CN110533454A

CN110533454A - A kind of method and system identifying business object group

Info

Publication number: CN110533454A
Application number: CN201910669718.2A
Authority: CN
Inventors: 宋博文
Original assignee: Alibaba Group Holding 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: 2019-12-03
Anticipated expiration: 2039-07-24
Also published as: CN110533454B

Abstract

Subject description discloses a kind of method and system for identifying business object group, are analysed to geographic area according to specific trellis and are divided into M geographic grid fence, and obtain the respective business association data of the M geographic grid fence.According to the respective business association data of the M geographic grid fence, determine the respective fence temperature of the M geographic grid fence, further according to the respective fence temperature of the M geographic grid fence, hot spot fence area is determined from the M geographic grid fence, is obtained the corresponding business object group in the hot spot fence area and is recommended.

Description

A kind of method and system identifying business object group

Technical field

This application involves Internet technical field more particularly to a kind of method and system for identifying business object group.

Background technique

With the continuous development of Internet technology, people have also enjoyed the various conveniences of development in science and technology bring, for example, from Traditional a small range, which is commenced business, to be had turned to the whole world and commences business.

And for the ease of carrying out world business, present many business platforms have put into a large amount of manpowers and computer resource and have sent out The related fields of pick potential customers group expand research.

Potential customers group is the group that business platform emphasis is excavated, and can orient a large amount of computer resources of investment to potential excellent Matter customer group carries out excavation culture.If potential top-tier customer Stock discrimination inaccuracy, will result in computer resource waste.

Therefore, it need to be to solve asking due to the inaccurate caused computer resource waste of identification of potential customers group at present Topic.

Summary of the invention

Present description provides a kind of method and system for identifying business object group, are solved with solution or part potential Caused by customer group's identification is inaccurate the technical issues of computer resource waste.

In order to solve the above technical problems, present description provides a kind of method for identifying business object group, the method Include:

Geographic area, which is analysed to, according to specific trellis is divided into M geographic grid fence, M >=1 and be positive integer；

Obtain the respective business association data of the M geographic grid fence；

According to the respective business association data of the M geographic grid fence, the M geographic grid fence is determined respectively Fence temperature；Wherein, the business that the fence temperature is used to characterize the business object group in corresponding geographic grid fence is opened up Exhibition value；

According to the respective fence temperature of the M geographic grid fence, hot spot is determined from the M geographic grid fence Fence area；

The corresponding business object group in the hot spot fence area is obtained to be recommended.

Subject description discloses a kind of systems for identifying business object group, comprising:

Division module is divided into M geographic grid fence for being analysed to geographic area according to specific trellis, M >=1 and For positive integer；

First obtains module, for obtaining the respective business association data of the M geographic grid fence；

First determining module, for determining the M according to the respective business association data of the M geographic grid fence A respective fence temperature of geographic grid fence；Wherein, the fence temperature is used to characterize the industry in corresponding geographic grid fence The business development value of business subject population；

Second determining module is used for according to the respective fence temperature of the M geographic grid fence, geographical from described M Hot spot fence area is determined in grid fence；

Recommending module is recommended for obtaining the corresponding business object group in the hot spot fence area.

Subject description discloses a kind of computer readable storage mediums, are stored thereon with computer program, which is located Manage the step of realizing the above method when device executes.

Subject description discloses a kind of computer equipment, including memory, processor and storage are on a memory and can be The step of computer program run on processor, the processor realizes the above method when executing described program.

By one or more technical solution of this specification, this specification has the advantages that or advantage:

Subject description discloses a kind of method and system for identifying business object group, since business object group can negate Level is really and business association data are closely bound up, therefore, is first analysed to geographic area according to specific trellis and is divided into M geography Grid fence, and obtain the respective business association data of the M geographic grid fence.Further, geographical according to described M The respective business association data of grid fence determine the respective fence temperature of the M geographic grid fence.Due to fence temperature It is to be obtained by business association data, therefore fence temperature, for characterizing the business object group in corresponding geographic grid fence The business development of body is worth, and fence temperature is higher, indicates that it corresponds to the business development of the business object group of geographic grid fence Value is higher, and the computer resource of investment can more obtain abundant business return.Therefore, based on fence temperature from the M Hot spot fence area is determined in geographic grid fence；It obtains the corresponding business object group in the hot spot fence area and carries out business Recommend, can accurately be recommended positioning service subject population.It, can be reasonable due to the accurate positioning of business object group Computer resource is put into, the waste of computer resource is avoided, and obtains high touching and is returned up to degree and abundant business.

Above description is only the general introduction of this specification technical solution, in order to better understand the technology hand of this specification Section, and can be implemented in accordance with the contents of the specification, and in order to allow above and other objects, features and advantages of this specification It can be more clearly understood, below the special specific embodiment for lifting this specification.

Detailed description of the invention

By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to this explanation The limitation of book.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:

The method that Fig. 1 shows the method for the identification business object group according to this specification one embodiment shows process Figure；

Fig. 2 shows the grid dividing schematic diagrames according to the geographic area to be analyzed of this specification one embodiment；

Fig. 3 shows the schematic diagram of the system of the identification business object group according to this specification one embodiment；

Fig. 4 shows a kind of schematic diagram of computer equipment according to this specification one embodiment.

Specific embodiment

Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure It is fully disclosed to those skilled in the art.

This specification embodiment provides a kind of method for identifying business object group, is solved with solution or part existing In technology the problem of caused computer resource waste inaccurate due to the positioning of potential customers group.

The method of this specification is applied in all kinds of business platforms and/or all kinds of service servers, such as shopping service is flat Platform (such as shopping online store), banking platform, information publishing platform (such as microblogging distribution platform) etc..So that all kinds of Business platform and/or all kinds of service servers use this method to realize accurately business object group positioning, so as to each business It is business recommended that platform and/or all kinds of service servers call internet computer resource to be oriented, and obtains abundant business Return.

There are many kinds of the business packet of this specification meaning contains, such as shopping service, information issuing service, bank transaction business Etc..

It in the prior art, include that domestic service and cross-border trip business (refer to foreign countries by taking shopping service as an example, in shopping service Business).The language environment and data system comparatively perfect of domestic service.After investment in terms of manpower computer resource (such as it is double 11, the shopping sections such as 618 shopping platform advertising resource investment, risk data identification etc. resource input), can obtain compared with Height touching forms the operation closed loop of relative maturity up to degree and business return.Current cross-border trip business depends on manpower Expand operation.Since region and language environment limit, human input is difficult, and the subjective hobby of manpower is different, in addition not having Data system support is revealed all the details.Cross-border trip business is difficult the high-quality business object of precise positioning, even if investment and domestic identical manpower With computer resource (such as advertising resource and risk data identify resource), it is also difficult to obtain the touching with domestic service phase same level Up to degree and business return, cause computer resource waste or risk data identification it is wrong, can not more be formed data closed loop, Run closed loop etc..

By taking news briefing business as an example, news briefing platform can be orientated business object group and recommend association news, if industry Groups of objects of being engaged in positioning is inaccurate, then News Resources and business object group that news briefing platform is recommended mismatch, is just difficult to High clicking rate is obtained, and then wastes the computer resource of news briefing platform.Similarly, there is also equally ask for ad distribution platform Topic.

To solve the above-mentioned problems, one or more embodiment of this specification discloses a kind of identification business object group The method of body, since can business object group accurate positioning and business association data (transaction data, logon data etc.) breath Manner of breathing closes, and therefore, first being analysed to geographic area according to specific trellis is divided into M geographic grid fence, and obtains the M The respective business association data of geographic grid fence.Further, according to the respective business association of M geographic grid fence Data determine the respective fence temperature of the M geographic grid fence.Since fence temperature is obtained by business association data , therefore fence temperature, the business development for characterizing the business object group in corresponding geographic grid fence are worth, fence heat Degree is higher, indicates that it corresponds to the business development of the business object group of geographic grid fence and is worth higher, the computer money of investment Source can more obtain abundant business return.Therefore, determine that hot spot is enclosed from the M geographic grid fence based on fence temperature Column region；It is business recommended to obtain the corresponding business object group progress in the hot spot fence area, it being capable of accurate positioning service Subject population is recommended.Due to the accurate positioning of business object group, can Reasonable input computer resource, avoid calculating The waste of machine resource, and obtain high touching and returned up to degree and abundant business.

Referring to Fig. 1, method disclosed in one or more embodiment of this specification includes the following steps:

Step 11, geographic area is analysed to according to specific trellis be divided into M geographic grid fence.

Wherein, M >=1 and be positive integer, that is, the quantity of geographic grid fence is indefinite.

Specifically, geographic area to be analyzed is determined according to actual geographic position, such as according to longitude and latitude, geographic areas etc. Etc. being divided.For example, by longitude (100 ° of 31 ' E), latitude (13 ° of 45 ' N), the Thailand that 1568 square kilometres of geographic areas Bangkok is as geographic area to be analyzed.

Specific trellis is a kind of criteria for classifying, which has a size, size can be arranged by system or It is customized by the user setting.For example, using 1.2 kilometers * 0.6 kilometer of grid as specific trellis.

And during division, treating analysis geographic area according to specific trellis carries out cutting grid processing, and then obtains More than one geographic grid fence.Each geographic grid fence is corresponding with band of position range and location information.

The grid dividing schematic diagram of geographic area to be analyzed referring to Fig. 2, be analysed to geographic area be divided into it is multiple Latticed region.

Step 12, the respective business association data of the M geographic grid fence are obtained.

Wherein, business association data include at least transaction data, logon data, type of service etc..Business association data Data are that business object generates and business object is closely bound up, therefore its liveness for being able to reflect business object and business The business development of object is worth.For example, business association data are high, then the liveness of its corresponding business object is high, business pair As namely more there is Development volue, if putting into computer resource to it, abundant business return can be more obtained.And business Object refers to the login object in all kinds of business platforms and/or all kinds of service servers；Or it refers in all kinds of business The object of business contact is generated in platform and/or all kinds of service servers.The business object of this specification simultaneously only refers to natural person This class object, the object as unit of company and enterprise are also contained among the meaning of the business object of the application.

Transaction data refers to the related data generated in business object transaction, includes at least: transaction stroke count (trans_ Count), transaction amount (trans_amount), trade user number (user_count), the equal amount information (avg_ of pen Amount), the one or more kinds of indicator combinations of average multiple purchase rate (avg_user_trans_count) of user etc., each finger Mark is lower to have corresponding real data.By taking shopping platform as an example, the barcode scanning payment at present in shopping platform is relatively conventional, works as payment Transaction is initiated by barcode scanning scene in front end, if user's barcode scanning, shopping platform can obtain associated transaction data, in conjunction with the use of acquisition Family position (such as latitude and longitude information) and M geographic grid fence respective positions region, can be recorded corresponding geography network In lattice fence.Each geographic grid fence can collect respective transaction data as a result,.

Logon data refers to the related data generated when business object logs in.It includes at least: login times, login user number, User stops average time etc. one or more kinds of indicator combinations, has corresponding real data under each index.With information For distribution platform, after user login information distribution platform, information publishing platform can be obtained user location, compare M geography Grid fence respective positions region, can be recorded in corresponding geographic grid fence.Each geographic grid fence can as a result, Collect respective logon data.

Specifically, the respective business association data of the M geographic grid fence can be acquired periodically or in real time.Periodically adopt The interval time of collection can be arbitrarily arranged.

Step 13, according to the respective business association data of the M geographic grid fence, the M geographic grid is determined The respective fence temperature of fence.

Specifically, fence temperature, for characterizing the business development of the business object group in corresponding geographic grid fence Value.Fence temperature is higher, indicates that the business development value of the business object group within the scope of its is higher, puts into computer to it Resource, which is got over, can obtain abundant business return.Fence temperature is lower, indicates that the business development value of its business object group is got over It is low, the business return obtained after computer resource is put into it far below the costly business of business development, often investment is big In output, computer resource is caused to waste.

Each geographic grid fence has respective business association data, thus can be determining pair according to its business association data The fence temperature answered.It need to know, each geographic grid fence can only determine the fence heat of itself according to the business association data of itself It spends unrelated with the data of other geographic grid fences.

As a kind of optional embodiment, if calculating enclosing for geographic grid fence with the transaction data in business association data Column temperature, specifically, it is each to obtain the M geographic grid fence according to the respective transaction data of M geographic grid fence From transaction score.Transaction score is used to characterize the fence temperature of geographic grid fence.It need to know, number of deals can be used in transaction score One or more index in is calculated.

By taking transaction stroke count that transaction data includes, transaction amount, trade user number, the equal amount information of pen as an example, for M Each geographical network fence in geographical network fence, is all handled as follows:

According to the transaction amount and weight of each geographic grid fence, the transaction pen of each geographic grid fence Several and weight, the trade user number and weight of each geographic grid fence and the pen of each geographic grid fence are equal Amount information and weight obtain the transaction score of each geographic grid fence.

In each geographic grid fence, transaction amount has its corresponding weight, and the specific assignment of the weight is all Geographic grid fence can identical (that is, in all geographic grid fences, the weighted value of transaction amount is all), can also not With (that is, transaction amount in each geographic grid fence, having respectively different weighted values), the weights of other indexs can be with Similar setting, details are not described herein.

In the specific implementation process, it according to the corresponding transaction amount of each geographic grid fence and weight, obtains The transaction amount score of each geographic grid fence.There are many kinds of the embodiments for obtaining transaction amount score.For example, straight Connecing the product by transaction amount and multiplied by weight, obtained is transaction amount score；Or handled transaction amount (such as Quadratic power product etc. is sought to transaction amount sqrt, or to transaction amount), processing result and multiplied by weight obtain Product be transaction amount score.

Similarly, according to the corresponding transaction stroke count of each geographic grid fence and weight, each geography network is obtained The transaction stroke count score of lattice fence.Specific mode is similar with the embodiment of above-mentioned acquisition transaction amount score, so herein It repeats no more.

Similarly, according to the corresponding trade user number of each geographic grid fence and weight, each geography is obtained The trade user number score of grid fence.Specific mode is similar with the embodiment of above-mentioned acquisition transaction amount score, so Details are not described herein again.

Similarly, according to the equal amount information of the corresponding pen of each geographic grid fence and weight, obtain it is described eachly Manage the equal amount information score of pen of grid fence.Specific mode is similar with the embodiment of above-mentioned acquisition transaction amount score, So details are not described herein again.

According to the transaction amount score of each geographic grid fence, the transaction stroke count of each geographic grid fence The equal amount of money letter of the pen of score, the trade user number score of each geographic grid fence and each geographic grid fence Score is ceased, determines the transaction score of each geographic grid fence.Specifically, it in each geographic grid fence, will hand over Easy amount of money score, stroke count score of trading, trade user number score, He Bijun amount information score are added, and obtain total score, this is total Score is the transaction score of each geographic grid fence.

If being illustrated using model, the present embodiment uses the first default weighted model and handles transaction data. Wherein, the first default weighted model includes linear regression model (LRM).If golden with stroke count of trading, transaction amount, trade user number, pen For volume information.According to the respective transaction data of M geographic grid fence, it is each to obtain the M geographic grid fence From transaction score specific implementation process in, by the M geographic grid fence respective transaction data input described first Default weighted model score_final=α₁·x_{trans_amount}+α₂·x_{trans_count}+α₃·x_{user_count}+α₄·x_{avg_amount}, obtain Obtain each respective transaction score of geographic grid fence；Wherein, score_finalFor trading for single geographic grid fence Point, x_{trans_amount}For the transaction amount of single geographic grid fence, α₁Transaction amount for single geographic grid fence is corresponding Weight；x_{trans_count}For the transaction stroke count of single geographic grid fence, α₂It is corresponding for the transaction stroke count of single geographic grid fence Weight；x_{user_count}For the trade user number of single geographic grid fence, α₃For the trade user number of single geographic grid fence Corresponding weight；x_{avg_amount}For the equal amount information of pen of single geographic grid fence, α₄Pen for single geographic grid fence is equal The corresponding weight of amount information.α₁、α₂、α₃、α₄For constant.

Certainly, the first default weighted model is not limited in above-mentioned formula, for example, the M geographic grid fence is each From transaction data input the first default weighted modelObtain each geography network The respective transaction score of lattice fence.Certainly, the first default weighted model can also have other modifications, herein no longer excessive citing.

As a kind of optional embodiment, transaction data is handled in order to more fully accurately obtain, and then is made Transaction score also can more accurately position business object group.The multiple purchase rate avg_user_ that user can be averaged Trans_count considers wherein.That is, average with stroke count of trading, transaction amount, trade user number, the equal amount information of pen, user Multiple purchase rate for, for each geographical network fence in M geographical network fence, be all handled as follows:

According to the transaction amount and weight of each geographic grid fence, the transaction pen of each geographic grid fence Several and weight, the pen of the trade user number and weight of each geographic grid fence, each geographic grid fence are golden The user of volume information and weight and each geographic grid fence average multiple purchase rate and weight obtain each geography The transaction score of grid fence.

Similarly, the multiple purchase rate and weight average according to the corresponding user of each geographic grid fence obtain described every The average multiple purchase rate score of the user of a geographic grid fence.The embodiment party of specific mode and above-mentioned acquisition transaction amount score Formula is similar, so details are not described herein again.

According to the transaction amount score of each geographic grid fence, the transaction stroke count of each geographic grid fence Score, the trade user number score of each geographic grid fence, the equal amount information of pen of each geographic grid fence The average multiple purchase rate score of the user of score and each geographic grid fence, determines each geographic grid fence Transaction score.Specifically, in each geographic grid fence, by transaction amount score, stroke count score of trading, trade user number Score, the equal amount information score of the pen multiple purchase rate score average with user are added, and obtain total score, and the total score is as each The transaction score of geographic grid fence.

If being illustrated using model, the present embodiment uses the first default weighted model and handles transaction data. Wherein, the first default weighted model includes linear regression model (LRM).If golden with stroke count of trading, transaction amount, trade user number, pen For the average multiple purchase rate of volume information, user.According to the respective transaction data of M geographic grid fence, the M is obtained In the specific implementation process of a respective transaction score of geographic grid fence, by the respective transaction of M geographic grid fence Data input the first default weighted model score_final=α₁·x_{trans_amount}+α₂·x_{trans_count}+α₃·x_{user_count}+α₄· x_{avg_amount}+α₅·x_{avg_user_trans_count}, obtain each respective transaction score of geographic grid fence；Wherein, score_finalFor the transaction score of single geographic grid fence, x_{trans_amount}For the transaction amount of single geographic grid fence, α₁ For the corresponding weight of transaction amount of single geographic grid fence；x_{trans_count}For the transaction stroke count of single geographic grid fence, α₂For the corresponding weight of transaction stroke count of single geographic grid fence；x_{user_count}For the trade user of single geographic grid fence Number, α₃For the corresponding weight of trade user number of single geographic grid fence；x_{avg_amount}Pen for single geographic grid fence is equal Amount information, α₄For the corresponding weight of the equal amount information of pen of single geographic grid fence；x_{avg_user_trans_count}For individually Manage the average multiple purchase rate of the user of grid fence, α₅For the average corresponding power of multiple purchase rate of the user of single geographic grid fence Weight.α₁、α₂、α₃、α₄、α₅For constant.

Certainly, the first default weighted model is not limited in above-mentioned formula, for example, the M geographic grid fence is each From transaction data input the first default weighted modelObtain institute State the respective transaction score of each geographic grid fence.Certainly, the first default weighted model can also have other modifications, herein not After more citings.

It can be seen that one or more index in transaction data, which can be used, in the embodiment of this specification determines ground Manage the transaction score of grid fence, it is not limited to the above-mentioned transaction index enumerated and model formation.

In the case where there is transaction to generate or transaction data meets default transaction threshold, transaction data is preferentially used Determine the temperature of geographic grid fence.And for no transaction generate or transaction data it is few in the case where (at transaction data Under default transaction threshold, such as transaction stroke count is less than default transaction stroke count, and transaction amount is less than default transaction amount etc.), Similar operation can be carried out using logon data, the temperature of geographic grid fence is characterized with login score.Although heat at present (i.e. user the logs in more area) overwhelming majority in point area should be covered by transaction.But since all parts of the world is mutual The development of networking technology, although few without transaction data or transaction data, logon data can still embody this area Tap value.So determining that fence temperature is also the emphasis of the application protection by logon data.If business association data It is each to be obtained according to the respective logon data of M geographic grid fence for the M geographic grid fence including logon data From login score, the score that logs in is used to characterize the fence temperature of geographic grid fence.It need to know, login score, which can be used, steps on The one or more index in data is recorded to be calculated.

The login times for including with logon data, login user number, user (certainly, take wherein for stopping average time Any two indexs can also calculate in the following manner, and details are not described herein), in M geographical network fence eachly Network fence is managed, is all handled as follows:

According to the login times and weight of each geographic grid fence, the login of each geographic grid fence is used The user of amount and weight and each geographic grid fence stops average time and weight, determines each geography network The login score of lattice fence.

In each geographic grid fence, login times have its corresponding weight, and the specific assignment of the weight is all Geographic grid fence can identical (that is, in all geographic grid fences, the weighted value of login times is all), can also not With (that is, login times in each geographic grid fence, having respectively different weighted values), the weights of other indexs can be with Similar setting, details are not described herein.

In the specific implementation process, according to the login times and weight of each geographic grid fence, described in acquisition The login times score of each geographic grid fence.There are many kinds of the embodiments for obtaining login times score.For example, directly will Login times and multiplied by weight, obtained product are login times score；Or handled login times (such as to stepping on Number sqrt is recorded, or quadratic power product etc. is asked to login times), by processing result and multiplied by weight, acquisition multiplies Product is login times score.

Similarly, according to the corresponding login user number of each geographic grid fence and weight, each geography is obtained The login user number score of grid fence.Specific mode is similar with the embodiment of above-mentioned acquisition login times score, so Details are not described herein again.

Similarly, average time and weight are stopped according to the user of each geographic grid fence, obtains each geography network The user of lattice fence stops average time score.Specific mode is similar with the embodiment of above-mentioned acquisition login times score, So details are not described herein again.

According to the login times score of each geographic grid fence, the login user number score of each geographic grid fence, Average time score is stopped with the user of each geographic grid fence, determines the login score of each geographic grid fence.Specifically , in each geographic grid fence, by login times score, login user number score and user stop average time score It is added, obtains total score, which is the login score of each geographic grid fence.

If being illustrated with model, the present embodiment uses the second default weighted model and handles logon data.Its In, the second default weighted model includes linear regression model (LRM).If login user number, user stops average time with login times For, the M geographic grid fence is respective to be stepped on obtaining according to the respective logon data of M geographic grid fence In the specific implementation process for recording score, by the default weighting mould of the respective logon data input second of the M geographic grid fence Type score_login=β₁·x_{login_amount}+β₂·x_{login_user_count}+β₃·x_{avg_login_user_staytime}, obtain the M ground Manage the respective login score of grid fence；Wherein, score_loginFor the login score of single geographic grid fence, x_{login_amount} For the login times of single geographic grid fence, β₁For the corresponding weight of login times of single geographic grid fence； x_{login_user_count}For the login user number of single geographic grid fence, β₂For the login user number pair of single geographic grid fence The weight answered；x_{avg_login_user_staytime}Average time, β are stopped for the user of single geographic grid fence₃For single geography network The user of lattice fence stops average time corresponding weight.Wherein, β₁、β₂、β₃For constant.

Certainly, the second default weighted model is not limited in above-mentioned formula, for example, the M geographic grid fence is each From logon data input the second default weighted modelThe M geographic grid is obtained to enclose The respective login score in column.Certainly, the second default weighted model can also have other modifications, herein no longer excessive citing.

Further, due in current hot zones (i.e. the more area of logon data) it is some or all of by Transaction covering.Therefore, logon data is being handled using the second default weighted model to obtain M geographic grid fence respectively Fence temperature after, can be geographical from M in order to avoid computing repeatedly the problem for leading to the business object group inaccuracy recommended Marked hot spot fence area is deleted in grid fence, then is carried out subsequent operation and (utilized the marked hot spot fence area of deletion Remaining geographic grid fence determines that corresponding hot spot fence area etc. operates afterwards), to improve the accuracy calculated.

Above-mentioned one or more embodiment can be determined and be corresponded to according to the business association data of geographic grid fence Fence temperature, be specifically chosen which kind of mode depending on reality.Certainly, other methods for determining fence temperature should also be as belonging to Within the protection scope of this specification.

Step 14, according to the respective fence temperature of the M geographic grid fence, from the M geographic grid fence Determine hot spot fence area.

Wherein, hot spot fence area, for representing M geographic grid fence, corresponding fence temperature is higher than default heat Spend threshold value.Since the fence temperature of M geographic grid fence is had nothing in common with each other, the fence temperature of all geographic grid fences is included in Recommended range complexity is higher.In addition, if in M geographic grid fence the fence temperature of most of geographic grid fence all compared with Height, but extremely a other fence temperature is extremely low, is considered the fence temperature that can wherein drag down all geographic grid fences, can made At the positioning mistake of business object group.In addition, the geographic grid fence of extremely low fence temperature, corresponding business object group Business development value it is also very low, computer resource is put into it may greatly slattern, therefore, can be from M geography network According to hot spot fence area of the fence temperature higher than preset heat threshold value is determined in lattice fence, as M geographic grid The representative of fence can be avoided above situation appearance, and then save computer resource.Since hot spot fence area is as M ground The representative of grid fence is managed, then the fence temperature of hot spot fence area can represent the fence heat of all geographic grid fences Degree.

In the specific implementation process, determine that there are many kinds of real for hot spot fence area from the M geographic grid fence Apply mode.In order to illustrate with explain this specification, enumerate common two kinds in following embodiment, any other determining heat The mode of point fence area should be all included within the protection scope of this specification.

As an alternative embodiment, the highest geographic grid of fence temperature is enclosed in M geographic grid fence Column is determined as hot spot fence area.Specifically, the highest geographic grid of fence temperature is determined from M geographic grid fence Fence, judges whether the fence temperature of the geographic grid fence is higher than preset heat threshold value, if so, as hot spot fence Region.If not, then it represents that the business object group in geographic area to be analyzed is not potential customers, then end operation.Currently, If it is not, the recognition methods that next geographic area to be analyzed executes the business object group of this specification again can be acquired.It lifts For example, by the geographic grid fence of such a geographic range of the highest 1.2*0.6 of fence temperature directly as hot spot fence Region.

As one of embodiment, N number of geographic grid fence fusion is determined from the M geographic grid fence For hot spot fence area.Wherein, the distance of any two geographic grid fence is less than pre-determined distance in N number of geographic grid fence. In the specific implementation process, firstly, according to fence temperature height to the respective fence temperature of the M geographic grid fence into Row sequence, obtains ranking results.In the ranking results, the fence temperature of geographic grid fence is higher, sorts more forward；It is geographical The fence temperature of grid fence is lower, and sequence is more rearward.Secondly, judging the top n geographic grid fence in the ranking results Whether mutual distance is less than pre-determined distance；2≤N≤M, N are positive integer.If so, using Mesh Fusion technology to the N A geographic grid fence is merged, and the hot spot fence area is obtained.For example, by preceding 10 geographic grids in ranking results Fence takes out, and judges whether the mutual distance of this 10 geographic grid fences is less than pre-determined distance.If so, indicating this 10 The mutual distance of geographic grid fence is both less than pre-determined distance, then this 10 geographic grid fences is fused to hot spot fence Region.If not, then it represents that the business object group in geographic area to be analyzed is not potential customers, then end operation.Currently, If it is not, the recognition methods that next geographic area to be analyzed executes the business object group of this specification again can be acquired.Again For example, by before fence hot spot ranking 5% and two-by-two relative distance be less than pre-determined distance geographic grid fence be fused to hot spot Fence area.

During being merged using Mesh Fusion technology to N number of geographic grid fence, multiple grids are enclosed The adjacent boundary in column neglects, and retains non-conterminous boundary and is merged, and the regional scope of fused hot spot fence area is just It is the sum of the regional scope of N number of grid fence.

Wherein, hot spot fence area is corresponding with fence temperature, and the fence temperature of hot spot fence area is obtained by following step :

Obtain the business association data in hot spot fence area；

According to the business association data in the hot spot fence area, the fence temperature of the hot spot fence area is obtained.

Since the business association data in hot spot fence area include transaction data and logon data.Therefore, according to institute The business association data in hot spot fence area are stated, it, will in the implementation process for obtaining the fence temperature of the hot spot fence area It is inputted in the first default weighted model in transaction data in hot spot fence area, obtains the transaction score of hot spot fence area. The transaction score of hot spot fence area is used to characterize the fence temperature of hot spot fence area.Specifically, due at this time inputting It is the transaction data in hot spot fence area, therefore the meaning of each symbol in the first default weighted model can be by " individually The corresponding relevant parameter for becoming " hot spot fence area " of the relevant parameter of reason grid fence ".Such as score_finalIt is corresponding to become heat The transaction score of point fence area, x_{trans_amount}The corresponding transaction amount etc. for becoming hot spot fence area, other symbols Meaning also can accordingly change, and details are not described herein again.

As an alternative embodiment, obtaining institute according to the business association data in the hot spot fence area It states in the implementation process of fence temperature of hot spot fence area, the logon data input second in hot spot fence area is preset and is added It weighs in model, obtains the login score of hot spot fence area.The login score of hot spot fence area is for characterizing hot spot fence area The fence temperature in domain.Specifically, default first since what is inputted at this time is transaction data in hot spot fence area The meaning of each symbol in weighted model can become " hot spot fence area by the relevant parameter of " single geographic grid fence " correspondence The relevant parameter in domain ".Such as score_loginThe corresponding login score for becoming hot spot fence area, x_{login_amount}It is corresponding to become heat The login times, etc. of point fence area, the meaning of other symbols also can accordingly change, and details are not described herein again.

Step 15, the corresponding business object group in the hot spot fence area is obtained to be recommended.

Specifically, during recommendation, display can be recommended by the corresponding business object group in hot spot fence area, The related system for either recommending business development carries out in next step the targetedly operation such as analysis or resource input.The side of recommendation Formula includes but is not limited to be in a manner of list, document, file etc..

As a kind of optional embodiment, the fence temperature of hot spot fence area is represented in entire hot spot fence area The temperature of business object group, but the transaction data of not all business object inside hot spot fence area all meets and wants (such as trading volume, turnover have been above related setting threshold value) is asked, the business object group met the requirements is corresponding according to its Business association data put into computer resource.And transaction data is also likely to be present in hot spot fence area and is less than correlation The business object group to be checked of the low trading volume of given threshold, low turnover, the business object group to be checked of the present embodiment Refer to that transaction data is less than the group of related setting threshold value.The problem of this kind of business object group to be checked does not solve can shadow Business return rate after ringing the investment of current computer resource, it is therefore desirable to check this kind of wait check inside hot spot fence area The reason of business object group is less than related setting threshold value there are transaction data can targetedly put into after knowing reason Computer resource improves business return rate.

Specifically, the business for obtaining each business object in the corresponding business object group in the hot spot fence area is closed Join data information, and the business association data based on each business object, from the corresponding business in the hot spot fence area Business object group to be checked is determined in subject population.Specifically, according to business association data acquisition transaction data, and according to Judge whether transaction data is more than related setting threshold value, if transaction data is less than related setting threshold value, by corresponding business Object is determined as business object to be checked, and then obtains business object group to be checked.

Obtain the investigation result of the business object group to be checked.Further, according to business object group to be checked Register information and hot spot fence area in business association data, obtain the investigation result of business object group to be checked.Tool For body, the register information of business object group include: registration personal related data and registration into number of packages evidence.It is personal related Data, including name, age, type etc. of doing business.Into number of packages according to include into part title, into part type, into number of packages etc. Related data.It is compared and analyzed by these relevant informations and business association data, you can learn that business object group to be checked The reason of being less than related setting threshold value there are transaction data of body, namely investigation result.The investigation result includes but is not limited to Be: the type of service of business object group to be checked being engaged in does not agree with the type of service of hot spot fence area；Not into part information It is accurate etc..The investigation result can accurately indicate that the transaction data of business object group to be checked is less than related setting threshold value The reason of, therefore, investigation result and business object group to be checked are recommended, it is fixed can targetedly to carry out resource accordingly To investment, and then improve business return rate.

As a kind of optional embodiment, for the new business subject population namely hot spot fence in hot spot fence area The business object group that region is added after determining obtains the register information of new business subject population, according to the new business object The register information of group and the service related data of hot spot fence area obtain the investigation of new business subject population as a result, and pushing away The investigation of new business subject population is recommended as a result, so that system adjusts the investment of computer resource accordingly, to guarantee business abundant Return.

Further, on the basis of the positioning of business object group is more accurate, during further, mistake is analyzed Business object colonial need to pick out the quantity analyzed again again less, can more save computer resource.And And on the basis of the positioning of business object group is more accurate, the computer resource that less input can obtain abundant industry Business return, can also improve business return rate on the basis of saving computer resource.

Based on inventive concept same in previous embodiment, this specification embodiment also provides a kind of identification business object The system of group, referring to Fig. 3, comprising:

Division module 31 is divided into M geographic grid fence, M >=1 for being analysed to geographic area according to specific trellis It and is positive integer；

First obtains module 32, for obtaining the respective business association data of the M geographic grid fence；

First determining module 33, described in determining according to the respective business association data of the M geographic grid fence The respective fence temperature of M geographic grid fence；Wherein, the fence temperature is used to characterize the industry in corresponding geographic grid fence The business development value of business subject population；

Second determining module 34 is used for according to the respective fence temperature of the M geographic grid fence, from the M ground It manages and determines hot spot fence area in grid fence；

Recommending module 35 is recommended for obtaining the corresponding business object group in the hot spot fence area.

As an alternative embodiment, the business association data include transaction data；

First determining module 32 is specifically used for obtaining institute according to the respective transaction data of M geographic grid fence The respective transaction score of M geographic grid fence is stated, the transaction score is used to characterize the fence temperature of geographic grid fence.

As an alternative embodiment, the transaction data includes: transaction stroke count, transaction amount, trade user number, The combination of one or more of the pen average multiple purchase rate of amount information, user.

By taking transaction stroke count that transaction data includes, transaction amount, trade user number, the equal amount information of pen as an example, described One determining module 32 is specifically used for for each geographical network fence in M geographical network fence, according to each geography network The transaction amount and weight of lattice fence, the transaction stroke count and weight of each geographic grid fence, each geographic grid The equal amount information of pen and weight of the trade user number and weight of fence and each geographic grid fence obtain described every The transaction score of a geographic grid fence.

If being illustrated using model, the present embodiment uses the first default weighted model and handles transaction data. Wherein, the first default weighted model includes linear regression model (LRM).If golden with stroke count of trading, transaction amount, trade user number, pen For volume information.First determining module 32 is specifically used for inputting the respective transaction data of the M geographic grid fence The first default weighted model score_final=α₁·x_{trans_amount}+α₂·x_{trans_count}+α₃·x_{user_count}+α₄· x_{avg_amount}, obtain each respective transaction score of geographic grid fence；Wherein, score_finalIt is enclosed for single geographic grid The transaction score on column, x_{trans_amount}For the transaction amount of single geographic grid fence, α₁For the transaction of single geographic grid fence The corresponding weight of the amount of money；x_{trans_count}For the transaction stroke count of single geographic grid fence, α₂For the friendship of single geographic grid fence The corresponding weight of easy stroke count；x_{user_count}For the trade user number of single geographic grid fence, α₃For single geographic grid fence The corresponding weight of trade user number；x_{avg_amount}For the equal amount information of pen of single geographic grid fence, α₄For single geographic grid The corresponding weight of the equal amount information of the pen of fence.

Certainly, the first default weighted model is not limited in above-mentioned formula, for example, first determining module 32, specifically For the respective transaction data of the M geographic grid fence to be inputted the first default weighted modelObtain each geography network The respective transaction score of lattice fence.Certainly, the first default weighted model can also have other modifications, herein no longer excessive citing.

Transaction data is handled in order to more fully accurately obtain, and then makes transaction score also can be more accurate Business object group is positioned.The multiple purchase rate avg_user_trans_count that user can be averaged considers wherein. That is, by taking the average multiple purchase rate of stroke count of trading, transaction amount, trade user number, the equal amount information of pen, user as an example:

First determining module 32 is specifically used for being directed to each geographical network fence in M geographical network fence, according to The transaction amount and weight of each geographic grid fence, the transaction stroke count and weight of each geographic grid fence, institute State the trade user number and weight of each geographic grid fence, the equal amount information of pen and power of each geographic grid fence The user of weight and each geographic grid fence average multiple purchase rate and weight, obtain each geographic grid fence Transaction score.

In the specific implementation process, first determining module 32, is specifically used for:

According to the corresponding transaction amount of each geographic grid fence and weight, each geographic grid fence is obtained Transaction amount score.There are many kinds of the embodiments for obtaining transaction amount score.For example, directly by transaction amount and weight phase Multiply, obtained product is transaction amount score；Or handled transaction amount (such as to transaction amount sqrt, Or quadratic power product etc. is asked to transaction amount), by processing result and multiplied by weight, the product of acquisition is that transaction amount obtains Point.

If being illustrated using model, the present embodiment uses the first default weighted model and handles transaction data. Wherein, the first default weighted model includes linear regression model (LRM).If golden with stroke count of trading, transaction amount, trade user number, pen For the average multiple purchase rate of volume information, user.First determining module 32 is specifically used for the M geographic grid fence Respective transaction data inputs the first default weighted model score_final=α₁·x_{trans_amount}+α₂·x_{trans_count}+ α₃·x_{user_count}+α₄·x_{avg_amount}+α₅·x_{avg_user_trans_count}, obtain each respective friendship of geographic grid fence Easy score；

Wherein, score_finalFor the transaction score of single geographic grid fence, x_{trans_amount}For single geographic grid fence Transaction amount, α₁For the corresponding weight of transaction amount of single geographic grid fence；x_{trans_count}It is enclosed for single geographic grid The transaction stroke count on column, α₂For the corresponding weight of transaction stroke count of single geographic grid fence；x_{user_count}It is enclosed for single geographic grid The trade user number on column, α₃For the corresponding weight of trade user number of single geographic grid fence；x_{avg_amount}For single geography network The equal amount information of the pen of lattice fence, α₄For the corresponding weight of the equal amount information of pen of single geographic grid fence； x_{avg_user_trans_count}For the average multiple purchase rate of the user of single geographic grid fence, α₅For the user of single geographic grid fence The average corresponding weight of multiple purchase rate.

Certainly, the first default weighted model is not limited in above-mentioned formula, for example, first determining module 32, specifically For the respective transaction data of the M geographic grid fence to be inputted the first default weighted modelObtain institute State the respective transaction score of each geographic grid fence.Certainly, the first default weighted model can also have other modifications, herein not After more citings.

As an alternative embodiment, the business association data include logon data；

In the case where there is transaction to generate or transaction data meets default transaction threshold, transaction data is preferentially used Determine the temperature of geographic grid fence.And for no transaction generate or transaction data it is few in the case where (at transaction data Under default transaction threshold, such as transaction stroke count is less than default transaction stroke count, and transaction amount is less than default transaction amount etc.), Similar operation can be carried out using logon data, the temperature of geographic grid fence is characterized with login score.Although heat at present (i.e. user the logs in more area) overwhelming majority in point area should be covered by transaction.But since all parts of the world is mutual The development of networking technology, although few without transaction data or transaction data, logon data can still embody this area Tap value.So determining that fence temperature is also the emphasis of the application protection by logon data.If business association data Including logon data, first determining module 32 is specifically used for according to the respective login number of the M geographic grid fence According to obtaining the respective login score of the M geographic grid fence, the login score is for characterizing enclosing for geographic grid fence Column temperature.

As an alternative embodiment, the logon data includes: login times, login user number, user's stop The combination of one or more of average time.It need to know, log in the one or more index in the usable logon data of score To be calculated.

First determining module 32 is specifically used for being directed to each geographical network fence in M geographical network fence, according to The login times and weight of each geographic grid fence, the login user number and weight of each geographic grid fence, Average time and weight are stopped with the user of each geographic grid fence, determines the login of each geographic grid fence Score.

In the specific implementation process, first determining module 32, specifically for being enclosed according to each geographic grid The login times and weight on column obtain the login times score of each geographic grid fence.Obtain login times score There are many kinds of embodiments.For example, obtained product is login times score directly by login times and multiplied by weight；Or Login times are handled and (such as to login times sqrt, or seek quadratic power product etc. to login times) by person, By processing result and multiplied by weight, the product of acquisition is login times score.

If being illustrated with model, the present embodiment uses the second default weighted model and handles logon data.Its In, the second default weighted model includes linear regression model (LRM).If login user number, user stops average time with login times For, first determining module 32 is specifically used for the respective logon data input second of the M geographic grid fence is pre- If weighted model score_login=β₁·x_{login_amount}+β₂·x_{login_user_count}+β₃·x_{avg_login_user_staytime}, obtain institute State the respective login score of M geographic grid fence；

Wherein, score_loginFor the login score of single geographic grid fence, x_{login_amount}For single geographic grid fence Login times, β₁For the corresponding weight of login times of single geographic grid fence；x_{login_user_count}For single geographic grid The login user number of fence, β₂For the corresponding weight of login user number of single geographic grid fence；x_{avg_login_user_staytime} Average time, β are stopped for the user of single geographic grid fence₃Average time pair is stopped for the user of single geographic grid fence The weight answered.

Certainly, the second default weighted model is not limited in above-mentioned formula, for example, first determining module 32, specifically For the respective logon data of the M geographic grid fence to be inputted the second default weighted modelThe M geographic grid is obtained to enclose The respective login score in column.Certainly, the second default weighted model can also have other modifications, herein no longer excessive citing.

As an alternative embodiment, second determining module 33, comprising:

Sorting module, for being carried out according to fence temperature height to the respective fence temperature of the M geographic grid fence Sequence obtains ranking results；

Judgment module, for judging whether the mutual distance of N number of geographic grid fence in the ranking results is small In pre-determined distance；2≤N≤M, N are positive integer；

Mesh Fusion module, for if so, merged using Mesh Fusion technology to N number of geographic grid fence, Obtain the hot spot fence area.

As an alternative embodiment, the system also includes:

Second obtains module, for obtaining the business association data in the hot spot fence area；

Third obtains module, for obtaining the hot spot and enclosing according to the business association data in the hot spot fence area The fence temperature in column region.

As an alternative embodiment, the system also includes:

4th obtains module, for obtaining each business object in the corresponding business object group in the hot spot fence area Business association data；

Third determining module, for the business association data based on each business object, from hot spot fence area Business object group to be checked is determined in the corresponding business object group in domain；

Module is checked, for according to the register information of the business object group to be checked and the hot spot fence area Service related data obtains the investigation result of the business object group to be checked.

Based on inventive concept same in previous embodiment, this specification embodiment also provides a kind of computer-readable deposit The step of storage media is stored thereon with computer program, and any the method above is realized when which is executed by processor.

Based on inventive concept same in previous embodiment, the embodiment of this specification also provides a kind of computer and sets It is standby, as shown in figure 4, including memory 404, processor 402 and being stored on memory 404 and can run on the processor 402 Computer program, the step of processor 402 realizes any the method above when executing described program.

Wherein, in Fig. 4, bus architecture (is represented) with bus 400, and bus 400 may include any number of interconnection Bus and bridge, bus 400 will include the one or more processors represented by processor 402 and what memory 404 represented deposits The various circuits of reservoir link together.Bus 400 can also will peripheral equipment, voltage-stablizer and management circuit etc. it Various other circuits of class link together, and these are all it is known in the art, therefore, no longer carry out further to it herein Description.Bus interface 405 provides interface between bus 400 and receiver 401 and transmitter 404.Receiver 401 and transmitter 404 can be the same element, i.e. transceiver, provide for the list over a transmission medium with various other terminal equipment in communication Member.Processor 402 is responsible for management bus 400 and common processing, and memory 404 can be used for storage processor 402 and exist Execute used data when operation.

By one or more embodiment of this specification, this specification has the advantages that or advantage:

Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein. Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system Structure be obvious.In addition, this specification is also not for any particular programming language.It should be understood that can use each Kind programming language realizes the content of this specification described herein, and the description done above to language-specific is to disclose The preferred forms of this specification.

In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the reality of this specification Applying example can practice without these specific details.In some instances, well known method, knot is not been shown in detail Structure and technology, so as not to obscure the understanding of this specification.

Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects, In Above in the description of the exemplary embodiment of this specification, each feature of this specification is grouped together into single reality sometimes It applies in example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required This specification of protection requires features more more than feature expressly recited in each claim.More precisely, such as As following claims reflect, inventive aspect is all features less than single embodiment disclosed above. Therefore, it then follows thus claims of specific embodiment are expressly incorporated in the specific embodiment, wherein each right is wanted It asks in itself all as the separate embodiments of this specification.

Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose It replaces.

In addition, it will be appreciated by those of skill in the art that although some embodiments in this include institute in other embodiments Including certain features rather than other feature, but the combination of the feature of different embodiment means the model for being in this specification Within enclosing and form different embodiments.For example, in the following claims, embodiment claimed it is any One of can in any combination mode come using.

The various component embodiments of this specification can be implemented in hardware, or to transport on one or more processors Capable software module is realized, or is implemented in a combination thereof.It will be understood by those of skill in the art that can make in practice It realized with microprocessor or digital signal processor (DSP) according to the gateway of this specification embodiment, proxy server, be The some or all functions of some or all components in system.This specification is also implemented as being retouched here for executing The some or all device or device programs (for example, computer program and computer program product) for the method stated. Such program for realizing this specification can store on a computer-readable medium, or can have one or more letter Number form.Such signal can be downloaded from an internet website to obtain, and perhaps be provided on the carrier signal or with any Other forms provide.

This specification is limited it should be noted that above-described embodiment illustrates rather than this specification, and Those skilled in the art can be designed alternative embodiment without departing from the scope of the appended claims.In claim In, any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" is not excluded for depositing In element or step not listed in the claims.Word "a" or "an" located in front of the element do not exclude the presence of it is multiple this The element of sample.This specification can be by means of including the hardware of M different elements and by means of properly programmed computer To realize.In the unit claim for listing M device, M in these devices be can be through the same hardware It embodies.The use of word first, second, and third does not indicate any sequence.These words can be construed to Title.

Claims

1. a kind of method for identifying business object group, which comprises

According to the respective business association data of the M geographic grid fence, determines that the M geographic grid fence is respective and enclose Column temperature；Wherein, the fence temperature is used to characterize the business development valence of the business object group in corresponding geographic grid fence Value；

According to the respective fence temperature of the M geographic grid fence, hot spot fence is determined from the M geographic grid fence Region；

2. the method as described in claim 1, the business association data include transaction data；

It is described according to the respective business association data of the M geographic grid fence, determine the M geographic grid fence respectively Fence temperature, comprising:

According to the respective transaction data of M geographic grid fence, obtain that the M geographic grid fence is respective to trade Point, the transaction score is used to characterize the fence temperature of geographic grid fence.

3. method according to claim 2, the transaction data includes: transaction stroke count, transaction amount, trade user number, pen The combination of one or more of the average multiple purchase rate of equal amount information, user.

4. the method as described in claim 1, the business association data include logon data；

According to the respective logon data of M geographic grid fence, obtain that the M geographic grid fence is respective to be logged in Point, the fence temperature for logging in score and being used to characterize geographic grid fence.

5. method as claimed in claim 4, the logon data includes: login times, and login user number, user stops average The combination of one or more of time.

6. the method as described in claim 1, described according to the respective fence temperature of the M geographic grid fence, from the M Hot spot fence area is determined in a geographic grid fence, comprising:

The respective fence temperature of the M geographic grid fence is ranked up according to fence temperature height, obtains ranking results；

Judge whether the mutual distance of N number of geographic grid fence in the ranking results is less than pre-determined distance；2≤N≤ M, N are positive integer；

If so, merging using Mesh Fusion technology to N number of geographic grid fence, the hot spot fence area is obtained.

7. the method as described in claim 1, described according to the respective fence temperature of the M geographic grid fence, from the M After determining hot spot fence area in a geographic grid fence, the method also includes:

Obtain the business association data in the hot spot fence area；

8. the method as described in claim 1, the corresponding business object group in the hot spot fence area that obtains is pushed away After recommending, the method also includes:

Obtain the business association data of each business object in the corresponding business object group in the hot spot fence area；

Based on the business association data of each business object, from the corresponding business object group in the hot spot fence area Determine business object group to be checked；

According to the service related data of the register information of the business object group to be checked and the hot spot fence area, obtain The investigation result of the business object group to be checked.

9. a kind of system for identifying business object group, comprising:

Division module is divided into M geographic grid fence for being analysed to geographic area according to specific trellis, M >=1 and is positive Integer；

First determining module, for determining the M ground according to the respective business association data of the M geographic grid fence Manage the respective fence temperature of grid fence；Wherein, the fence temperature is used to characterize the business pair in corresponding geographic grid fence As the business development of group is worth；

Second determining module is used for according to the respective fence temperature of the M geographic grid fence, from the M geographic grid Hot spot fence area is determined in fence；

10. system as claimed in claim 9, the business association data include transaction data；

First determining module is specifically used for obtaining the M according to the respective transaction data of M geographic grid fence The respective transaction score of geographic grid fence, the transaction score are used to characterize the fence temperature of geographic grid fence.

11. system as claimed in claim 10, the transaction data includes: transaction stroke count, transaction amount, trade user number, The combination of one or more of the pen average multiple purchase rate of amount information, user.

12. system as claimed in claim 9, the business association data include logon data；

First determining module is specifically used for obtaining the M according to the respective logon data of M geographic grid fence A respective login score of geographic grid fence, the fence temperature for logging in score and being used to characterize geographic grid fence.

13. system as claimed in claim 12, the logon data includes: login times, login user number, user stops flat The combination of one or more of equal time.

14. system as claimed in claim 9, second determining module, comprising:

Sorting module, for being ranked up according to fence temperature height to the respective fence temperature of the M geographic grid fence, Obtain ranking results；

Judgment module, for judging it is pre- whether the mutual distance of N number of geographic grid fence in the ranking results is less than If distance；2≤N≤M, N are positive integer；

Mesh Fusion module, for if so, being merged using Mesh Fusion technology to N number of geographic grid fence, acquisition The hot spot fence area.

15. it is system as claimed in claim 9, the system also includes:

Third obtains module, for obtaining hot spot fence area according to the business association data in the hot spot fence area The fence temperature in domain.

16. it is system as claimed in claim 9, the system also includes:

4th obtains module, for obtaining the industry of each business object in the corresponding business object group in the hot spot fence area Business associated data；

Third determining module, for the business association data based on each business object, from the hot spot fence area pair Business object group to be checked is determined in the business object group answered；

Module is checked, for according to the register information of business object group to be checked and the business of the hot spot fence area Related data obtains the investigation result of the business object group to be checked.

17. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor The step of any one of claim 1-8 the method is realized when execution.

18. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor Calculation machine program, which is characterized in that the processor realizes the step of any one of claim 1-8 the method when executing described program Suddenly.