CN117312678A - Intelligent recommendation method, equipment and storage medium for potential clients based on big data - Google Patents
Intelligent recommendation method, equipment and storage medium for potential clients based on big data Download PDFInfo
- Publication number
- CN117312678A CN117312678A CN202311383092.1A CN202311383092A CN117312678A CN 117312678 A CN117312678 A CN 117312678A CN 202311383092 A CN202311383092 A CN 202311383092A CN 117312678 A CN117312678 A CN 117312678A
- Authority
- CN
- China
- Prior art keywords
- data
- client
- development
- recommendation
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000011161 development Methods 0.000 claims abstract description 95
- 238000004088 simulation Methods 0.000 claims abstract description 59
- 239000000463 material Substances 0.000 claims abstract description 26
- 238000012937 correction Methods 0.000 claims abstract description 8
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 206010048909 Boredom Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000010206 sensitivity analysis Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a potential customer intelligent recommendation method, equipment and a storage medium based on big data, belonging to the technical field of service development, wherein the method comprises the following steps: acquiring user enterprise information, and establishing a material library according to the user enterprise information; the material library is used for storing customer simulation information; opening rights of each salesman to access a material library in a user enterprise; the salesman selects corresponding client simulation information from the material library according to the client development requirement, and integrates the client simulation information into client development data; establishing a recommendation model and an interpretation model, wherein the recommendation model is used for recommending potential clients according to client development data; the interpretation model is used for interpreting each influence factor and the proportion in the recommendation result; analyzing the client development data through a recommendation model to obtain a plurality of recommendation results; when the recommendation result of the salesman is unsatisfactory, determining correction data, and analyzing the correction data through an interpretation model to obtain interpretation data; adjustment data is set based on the interpretation data.
Description
Technical Field
The invention belongs to the technical field of service development, and particularly relates to a potential customer intelligent recommendation method, equipment and storage medium based on big data.
Background
With the popularization and development of the internet and the digitizing technology, enterprises face massive potential customers and market information, and how to efficiently find potential customers and conduct personalized recommendation becomes an important problem; with the progress of data science and machine learning, a powerful tool and method are provided for intelligent recommendation of potential customers; by analyzing large-scale user behavior data and characteristic information of potential clients, interests and behaviors of the users can be predicted by utilizing machine learning and data mining technologies, so that personalized potential client recommendation is performed, and client development of the users is greatly facilitated.
However, existing potential customer recommendation systems also suffer from several drawbacks, such as:
1. data sparsity: for new users or users with low activity, it is difficult to accurately predict their interests because of the lack of sufficient behavioral data, especially when the user enterprise is specific to each salesman, accurate potential customer recommendations are difficult to make.
2. Interpretation problem: some recommendations are difficult to interpret, and users have difficulty understanding why certain potential customers are recommended; and the user is difficult to recommend and adjust according to the requirements.
3. Information overload: the recommendation system can recommend a large number of potential clients to the user, but the user is not necessarily interested, so that the problem of information overload is brought to the user, and the user is bothered; especially, on the premise of explanatory problems, the user cannot recommend and optimize according to the requirements, so that a lot of invalid client data are recommended.
4. Privacy problem: the potential customer recommends that personal data of a user need to be analyzed, and certain infringement is caused to the privacy of the user; such as invoking customer data of a customer enterprise, may in some cases easily lead to leakage of customer data.
Disclosure of Invention
In order to solve the problems of the scheme, the invention provides a potential customer intelligent recommendation method, equipment and storage medium based on big data.
The aim of the invention can be achieved by the following technical scheme:
the intelligent recommendation method for the potential clients based on the big data comprises the following steps:
step S1: acquiring user enterprise information, and establishing a material library according to the user enterprise information; the material library is used for storing customer simulation information;
further, the method for establishing the material library comprises the following steps:
establishing a simulation library by an operator, wherein the simulation library is used for storing various client simulation information of operator simulation settings;
inputting the user enterprise information into the simulation library for matching to obtain a plurality of pieces of client simulation information conforming to the user enterprise information;
and establishing a database of the user enterprise, sending the obtained client simulation information to the database for classified storage, and marking the current database as a material library.
Further, the simulation library is established at the cloud.
Step S2: each salesman in the open user enterprise accesses the rights of the material library; the salesman selects corresponding client simulation information from the material library according to the client development requirement, and integrates the client simulation information into client development data;
further, sample expansion is performed on the customer development data.
Further, collaborative data is set according to the client development data, and the collaborative data setting method includes:
determining corresponding business development requirements based on the client development data; matching customer simulation information meeting the service development requirement from a material library, and marking the customer simulation information as information to be selected; determining target business in each piece of information to be selected;
calculating a corresponding coincidence value FHZ according to a coincidence value formula FHZ =gb×Σci;
wherein: FHZ is a coincidence value; GB is the customer scale; ci is the demand ratio of the corresponding target service, i=1, 2, … …, n is a positive integer;
and selecting the information to be selected which accords with N before value ordering, integrating the information to be selected into cooperative data, wherein N is a positive integer.
Step S3: establishing a recommendation model and an interpretation model, wherein the recommendation model is used for recommending potential clients according to client development data; the interpretation model is used for interpreting each influence factor and the occupied proportion in the recommendation result;
step S4: analyzing the client development data through a recommendation model to obtain a plurality of recommendation results, wherein the recommendation results are determined potential clients;
step S5: when the recommended result is not satisfied by the service staff, determining correction data, and analyzing the correction data through the interpretation model to obtain interpretation data; setting adjustment data based on the interpretation data, and optimizing the recommendation model according to the adjustment data.
Further, conflict clients of all the operators are identified in real time, and anti-collision processing is carried out according to the identified conflict clients.
Further, the method for anti-collision treatment comprises the following steps:
and marking corresponding conflict clients in the potential client list in real time, and supplementing salesman information corresponding to the marks.
Further, another method of anti-collision treatment includes:
marking the salesmen of the conflicting client already in the potential client list as the previous salesmen; identifying development data and registration time of a previous salesman for a conflicting client;
setting a corresponding development value based on the development data; calculating a corresponding grade interval according to the registration time;
marking the enrollment interval and the development value as Tc and KF, respectively;
the corresponding priority value PKB is calculated according to the priority formula pkb=kf+30/Tc, and when the priority value is greater than the threshold value X1, the conflicting customer is still responsible for the previous salesman.
Further, carrying out real-time statistics on potential customer resources recommended to each salesman, and carrying out real-time display on statistical data to management staff;
the statistics include a list of potential customers and a statistical map built based on the list of potential customers.
The intelligent recommendation equipment for the potential clients based on the big data comprises a user module, a recommendation module and an interpretation module;
the user module is used for acquiring client development data of a user enterprise;
the recommending module is used for recommending corresponding potential clients according to the client development data;
the interpretation module is used for interpreting the recommendation reasons of the potential clients of each recommendation.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of a big data based potential customer intelligent recommendation method.
Compared with the prior art, the invention has the beneficial effects that:
the intelligent recommendation method and the intelligent recommendation system realize intelligent recommendation for the potential clients and solve the defects of the current potential client recommendation system.
Through the arrangement of the step S1 and the step S2, the development requirements of clients of the user enterprises are determined on the premise that the business confidential data of the user enterprises are not acquired, the business data leakage of the user enterprises is avoided, the trust of the user enterprises to the system is greatly increased, and the data sparsity problem and the privacy problem are solved; meanwhile, personalized recommendation specific to each salesman is realized according to different demands of different salesmen in different periods under a user enterprise; the service development efficiency of a user enterprise is improved, and the problem of accurate customer development requirements caused by different service experiences of various service operators is solved; the service staff of the same service has difference in selection of the client simulation information in the same service field because of experience difference of self service clients and development clients, so that the client development requirements of different service staff are required to be met, the self experience of the service staff is fully exerted, and the efficiency is improved.
The problems of interpretation and information overload are solved through the steps S3 to S5, meanwhile, the use of operators is facilitated, and potential customer pushing is performed for each operator more accurately.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the intelligent recommendation method for potential clients based on big data comprises the following steps:
step S1: acquiring user enterprise information, and establishing a corresponding material library according to the acquired user enterprise information;
the user enterprise information is set and uploaded by enterprise management staff, because detailed and accurate user enterprise information is difficult to obtain through network data on the premise of not accessing business confidential data of the user enterprise, such as the business scope of each enterprise disclosed in the current network, and the business scope of actual operation has larger difference from the business scope disclosed in the network; thus requiring manual input by the user enterprise manager; the user enterprise information comprises data such as service range, client enterprise, client description and the like; wherein, the customer enterprise generally only needs the name of the customer enterprise, and the business confidentiality of the customer enterprise is not revealed; the client description refers to describing which demands and conditions of the client enterprises are preconditions for cooperation through the cooperation process between the client enterprises; the setting of the user enterprise information can be as detailed as possible, so that the screening range is convenient to narrow.
The method for establishing the material library according to the enterprise information of the user comprises the following steps:
establishing a simulation library by an operator, wherein the simulation library is used for storing various client simulation information, namely, client simulation information is used for simulating and setting different client enterprises, such as an enterprise of a certain costume, according to enterprises of various industries, and setting different detailed client information corresponding to the enterprise of the certain costume according to the difference of the enterprise of the city costume to form a plurality of pieces of client simulation information, such as related data of the scale, sales volume, business scope, possible business requirements and the like of the simulated client enterprise; the simulation setting can be performed manually, and the setting can be performed by using the existing intelligent generation technology, so that the client simulation information in different fields can be intelligently generated; storing the obtained customer simulation information into a simulation library; the simulation library can be arranged at the cloud end, so that the material library of each user enterprise can be conveniently arranged and updated in a subsequent synchronous mode.
The method comprises the steps of obtaining user enterprise information, inputting the obtained user enterprise information into a simulation library for matching, obtaining a plurality of pieces of matched client simulation information, building a material library according to the obtained client simulation information, and storing all the client simulation information in the material library in a classified mode.
For the process of matching the client simulation information according to the user enterprise information, firstly, according to the limiting conditions in the user enterprise information, such as a service range and the like; and (3) narrowing the matching field range, and matching by utilizing the existing similarity algorithm according to the data of client enterprises, client descriptions and the like to obtain client simulation data meeting the requirements.
Step S2: opening rights of each salesman to access a material library in a user enterprise; each salesman selects each piece of client simulation information conforming to the business development of the salesman from the material library according to the client development requirement to form client development data;
in one embodiment, when the data size of the client development data set by the salesman is small and the analysis requirement is not met, the existing sample expansion technology can be utilized to perform sample expansion based on the client development data, a large amount of similar data is generated, and the data size is expanded; and if the simulation setting process of the client simulation information is combined, corresponding simulation expansion is carried out according to the client development data.
In one embodiment, as each salesman continues to use, the situation that the recommendation range is too narrow, that is, more and more potential customers repeatedly recommend occurs, because through accurate simulation selection of the salesman, although accurate recommendation and quick recommendation of the salesman are facilitated, development of corresponding services may be disadvantageous in other fields, large experience limitation exists, accurate recommendation can be performed by the salesman with sufficient customer development experience, retrieval and recommendation can only be performed in a limited result range for the salesman with relatively low experience, and efficiency is low.
The setting method of the cooperative data comprises the following steps:
identifying client development data, setting corresponding service development requirements according to the client development data, wherein the service development requirements are that the direction of the service personnel which wants to carry out service development is determined according to the client development data and user enterprise information, for example, enterprises produce and sell various products, the service personnel wants to accurately develop potential clients of a certain product, and the corresponding potential client recommendations are different;
matching each piece of customer simulation information meeting the service development requirements from the material library, and matching according to possible service requirements in the customer simulation information; marking as information to be selected; and outputting the coincidence value of each piece of information to be selected, wherein each piece of client simulation information is simulated by an operator, the size, the degree and the like of the client simulation information on the service requirement can be preset, and the client simulation information is represented by different service requirement proportion, for example, basically each company has toilet paper requirements, but the corresponding service proportion is greatly different, so that the duty ratio of each service requirement can be set for the client simulation information in a simulation library at the operator by combining the embodiment; identifying service types in service development requirements in the information to be selected, possibly a plurality of service types, and marking the service types as target services; marking the corresponding demand ratio of the target service as ci, wherein i represents the corresponding target service, i=1, 2, … … and n, and n is a positive integer; identifying the customer scale of the information to be selected, such as sales, total value of assets, etc., as specific amount data; marking the obtained customer scale as GB; the following formula: FHZ =gb×Σcicalculating the corresponding coincidence value FHZ;
selecting N pieces of information to be selected before the coincidence value sequencing, and integrating the N pieces of information to be selected into cooperative data, wherein the sequencing refers to sequencing according to the sequence from the large coincidence value to the small coincidence value; n is a positive integer.
Through the arrangement of the step S1 and the step S2, the development requirements of clients of the user enterprises are determined on the premise that the business confidential data of the user enterprises are not acquired, the business data leakage of the user enterprises is avoided, the trust of the user enterprises to the system is greatly increased, and the data sparsity problem and the privacy problem are solved; meanwhile, personalized recommendation specific to each salesman is realized according to different demands of different salesmen in different periods under a user enterprise; the service development efficiency of a user enterprise is improved, and the problem of accurate customer development requirements caused by different service experiences of various service operators is solved; as for the service staff of the same service, because of the experience difference of the service client and the development client, the selection of the client simulation information in the same service field is different, so that the client development requirements of different service staff are required to be met, the self experience of the service staff is fully exerted, and the efficiency is improved.
Step S3: establishing a recommendation model and an interpretation model, wherein the recommendation model is used for recommending potential clients according to client development data; the interpretation model is used for analyzing a recommending process of the potential clients and corresponding occupied weight factors, and interpreting which factors have the greatest influence on the recommending result;
the recommendation model is established based on the existing potential customer recommendation system, and the interpretation model is set in a matched mode according to the recommendation model; setting a recommendation model of the user enterprise based on a current decision tree, rule reasoning, a neural network or a deep learning model and the like; the similarity model can also be used to calculate the similarity between the client development data and the internet, and the potential clients are screened based on the calculated similarity.
The importance of each feature in the model and the contribution degree to the recommended result are quantified by using methods such as feature importance analysis, local sensitivity analysis or causal inference, and the decision process of the recommended model can be interpreted by a meta-interpreter, including factors with the greatest influence on the recommended result, so that the interpretability of the recommended result is improved; the recommendation model and the interpretation model are set according to the actual situation of the user enterprise in a manual mode.
The recommendation model has optimizability, namely, after each influence factor and occupied proportion in recommendation result interpretation are adjusted according to a salesman, response can be learned; if the preference is recommended in each piece of software, the user can adjust the recommendation proportion of each recommendation class according to the self requirement, and then the preference recommendation is performed according to the adjusted recommendation class proportion.
Step S4: analyzing the client development data of the corresponding operators through a recommendation model to obtain a plurality of recommendation results, wherein the recommendation results are the determined potential clients;
a client list provided by the user enterprise is built in and only comprises corresponding information such as the enterprise name and the like, and the client list is used for eliminating the enterprise in the client list during recommendation.
Step S5: when a salesman is not satisfied with a certain recommended result or a certain recommended results, marking the corresponding recommended result as correction data, and explaining the correction data through an explanation model to obtain explanation data, namely each influence factor and the proportion of each recommended result;
and the business personnel adjusts each influencing factor and the occupied proportion in the interpretation data according to the self requirements, obtains corresponding adjustment data, and optimizes the recommendation model according to the obtained adjustment data.
The problems of interpretation and information overload are solved through the steps S3 to S5, meanwhile, the use of operators is facilitated, and potential customer pushing is performed for each operator more accurately.
The intelligent recommendation method and the intelligent recommendation system realize intelligent recommendation for the potential clients and solve the defects of the current potential client recommendation system.
In one embodiment, because the potential client recommendation is specific to each salesman, and a user enterprise generally has a plurality of salesmen, the same potential client recommendation is caused to a plurality of salesmen in the actual recommendation process, and the problems of repeated development, low efficiency and the like are easily caused under the condition that each salesman is unknowing; in this embodiment, therefore, the above-described problem is solved in two ways.
The solution method is as follows:
identifying potential clients recommended to each salesman in real time, identifying potential clients with the same recommendation at each salesman, and marking the potential clients as conflict clients; corresponding conflicting clients and corresponding salesmen are marked in real time in the potential client list of each salesmen.
The method is to mark each conflict client in the potential client list in real time, prompt a service staff to communicate with a service staff with conflict when the potential client is developed, and avoid invalid communication and frequent contact of different service staff of the same company with the potential client, thereby causing boredom of the potential client.
Another solution is: identifying in real time conflicting clients having a potential for conflict, i.e., when a potential client is determined, discovering that there is also a potential client in the list of riders of other operators, as a conflicting client; recommending the conflict client to the service person with the highest priority according to the priority of the conflict client relative to each service person, and not recommending other service persons, wherein the specific method comprises the following steps:
identifying development data and registration time corresponding to the conflict client, wherein the development data refers to data such as whether a former salesman has contacted development, conflict client feedback condition, whether tracking service is still performed or not for the development condition of the conflict client; registration time refers to the time of registration in the list of potential clients of the previous salesman, in which method at most only one salesman has possession of the conflicting client;
the possible various development conditions are synthesized, corresponding development values are set according to the corresponding client development results and the interests of the operators of the various development conditions, if undeveloped, failed development (the conflicting client is not needed), and the like, the conflicting clients are handed over to other operators and cannot infringe the labor results and the corresponding interests, and at the moment, a lower development value is corresponding, if the developer is equal to 1; if the client development is in progress, the handover cannot be performed, and the development value is higher and is larger than the threshold value X1; other conditions are set between 1 and X1 according to the difference of conditions, because the development conditions are less in variety, the development conditions are generally adjusted and set by a user enterprise manager, namely, a set of assignment standard is built in, and when the user enterprise manages, assignment corresponding to different development conditions, namely, development values, are adjusted according to the management system of the user enterprise;
calculating a current registration interval according to the registration time, wherein the unit is day, the registration interval is not equal to 0, and the registration is just regarded as 1 day by adopting a next method; marking the obtained registration interval and development value as Tc and KF respectively; and removing the dimension, taking the numerical value for calculation, and calculating a corresponding priority value PKB according to a priority formula PKB=KF+30/Tc, wherein when the priority value is larger than a threshold value X1, the conflict client is not recommended to the salesman and is still responsible for the former salesman.
In one embodiment, because the recommended potential clients are directly sent to each salesman, the business development condition and the resource utilization condition of each salesman cannot be known in time by the enterprise manager, so that the management of the enterprise is not facilitated; because the system is different from the system which is directly distributed to the operators by enterprises, the enterprises directly distribute potential customer resources, and corresponding management staff can timely know the customer data and the customer development condition of each operator, and whether the condition of customer resource waste exists or not; for the invention, the manager cannot accurately know the potential customer data recommended to each salesman, and cannot know various data such as the customer development efficiency, the resource utilization condition and the like; in some cases, the situation that the salesmen sell and recommend potential customer resources can occur, and the training of the salesmen with low development efficiency is not facilitated; based on this, the embodiment is provided, and the real-time statistics is performed on the potential customer data of each salesman, and the specific method includes:
recording potential customer data sent to each salesman in real time, and establishing and updating a potential customer detail table of each salesman;
acquiring potential customer development conditions of a salesman in real time, and carrying out real-time updating marking in a potential customer detail table according to the acquired development conditions; marking dynamic conditions of each potential customer, such as undeveloped, developing success, developing failure and the like;
generating a statistical diagram of each salesman according to the potential customer detail table, wherein the statistical diagram generally comprises a customer development success rate and development efficiency, and can be adjusted according to enterprise management requirements; and displaying the obtained client detail list and the statistical chart to corresponding management personnel in real time.
The intelligent recommendation equipment for the potential clients based on the big data comprises a user module, a recommendation module and an interpretation module.
The user module is used for acquiring client development data of a user enterprise.
The recommending module is used for recommending corresponding potential clients according to the client development data.
The interpretation module is used for interpreting the recommendation reasons of the potential clients of each recommendation.
Since the embodiments of the apparatus portion and the embodiments of the method portion correspond to each other, the embodiments of the apparatus portion are referred to the description of the embodiments of the method portion, and are not repeated herein.
A corresponding embodiment of a computer readable storage medium. The computer readable storage medium has stored thereon a computer program which when executed by a processor performs the steps as described in the embodiments of the big data based latent client intelligent recommendation method described above.
It will be appreciated that the methods of the above embodiments, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored on a computer readable storage medium. With such understanding, the technical solution of the present application, or a part or all of the technical solution contributing to the prior art, may be embodied in the form of a software product stored in a storage medium, performing all or part of the steps of the method described in the various embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas which are obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and preset parameters and preset thresholds in the formulas are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (10)
1. The intelligent recommendation method for the potential clients based on the big data is characterized by comprising the following steps:
acquiring user enterprise information, and establishing a material library according to the user enterprise information; the material library is used for storing customer simulation information;
each salesman in the open user enterprise accesses the rights of the material library; the salesman selects corresponding client simulation information from the material library according to the client development requirement, and integrates the client simulation information into client development data;
establishing a recommendation model and an interpretation model, wherein the recommendation model is used for recommending potential clients according to client development data; the interpretation model is used for interpreting each influence factor and the occupied proportion in the recommendation result;
analyzing the client development data through a recommendation model to obtain a plurality of recommendation results;
when the recommended result is not satisfied by the service staff, determining correction data, and analyzing the correction data through the interpretation model to obtain interpretation data; setting adjustment data based on the interpretation data, and optimizing the recommendation model according to the adjustment data.
2. The big data-based potential customer intelligent recommendation method according to claim 1, wherein the method for establishing the material library comprises the following steps:
establishing a simulation library by an operator, wherein the simulation library is used for storing various client simulation information of operator simulation settings;
inputting the user enterprise information into the simulation library for matching to obtain a plurality of pieces of client simulation information conforming to the user enterprise information;
and establishing a database of the user enterprise, sending the obtained client simulation information to the database for classified storage, and marking the current database as a material library.
3. The big data based potential customer intelligent recommendation method according to claim 2, wherein the simulation library is established in a cloud.
4. The big data based potential customer intelligent recommendation method according to claim 1, wherein the customer development data is sample extended.
5. The big data based potential customer intelligent recommendation method according to claim 1, wherein collaborative data is set according to the customer development data, the collaborative data setting method comprising:
determining corresponding business development requirements based on the client development data; matching customer simulation information meeting the service development requirements from the material library, and marking the customer simulation information as information to be selected; determining target business in each piece of information to be selected;
calculating a corresponding coincidence value FHZ according to a coincidence value formula FHZ =gb×Σci;
wherein: FHZ is a coincidence value; GB is the customer scale; ci is the demand ratio of the corresponding target service, i=1, 2, … …, n is a positive integer;
and selecting the information to be selected which accords with N before value ordering, integrating the information to be selected into cooperative data, wherein N is a positive integer.
6. The big data based intelligent recommendation method for potential customers according to claim 5, wherein conflicting customers of each salesman are identified in real time, and anti-collision processing is performed according to the identified conflicting customers.
7. The big data based potential customer intelligent recommendation method according to claim 6, wherein the anti-collision processing method comprises:
marking the salesmen of the conflicting client already in the potential client list as the previous salesmen; identifying development data and registration time of a previous salesman for a conflicting client;
setting a corresponding development value based on the development data; calculating a corresponding grade interval according to the registration time;
marking the enrollment interval and the development value as Tc and KF, respectively;
the corresponding priority value PKB is calculated according to the priority formula pkb=kf+30/Tc, and when the priority value is greater than the threshold value X1, the conflicting customer is still responsible for the previous salesman.
8. The big data-based potential customer intelligent recommendation method according to claim 1, wherein the potential customer resources recommended to each salesman are counted in real time, and the counted data are displayed to a manager in real time;
the statistics include a list of potential customers and a statistical map built based on the list of potential customers.
9. Big data based potential customer intelligent recommendation device, characterized in that the big data based potential customer intelligent recommendation method according to any of claims 1 to 8 is performed; the system comprises a user module, a recommendation module and an interpretation module;
the user module is used for acquiring client development data of a user enterprise;
the recommending module is used for recommending corresponding potential clients according to the client development data;
the interpretation module is used for interpreting the recommendation reasons of the potential clients of each recommendation.
10. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the big data based potential customer intelligent recommendation method according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311383092.1A CN117312678B (en) | 2023-10-24 | 2023-10-24 | Intelligent recommendation method, equipment and storage medium for potential clients based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311383092.1A CN117312678B (en) | 2023-10-24 | 2023-10-24 | Intelligent recommendation method, equipment and storage medium for potential clients based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117312678A true CN117312678A (en) | 2023-12-29 |
| CN117312678B CN117312678B (en) | 2024-04-05 |
Family
ID=89262007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311383092.1A Active CN117312678B (en) | 2023-10-24 | 2023-10-24 | Intelligent recommendation method, equipment and storage medium for potential clients based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117312678B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117710066A (en) * | 2024-02-05 | 2024-03-15 | 厦门傲凡科技股份有限公司 | Financial customer recommendation method and system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8200527B1 (en) * | 2007-04-25 | 2012-06-12 | Convergys Cmg Utah, Inc. | Method for prioritizing and presenting recommendations regarding organizaion's customer care capabilities |
| US20130325541A1 (en) * | 2012-05-08 | 2013-12-05 | John A. Capriotti | System and method for managing and providing vehicle maintenance |
| CN108960467A (en) * | 2018-07-09 | 2018-12-07 | 重庆锐云科技有限公司 | Realty information management and data analysis system |
| CN109740873A (en) * | 2018-12-19 | 2019-05-10 | 泰康保险集团股份有限公司 | Distribution method, device, medium and the electronic equipment of declaration form |
| CN110968790A (en) * | 2019-12-19 | 2020-04-07 | 苏州朗动网络科技有限公司 | Latent customer intelligent recommendation method, device and storage medium based on big data |
| CN112015987A (en) * | 2020-08-28 | 2020-12-01 | 青岛格兰德信用管理咨询有限公司 | Potential customer recommendation system and method based on enterprise tags |
| US20210065203A1 (en) * | 2019-09-04 | 2021-03-04 | Optum, Inc. | Machine-learning based systems and methods for generating an ordered listing of objects for a particular user |
| CN112667903A (en) * | 2020-12-31 | 2021-04-16 | 北京博瑞彤芸科技股份有限公司 | Method and system for intelligently acquiring customer |
| CN114998039A (en) * | 2022-06-27 | 2022-09-02 | 南京众智科技服务咨询有限公司 | Insurance business cooperative processing method, system, storage medium and electronic equipment |
| CN115587170A (en) * | 2022-09-26 | 2023-01-10 | 中国太平洋人寿保险股份有限公司 | Personalized problem item recommendation method, system and storage medium |
| CN115587739A (en) * | 2022-11-03 | 2023-01-10 | 平安科技（深圳）有限公司 | Client list distribution method and device, computer equipment and storage medium |
| CN116205744A (en) * | 2022-11-16 | 2023-06-02 | 泰康保险集团股份有限公司 | Linkage recommendation display system, device and method |
| CN116911952A (en) * | 2023-07-28 | 2023-10-20 | 中国工商银行股份有限公司 | Financial service pushing method and device |
-
2023
- 2023-10-24 CN CN202311383092.1A patent/CN117312678B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8200527B1 (en) * | 2007-04-25 | 2012-06-12 | Convergys Cmg Utah, Inc. | Method for prioritizing and presenting recommendations regarding organizaion's customer care capabilities |
| US20130325541A1 (en) * | 2012-05-08 | 2013-12-05 | John A. Capriotti | System and method for managing and providing vehicle maintenance |
| CN108960467A (en) * | 2018-07-09 | 2018-12-07 | 重庆锐云科技有限公司 | Realty information management and data analysis system |
| CN109740873A (en) * | 2018-12-19 | 2019-05-10 | 泰康保险集团股份有限公司 | Distribution method, device, medium and the electronic equipment of declaration form |
| US20210065203A1 (en) * | 2019-09-04 | 2021-03-04 | Optum, Inc. | Machine-learning based systems and methods for generating an ordered listing of objects for a particular user |
| CN110968790A (en) * | 2019-12-19 | 2020-04-07 | 苏州朗动网络科技有限公司 | Latent customer intelligent recommendation method, device and storage medium based on big data |
| CN112015987A (en) * | 2020-08-28 | 2020-12-01 | 青岛格兰德信用管理咨询有限公司 | Potential customer recommendation system and method based on enterprise tags |
| CN112667903A (en) * | 2020-12-31 | 2021-04-16 | 北京博瑞彤芸科技股份有限公司 | Method and system for intelligently acquiring customer |
| CN114998039A (en) * | 2022-06-27 | 2022-09-02 | 南京众智科技服务咨询有限公司 | Insurance business cooperative processing method, system, storage medium and electronic equipment |
| CN115587170A (en) * | 2022-09-26 | 2023-01-10 | 中国太平洋人寿保险股份有限公司 | Personalized problem item recommendation method, system and storage medium |
| CN115587739A (en) * | 2022-11-03 | 2023-01-10 | 平安科技（深圳）有限公司 | Client list distribution method and device, computer equipment and storage medium |
| CN116205744A (en) * | 2022-11-16 | 2023-06-02 | 泰康保险集团股份有限公司 | Linkage recommendation display system, device and method |
| CN116911952A (en) * | 2023-07-28 | 2023-10-20 | 中国工商银行股份有限公司 | Financial service pushing method and device |
Non-Patent Citations (2)
| Title |
|---|
| MICHAEL AHEARNE 等: "Examining the effect of salesperson service behavior in a competitive context", 《JOURNAL OF THE ACADEMY OF MARKETING SCIENCE》, vol. 35, 13 February 2007 (2007-02-13), pages 603 * |
| 丁咚: "J人寿保险公司基于客户画像的精准营销策略分析", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》, no. 12, 15 December 2022 (2022-12-15), pages 152 - 743 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117710066A (en) * | 2024-02-05 | 2024-03-15 | 厦门傲凡科技股份有限公司 | Financial customer recommendation method and system |
| CN117710066B (en) * | 2024-02-05 | 2024-05-10 | 厦门傲凡科技股份有限公司 | Financial customer recommendation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117312678B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3893154A1 (en) | Recommendation model training method and related apparatus | |
| Gozhyj et al. | Web resources management method based on intelligent technologies | |
| US11604980B2 (en) | Targeted crowd sourcing for metadata management across data sets | |
| WO2018022251A1 (en) | Method and system for improving content searching in a question and answer customer support system by using a crowd-machine learning hybrid predictive model | |
| US20160210658A1 (en) | Determining touchpoint attributions in a segmented media campaign | |
| CN117312678B (en) | Intelligent recommendation method, equipment and storage medium for potential clients based on big data | |
| Naim et al. | Role of information systems in customer relationship management | |
| CN110008397A (en) | A kind of recommended models training method and device | |
| Javan et al. | A hybrid advertising media selection model using AHP and fuzzy-based GA decision making | |
| CN113157752A (en) | Scientific and technological resource recommendation method and system based on user portrait and situation | |
| JP2022002025A (en) | Information processing device and information processing method | |
| JP2009244981A (en) | Analysis apparatus, analysis method, and analysis program | |
| Zhang et al. | Locally optimal design for a/b tests in the presence of covariates and network dependence | |
| Huang et al. | Exploring structural features in predicting social network evolution | |
| US20200342302A1 (en) | Cognitive forecasting | |
| US10474649B2 (en) | Providing action corrections using a dual model system | |
| US11895180B2 (en) | System and a method for multisession analysis | |
| CN116485352B (en) | Member management and data analysis method, device, equipment and storage medium | |
| Abakouy et al. | Machine Learning as an Efficient Tool to Support Marketing Decision-Making | |
| CN117150389B (en) | Model training method, carrier card activation prediction method and equipment thereof | |
| EP4354382A1 (en) | Contextually relevant content sharing in high-dimensional conceptual content mapping | |
| Patkar et al. | Data-driven persona creation, validation, and evolution | |
| Turner et al. | A T-shaped Measure of Multidisciplinarity in Academic Research Networks: The GRAND Case Study | |
| US20230058770A1 (en) | Insight capturing engine in a data analytics system | |
| CN114186126A (en) | Object recommendation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |