CN113435762B

CN113435762B - Enterprise risk identification method, device and equipment

Info

Publication number: CN113435762B
Application number: CN202110757269.4A
Authority: CN
Inventors: 崔阳; 章鹏; 朱标; 刘小刚; 张旭
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2020-05-06
Filing date: 2020-05-06
Publication date: 2023-08-08
Anticipated expiration: 2040-05-06
Also published as: CN113435762A; CN111489105A; CN111489105B

Abstract

The embodiment of the specification discloses an enterprise risk identification method, device and equipment, and the scheme includes: acquiring standardized recruitment data, adopting a recruitment body enterprise identification model to identify a recruitment body enterprise corresponding to the recruitment data, and generating a first enterprise recruitment information portrait of the recruitment body enterprise according to the recruitment data; then determining a second enterprise recruitment information portrait of the analog enterprise of the recruitment subject enterprise according to the acquired registration data of the recruitment subject enterprise; calculating a difference value between the first enterprise recruitment information representation and the second enterprise recruitment information representation; and when the difference value is larger than a first preset threshold value, determining that the recruitment subject enterprise has risks.

Description

Enterprise risk identification method, device and equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to an enterprise risk identification method, apparatus, and device.

Background

With the rapid development of the internet, a large amount of data is disclosed in the internet, and related data of a large amount of enterprises is also included. After collecting and mining the public information of the internet, the wind control mechanism can perform global scanning on risks of enterprises. The enterprise risk relates to aspects of enterprise management, asset allocation, fund application, profit allocation, information disclosure and the like, and if the enterprise has large risk, the enterprise, investors, job seekers, countries and groups can be greatly lost. Therefore, it is particularly important to identify the risk of enterprises based on the data disclosed in the internet.

The data about the enterprise disclosed in the internet can comprise a large amount of different types of data such as enterprise network data, associated enterprise data, enterprise APP data, enterprise recruitment data and the like, and when the enterprise risk is judged in the prior art, the data disclosed in the internet are often analyzed manually, so that the risk of the enterprise is identified, and the identification accuracy and the identification efficiency are lower.

Accordingly, there is a need to provide a more reliable enterprise risk identification scheme.

Disclosure of Invention

The embodiment of the specification provides an enterprise risk identification method and device, which are used for solving the problems of low efficiency and low accuracy of manually identifying enterprise risk.

In order to solve the above technical problems, the embodiments of the present specification are implemented as follows:

the enterprise risk identification method provided by the embodiment of the specification comprises the following steps:

acquiring standardized recruitment data;

identifying a recruitment subject enterprise corresponding to the recruitment data by adopting a recruitment subject enterprise identification model;

generating a first enterprise recruitment information portrait of the recruitment subject enterprise according to the recruitment data;

acquiring registration data of the recruitment subject enterprise;

determining a second enterprise recruitment information representation according to the registration data, wherein the second enterprise recruitment information representation is of an analog enterprise of the recruitment subject enterprise;

Calculating a difference value between the first enterprise recruitment information representation and the second enterprise recruitment information representation;

judging whether the difference value is larger than a first preset threshold value or not to obtain a judging result;

and when the judging result shows that the difference value is larger than a first preset threshold value, determining that the recruitment subject enterprise has risks.

An enterprise risk identification apparatus provided in an embodiment of the present disclosure includes:

the recruitment data acquisition module is used for acquiring standardized recruitment data;

the recruitment subject enterprise identification module is used for identifying the recruitment subject enterprise corresponding to the recruitment data by adopting a recruitment subject enterprise identification model;

the first enterprise recruitment information portrait generation module is used for generating a first enterprise recruitment information portrait of the recruitment subject enterprise according to the recruitment data;

the registration data acquisition module is used for acquiring registration data of the recruitment subject enterprise;

the second enterprise recruitment information portrait determining module is used for determining a second enterprise recruitment information portrait according to the registration data, wherein the second enterprise recruitment information portrait is a recruitment information portrait of an analog enterprise of the recruitment subject enterprise;

the recruitment information portrait difference value determining module is used for calculating a difference value between the first enterprise recruitment information portrait and the second enterprise recruitment information portrait;

The judging module is used for judging whether the difference value is larger than a first preset threshold value or not to obtain a judging result;

and the enterprise risk identification module is used for determining that the recruitment subject enterprise has risk when the judging result shows that the difference value is larger than a first preset threshold value.

at least one processor; the method comprises the steps of,

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores instructions executable by the at least one processor to enable the at least one processor to:

acquiring standardized recruitment data;

acquiring registration data of the recruitment subject enterprise;

Embodiments of the present disclosure provide a computer readable medium having computer readable instructions stored thereon that are executable by a processor to implement an enterprise risk identification method.

One embodiment of the present specification achieves the following advantageous effects: identifying a recruitment subject enterprise from the standardized recruitment data by adopting a recruitment subject enterprise identification model, and then generating a first enterprise recruitment information portrait of the recruitment subject enterprise according to the recruitment data; acquiring registration data of a recruitment subject enterprise, and determining a second enterprise recruitment information portrait of an analog enterprise of the recruitment subject enterprise according to the registration data; calculating a difference value between the first enterprise recruitment information representation and the second enterprise recruitment information representation; and when the difference value is larger than a first preset threshold value, determining that the recruitment subject enterprise has risks. Through the method, the recruitment subject enterprises can be automatically identified from the recruitment data, and whether the recruitment subject enterprises have risks can be judged, so that the problems of low risk efficiency and low accuracy of manually identifying the enterprises are solved, the automatic identification of the enterprise risks in the recruitment data is realized, and early warning is realized.

Drawings

In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.

FIG. 1 is a system framework diagram of an enterprise risk identification method provided by an embodiment of the present disclosure;

FIG. 2 is a flowchart of an enterprise risk identification method provided in an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of an enterprise risk identification apparatus corresponding to FIG. 2 provided in an embodiment of the present disclosure;

fig. 4 is a schematic diagram of an enterprise risk identification apparatus corresponding to fig. 2 provided in an embodiment of the present disclosure.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of one or more embodiments of the present specification more clear, the technical solutions of one or more embodiments of the present specification will be clearly and completely described below in connection with specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without undue burden, are intended to be within the scope of one or more embodiments herein.

The relevant data of each enterprise in the Internet also comprises recruitment information on a recruitment platform disclosed by the Internet, the enterprise recruitment information is an emerging data source, and the traditional industrial and commercial data can be used as a good supplement. Recruitment information is reasonably processed and deeply mined, and can be used for identifying risks of enterprises, such as: and identifying the operation risks and compliance risks such as the off-site operation risks, the out-of-range operation risks and the like of the enterprise.

The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.

Fig. 1 is a system framework diagram of an enterprise risk identification method according to an embodiment of the present disclosure. As shown in FIG. 1, the present solution can be divided from a system framework into a data collector, a standard converter, a recruitment subject identifier, an enterprise recruitment information representation generator, an analog enterprise recruitment representation generator, and a risk identifier. The data acquisition device can acquire industrial and commercial data and recruitment data, the acquired recruitment data need to be converted by adopting a standard converter, the standard converter comprises a post knowledge graph and an enterprise knowledge graph, the post knowledge graph is adopted to normalize a post name, the enterprise knowledge graph is adopted to normalize an enterprise name, the normalized recruitment data is finally obtained, after the normalized recruitment data is obtained, a recruitment subject enterprise in the recruitment data can be identified by adopting a recruitment subject identifier, wherein the recruitment subject identifier can comprise a recruitment subject enterprise identification model, the data input into the recruitment subject identification model can be normalized recruitment data or normalized recruitment data and entity attributes, and the entity attributes can represent the attributes of the enterprise, such as: internet businesses, automobile manufacturing businesses, and the like.

After the recruitment subject identifier identifies the recruitment subject enterprise, a recruitment information representation of the recruitment subject enterprise can be generated according to the standardized recruitment data, and the recruitment information representation generated by the enterprise recruitment information representation generator can include a recruitment post type, recruitment post conditions (salary, academic, working age, number of people, working content, and the like) and a recruitment post address. And then, according to the registration data, the analog enterprise of the recruitment subject enterprise can be determined, the recruitment information portrait of the analog enterprise is generated, and finally, according to the recruitment information portrait of the analog enterprise and the recruitment information portrait of the recruitment subject enterprise, the risk type in the recruitment data is identified by adopting a risk identifier.

Next, a specific description will be given of a data privacy type identification method provided for an embodiment of the specification with reference to the accompanying drawings:

fig. 2 is a flow chart of an enterprise risk identification method according to an embodiment of the present disclosure. From the program perspective, the execution subject of the flow may be a program or an application client that is installed on an application server.

As shown in fig. 2, the process may include the steps of:

step 202: and acquiring standardized recruitment data.

It should be noted that the recruitment data may refer to recruitment data on a recruitment platform, and the recruitment data may be recruitment data corresponding to multiple enterprises. The recruitment data may include data such as a recruitment subject business, a business that issues recruitment information instead, recruitment post information, a post work address, and recruitment conditions.

The above-mentioned "standardization" can be understood as preprocessing the initial recruitment data acquired in the recruitment platform, and can be understood as that the enterprise name in the standardized recruitment data is a standard enterprise name, and does not contain incomplete or incorrect enterprise names; the post names in the standardized recruitment data are standard post names, and the post names with missing, wrong, nonstandard and synonymous different names are not included.

The recruitment data obtained in the above steps may be a piece of recruitment data, where the recruitment platform includes a plurality of pieces of recruitment data, and each piece of recruitment data corresponds to a recruitment subject enterprise, and in this embodiment, processing one piece of recruitment data is taken as an example.

Step 204: and identifying the recruitment subject enterprise corresponding to the recruitment data by adopting a recruitment subject enterprise identification model.

The "recruiter business" herein may refer to a business of actual recruiters. The distribution of a piece of recruitment data may not be truly a recruiter enterprise, and may be performed by individuals or other institutions instead. The business name of the recruitment subject business is a standardized business name, and the individual or institution name that is used to instead send the recruitment information is not a true recruitment subject business.

The recruitment subject enterprise recognition model belongs to a neural network model, and particularly can be a machine learning model or a deep learning model, and can mine a real recruitment subject enterprise for issuing recruitment information from recruitment data.

Step 206: and generating a first enterprise recruitment information portrait of the recruitment subject enterprise according to the recruitment data.

The enterprise recruitment information portrait can be understood as an impression given by an enterprise, and the recruitment characteristics of the enterprise can be known through the enterprise recruitment information portrait. Specifically, the post type of the enterprise recruitment can be obtained from the post information portrait, and the information such as salary, academic, working age, statistics indexes such as the number of people, post work area, post work content keyword cloud and the like of various posts can be obtained.

Features constructing the enterprise recruitment information representation can be extracted from the recruitment data, and then the enterprise recruitment information representation is generated according to the extracted features.

Step 208: and acquiring registration data of the recruitment subject enterprise.

The registration data may refer to enterprise data that an enterprise registers with a third party authority or authority, and the enterprise registration data may include information of an enterprise name, legal representative, established date, address, business deadline, business scope, registration authority, registration status, registered capital, real-time capital, stakeholder, high-authority, and the like of the enterprise. In this scheme, the obtained registration data mainly includes enterprise registration address, registration time, registration capital, and operation scope.

Step 210: and determining a second enterprise recruitment information portrait according to the registration data, wherein the second enterprise recruitment information portrait is the recruitment information portrait of the analogy enterprise of the recruitment subject enterprise.

The second business recruitment information representation in this step may be a recruitment information representation of an analog business of the recruiting subject business. Wherein, the analog enterprise may refer to an enterprise that is the same as or similar to the recruiter enterprise in a certain dimension, such as: the analog enterprise may be an enterprise having the same registration address as the recruiter enterprise, or may be an enterprise having the same operation range as the recruiter enterprise, or the like.

The registration address, registration time, registration capital and operation range of the recruitment body enterprise can be determined according to the registration data of the recruitment body enterprise, the registration address, registration time, registration capital and operation range can be understood as four specific dimensions corresponding to the recruitment body enterprise, and when the analog enterprise of the recruitment body enterprise is determined, the enterprise which is the same as or similar to the recruitment body enterprise in the four specific dimensions can be taken as the analog enterprise of the recruitment body enterprise. Such as: the recruitment subject enterprise is enterprise A, the registration addresses of enterprise B and enterprise A are all in the Beijing Kogyo area, the operation ranges of enterprise C and enterprise A are daily necessities, enterprise D and enterprise A are all registered in 2010, and at this time, enterprise B, enterprise C and enterprise D can be determined as analog enterprises of the recruitment subject enterprise.

Step 212: and calculating a difference value between the first enterprise recruitment information portrait and the second enterprise recruitment information portrait.

In this scheme, the default risk of recruitment information of the analog enterprise is low, so when the deviation between the recruitment information representation of the recruitment subject enterprise and the recruitment information of the analog enterprise is too large, for example: when the abnormal high salary low requirements which obviously do not meet the normal salary range and the senior academic requirements of the financial consultant in the different industries are presented, the recruitment subject enterprise can be considered to be possibly hidden in risks. Therefore, the difference value between the recruitment information representation of the recruiter enterprise and the recruitment information representation of the analog enterprise can be calculated.

The "difference value" in the above step may represent a difference between the recruitment information representation of the analog enterprise and the recruitment information representation of the recruitment subject enterprise, and the difference value may be an amount capable of representing the difference therebetween. Such as: the recruitment information portrait of the analog enterprise and the recruitment information portrait of the recruitment subject enterprise can be converted into vectors, and the difference value between the two vectors is calculated. The specific calculation mode for calculating the difference value can be selected according to actual requirements, and the scheme is not limited to this.

Step 214: and judging whether the difference value is larger than a first preset threshold value or not to obtain a judging result.

After the difference value between the recruitment information representation of the analog enterprise and the recruitment information representation of the recruitment subject enterprise is calculated, the larger the difference value, the larger the risk of the recruitment subject enterprise can be considered.

Step 216: and when the judging result shows that the difference value is larger than a first preset threshold value, determining that the recruitment subject enterprise has risks.

In an actual application scenario, a preset threshold corresponding to the difference value can be set, and when the difference value exceeds the preset threshold, the recruitment subject enterprise can be considered to have risks. The specific setting of the preset threshold value can be defined according to actual requirements.

It should be understood that the method according to one or more embodiments of the present disclosure may include the steps in which some of the steps are interchanged as needed, or some of the steps may be omitted or deleted.

The method of fig. 2, wherein a recruitment subject enterprise is identified from standardized recruitment data by using a recruitment subject enterprise identification model, and then a first enterprise recruitment information representation of the recruitment subject enterprise is generated according to the recruitment data; acquiring registration data of a recruitment subject enterprise, and determining a second enterprise recruitment information portrait of an analog enterprise of the recruitment subject enterprise according to the registration data; calculating a difference value between the first enterprise recruitment information representation and the second enterprise recruitment information representation; and when the difference value is larger than a first preset threshold value, determining that the recruitment subject enterprise has risks. Through the method, the recruitment subject enterprises can be automatically identified from the recruitment data, and whether the recruitment subject enterprises have risks can be judged, so that the problems of low risk efficiency and low accuracy of manually identifying the enterprises are solved, the automatic identification of the enterprise risks in the recruitment data is realized, and early warning is realized.

The examples of the present specification also provide some specific embodiments of the method based on the method of fig. 2, which is described below.

Optionally, before the acquiring the standardized recruitment data, the method further includes:

acquiring initial recruitment data from a recruitment platform;

constructing an enterprise knowledge graph according to the initial recruitment data and registration data in a third party mechanism;

constructing a post knowledge graph according to the initial recruitment data;

standardizing the enterprise names in the initial recruitment data according to the enterprise knowledge graph to obtain standard enterprise names;

the post names in the initial recruitment data are standardized according to the post knowledge graph to obtain standard post names;

and replacing the post name in the initial recruitment data with the standard post name, and replacing the enterprise name in the initial recruitment data with the standard enterprise name to obtain standardized recruitment data.

Specifically, when the recruitment subject enterprise name is standardized according to the enterprise knowledge graph of the recruitment subject enterprise, the following method may be adopted:

the establishing the enterprise knowledge graph according to the initial recruitment data and the registration data in the third party mechanism may specifically include:

Determining historical registration data of a business entity in a third party institution for the business entity;

determining a standard enterprise name and a great-use name of the enterprise entity according to the historical registration data;

extracting a business alias of the business entity from the initial recruitment data;

constructing the enterprise knowledge graph according to the standard enterprise name, the great-use name and the enterprise alias of the enterprise entity;

the normalizing the enterprise name in the initial recruitment data according to the enterprise knowledge graph to obtain a standard enterprise name may specifically include:

and uniformly converting the great-use names and the enterprise aliases into the standard enterprise names.

When the recruitment post names are standardized according to the post knowledge graph, the following method can be adopted:

the building of the post knowledge graph according to the initial recruitment data may specifically include:

extracting an active post name of a post entity from the initial recruitment data for the post entity;

constructing the post knowledge graph according to the current post name;

determining the current post name with highest occurrence frequency in the post knowledge graph as a standard post name;

The step of normalizing the post names in the initial recruitment data according to the post knowledge graph to obtain standard post names may specifically include:

and converting the active post name into the standard post name.

It should be noted that the knowledge graph is a set of knowledge representation, iteration and growth frameworks based on semantic network, and describes concepts, entities and relationships thereof in the objective world in a structured form. The knowledge graph comprises a graph and graph calculation, wherein the graph is an abstract data structure for representing the association relation between objects, and is described by using nodes and edges, the vertexes represent the objects, and the edges represent the relation between the objects.

In the scheme, for the enterprise knowledge graph, each enterprise entity can be used as a point in the enterprise knowledge graph, and corresponding description information can be arranged on each point, wherein the description information is used for describing related information of the corresponding enterprise entity, which enterprise entities and recruitment subject enterprises belong to the same enterprise according to the description information, and only the names are inconsistent, so that a plurality of enterprise names belonging to the same enterprise can be determined.

Therefore, the knowledge graph of the company in the scheme can be understood as constructing an alias library about recruitment subject enterprises. The enterprise knowledge graph may include all aliases corresponding to the recruitment subject enterprise, which may be aliases identified from recruitment data, or enterprise registration names obtained from registration data of a third party platform, for example: the enterprise A changes the enterprise name for 4 times before and after the third party registration platform, so that the four enterprise names before and after the change can be the registration names of recruitment main enterprises or can be contained in an enterprise knowledge graph. Thus, in constructing the enterprise knowledge graph, construction can be based on the initial recruitment data and registration data in the third party institution.

Of course, when the enterprise knowledge graph is specifically constructed, common punctuation rules and misplaced word dictionaries can be considered, so that the constructed enterprise knowledge graph can be more comprehensively associated with various great names, aliases or nonstandard names of recruitment main enterprises. The non-canonical name herein may refer to a name that does not comply with punctuation rules or that has a wrongly written word.

After the enterprise knowledge graph is constructed, the currently used enterprise name registered by the recruitment subject in the registration data can be used as a standard enterprise name. All aliases and the great-use names of the recruitment subject business determined from the business knowledge graph are then converted to standard business names. Such as: the currently used business name registered by the recruiting subject business a in the third party platform is named X, where the name X can be used as a standard business name, the aliases of the business a are (X1, X2, X3, X4), the great-use names of the business are (X ', X "), and at this time, all of X1, X2, X3, X4, X' and x″ can be uniformly converted into the standard business name X.

When building the post knowledge graph, each post entity can correspond to a point in the post knowledge graph, and the description information of each point can be related information of each post. After the post knowledge graph is built, the aliases corresponding to the same post can be determined according to the related information of the post, for example: the service manager and the service sales manager find that the responsibility ranges, the requirement academy, the salary treatment and the like of the two posts are not quite different through comparison, and at the moment, the service manager and the service sales manager can be considered to be the current names belonging to the same post. Of course, when the post knowledge map is constructed, the post knowledge map can be constructed by combining business experience and data statistical analysis besides the initial recruitment data of the recruitment platform so as to associate various aliases of common recruitment posts.

After the post knowledge graph is constructed, the post name with the highest occurrence frequency in the post knowledge graph can be used as a standard post name, and then the existing post name in the post knowledge graph is converted into the standard post name.

By the method, the enterprise knowledge graph and the post knowledge graph are constructed, and the great-use names, the aliases and the nonstandard names in the initial recruitment data are reliably normalized by utilizing the enterprise knowledge graph; the acquired post names are normalized by using the post knowledge graph, so that posts issued by various aliases can be unified under the same concept, recruitment main enterprises and post names are standardized, and therefore, the source data of the recruitment enterprises are effectively integrated, compared and mined, and subsequent portrait and risk mining are effectively performed.

The identifying the recruitment subject enterprise from the recruitment data by using the recruitment subject enterprise identification model may specifically include:

acquiring all enterprise entities in the recruitment data;

inputting the recruitment data into the recruitment subject enterprise identification model to obtain the prediction probability that each enterprise entity in the all enterprise entities belongs to the recruitment subject enterprise;

And determining the enterprise entity with the prediction probability larger than a preset threshold and the maximum prediction probability as the recruitment subject enterprise.

It should be noted that, in practical applications, one recruitment data X may include a plurality of business entities, for example: the enterprise A mainly recruits the post personnel, entrust platform B sends recruitment information of the recruitment post personnel instead, manager small C of platform B issues the recruitment information on the recruitment platform, and at this time, enterprise entities contained in the recruitment data are enterprise A, platform B and manager C.

And inputting recruitment data into an enterprise identification model, so that the prediction probability that each enterprise entity belongs to the recruitment subject enterprise can be obtained, and determining the enterprise entity with the prediction probability value larger than a preset threshold and the maximum preset probability as the recruitment subject enterprise. By using the above example, the recruitment data X is input into the recruitment subject enterprise recognition model, so as to obtain that the prediction probability that the enterprise a belongs to the recruitment subject enterprise is 0.9, the prediction probability that the platform B belongs to the recruitment subject enterprise is 0.4, the prediction probability that the manager C belongs to the recruitment subject enterprise is 0.1, the preset threshold is assumed to be 0.6, and the enterprise greater than the preset threshold is the enterprise a, and at this time, the enterprise a can be determined as the recruitment subject enterprise. Of course, the specific value of the prediction probability may be set according to the actual requirement, which is not limited in the embodiment of the present specification.

It should be noted that, the recruitment subject enterprise in the recruitment data may be explicit, for example: if only one business entity exists in a piece of recruitment data, the entity may be determined to be a recruiter business. If the recruiter's business in the recruitment data is ambiguous, such as: the recruitment data can be standardized first and then identified by using the recruitment body enterprise identification model when the recruitment body enterprises cannot be clearly identified due to the fact that a plurality of enterprise entities cannot judge the real recruitment enterprise entities or due to the fact that enterprise names in the recruitment data are not standard.

Of course, it should be noted that, in practical application, the relevant model in the natural language algorithm may be used to identify the recruitment subject enterprise, and the naming of the "recruitment subject enterprise model" in the above steps is only used to indicate that the model may identify the recruitment subject enterprise, and does not limit the model type.

Before application, the recruitment subject identification model needs to be trained, and when specific training is performed, the following method can be adopted:

before the recruitment subject enterprise corresponding to the recruitment data is identified by adopting the recruitment subject enterprise identification model, the method may further include:

Acquiring a recruitment data training sample set of a known recruitment subject enterprise;

inputting the training samples into an initial recruitment subject enterprise identification model for each training sample in the training sample set, and outputting recruitment subject enterprises;

and adjusting model parameters of the initial recruitment subject enterprise identification model according to the difference between the recruitment subject enterprise and the known recruitment subject enterprise to obtain a trained recruitment subject enterprise identification model.

When specific training is performed, a plurality of samples can be arranged in the training sample set, recruitment subject enterprises in each sample are known, the training samples can be input into an initial recruitment subject enterprise identification model, and model parameters of the initial recruitment subject enterprise identification model are adjusted according to the difference between the output result and the known recruitment subject enterprises, so that the trained recruitment subject enterprise identification model is obtained.

By the method, the real recruitment main body enterprise is identified with high accuracy from the recruitment data through the natural language algorithm technology, and the problem of vulnerability of the direct data matching method to nonstandard input can be solved.

In an actual application scenario, the generating the first enterprise recruitment information representation of the recruitment subject enterprise according to the recruitment data may specifically include:

Extracting an portrait tag of the recruitment subject enterprise from the recruitment data, wherein the portrait tag is used for representing recruitment characteristics of the recruitment subject enterprise in a specific dimension; the portrait tag at least comprises a recruitment type tag of the recruitment subject enterprise, a condition tag of each recruitment, and a work area tag of each recruitment;

and generating a first enterprise recruitment information portrait of the recruitment subject enterprise according to the portrait tag.

The image tags can be used to characterize recruitment characteristics of a recruiter company in a particular dimension, such as: the type of job recruited, the recruitment conditions for each type of job, and so forth. Colloquially speaking, the recruitment subject enterprise is marked, and the marking is an identification obtained through analysis of recruitment information of the recruitment subject enterprise. Some highly summarized and easily understood features may be utilized by tagging to describe recruitment information for a recruiter company.

The portrait tag can include at least a recruitment type tag of a recruitment subject enterprise, a condition tag of each recruitment, and a work area tag of each recruitment. The condition labels of each recruitment post can be as follows: salaries, academia, working age, number of people, work content, welfare vacations and the like of various recruitment posts.

After extracting the portrait tag of the recruitment body enterprise from the recruitment data, a first enterprise recruitment information portrait of the recruitment body enterprise can be generated according to the extracted portrait tag. Wherein the first business recruitment information representation may be a piece of text information, such as: the information that can be contained in the recruitment representation of enterprise A is: the type of post recruited by enterprise a, the conditions required by each type of post, the actual work address of each post, etc.

When judging whether the recruitment subject enterprise has risks, judging that the recruitment subject enterprise has risks by comparing the differences between the recruitment information images of the recruitment subject enterprise and the recruitment information images of the analog enterprises, so that after the recruitment information images of the recruitment subject enterprise are determined, the analog enterprises of the recruitment subject enterprise are also required to be found out, and the recruitment information images of the analog enterprises are determined, and the method specifically comprises the following steps:

the determining the second enterprise recruitment information representation according to the registration data may specifically include:

acquiring a plurality of recruitment data on a recruitment platform; the plurality of recruitment data is recruitment data corresponding to a plurality of enterprises;

Performing cluster analysis on the recruitment data according to the characteristic of the specific dimension in the registration data to obtain a plurality of analogy enterprises;

vectorizing the enterprise images corresponding to the plurality of analog enterprises to obtain vectors corresponding to the respective analog enterprise images;

calculating the gravity center position of the vector according to the vector corresponding to each analog enterprise image;

and converting the vector corresponding to the gravity center position of the vector into text information, and determining a second recruitment information portrait of the analog enterprise based on the text information.

The recruitment platform is also called a recruitment management platform. The recruitment management platform based on the Internet aims to assist the HR to complete the work of attracting, identifying, screening and recording talents outside enterprises in a more efficient manner. As an integral part of the talent management platform (Talent Management System). The recruitment platform comprises recruitment information corresponding to a large number of enterprises and resume information of a large number of job seekers.

The specific dimension in the above steps may refer to a dimension set according to a scene requirement in an actual application scene, for example: the operation scope of the enterprise, the operation address of the enterprise, the registration time of the enterprise, the registration capital, the business deadline, the registration authority, the registration status, the registration capital, the real-harvest capital, and the like.

Clustering is a process of classifying data into different classes or clusters, so objects in the same class or cluster have a large similarity, while objects in different classes or clusters have a large dissimilarity.

The goal of cluster analysis is to collect data on a similar basis to classify. Cluster analysis is used as descriptive data to measure similarity between different data sources and to classify the data sources into different clusters. Cluster Analysis (Cluster Analysis) is also known as group Analysis, and is a multivariate statistical Analysis method for classifying samples or indexes according to the theory of "physical clustering", the object in question is a large number of samples, and reasonable classification can be reasonably performed according to the respective characteristics, and no pattern is available for reference or follow, i.e. the classification is performed without prior knowledge.

The cluster analysis may have a variety of algorithms, and specific algorithms may include: euclidean distance, mahalanobis distance, mintype distance, manhattan distance, chi-square distance, binary variable distance, cosine similarity, pearson correlation coefficient, furthest (near) distance, center of gravity distance, and the like. Specifically, an algorithm of cluster analysis can be selected according to an actual application scene, and the method is not limited in the scheme.

In the scheme, cluster analysis is carried out on the recruitment data according to the characteristic of the specific dimension in the registration data, an analog enterprise which is relatively similar to the business type or the enterprise characteristic of each recruitment main enterprise is calculated, and then the portrait of the analog enterprise is vectorized to calculate the gravity center position of the vector to be used as a reference portrait of the analog enterprise group. Where the business type may refer to an empirical range of the enterprise, and the enterprise characteristics may refer to a registered place, a registered capital, a registered time, or a personnel scale of the enterprise, etc.

In this scheme, the representation generated by the analog enterprise recruitment representation generator may be considered as a low risk condition, and when some sensitive dimensions of a recruitment subject enterprise deviate too much from the analog enterprise recruitment representation, the risk may be implied and attention is required. Such as presenting a significant range of normal compensation that does not meet financial advisors in the industry, or anomalies in the senior history requirements, high salary low requirements, etc., may imply a risk.

In the above step, the clustering analysis is performed on the plurality of recruitment data according to the characteristic of the specific dimension in the registration data to obtain a plurality of analog enterprises, which may specifically include:

Performing cluster analysis on the recruitment data according to the registration address information in the registration data to obtain a first-class enterprise;

performing cluster analysis on the recruitment data according to the registration time information in the registration data to obtain a second-class enterprise;

performing cluster analysis on the recruitment data according to the registered capital information in the registered data to obtain a third analogy enterprise;

and carrying out cluster analysis on the recruitment data according to the operation range information in the registration data to obtain a fourth analogy enterprise.

In the above steps, the specific dimension is set as registration address information, registration time information, registration capital information and operation range information of the recruiter company, and a plurality of analog companies corresponding to each dimension are respectively determined based on each dimension. For example: the registration time of recruitment subject enterprises is 2 months and 10 days in 2009, the registration capital is 100 ten thousand RMB, and the registration address is: the experimental range of Beijing city is: and consulting house property information. At this time, according to the registration time of the recruitment subject enterprise, cluster analysis is performed on the plurality of recruitment data, and the first-class enterprise is obtained as follows: { Enterprise A, enterprise B, enterprise C }, the relationship between the registration time of the enterprise A, enterprise B and Enterprise C at this time and the registration time of the recruitment subject enterprise satisfies the preset condition, such as: the registration times are the same or the registration times are less than or equal to 1 year apart. According to the registration address of the recruitment subject enterprise, performing cluster analysis on the plurality of recruitment data to obtain a second-class enterprise as follows: { Enterprise D, enterprise E, enterprise F, enterprise G }, at this time, the relationship between the registration address of Enterprise D, enterprise E, enterprise F, enterprise G and the registration address of recruitment subject enterprise satisfies the preset condition, such as: the registered addresses are the same or belong to an integrated region, for example: the registered address belongs to any address in Jing Ji. According to the registered capital of the recruitment subject enterprise, performing cluster analysis on the plurality of recruitment data to obtain a third analogy enterprise as follows: { Enterprise H, enterprise I, enterprise J }, at this time, the relationship between the registered capital of Enterprise H, enterprise I, enterprise J and the registered capital of the recruited subject enterprise satisfies the preset condition, such as: the registered capital difference is between 20 tens of thousands. According to the experience range of the recruitment subject enterprise, cluster analysis is carried out on the plurality of recruitment data, and a fourth analogy enterprise is obtained as follows: { Enterprise K, enterprise L, enterprise M }, at this time, the experience scope of Enterprise K, enterprise L, enterprise M may be the same as the experience scope of recruited subject enterprises.

The image tag for generating the recruitment information image of the recruitment subject enterprise and the image tag for generating the recruitment information image of the analog enterprise are not fixed, and the image tag can be expanded according to the requirements in the actual application scene.

Through the method, various labels capable of representing enterprise recruitment features are automatically generated according to the standardized recruitment data, so that enterprise recruitment portraits are formed, the portraits labels can be flexibly called in a modular manner for subsequent risk identification, the development cost of a risk identification model is greatly reduced, and meanwhile, the labels are expandable at any time, so that the expandability is improved.

After the recruitment information portrait of the recruitment subject enterprise and the recruitment information portrait of the analog enterprise are determined, whether the recruitment subject enterprise has a risk can be determined by comparing the difference values between the two information portraits. When the difference value is greater than a first preset threshold, it can be determined that the recruitment subject enterprise is at risk, otherwise, it can be determined that the recruitment subject enterprise is not at risk. When determining that the recruitment subject enterprise is at risk, the risk type of the recruitment subject enterprise can be further determined, and specifically, the following method can be adopted:

Determining a risk key label in the recruitment subject enterprise for calculating the difference value, wherein the risk key label at least comprises the registration place, the actual operation place, the operation range and the post basic information;

comparing the risk key label in the first enterprise recruitment information portrait with the risk key label in the second enterprise recruitment information portrait to obtain similarity values of the same risk labels in the first enterprise recruitment information portrait and the second enterprise recruitment information portrait;

and determining the risk type of the recruitment subject enterprise according to the risk label with the similarity value smaller than a second preset threshold value.

Risk critical tags may represent tags that may be at risk, such as: for the remote management risk, the risk label can be an enterprise registration address and an enterprise actual management address; for out-of-range operations, the risk key tag may be the business's operational range. Therefore, the risk key label is related to the actual risk type, and in actual application, the preset risk label may be labels corresponding to as many enterprise risk types as possible.

Common risk types include: off-site management risk, over-range management risk, funds chain warning risk, delivery risk, illegal lending risk, and the like. The risk key tags may include registered place, actual business place, business scope, post basic information, etc.

For example: determining a risk tag of a recruitment subject enterprise a: the registered place is Beijing, the actual place: shanghai, registered business scope: wholesale and actual operation of Chinese patent medicines: the Chinese medicine and the Chinese patent medicine are wholesale and retail, western medicine and health care products are wholesale and retail. The registering place and the actual operating place of the analogy enterprise are the same as those of Beijing, and the operating range and the registering operating range are the same as each other: the Chinese patent medicine is wholesale. By comparison, enterprise A can be considered to be at risk for off-site operations and overseas operations.

The remote operation may refer to that the actual operation place of the enterprise is not registered, and the out-of-range operation may refer to that the operation subject goes beyond the operation range approved by the registration authority to conduct the operation.

The risk label and the risk type have a certain corresponding relation, for example: the risk tag is a business scope, then the risk type may be out-of-scope business, the risk tag is a registered address and an actual business place, then the risk type may be off-site business.

Of course, in practical application, the recruitment information portrait of the recruitment subject enterprise and the recruitment information portrait or business data of the analogy enterprise can be input into the risk identifier, and a plurality of risk probabilities of different risk types inferred according to the recruitment data can be output. Wherein each risk type corresponds to an identification model or a set of identification strategies, and can be flexibly added, deleted and modified by a user. The risk prediction based on recruitment data can be independently used for early warning, and the accuracy can be further improved by combining with other risk prediction modes. And (3) identifying the probability of each risk type in recruitment data by using a risk identifier, and when the probability of a certain type of risk exceeds a preset threshold, carrying out early warning on the risk type for a user to carry out risk study and judgment or continuously paying attention.

By the method in the foregoing embodiment, the technical effects that may be achieved in this solution may include:

1) The recruitment data is processed and actively identified in an automatic mode, so that the recruitment data early warning system has the capability of early warning, is easy to operate and maintain, and can realize early warning.

2) The real recruitment main body is identified from the nonstandard recruitment information with high accuracy through a natural language algorithm technology, and the vulnerability of the direct data matching method to nonstandard input is solved.

3) In addition, the scheme creatively provides an enterprise recruitment portrait technology, and performs labeled definition and management on enterprise recruitment information to form a portrait which can be flexibly pulled out and plugged into a component and can be reused by different applications.

4) Various labels capable of representing enterprise recruitment characteristics are automatically generated, so that enterprise recruitment portraits are formed, the portraits labels can be flexibly called in a modular mode for subsequent risk identification, the development cost of a risk identification model is greatly reduced, meanwhile, the labels are expandable at any time, and the expandability of the labels is improved.

Based on the same thought, the embodiment of the specification also provides a device corresponding to the method. Fig. 3 is a schematic diagram of an enterprise risk identification apparatus corresponding to fig. 2 provided in an embodiment of the present disclosure. As shown in fig. 3, the apparatus may include:

A recruitment data acquisition module 302, configured to acquire standardized recruitment data;

a recruitment subject enterprise identification module 304, configured to identify a recruitment subject enterprise corresponding to the recruitment data using a recruitment subject enterprise identification model;

a first enterprise recruitment information representation generating module 306 configured to generate a first enterprise recruitment information representation of the recruitment subject enterprise according to the recruitment data;

a registration data obtaining module 308, configured to obtain registration data of the recruitment subject enterprise;

a second enterprise recruitment information representation determining module 310, configured to determine a second enterprise recruitment information representation according to the registration data, where the second enterprise recruitment information representation is a recruitment information representation of an analog enterprise of the recruiting subject enterprise;

a recruitment information representation difference value determination module 312 for calculating a difference value between the first enterprise recruitment information representation and the second enterprise recruitment information representation;

a judging module 314, configured to judge whether the difference value is greater than a first preset threshold, to obtain a judging result;

and an enterprise risk identification module 316 configured to determine that the recruitment subject enterprise is at risk when the determination result indicates that the difference value is greater than a first preset threshold.

The present examples also provide some embodiments of the method based on the apparatus of fig. 3, as described below.

Optionally, the apparatus may further include:

the initial recruitment data acquisition module is used for acquiring initial recruitment data from the recruitment platform;

the enterprise knowledge graph construction module is used for constructing an enterprise knowledge graph according to the initial recruitment data and registration data in the third party mechanism;

the post knowledge graph construction module is used for constructing a post knowledge graph according to the initial recruitment data;

the standard enterprise name determining module is used for standardizing the enterprise names in the initial recruitment data according to the enterprise knowledge graph to obtain standard enterprise names;

the standard post name determining module is used for standardizing the post names in the initial recruitment data according to the post knowledge graph to obtain standard post names;

and the recruitment data standardization module is used for replacing the post names in the initial recruitment data by the standard post names and replacing the enterprise names in the initial recruitment data by the standard enterprise names to obtain standardized recruitment data.

Optionally, the enterprise knowledge graph construction module may specifically include:

A historical registration data determining unit, configured to determine, for a business entity, historical registration data of the business entity in a third party institution;

the standard enterprise name and great-use name determining unit is used for determining the standard enterprise name and great-use name of the enterprise entity according to the historical registration data;

a business alias determining unit, configured to extract a business alias of the business entity from the initial recruitment data;

the enterprise knowledge graph construction unit is used for constructing the enterprise knowledge graph according to the standard enterprise name, the great-use name and the enterprise alias of the enterprise entity;

the standard enterprise determination module may be specifically configured to:

Optionally, the post knowledge graph construction module may specifically include:

the active post name determining unit is used for extracting the active post name of a post entity from the initial recruitment data aiming at the post entity;

the post knowledge graph construction unit is used for constructing the post knowledge graph according to the current post name;

the standard post name determining unit is used for determining the current post name with the highest occurrence frequency in the post knowledge graph as a standard post name;

The standard post name determining module may be specifically configured to:

and converting the active post name into the standard post name.

Optionally, the recruitment subject enterprise identification module 304 may specifically include:

an all-enterprise-entity obtaining unit, configured to obtain all enterprise entities in the recruitment data;

the recruitment entity enterprise probability prediction unit is used for inputting the recruitment data into the recruitment entity enterprise identification model to obtain the prediction probability that each enterprise entity in all enterprise entities belongs to the recruitment entity enterprise;

and the recruitment subject enterprise determining unit is used for determining the enterprise entity with the prediction probability larger than a preset threshold and the maximum prediction probability as the recruitment subject enterprise.

Optionally, the first recruitment information representation generating module 306 may specifically include:

the portrait tag determining unit is used for extracting a portrait tag of the recruitment subject enterprise from the recruitment data, and the portrait tag is used for representing recruitment characteristics of the recruitment subject enterprise in a specific dimension; the portrait tag at least comprises a recruitment type tag of the recruitment subject enterprise, a condition tag of each recruitment, and a work area tag of each recruitment;

And the first enterprise recruitment information portrait generation unit is used for generating a first enterprise recruitment information portrait of the recruitment subject enterprise according to the portrait tag.

Optionally, the second recruitment information representation determining module 310 may be specifically configured to:

Optionally, the cluster analysis unit may specifically be configured to:

Optionally, the apparatus may further include:

the risk key label determining module is used for determining a risk key label in the recruitment subject enterprise for calculating the difference value, wherein the risk key label at least comprises the registration place, the actual operation place, the operation range and the post basic information;

the risk key label comparison module is used for comparing the risk key label in the first enterprise recruitment information portrait with the risk key label in the second enterprise recruitment information portrait to obtain similarity values of the same risk labels in the first enterprise recruitment information portrait and the second enterprise recruitment information portrait;

the risk type determining unit is used for determining the risk type of the recruitment subject enterprise according to the risk label with the similarity value smaller than a second preset threshold value.

Optionally, the apparatus may further include:

The training sample acquisition module is used for acquiring a recruitment data training sample set of a known recruitment subject enterprise;

the output module is used for inputting the training samples into an initial recruitment subject enterprise identification model for each training sample in the training sample set and outputting recruitment subject enterprises;

and the training module is used for adjusting the model parameters of the initial recruitment subject enterprise identification model according to the difference between the recruitment subject enterprise and the known recruitment subject enterprise to obtain a trained recruitment subject enterprise identification model.

Based on the same thought, the embodiment of the specification also provides equipment corresponding to the method.

Fig. 4 is a schematic diagram of an enterprise risk identification apparatus corresponding to fig. 2 provided in an embodiment of the present disclosure. As shown in fig. 4, the apparatus 400 may include:

at least one processor 410; the method comprises the steps of,

a memory 430 communicatively coupled to the at least one processor; wherein,,

the memory 430 stores instructions 420 executable by the at least one processor 410, the instructions being executable by the at least one processor 410 to enable the at least one processor 410 to:

acquiring standardized recruitment data;

acquiring registration data of the recruitment subject enterprise;

Based on the same thought, the embodiment of the specification also provides a computer readable medium corresponding to the method. Computer readable instructions stored on a computer readable medium, the computer readable instructions being executable by a processor to perform a method of:

acquiring standardized recruitment data;

acquiring registration data of the recruitment subject enterprise;

In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable Gate Array, FPGA)) is an integrated circuit whose logic function is determined by the programming of the device by a user. The designer programs itself to "integrate" a digital system onto a single PLD without requiring the chip manufacturer to design and fabricate application specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), lava, lola, myHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC625D, atmelAT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. An enterprise risk identification method, comprising:

acquiring standardized recruitment data; the standardized recruitment data comprises a standard enterprise name and a standard post name, wherein the standard enterprise name is obtained through an enterprise knowledge graph, and the standard post name is obtained through a post knowledge graph;

generating a first enterprise recruitment information portrait of the recruitment subject enterprise according to the recruitment data; the first enterprise recruitment information portrait is used for knowing recruitment characteristics of the recruitment subject enterprise;

acquiring registration data of the recruitment subject enterprise;

Identifying the risk of the recruitment subject business based on the difference value of the first business recruitment information portrait and the second business recruitment information portrait specifically comprises:

2. The method of claim 1, further comprising, prior to the obtaining the normalized recruitment data:

acquiring initial recruitment data from a recruitment platform;

constructing a post knowledge graph according to the initial recruitment data;

3. The method of claim 2, wherein the constructing an enterprise knowledge graph based on the initial recruitment data and registration data in a third party institution, specifically comprises:

the step of normalizing the enterprise name in the initial recruitment data according to the enterprise knowledge graph to obtain a standard enterprise name specifically comprises the following steps:

4. The method of claim 2, wherein the constructing a post knowledge-graph from the initial recruitment data comprises:

constructing the post knowledge graph according to the current post name;

the post names in the initial recruitment data are standardized according to the post knowledge graph to obtain standard post names, and the method specifically comprises the following steps:

and converting the active post name into the standard post name.

5. The method of claim 1, wherein the identifying the recruitment subject business from the recruitment data using a recruitment subject business identification model comprises:

acquiring all enterprise entities in the recruitment data;

6. The method of claim 1, the generating a first representation of the recruitment information for the recruiter's enterprise based on the recruitment data, comprising:

7. The method of claim 1, the determining a second business recruitment information representation based on the registration data, comprising:

8. The method of claim 7, wherein the clustering analysis is performed on the plurality of recruitment data according to the characteristic of the specific dimension in the registration data to obtain a plurality of analog enterprises, and the method specifically comprises:

9. The method of claim 1, after the determining that the recruitment subject enterprise is at risk, further comprising:

determining a risk key label in the recruitment subject enterprise for calculating the difference value, wherein the risk key label at least comprises registration place, actual operation place, operation range and post basic information;

10. The method of claim 1, further comprising, prior to identifying the recruiter business corresponding to the recruitment data using a recruiter business identification model:

11. An enterprise risk identification apparatus, comprising:

the recruitment data acquisition module is used for acquiring standardized recruitment data; the standardized recruitment data comprises a standard enterprise name and a standard post name, wherein the standard enterprise name is obtained through an enterprise knowledge graph, and the standard post name is obtained through a post knowledge graph;

the first enterprise recruitment information portrait generation module is used for generating a first enterprise recruitment information portrait of the recruitment subject enterprise according to the recruitment data; the first enterprise recruitment information portrait is used for knowing recruitment characteristics of the recruitment subject enterprise;

the enterprise risk identification module is used for identifying the risk of the recruitment main enterprise based on the difference value of the first enterprise recruitment information portrait and the second enterprise recruitment information portrait; the enterprise risk identification module is specifically configured to calculate a difference value between the first enterprise recruitment information portrait and the second enterprise recruitment information portrait; judging whether the difference value is larger than a first preset threshold value or not to obtain a judging result; and when the judging result shows that the difference value is larger than a first preset threshold value, determining that the recruitment subject enterprise has risks.

12. The apparatus of claim 11, the apparatus further comprising:

13. The apparatus of claim 12, the enterprise knowledge graph construction module specifically comprising:

the standard enterprise determination module is specifically configured to:

14. The device of claim 12, wherein the post knowledge graph construction module specifically comprises:

the standard post name determining module is specifically configured to:

and converting the active post name into the standard post name.

15. The apparatus of claim 11, the recruitment subject enterprise identification module comprising:

16. The apparatus of claim 11, the first enterprise recruitment information representation generation module comprising:

17. The apparatus of claim 11, wherein the second enterprise recruitment information representation determining module is configured to:

18. The apparatus of claim 11, the apparatus further comprising:

the risk key label determining module is used for determining a risk key label in the recruitment subject enterprise for calculating the difference value, wherein the risk key label at least comprises basic information of a registration place, an actual operation place, an operation range and a post;

19. The apparatus of claim 11, the apparatus further comprising:

20. An enterprise risk identification apparatus, comprising:

at least one processor; the method comprises the steps of,

a memory communicatively coupled to the at least one processor; wherein,,

acquiring registration data of the recruitment subject enterprise;

21. A computer readable medium having stored thereon computer readable instructions executable by a processor to implement the enterprise risk identification method of any of claims 1 to 10.