CN110533454B

CN110533454B - Method and system for identifying business object group

Info

Publication number: CN110533454B
Application number: CN201910669718.2A
Authority: CN
Inventors: 宋博文
Original assignee: Advanced New Technologies Co Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2019-07-24
Filing date: 2019-07-24
Publication date: 2023-07-07
Anticipated expiration: 2039-07-24
Also published as: CN110533454A

Abstract

The specification discloses a method and a system for identifying a business object group, wherein a geographic area to be analyzed is divided into M geographic grid fences according to a preset grid, and business associated data of each of the M geographic grid fences is obtained. Determining respective rail heat of the M geogrid rails according to respective business association data of the M geogrid rails, determining a hot spot rail area from the M geogrid rails according to respective rail heat of the M geogrid rails, and obtaining a business object group corresponding to the hot spot rail area for recommendation.

Description

Method and system for identifying business object group

Technical Field

The present application relates to the field of internet technologies, and in particular, to a method and system for identifying a business object group.

Background

With the continuous development of internet technology, people also enjoy various convenience brought by technological development, for example, the development of business from traditional small scale has been changed into the global development of business.

In order to facilitate the development of global business, many business platforms have now invested a great deal of manpower and computer resources to develop research in exploring the relevance of potential customer groups.

The potential customer group is a group which is mainly discovered by a service platform, and a large amount of computer resources can be directionally input to carry out mining culture on the potential high-quality customer group. If the identification of the potential high-quality customer group is inaccurate, the computer resource waste is caused.

Therefore, the problem of computer resource waste caused by inaccurate identification of potential customer groups is currently needed to be solved.

Disclosure of Invention

The specification provides a method and a system for identifying business object groups, which are used for solving or partially solving the technical problem of computer resource waste caused by inaccurate identification of potential customer groups.

To solve the above technical problem, the present specification provides a method for identifying a business object group, the method including:

dividing a geographic area to be analyzed into M geographic grid fences according to a preset grid, wherein M is more than or equal to 1 and is a positive integer;

acquiring service association data of each of the M geogrid fences;

determining the fence heat of each of the M geogrid fences according to the business association data of each of the M geogrid fences; wherein the fence heat is used for representing the business expansion value of business object groups in the corresponding geogrid fence;

Determining a hot spot fence area from the M geogrid fences according to the fence heat of each of the M geogrid fences;

and obtaining a business object group corresponding to the hot spot fence area for recommendation.

The present specification discloses a system for identifying a business object group, comprising:

the dividing module is used for dividing the geographic area to be analyzed into M geographic grid fences according to preset grids, wherein M is more than or equal to 1 and is a positive integer;

a first obtaining module, configured to obtain service association data of each of the M geogrid fences;

a first determining module, configured to determine, according to the service association data of each of the M geogrid fences, a fence heat of each of the M geogrid fences; wherein the fence heat is used for representing the business expansion value of business object groups in the corresponding geogrid fence;

a second determining module, configured to determine a hot spot fence area from the M geogrid fences according to respective fence heats of the M geogrid fences;

and the recommending module is used for acquiring the business object group corresponding to the hot spot fence area to recommend.

The present specification discloses a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.

The present specification discloses a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the program.

Through one or more technical schemes of the specification, the specification has the following beneficial effects or advantages:

the specification discloses a method and a system for identifying a business object group, and because whether the business object group can be accurately positioned and business associated data are closely related, a geographic area to be analyzed is divided into M geographic grid fences according to a preset grid, and the business associated data of each of the M geographic grid fences are obtained. Further, according to the business association data of each of the M geogrid fences, the fence heat of each of the M geogrid fences is determined. The fence heat is obtained through the business association data, so that the fence heat is used for representing business expansion values of business object groups in the corresponding geogrid fences, and the higher the fence heat is, the higher the business expansion values of the business object groups of the corresponding geogrid fences are, and the thicker business returns can be obtained by the input computer resources. Thus, a hotspot fence area is determined from the M geogrid fences based on fence heat; and acquiring a service object group corresponding to the hot spot fence area to conduct service recommendation, and accurately positioning the service object group to conduct recommendation. Because the business object group is positioned accurately, the computer resource can be put into reasonably, the waste of the computer resource is avoided, and the high touch and plump business return is obtained.

The foregoing description is only an overview of the technical solutions of the present specification, and may be implemented according to the content of the specification in order to make the technical means of the present specification more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present specification more clearly understood, the following detailed description of the present specification is given.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the specification. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:

FIG. 1 illustrates a method flow diagram of a method of identifying a business object community in accordance with one embodiment of the present description;

FIG. 2 illustrates a meshing schematic of a geographic area to be analyzed in accordance with one embodiment of the present disclosure;

FIG. 3 illustrates a schematic diagram of a system for identifying a business object community in accordance with one embodiment of the present description;

fig. 4 shows a schematic diagram of a computer device according to one embodiment of the present description.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The embodiment of the specification provides a method for identifying business object groups, which aims to solve or partially solve the problem of computer resource waste caused by inaccurate positioning of potential customer groups in the prior art.

The method is applied to various service platforms and/or various service servers, such as shopping service platforms (e.g. online shopping malls), banking service platforms, information release platforms (e.g. microblog release platforms) and the like. The method is used for realizing accurate business object group positioning by various business platforms and/or various business servers, so that the various business platforms and/or various business servers call Internet computer resources to conduct directional business recommendation, and a rich business return is obtained.

The services referred to in this specification include a wide variety of services such as shopping services, information distribution services, banking services, and the like.

In the prior art, taking a shopping service as an example, the shopping service comprises domestic service and cross-border travel service (foreign service is referred to). The language environment and the data system of domestic business are relatively perfect. After human computer resources are input (such as advertisement resources input of shopping platforms of shopping nodes of double 11 and 618, and resource input in aspects of risk data identification and the like), higher accessibility and service return can be obtained, and a relatively mature operation closed loop is formed. The existing cross-border travel service mainly depends on human expansion operation. Due to the limitations of regions and language environments, human input is difficult, subjective favorites of human are different, and no data system supports spam. The cross-border tour service is difficult to accurately position a high-quality service object, even if the same manpower and computer resources (such as advertisement resources and risk data identification resources) are input into the country, the same level of touch degree and service return as those of the domestic service are difficult to obtain, so that the computer resources are wasted, or the risk data identification is wrong, and a data closed loop, an operation closed loop and the like cannot be formed.

Taking news release service as an example, the news release platform can recommend related news for a service object group, if the service object group is positioned inaccurately, news resources recommended by the news release platform are not matched with the service object group, high click rate is difficult to obtain, and then computer resources of the news release platform are wasted. Similarly, the same problems exist with advertising platforms.

To solve the above-mentioned problems, one or more embodiments of the present disclosure disclose a method for identifying a business object group, where, because whether the business object group can be accurately located and related to business association data (transaction data, login data, etc.), a geographic area to be analyzed is divided into M geogrid fences according to a preset grid, and the business association data of each of the M geogrid fences is obtained. Further, according to the business association data of each of the M geogrid fences, the fence heat of each of the M geogrid fences is determined. The fence heat is obtained through the business association data, so that the fence heat is used for representing business expansion values of business object groups in the corresponding geogrid fences, and the higher the fence heat is, the higher the business expansion values of the business object groups of the corresponding geogrid fences are, and the thicker business returns can be obtained by the input computer resources. Thus, a hotspot fence area is determined from the M geogrid fences based on fence heat; and acquiring a service object group corresponding to the hot spot fence area to conduct service recommendation, and accurately positioning the service object group to conduct recommendation. Because the business object group is positioned accurately, the computer resource can be put into reasonably, the waste of the computer resource is avoided, and the high touch and plump business return is obtained.

Referring to fig. 1, one or more embodiments of the present specification disclose a method comprising the steps of:

and step 11, dividing the geographic area to be analyzed into M geographic grid fences according to a preset grid.

Wherein M is greater than or equal to 1 and is a positive integer, i.e., the number of geogrid pens is variable.

Specifically, the geographic area to be analyzed is determined from the actual geographic location, e.g., divided according to latitude and longitude, geographic area, and the like. For example, a geographic area 1568 square kilometers of thailand mankind is taken as the geographic area to be analyzed with longitude (100 ° 31 'e), latitude (13 ° 45' n).

The preset mesh is a division standard having a size that can be set by the system or customized by the user. For example, a grid of 1.2 km by 0.6 km is used as the preset grid.

And in the dividing process, carrying out grid cutting processing on the geographic area to be analyzed according to the preset grid, so as to obtain more than one geographic grid fence. Each geogrid fence corresponds to a location area range and location information.

Referring to fig. 2, a schematic diagram of meshing of a geographic area to be analyzed is shown, where the geographic area to be analyzed is partitioned into a plurality of meshed areas.

And step 12, obtaining service association data of each of the M geogrid fences.

Wherein the business-related data includes at least transaction data, login data, business type, and the like. The business association data is generated by the business object and is closely related to the business object, so that the business association data can reflect the activity of the business object and the business expansion value of the business object. For example, if the business association data is high, the activity of the corresponding business object is high, and the business object has more development value, if the business object is put into computer resources, the thicker business return can be obtained. The business object refers to login objects in various business platforms and/or various business servers; or refers to objects that generate business transactions in various types of business platforms and/or various types of business servers. The business objects in this specification refer to such objects as natural persons alone, and objects in units of companies and enterprises are also included in the meaning of the business objects in this application.

Transaction data refers to related data generated in a business object transaction, and at least comprises: transaction number (trans_count), transaction amount (trans_count), transaction number of users (user_count), average amount information (avg_count), average rate of purchase of users (avg_user_trans_count), and the like, with corresponding actual data under each index. Taking a shopping platform as an example, code scanning payment in the current shopping platform is common, when the front end of payment initiates a transaction through a code scanning scene, if a user scans the code, the shopping platform can obtain related transaction data, and the acquired user position (such as longitude and latitude information) and the respective position areas of M geogrid fences can be combined to record the corresponding geogrid fences. Thus, each geogrid fence is able to collect respective transaction data.

The login data refers to related data generated when the business object is logged in. At least comprises: the number of logins, the number of login users, the average residence time of the users and the like, and each index has corresponding actual data. Taking the information release platform as an example, after a user logs in the information release platform, the information release platform can obtain the position of the user, and the position areas of the M geogrid fences can be compared and recorded in the corresponding geogrid fences. Thus, each geogrid fence is able to collect its own log-in data.

In particular, the business-related data for each of the M geogrid pens may be collected periodically or in real-time. The interval time of periodic collection can be set at will.

And step 13, determining the rail heat of each of the M geogrid rails according to the business association data of each of the M geogrid rails.

Specifically, rail heat is used to characterize business expansion value for a business object population in a corresponding geogrid rail. The higher the fence heat is, the higher the service expansion value of the service object group in the range is, and the thicker service return can be obtained for the service object group which is put into computer resources. The lower the fence heat is, the lower the service expansion value of the service object group is, the service return obtained after the fence is put into computer resources is far lower than the service with high service expansion value, and the investment is often greater than the output, so that the computer resources are wasted.

Each geogrid fence has respective business-related data, and thus a corresponding fence heat can be determined from its business-related data. It should be appreciated that each geogrid fence can only determine its fence heat from its business-related data, independent of the data of other geogrid fences.

As an optional embodiment, if the fence heat of the geogrid fence is calculated according to the transaction data in the business association data, specifically, the transaction scores of the M geogrid fences are obtained according to the transaction data of the M geogrid fences. The transaction score is used to characterize the fence heat of the geogrid fence. It is noted that the transaction score may be calculated using one or more metrics in the transaction data.

Taking transaction amount, transaction user number and amount information contained in the transaction data as examples, for each of the M geonetwork fences, the following processing is performed:

and obtaining the transaction score of each geogrid fence according to the transaction amount and weight of each geogrid fence, the transaction number and weight of each geogrid fence, the transaction amount information and weight of each geogrid fence and the transaction amount information and weight of each geogrid fence.

In each geogrid fence, the transaction amount has its corresponding weight, the specific assignment of the weight may be the same in all geogrid fences (i.e., the weight value of the transaction amount is the same in all geogrid fences), or may be different (i.e., the transaction amount in each geogrid fence has a different weight value), and the weights of other indicators may be similarly set, which will not be described in detail herein.

In a specific implementation process, the transaction amount score of each geogrid fence is obtained according to the transaction amount and the weight corresponding to each geogrid fence. There are a number of embodiments for obtaining a transaction amount score. For example, directly multiplying the transaction amount by the weight, and obtaining the product, namely the transaction amount score; or processing the transaction amount (for example, square root of the transaction amount, square product of the transaction amount, etc.), and multiplying the processing result by the weight to obtain the product, namely the transaction amount score.

And similarly, obtaining the transaction score of each geogrid fence according to the transaction score and the weight corresponding to each geogrid fence. The specific manner is similar to the embodiment for obtaining the transaction amount score, so that the description is omitted here.

And similarly, obtaining the number of the transaction users of each geogrid fence according to the number of the transaction users and the weight corresponding to each geogrid fence. The specific manner is similar to the embodiment for obtaining the transaction amount score, so that the description is omitted here.

And similarly, obtaining the pen average amount information score of each geogrid fence according to the pen average amount information and the weight corresponding to each geogrid fence. The specific manner is similar to the embodiment for obtaining the transaction amount score, so that the description is omitted here.

Determining the transaction score of each geogrid fence according to the transaction amount score of each geogrid fence, the transaction number score of each geogrid fence, the transaction user number score of each geogrid fence and the pen average amount information score of each geogrid fence. Specifically, in each geogrid fence, the transaction amount score, the transaction number score, the transaction user number score, and the average amount information score are added to obtain a total score, which is the transaction score of each geogrid fence.

If the model is used for explanation, the first preset weighting model is used to process the transaction data in this embodiment. Wherein the first preset weighting model comprises a linear regression model. If the transaction is based on the transaction number The amount, the number of transaction users, and the amount information of the transaction amount are exemplified. In a specific implementation process of obtaining the transaction scores of the M geogrid fences according to the transaction data of the M geogrid fences, the transaction data of the M geogrid fences are input into the first preset weighting model score _final ＝α ₁ ·x _{trans_amount} +α ₂ ·x _{trans_count} +α ₃ ·x _{user_count} +α ₄ ·x _{avg_amount} Obtaining a respective transaction score for each geogrid fence; wherein score _final Transaction score, x for a single geogrid fence _{trans_amount} Transaction amount, alpha, for a single geogrid fence ₁ A weight corresponding to the transaction amount for a single geogrid fence; x is x _{trans_count} Transaction count, α, for a single geogrid fence ₂ A weight corresponding to the transaction number for a single geogrid fence; x is x _{user_count} Number of transaction users, α, for a single geogrid fence ₃ A weight corresponding to the number of transaction users for a single geogrid fence; x is x _{avg_amount} Pen-average amount information, alpha, for a single geogrid fence ₄ Weights corresponding to pen-average amount information for a single geogrid fence. Alpha ₁ 、α ₂ 、α ₃ 、α ₄ Is constant.

Of course, the first pre-determined weighting model is not limited to the above formula, e.g., the transaction data of each of the M geogrid pens is entered into the first pre-determined weighting model

A respective transaction score for each geogrid fence is obtained. Of course, other variations of the first preset weighting model are possible and are not exemplified here.

As an alternative embodiment, in order to obtain more comprehensively and accurately and process the transaction data, the transaction score can also be used for positioning the business object group more accurately. The user-average repurchase rate avg _ user _ trans _ count may be considered. That is, taking the transaction number, the transaction amount, the transaction number of users, the amount information of the transaction amount, the average repurchase rate of the users as an example, the following processing is performed for each of the M geonetwork fences:

and obtaining the transaction score of each geogrid fence according to the transaction amount and weight of each geogrid fence, the transaction number and weight of each geogrid fence, the amount information and weight of each geogrid fence, and the average repurchase rate and weight of the user of each geogrid fence.

And similarly, obtaining the average repurchase rate score of the users of each geogrid fence according to the average repurchase rate and the weight of the users corresponding to each geogrid fence. The specific manner is similar to the embodiment for obtaining the transaction amount score, so that the description is omitted here.

Determining the transaction score of each geogrid fence according to the transaction amount score of each geogrid fence, the transaction number score of each geogrid fence, the transaction user number score of each geogrid fence, the pen average amount information score of each geogrid fence and the average repurchase rate score of the users of each geogrid fence. Specifically, in each geogrid fence, the transaction amount score, the transaction number score, the transaction user number score, the average amount information score, and the average repurchase rate score of the user are added to obtain a total score, and the total score is the transaction score of each geogrid fence.

If the model is used for explanation, the first preset weighting model is used to process the transaction data in this embodiment. Wherein the first preset weighting model comprises a linear regression model. Taking transaction number, transaction amount, transaction number of users, amount information of the same amount, and average repurchase rate of the users as examples. In a specific implementation process of obtaining the transaction scores of the M geogrid fences according to the transaction data of the M geogrid fences, the transaction data of the M geogrid fences are input into a first preset weighting model score _final ＝α ₁ ·x _{trans_amount} +α ₂ ·x _{trans_count} +α ₃ ·x _{user_count} +α ₄ ·x _{avg_amount} +α ₅ ·x _{avg_user_trans_count} Obtaining each of the landsManaging respective transaction scores of the grid pens; wherein score _final Transaction score, x for a single geogrid fence _{trans_amount} Transaction amount, alpha, for a single geogrid fence ₁ A weight corresponding to the transaction amount for a single geogrid fence; x is x _{trans_count} Transaction count, α, for a single geogrid fence ₂ A weight corresponding to the transaction number for a single geogrid fence; x is x _{user_count} Number of transaction users, α, for a single geogrid fence ₃ A weight corresponding to the number of transaction users for a single geogrid fence; x is x _{avg_amount} Pen-average amount information, alpha, for a single geogrid fence ₄ Weights corresponding to the pen-average amount information of the single geogrid fence; x is x _{avg_user_trans_count} Average repurchase rate, alpha, for users of a single geogrid fence ₅ Weights corresponding to the average repurchase rates for users of a single geogrid fence. Alpha ₁ 、α ₂ 、α ₃ 、α ₄ 、α ₅ Is constant.

It will be appreciated that embodiments of the present description may use one or more metrics in the trade data to determine a trade score for a geogrid fence, and are not limited to the trade metrics and model formulas listed above.

In the event that there is transaction generation or the transaction data meets a preset transaction threshold, the transaction data is preferentially used to determine the popularity of the geogrid fence. In the event that no transactions are generated or there is little transaction data (transaction data is below a predetermined transaction threshold, e.g., transaction count is less than a predetermined transaction count, transaction amount is less than a predetermined transaction amount, etc.), log-in data may be used to similarly indicate how hot the geogrid fence is. Although the vast majority of the hot spots (i.e. areas where users log in more) should now be covered by transactions. However, due to the development of global internet technology, the log-in data can still represent the mining value of the region although there is no transaction data or little transaction data. It is also important to protect this application to determine fence heat by logging in data. And if the business association data comprise login data, obtaining login scores of the M geogrid fences according to the login data of the M geogrid fences, wherein the login scores are used for representing fence heat of the geogrid fences. It is noted that the login score may be calculated using one or more indicators in the login data.

Taking the number of logins and the number of users logged in as an example, which are included in the login data (of course, taking any two indexes of the login data as well as calculating according to the following manner, which is not repeated here), the following processing is performed for each of the M geographic network fences:

determining the login score of each geogrid fence according to the login times and the weights of each geogrid fence, the login user number and the weights of each geogrid fence, and the average residence time and the weights of the users of each geogrid fence.

In each geogrid fence, the number of logins has a corresponding weight, the specific assignment of the weight may be the same in all geogrid fences (i.e., the weight value of the number of logins is the same in all geogrid fences), or may be different (i.e., the number of logins in each geogrid fence has a different weight value), and the weights of other indicators may be similarly set, which will not be described herein.

In a specific implementation process, a login frequency score of each geogrid fence is obtained according to the login frequency and the weight of each geogrid fence. There are a number of embodiments for obtaining a log-in number score. For example, the login times and the weight are directly multiplied, and the obtained product is the login times score; or processing the login times (for example, square root of the login times, square product of the login times, etc.), and multiplying the processing result by the weight to obtain the product, namely the login times score.

And similarly, obtaining the number of the login user of each geogrid fence according to the number of the login user and the weight corresponding to each geogrid fence. The specific manner is similar to the embodiment for obtaining the login frequency score, so that the description is omitted here.

Similarly, a user stay average time score for each geogrid fence is obtained based on the user stay average time and the weight of each geogrid fence. The specific manner is similar to the embodiment for obtaining the login frequency score, so that the description is omitted here.

Determining a login score for each geogrid fence based on the login number score for each geogrid fence, the number of login users per geogrid fence, and the average time-to-stay score for the users per geogrid fence. Specifically, in each geogrid fence, the login frequency score, the login user number score and the average user residence time score are added to obtain a total score, and the total score is the login score of each geogrid fence.

If a model is used for illustration, the embodiment uses a second preset weighting model to process the login data. Wherein the second preset weighting model comprises a linear regression model. Taking the number of logins, the number of users logged in, and the average residence time of the users as an example, in the implementation process of obtaining the login scores of the M geogrid fences according to the login data of the M geogrid fences, the login data of the M geogrid fences is input into a second preset weighting model score _login ＝β ₁ ·x _{login_amount} +β ₂ ·x _{login_user_count} +β ₃ ·x _{avg_login_user_staytime} Obtaining a login score for each of the M geogrid fences; wherein score _login For a single geogrid fenceRegistration score, x _{login_amount} Number of logins for a single geogrid fence, beta ₁ The weight corresponding to the login times of the single geogrid fence; x is x _{login_user_count} User number, beta, for a single geogrid fence ₂ A weight corresponding to the number of registered users of a single geogrid fence; x is x _{avg_login_user_staytime} User stay average time for a single geogrid fence, beta ₃ The weight corresponding to the average time of stay for the users of a single geogrid fence. Wherein beta is ₁ 、β ₂ 、β ₃ Is constant.

Of course, the second preset weighting model is not limited to the above formula, e.g., the login data of each of the M geogrid pens is input into the second preset weighting model

A login score for each of the M geogrid fences is obtained. Of course, other variations of the second preset weighting model are possible and are not exemplified here.

Further, since some or all of the hot spots (i.e., areas with relatively high log-in data) are currently covered by transactions. Therefore, after the log-in data is processed by using the second preset weighting model to obtain the respective rail heat of the M geogrid rails, in order to avoid the problem that the recommended business object group is inaccurate due to repeated calculation, the marked hot-spot rail region may be deleted from the M geogrid rails, and then a subsequent operation (such as determining the corresponding hot-spot rail region by using the remaining geogrid rails after deleting the marked hot-spot rail region) may be performed, so as to improve the accuracy of calculation.

One or more of the above embodiments can determine the corresponding fence heat according to the business association data of the geogrid fence, and the specific selection mode is dependent on the actual situation. Of course, other methods of determining fence heat are within the scope of this disclosure.

Step 14, determining a hot spot fence area from the M geogrid fences according to the fence heat of each of the M geogrid fences.

The hot spot fence area is used for representing M geogrid fences, and the corresponding fence heat is higher than a preset heat threshold. Since the fence heats of the M geogrid fences vary, incorporating the fence heats of all geogrid fences into the recommended range is complicated. In addition, if the fence heat of most of the M geogrid fences is high, but the very individual fence heat is very low, taking into account the fence heat where all of the geogrid fences would be pulled low, a mislocalization of the business object population would result. In addition, the geogrid fence with extremely low fence heat has extremely low service expansion value of the corresponding service object group, and the computer resources are input into the geogrid fence to be extremely likely to be wasted, so that the hot spot fence area with the fence heat higher than the preset heat threshold value can be determined from M geogrid fences and used as the representative of M geogrid fences, the occurrence of the situation can be avoided, and the computer resources are further saved. Since the hot spot fence area is representative of M geogrid fences, the fence heat of the hot spot fence area can represent the fence heat of all geogrid fences.

In a specific implementation, there are many embodiments for determining a hotspot fence area from the M geogrid fences. For purposes of illustration and explanation of this specification, two general approaches to determining the hot spot fence area are listed in the following embodiments, and any other approach to determining the hot spot fence area is intended to be included within the scope of this specification.

As an alternative embodiment, among the M geogrid pens, the geogrid pen with the highest pen heat is determined as the hot spot pen area. Specifically, determining a geogrid fence with highest fence heat from M geogrid fences, judging whether the fence heat of the geogrid fence is higher than a preset heat threshold, and if so, taking the geogrid fence as a hot spot fence area. If not, the business object group in the geographic area to be analyzed is not a potential customer, and the operation is ended. Currently, if not, the next geographical area to be analyzed can be acquired to execute the identification method of the business object group of the specification again. For example, a geogrid fence having a geographic area of 1.2 x 0.6, where the fence has the highest heat, is used directly as a hot spot fence area.

As one embodiment, N geogrid fences are determined from the M geogrid fences to be fused into a hotspot fence area. Wherein the distance between any two of the N geogrid pens is less than a predetermined distance. In a specific implementation process, first, the rail heat of each of the M geogrid rails is ranked according to the rail heat level, so as to obtain a ranking result. In the ranking result, the higher the fence heat of the geogrid fence, the earlier the ranking; the lower the fence heat of the geogrid fence, the later the ranking. Secondly, judging whether the distance between the first N geogrid fences in the sequencing result is smaller than a preset distance; n is more than or equal to 2 and less than or equal to M, wherein N is a positive integer. If yes, fusing the N geogrid fences by using a grid fusion technology to obtain the hot spot fence area. For example, the first 10 geogrid pens in the ranking result are retrieved, and a determination is made as to whether the distance between the 10 geogrid pens is less than a predetermined distance. If it is, the distance between the 10 geogrid fences is smaller than the preset distance, then the 10 geogrid fences are fused into a hot spot fence area. If not, the business object group in the geographic area to be analyzed is not a potential customer, and the operation is ended. Currently, if not, the next geographical area to be analyzed can be acquired to execute the identification method of the business object group of the specification again. For another example, geogrid pens with 5% top ranking of rail hotspots and two-to-two relative distances less than a preset distance are fused into a hotspot rail area.

In the process of fusing the N geogrid fences by utilizing a grid fusion technology, the adjacent boundaries of the grid fences are ignored, the non-adjacent boundaries are reserved for fusion, and the area range of the fused hot spot fence area is the sum of the area ranges of the N grid fences.

Wherein, the hot spot fence area corresponds to a fence heat, and the fence heat of the hot spot fence area is obtained through the following steps:

acquiring service association data in a hotspot fence area;

and obtaining the fence heat of the hot spot fence area according to the business association data in the hot spot fence area.

Since the business-related data in the hotspot fence area contains transaction data and login data. Therefore, in the implementation process of obtaining the fence heat of the hot spot fence area according to the business association data in the hot spot fence area, the transaction data in the hot spot fence area is input into a first preset weighting model, and the transaction score of the hot spot fence area is obtained. The transaction score for a hotspot fence area is used to characterize the fence heat of the hotspot fence area. Specifically, since transaction data in the hot spot fence area is input at this time, the meaning of each symbol in the first preset weighting model is corresponding to the relevant parameter of the "hot spot fence area" from the relevant parameter of the "single geogrid fence". For example score _final Transaction score, x, corresponding to hotspot fence area _{trans_amount} The meaning of other symbols will also change accordingly, corresponding to transaction amounts for hot spot fenced areas, etc., and will not be described in detail herein.

In an optional implementation manner, in the implementation process of obtaining the fence heat of the hot spot fence area according to the business association data in the hot spot fence area, the login data in the hot spot fence area is input into a second preset weighting model, and the login score of the hot spot fence area is obtained. The login score for a hotspot fence area is used to characterize the fence heat of the hotspot fence area. Specifically, since transaction data in the hot spot fence area is input at this time, the meaning of each symbol in the first preset weighting model is corresponding to the relevant parameter of the "hot spot fence area" from the relevant parameter of the "single geogrid fence". For example score _login Registration score, x, corresponding to hotspot fence area _{login_amount} The meaning of other symbols will be changed accordingly, corresponding to the number of logins of the hotspot fence area, etc., and will not be described again here.

And 15, obtaining a business object group corresponding to the hot spot fence area for recommendation.

Specifically, in the recommending process, the service object group corresponding to the hot spot fence area can be recommended and displayed, or recommended to a related system of service expansion to perform the next operation such as targeted analysis or resource input. The recommended manner includes, but is not limited to, list, document, file, and the like.

As an alternative embodiment, the fence heat of the hot spot fence area is the heat of the business object group in the whole hot spot fence area, but not all the business object transaction data in the hot spot fence area meet the requirements (for example, the transaction amount and the transaction amount exceed the relevant set threshold values), and the business object group meeting the requirements only needs to be put into computer resources according to the corresponding business association data. In the hot spot fence area, there may be a low transaction amount and a low transaction amount group of the to-be-inspected service objects, where the transaction data does not exceed the relevant set threshold, and the group of the to-be-inspected service objects in the embodiment refers to a group where the transaction data does not exceed the relevant set threshold. The problem of the to-be-inspected business object group is not solved, and the business return rate of the current computer resource after input is not influenced, so that the reasons that the transaction data of the to-be-inspected business object group in the hot spot fence area does not exceed the relevant set threshold value are required to be inspected, the computer resource can be input in a targeted mode after the reasons are acquired, and the business return rate is improved.

Specifically, service association data information of each service object in the service object group corresponding to the hot spot fence area is obtained, and a service object group to be inspected is determined from the service object group corresponding to the hot spot fence area based on the service association data of each service object. Specifically, transaction data is obtained according to the service association data, whether the transaction data exceeds a relevant set threshold value is judged, if the transaction data does not exceed the relevant set threshold value, the corresponding service object is determined to be the service object to be checked, and then the service object group to be checked is obtained.

And obtaining the investigation result of the business object group to be investigated. Further, according to the registration information of the service object group to be inspected and the service association data in the hot spot fence area, an inspection result of the service object group to be inspected is obtained. Specifically, the registration information of the business object group includes: registered personal related data and registered feed data. Personal related data including name, age, type of business engaged, etc. The feed data includes feed name, feed type, feed number, etc. related data. And comparing and analyzing the related information and the business related data to obtain the reason that the transaction data of the business object group to be checked does not exceed the related set threshold value, namely the checking result. The investigation result includes, but is not limited to: the engaged business type of the business object group to be checked does not accord with the business type of the hot spot fence area; inaccurate feed information, and so on. The investigation result can accurately represent the reason that the transaction data of the business object group to be investigated does not exceed the relevant set threshold, so that the investigation result and the business object group to be investigated are recommended, the resource directional investment can be carried out in a targeted manner according to the investigation result and the business object group to be investigated, and the business return rate is further improved.

As an optional embodiment, for a new business object group in the hotspot fence area, that is, a business object group added after the hotspot fence area is determined, registration information of the new business object group is obtained, according to the registration information of the new business object group and business related data of the hotspot fence area, an investigation result of the new business object group is obtained, and the investigation result of the new business object group is recommended, so that the system adjusts investment of computer resources accordingly to ensure abundant business returns.

Furthermore, on the basis of more accurate positioning of the business object groups, in the further process, the number of the business object groups which are analyzed by mistake and need to be selected again for analysis is smaller, so that the computer resources can be saved more. And on the basis of more accurate positioning of business object groups, the method can obtain plentiful business return by inputting less computer resources, and can also improve the business return rate on the basis of saving the computer resources.

Based on the same inventive concepts as in the previous embodiments, the present embodiments also provide a system for identifying a business object group, referring to fig. 3, including:

The dividing module 31 is configured to divide the geographic area to be analyzed into M geographic grid fences according to a preset grid, where M is greater than or equal to 1 and is a positive integer;

a first obtaining module 32, configured to obtain service association data of each of the M geogrid pens;

a first determining module 33, configured to determine, according to the service association data of each of the M geogrid fences, a fence heat of each of the M geogrid fences; wherein the fence heat is used for representing the business expansion value of business object groups in the corresponding geogrid fence;

a second determining module 34, configured to determine a hot spot fence area from the M geogrid fences according to respective fence heats of the M geogrid fences;

and the recommending module 35 is configured to obtain a business object group corresponding to the hotspot fence area for recommendation.

As an alternative embodiment, the business-related data includes transaction data;

the first determining module 32 is specifically configured to obtain, according to the transaction data of each of the M geogrid fences, a transaction score of each of the M geogrid fences, where the transaction score is used to characterize a fence heat of the geogrid fence.

As an alternative embodiment, the transaction data includes: one or more of transaction number, transaction amount, transaction number of users, amount information, average rate of repurchase of users.

Taking the transaction number, the transaction amount, the number of transaction users, and the amount information of each geofence included in the transaction data as an example, the first determining module 32 is specifically configured to obtain, for each geofence of the M geofences, a transaction score of each geofence according to the transaction amount and the weight of each geofence, the transaction number and the weight of each geofence, the number of transaction users and the weight of each geofence, and the amount information and the weight of each geofence.

If the model is used for explanation, the first preset weighting model is used to process the transaction data in this embodiment. Wherein the first preset weighting model comprises a linear regression model. Taking transaction amount, transaction number of users and amount information as examples. The first determining module 32 is specifically configured to input the transaction data of each of the M geogrid fences into the first preset weighting model score _final ＝α ₁ ·x _{trans_amount} +α ₂ ·x _{trans_count} +α ₃ ·x _{user_count} +α ₄ ·x _{avg_amount} Obtaining a respective transaction score for each geogrid fence; wherein score _final Transaction score, x for a single geogrid fence _{trans_amount} Transaction amount, alpha, for a single geogrid fence ₁ A weight corresponding to the transaction amount for a single geogrid fence; x is x _{trans_count} Transaction count, α, for a single geogrid fence ₂ A weight corresponding to the transaction number for a single geogrid fence; x is x _{user_count} Number of transaction users, α, for a single geogrid fence ₃ A weight corresponding to the number of transaction users for a single geogrid fence; x is x _{avg_amount} Pen-average amount information, alpha, for a single geogrid fence ₄ Weights corresponding to pen-average amount information for a single geogrid fence.

Of course, the first preset weighting model is not limited to the above formula, and, for example, the first determining module 32 is specifically configured to input the transaction data of each of the M geogrid pens into the first preset weighting model

In order to obtain and process the transaction data more comprehensively and accurately, the transaction score can be used for positioning the business object group more accurately. The user-average repurchase rate avg _ user _ trans _ count may be considered. That is, taking transaction number, transaction amount, transaction number of users, amount information of the same amount, and average repurchase rate of the users as examples:

the first determining module 32 is specifically configured to obtain, for each of M geonetwork fences, a transaction score of each geogrid fence according to a transaction amount and a weight of each geogrid fence, a transaction number and a weight of each geogrid fence, a transaction user number and a weight of each geogrid fence, an amount information and a weight of each geogrid fence, and an average repurchase rate and a weight of a user of each geogrid fence.

In a specific implementation, the first determining module 32 is specifically configured to:

and obtaining the transaction amount score of each geogrid fence according to the transaction amount and the weight corresponding to each geogrid fence. There are a number of embodiments for obtaining a transaction amount score. For example, directly multiplying the transaction amount by the weight, and obtaining the product, namely the transaction amount score; or processing the transaction amount (for example, square root of the transaction amount, square product of the transaction amount, etc.), and multiplying the processing result by the weight to obtain the product, namely the transaction amount score.

If the model is used for explanation, the first preset weighting model is used to process the transaction data in this embodiment. Wherein the first preset weighting model comprises a linear regression model. Taking transaction number, transaction amount, transaction number of users, amount information of the same amount, and average repurchase rate of the users as examples. The first determining module 32 is specifically configured to input the transaction data of each of the M geogrid fences into the first preset weighting model score _final ＝α ₁ ·x _{trans_amount} +α ₂ ·x _{trans_count} +α ₃ ·x _{user_count} +α ₄ ·x _{avg_amount} +α ₅ ·x _{avg_user_trans_count} Obtaining a respective transaction score for each geogrid fence;

wherein score _final Transaction score, x for a single geogrid fence _{trans_amount} Transaction amount, alpha, for a single geogrid fence ₁ A weight corresponding to the transaction amount for a single geogrid fence; x is x _{trans_count} Transaction count, α, for a single geogrid fence ₂ A weight corresponding to the transaction number for a single geogrid fence; x is x _{user_count} Number of transaction users, α, for a single geogrid fence ₃ A weight corresponding to the number of transaction users for a single geogrid fence; x is x _{avg_amount} Pen-average amount information, alpha, for a single geogrid fence ₄ Weights corresponding to the pen-average amount information of the single geogrid fence; x is x _{avg_user_trans_count} Average repurchase rate, alpha, for users of a single geogrid fence ₅ Weights corresponding to the average repurchase rates for users of a single geogrid fence.

As an alternative embodiment, the service association data includes login data;

in the event that there is transaction generation or the transaction data meets a preset transaction threshold, the transaction data is preferentially used to determine the popularity of the geogrid fence. In the event that no transactions are generated or there is little transaction data (transaction data is below a predetermined transaction threshold, e.g., transaction count is less than a predetermined transaction count, transaction amount is less than a predetermined transaction amount, etc.), log-in data may be used to similarly indicate how hot the geogrid fence is. Although the vast majority of the hot spots (i.e. areas where users log in more) should now be covered by transactions. However, due to the development of global internet technology, the log-in data can still represent the mining value of the region although there is no transaction data or little transaction data. It is also important to protect this application to determine fence heat by logging in data. If the business-related data includes login data, the first determining module 32 is specifically configured to obtain login scores of the M geogrid fences according to the login data of the M geogrid fences, where the login scores are used to characterize fence heat of the geogrid fences.

As an alternative embodiment, the login data includes: number of logins, number of logged-in users, average user residence time. It is noted that the login score may be calculated using one or more indicators in the login data.

the first determining module 32 is specifically configured to determine, for each of the M geonetwork fences, a login score of each geogrid fence according to the login times and weights of each geogrid fence, the login user number and weights of each geogrid fence, and the average residence time and weights of the users of each geogrid fence.

In a specific implementation process, the first determining module 32 is specifically configured to obtain the login frequency score of each geogrid fence according to the login frequency and the weight of each geogrid fence. There are a number of embodiments for obtaining a log-in number score. For example, the login times and the weight are directly multiplied, and the obtained product is the login times score; or processing the login times (for example, square root of the login times, square product of the login times, etc.), and multiplying the processing result by the weight to obtain the product, namely the login times score.

If a model is used for illustration, the embodiment uses a second preset weighting model to process the login data. Wherein the second preset weighting model comprises a linear regression model. Taking the number of logins, the number of login users, and the average residence time of the users as an example, the first determining module 32 is specifically configured to input the login data of each of the M geogrid pens into a second preset weighting model score _login ＝β ₁ ·x _{login_amount} +β ₂ ·x _{login_user_count} +β ₃ ·x _{avg_login_user_staytime} Obtaining a login score for each of the M geogrid fences;

wherein score _login Login score, x for a single geogrid fence _{login_amount} Number of logins for a single geogrid fence, beta ₁ The weight corresponding to the login times of the single geogrid fence; x is x _{login_user_count} User number, beta, for a single geogrid fence ₂ A weight corresponding to the number of registered users of a single geogrid fence; x is x _{avg_login_user_staytime} User stay average time for a single geogrid fence, beta ₃ The weight corresponding to the average time of stay for the users of a single geogrid fence.

Of course, the second preset weighting model is not limited to the above formula, for example, the first determining module 32 is specifically configured to input the login data of each of the M geogrid pens into the second preset weighting model

As an alternative embodiment, the second determining module 33 includes:

the sequencing module is used for sequencing the rail heat of each of the M geogrid rails according to the rail heat level to obtain a sequencing result;

the judging module is used for judging whether the distance between N geogrid fences in the sequencing result is smaller than a preset distance; n is more than or equal to 2 and less than or equal to M, wherein N is a positive integer;

and the grid fusion module is used for fusing the N geogrid fences by utilizing a grid fusion technology if yes, so as to obtain the hot spot fence area.

As an alternative embodiment, the system further comprises:

the second obtaining module is used for obtaining the business association data in the hot spot fence area;

and the third obtaining module is used for obtaining the fence heat of the hot spot fence area according to the business association data in the hot spot fence area.

As an alternative embodiment, the system further comprises:

a fourth obtaining module, configured to obtain service association data of each service object in the service object group corresponding to the hotspot fence area;

the third determining module is used for determining a service object group to be inspected from the service object groups corresponding to the hot spot fence areas based on the service association data of each service object;

and the checking module is used for obtaining checking results of the business object group to be checked according to the registration information of the business object group to be checked and the business related data of the hot spot fence area.

Based on the same inventive concept as in the previous embodiments, the present description further provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements the steps of any of the methods described above.

Based on the same inventive concept as in the previous embodiments, the embodiments of the present disclosure further provide a computer device, as shown in fig. 4, including a memory 404, a processor 402, and a computer program stored on the memory 404 and executable on the processor 402, where the processor 402 implements the steps of any of the methods described above when executing the program.

Where in FIG. 4 a bus architecture (represented by bus 400), bus 400 may comprise any number of interconnected buses and bridges, with bus 400 linking together various circuits, including one or more processors, represented by processor 402, and memory, represented by memory 404. Bus 400 may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., as are well known in the art and, therefore, will not be described further herein. Bus interface 405 provides an interface between bus 400 and receiver 401 and transmitter 404. The receiver 401 and the transmitter 404 may be the same element, i.e. a transceiver, providing a unit for communicating with various other terminal devices over a transmission medium. The processor 402 is responsible for managing the bus 400 and general processing, while the memory 404 may be used to store data used by the processor 402 in performing operations.

Through one or more embodiments of the present specification, the present specification has the following benefits or advantages:

The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, this description is not directed to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present specification, and the above description of specific languages is provided for disclosure of preferred embodiments of the present specification.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present description may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the present specification, various features of the specification are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed specification requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this specification.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the present description and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

Various component embodiments of the present specification may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in a gateway, proxy server, system according to embodiments of the present description may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present description may also be embodied as an apparatus or device program (e.g., computer program and computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present specification may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The specification may be implemented by means of hardware comprising M distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

Claims

1. A method of identifying a population of business objects, the method comprising:

acquiring service association data of each of the M geogrid fences;

determining a hot spot fence area from the M geogrid fences based on the fence heat of each of the M geogrid fences, comprising: sorting the rail heat of each of the M geogrid rails according to the rail heat, so as to obtain a sorting result; judging whether the distance between the first N geogrid fences in the sequencing result is smaller than a preset distance; n is more than or equal to 2 and less than or equal to M, wherein N is a positive integer; if yes, fusing the N geogrid fences by using a grid fusion technology to obtain the hot spot fence area; the fence heat of the hotspot fence area may represent fence heat of all geogrid fences;

2. The method of claim 1, the business-related data comprising transaction data;

the determining the rail heat of each of the M geogrid rails according to the service association data of each of the M geogrid rails comprises:

and obtaining transaction scores of the M geogrid fences according to the transaction data of the M geogrid fences, wherein the transaction scores are used for representing the fence heat of the geogrid fences.

3. The method of claim 2, the transaction data comprising: one or more of transaction number, transaction amount, transaction number of users, amount information, average rate of repurchase of users.

4. The method of claim 1, the business-related data comprising login data;

and obtaining login scores of the M geogrid fences according to the login data of the M geogrid fences, wherein the login scores are used for representing the fence heat of the geogrid fences.

5. The method of claim 4, the login data comprising: number of logins, number of logged-in users, average user residence time.

6. The method of claim 1, said determining a hot spot fence area from said M geogrid fences based on respective fence heats of said M geogrid fences, said method further comprising:

acquiring service association data in the hotspot fence area;

7. The method of claim 1, wherein after the recommending the business object group corresponding to the hotspot fence area is obtained, the method further comprises:

acquiring service association data of each service object in the service object group corresponding to the hotspot fence area;

based on the business association data of each business object, determining a business object group to be examined from business object groups corresponding to the hot spot fence areas;

and obtaining the checking result of the business object group to be checked according to the registration information of the business object group to be checked and the business related data of the hot spot fence area.

8. A system for identifying a population of business objects, comprising:

a second determining module, configured to determine a hot spot fence area from the M geogrid fences according to respective fence heats of the M geogrid fences; the second determining module includes: the sequencing module is used for sequencing the rail heat of each of the M geogrid rails according to the rail heat level to obtain a sequencing result; the judging module is used for judging whether the distance between N geogrid fences in the sequencing result is smaller than a preset distance; n is more than or equal to 2 and less than or equal to M, wherein N is a positive integer; the grid fusion module is used for fusing the N geogrid fences by utilizing a grid fusion technology if yes, so as to obtain the hot spot fence area; the fence heat of the hotspot fence area may represent fence heat of all geogrid fences;

9. The system of claim 8, the business-related data comprising transaction data;

the first determining module is specifically configured to obtain, according to the transaction data of each of the M geogrid fences, a transaction score of each of the M geogrid fences, where the transaction score is used to characterize fence heat of the geogrid fence.

10. The system of claim 9, the transaction data comprising: one or more of transaction number, transaction amount, transaction number of users, amount information, average rate of repurchase of users.

11. The system of claim 8, the business-related data comprising login data;

the first determining module is specifically configured to obtain, according to the login data of each of the M geogrid fences, a login score of each of the M geogrid fences, where the login score is used to characterize fence heat of the geogrid fence.

12. The system of claim 11, the login data comprising: number of logins, number of logged-in users, average user residence time.

13. The system of claim 8, the system further comprising:

14. The system of claim 8, the system further comprising:

15. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1-7.

16. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1-7 when the program is executed by the processor.