headquarters location information corresponding to the branch), the business name information and the company type information. For example, for the target search term "Shenzhen XX Computer System Co., Ltd.", "Shenzhen" is the location information, "XX" is the business name entity corresponding to the company, "Computer System" is the industry entity, and "Co., Ltd." is the company type.

[0059] Normally, the place of origin information can be confirmed through the administrative division information of the associated country and the location information of the term in the search term, and the company type can be determined by term screening to determine the company type in the target search term. Industry entities need to be compared and confirmed through the industry entity data in the retrieval system, but when the industry entity data in the retrieval system is insufficient, it is easy to misidentify the industry entity in the target search term as a font size entity, that is, for the above target search term, the primary font size recognition result is "XX Computer System". Therefore, in this embodiment, it is necessary to identify the target search term and confirm the primary font size recognition result in the target search term so that the primary font size recognition result can be further identified and processed. For example, according to the naming rules of the company name, usually, the place of origin information and company type information in the target search term can be removed to obtain the term information as the primary font size recognition result.

[0060] S13, extracting the last preset digits of the primary font size recognition result as the target entity.

[0061] It is understandable that according to the naming habits and rules of company names, the industry entity in the target search term usually follows the font size entity, so the industry entity in the primary font size recognition result is mostly the last few digits of the primary font size recognition result. Therefore, the target entity can be obtained by truncating (extracting) the last preset digits of the primary font size recognition result.

[0062] For example, under normal circumstances, the field length of the industry entity can be 2 characters, 3 characters or 4 characters, and is located at the end of the primary font size recognition result. With the reading direction from left to right as the positive direction, 2 characters, 3 characters or 4 characters are intercepted from the end of the primary font size recognition result in the reverse direction as the target entity. Optionally, the target entity can be set to any one of the 2 characters, 3 characters or 4 characters at the end of the primary font size recognition result according to actual conditions, and the 2 characters, 3 characters and 4 characters at the end of the primary font size recognition result can also be intercepted as a font size set, and the font size set is determined as the target entity, so as to perform more comprehensive industry entity recognition later.

[0063] Optionally, the above step S13 includes:

[0064] Determine the font size length of the primary font size recognition result.

[0065] When the font size length does not reach the preset length threshold, the last two digits of the font size entity are truncated as the target entity.

[0066] When the font size length reaches a preset length threshold, the last three digits or more of the font size entity are truncated as the target entity.

[0067] Through the analysis of the company naming rules, it is determined that under normal circumstances, the industry font size in the primary font size recognition result is related to the font size length of the primary font size recognition result. For example, in the primary font size recognition result "XX Life", "XX" is the font size in the primary font size recognition result, and "Life" is the industry entity in the primary font size recognition result; in the primary font size recognition result "YY Education Technology", "YY" is the font size in the primary font size recognition result, and "Education Technology" is the industry entity in the primary font size recognition result. Therefore, in this embodiment, by identifying the font size length of the primary font size recognition result, the number of digits of the font size entity to be truncated from the end is determined. When the overall font size length of the primary font size recognition result does not reach the preset length threshold, the last two digits of the font size are reversely truncated from the end of the font size entity as the target entity. When the overall font size length of the primary font size recognition result reaches the preset length threshold, the last four digits of the font size entity are reversely truncated from the end of the font size entity as the target entity. For example, according to the naming rules of the company name, the preset length threshold is determined to be 6 characters, and for font size entities with a length of less than 6 characters, the last two characters are truncated as the target entity, and for font size entities with a length of more than 6 characters, the last four characters are truncated as the target entity.

[0068] S14, querying the target entity to determine the company information associated with the target entity, wherein the company information includes business scope information.

[0069] It is understandable that in the search system of this embodiment, when the corresponding search content is entered in the search bar, the corresponding company information will be returned according to the search content. The company information includes the company name, legal person, tax information, address information, business information, etc. The target entity obtained through the above steps is used as the search content, and the search system is queried to determine the company information associated with the target entity, and the company information includes business scope information.

[0070] For example, the associated companies determined by searching the target entity may include multiple companies, and the company with the strongest association can be determined as the corresponding company information based on the strength of the associated relationship. The strength of the association can be determined by the number of times the target entity words appear in all the company information corresponding to the query company, as the basis for determining the strength of the association. The more times the target entity words appear, the stronger the association between the company information and the target entity. It should be noted that the company information determined by the query should include business scope information, because usually the business scope information includes industry-related industry terms. If the target entity exists in the business scope information, it can be determined that the target entity is a missing industry entity.

[0071] Figure 2 is a schematic diagram of a method for determining company information according to an exemplary embodiment. Figure 2 The above step S14 includes:

[0072] S141, query the target entity to obtain multiple company information associated with the target entity.

[0073] S142, sorting the plurality of company information according to the strength of the correlation, and sequentially acquiring a preset number of plurality of company information.

[0074] It can be understood that the recognition model is applied to recognize the target entity obtained through the above steps, and multiple company information associated with the target entity is obtained according to the recognition rules of the recognition model, wherein the association relationship can be determined based on the fields corresponding to the target entity or other associated fields contained in the corresponding company information, and the strength of the association between each company identified and the target entity is determined according to the frequency of each field appearing in the corresponding company information. For example, the higher the frequency of the field corresponding to the target entity or the associated field in the corresponding company information, the stronger the association between the company and the target entity. The multiple company information identified are sorted according to the strength of the association, so as to obtain a company information sequence, and extraction is performed in the sequence, so as to obtain a preset number of multiple company information.

[0075] Optionally, the above step S142 includes:

[0076] The ranking of the multiple company information is obtained according to the strength of the correlation between the multiple company information and the target entity. The stronger the correlation between the company information and the target entity, the higher the priority in the ranking.

[0077] A preset number of extracted company information is obtained in descending order of priority in the sorting, so as to obtain a plurality of company information associated with the target entity.

[0078] It can be understood that in this embodiment, by searching the target entity, multiple company information associated with the target entity can be obtained. And according to the strength of the correlation between each company information and the target entity, the obtained multiple company information is prioritized, wherein the higher the priority, the stronger the correlation between the target entity and the company information. Obtain a preset number of multiple company information in the order of priority from high to low in the sorting list, thereby obtaining multiple company information associated with the target entity. For example, in order to improve the recognition speed while ensuring accurate recognition, the preset number of extractions is set to 10, and after obtaining multiple company information through the strength of the correlation and sorting the correlation from high to low, 10 company information related to the target entity are intercepted from high to low.

[0079] S15, when the target entity is included in the business scope information, marking the target entity as an industry entity.

[0080] It can be understood that in the company information obtained through retrieval, the fields recorded in the business scope information can reflect the industry information. By comparing the target entity with the business scope information in the company information, it is determined whether the target entity exists in the business scope information. If the target entity is included in the business scope information, it can be determined that the target entity is a missing industry word, and the target entity can be marked as an industry entity and stored in the retrieval system.

[0081] Optionally, the above step S15 includes:

[0082] Verify the target entity and the multiple business scope information corresponding to the multiple company information associated with it, and determine the amount of business scope information including the target entity.

[0083] When the quantity reaches a preset number, the target entity is marked as an industry entity.

[0084] It can be understood that in this embodiment, the company information corresponding to 10 different companies is obtained through the above steps, which includes 10 business scope information. The target entity is verified with the 10 business scope information to determine the number of business scope information of the target entity in the business scope information. When the number reaches the preset number, the target entity is determined to be an industry entity and stored in the retrieval system. For example, the preset number can be set to 5. When more than 5 of the 10 business scope information obtained include the target entity, the target entity is determined to be an industry entity, and the target entity is stored in the retrieval system as an industry entity, so that the corresponding search field can be subsequently identified as an industry entity; if less than 5 of the 10 business scope information include the target entity, the target entity is determined not to be an industry entity, and the target entity is returned to the font size entity.

[0085] Optionally, the above step S15 may further include:

[0086] Perform field identification on business scope information based on the target entity.

[0087] When the number of fields related to the target entity in the business scope information reaches a preset number threshold, the target entity is marked as an industry entity.

[0088] It is understandable that when a company is registered for industrial and commercial registration, in order to make the company's business scope include all business scopes of the industry, usually, the company's corresponding business scope information includes multiple industry entity information under the industry. In this embodiment, the company information most relevant to the target entity is determined through the above steps, and the business scope information corresponding to the company information is used as a reference. By comparing the business scope information with the target entity, it is determined whether the number of fields related to the target entity in the business scope information reaches a preset quantity threshold, thereby determining whether the target entity is an industry entity. For example, the preset quantity threshold is set to 5. When it is determined that the number of fields related to the target entity in the business scope information exceeds 5, the target entity is determined to be a missing industry entity, and the target entity is stored in the retrieval system as an industry entity.

[0089] Through the above technical solution, the target search term is obtained, the target search term is identified, the primary font size recognition result in the target search term is determined, the last preset digits of the primary font size recognition result are extracted as the target entity, and the target entity is queried to determine the company information associated with the target entity, the company information includes business scope information, and when the target entity is included in the business scope information, the target entity is marked as an industry entity. The industry entity recognition method, device, storage medium and electronic device provided by the present invention obtain the corresponding target entity by intercepting the font size entity of the corresponding length, and then retrieve the target entity to obtain the associated company information, confirm whether the corresponding target entity exists in the business scope information of the company information, determine whether the target entity is an industry entity, and add the corresponding industry entity to the training model, so that the training model can more accurately identify the industry entity information in the search content, and effectively improve the recognition accuracy of the entity category.

[0090] Figure 3 FIG. 1 is a block diagram of an identification device for an industry entity according to an exemplary embodiment. Figure 3 The identification device 100 includes an acquisition module 110 , a first determination module 120 , a generation module 130 , a second determination module 140 and a marking module 150 .

[0091] The acquisition module 110 is used to acquire the target search term.

[0092] The first determination module 120 is used to identify the target search term and determine the primary font size recognition result in the target search term.

[0093] The generating module 130 is used to extract the last preset digits of the primary font size recognition result as the target entity.

[0094] The second determination module 140 is used to query the target entity to determine the company information associated with the target entity, wherein the company information includes business scope information.

[0095] The marking module 150 is used to mark the target entity as an industry entity when the business scope information includes the target entity.

[0096] Optionally, the second determining module 140 includes:

[0097] The query submodule is used to query the target entity and obtain information of multiple companies associated with the target entity.

[0098] The extraction submodule is used to sort multiple company information according to the strength of the correlation and obtain a preset number of company information in sequence.

[0099] Optionally, the extraction submodule can also be used to:

[0100] The ranking of the multiple company information is obtained according to the strength of the correlation between the multiple company information and the target entity. The stronger the correlation between the company information and the target entity, the higher the priority in the ranking.

[0101] A preset number of extracted company information is obtained in descending order of priority in the sorting, so as to obtain a plurality of company information associated with the target entity.

[0102] Optionally, the marking module 150 may also be used for:

[0103] Verify the target entity and the multiple business scope information corresponding to the multiple company information associated with it, and determine the amount of business scope information including the target entity.

[0104] When the quantity reaches a preset number, the target entity is marked as an industry entity.

[0105] Optionally, the acquisition module 110 may also be used to:

[0106] Get multiple historical search terms and corresponding search times within a preset time period.

[0107] When the number of searches reaches a preset number of searches, the corresponding historical search terms are used as target search terms.

[0108] Optionally, the generating module 130 may also be used to:

[0109] Determine the font size length of the primary font size recognition result.

[0110] When the font size length does not reach the preset length threshold, the last two digits of the font size entity are truncated as the target entity.

[0111] When the font size length reaches a preset length threshold, the last three digits or more of the font size entity are truncated as the target entity.

[0112] Optionally, the marking module 150 may also be used for:

[0113] Perform field identification on business scope information based on the target entity.

[0114] When the number of fields related to the target entity in the business scope information reaches a preset number threshold, the target entity is marked as an industry entity.

[0115] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0116] Figure 4 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 4 As shown, the electronic device 400 may include: a processor 401 , a memory 402 . The electronic device 400 may also include one or more of a multimedia component 403 , an input / output (I / O) interface 404 , and a communication component 405 .

[0117] The processor 401 is used to control the overall operation of the electronic device 400 to complete all or part of the steps in the above-mentioned industry entity identification method. The memory 402 is used to store various types of data to support the operation of the electronic device 400, and these data may include, for example, instructions for any application or method used to operate on the electronic device 400, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 402 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 403 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 402 or sent through the communication component 405. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 404 provides an interface between the processor 401 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 4G, 5G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 405 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0118] In an exemplary embodiment, the electronic device 400 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned industry entity identification method.

[0119] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned method for identifying an industry entity are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 402 including program instructions, and the above-mentioned program instructions may be executed by the processor 401 of the electronic device 400 to complete the above-mentioned method for identifying an industry entity.

[0120] Figure 5 5 is a block diagram of another electronic device according to an exemplary embodiment. For example, the electronic device 500 may be provided as a server. Figure 5 The electronic device 500 includes a processor 522, which may be one or more, and a memory 542 for storing a computer program executable by the processor 522. The computer program stored in the memory 542 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 522 may be configured to execute the computer program to perform the above-mentioned industry entity identification method.

[0121] In addition, the electronic device 500 may further include a power supply component 526 and a communication component 550. The power supply component 526 may be configured to perform power management of the electronic device 500, and the communication component 550 may be configured to implement communication of the electronic device 500, for example, wired or wireless communication. In addition, the electronic device 500 may further include an input / output (I / O) interface 558. The electronic device 500 may operate based on an operating system stored in the memory 542, such as Windows Server 2003. TM , Mac OSX TM , Unix TM , Linux TM etc.

[0122] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned method for identifying an industry entity are implemented. For example, the non-transitory computer-readable storage medium may be the above-mentioned memory 542 including program instructions, and the above-mentioned program instructions may be executed by the processor 522 of the electronic device 500 to complete the above-mentioned method for identifying an industry entity.

[0123] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned industry entity identification method when executed by the programmable device.

[0124] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, a variety of simple modifications can be made to the technical solution of the present invention, and these simple modifications all belong to the protection scope of the present invention.

[0125] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction, and the present invention will not further explain various possible combinations.

[0126] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the present invention, they should also be regarded as the contents disclosed by the present invention.

Claims

1. A method for identifying an industry entity, characterized in that: include: Get the target search terms; Identify the target search term and determine a primary font size recognition result in the target search term; Extracting the last preset digit of the primary font size recognition result as the target entity; Querying the target entity to determine company information associated with the target entity, wherein the company information includes business scope information; In a case where the target entity is included in the business scope information, marking the target entity as an industry entity; The step of extracting the last preset digit of the primary font size recognition result as the target entity includes: Determining the font size length of the primary font size recognition result; When the font size length does not reach a preset length threshold, intercepting the last two digits of the primary font size recognition result as the target entity; When the length of the font size reaches a preset length threshold, the last three digits or more of the font size of the primary font size recognition result are intercepted as the target entity; When the target entity is included in the business scope information, marking the target entity as an industry entity includes: Verifying the target entity and the multiple business scope information corresponding to the multiple company information associated therewith, and determining the amount of business scope information including the target entity; When the number reaches a preset number, the target entity is marked as the industry entity.

2. The identification method according to claim 1, characterized in that: The querying the target entity to determine the company information associated with the target entity includes: Querying the target entity to obtain information of multiple companies associated with the target entity; The multiple company information are sorted according to the strength of the correlation, and a preset number of company information are obtained in sequence.

3. The identification method according to claim 2, characterized in that: The step of sorting the plurality of company information according to the strength of the correlation and sequentially acquiring a preset number of company information includes: Obtaining a ranking of the plurality of company information according to the strength of the relationship between the plurality of company information and the target entity, wherein the stronger the relationship between the company information and the target entity, the higher the priority in the ranking; A preset number of extracted company information is acquired in descending order of priority in the sorting to obtain a plurality of company information associated with the target entity.

4. The identification method according to claim 1, characterized in that: The step of obtaining a target search term includes: Obtaining multiple historical search terms and corresponding search times within a preset time period from a preset database; When the number of searches reaches a preset number of searches, the corresponding historical search terms are used as target search terms.

5. The identification method according to claim 1, characterized in that: When the target entity is included in the business scope information, marking the target entity as an industry entity includes: Performing field identification on the business scope information according to the target entity; When the number of fields related to the target entity in the business scope information reaches a preset number threshold, the target entity is marked as an industry entity.

6. An identification device for an industry entity, characterized in that: include: An acquisition module, used to acquire target search terms; A first determination module is used to identify the target search term and determine a primary font size recognition result in the target search term; A generating module, used for extracting the last preset digits of the primary font size recognition result as a target entity; The extracting the last preset digits of the primary font size recognition result as the target entity includes: determining the font size length of the primary font size recognition result; if the font size length does not reach the preset length threshold, intercepting the last two digits of the primary font size recognition result as the target entity; if the font size length reaches the preset length threshold, intercepting the last three digits and above of the primary font size recognition result as the target entity; A second determination module is used to query the target entity to determine company information associated with the target entity, wherein the company information includes business scope information; A marking module, used for marking the target entity as an industry entity when the target entity is included in the business scope information; marking the target entity as an industry entity when the target entity is included in the business scope information, including: verifying the target entity and multiple business scope information corresponding to the associated multiple company information, and determining the number of business scope information including the target entity; when the number reaches a preset number, marking the target entity as the industry entity.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 5 are implemented.

8. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 5.

Images