CN112232891A - Customer matching method and device based on big data analysis - Google Patents
Customer matching method and device based on big data analysis Download PDFInfo
- Publication number
- CN112232891A CN112232891A CN202011431438.7A CN202011431438A CN112232891A CN 112232891 A CN112232891 A CN 112232891A CN 202011431438 A CN202011431438 A CN 202011431438A CN 112232891 A CN112232891 A CN 112232891A
- Authority
- CN
- China
- Prior art keywords
- information
- client
- data
- obtaining
- course
- 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 44
- 238000007405 data analysis Methods 0.000 title claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 103
- 230000000694 effects Effects 0.000 claims abstract description 69
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 101150054987 ChAT gene Proteins 0.000 description 26
- 101100203187 Mus musculus Sh2d3c gene Proteins 0.000 description 26
- 238000004891 communication Methods 0.000 description 20
- 238000012795 verification Methods 0.000 description 13
- 238000003062 neural network model Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 11
- 230000007246 mechanism Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000004048 modification Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000003925 brain function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000366 juvenile effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000013515 script Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 239000009891 weiqi Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a customer matching method and a customer matching device based on big data analysis, wherein the method comprises the following steps: obtaining first course information; obtaining first course object information according to the first course information; obtaining first recommended client information according to the first course object information; obtaining client IP information according to the first recommended client information; acquiring first client network data according to the client IP information; inputting the first course object information and the first client network data into a first training model; obtaining output information of the first training model; judging whether the first relevance data meets a first preset threshold value or not; when satisfied, a first instruction is obtained. The technical problems that in the prior art, the reliability of a client list for popularization and use is not high, invalid numbers are more, propaganda cost is wasted, and the popularization effect is influenced are solved.
Description
Technical Field
The invention relates to the field related to online education client matching, in particular to a client matching method and device based on big data analysis.
Background
Now children have attended various training interest classes in order to win on the starting line, such as: piano, english, calligraphy, football, weiqi etc. have brought a lot of business machines simultaneously with this, have appeared multiple education training mechanism, have online, off-line variety simultaneously, and the selectivity is wider also can be fierce to education mechanism's competition simultaneously, in order to receive many biographies, each mechanism can promote through the mode of telemarketing, finds accurate customer group very effective to the popularization effect, avoids the blank to beat and causes the waste.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the technical problems that the reliability of a client list used for popularization is low, the number of invalid numbers is large, the propaganda cost is wasted, and the popularization effect is influenced exist in the prior art.
Disclosure of Invention
The embodiment of the application provides a client matching method and device based on big data analysis, and solves the technical problems that in the prior art, the reliability of a client list for popularization and use is not high, invalid numbers are more, propaganda cost is wasted, and the popularization effect is influenced. The technical effects of pertinently matching clients through the content of courses, analyzing the group chatting of the clients by utilizing big data, correcting the client data, improving the accuracy of the client data, enabling the matching degree of promoted clients to be higher and improving the success rate of promotion are achieved.
The embodiment of the application provides a customer matching method based on big data analysis, wherein the method further comprises the following steps: obtaining first course information; obtaining first course object information according to the first course information; obtaining first recommended client information according to the first course object information; obtaining client IP information according to the first recommended client information; according to the client IP information, first client network data is obtained, and the first client network data is group chat information participated by the first client; inputting the first course object information and the first client network data into a first training model, wherein the first training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: said first course object information, said first customer network data and identification information identifying first association data; obtaining output information of the first training model, wherein the output information includes the first relevance data representing a relevance between the first client network data and the first course object information; judging whether the first relevance data meets a first preset threshold value or not; and when the first instruction is met, acquiring a first instruction, wherein the first instruction is that the first recommended client is successfully matched with the first course information, and storing the first recommended client in a client database.
On the other hand, the application also provides a customer matching device based on big data analysis, wherein the device comprises: a first obtaining unit: the first obtaining unit is used for obtaining first course information; a second obtaining unit: the second obtaining unit is used for obtaining first course object information according to the first course information; a third obtaining unit: the third obtaining unit is used for obtaining first recommended client information according to the first course object information; a fourth obtaining unit: the fourth obtaining unit is used for obtaining the client IP information according to the first recommended client information; a fifth obtaining unit: the fifth obtaining unit is configured to obtain first client network data according to the client IP information, where the first client network data is group chat information that the first client participates in; a first input unit: the first input unit is configured to input the first course object information and the first client network data into a first training model, where the first training model is obtained through training of multiple sets of training data, and each set of training data in the multiple sets of training data includes: said first course object information, said first customer network data and identification information identifying first association data; a sixth obtaining unit: the sixth obtaining unit is configured to obtain output information of the first training model, where the output information includes the first relevance data, and the first relevance data represents a relevance between the first client network data and the first course object information; a first judgment unit: the first judging unit is used for judging whether the first relevance data meets a first preset threshold value; a seventh obtaining unit: the seventh obtaining unit is configured to, when the first instruction is satisfied, obtain a first instruction, where the first instruction is that the first recommended client is successfully matched with the first course information, and store the first recommended client in a client database.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
through obtaining first course object information, first customer network data information, and will first course object information, first customer network data information input first neural network model carries out continuous training for the output result is more accurate, has reached and has made the first relevance data of output, promptly first customer network data with the relevance is more accurate between the first course object information, and then makes popularization customer's matching degree higher, improves the technological effect who promotes the success rate.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Fig. 1 is a schematic flowchart of a customer matching method based on big data analysis according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a client matching apparatus based on big data analysis according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a fifth obtaining unit 15, a first input unit 16, a sixth obtaining unit 17, a first judging unit 18, a seventh obtaining unit 19, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 305.
Detailed Description
The embodiment of the application provides a client matching method and device based on big data analysis, and solves the technical problems that in the prior art, the reliability of a client list for popularization and use is not high, invalid numbers are more, propaganda cost is wasted, and the popularization effect is influenced. The technical effects of pertinently matching clients through the content of courses, analyzing the group chatting of the clients by utilizing big data, correcting the client data, improving the accuracy of the client data, enabling the matching degree of promoted clients to be higher and improving the success rate of promotion are achieved.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
At present, children participate in various training interest classes in order to win on-line starting, meanwhile, a plurality of business opportunities are brought, various education and training mechanisms appear, on-line and off-line diversity exists, the selectivity is wider, meanwhile, competition can be fierce for the education mechanisms, in order to receive a plurality of biographies, all the mechanisms can be popularized in a telemarketing mode, however, the reliability of a client list used for popularization is not high, invalid numbers are more, the propaganda cost is wasted, and the popularization effect is influenced
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides a customer matching method based on big data analysis, wherein the method further comprises the following steps: obtaining first course information; obtaining first course object information according to the first course information; obtaining first recommended client information according to the first course object information; obtaining client IP information according to the first recommended client information; according to the client IP information, first client network data is obtained, and the first client network data is group chat information participated by the first client; inputting the first course object information and the first client network data into a first training model, wherein the first training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: said first course object information, said first customer network data and identification information identifying first association data; obtaining output information of the first training model, wherein the output information includes the first relevance data representing a relevance between the first client network data and the first course object information; judging whether the first relevance data meets a first preset threshold value or not; and when the first instruction is met, acquiring a first instruction, wherein the first instruction is that the first recommended client is successfully matched with the first course information, and storing the first recommended client in a client database.
For better understanding of the above technical solutions, the following detailed descriptions will be provided in conjunction with the drawings and the detailed description of the embodiments.
Example one
As shown in fig. 1, an embodiment of the present application provides a customer matching method based on big data analysis, where the method further includes:
step S100: obtaining first course information;
specifically, the first course information is the course information that the client learns through the online education platform, and the first course information is various in types, including various professional classes and various interest tutor classes, and is not specifically set herein.
Step S200: obtaining first course object information according to the first course information;
specifically, the first course object information is an object for learning through online education, and the first course object information corresponds to the first course information one to one, which is further understood that when the first course information is a juvenile english training course, the first course object information is a child or the like.
Step S300: obtaining first recommended client information according to the first course object information;
specifically, the first recommended client information is one of the plurality of objects of the first lesson object, that is, a client is screened from the first lesson object information, and the first recommended client information and the first lesson object information are the same in learning direction and learning content.
Step S400: obtaining client IP information according to the first recommended client information;
specifically, the client IP information is network address information of the first recommended client information for internet access. The IP address is a uniform address format provided by an IP protocol, a logical address is allocated to each network and each host on the Internet so as to shield the difference of physical addresses, and due to the unique address, a user can efficiently and conveniently select a needed object from thousands of computers when operating on the networked computer.
Step S500: according to the client IP information, first client network data is obtained, and the first client network data is group chat information participated by the first client;
specifically, the client IP information is known, and first client network data, which is group chat information in which the first client participates, that is, chat information of a learning communication group to which the first user adds according to a corresponding learning subject, can be further obtained, and the first client can autonomously learn from the chat information of the learning communication group.
Step S600: inputting the first course object information and the first client network data into a first training model, wherein the first training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: said first course object information, said first customer network data and identification information identifying first association data;
step S700: obtaining output information of the first training model, wherein the output information includes the first relevance data representing a relevance between the first client network data and the first course object information;
specifically, the first lesson object information and the first client network data may be input into a first training model, where the first training model is a model for continuous self-training learning according to training data, and further, the training model is a Neural network model, i.e., a Neural network model in machine learning, and a Neural Network (NN) is a complex Neural network system formed by widely interconnecting a large number of simple processing units (called neurons), reflects many basic features of human brain functions, and is a highly complex nonlinear dynamical learning system. Neural network models are described based on mathematical models of neurons. Artificial Neural Networks (Artificial Neural Networks) are a description of the first-order properties of the human brain system.
Briefly, it is a mathematical model. Training based on a large amount of training data, wherein each set of training data comprises: the first course object information, the first client network data and identification information for identifying first relevance data, the neural network model being continuously self-correcting, and the supervised learning process ending when the output information of the neural network model reaches a predetermined accuracy/convergence status. Through data training of the neural network model, the neural network model can process the input data more accurately, and the output first relevance data, namely the relevance between the first client network data and the first course object information is more accurate. Based on the characteristic that the training model is more accurate in data processing after training, the first course object information and the first client network data are input into the first training model, a first result is accurately obtained through output information of the training model, client data are corrected, accuracy of the client data is improved, and therefore the technical effects that matching degree of popularization clients is higher, and popularization success rate is improved are achieved.
Step S800: judging whether the first relevance data meets a first preset threshold value or not;
step S900: and when the first instruction is met, acquiring a first instruction, wherein the first instruction is that the first recommended client is successfully matched with the first course information, and storing the first recommended client in a client database.
Specifically, the first predetermined threshold is a standard value of the preset first relevance data, the first relevance data may be determined, whether the first relevance data meets a first predetermined threshold is determined, when the first relevance data meets the first predetermined threshold, that is, the first relevance data meets the standard, a first instruction is obtained, the first instruction is that the first recommended client is successfully matched with the first course information, that is, the learning direction and content of the first recommended client are consistent with the teaching direction and content of the first course information, the first recommended client is stored in a client database, and the client database may be updated in real time, so that a suitable communication group is matched for the client, and the technical effect of increasing the success rate of popularization is achieved.
When a result is included in the first client network data, the embodiment of the present application further includes:
step S1010: judging whether the first relevance data meets a first preset threshold value or not;
step S1020: and when the first recommendation client is not satisfied, obtaining a second instruction, wherein the second instruction is used for deleting the first recommendation client.
In particular, when a result has been included in the first client network data, i.e. the first client has added a learning communication group, inputting the AC learning group added with one item into the first training model for training, further obtaining corresponding first relevance data, judging whether the first relevance data meet a first preset threshold value or not, when the first relevance data do not meet the first preset threshold value, obtaining second instructions for deleting the first recommended customer by ensuring that the customer learned relevancy data in the customer database all meets a first predetermined threshold, and further, the learning direction and the content of the client are consistent with the teaching direction and the content of the course information, so that the technical effects of improving the matching degree of the promoted client and improving the success rate of the promotion are achieved.
When the first client network data includes two or more results, the embodiment of the present application further includes:
step S1110: obtaining the first relevance data according to the first course information and a first result in the first client network data; obtaining second relevance data according to the first course information and a second result in the first client network data; repeating the steps until the P-th relevance data is obtained according to the first course information and the P-th result in the first client network data, wherein P is a natural number larger than 1;
step S1120: respectively judging whether the first relevance data, the second relevance data and the third relevance data meet the first preset threshold value or not until the second relevance data;
step S1130: and when at least one of the judgment results is satisfied, obtaining a third instruction, wherein the third instruction is that the first recommended client is successfully matched with the first course information, and storing the first recommended client in the client database.
Specifically, when the first client network data includes two or more results, that is, the first client has added more than one learning communication group, and possibly two or more learning communication groups including languages, mathematics and the like, the first course information has only one subject, which may be any one subject of the languages, mathematics, foreign languages and the like, and should be judged and matched respectively. Obtaining the first relevance data according to the first course information and the first result in the first client network data, and so on until the pth result in the first course information and the first client network data is obtained, obtaining different results by respectively judging whether the first relevance data, the second relevance data and the pth result in the pth relevance data meet the first predetermined threshold, wherein at least one of the different results meets the first predetermined threshold, that is, at least one result is matched with the first course information, obtaining a third instruction when at least one of the judgment results meets the first predetermined threshold, wherein the third instruction is that the first recommended client is successfully matched with the first course information, and saving the first recommended client in the client database, the learning communication group is matched with the first course information of the first recommending client more accurately, so that the matching degree of the promoting client is higher, and the technical effect of improving the promoting success rate is achieved.
In order to match the corresponding learning exchange group to more client groups, the embodiment of the present application further includes:
step 1210: obtaining first associated customer information according to the first recommended customer information and the first customer network data;
step S1220: obtaining a first screening result according to the first associated customer information and the customer database;
step S1230: and when the first screening result is negative, obtaining a fourth instruction, wherein the fourth instruction is that the first associated client is successfully matched with the first course information, and storing the first associated client in the client database.
Specifically, in order to match a corresponding learning exchange group with more client groups, first associated client information may be obtained according to the first recommended client information and the first client network data, and further, a first screening result is obtained according to the first associated client information and the client database, that is, the client database is screened, whether the first associated client information exists in the client database is determined, and when the first screening result is negative, that is, the first associated client information does not exist in the client database, a fourth instruction is obtained, where the fourth instruction is that the first associated client and the first course information are successfully matched, and the first associated client is stored in the client database, and further, the technical effects of matching corresponding learning communication groups with more client groups and expanding the client groups are achieved.
After determining whether the first relevance data meets the first predetermined threshold, step S800 further includes:
step S810: when the first relevance data meets the first preset threshold value, obtaining a first network group chat topic according to the first customer network data;
step S820: obtaining a first course theme according to the first course information;
step S830: obtaining first similarity data according to the first network group chat topic and the first course topic;
step S840: judging whether the first similarity data meet a second preset threshold value or not;
step S850: and when the first recommendation client is satisfied, acquiring a fifth instruction, wherein the fifth instruction is used for listing the first recommendation client as an alternative client and storing the first recommendation client in an alternative client set.
Specifically, for more user-friendly performing client group chat matching, when the first relevance data satisfies the first predetermined threshold, that is, the learning direction and content of the client are consistent with the teaching direction and content of the course information, a first network group chat topic is obtained according to the first client network data, the first network group chat topic is a chat topic in a learning communication group added by the first client, and it can be further understood that an english tutor class reported by a parent for a child learns, the corresponding group chat topic should be an english topic, the first course topic is the main content of the first course information, and further it can be understood that the child learns primary english, and the first course topic corresponds to the learning content of primary english, rather than the super-class contents of primary english, high-middle english, and the like, and further according to the first network group chat topic, The first course topic obtains first similarity data, the first similarity information can be understood as the similarity between the chat topic of the learning communication group added by the parent and the content actually needed to be learned by the child, whether the first similarity data meets a second preset threshold value is judged, whether the first similarity data meets the data of the basic requirement is judged, when the first similarity data meets the data of the basic requirement, the similarity between the chat topic of the learning communication group added by the parent and the content actually needed to be learned by the child is extremely close, a fifth instruction is obtained, the fifth instruction is used for listing the first recommended client as an alternative client and saving in an alternative client set, namely, the client can be listed as an alternative client firstly, and the related learning course is recommended to the child after the learning assistant class reported by the parent and the child is finished, the technical effects of more humanized customer group chat matching and improvement of the popularization success rate are achieved.
After determining whether the first similarity data satisfies a second predetermined threshold, step S840 further includes:
step S841: obtaining the first instruction when the first similarity data does not satisfy a second predetermined threshold.
Specifically, if the first similarity data does not satisfy the second predetermined threshold, it may be understood that the chat theme of the learning communication group added by the parent does not conform to the content actually required to be learned by the child, and no promotion is given to the learning of the child, the first instruction is obtained, according to the first instruction, the first recommended client is successfully matched with the first course information, and a suitable learning communication group is matched for the child, so that a technical effect of performing client group chat matching more reasonably and scientifically is achieved.
Further, the embodiment of the present application further includes:
step 1310: taking the first client IP information as first input data;
step S1320: taking the first customer network data as second input data;
step S1330: inputting the first input data and the second input data into a second training model, wherein the second training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data includes: the first input data, the second input data, and identification information to identify first liveness information;
step S1340: obtaining output information of the second training model, wherein the output information includes the first activity information, the first activity information representing an activity of the first recommended client in the first client network data, wherein the first activity information includes an activity time and an activity level;
step S1350: judging whether the first activeness information meets a third preset threshold value;
step S1360: when the first activity interval time does not meet the first activity requirement, obtaining first activity interval time according to the first activity information;
step S1370: judging whether the first active interval time meets a fourth preset threshold value;
step S1380: and when the first recommended customer information is met, acquiring a sixth instruction, wherein the sixth instruction is that the first recommended customer is successfully matched with the first course information, and the first associated customer is removed from the spare customer set and stored in the customer database.
Specifically, after determining whether the first relevance data meets a first predetermined threshold, it may further determine whether the reported learning coaching class is about to expire or end by learning the speaking activity and the group entering time in the communication group, so as to match a suitable learning communication group again for the child. The supervised learning process may be ended by inputting the first client IP information and the first client network data into a second training model, which is used to train the input data continuously with the first training model, and will not be described in detail herein until the output information of the neural network model reaches a predetermined accuracy/reaches a convergence state. Through data training of the neural network model, the neural network model is enabled to process the input data more accurately, and the output first activity information, namely the activity of the first recommended client in the first client network data, is enabled to be output, wherein the first activity information comprises an activity time and an activity degree, and is further enabled to judge whether the first activity information meets a third preset threshold value, namely whether the information, such as the speaking activity degree and the speaking time of the first client in learning a communication group, meets the most basic activity degree, when the information does not meet the basic activity degree, a first activity interval time is obtained according to the first activity information, the first activity interval time is a time interval for the first client to speak in the group, and the activity degree of the first client can be further judged according to the first activity interval time, when the first active interval time is too long, a sixth instruction is obtained, the first recommended client is successfully matched with the first course information, the first associated clients are intensively moved out from the standby clients and stored in the client database, whether the learning period is about to expire or not is judged according to the actual group chat activity of the users, and suitable learning communication groups are recommended to the first clients timely, so that more humanized and more reasonable matching learning communication groups are achieved, the matching degree of promoted clients is higher, and the technical effect of the popularization success rate is improved.
In order to effectively record and store the customer database information, the embodiment of the present application further includes:
generating a first verification code according to first customer data information, wherein the first verification code corresponds to the first customer data information one to one;
generating a second verification code according to second client data information, wherein the second verification code corresponds to the second client data information one to one, and by analogy, obtaining Nth client data information, and generating an Nth verification code according to the Nth client data information, wherein N is a natural number greater than 1;
and respectively copying and storing all the client data information and the verification codes in M devices, wherein M is a natural number greater than 1.
Specifically, to ensure that the customer database information can be effectively recorded and saved, encryption operations based on block chains can be performed on the customer database information to ensure that the data is not tampered. The block chain technology is a universal underlying technical framework, and can generate and synchronize data on distributed nodes through a consensus mechanism, and realize automatic execution and data operation of contract terms by means of programmable scripts. A block chain is defined as a data structure that organizes data blocks in time sequence, with chain-like connections being formed in order between different blocks, by means of which a digital ledger is built.
Generating a first verification code according to first customer data information, wherein the first verification code corresponds to the first customer data information one to one; generating a second verification code according to second client data information, wherein the second verification code corresponds to the second client data information one to one, and by analogy, obtaining Nth client data information, and generating an Nth verification code according to the Nth client data information, wherein N is a natural number greater than 1; and respectively copying and storing all the client data information and the verification codes in M devices, wherein M is a natural number greater than 1. And carrying out encrypted storage on the first customer data information, wherein each device corresponds to one node, all the nodes are combined to form a block chain, and the block chain forms a total account book which is convenient to verify (the Hash value of the last block is verified to be equivalent to the whole version), and cannot be changed (the Hash value of all the following blocks is changed by changing any transaction information, so that the transaction information cannot pass the verification).
The block chain system adopts a distributed data form, each participating node can obtain a complete database backup, and unless 51% of nodes in the whole system can be controlled simultaneously, modification of the database by a single node is invalid, and data contents on other nodes cannot be influenced. Therefore, the more nodes participating in the system, the more powerful the computation, and the higher the data security in the system. The client database information is encrypted based on the block chain, so that the storage safety of the client database information is effectively ensured, and the technical effect of safely recording and storing the client database information is achieved.
To sum up, the customer matching method and device based on big data analysis provided by the embodiment of the application have the following technical effects:
1. through obtaining first course object information, first customer network data information, and will first course object information, first customer network data information input first neural network model carries out continuous training for the output result is more accurate, has reached and has made the first relevance data of output, promptly first customer network data with the relevance is more accurate between the first course object information, and then makes popularization customer's matching degree higher, improves the technological effect who promotes the success rate.
2. By obtaining the activity level information of the first client in the learning communication group, whether the learning period of the first client is about to expire or not can be judged, and then other suitable learning communication groups are matched for the first client, so that the technical effect of carrying out client learning group chat matching more humanizedly is achieved.
Example two
Based on the same inventive concept as the customer matching method based on big data analysis in the foregoing embodiment, the present invention further provides a customer matching device based on big data analysis, as shown in fig. 2, the device includes:
the first obtaining unit 11: the first obtaining unit 11 is configured to obtain first course information;
the second obtaining unit 12: the second obtaining unit 12 is configured to obtain first course object information according to the first course information;
the third obtaining unit 13: the third obtaining unit 13 is configured to obtain first recommended client information according to the first course object information;
the fourth obtaining unit 14: the fourth obtaining unit 14 is configured to obtain client IP information according to the first recommended client information;
the fifth obtaining unit 15: the fifth obtaining unit 15 is configured to obtain first client network data according to the client IP information, where the first client network data is group chat information that the first client participates in;
the first input unit 16: the first input unit 16 is configured to input the first course object information and the first client network data into a first training model, where the first training model is obtained by training multiple sets of training data, and each of the multiple sets of training data includes: said first course object information, said first customer network data and identification information identifying first association data;
sixth obtaining unit 17: the sixth obtaining unit 17 is configured to obtain output information of the first training model, where the output information includes the first relevance data, and the first relevance data represents a relevance between the first client network data and the first course object information;
the first judgment unit 18: the first judging unit 18 is configured to judge whether the first relevance data meets a first predetermined threshold;
the seventh obtaining unit 19: the seventh obtaining unit 19 is configured to, when the first instruction is satisfied, obtain a first instruction, where the first instruction is that the first recommended client and the first course information are successfully matched, and store the first recommended client in a client database.
Further, the apparatus further comprises:
a second judgment unit: the second judging unit is configured to judge whether the first relevance data meets a first predetermined threshold;
an eighth obtaining unit: the eighth obtaining unit is configured to obtain a second instruction when the second instruction is not satisfied, where the second instruction is used to delete the first recommended client.
Further, the apparatus further comprises:
a ninth obtaining unit: the ninth obtaining unit is configured to obtain the first relevance data according to the first course information and a first result in the first client network data; obtaining second relevance data according to the first course information and a second result in the first client network data; repeating the steps until the P-th relevance data is obtained according to the first course information and the P-th result in the first client network data, wherein P is a natural number larger than 1;
a third judging unit: the third judging unit is configured to respectively judge whether the first relevance data, the second relevance data, and the third relevance data meet the first predetermined threshold value or not;
a tenth obtaining unit: the tenth obtaining unit is configured to, when at least one of the judgment results is satisfied, obtain a third instruction, where the third instruction is that the first recommended client is successfully matched with the first course information, and store the first recommended client in the client database.
Further, the apparatus further comprises:
an eleventh obtaining unit: the eleventh obtaining unit is configured to obtain first associated customer information according to the first recommended customer information and the first customer network data;
a twelfth obtaining unit: the twelfth obtaining unit is configured to obtain a first screening result according to the first associated customer information and the customer database;
a thirteenth obtaining unit: the thirteenth obtaining unit is configured to, if the first screening result is negative, obtain a fourth instruction, where the fourth instruction is that the first associated client is successfully matched with the first course information, and store the first associated client in the client database.
Further, the apparatus further comprises:
a fourteenth obtaining unit: the fourteenth obtaining unit is configured to, when the first relevance data meets the first predetermined threshold, obtain a first network group chat topic according to the first customer network data;
a fifteenth obtaining unit: the fifteenth obtaining unit is configured to obtain a first course topic according to the first course information;
a sixteenth obtaining unit: the sixteenth obtaining unit is configured to obtain first similarity data according to the first network group chat topic and the first course topic;
a fourth judging unit: the fourth judging unit is used for judging whether the first similarity data meets a second preset threshold value;
a seventeenth obtaining unit: the seventeenth obtaining unit is configured to obtain a fifth instruction when the first recommendation client is satisfied, where the fifth instruction is used to list the first recommendation client as an alternative client and store the alternative client in an alternative client set.
Further, the apparatus further comprises:
an eighteenth obtaining unit: the eighteenth obtaining unit is configured to obtain the first instruction when the first similarity data does not satisfy a second predetermined threshold.
Further, the apparatus further comprises:
a second input unit: the second input unit is configured to input the first input data and the second input data into a second training model, where the second training model is obtained through training of multiple sets of training data, and each set of training data in the multiple sets of training data includes: the first input data, the second input data, and identification information to identify first liveness information;
a nineteenth obtaining unit: the nineteenth obtaining unit is configured to obtain output information of the second training model, where the output information includes the first activity information, and the first activity information represents an activity of the first recommended client in the first client network data, where the first activity information includes an activity time and an activity level;
a fifth judging unit: the fifth judging unit is used for judging whether the first activity information meets a third preset threshold value;
a twentieth obtaining unit: the twentieth obtaining unit is configured to obtain a first activity interval time according to the first activity level information when the first activity level is not satisfied;
a sixth judging unit: the sixth judging unit is used for judging whether the first active interval time meets a fourth preset threshold value;
a twenty-first obtaining unit: the twenty-first obtaining unit is configured to, when the first instruction is satisfied, obtain a sixth instruction, where the sixth instruction is that the first recommended customer is successfully matched with the first course information, and remove the first associated customer from the spare customer set and store the first associated customer in the customer database.
Various changes and specific examples of the customer matching method based on big data analysis in the first embodiment of fig. 1 are also applicable to the customer matching device based on big data analysis in the present embodiment, and through the foregoing detailed description of the customer matching method based on big data analysis, those skilled in the art can clearly know the implementation method of the customer matching device based on big data analysis in the present embodiment, so for the brevity of the description, detailed description is not repeated again.
EXAMPLE III
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the big data analysis based customer matching method in the foregoing embodiments, the present invention further provides a big data analysis based customer matching device, on which a computer program is stored, which when executed by a processor implements the steps of any one of the foregoing big data analysis based customer matching methods.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the application provides a customer matching method based on big data analysis, wherein the method further comprises the following steps: obtaining first course information; obtaining first course object information according to the first course information; obtaining first recommended client information according to the first course object information; obtaining client IP information according to the first recommended client information; according to the client IP information, first client network data is obtained, and the first client network data is group chat information participated by the first client; inputting the first course object information and the first client network data into a first training model, wherein the first training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: said first course object information, said first customer network data and identification information identifying first association data; obtaining output information of the first training model, wherein the output information includes the first relevance data representing a relevance between the first client network data and the first course object information; judging whether the first relevance data meets a first preset threshold value or not; and when the first instruction is met, acquiring a first instruction, wherein the first instruction is that the first recommended client is successfully matched with the first course information, and storing the first recommended client in a client database.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A customer matching method based on big data analysis, wherein the method comprises:
obtaining first course information;
obtaining first course object information according to the first course information;
obtaining first recommended client information according to the first course object information;
obtaining client IP information according to the first recommended client information;
according to the client IP information, first client network data is obtained, and the first client network data is group chat information participated by the first client;
inputting the first course object information and the first client network data into a first training model, wherein the first training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: said first course object information, said first customer network data and identification information identifying first association data;
obtaining output information of the first training model, wherein the output information includes the first relevance data representing a relevance between the first client network data and the first course object information;
judging whether the first relevance data meets a first preset threshold value or not;
and when the first instruction is met, acquiring a first instruction, wherein the first instruction is that the first recommended client is successfully matched with the first course information, and storing the first recommended client in a client database.
2. The method of claim 1, wherein when a result is included in the first customer network data, the method comprises:
judging whether the first relevance data meets a first preset threshold value or not;
and when the first recommendation client is not satisfied, obtaining a second instruction, wherein the second instruction is used for deleting the first recommendation client.
3. The method of claim 2, wherein when two or more results are included in the first customer network data, the method comprises:
obtaining the first relevance data according to the first course information and a first result in the first client network data; obtaining second relevance data according to the first course information and a second result in the first client network data; repeating the steps until the P-th relevance data is obtained according to the first course information and the P-th result in the first client network data, wherein P is a natural number larger than 1;
respectively judging whether the first relevance data, the second relevance data and the third relevance data meet the first preset threshold value or not until the second relevance data;
and when at least one of the judgment results is satisfied, obtaining a third instruction, wherein the third instruction is that the first recommended client is successfully matched with the first course information, and storing the first recommended client in the client database.
4. The method of claim 1, wherein the method comprises:
obtaining first associated customer information according to the first recommended customer information and the first customer network data;
obtaining a first screening result according to the first associated customer information and the customer database;
and when the first screening result is negative, obtaining a fourth instruction, wherein the fourth instruction is that the first associated client is successfully matched with the first course information, and storing the first associated client in the client database.
5. The method of claim 1, wherein said determining whether said first relevance data meets a first predetermined threshold further comprises:
when the first relevance data meets the first preset threshold value, obtaining a first network group chat topic according to the first customer network data;
obtaining a first course theme according to the first course information;
obtaining first similarity data according to the first network group chat topic and the first course topic;
judging whether the first similarity data meet a second preset threshold value or not;
and when the first recommendation client is satisfied, acquiring a fifth instruction, wherein the fifth instruction is used for listing the first recommendation client as an alternative client and storing the first recommendation client in an alternative client set.
6. The method of claim 5, wherein said determining whether the first similarity data satisfies a second predetermined threshold comprises:
obtaining the first instruction when the first similarity data does not satisfy a second predetermined threshold.
7. The method of claim 5, wherein the method comprises:
taking the first client IP information as first input data;
taking the first customer network data as second input data;
inputting the first input data and the second input data into a second training model, wherein the second training model is obtained by training a plurality of sets of training data, and each set of training data in the plurality of sets of training data includes: the first input data, the second input data, and identification information to identify first liveness information;
obtaining output information of the second training model, wherein the output information includes the first activity information, the first activity information representing an activity of the first recommended client in the first client network data, wherein the first activity information includes an activity time and an activity level;
judging whether the first activeness information meets a third preset threshold value;
when the first activity interval time does not meet the first activity requirement, obtaining first activity interval time according to the first activity information;
judging whether the first active interval time meets a fourth preset threshold value;
and when the first recommended customer information is met, acquiring a sixth instruction, wherein the sixth instruction is that the first recommended customer is successfully matched with the first course information, and the first associated customer is removed from the spare customer set and stored in the customer database.
8. A customer matching apparatus based on big data analysis, wherein the apparatus comprises:
a first obtaining unit: the first obtaining unit is used for obtaining first course information;
a second obtaining unit: the second obtaining unit is used for obtaining first course object information according to the first course information;
a third obtaining unit: the third obtaining unit is used for obtaining first recommended client information according to the first course object information;
a fourth obtaining unit: the fourth obtaining unit is used for obtaining the client IP information according to the first recommended client information;
a fifth obtaining unit: the fifth obtaining unit is configured to obtain first client network data according to the client IP information, where the first client network data is group chat information that the first client participates in;
a first input unit: the first input unit is configured to input the first course object information and the first client network data into a first training model, where the first training model is obtained through training of multiple sets of training data, and each set of training data in the multiple sets of training data includes: said first course object information, said first customer network data and identification information identifying first association data;
a sixth obtaining unit: the sixth obtaining unit is configured to obtain output information of the first training model, where the output information includes the first relevance data, and the first relevance data represents a relevance between the first client network data and the first course object information;
a first judgment unit: the first judging unit is used for judging whether the first relevance data meets a first preset threshold value;
a seventh obtaining unit: the seventh obtaining unit is configured to, when the first instruction is satisfied, obtain a first instruction, where the first instruction is that the first recommended client is successfully matched with the first course information, and store the first recommended client in a client database.
9. A customer matching apparatus based on big data analysis, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011431438.7A CN112232891B (en) | 2020-12-10 | 2020-12-10 | Customer matching method and device based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011431438.7A CN112232891B (en) | 2020-12-10 | 2020-12-10 | Customer matching method and device based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112232891A true CN112232891A (en) | 2021-01-15 |
| CN112232891B CN112232891B (en) | 2021-07-09 |
Family
ID=74123964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011431438.7A Active CN112232891B (en) | 2020-12-10 | 2020-12-10 | Customer matching method and device based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112232891B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112788186A (en) * | 2021-01-28 | 2021-05-11 | 深圳通联金融网络科技服务有限公司 | Method and device for automatic batch call forwarding based on open source software development |
| CN112950350A (en) * | 2021-02-06 | 2021-06-11 | 中国建设银行股份有限公司 | Loan product recommendation method and system based on machine learning |
| CN113191514A (en) * | 2021-04-25 | 2021-07-30 | 云赛智联股份有限公司 | Visitor vehicle information reservation auditing method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544663A (en) * | 2013-06-28 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for recommending network public classes and mobile terminal |
| CN109218390A (en) * | 2018-07-12 | 2019-01-15 | 北京比特智学科技有限公司 | User's screening technique and device |
| CN110737730A (en) * | 2019-10-21 | 2020-01-31 | 腾讯科技（深圳）有限公司 | Unsupervised learning-based user classification method, unsupervised learning-based user classification device, unsupervised learning-based user classification equipment and storage medium |
-
2020
- 2020-12-10 CN CN202011431438.7A patent/CN112232891B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544663A (en) * | 2013-06-28 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for recommending network public classes and mobile terminal |
| CN109218390A (en) * | 2018-07-12 | 2019-01-15 | 北京比特智学科技有限公司 | User's screening technique and device |
| CN110737730A (en) * | 2019-10-21 | 2020-01-31 | 腾讯科技（深圳）有限公司 | Unsupervised learning-based user classification method, unsupervised learning-based user classification device, unsupervised learning-based user classification equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112788186A (en) * | 2021-01-28 | 2021-05-11 | 深圳通联金融网络科技服务有限公司 | Method and device for automatic batch call forwarding based on open source software development |
| CN112950350A (en) * | 2021-02-06 | 2021-06-11 | 中国建设银行股份有限公司 | Loan product recommendation method and system based on machine learning |
| CN113191514A (en) * | 2021-04-25 | 2021-07-30 | 云赛智联股份有限公司 | Visitor vehicle information reservation auditing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112232891B (en) | 2021-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112232891B (en) | Customer matching method and device based on big data analysis | |
| US10169717B2 (en) | System and method for defining and using different levels of ground truth | |
| Hahn et al. | Truth tracking performance of social networks: How connectivity and clustering can make groups less competent | |
| WO2020005725A1 (en) | Knowledge-driven dialog support conversation system | |
| US11443112B2 (en) | Outcome of a natural language interaction | |
| CN111797222B (en) | Course knowledge graph construction method, device, terminal and storage medium | |
| CN107832275A (en) | The generation method of intelligent Contract ID, apparatus and system in block chain | |
| CN112580352B (en) | Keyword extraction method, device and equipment and computer storage medium | |
| CN110111010B (en) | Question and answer task allocation method and system based on crowd-sourcing network | |
| CN113283238B (en) | Text data processing method and device, electronic equipment and storage medium | |
| CN112101577B (en) | XGboost-based cross-sample federal learning and testing method, system, device and medium | |
| US11861463B2 (en) | Identifying related messages in a natural language interaction | |
| Kengphanphanit et al. | Automatic requirements elicitation from social media (ARESM) | |
| US11816548B2 (en) | Distributed learning using ensemble-based fusion | |
| CN115408502A (en) | Cognitive learning in a synchronous conference to generate scripts that simulate live agent actions | |
| CN114780733A (en) | DIKW atlas-based intelligent patent modification method, auxiliary response method and system | |
| CN112148759A (en) | Method and system for selecting image based on cloud platform | |
| US20200364304A1 (en) | Automatic evaluation of artificial intelligence-based processes | |
| WO2023245523A1 (en) | Method and apparatus for generating training data | |
| US20230081891A1 (en) | System and method of managing knowledge for knowledge graphs | |
| CN113420261B (en) | Course recommendation method, device, equipment and medium based on attribution analysis | |
| Kessentini et al. | Improving web services design quality using heuristic search and machine learning | |
| CN117033997A (en) | Data segmentation method, device, electronic equipment and medium | |
| CN115098665A (en) | Method, device and equipment for expanding session data | |
| Alahmed et al. | “How Does ChatGPT Work” Examining Functionality To The Creative AI CHATGPT on X's (Twitter) Platform |
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 |