Method, device and equipment for identifying company to which user belongs, and storage medium

Abstract

The invention discloses an identification method and device for a company to which a user belongs, equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring to-be-processed company information of a target user, and determining an information source of the to-be-processed company information; based on the information source, accurately matching the company information to be processed with the company basic information database; if the information source is a non-credible source and the accurate matching is not passed, performing fuzzy matching on the to-be-processed company information and a company basic information database to obtain at least one candidate company; determining candidate user data and candidate company data of the at least one candidate company according to the company information to be processed and the at least one candidate company; and based on an inverted deep learning model, according to the candidate user data and the candidate company data of the at least one candidate company, determining a target company to which the target user belongs from the candidate companies. According to the technical scheme, the accuracy and reliability of identifying the company to which the user belongs can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, in particular to the field of artificial intelligence technology, and specifically to a method, device, equipment and storage medium for identifying a company to which a user belongs. Background Art

[0002] At present, there are many channels for obtaining the company information of bank customers, including channels for customers to apply for business, channels for salary payment, channels for social security and provident fund, etc. How to integrate the company information sources from these multiple channels and how to confirm the correct company information is a big problem.

[0003] There is no mature solution for this specific fine-grained problem. At the specific analysis level, a certain channel may be used as the standard, but at the actual operation level, customer information is not available in every channel, so it is impossible to use only one channel as the standard. At present, the above problem is mainly dealt with in combination with the semantic similarity analysis model. There are mainly two existing semantic similarity methods: vector similarity and edit distance similarity. The similarity of vector similarity and edit distance is mainly for the determination of vectors and edit distances. The requirements are relatively high. In the case of semantic similarity analysis in fuzzy scenes, the accuracy and reliability of semantic analysis cannot be guaranteed. Summary of the invention

[0004] The present application provides a method, apparatus, device and storage medium for identifying a company to which a user belongs, so as to improve the accuracy and reliability of identifying a company to which a user belongs.

[0005] According to one aspect of the present application, a method for identifying a company to which a user belongs is provided, the method comprising:

[0006] Obtaining the target user's company information to be processed, and determining the information source of the company information to be processed; the information source includes a trusted source and an untrusted source;

[0007] Based on the information source, accurately match the company information to be processed with the company basic information database;

[0008] If the information source is an untrusted source and the precise matching fails, fuzzy matching is performed on the company information to be processed and the company basic information database to obtain at least one candidate company;

[0009] Determining candidate user data and candidate company data of the at least one candidate company according to the to-be-processed company information and the at least one candidate company;

[0010] Based on the inverted deep learning model, the target company to which the target user belongs is determined from the candidate companies according to the candidate user data and the candidate company data of the at least one candidate company.

[0011] According to another aspect of the present application, a device for identifying a company to which a user belongs is provided, the device comprising:

[0012] An information source determination module is used to obtain the target user's company information to be processed and determine the information source of the company information to be processed; the information source includes a trusted source and an untrusted source;

[0013] A first information matching module, used for accurately matching the company information to be processed with a company basic information database based on the information source;

[0014] A second information matching module, configured to perform fuzzy matching on the company information to be processed and the company basic information database to obtain at least one candidate company if the information source is an untrusted source and the precise matching fails;

[0015] a data determination module, configured to determine candidate user data and candidate company data of the at least one candidate company according to the to-be-processed company information and the at least one candidate company;

[0016] A company determination module is used to determine the target company to which the target user belongs from the candidate companies based on the inverted deep learning model and according to the candidate user data and the candidate company data of the at least one candidate company.

[0017] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0018] one or more processors;

[0019] A memory for storing one or more programs;

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement any one of the methods for identifying the company to which a user belongs provided in the embodiments of the present application.

[0021] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for identifying the company to which a user belongs provided in any one of the embodiments of the present application is implemented.

[0022] According to another aspect of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the computer program implements any method for identifying a company to which a user belongs provided in the embodiments of the present application.

[0023] This application obtains the target user's company information to be processed and determines the information source of the company information to be processed; the information source includes a trusted source and an untrusted source; based on the information source, the company information to be processed is accurately matched with the company basic information database; if the information source is an untrusted source and the accurate match fails, the company information to be processed is fuzzy matched with the company basic information database to obtain at least one candidate company; based on the company information to be processed and at least one candidate company, the candidate user data and the candidate company data of at least one candidate company are determined; based on the inverted deep learning model, the target company to which the target user belongs is determined from the candidate companies based on the candidate user data and the candidate company data of at least one candidate company. The above technical solution can improve the accuracy and reliability of identifying the company to which the user belongs. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a method for identifying a company to which a user belongs provided according to Embodiment 1 of the present application;

[0025] Figure 2 is a flow chart of a method for identifying a company to which a user belongs provided according to Embodiment 2 of the present application;

[0026] Figure 3 is a schematic diagram of the structure of a device for identifying a company to which a user belongs provided according to Embodiment 3 of the present application;

[0027] Figure 4 It is a structural diagram of an electronic device that implements the method for identifying the company to which a user belongs according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application 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 interchangeable where appropriate, so that the embodiments of the present application 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 comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] In addition, it should be noted that in the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of relevant data such as the company information to be processed and the source of information are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals; the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with the relevant laws, regulations and standards of the relevant regions.

[0031] Embodiment 1

[0032] Figure 1 This is a flowchart of a method for identifying the company to which a user belongs provided according to the first embodiment of the present application. This embodiment can be applied to identifying the company to which a user belongs in ambiguous scenarios, and can be executed by an identification device for the company to which the user belongs. The identification device for the company to which the user belongs can be implemented in the form of hardware and / or software, and the identification device for the company to which the user belongs can be configured in a computer device, such as a server.

[0033] like Figure 1 As shown, the method includes:

[0034] S110, obtaining the target user's company information to be processed, and determining the information source of the company information to be processed; the information source includes a trusted source and an untrusted source.

[0035] In this embodiment, the target user is a specific user that needs to be processed in the system or service, usually the object that the system or application pays attention to and needs to process or analyze data; wherein the target user may be a customer of the banking system. The company information to be processed refers to the company data that has not yet been processed or confirmed; such data may come from external or internal unaudited information and needs to be verified or matched; wherein the company information to be processed refers to the information of the company to which the target user belongs. The source of information refers to the source channel of the company information to be processed, which is divided into trusted sources and untrusted sources; wherein, a trusted source refers to a reliable and verified source, usually from an official or certified channel (such as social security, provident fund, etc.), with high information quality; an untrusted source refers to a source that is not fully trusted, which may be unverified third-party data or a signal from an uncertain source (such as the source of the information may be manually entered), and the information may be erroneous or inaccurate.

[0036] Exemplarily, the to-be-processed company information of the company to which the target customer of the banking system belongs is obtained, and the information source of the to-be-processed company information is determined.

[0037] S120. Based on the information source, accurately match the company information to be processed with the company basic information database.

[0038] In this embodiment, the company basic information database refers to a database that stores basic enterprise data (such as company name, registration information, business scope, etc.); this database is usually used as a basis for data matching and verification. Accurate matching refers to an accurate algorithm or rule that compares the company information to be processed with the relevant data in the company basic information database with high precision.

[0039] Exemplarily, based on the source of information, the company name or company account in the company information to be processed is accurately matched with the company basic information database.

[0040] S130. If the information source is an untrustworthy source and the exact match fails, the company information to be processed is fuzzily matched with the company basic information database to obtain at least one candidate company.

[0041] In this embodiment, fuzzy matching refers to using looser matching rules for comparison, allowing for small deviations or incomplete consistency in some data. Candidate companies refer to multiple companies that may match the company information to be processed and are selected from the company basic information database after fuzzy matching; due to incompletely credible information sources or incomplete matching, the system provides multiple candidate items for further analysis.

[0042] Exemplarily, if the information source is an untrusted source and the exact match fails, a fuzzy search is performed in the company basic information database based on the company name in the company information to be processed to find the suspected company and obtain at least one candidate company.

[0043] Furthermore, if the fuzzy match fails, a data anomaly alarm is generated.

[0044] In an optional implementation, if the precise match is successful, the company in the company basic information database that matches the company information to be processed is determined as the target company of the target user; if the information source is a trusted source and the precise match is not successful, a data anomaly alarm is generated.

[0045] In this embodiment, the data abnormality alarm refers to an alarm instruction for authenticating abnormal customer data, which requires manual intervention and judgment.

[0046] It should be noted that regardless of whether the information source is a trusted source or an untrusted source, if the company name or company account in the company information to be processed can be accurately matched with the company basic information database, then the company information to be processed is deemed to be correct, and the company name or company account in the company information to be processed can be directly determined to be the target company name or company account to which the target user belongs.

[0047] S140: Determine candidate user data and candidate company data of at least one candidate company according to the company information to be processed and at least one candidate company.

[0048] In this embodiment, candidate user data refers to possible data related to the target user extracted by the system based on the company information to be processed and the candidate company information; these data may include the target user's preferences, background, or related information associated with the candidate company; wherein the candidate user data may be serialized multi-dimensional time series data. Candidate company data refers to all information related to the candidate company, which is used to further analyze and identify the company to which the target user belongs; these data usually include company details, business areas, historical records, etc.; wherein the candidate company data may be serialized multi-dimensional time series data.

[0049] Exemplarily, data extraction is performed on the company information to be processed and the company information of at least one candidate company to obtain user structured data and at least one company structured data; and the user structured data and at least one company structured data are serialized to obtain candidate user data and candidate company data of at least one candidate company.

[0050] S150. Based on the inverted deep learning model, determine the target company to which the target user belongs from the candidate companies according to the candidate user data and the candidate company data of at least one candidate company.

[0051] In this embodiment, the inverted deep learning model refers to a machine learning model that infers a target or conclusion through reverse reasoning or based on existing data; unlike the traditional deep learning model, its reasoning process may be to reversely deduce input data or categories from the result or output; wherein, the inverted deep learning model may be an inverted attention mechanism model. The target company refers to the company that is finally determined to belong to the target user.

[0052] Exemplarily, determining the target company to which the target user belongs from the candidate companies may be determining the name of the target company to which the target user belongs from the company names of the candidate companies.

[0053] The embodiment of the present application obtains the target user's company information to be processed and determines the information source of the company information to be processed; the information source includes a trusted source and an untrusted source; based on the information source, the company information to be processed is accurately matched with the company basic information database; if the information source is an untrusted source and the accurate match fails, the company information to be processed is fuzzy matched with the company basic information database to obtain at least one candidate company; based on the company information to be processed and at least one candidate company, the candidate user data and the candidate company data of at least one candidate company are determined; based on the inverted deep learning model, the target company to which the target user belongs is determined from the candidate companies based on the candidate user data and the candidate company data of at least one candidate company. The above technical solution can improve the accuracy and reliability of identifying the company to which the user belongs.

[0054] Embodiment 2

[0055] Figure 2 This is a flow chart of a method for identifying the company to which a user belongs provided in accordance with Example 2 of the present application. Based on the technical solutions of the above-mentioned embodiments, this embodiment refines "based on an inverted deep learning model, according to candidate user data and candidate company data of at least one candidate company, determining the target company to which the target user belongs from candidate companies" into "based on an inverted deep learning model, reconstructing candidate user data and candidate company data of at least one candidate company to obtain candidate user text and candidate company text of at least one candidate company; calculating similarity between the candidate company text and the candidate company text of at least one candidate company, respectively, to obtain similarity calculation results; determining the target company to which the target user belongs from among the candidate companies based on the similarity calculation results". It should be noted that for the parts not described in detail in the embodiments of the present application, please refer to the relevant statements of other embodiments. Figure 2 As shown, the method includes:

[0056] S210, obtaining the target user's company information to be processed, and determining the information source of the company information to be processed; the information source includes a trusted source and an untrusted source.

[0057] S220. Based on the information source, accurately match the company information to be processed with the company basic information database.

[0058] S230: If the information source is an untrustworthy source and the exact match fails, the company information to be processed is fuzzily matched with the company basic information database to obtain at least one candidate company.

[0059] S240: Determine candidate user data and candidate company data of at least one candidate company according to the company information to be processed and at least one candidate company.

[0060] Optionally, data extraction is performed on the company information to be processed to obtain user structured data of the target user; taking at least one candidate company as an index, candidate company information corresponding to at least one candidate company is obtained from the company basic information database; data extraction is performed on the candidate company information corresponding to at least one candidate company to obtain company structured data of at least one candidate company; user structured data and company structured data of at least one candidate company are serialized respectively to obtain candidate user data and candidate company data of at least one candidate company.

[0061] In this embodiment, user structured data refers to detailed information about the user, which is stored in a predefined format, usually information about the user's identity, tax number, industry field of the company to which they belong, etc. Candidate company information refers to detailed data of candidate companies, usually including a series of structured information such as company name, industry category, contact information, founder, annual income, etc. Data extraction refers to the process of extracting useful information from a data source. Company structured data refers to company information stored in a pre-set format. These data can usually be conveniently stored in structured forms such as tables and databases, and are easy to query, process and analyze. Serialization refers to the conversion of data structures (such as objects, arrays, data tables, etc.) into a format that can be stored or transmitted.

[0062] S250. Based on the inverted deep learning model, reconstruct the candidate user data and the candidate company data of at least one candidate company to obtain the candidate user text and the candidate company text of at least one candidate company.

[0063] In this embodiment, the candidate user text refers to the text information reconstructed based on the candidate user data. These text descriptions may include user identity, tax number, company industry, etc., and are usually natural language texts generated from structured data through models. Candidate company text refers to the text information reconstructed from candidate company data through an inverted deep learning model, and is usually used to describe the company's characteristics, business areas, scale, etc.

[0064] Exemplarily, the inverted attention mechanism model is used to reconstruct the candidate user data and the candidate company data respectively to obtain candidate user text and candidate company text of at least one candidate company.

[0065] In an optional embodiment, the inverted deep learning model can be an inverted attention mechanism model; the inverted attention mechanism model is a model that only contains an encoder structure; the inverted attention mechanism model includes an embedding layer, a mapping layer and an attention mechanism module; wherein the attention mechanism module includes an attention layer, a normalization layer and a feedforward layer.

[0066] It should be noted that the embedding layer and the mapping layer in the inverted attention mechanism model of the present application are both implemented using a multi-layer perceptron.

[0067] It is understandable that the traditional attention mechanism model has the problem of insufficient multi-dimensional feature extraction. The inverted attention mechanism model can independently map the entire sequence of variables into tokens (the basic unit of the input sequence) to mine multi-variable correlation features in tokens. By generating sequences, the input information (the company information to be processed and the candidate company information of fuzzy matching) can be reconstructed.

[0068] S260: Calculate similarity between the candidate company text and the candidate company text of at least one candidate company to obtain a similarity calculation result.

[0069] In this embodiment, similarity calculation refers to measuring the similarity between two texts by some mathematical or algorithmic means. The similarity calculation result refers to the quantitative result obtained by some similarity calculation method, which is usually a numerical value, indicating the similarity or difference between the two texts; this numerical value can be used to sort companies, filter similar companies or recommend companies.

[0070] Exemplarily, based on the large model, similarity calculations are performed on the candidate company texts respectively with the candidate company texts of at least one candidate company to obtain at least one similarity value; the similarity values ​​are aggregated to obtain a similarity calculation result.

[0071] It should be noted that the method of similarity calculation is artificially preset according to actual conditions or experience values, and this application does not make any specific limitation on this; illustratively, the similarity calculation can be cosine similarity calculation or Euclidean distance similarity calculation.

[0072] S270: Determine the target company to which the target user belongs from the candidate companies according to the similarity calculation result.

[0073] Optionally, the similarity calculation result includes at least one similarity value; the similarity value and the candidate company have a one-to-one correspondence.

[0074] In this embodiment, the similarity value refers to a numerical value that measures the similarity between two data objects (such as company documents); generally, the higher the similarity value, the greater the similarity between the two objects.

[0075] Furthermore, if the similarity value meets the similarity threshold requirement, the candidate company corresponding to the similarity value is determined as the candidate company; and the target company to which the target user belongs is determined from the candidate companies according to the similarity value of at least one candidate company.

[0076] In this embodiment, the similarity threshold requirement is artificially preset according to actual conditions or experience values, and the requirement may be that the similarity value is greater than the similarity threshold. The candidate company refers to a company obtained by screening the similarity values ​​of the candidate companies.

[0077] Optionally, determining the target company to which the target user belongs from the candidate companies based on the similarity value of at least one candidate company can be by numerically comparing the similarity value of at least one candidate company to determine the maximum similarity value; and determining the candidate company corresponding to the maximum similarity value as the target company to which the target user belongs.

[0078] Exemplarily, for each similarity value corresponding to a candidate company, if the similarity value exceeds a similarity threshold, the candidate company corresponding to the similarity value is determined as the candidate company; the similarity values ​​of the candidate companies are compared, and the candidate company with the largest similarity value is determined as the target company.

[0079] In an optional implementation, if there is no similarity value that satisfies the similarity threshold result in the similarity calculation result, a data anomaly alarm is generated.

[0080] The embodiment of the present application obtains the target user's company information to be processed and determines the information source of the company information to be processed; the information source includes a trusted source and an untrusted source; based on the information source, the company information to be processed is accurately matched with the company basic information database; if the information source is an untrusted source and the accurate match fails, the company information to be processed is fuzzy matched with the company basic information database to obtain at least one candidate company; based on the company information to be processed and at least one candidate company, the candidate user data and the candidate company data of at least one candidate company are determined; based on the inverted deep learning model, the candidate user data and the candidate company data of at least one candidate company are reconstructed to obtain the candidate user text and the candidate company text of at least one candidate company; the candidate company text is respectively calculated for similarity with the candidate company text of at least one candidate company to obtain a similarity calculation result; based on the similarity calculation result, the target company to which the target user belongs is determined from the candidate companies. The above technical scheme can improve the accuracy and reliability of identifying the company to which the user belongs.

[0081] Embodiment 3

[0082] Figure 3 This is a schematic diagram of a structure of a device for identifying a company to which a user belongs according to Embodiment 3 of the present application, which can be applied to identifying a company to which a user belongs in a fuzzy scene. The device for identifying a company to which a user belongs can be implemented in the form of hardware and / or software, and can be configured in a computer device, such as a server. Figure 3 As shown, the device comprises:

[0083] The information source determination module 310 is used to obtain the target user's company information to be processed and determine the information source of the company information to be processed; the information source includes a trusted source and an untrusted source;

[0084] The first information matching module 320 is used to accurately match the company information to be processed with the company basic information database based on the information source;

[0085] The second information matching module 330 is used to perform fuzzy matching between the company information to be processed and the company basic information database to obtain at least one candidate company if the information source is an untrustworthy source and the exact match fails;

[0086] A data determination module 340, configured to determine candidate user data and candidate company data of at least one candidate company based on the company information to be processed and at least one candidate company;

[0087] The company determination module 350 is used to determine the target company to which the target user belongs from the candidate companies based on the inverted deep learning model according to the candidate user data and the candidate company data of at least one candidate company.

[0088] The embodiment of the present application obtains the target user's company information to be processed and determines the information source of the company information to be processed; the information source includes a trusted source and an untrusted source; based on the information source, the company information to be processed is accurately matched with the company basic information database; if the information source is an untrusted source and the accurate match fails, the company information to be processed is fuzzy matched with the company basic information database to obtain at least one candidate company; based on the company information to be processed and at least one candidate company, the candidate user data and the candidate company data of at least one candidate company are determined; based on the inverted deep learning model, the target company to which the target user belongs is determined from the candidate companies based on the candidate user data and the candidate company data of at least one candidate company. The above technical solution can improve the accuracy and reliability of identifying the company to which the user belongs.

[0089] Optionally, the company determination module 350 includes:

[0090] A data reconstruction unit, configured to reconstruct the candidate user data and the candidate company data of at least one candidate company based on an inverted deep learning model to obtain a candidate user text and a candidate company text of at least one candidate company;

[0091] A similarity calculation unit, used to perform similarity calculation on the candidate company text and the candidate company text of at least one candidate company to obtain a similarity calculation result;

[0092] The company determination unit is used to determine the target company to which the target user belongs from the candidate companies according to the similarity calculation result.

[0093] Optionally, the similarity calculation result includes at least one similarity value; the similarity value and the candidate company are in a one-to-one correspondence; accordingly, the company determination unit includes:

[0094] A first company determination subunit is used to determine the candidate company corresponding to the similarity value as the company to be selected if the similarity value meets the similarity threshold requirement;

[0095] The second company determination subunit is used to determine the target company to which the target user belongs from the companies to be selected according to the similarity value of at least one company to be selected.

[0096] Optionally, the second company determines a subunit specifically for:

[0097] Numerically comparing the similarity values ​​of at least one candidate company to determine a maximum similarity value;

[0098] The candidate company corresponding to the maximum similarity value is determined as the target company to which the target user belongs.

[0099] Optionally, the data determination module 340 is specifically configured to:

[0100] Extract data from the company information to be processed and obtain the user structured data of the target users;

[0101] Taking at least one candidate company as an index, obtaining candidate company information corresponding to at least one candidate company from a company basic information database;

[0102] Extracting data from candidate company information corresponding to at least one candidate company to obtain company structured data of at least one candidate company;

[0103] The user structured data and the company structured data of at least one candidate company are serialized respectively to obtain candidate user data and candidate company data of at least one candidate company.

[0104] Optionally, the first information matching module 320 is specifically configured to:

[0105] If the exact match is successful, the company in the company basic information database that matches the company information to be processed will be determined as the target company of the target user;

[0106] If the information source is a trusted source and the exact match fails, a data anomaly alarm is generated.

[0107] The device for identifying the company to which a user belongs provided in the embodiment of the present application can execute the method for identifying the company to which a user belongs provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the method for identifying the company to which each user belongs.

[0108] According to an embodiment of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.

[0109] Embodiment 4

[0110] Figure 4 4 is a schematic diagram of the structure of an electronic device 410 that implements the method for identifying the company to which the user belongs in the embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may 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 application described and / or required herein.

[0111] like Figure 4 As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In RAM413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, ROM412 and RAM413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0112] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0113] Processor 411 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. Processor 411 performs the various methods and processes described above, such as a method for identifying a company to which a user belongs.

[0114] In some embodiments, the method for identifying the company to which the user belongs may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the method for identifying the company to which the user belongs described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured as the method for identifying the company to which the user belongs by any other appropriate means (e.g., by means of firmware).

[0115] 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.

[0116] Computer programs for implementing the methods of the present application 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 user's company identification 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 as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0117] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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 recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0122] The above specific implementations do not constitute a limitation on the protection scope of this application. 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 modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for identifying a company to which a user belongs, characterized in that: include: Obtaining the target user's company information to be processed, and determining the information source of the company information to be processed; the information source includes a trusted source and an untrusted source; Based on the information source, accurately match the company information to be processed with the company basic information database; If the information source is an untrusted source and the precise matching fails, fuzzy matching is performed on the company information to be processed and the company basic information database to obtain at least one candidate company; Determining candidate user data and candidate company data of the at least one candidate company according to the to-be-processed company information and the at least one candidate company; Based on the inverted deep learning model, the target company to which the target user belongs is determined from the candidate companies according to the candidate user data and the candidate company data of the at least one candidate company.

2. The method according to claim 1, characterized in that: Based on the inverted deep learning model, determining the target company to which the target user belongs from the candidate companies according to the candidate user data and the candidate company data of the at least one candidate company, comprising: Based on the inverted deep learning model, reconstruct the candidate user data and the candidate company data of the at least one candidate company to obtain a candidate user text and a candidate company text of the at least one candidate company; Calculate similarity between the candidate company text and the candidate company text of the at least one candidate company to obtain a similarity calculation result; According to the similarity calculation result, the target company to which the target user belongs is determined from the candidate companies.

3. The method according to claim 2, characterized in that The similarity calculation result includes at least one similarity value; the similarity value and the candidate company are in a one-to-one correspondence; accordingly, determining the target company to which the target user belongs from the candidate companies according to the similarity calculation result includes: If the similarity value meets the similarity threshold requirement, the candidate company corresponding to the similarity value is determined as the company to be selected; According to the similarity value of at least one company to be selected, a target company to which the target user belongs is determined from the companies to be selected.

4. The method according to claim 3, characterized in that Determining a target company to which the target user belongs from the companies to be selected according to a similarity value of at least one company to be selected includes: Numerically comparing the similarity values ​​of at least one candidate company to determine a maximum similarity value; The candidate company corresponding to the maximum similarity value is determined as the target company to which the target user belongs.

5. The method according to claim 1, characterized in that The determining, according to the to-be-processed company information and the at least one candidate company, candidate user data and candidate company data of the at least one candidate company comprises: Extracting data from the company information to be processed to obtain structured user data of the target user; Taking the at least one candidate company as an index, acquiring candidate company information corresponding to the at least one candidate company from the company basic information database; Extracting data from candidate company information corresponding to the at least one candidate company respectively to obtain company structured data of the at least one candidate company; The user structured data and the company structured data of the at least one candidate company are serialized respectively to obtain candidate user data and candidate company data of the at least one candidate company.

6. The method according to claim 1, characterized in that The method further comprises: If the precise match is successful, the company in the company basic information database that matches the company information to be processed is determined as the target company of the target user; If the information source is a credible source and the precise match fails, a data anomaly alarm is generated.

7. A device for identifying a company to which a user belongs, characterized in that: include: An information source determination module is used to obtain the target user's company information to be processed and determine the information source of the company information to be processed; the information source includes a trusted source and an untrusted source; A first information matching module, used for accurately matching the company information to be processed with a company basic information database based on the information source; A second information matching module, configured to perform fuzzy matching on the company information to be processed and the company basic information database to obtain at least one candidate company if the information source is an untrusted source and the precise matching fails; a data determination module, configured to determine candidate user data and candidate company data of the at least one candidate company according to the to-be-processed company information and the at least one candidate company; A company determination module is used to determine the target company to which the target user belongs from the candidate companies based on the inverted deep learning model and according to the candidate user data and the candidate company data of the at least one candidate company.

8. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for identifying the company to which a user belongs as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for identifying the company to which a user belongs as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for identifying a company to which a user belongs according to any one of claims 1 to 6.

Images