Enterprise operation address migration prediction method and device, electronic equipment and medium

Abstract

The invention discloses an enterprise operation address migration prediction method and apparatus, an electronic device and a medium. The method comprises the steps of obtaining an enterprise operation address migration feature data set; constructing a plurality of enterprise operation address migration influence factors, and determining target quantitative data corresponding to each enterprise operation address migration influence factor from the enterprise migration feature data set; determining a quantization index corresponding to each enterprise migration influence factor according to the target quantization data corresponding to each enterprise operation address migration influence factor; and obtaining an enterprise migration tendency quantitative evaluation model, and generating an enterprise operation address migration prediction result by using the enterprise migration tendency quantitative evaluation model according to the quantitative index corresponding to each enterprise migration influence factor. The method can achieve the prediction of the migration of the enterprise operation address, improves the accuracy and efficiency of the prediction of the migration of the enterprise operation address, and can be widely applied to the technical field of enterprise management.

Description

Technical Field

[0001] The present application relates to the field of enterprise management technology, and in particular to a method, device, electronic equipment and medium for predicting the migration of an enterprise's business address. Background Art

[0002] Enterprise relocation refers to the process of transferring the registered address or actual business location of an enterprise from one location to another. This includes the relocation of the enterprise's headquarters, the transfer of production bases, the establishment or cancellation of branches, etc. Enterprise relocation is a common phenomenon in the market economy and is affected by many factors, such as cost, market proximity, industrial chain supply chain optimization, policy environment, tax incentives, etc. Enterprise relocation has a very significant impact and significance on enterprises and economic markets.

[0003] In the related technologies, the prediction of enterprise business address relocation is mainly carried out by constructing multi-source basic data such as enterprise basic information, enterprise business activities and enterprise external environment, and building an enterprise migration prediction model through machine learning and artificial intelligence algorithms to obtain enterprise migration prediction results. It is mainly based on the reflection of the enterprise's proactive behavior and cannot fully and effectively reflect the current migration situation of the enterprise. If the enterprise changes but the relevant data is not updated in time, there will be a lag in migration prediction, resulting in a decrease in the accuracy and efficiency of the enterprise business address relocation prediction. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a method, device, electronic device and medium for predicting the migration of an enterprise business address, which can realize the prediction of the migration of an enterprise business address and improve the accuracy and efficiency of the prediction of the migration of an enterprise business address.

[0005] On the one hand, the embodiment of the present application proposes a method for predicting the migration of an enterprise's business address, the method comprising the following steps:

[0006] Acquire a data set of enterprise business address migration characteristics; the data set of enterprise business address migration characteristics at least includes enterprise macro-factor migration data, enterprise business management data and enterprise communication big data;

[0007] Constructing a plurality of enterprise business address migration influencing factors, and determining target quantitative data corresponding to each of the enterprise business address migration influencing factors from the enterprise migration feature data set;

[0008] Determine the quantitative index corresponding to each of the enterprise relocation influencing factors according to the target quantitative data corresponding to each of the enterprise business address relocation influencing factors;

[0009] A quantitative assessment model for enterprise migration tendency is obtained, and the enterprise migration tendency quantitative assessment model is used to generate a prediction result of enterprise business address migration according to the quantitative index corresponding to each enterprise migration influencing factor.

[0010] In some embodiments, the constructing of multiple enterprise business address migration influencing factors and determining target quantitative data corresponding to each of the enterprise business address migration influencing factors from the enterprise migration feature data set specifically includes:

[0011] Filtering the enterprise macro-factor migration data from the enterprise business address migration feature data set, and constructing the enterprise migration macro-influence factor according to the enterprise macro-factor migration data;

[0012] Selecting the business administration data of the enterprise from the business address migration feature data set, and constructing the influencing factors of the business operation change of the enterprise according to the business administration data of the enterprise;

[0013] The enterprise communication big data is selected from the enterprise business address migration feature data set, and an enterprise communication aggregation tendency influencing factor is constructed based on the enterprise communication big data.

[0014] In some embodiments, determining the quantitative index corresponding to each of the enterprise relocation influencing factors according to the target quantitative data corresponding to each of the enterprise business address relocation influencing factors specifically includes:

[0015] According to the enterprise macro-factor migration data, a first quantitative index is determined, where the first quantitative index is a quantitative index corresponding to the enterprise migration macro-influencing factor, wherein the first quantitative index is calculated by the following formula:

[0016] PI = (p1 + p2) / 2;

[0017]

[0018] p i ={x i ,y i};

[0019] p2 = θ / 90;

[0020] θ = [180*arctan(b)] / π;

[0021]

[0022] Among them, PI is the first quantitative index, p1 is the first indicator of macro factors, and p i represents the number of macro strategies released in the i-th month of the current year, p z is the total amount of macro strategy released in the current year, p2 is the second indicator of macro factors, {x i ,y i}composes a time series data set, x i Indicates the current month, yi Indicates the current month x i The number of macro strategies released, n is the sequence length of the time series data set, b is the time series data set {x i ,y i} is the slope of the linear fitting curve corresponding to θ, and θ is the curve mapping angle corresponding to the slope b;

[0023] According to the business administration data of the enterprise, a second quantitative index is calculated, where the second quantitative index is a quantitative index corresponding to the enterprise operation change influencing factor, wherein the enterprise operation change influencing factor includes a revenue scale influencing factor and a manpower scale influencing factor, and the second quantitative index is calculated by the following formula:

[0024]

[0025] Among them, EMC is the second quantitative index, is the quantitative index of the revenue scale influencing factor, and ECC is the quantitative index of the manpower scale influencing factor;

[0026] According to the enterprise communication big data, the current office gathering place of the enterprise is determined, the office gathering data corresponding to the current office gathering place of the enterprise is obtained, and a third quantitative index is calculated. The third quantitative index is a quantitative index corresponding to the enterprise communication gathering tendency influencing factor, wherein the current office gathering place of the enterprise is the office address where the largest number of office personnel gather within a continuous time preset by the current enterprise, and the third quantitative index is calculated by the following formula:

[0027] EA=[180*arctan(b wl )] / 90π;

[0028]

[0029]

[0030] Among them, EA is the third quantitative index, s is the total number of employees in the enterprise, and w k is the kth time step, is a sequence data set showing the number of employees in the current office cluster of an enterprise changing with the preset time step, h is the total number of time steps, m is the total number of time steps, k is the number of employees in the current office cluster of the enterprise at the kth time step, b wl For sequence data sets The slope of the corresponding linear fitting curve.

[0031] In some embodiments, the step of obtaining a quantitative assessment model for enterprise migration tendency and using the quantitative assessment model for enterprise migration tendency to generate a prediction result of enterprise business address migration according to the quantitative index corresponding to each enterprise migration influencing factor specifically includes:

[0032] Using the enterprise migration tendency quantitative assessment model to perform weighted correction calculation according to the first quantitative index, the second quantitative index and the third quantitative index, to determine the corresponding quantitative value of the enterprise business address migration;

[0033] Get the company's current registered business address;

[0034] When the quantified value of the enterprise's business address migration is greater than a given migration quantification threshold, and the enterprise's current registered business address is inconsistent with the enterprise's current office cluster, the enterprise's business address migration prediction result is determined to be a migration from the enterprise's current registered business address to the enterprise's current office cluster, and the enterprise's current office cluster is set as the enterprise's current registered business address; otherwise, the enterprise's business address migration prediction result is determined to be to stop the enterprise's business address migration.

[0035] In some embodiments, the enterprise migration tendency quantitative assessment model is represented by the following formula:

[0036] ERT=EA*ω3+EMC*ω2+PI*ω1;

[0037] Among them, ERT is the quantitative value of the enterprise business address migration, EA is the third quantitative index, ω3 is the weight corresponding to the third quantitative index, EMC is the second quantitative index, ω2 is the weight corresponding to the second quantitative index, PI is the first quantitative index, and ω1 is the weight corresponding to the first quantitative index.

[0038] In some embodiments, the quantitative index of the revenue scale impact factor Calculated by the following formula:

[0039]

[0040]

[0041]

[0042] in, is a quantitative index of the revenue scale influencing factor, RA avg for The value before logarithmic transformation, RA qis the quantitative indicator corresponding to the qth revenue scale influencing factor. The quantitative indicators corresponding to the revenue scale influencing factor at least include the registered capital of the enterprise, the operating income of the enterprise and the amount of the enterprise's large order winning bid. g is the number of quantitative indicators, r q1 For RA q The current year specific value, r q0 For RA q The CI is the preset inflation factor.

[0043] In some embodiments, the quantitative index ECC of the manpower scale impact factor is calculated by the following formula:

[0044]

[0045] b e =[180*arctan(b el )] / 90π;

[0046]

[0047] RN = {c t , d t};

[0048]

[0049] Among them, EC is the year-on-year change rate of employees in the enterprise, the enterprise business administration data includes the enterprise human resource scale data, e1 is the number of employees in the enterprise in the current year contained in the enterprise human resource scale data, e0 is the number of employees in the enterprise in the previous year contained in the enterprise human resource scale data, μ is the preset year-on-year change rate deviation threshold, RN is a time series data set constructed based on the number of employees recruited by the enterprise each month, c t is the tth recruitment month of the current year, d t For recruitment month c t The corresponding number of employees recruited by the enterprise, t = 1, 2, 3, ..., T, T is the number of recruitment months in the current year, b el is the slope of the linear fitting curve corresponding to the time series data set RN, b e is the slope b el The corresponding curve mapping angle, d is the total number of recruits in the current year.

[0050] On the other hand, an embodiment of the present application provides a device for predicting the migration of an enterprise's business address, the device comprising:

[0051] The first module is used to obtain a data set of enterprise business address migration characteristics; the data set of enterprise business address migration characteristics at least includes enterprise macro-factor migration data, enterprise business management data and enterprise communication big data;

[0052] The second module is used to construct a plurality of enterprise business address migration influencing factors, and determine the target quantitative data corresponding to each of the enterprise business address migration influencing factors from the enterprise migration feature data set;

[0053] The third module is used to determine the quantitative index corresponding to each of the enterprise relocation influencing factors according to the target quantitative data corresponding to each of the enterprise business address relocation influencing factors;

[0054] The fourth module is used to obtain a quantitative assessment model for enterprise migration tendency, and use the quantitative assessment model for enterprise migration tendency to generate a prediction result of enterprise business address migration according to the quantitative index corresponding to each enterprise migration influencing factor.

[0055] On the other hand, an embodiment of the present application provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the aforementioned method when executing the computer program.

[0056] On the other hand, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0057] The embodiments of the present application include at least the following beneficial effects: the present application provides a method, device, electronic device and medium for predicting the migration of an enterprise business address, which obtains a characteristic data set of the migration of an enterprise business address, constructs multiple influencing factors of the migration of an enterprise business address, determines the target quantitative data corresponding to each enterprise business address migration influencing factor from the enterprise migration characteristic data set, determines the quantitative index corresponding to each enterprise migration influencing factor according to the target quantitative data corresponding to each enterprise business address migration influencing factor, and generates the prediction result of the migration of an enterprise business address according to the quantitative index corresponding to each enterprise migration influencing factor using the quantitative evaluation model of enterprise migration tendency. The present application can comprehensively integrate enterprise macro-factor migration data, enterprise business management data and enterprise communication big data to obtain a characteristic data set of the migration of an enterprise business address, predict the migration of an enterprise business address based on the characteristic data set of the migration of an enterprise business address, realize the prediction of the migration of an enterprise business address, and improve the accuracy and efficiency of the prediction of the migration of an enterprise business address. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of a method for predicting the migration of an enterprise's business address provided in an embodiment of the present application;

[0059] Figure 2 is a flowchart of step S102 in an embodiment of the present application;

[0060] Figure 3is a flowchart of step S103 in an embodiment of the present application;

[0061] Figure 4 is a schematic diagram of determining the current office gathering place of an enterprise in an embodiment of the present application;

[0062] Figure 5 It is a schematic diagram of the factors affecting business operation changes in the embodiment of the present application;

[0063] Figure 6 is a flowchart of step S104 in an embodiment of the present application;

[0064] Figure 7 is a schematic diagram of a quantitative assessment model for enterprise migration tendency in an embodiment of the present application;

[0065] Figure 8 is a flowchart of step S403 in an embodiment of the present application;

[0066] Fig. 9 It is a structural schematic diagram of a device for predicting business address migration of an enterprise provided in an embodiment of the present application;

[0067] Fig.10 It is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0069] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0070] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0071] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0072] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0073] In addition to the impact of policy adjustments on business costs and opportunities, the relocation of business addresses will also be affected by corporate strategic adjustments, brand and market expansion, etc. Companies that pay attention to regional corporate relocation or government industrial planning are conducive to seeking lower operating costs, such as labor, rent, energy, etc. As the concept of digital business continues to deepen in the economic market, companies are also paying more attention to the improvement of target markets and brand image in their development because they want to improve market response speed and customer service quality. In this process, companies will spontaneously combine local policies to carry out corporate relocation activities.

[0074] With the high-quality development of the digital economy, the relocation of business addresses of enterprises has also had an important impact on the economic market. The relocation of business addresses of enterprises is conducive to promoting local industrial upgrading and structural adjustment, spontaneously eliminating backward production capacity, and introducing new industries. In view of the uneven economic development among regions, the relocation of enterprises can promote regional economic growth and achieve the role of regional balanced regulation. In addition, the relocation of high-tech enterprises can also drive the improvement of innovation capabilities, promote technological progress and promote the high-quality improvement of the market economy.

[0075] The relevant technologies for predicting the migration of business addresses are as follows:

[0076] Patent No. CN202211267371.7 "A method and device for monitoring and early warning of enterprise migration big data for urban operations" mainly constructs a multi-source basic database for enterprise migration analysis including an enterprise basic information database, an enterprise business activity database and an enterprise external environment database; based on the multi-source basic database for enterprise migration analysis, constructs an enterprise migration analysis feature vector including basic information characteristics, business activity characteristics and external environment characteristics; constructs an enterprise migration risk prediction model through a machine learning algorithm; and inputs the enterprise migration analysis feature vector into the enterprise migration risk prediction model to obtain an enterprise migration risk prediction result.

[0077] Patent No. CN202111386130.X "A method for analyzing enterprise migration and park investment promotion based on artificial intelligence algorithm" mainly organizes the feature data set of migrated enterprises; normalizes the feature data set of migrated enterprises and processes it into numerical type features that can be recognized by the algorithm; inputs the organized data set into the PCA principal component analysis algorithm for feature optimization and dimensionality reduction; divides the feature set obtained after PCA processing into a training set and a test set; inputs the training set into the LSSVM classification model for training to train the distinguishing boundary between migrated and non-migrated enterprises, and then uses the test data to test the accuracy of the distinguishing boundary analyzed by the LSSVM model, obtains the classification boundary between migrated and non-migrated enterprises, and predicts and judges the migration trend of enterprises.

[0078] In the related technologies, the prediction of enterprise business address relocation is mainly carried out by constructing multi-source basic data such as enterprise basic information, enterprise business activities and enterprise external environment, and building an enterprise migration prediction model through machine learning and artificial intelligence algorithms to obtain enterprise migration prediction results. It is mainly based on the reflection of the enterprise's proactive behavior and cannot fully and effectively reflect the current migration situation of the enterprise. If the enterprise changes but the relevant data is not updated in time, there will be a lag in migration prediction, resulting in a decrease in the accuracy and efficiency of the enterprise business address relocation prediction.

[0079] Based on this, the embodiments of the present application propose a method, device, electronic device and medium for predicting the migration of an enterprise business address, which combines enterprise macro-factor migration data, enterprise industrial and commercial management data, enterprise communication big data and other enterprise business address migration related data to construct a variety of enterprise business address migration influencing factors. Based on the target quantitative index of the multiple enterprise business address migration influencing factors, the enterprise business address migration prediction results are generated through the enterprise migration tendency quantitative evaluation model, so as to achieve efficient and comprehensive enterprise business address migration prediction.

[0080] Reference Figure 1 , Figure 1This is an optional flowchart of a method for predicting the migration of an enterprise business address provided in an embodiment of the present application. The method may include but is not limited to steps S101 to S104:

[0081] Step S101, obtaining a data set of enterprise business address migration characteristics; the data set of enterprise business address migration characteristics at least includes enterprise macro-factor migration data, enterprise business management data and enterprise communication big data;

[0082] Step S102, constructing a plurality of enterprise business address migration influencing factors, and determining target quantitative data corresponding to each enterprise business address migration influencing factor from the enterprise migration feature data set;

[0083] Step S103, determining the quantitative index corresponding to each enterprise relocation influencing factor according to the target quantitative data corresponding to each enterprise's business address relocation influencing factor;

[0084] Step S104, obtaining a quantitative assessment model for enterprise migration tendency, and using the quantitative assessment model for enterprise migration tendency to generate a prediction result of enterprise business address migration according to the quantitative index corresponding to each enterprise migration influencing factor.

[0085] In some embodiments, there are many factors that affect the relocation of an enterprise from an existing office address to another address, such as changes in the local business environment, changes in rent, expansion of the enterprise's operating area, industrial supporting facilities, enterprise expansion, etc. Therefore, in the process of judging the relocation of an enterprise's operating address, in order to more accurately quantify whether the enterprise has relocated or has a tendency to relocate, it is necessary to fully consider various factors that affect the relocation of the enterprise's operating address.

[0086] By integrating data sources such as enterprise macro-factor migration data, enterprise industrial and commercial data, and enterprise communication big data, we build an enterprise migration analysis dataset to characterize the migration characteristics of enterprise business addresses.

[0087] Optionally, the enterprise macro-factor migration data includes changes in support for the industry to which the enterprise belongs, such as industry support, policy release time, and number of policy releases; the enterprise business management data mainly includes two aspects of data: enterprise basic information and enterprise operating information. The basic information of the enterprise includes enterprise establishment time, enterprise industry affiliation, enterprise registered capital information and other enterprise industrial and commercial registration information; the enterprise operating information includes annual report information, address change information, changes in the number of social security payers and other enterprise operating related information, which is used to show the dynamic changes of expansion and contraction of enterprise operations.

[0088] Compared with the enterprise macro-factor migration data and enterprise business management data, which are updated infrequently, enterprise communication big data contains more and more timely dynamic information on enterprise changes, which helps to timely understand the enterprise migration tendency. Enterprise communication big data includes communication behavior data generated in daily business production activities such as enterprise call frequency, Internet access time, and short message sending and receiving. It shows the changes in the business activities of the enterprise on the time axis in real-time time dimension. This part of data is combined with communication base station information to generate enterprise business address migration feature data in spatial locations such as the location of the base station of enterprise personnel communication equipment, the location of the enterprise business location, and changes in active communication gathering places. Therefore, enterprise communication big data can dynamically display the changes in the business location of the enterprise from the time and space dimensions, and quantitatively evaluate the possibility of enterprise business address migration. At the same time, the real-time nature of enterprise communication big data can reduce the inability to timely estimate the changes in the business address of the enterprise due to the lag in update time.

[0089] In some embodiments, reference Figure 2 , Figure 2 This is an optional flowchart of step S102 in the embodiment of the present application. Step S102 may include but is not limited to steps S201 to S203:

[0090] Step S201, filtering out enterprise macro-factor migration data from the enterprise business address migration feature data set, and constructing enterprise migration macro-influencing factors based on the enterprise macro-factor migration data;

[0091] Step S202, selecting the business administration data of enterprises from the business address migration feature data set, and constructing the influencing factors of business operation changes according to the business administration data of enterprises;

[0092] Step S203, filtering out enterprise communication big data from the enterprise business address migration feature data set, and constructing enterprise communication aggregation tendency influencing factors based on the enterprise communication big data.

[0093] In step S201 of some embodiments, with respect to macro factors affecting enterprise migration, optionally, the preferential policies of the relevant management department of the place of business address for the industry to which the enterprise belongs, such as the number of relevant preferential policies issued, the time of issuance, the authority of the issuing unit, etc., have a great correlation with maintaining the stability of the enterprise's place of business; secondly, the degree of concentration of the industry to which the enterprise belongs in the place of business, the completeness of the industry chain supply chain, the scale of the industry and other industry-related industry characteristics are greatly related to whether the enterprise continues to operate in the place of business.

[0094] Based on the above analysis, the macro-influencing factors of enterprise migration are determined, including the number of industry policies in the current year, the time of the latest policy, the number of monthly policies in the current year (such as the number of macro-strategy releases), etc.

[0095] In step S202 of some embodiments, the development of the enterprise itself has a very high impact on the enterprise's decision to relocate. When the scale of the enterprise changes, the choice of office location will change to a certain extent. For example, when the enterprise develops well, the scale of the enterprise expands and the overall economic strength increases, in order to demonstrate the strength of the enterprise, the requirements for the size of the office area and the quality of the office environment will be higher. If the current office location cannot meet the needs, relocation may occur. On the contrary, when the performance of the enterprise declines and the business operation has problems, resulting in the shrinking of the scale of the enterprise, the enterprise may decide to relocate due to cost issues in order to balance income and expenditure. Based on the above analysis, the influencing factors of the enterprise's business changes are determined from the dimension of business information changes.

[0096] Changes in human resource scale and revenue scale can directly reflect changes in business operations of an enterprise. Therefore, from the perspective of changes in human resource scale and revenue scale, based on the characteristic indicator data such as the number of employees in the enterprise, the registered capital of the enterprise, the number of employees recruited by the enterprise, the operating income of the enterprise, and the amount of the winning bid of large orders contained in the business management data of the enterprise, the influencing factors of business operations changes are constructed and quantitative calculations are performed.

[0097] In step S203 of some embodiments, the operator network communication capabilities are needed in the daily production and life of the enterprise, business dealings between enterprises, and communication activities among internal personnel of the enterprise. For example, the use of electronic products such as calls, video conferencing, and electronic office work all require connection to the operator network to be implemented. In this process, a large amount of communication trajectory behavior information will be retained. By analyzing the changes in the trajectory positions of all enterprise employees, the office gathering places of enterprise employees can be analyzed in a timely and effective manner, thereby gaining effective insight into the changing trends of the enterprise office gathering places.

[0098] According to the changing trend of corporate office clusters, that is, the changing trend of the number of corporate employees in each office cluster, the influencing factors of corporate communication clustering tendency are constructed and quantitatively calculated.

[0099] In some embodiments, reference Figure 3 , Figure 3 This is an optional flowchart of step S103 in the embodiment of the present application. Step S103 may include but is not limited to steps S301 to S303:

[0100] Step S301, determining a first quantitative index according to the enterprise macro-factor migration data, where the first quantitative index is a quantitative index corresponding to the enterprise migration macro-influencing factor;

[0101] Step S302, calculating a second quantitative index based on the business administration data of the enterprise, where the second quantitative index is a quantitative index corresponding to the enterprise operation change influencing factor, wherein the enterprise operation change influencing factor includes a revenue scale influencing factor and a manpower scale influencing factor;

[0102] Step S303, based on the enterprise communication big data, determine the current office clustering location of the enterprise, obtain the office clustering data corresponding to the current office clustering location of the enterprise, and calculate the third quantitative index, where the third quantitative index is the quantitative index corresponding to the enterprise communication clustering tendency influencing factor, wherein the current office clustering location of the enterprise is the office address with the largest number of office personnel gathered within the continuous time preset by the current enterprise.

[0103] In some embodiments, enterprise communication big data includes communication track information of all employees of the enterprise. By analyzing the communication track information of all employees of the enterprise, the office cluster with the most densely communicated in a continuous period of time is determined, and the office cluster with the most densely communicated in a continuous period of time is determined as the current office cluster of the enterprise.

[0104] Exemplarily, the communication trajectory information of enterprise employees includes the communication trajectory information during working hours and non-working hours. In order to effectively distinguish the information of enterprise employees' working places and non-working places, for enterprise employees, it is assumed that the working time period is from 9:00 am to 6:00 pm, and Saturdays, Sundays and holidays are not calculated. Based on this, the communication locations of enterprise employees are analyzed. In order to prevent the influence of abnormal data factors on the universality of the rules, one week is used as the time step, and the location of the workplace with the longest working time in a week is calculated as the actual workplace of the enterprise employees. It is assumed that the working time of the enterprise employees at the actual workplace every day corresponds to t w , the number of working days in a week for enterprise employees is week, T si is the maximum working time, T si The corresponding actual working place is p si , T si The calculation formula is as follows:

[0105]

[0106] Based on the T si , determine the actual work location corresponding to each enterprise employee si , the actual work location corresponding to each enterprise employee si Perform statistical summary and take the p with the highest number of occurrences si As the current office gathering place for enterprises.

[0107] Optionally, refer to Figure 4 , Figure 4It is an optional schematic diagram for determining the current office gathering place of an enterprise in an embodiment of the present application, wherein the enterprise employees include 1 to 8, the longest working time of each enterprise employee is calculated, and the work position corresponding to the longest working time is determined as the actual work place of the enterprise employee. The actual work places of enterprise employees 1 to 5 are all p1, the actual work places of enterprise employees 6 and 7 are p2, and the actual work place of enterprise employee 8 is p3. Therefore, p1 appears the most times compared with p2 and p3, and p1 is determined as the current office gathering place ps of the enterprise.

[0108] In some embodiments, the first quantitative index is calculated by the following formula:

[0109] PI = (p1 + p2) / 2;

[0110]

[0111] p i ={x i ,y i};

[0112] p2 = θ / 90;

[0113] θ = [180*arctan(b)] / π;

[0114]

[0115] Among them, PI is the first quantitative index, p1 is the first indicator of macro factors, and p i represents the number of macro strategies released in the i-th month of the current year, p z is the total amount of macro strategy released in the current year, p2 is the second indicator of macro factors, {x i ,y i}composes a time series data set, x i Indicates the current month, y i Indicates the current month x i The number of macro strategies released, n is the sequence length of the time series data set, b is the time series data set {x i ,y i} is the slope of the linear fitting curve corresponding to , and θ is the curve mapping angle corresponding to the slope b.

[0116] To quantify the trend of the number of macro factor strategy releases over time, a p-value is constructed based on the number of macro factor strategy releases per month. i ={X i ,y iBased on the time series data set, the least squares regression method is used for linear regression fitting to calculate the slope b of the fitting equation. Then, based on the positive or negative value of the slope b, it is determined whether the number of macro-factor strategy releases changes over time in an increasing or decreasing trend. At the same time, the magnitude of the trend change is determined based on the absolute value of b.

[0117] Then, b is normalized through trigonometric transformation, the value range of b is mapped to the interval (-1, 1), the slope b is converted into the curve mapping angle θ through trigonometric transformation, and then θ is mapped to the interval [0, 90 degrees) through trigonometric transformation, and normalized calculation is performed to obtain p2.

[0118] In some embodiments, the second quantitative index is calculated by the following formula:

[0119]

[0120] Among them, EMC is the second quantitative index, It is a quantitative index of the factors affecting revenue scale, and ECC is a quantitative index of the factors affecting manpower scale.

[0121] Optionally, a quantitative index of the revenue scale impact factor Calculated by the following formula:

[0122]

[0123]

[0124]

[0125] in, is a quantitative index of the revenue scale influencing factor, RA avg for The value before logarithmic transformation, RA q is the quantitative indicator corresponding to the qth revenue scale influencing factor. The quantitative indicators corresponding to the revenue scale influencing factor at least include the registered capital of the enterprise, the operating income of the enterprise and the amount of the enterprise's large order winning bid. g is the number of quantitative indicators, r q1 For RA q The current year specific value, r q0 For RA q The CI is the preset inflation factor.

[0126] Optionally, if RA q If RA is positive, it means that the company's revenue in the current year is improving and the company's capabilities are improving. q If it is negative, it means that the company's revenue in the current year has declined and the company may have certain operational problems.

[0127] In order to comprehensively consider the impact of the quantitative indicators corresponding to the revenue scale influencing factors, the average value RA of the indicator is calculated. avg In order to more intuitively show the changes in revenue and facilitate qualitative and quantitative analysis of related variables, RA is transformed into avg The interval is mapped to the interval [-1, 1], and we get

[0128] The quantitative index ECC of the human scale impact factor is calculated by the following formula:

[0129]

[0130] b e =[180*arctan(b el )] / 90π;

[0131]

[0132] RN = {c t , d t};

[0133]

[0134] Among them, EC is the year-on-year change rate of employees in the enterprise, the enterprise business administration data includes the enterprise human resource scale data, e1 is the number of employees in the enterprise in the current year contained in the enterprise human resource scale data, e0 is the number of employees in the enterprise in the previous year contained in the enterprise human resource scale data, μ is the preset year-on-year change rate deviation threshold, RN is a time series data set constructed based on the number of employees recruited by the enterprise each month, c t is the tth recruitment month of the current year, d t For recruitment month c t The corresponding number of employees recruited by the enterprise, t = 1, 2, 3, ..., T, T is the number of recruitment months in the current year, b el is the slope of the linear fitting curve corresponding to the time series data set RN, b e is the slope b el The corresponding curve mapping angle, d is the total number of recruits in the current year.

[0135] The impact of changes in the number of employees on the relocation of the company's business address is quantified by calculating the year-on-year change rate EC. The larger the EC value, the greater the possibility of the company's business address relocation, and vice versa.

[0136] The least squares regression method is used to perform linear regression fitting on the time series data set RN. According to the slope b of the linear fitting curve el The positive or negative value of b determines whether the number of employees recruited by the enterprise is increasing or decreasing over time. elThe size of the absolute value determines the extent of the change in the number of recruits.

[0137] To optimize EC, b el Mapped to the same coordinate space as EC, considering that there are great differences in the number of employees in different companies, resulting in a large deviation in the degree of influence of the number of recruits on the human resource migration factor of the enterprise, in order to improve the reliability of the correction of the influence of the number of recruits on the human resource scale factor, the ratio of the total number of recruits d in the current year to the number of employees e1 in the current year is introduced as b e The correction factor of .

[0138] In some embodiments, the number of employees in an enterprise reflects the human resource scale of the enterprise. The more employees there are, the greater the cost of relocating the enterprise's business address and the smaller the possibility of relocation. The number of employees recruited by the enterprise reflects the dynamic changes in personnel. For example, if a large number of employees are recruited, the enterprise needs a large number of people to support projects, which means that the enterprise is on an upward trend and there is a great possibility that the office area needs to be expanded, and the enterprise's business address needs to be relocated.

[0139] In some embodiments, the three indicators of enterprise registered capital, enterprise operating income, and enterprise large order winning amount mainly reflect the changes in assets in the actual operation of the enterprise. Among them, the change of enterprise registered capital reflects the change of enterprise scale, the change of enterprise operating income reflects the overall revenue capacity of the enterprise, and the winning amount of enterprise large orders reflects the core revenue capacity of the enterprise. The change of enterprise revenue is quantified by calculating the year-on-year change rate of the three indicators. At the same time, taking into account the inflation factor, the inflation CI (currency inflation) factor is added as a coefficient to correct the enterprise revenue in the current year.

[0140] In some embodiments, reference Figure 5 , Figure 5 It is an optional schematic diagram of the influencing factors of business operations changes in the embodiment of the present application, wherein the influencing factors of business operations changes include revenue scale influencing factors and manpower scale influencing factors. The revenue scale influencing factors are constructed based on three characteristic indicators: the registered capital of the enterprise, the business income of the enterprise, and the amount of the winning bid for large orders of the enterprise. The manpower scale influencing factors are constructed based on the number of employees in the enterprise and the number of employees recruited by the enterprise.

[0141] In some embodiments, the third quantitative index is calculated by the following formula:

[0142] EA=[180*arctan(b wl )] / 90π;

[0143]

[0144]

[0145] Among them, EA is the third quantitative index, s is the total number of employees in the enterprise, and w k is the kth time step, is a sequence data set showing the number of employees in the current office cluster of an enterprise changing with the preset time step, h is the total number of time steps, m is the total number of time steps, k is the number of employees in the current office cluster of the enterprise at the kth time step, b w1 For sequence data sets The slope of the corresponding linear fitting curve.

[0146] Alternatively, assuming that EA is positive, it means that the office concentration level of the enterprise's current office concentration location is on an increasing trend. The larger the EA value, the greater the probability of enterprise business address relocation.

[0147] In some embodiments, reference Figure 6 , Figure 6 This is an optional flowchart of step S104 in the embodiment of the present application. Step S104 may include but is not limited to steps S401 to S403:

[0148] Step S401, using the enterprise migration tendency quantitative assessment model to perform weighted correction calculation according to the first quantitative index, the second quantitative index and the third quantitative index to determine the corresponding quantitative value of the enterprise business address migration;

[0149] Step S402, obtaining the current registered business address of the enterprise;

[0150] Step S403, when the quantified value of the enterprise's business address migration is greater than a given migration quantification threshold, and the enterprise's current registered business address is inconsistent with the enterprise's current office cluster, the enterprise's business address migration prediction result is determined to be migration from the enterprise's current registered business address to the enterprise's current office cluster, and the enterprise's current office cluster is set as the enterprise's current registered business address; otherwise, the enterprise's business address migration prediction result is determined to stop the enterprise's business address migration.

[0151] In some embodiments, the enterprise migration tendency quantitative assessment model is expressed by the following formula:

[0152] ERT=EA*ω3+EMC*ω2+PI*ω1;

[0153] Among them, ERT is the quantitative value of the enterprise business address migration, EA is the third quantitative index, ω3 is the weight corresponding to the third quantitative index, EMC is the second quantitative index, ω2 is the weight corresponding to the second quantitative index, PI is the first quantitative index, and ω1 is the weight corresponding to the first quantitative index.

[0154] In some embodiments, reference Figure 7 , Figure 7It is an optional schematic diagram of the quantitative evaluation model of enterprise relocation tendency in the embodiment of the present application. For the quantitative value ERT (Enterprise Relocation Tendency) of enterprise business address relocation, by analyzing the enterprise business change influencing factors, enterprise communication aggregation tendency influencing factors and enterprise migration macro-influence factors, the enterprise communication aggregation tendency influencing factors reflect the changes in the actual office location of the enterprise from the perspective of enterprise employee aggregation, while the enterprise migration macro-influence factors and enterprise business change influencing factors are mainly quantified from the perspective of enterprise business. In order to further improve the accuracy of the enterprise business address relocation assessment, the third quantitative index EA corresponding to the enterprise communication aggregation tendency influencing factors is mainly used, and the first quantitative index PI corresponding to the enterprise migration macro-influence factors and the second quantitative index EMC corresponding to the enterprise business change influencing factors are used as auxiliary. Combined with the above ω1, ω2 and ω3, weighted sum correction is performed to calculate the quantitative value ERT of enterprise business address relocation. Optionally, ω1≤ω2<ω3 or ω2≤ω1<ω3.

[0155] In some embodiments, reference Figure 8 , Figure 8 This is an optional flowchart of step S403 in the embodiment of the present application. Step S403 may include but is not limited to steps S501 to S506:

[0156] Step S501, obtaining a quantitative value of the enterprise's business address migration;

[0157] Step S502, judging whether the enterprise business address migration quantification value is greater than a given migration quantification threshold, if yes, jump to step S503, otherwise jump to step S505;

[0158] Step S503, obtaining the current registered business address and the current office location of the enterprise;

[0159] Step S504, determine whether the current registered business address of the enterprise is consistent with the current office gathering place of the enterprise, if yes, jump to step S505, otherwise jump to step S506;

[0160] Step S505, stop the enterprise business address migration;

[0161] Step S506, predicting that the business address of the enterprise will be moved from the current registered business address of the enterprise to the current office cluster of the enterprise.

[0162] The method for predicting the migration of an enterprise's business address provided in the embodiment of the present application has at least the following beneficial effects:

[0163] 1) Comprehensive data source: In addition to basic enterprise information (including enterprise business administration data), it also combines enterprise communication big data and enterprise macro-factor migration data. Enterprise communication big data can more comprehensively reflect the changes in the communication location of the enterprise, thereby more accurately and timely mining the inconsistency between the enterprise's business address and the actual office address.

[0164] 2) Higher model accuracy and applicability: The enterprise migration tendency quantitative assessment model uses big data algorithms and customized thresholds based on rich and diverse data dimensions to avoid subjective human judgment of risk situations.

[0165] 3) Advantages of big data analysis: Enterprise communication big data is often massive, and big data analysis technology can be used to mine patterns and associations. By analyzing and modeling enterprise communication big data, the difference between the actual office address of the enterprise and the place where employees gather can be obtained, and the potential migration tendency of the enterprise can be discovered.

[0166] 4) Quasi-real-time: Enterprise communication big data is usually recorded in real time. Compared with non-real-time information such as macro-factor migration data and enterprise business management data, it can instantly reflect the latest communication behavior dynamics of the enterprise and help to understand and track the enterprise's activities in the current area in real time.

[0167] Reference Fig. 9 , Fig. 9 : is an optional structural diagram of a device for predicting the migration of business addresses of enterprises provided in an embodiment of the present application. The device is used to implement the above-mentioned method for predicting the migration of business addresses of enterprises. The device may include:

[0168] The first module is used to obtain a data set of enterprise business address migration characteristics; the data set of enterprise business address migration characteristics at least includes enterprise macro-factor migration data, enterprise business management data and enterprise communication big data;

[0169] The second module is used to construct multiple enterprise business address migration influencing factors and determine the target quantitative data corresponding to each enterprise business address migration influencing factor from the enterprise migration feature data set;

[0170] The third module is used to determine the quantitative index corresponding to each enterprise relocation influencing factor based on the target quantitative data corresponding to each enterprise's business address relocation influencing factor;

[0171] The fourth module is used to obtain a quantitative assessment model for enterprise migration tendency, and use the quantitative assessment model for enterprise migration tendency to generate enterprise business address migration prediction results based on the quantitative index corresponding to each enterprise migration influencing factor.

[0172] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0173] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned enterprise business address migration prediction method when executing the computer program. The electronic device can be any smart terminal including a tablet computer.

[0174] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0175] See also Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0176] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0177] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the enterprise business address migration prediction method of the embodiment of this application;

[0178] Input / output interface 903, used to implement information input and output;

[0179] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0180] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0181] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0182] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned enterprise business address migration prediction method is implemented.

[0183] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0184] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0185] The embodiments of the present application provide a method, device, electronic device and medium for predicting the migration of an enterprise business address, which obtains a characteristic data set of the migration of an enterprise business address, constructs multiple influencing factors of the migration of an enterprise business address, determines the target quantitative data corresponding to each enterprise business address migration influencing factor from the enterprise migration characteristic data set, determines the quantitative index corresponding to each enterprise migration influencing factor according to the target quantitative data corresponding to each enterprise business address migration influencing factor, and generates a prediction result of the migration of an enterprise business address according to the quantitative index corresponding to each enterprise migration influencing factor using the quantitative evaluation model of enterprise migration tendency. The embodiments of the present application can comprehensively integrate enterprise macro-factor migration data, enterprise industrial and commercial management data and enterprise communication big data to obtain a characteristic data set of the migration of an enterprise business address, perform enterprise business address migration prediction based on the characteristic data set of the migration of an enterprise business address, realize enterprise business address migration prediction, and improve the accuracy and efficiency of enterprise business address migration prediction.

[0186] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0187] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0188] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0190] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0191] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0192] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0193] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0194] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0195] It should be appreciated that embodiments of the present invention may be implemented or enforced by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method may be implemented in a computer program using standard programming techniques including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the methods and drawings described in the specific embodiments. Each program may be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if desired, the program may be implemented in an assembly or machine language. In any case, the language may be a compiled or interpreted language. In addition, the program may be run on a programmed ASIC for this purpose.

[0196] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0197] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for predicting the migration of business addresses of enterprises, characterized in that: The method comprises the following steps: Acquire a data set of enterprise business address migration characteristics; the data set of enterprise business address migration characteristics at least includes enterprise macro-factor migration data, enterprise business management data and enterprise communication big data; Constructing a plurality of enterprise business address migration influencing factors, and determining target quantitative data corresponding to each of the enterprise business address migration influencing factors from the enterprise migration feature data set; Determine the quantitative index corresponding to each of the enterprise relocation influencing factors according to the target quantitative data corresponding to each of the enterprise business address relocation influencing factors; A quantitative assessment model for enterprise migration tendency is obtained, and the enterprise migration tendency quantitative assessment model is used to generate a prediction result of enterprise business address migration according to the quantitative index corresponding to each enterprise migration influencing factor.

2. The method according to claim 1, characterized in that The step of constructing a plurality of enterprise business address migration influencing factors and determining target quantitative data corresponding to each of the enterprise business address migration influencing factors from the enterprise migration feature data set specifically includes: Filtering the enterprise macro-factor migration data from the enterprise business address migration feature data set, and constructing the enterprise migration macro-influence factor according to the enterprise macro-factor migration data; Selecting the business administration data of the enterprise from the business address migration feature data set, and constructing the influencing factors of the business operation change of the enterprise according to the business administration data of the enterprise; The enterprise communication big data is selected from the enterprise business address migration feature data set, and an enterprise communication aggregation tendency influencing factor is constructed based on the enterprise communication big data.

3. The method according to claim 2, characterized in that Determining the quantitative index corresponding to each of the enterprise relocation influencing factors according to the target quantitative data corresponding to each of the enterprise business address relocation influencing factors specifically includes: According to the enterprise macro-factor migration data, a first quantitative index is determined, where the first quantitative index is a quantitative index corresponding to the enterprise migration macro-influencing factor, wherein the first quantitative index is calculated by the following formula: PI = (p1 + p2) / 2; p i ={x i ,y i }; p2 = θ / 90; θ = [180*arctan(b)] / π; Among them, PI is the first quantitative index, p1 is the first indicator of macro factors, and p i represents the number of macro strategies released in the i-th month of the current year, p z is the total amount of macro strategy released in the current year, p2 is the second indicator of macro factors, {x i ,y i }composes a time series data set, x i Indicates the current month, y i Indicates the current month x i The number of macro strategies released, n is the sequence length of the time series data set, b is the time series data set {x i ,y i } is the slope of the linear fitting curve corresponding to θ, and θ is the curve mapping angle corresponding to the slope b; According to the business administration data of the enterprise, a second quantitative index is calculated, where the second quantitative index is a quantitative index corresponding to the enterprise operation change influencing factor, wherein the enterprise operation change influencing factor includes a revenue scale influencing factor and a manpower scale influencing factor, and the second quantitative index is calculated by the following formula: Among them, EMC is the second quantitative index, is the quantitative index of the revenue scale influencing factor, and ECC is the quantitative index of the manpower scale influencing factor; According to the enterprise communication big data, the current office gathering place of the enterprise is determined, the office gathering data corresponding to the current office gathering place of the enterprise is obtained, and a third quantitative index is calculated. The third quantitative index is a quantitative index corresponding to the enterprise communication gathering tendency influencing factor, wherein the current office gathering place of the enterprise is the office address where the largest number of office personnel gather within a continuous time preset by the current enterprise, and the third quantitative index is calculated by the following formula: EA=[180*arctan(b wl )] / 90π; Among them, EA is the third quantitative index, s is the total number of employees in the enterprise, and w k is the kth time step, is a sequence data set showing the number of employees in the current office cluster of an enterprise changing with the preset time step, h is the total number of time steps, m is the total number of time steps, k is the number of employees in the current office cluster of the enterprise at the kth time step, b wl For sequence data sets The slope of the corresponding linear fitting curve.

4. The method according to claim 3, characterized in that The step of obtaining a quantitative assessment model for enterprise migration tendency and using the quantitative assessment model for enterprise migration tendency to generate a prediction result of enterprise business address migration according to the quantitative index corresponding to each enterprise migration influencing factor specifically includes: Using the enterprise migration tendency quantitative assessment model to perform weighted correction calculation according to the first quantitative index, the second quantitative index and the third quantitative index, to determine the corresponding quantitative value of the enterprise business address migration; Get the company's current registered business address; When the quantified value of the enterprise's business address migration is greater than a given migration quantification threshold, and the enterprise's current registered business address is inconsistent with the enterprise's current office cluster, the enterprise's business address migration prediction result is determined to be a migration from the enterprise's current registered business address to the enterprise's current office cluster, and the enterprise's current office cluster is set as the enterprise's current registered business address; otherwise, the enterprise's business address migration prediction result is determined to be to stop the enterprise's business address migration.

5. The method according to claim 4, characterized in that The quantitative evaluation model of enterprise migration tendency is expressed by the following formula: ERT=EA*ω3+EMC*ω2+PI*ω1; Among them, ERT is the quantitative value of the enterprise business address migration, EA is the third quantitative index, ω3 is the weight corresponding to the third quantitative index, EMC is the second quantitative index, ω2 is the weight corresponding to the second quantitative index, PI is the first quantitative index, and ω1 is the weight corresponding to the first quantitative index.

6. The method according to claim 3, characterized in that Quantitative index of the revenue scale impact factor Calculated by the following formula: in, is a quantitative index of the revenue scale influencing factor, RA avg for The value before logarithmic transformation, RA q is the quantitative indicator corresponding to the qth revenue scale influencing factor. The quantitative indicators corresponding to the revenue scale influencing factor include at least the registered capital of the enterprise, the operating income of the enterprise and the amount of the enterprise's large order winning bid. g is the number of quantitative indicators, r q1 For RA q The current year specific value, r q0 For RA q The CI is the preset inflation factor.

7. The method according to claim 3, characterized in that The quantitative index ECC of the human scale impact factor is calculated by the following formula: b e =[180*arctan(b el )] / 90π; RN={c t ,d t }; Among them, EC is the year-on-year change rate of employees in the enterprise, the enterprise business administration data includes the enterprise human resource scale data, e1 is the number of employees in the enterprise in the current year contained in the enterprise human resource scale data, e0 is the number of employees in the enterprise in the previous year contained in the enterprise human resource scale data, μ is the preset year-on-year change rate deviation threshold, RN is a time series data set constructed based on the number of employees recruited by the enterprise each month, c t is the tth recruitment month of the current year, d t For recruitment month c t The corresponding number of employees recruited by the enterprise, t = 1, 2, 3, ..., T, T is the number of recruitment months in the current year, b el is the slope of the linear fitting curve corresponding to the time series data set RN, b e is the slope b el The corresponding curve mapping angle, d is the total number of recruits in the current year.

8. A device for predicting the migration of business addresses of enterprises, characterized in that: The device comprises: The first module is used to obtain a data set of enterprise business address migration characteristics; the data set of enterprise business address migration characteristics at least includes enterprise macro-factor migration data, enterprise business management data and enterprise communication big data; The second module is used to construct a plurality of enterprise business address migration influencing factors, and determine the target quantitative data corresponding to each of the enterprise business address migration influencing factors from the enterprise migration feature data set; The third module is used to determine the quantitative index corresponding to each of the enterprise relocation influencing factors according to the target quantitative data corresponding to each of the enterprise business address relocation influencing factors; The fourth module is used to obtain a quantitative assessment model for enterprise migration tendency, and use the quantitative assessment model for enterprise migration tendency to generate a prediction result of enterprise business address migration according to the quantitative index corresponding to each enterprise migration influencing factor.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images