Methods, apparatuses, devices, and media for identifying an industry to which a business belongs

Abstract

The present application relates to the technical field of data processing, and particularly relates to a method, device and medium for identifying the industry of an enterprise. The method comprises: obtaining a candidate enterprise set having a direct or indirect close transaction relationship with a leading enterprise in a specific industry; matching the industry description of the specific industry with the business scope of each candidate enterprise in the candidate enterprise set; when the two are matched, determining that the candidate enterprise belongs to the specific industry, otherwise, determining that the candidate enterprise does not belong to the specific industry. The present application is not completely based on expert experience, guarantees objectivity, can timely respond to the development and change of external environment and internal business, can further improve the accuracy and adjustability of industry identification, has strong interpretability, meets the requirements of supervision and auditing, and can be implemented by using computer and network technology, and has lower implementation cost than learning models.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a method, device, equipment and medium for identifying the industry of an enterprise. BACKGROUND

[0002] The state macro level often provides policy guidance and support for different industries according to needs, so a method for quickly and accurately identifying the industry of an enterprise is needed to meet the needs of banks to tilt credit resources.

[0003] At present, the method for identifying whether an enterprise is in a specific industry mainly falls into two categories. One is the artificial rule type, which uses expert experience and business development trends to solidify the knowledge of identifying an enterprise as a specific industry into rules, and uses the rules to identify whether an enterprise belongs to a specific industry. The other is the learning model type, which uses a deep learning model to identify whether an enterprise belongs to a specific industry.

[0004] However, the expert experience and other knowledge used in the artificial rule type often have subjectivity, and different experts may not have the same understanding of the industry of an enterprise. In addition, the external environment and industry development are constantly changing, and the solidified rules may not be able to keep up with the changes in the outside world. The deep learning model used in the learning model type is not mature in technology, and is difficult to implement. In addition, the deep learning model often has poor interpretability, which cannot meet the regulatory and audit requirements of banks. SUMMARY

[0005] In view of the above problems of the prior art, the purpose of the present application is to provide a method, device, equipment and medium for identifying the industry of an enterprise, which is not completely based on expert experience, ensures objectivity, can respond to the development and changes of the external environment and internal business in a timely manner, can further improve the accuracy and adjustability of industry identification, has strong interpretability, meets regulatory and audit requirements, and can be implemented using computer and network technology, with lower implementation cost than the learning model type.

[0006] To solve the above problems, the present application provides a method for identifying the industry of an enterprise, characterized in that the method is used in an electronic device, and the method comprises:

[0007] obtaining a candidate enterprise set having a direct or indirect close transaction relationship with a head enterprise in a specific industry;

[0008] matching the industry description of the specific industry with the business scope of each candidate enterprise in the candidate enterprise set;

[0009] When the two are matched, it is determined that the candidate enterprise belongs to the specific industry, otherwise it is determined that the candidate enterprise does not belong to the specific industry.

[0010] Further, the obtaining the candidate enterprise set having a direct or indirect close trading relationship with the head enterprise in the specific industry further comprises:

[0011] obtaining a head enterprise set of a specific industry, and for each head enterprise to be processed in the head enterprise set, obtaining all candidate enterprises having a direct or indirect close trading relationship with the head enterprise, and adding the head enterprise and the obtained all candidate enterprises to the candidate enterprise set, wherein a first candidate enterprise having a direct close trading relationship with the head enterprise in a time period is obtained, a second candidate enterprise having a direct close trading relationship with the first candidate enterprise in a time period is obtained, and so on, all candidate enterprises having a direct close trading relationship with each other in a time period are obtained as the obtained all candidate enterprises.

[0012] Further, if the total transaction amount between the first enterprise and the second enterprise in a time period is greater than or equal to a threshold value, and the total transaction times is greater than or equal to a threshold value, it is determined that the first enterprise and the second enterprise have a direct close trading relationship.

[0013] Further, a fund flow direction graph is constructed based on the supply and marketing relationship between enterprises, and the head enterprise set and the candidate enterprise set are obtained based on the fund flow direction graph, wherein each point in the fund flow direction graph indicates an enterprise and whether the enterprise is a head enterprise in the specific industry, and each edge between each two points in the fund flow direction graph indicates a transaction between the corresponding enterprises and the transaction amount and transaction time of the transaction.

[0014] Further, the matching the industry description of the specific industry with the business scope of each candidate enterprise in the candidate enterprise set further comprises:

[0015] extracting keywords in the industry description of the specific industry and the business scope of each candidate enterprise;

[0016] feature vectorizing all extracted keywords;

[0017] calculating the similarity between the keywords in the feature vectorized industry description and the keywords in the business scope;

[0018] if the aggregated similarity is greater than or equal to a threshold value, it is determined that the industry description matches the business scope.

[0019] Another aspect of the present application provides a device for identifying the industry to which an enterprise belongs, characterized in that the device comprises:

[0020] an obtaining module configured to obtain a candidate enterprise set having a direct or indirect close transaction relationship with a head enterprise in a specific industry;

[0021] a matching module configured to match an industry description of the specific industry with a business scope of each candidate enterprise in the candidate enterprise set;

[0022] a determining module configured to determine that the candidate enterprise belongs to the specific industry when the two are matched, and otherwise determine that the candidate enterprise does not belong to the specific industry.

[0023] Further, the obtaining module is further configured to:

[0024] obtain a head enterprise set of the specific industry, and for each head enterprise to be processed in the head enterprise set, obtain all candidate enterprises having a direct or indirect close transaction relationship with the head enterprise, and add the head enterprise and the obtained all candidate enterprises to the candidate enterprise set, wherein a first candidate enterprise having a direct close transaction relationship with the head enterprise within a time period is obtained, a second candidate enterprise having a direct close transaction relationship with the first candidate enterprise within a time period is obtained, and so on, all candidate enterprises having a direct close transaction relationship with each other within a time period are obtained as the obtained all candidate enterprises.

[0025] Further, if the total transaction amount between a first enterprise and a second enterprise within a time period is greater than or equal to a threshold value, and the total transaction times are greater than or equal to a threshold value, it is determined that the first enterprise and the second enterprise have a direct close transaction relationship.

[0026] Further, a fund flow direction graph is constructed based on the supply and marketing relationship between enterprises, and the head enterprise set and the candidate enterprise set are obtained based on the fund flow direction graph, wherein each point in the fund flow direction graph indicates an enterprise and whether the enterprise is a head enterprise in the specific industry, and each edge between each two points in the fund flow direction graph indicates a transaction between the corresponding enterprises and a transaction amount and a transaction time of the transaction.

[0027] Further, the matching module is further configured to:

[0028] extract keywords in the industry description of the specific industry and the business scope of each candidate enterprise;

[0029] feature vectorize all extracted keywords;

[0030] calculate the similarity between the keywords in the industry description after feature vectorization and the keywords in the business scope;

[0031] If the similarity after the aggregation is greater than or equal to the threshold value, it is determined that the industry description matches the business scope.

[0032] Another aspect of the present application provides an electronic device, comprising a memory storing computer executable instructions and a processor configured to execute the instructions to implement the method of identifying the industry to which an enterprise belongs described above.

[0033] Another aspect of the present application provides a computer storage medium encoded with a computer program, the computer program comprising instructions executed by a computer to implement the method of identifying the industry to which an enterprise belongs described above.

[0034] Another aspect of the present application provides a computer program product comprising computer instructions, which, when executed, implement the method of identifying the industry to which an enterprise belongs described above.

[0035] Due to the above technical solutions, the present application has the following beneficial effects:

[0036] According to the method of identifying the industry to which an enterprise belongs according to the embodiments of the present application, considering that people are grouped and classified, enterprises that have direct or indirect close trading relationships with head enterprises in a certain specific industry are probably related to the specific industry, for example, located on the upstream and downstream of the supply chain of the specific industry, and therefore, such enterprises are first found as a candidate enterprise set for subsequent fine screening; continuing from the business scope in the enterprise business data, by matching the business scope and the industry description, not relying completely on expert experience, the objectivity is guaranteed, and the development and changes of the external environment and internal business can be responded in time; by setting a similarity threshold, the accuracy and adjustability of industry identification can be further improved; the entire method has strong interpretability, meets the requirements of supervision and audit, and can be implemented using computer and network technology, and the implementation cost is lower than that of a learning model. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0038] Figure 1 is a flowchart of the method of identifying the industry to which an enterprise belongs provided by an embodiment of the present application;

[0039] Figure 2 is a schematic diagram of obtaining functions provided by an embodiment of the present application;

[0040] Figure 3 is a schematic diagram of a fund flow direction diagram provided by one embodiment of the present application;

[0041] Figure 4 is a schematic diagram of a matching function provided by one embodiment of the present application;

[0042] Figure 5 is a structural schematic diagram of an apparatus for identifying an industry to which an enterprise belongs provided by one embodiment of the present application;

[0043] Figure 6 is a structural schematic diagram of an electronic device provided by one embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the personnel in the art better understand the present application scheme, the technical scheme in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0045] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, 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 "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, device, product or apparatus that includes a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatuses.

[0046] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer and more apparent, the embodiments of the present application will be further described in detail below in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present application, and are not used to limit the embodiments of the present application. First, the embodiments of the present application explain the following concepts:

[0047] Enterprise: also known as unit, refers to an entity that effectively carries out various economic activities, and is a carrier for dividing industries of the national economy.

[0048] Industry: refers to the industry (or industry) refers to the collection of all units engaged in the same nature of economic activities. The corresponding industry classification and the corresponding industry description can be obtained from the National Economic Industry Classification.

[0049] Head enterprise: also known as leading enterprise, refers to the enterprise in a certain industry, which has a deep influence, appeal and certain demonstration, guidance on other enterprises in the same industry, and makes outstanding contributions to the region, the industry or the country.

[0050] Business scope: refers to the category, variety and service project of goods allowed by the state for enterprises to produce and operate, reflects the content and production and operation direction of enterprise business activities, is the legal limit of enterprise business activity range, and embodies the core content of enterprise civil capacity and behavior capacity.

[0051] Reference specification appendix Figure 1 , which shows the flowchart of the method for identifying the industry to which the enterprise belongs provided by the embodiment of the application, as shown in Figure 1 , the method can include the following steps:

[0052] S110: obtaining a candidate enterprise set having direct or indirect close transaction relationship with the head enterprise in a specific industry.

[0053] The embodiment of the application considers that people are divided into groups, and considers that the enterprise having direct or indirect close transaction relationship with the head enterprise in a specific industry is probably related to the specific industry, for example, located on the upstream and downstream of the supply chain of the specific industry, so the enterprise is first found as a candidate enterprise set for subsequent fine screening.

[0054] In combination with the reference specification appendix Figure 2 , the obtaining of the candidate enterprise set having direct or indirect close transaction relationship with the head enterprise in a specific industry further includes:

[0055] Obtain the head enterprise set of the specific industry, and for each head enterprise to be processed in the head enterprise set, obtain all candidate enterprises having direct or indirect close transaction relationship with the head enterprise, and add the head enterprise and the obtained all candidate enterprises to the candidate enterprise set, wherein the first candidate enterprise having direct close transaction relationship with the head enterprise within a time period is obtained, the second candidate enterprise having direct close transaction relationship with the first candidate enterprise within a time period is obtained, and all candidate enterprises having direct close transaction relationship with each other within a time period are obtained as the obtained all candidate enterprises.

[0056] Specifically, if the total transaction amount of the first enterprise and the second enterprise is greater than or equal to a threshold value and the total transaction times is greater than or equal to a threshold value in a time period, it is determined that the first enterprise and the second enterprise have a direct close transaction relationship.

[0057] It should be noted that the time period is a configurable parameter, and the time period can be in units of weeks, months, seasons and years according to the amount of data. It can be understood that the time period can also be set according to actual conditions, and the embodiments of the application do not limit this.

[0058] In combination with the accompanying drawings of the specification Figure 3 , a fund flow direction graph is constructed based on the supply and marketing relationship between enterprises, and the head enterprise set and the candidate enterprise set are obtained based on the fund flow direction graph.

[0059] Each point Ent i in the fund flow direction graph indicates an enterprise, and each point Ent i has an additional attribute isTop for indicating whether the enterprise is a head enterprise in the specific industry. All head enterprises in the specific industry can be added to the head enterprise set of the specific industry.

[0060] Each edge (Ent i , Ent j ) between each two points Ent i and Ent j in the fund flow direction graph indicates a transaction between the corresponding enterprises, and each edge (Ent i , Ent j ) has an additional attribute <money i , dateTime i > for indicating the transaction amount money i and the transaction time dateTime i of the transaction.

[0061] It can be understood that the supply and marketing relationship between enterprises can be obtained by a bank or any third party, and whether each enterprise is a head enterprise in the specific industry can be manually annotated in advance. It is worth noting that the acquisition, storage, use, processing and the like of data in the technical solutions disclosed in the embodiments of the application all comply with the relevant provisions of national laws and regulations.

[0062] After the fund flow direction graph and the head enterprise set are constructed, a to-be-processed head enterprise is extracted from the head enterprise set, and the head enterprise is added to the candidate enterprise set {Ent i}.

[0063] Then, taking the head enterprise as a starting point, first candidate enterprises that have a direct close transaction relationship with the head enterprise are found in the fund flow graph, and the first candidate enterprises are added to the candidate enterprise set {Ent i} if a first candidate enterprise is already in the candidate enterprise set {Ent i}.

[0064] Therefore, other points that have a direct connection relationship with the point represented by the head enterprise are found in the fund flow graph. It is determined whether the transaction time in the additional attribute of each edge between each point and the point represented by the head enterprise is within the time period. If it is not within the time period, the edge is omitted, and if it is within the time period, the edge is marked. The transaction amount in the additional attribute of all marked edges between the point and the point represented by the head enterprise is summed (i.e., the total transaction amount), and the number of marked edges (i.e., the total transaction times) is determined. If the total transaction amount is greater than or equal to the threshold moneySum, and the total transaction times is greater than or equal to the threshold tradeCount, it is determined that the enterprise represented by the point (i.e., the first candidate enterprise) has a direct close transaction relationship with the head enterprise.

[0065] It can be understood that, for the sake of clarity, each edge (Ent i , Ent j ) between each two points Ent i and Ent j in the fund flow graph can also indicate all transactions between the corresponding enterprises, and each edge (Ent i , Ent j ) has one or more additional attributes <money i , dateTime i > for indicating the transaction amount money i and the transaction time dateTime i of one or more transactions.

[0066] In this case, other points having a direct connection relationship with the point represented by the head enterprise are found in the fund flow graph. Whether the transaction time in each additional attribute of the edge between each point and the point represented by the head enterprise is within the time period is determined. If not within the time period, the additional attribute is omitted, and if within the time period, the additional attribute is marked. The transaction amount in all marked additional attributes of the edge between the point and the point represented by the head enterprise is summed (i.e., total transaction amount), and the number of marked additional attributes (i.e., total transaction times) is determined. If the total transaction amount is greater than or equal to the threshold value moneySum, and the total transaction times is greater than or equal to the threshold value tradeCount, it is determined that the enterprise represented by the point (i.e., the first candidate enterprise) has a direct close transaction relationship with the head enterprise.

[0067] It should be noted that the threshold value moneySum of the total transaction amount and the threshold value tradeCount of the total transaction times are configurable parameters, which can be set according to actual conditions, and embodiments of the present application do not limit this.

[0068] Then, taking each first candidate enterprise as a starting point, a second candidate enterprise having a direct close transaction relationship with the first candidate enterprise is found in the fund flow graph, and the second candidate enterprise is added to the candidate enterprise set {Ent i} if the second candidate enterprise is already in the candidate enterprise set {Ent i}, it can not be added repeatedly.

[0069] Wherein, the method of finding the second candidate enterprise is similar to the method of finding the first candidate enterprise, which will not be repeated here.

[0070] By analogy, all candidate enterprises having a direct close transaction relationship with each other within the time period are obtained, and the candidate enterprises are added to the candidate enterprise set {Ent i} if the candidate enterprise is already in the candidate enterprise set {Ent i}, it can not be added repeatedly. These candidate enterprises all have a direct or indirect close transaction relationship with the head enterprise.

[0071] Then, a head enterprise to be processed is re-drawn from the head enterprise set, the head enterprise is added to the candidate enterprise set {Ent i}, and the candidate enterprise having a direct or indirect close transaction relationship with the head enterprise is found based on the above steps.

[0072] The process ends when all top companies in the aforementioned top company set have been processed. It can be said that the candidate company set {Ent} obtained at this point is... i Each candidate company in the list is likely to belong to the specific industry in which the set of leading companies is located, but there may still be some error.

[0073] S120: Match the industry description of the specific industry with the business scope of each candidate enterprise in the candidate enterprise set.

[0074] This invention continues to start with the business scope in the enterprise's business registration data. By matching the business scope with industry descriptions, it does not rely entirely on expert experience, thus ensuring objectivity and enabling timely responses to changes in the external environment and internal business.

[0075] Specifically, the step of matching the industry description of the specific industry with the business scope of each candidate enterprise in the candidate enterprise set further includes:

[0076] Extract keywords from the industry description of the specific industry and the business scope of each candidate company;

[0077] All extracted keywords are vectorized into features;

[0078] The similarity between the keywords in the industry description (after feature vectorization) and the keywords in the business scope is calculated.

[0079] If the aggregated similarity is greater than or equal to the threshold, then the industry description is determined to match the business scope.

[0080] Refer to the attached reference manual Figure 4 Since the business scope of the candidate companies is unstructured plain text data, keyword extraction technology based on TF-IDF can be used.

[0081] The document number (DN) parameter refers to the set of candidate companies {Ent} i The number of business scope entries for all candidate companies in the set {Ent}. That is, the number of business scope entries for the candidate company set {Ent}. i The number of candidate companies corresponds to the number of business scopes.

[0082] The term frequency (TF) parameter refers to the number of times each word appears in a given business scope after segmenting the business scope and filtering out stop words. A higher frequency indicates that the word is more representative of the candidate company's business scope.

[0083] For the inverse document frequency (IDF) parameter, it can be calculated as log(DN / DF) or log(DN / (DF+1)). Wherein, DF represents the number of business scopes containing the word t, and IDF represents that if the word t appears in many business scopes, its importance is also reduced due to its weakened discrimination ability.

[0084] For the TF-IDF value, it can be calculated as TF*IDF. Wherein, the words in each business scope are sorted in descending order of TF-IDF value, and the top N words are taken as keywords. It should be noted that the N is a configurable parameter, which can be set according to actual conditions, and the embodiments of the present application do not limit this.

[0085] Similarly, the industry description of the specific industry is also unstructured pure text data, so the TF-IDF-based keyword extraction technology can also be used, which will not be repeated here.

[0086] Then, for all the keywords extracted from the industry description of the specific industry and the business scope of each candidate enterprise, the word2vec technology is used for feature vectorization. That is, all the keywords are converted into <w1, w2, …, w i ,…,w n > and AKeyWord i represents the keyword vector value corresponding to the business scope, and BKeyWord i represents the keyword vector value corresponding to the industry description.

[0087] Then, the N keywords corresponding to each business scope and the N keywords of the industry description are calculated for similarity, preferably using the cosine distance formula for similarity calculation, which can form the following two-dimensional matrix table of Table 1.

[0088] <AKeyWord2> <AKeyWord2> <AKeyWord3> …… A KeyWord N ]] BKeyWord1 S(1,1) S(1,2) S(1,3) …… S(1,N) BKeyWord2 S(2,1) S(2,2) S(2,3) …… S(2,N) BKeyWord3 S(3,1) S(3,2) S(3,3) …… S(3,N) …… …… …… …… …… …… BKeyWord N ]]> S(N,1) S(N,2) S(N,3) …… S(N,N)

[0089] Table 1 Two-dimensional matrix table of keyword similarity calculation

[0090] Wherein, S(i,j) represents the similarity of the keywords corresponding to the business scope and the keywords corresponding to the industry description.

[0091] Then, the similarity of the N keywords corresponding to this business scope is summarized, preferably added and averaged, and the value AVG_S represents how similar the business scope is to the industry description, that is:

[0092]

[0093] S130: when the two match, it is determined that the candidate enterprise belongs to the specific industry, otherwise it is determined that the candidate enterprise does not belong to the specific industry.

[0094] The embodiment of the application can further improve the accuracy and adjustability of industry identification by setting a similarity threshold.

[0095] Specifically, it is determined whether the value AVG_S is greater than or equal to the threshold Sim. If yes, it is considered that the business scope matches the industry description; that is, the candidate enterprise corresponding to the business scope matches the specific industry corresponding to the industry description; in other words, the candidate enterprise and the head enterprise belong to the same industry. If not, it is considered that the candidate enterprise and the head enterprise do not belong to the same industry.

[0096] It should be noted that the threshold Sim is a configurable parameter, which can be set according to actual conditions, and the embodiment of the application does not limit this.

[0097] Until all candidate enterprises in the candidate enterprise set {Ent i} are processed, the entire process ends. It can be said that all candidate enterprises that meet the threshold Sim can be considered to belong to the same industry as the head enterprise.

[0098] In summary, according to the method for identifying the industry to which an enterprise belongs according to the embodiment of the application, considering that people live in groups and animals are classified, it is considered that an enterprise that has a direct or indirect close trading relationship with a head enterprise in a specific industry is probably related to the specific industry, for example, located on the upstream and downstream of the supply chain of the specific industry, and the like, so such an enterprise is first found as a candidate enterprise set for subsequent fine screening; continuing from the business scope in the enterprise business data, by matching the business scope and the industry description, not relying entirely on expert experience, the objectivity is guaranteed, and the development and change of the external environment and the internal business can be responded in time; by setting a similarity threshold, the accuracy and adjustability of industry identification can be further improved; the entire method has strong interpretability, meets the supervision and audit requirements, and can be implemented using computer and network technology, and the implementation cost is lower than that of a learning model.

[0099] Reference is made to the accompanying drawings Figure 5 which show the structure of the device for identifying the industry to which an enterprise belongs according to an embodiment of the application, as shown in Figure 5 The device 500 can include the following modules:

[0100] The acquisition module 510 is configured to acquire a candidate enterprise set that has a direct or indirect close trading relationship with a head enterprise in a specific industry;

[0101] The matching module 520 is configured to match the industry description of the specific industry with the business scope of each candidate enterprise in the candidate enterprise set;

[0102] The determination module 530 is configured to determine that the candidate enterprise belongs to the specific industry when both are matched, and otherwise determine that the candidate enterprise does not belong to the specific industry.

[0103] In one possible embodiment, the acquisition module 510 is further configured to:

[0104] Acquire a set of head enterprises of a specific industry, and for each head enterprise to be processed in the set of head enterprises, acquire all candidate enterprises having direct or indirect close transaction relationship with the head enterprise, and add the head enterprise and the acquired all candidate enterprises to the candidate enterprise set, wherein a first candidate enterprise having direct close transaction relationship with the head enterprise within a time period is acquired, a second candidate enterprise having direct close transaction relationship with the first candidate enterprise within a time period is acquired, and so on, all candidate enterprises having direct close transaction relationship with each other within a time period are acquired as the acquired all candidate enterprises.

[0105] In one possible embodiment, if the total transaction amount between a first enterprise and a second enterprise within a time period is greater than or equal to a threshold value, and the total transaction times are greater than or equal to a threshold value, it is determined that the first enterprise and the second enterprise have direct close transaction relationship.

[0106] In one possible embodiment, a fund flow direction graph is constructed based on the supply and marketing relationship between enterprises, and the set of head enterprises and the candidate enterprise set are acquired based on the fund flow direction graph, wherein each point in the fund flow direction graph indicates an enterprise and whether the enterprise is a head enterprise in the specific industry, and each edge between each two points in the fund flow direction graph indicates a transaction between the corresponding enterprises and the transaction amount and transaction time of the transaction.

[0107] In one possible embodiment, the matching module 520 is further configured to:

[0108] Extract keywords in the industry description of the specific industry and the business scope of each candidate enterprise;

[0109] Feature vectorize all extracted keywords;

[0110] Calculate the similarity between the keywords in the industry description after feature vectorization and the keywords in the business scope;

[0111] If the similarity after the aggregation is greater than or equal to the threshold value, it is determined that the industry description matches the business scope.

[0112] It should be noted that the apparatus provided in the above embodiments, when realizing its functions, is only exemplified by the above division of functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the apparatus provided in the above embodiments and the corresponding method embodiments belong to the same concept, and the specific implementation process is detailed in the corresponding method embodiments, which will not be repeated here.

[0113] One embodiment of the present application also provides an electronic device, which comprises a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the method for identifying the industry to which an enterprise belongs provided in the above method embodiments.

[0114] The memory can be used to store software programs and modules, and the processor can execute various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required by functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory can also include a memory controller to provide access of the processor to the memory.

[0115] The method embodiments provided in the embodiments of the present application can be executed in a terminal, a server or a similar computing device, that is, the above electronic device can include a terminal, a server or a similar computing device. Taking the case of running on a server as an example, as shown in Figure 6As shown, it shows a structural schematic diagram of a server for implementing the method of identifying the industry of an enterprise according to an embodiment of the present application. The server 600 can be quite different due to different configurations or performances, and can include one or more central processing units (CPU) 610 (for example, one or more processors) and a memory 630, one or more storage media 620 (for example, one or more mass storage devices) for storing application programs 623 or data 622. Among them, the memory 630 and the storage medium 620 can be temporary storage or persistent storage. The programs stored in the storage medium 620 can include one or more modules, and each module can include a series of instruction operations in the server. Furthermore, the central processing unit 610 can be configured to communicate with the storage medium 620 to execute a series of instruction operations in the storage medium 620 on the server 600. The server 600 can also include one or more power supplies 660, one or more wired or wireless network interfaces 650, one or more input / output interfaces 640, and / or one or more operating systems 621, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0116] The input / output interface 640 can be used to receive or send data via a network. The above-mentioned specific examples of the network can include a wireless network provided by a communication provider of the server 600. In one example, the input / output interface 640 includes a network interface controller (NIC) which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the input / output interface 640 can be a radio frequency (RF) module for communicating with the Internet in a wireless manner, and the wireless communication can use any communication standard or protocol, including but not limited to global system for mobile communication (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), email, short message service (SMS), etc.

[0117] Those skilled in the art can understand that Figure 6 The structure shown is only schematic, and the server 600 can also include more or fewer components than shown, or have a different configuration or arrangement of the components shown than shown. Figure 6 The server 600 can also include more or fewer components than shown, or have a different configuration or arrangement of the components shown than shown. Figure 6 The server 600 can also include more or fewer components than shown, or have a different configuration or arrangement of the components shown than shown.

[0118] The embodiment of the present application also provides a computer readable storage medium, which can be arranged in an electronic device to store at least one instruction or at least one program for implementing a method for identifying an industry to which an enterprise belongs, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for identifying an industry to which an enterprise belongs provided by the above-mentioned method embodiment.

[0119] Optionally, in the embodiment of the present application, the storage medium can include but is not limited to: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk and various storage program codes.

[0120] The embodiment of the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for identifying an industry to which an enterprise belongs provided in the various optional implementation examples.

[0121] It should be noted that: the above-mentioned embodiment order of the present application is only for description, not representing the advantages and disadvantages of the embodiments. And the above-mentioned embodiment of the present application is described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be executed in different order from the embodiments and still can achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0122] Each embodiment in the present specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments. Especially, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts can be referred to the part of the method embodiment.

[0123] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or can be instructed to relevant hardware by program. The program can be stored in a computer readable storage medium, and the storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0124] The above description is merely preferred embodiments of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of identifying an industry to which a business belongs, characterized by, The method is used for an electronic device, and the method comprises: obtaining a candidate enterprise set having a direct or indirect close transaction relationship with a head enterprise in a specific industry; matching an industry description of the specific industry with a business scope of each candidate enterprise in the candidate enterprise set; determining that the candidate enterprise belongs to the specific industry when the two match, otherwise determining that the candidate enterprise does not belong to the specific industry, wherein the obtaining a candidate enterprise set having a direct or indirect close transaction relationship with a head enterprise in a specific industry further comprises: obtaining a head enterprise set of the specific industry, and for each head enterprise to be processed in the head enterprise set, obtaining all candidate enterprises having a direct or indirect close transaction relationship with the head enterprise, and adding the head enterprise and the obtained all candidate enterprises to the candidate enterprise set, wherein a first candidate enterprise having a direct close transaction relationship with the head enterprise within a time period is obtained, a second candidate enterprise having a direct close transaction relationship with the first candidate enterprise within the time period is obtained, and so on, all candidate enterprises having a direct close transaction relationship with each other within the time period are obtained as the obtained all candidate enterprises.

2. The method of claim 1, wherein, If the total transaction amount between a first enterprise and a second enterprise within a time period is greater than or equal to a threshold value, and the total transaction times are greater than or equal to a threshold value, it is determined that the first enterprise and the second enterprise have a direct close transaction relationship.

3. The method of claim 1, wherein, A fund flow direction graph is constructed based on the supply and marketing relationship between enterprises, and the head enterprise set and the candidate enterprise set are obtained based on the fund flow direction graph, wherein each point in the fund flow direction graph indicates an enterprise and whether the enterprise is a head enterprise in the specific industry, and each edge between each two points in the fund flow direction graph indicates a transaction between the corresponding enterprises and a transaction amount and a transaction time of the transaction.

4. The method of claim 1, wherein, The matching the industry description of the specific industry with the business scope of each candidate enterprise in the candidate enterprise set further comprises: extracting keywords in the industry description of the specific industry and the business scope of each candidate enterprise; feature vectorizing all extracted keywords; calculating the similarity of the keywords in the feature vectorized industry description and the keywords in the business scope; if the aggregated similarity is greater than or equal to a threshold value, it is determined that the industry description matches the business scope.

5. A device for identifying the industry to which a company belongs, characterized in that, The device comprises: an obtaining module configured to obtain a candidate enterprise set having a direct or indirect close transaction relationship with a head enterprise in a specific industry; a matching module configured to match an industry description of the specific industry with a business scope of each candidate enterprise in the candidate enterprise set; a determining module configured to determine that the candidate enterprise belongs to the specific industry when the two match, otherwise determine that the candidate enterprise does not belong to the specific industry, wherein the obtaining module is further configured to: A set of head enterprises of a specific industry is obtained, and for each head enterprise to be processed in the set of head enterprises, all candidate enterprises in direct or indirect close transaction relationship with the head enterprise are obtained, and the head enterprise and all the obtained candidate enterprises are added to the set of candidate enterprises, wherein a first candidate enterprise in direct close transaction relationship with the head enterprise within a time period is obtained, a second candidate enterprise in direct close transaction relationship with the first candidate enterprise within a time period is obtained, and so on, all candidate enterprises in direct close transaction relationship with each other within a time period are obtained as all the obtained candidate enterprises.

6. The apparatus of claim 5, wherein, If the total transaction amount between the first enterprise and the second enterprise within a time period is greater than or equal to a threshold value, and the total transaction times are greater than or equal to a threshold value, it is determined that the first enterprise and the second enterprise are in direct close transaction relationship.

7. The apparatus of claim 5, wherein, A fund flow direction graph is constructed based on the supply and demand relationship between enterprises, and the set of head enterprises and the set of candidate enterprises are obtained based on the fund flow direction graph, wherein each point in the fund flow direction graph indicates an enterprise and whether the enterprise is a head enterprise in the specific industry, and each edge between each two points in the fund flow direction graph indicates a transaction between the corresponding enterprises and the transaction amount and transaction time of the transaction.

8. The apparatus of claim 5, wherein, The matching module is further configured to: extract keywords in the industry description of the specific industry and the business scope of each candidate enterprise; vectorize all the extracted keywords as feature vectors; calculate the similarity between the keywords in the industry description and the keywords in the business scope after feature vectorization; if the aggregated similarity is greater than or equal to a threshold value, it is determined that the industry description and the business scope match.

9. An electronic device, comprising: The electronic device includes a processor and a memory, the memory stores at least one instruction or at least one program, the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for identifying the industry to which an enterprise belongs according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the method for identifying the industry to which an enterprise belongs according to any one of claims 1 to 4.

11. A computer program product, characterised in that, The computer program product includes computer instructions, which, when executed, implement the method for identifying the industry to which an enterprise belongs according to any one of claims 1 to 4.

Images