CN111538910A - Intelligent recommendation method and device and computer storage medium - Google Patents
Intelligent recommendation method and device and computer storage medium Download PDFInfo
- Publication number
- CN111538910A CN111538910A CN202010583898.5A CN202010583898A CN111538910A CN 111538910 A CN111538910 A CN 111538910A CN 202010583898 A CN202010583898 A CN 202010583898A CN 111538910 A CN111538910 A CN 111538910A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- historical
- recommendation
- access
- 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.)
- Pending
Links
Images
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
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent recommendation method, which is applied to the technical field of intelligent recommendation and comprises the following steps: obtaining historical user data, wherein the historical user data at least comprises: user behavior data and user tag data; training a model based on the number of the historical users to obtain a trained target model; and acquiring user access information, and training the access user information by combining the target model and the business processing rule to acquire a recommendation result corresponding to the access user information. And an intelligent recommendation apparatus and a computer storage medium are provided. By applying the embodiment of the invention, under the conditions of complex client types and various client requirements, client group classification and personalized display optimization are carried out, so that the continuous improvement of client experience is brought; the method aims to construct a data model by analyzing the historical records of the client behaviors and show different types of official website contents to the client so as to achieve the purpose of scene marketing and service.
Description
Technical Field
The invention relates to the technical field of intelligent recommendation, in particular to an intelligent recommendation method, an intelligent recommendation device and a computer storage medium.
Background
With the rise of insurance industry, competition among insurance enterprises becomes more and more fierce, how to accurately serve customers and improve the satisfaction of the customers on the services are key factors influencing the sales performance of insurance sales personnel.
Currently, with the development of big data, a user tag is established for a customer by using a big data analysis technology, and an insurance product suitable for the user is matched through the user tag. Then, due to the complexity of the client and the fact that the potential user accesses the website through the website or the APP, the part of the user is difficult to be covered through the client service, and the client cannot know the self guarantee requirement.
Therefore, the insurance product is recommended according to the historical behaviors of the user, so that the client can comprehensively know the self guarantee defects, the satisfaction degree of the client on the service is improved, and the recommendation success rate of the insurance product can be improved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an intelligent recommendation method, an intelligent recommendation device and a computer storage medium, which are used for carrying out guest group classification and personalized display optimization under the conditions of complex customer types and various customer requirements, thereby bringing continuous improvement on customer experience; the method aims to construct a data model by analyzing the historical records of the client behaviors and show different types of official website contents to the client so as to achieve the purpose of scene marketing and service.
The invention is realized by the following steps:
the invention provides an intelligent recommendation method, which comprises the following steps:
obtaining historical user data, wherein the historical user data at least comprises: user behavior data and user tag data;
training a model based on the number of the historical users to obtain a trained target model;
and acquiring user access information, and training the access user information by combining the target model and the business processing rule to acquire a recommendation result corresponding to the access user information.
In one implementation manner, the step of obtaining user access information and training the access user information in combination with the target model and the business processing rule to obtain a recommendation result corresponding to the access user information includes:
acquiring a client accessing a target website;
judging whether the user is a login client or not;
if yes, obtaining the user information of the login client;
and training the information of the access user by combining the target model and the business processing rule based on the user information to obtain a recommendation result corresponding to the information of the access user.
In one implementation, if the accessing client is a non-login client, the method further comprises:
recording the access address of the user;
acquiring a historical access record of the access address;
training the information of the access user by combining the target model and the business processing rule based on the historical access record to obtain a recommendation result corresponding to the information of the access user
In one implementation, the step of obtaining historical user data includes:
acquiring historical search information and historical reference information corresponding to a user according to account information corresponding to the user;
and acquiring historical user data according to the historical search information and the historical consulting information.
In one implementation, the method further comprises:
acquiring a recommendation result list according to the recommendation result;
and displaying the recommendation result list according to a preset display condition.
In one implementation manner, the step of obtaining a recommendation result list according to the recommendation result includes:
acquiring a recommendation score of each recommendation result;
and ranking according to the recommendation scores from high to low, and taking the recommendation results corresponding to the ranking sequence as a recommendation result list.
In one implementation, the step of obtaining historical user data includes:
obtaining raw data of each user in historical users, wherein the raw data comprises user information, user behaviors, user historical insurance application and/or policy information;
and adding labels to the historical users according to the original acquisition, wherein the labels include but are not limited to: user attribute statistics, product purchase times, product purchase trends, complaint times, channel use frequency and service use frequency.
In one implementation, at the step of obtaining a trained target model, the method further includes:
and establishing labels for the target model, wherein the labels comprise but are not limited to a square type, a channel source, a browsing record, a page hotspot, a search history, access times, a staying time, information input, an access terminal, a browser version and a client IP.
In addition, the invention also discloses an intelligent recommendation device, which comprises a processor and a memory connected with the processor through a communication bus; wherein the content of the first and second substances,
the memory is used for storing the intelligent recommendation program;
the processor is used for executing the intelligent recommendation program to realize any intelligent recommendation step.
Also, a computer storage medium is disclosed that stores one or more programs that are executable by one or more processors to cause the one or more processors to perform any of the intelligent recommendation steps.
The intelligent recommendation method, the intelligent recommendation device and the computer storage medium have the following beneficial effects:
(1) under the conditions of complex client types and various client requirements, the client group classification and personalized display optimization are carried out, and further the continuous improvement of client experience is brought.
(2) The method aims to construct a data model by analyzing the historical records of the client behaviors and show different types of official website contents to the client so as to achieve the purpose of scene marketing and service.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an intelligent recommendation method according to an embodiment of the present invention;
fig. 2 is a schematic view of an application scenario of the intelligent recommendation method according to the embodiment of the present invention;
fig. 3 is a schematic view of another application scenario of the intelligent recommendation method according to the embodiment of the present invention;
fig. 4 is a schematic view of another application scenario of the intelligent recommendation method according to the embodiment of the present invention
Fig. 5 is a schematic view of an application scenario of the intelligent recommendation device according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the processing and calculation of data on which recommendation depends are based on a big data platform, a calculation mode of Sparkon Yarn is adopted, a resource scheduling mechanism mature by Yarn and the operation of Spark based on a memory level are depended on, and the calculation efficiency and performance are greatly improved.
The back end adopts a CAF unified development framework, and based on the technologies of springMVC, Spring and Mybatis, the framework bottom layer encapsulates project basic functions, cache processing, transaction management and log processing, and the method has the advantages of maturity, stability, reliability and simplicity.
The front end adopts a VUE + IVEW frame, supports a system to construct an interface with uniform style, attractive appearance and delicacy, has quick page response speed, enables a user to obtain smooth experience, and has good third party compatibility and browser compatibility.
The client is added into containerization management, continuous integration is facilitated, and the continuous integration is very convenient through association with the codes.
Referring to fig. 1, an embodiment of the present invention provides an intelligent recommendation method, where the method includes:
s101, obtaining historical user data, wherein the historical user data at least comprises: user behavior data and user tag data.
It should be noted that, as shown in fig. 2 and fig. 3, when a user purchases insurance or logs in an insurance website, user information, such as login information of the user, access information of the user, and the like, is left, and these data are kept in a specified database, so that the corresponding history data can be obtained from the database according to each user.
In one implementation mode of the invention, when a user logs in through an account, historical search information and historical reference information corresponding to the user can be obtained according to account information corresponding to the user; and acquiring historical user data according to the historical search information and the historical consulting information.
In another implementation of the present invention, as shown in fig. 3, raw data of each user in the historical users is obtained, where the raw data includes, but is not limited to, user information, user behavior, user historical application and/or policy information; and adding labels to the historical users based on the original acquisition, wherein the labels include but are not limited to: user attribute statistics, product purchase times, product purchase trends, complaint times, channel use frequency and service use frequency.
In yet another implementation, if the accessing client is a non-login client, the method further comprises: recording the access address of the user; and acquiring a historical access record of the access address.
And S102, training the model based on the number of the historical users to obtain a trained target model.
It should be noted that the model may be a machine learning model, a deep learning model, an LSTM model, or the like, and the embodiment of the present invention is not limited in particular. Historical data is input into the model as a training data set, and according to the training requirements of the model, the model is regarded as a qualified model and can be put into use when the requirements are met, namely, the acquisition process of the target model is realized.
In the embodiment of the invention, a client accessing a target website is obtained firstly; judging whether the user is a login client or not; if yes, obtaining the user information of the login client; and training the information of the access user by combining the target model and the business processing rule based on the user information to obtain a recommendation result corresponding to the information of the access user. In addition, if the access client is a non-login client, recording the access address of the user; and acquiring a historical access record of the access address, and training access user information by combining the target model and the service processing rule based on the historical access record to acquire a recommendation result corresponding to the access user information.
S103, obtaining user access information, and training the access user information by combining the target model and the business processing rule to obtain a recommendation result corresponding to the access user information.
The service processing rule according to the embodiment of the present invention may include:
1. and judging whether the tourist is available or not according to the field of the APP participation or not.
2. No mobile field is guest:
a) reading a database according to user distint _ id (user identification) to obtain products browsed by a user within 90 days and sold by APP, and pushing the same products for products (in a product library but not in the sale) which do not meet the conditions;
b) reading the area personalized table to obtain products meeting the conditions;
c) reading the holiday theme table to obtain products meeting the conditions;
d) reading a hot pin table;
3. there is a mobile (phone number) field;
a) and calling the unified authentication interface by taking the mobile phone number as the input reference to acquire three elements, and calling the label system interface by taking the three elements as the input reference to judge whether the user is a marketer. (if the interface is not communicated, the process is judged to be not the marketer) whether the interface is the marketer or not is only distinguished by adding a layer of judgment whether the product can be pushed out or not when the product is recommended. Since the current product does not distinguish whether a recommendation is made to the marketer, the judgment of whether the marketer is exists but is not in effect.
b) Reading the database according to the mobile phone number of the user to obtain products which are browsed by the user within 90 days and sold by APP, and pushing the same products for products which do not meet the conditions (products which are sold but not sold in the product library)
c) Notching:
i. inquiring a database according to the mobile phone number of the user to obtain the age bracket and the gender label of the user,
if the information can not be obtained, the information is processed according to the tourists
Ps: the unified certification provides the user data to a big data platform in a form of T +1, and the user data is input into a database of the party by the party in a daily batch running mode.
Obtaining a list of recommendable risk categories that are consistent with the gender and age of the user
Querying a database according to the mobile phone number of the user to obtain dangerous seeds purchased by the user
Ps: the IDS feeds policy data to the big data platform in the form of T +1, and my party incorporates user data and policy data into my party database in the form of identity numbers by running batches each day.
Removing the user purchased the dangerous species.
And v, pushing the corresponding products for the user according to the priority of the remaining dangerous seeds and the priority of the products under each dangerous seed.
d) And (4) policy keeping reminding:
i. and inquiring a database according to the mobile phone number of the user to obtain the product purchased by the user.
Judging the product which is about to expire within 45 days and deducing the following:
e) the new product is judged according to the sale date of the sale plan.
f) Hot sales, holiday themes, regional personalization with visitors.
As shown in FIG. 4, the embodiment of the present invention relates to a presentation layer, which includes a product recommendation interface and a background management system; and an application layer, the component relates to a product recommendation interface, a management background and a model; the model layer is modified to comprise user label data, user behavior data, recommendation strategies and model training; and a base layer modified to include rights control, caching service, rule management, log service, product management, and user management; and a storage tier that is a role of data storage, including, for example, Mysql, Redis, big data platforms, and the like.
In one implementation, the method further comprises:
acquiring a recommendation result list according to the recommendation result;
and displaying the recommendation result list according to a preset display condition.
In one implementation manner, the step of obtaining a recommendation result list according to the recommendation result includes:
acquiring a recommendation score of each recommendation result;
and ranking according to the recommendation scores from high to low, and taking the recommendation results corresponding to the ranking sequence as a recommendation result list.
In one implementation, at the step of obtaining a trained target model, the method further includes:
and establishing labels for the target model, wherein the labels comprise but are not limited to a square type, a channel source, a browsing record, a page hotspot, a search history, access times, a staying time, information input, an access terminal, a browser version and a client IP.
In addition, as shown in fig. 5, the present invention also discloses an intelligent recommendation device 500, wherein the device 500 comprises a processor 510, and a memory 520 connected to the processor 510 through a communication bus 530; wherein the content of the first and second substances,
the memory 520 is used for storing an intelligent recommendation program;
the processor 510 is configured to execute the intelligent recommendation program to implement any of the intelligent recommendation steps.
And a computer storage medium storing one or more programs executable by one or more processors 510 as shown in FIG. 5 to cause the one or more processors 510 to perform any of the intelligent recommendation steps is disclosed.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. An intelligent recommendation method, characterized in that the method comprises:
obtaining historical user data, wherein the historical user data at least comprises: user behavior data and user tag data;
training a model based on the number of the historical users to obtain a trained target model;
and acquiring user access information, and training the access user information by combining the target model and the business processing rule to acquire a recommendation result corresponding to the access user information.
2. The intelligent recommendation method of claim 1, wherein the step of obtaining the user access information, training the access user information in combination with the target model and the business process rule to obtain the recommendation result corresponding to the access user information comprises:
acquiring a client accessing a target website;
judging whether the user is a login client or not;
if yes, obtaining the user information of the login client;
and training the information of the access user by combining the target model and the business processing rule based on the user information to obtain a recommendation result corresponding to the information of the access user.
3. The intelligent recommendation method of claim 2, wherein if the visiting client is a non-logged-on client, said method further comprises:
recording the access address of the user;
acquiring a historical access record of the access address;
and training the information of the access user by combining the target model and the business processing rule based on the historical access record to obtain a recommendation result corresponding to the information of the access user.
4. The intelligent recommendation method of any one of claims 1-3, wherein said step of obtaining historical user data comprises:
acquiring historical search information and historical reference information corresponding to a user according to account information corresponding to the user;
and acquiring historical user data according to the historical search information and the historical consulting information.
5. The intelligent recommendation method of claim 4, wherein the method further comprises:
acquiring a recommendation result list according to the recommendation result;
and displaying the recommendation result list according to a preset display condition.
6. The intelligent recommendation method of claim 5, wherein the step of obtaining a recommendation list according to the recommendation comprises:
acquiring a recommendation score of each recommendation result;
and ranking according to the recommendation scores from high to low, and taking the recommendation results corresponding to the ranking sequence as a recommendation result list.
7. The intelligent recommendation method of claim 1, wherein said step of obtaining historical user data comprises:
obtaining raw data of each user in historical users, wherein the raw data comprises user information, user behaviors, user historical insurance application and/or policy information;
and adding labels to the historical users according to the original acquisition, wherein the labels include but are not limited to: user attribute statistics, product purchase times, product purchase trends, complaint times, channel use frequency and service use frequency.
8. The intelligent recommendation method of claim 2, wherein, at said step of obtaining a trained target model, said method further comprises:
and establishing labels for the target model, wherein the labels comprise but are not limited to a square type, a channel source, a browsing record, a page hotspot, a search history, access times, a staying time, information input, an access terminal, a browser version and a client IP.
9. An intelligent recommendation device, characterized in that the device comprises a processor and a memory connected with the processor through a communication bus; wherein the content of the first and second substances,
the memory is used for storing the intelligent recommendation program;
the processor is used for executing the intelligent recommendation program to realize the intelligent recommendation steps of any one of claims 1 to 8.
10. A computer storage medium, characterized in that the computer storage medium stores one or more programs executable by one or more processors to cause the one or more processors to perform the intelligent recommendation step of any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010583898.5A CN111538910A (en) | 2020-06-23 | 2020-06-23 | Intelligent recommendation method and device and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010583898.5A CN111538910A (en) | 2020-06-23 | 2020-06-23 | Intelligent recommendation method and device and computer storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111538910A true CN111538910A (en) | 2020-08-14 |
Family
ID=71979778
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010583898.5A Pending CN111538910A (en) | 2020-06-23 | 2020-06-23 | Intelligent recommendation method and device and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111538910A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112102095A (en) * | 2020-09-17 | 2020-12-18 | 中国建设银行股份有限公司 | Fund product recommendation method, device and equipment |
CN112488854A (en) * | 2020-11-20 | 2021-03-12 | 中国人寿保险股份有限公司 | Service manager personalized recommendation method and related equipment |
CN112561709A (en) * | 2020-11-30 | 2021-03-26 | 泰康保险集团股份有限公司 | Product information method, device, equipment and medium |
CN112561565A (en) * | 2020-11-27 | 2021-03-26 | 四川新网银行股份有限公司 | User demand identification method based on behavior log |
CN112925988A (en) * | 2021-01-28 | 2021-06-08 | 广州大学华软软件学院 | Intelligent gift area recommendation method and device |
CN113256401A (en) * | 2021-05-26 | 2021-08-13 | 中科柏诚科技(北京)股份有限公司 | Method, device, server and storage medium for intercepting user outside pre-loan domain |
CN114048104A (en) * | 2021-11-24 | 2022-02-15 | 国家电网有限公司大数据中心 | Monitoring method, device, equipment and storage medium |
CN117539638A (en) * | 2024-01-04 | 2024-02-09 | 江西拓荒者科技有限公司 | Data processing method and system for industrial big data platform |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术(北京)有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
CN102799662A (en) * | 2012-07-10 | 2012-11-28 | 北京奇虎科技有限公司 | Method, device and system for recommending website |
CN109165983A (en) * | 2018-09-04 | 2019-01-08 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
CN110399559A (en) * | 2019-07-26 | 2019-11-01 | 阳光保险集团股份有限公司 | Intelligence insurance recommender system and computer storage medium |
CN110598109A (en) * | 2019-09-16 | 2019-12-20 | 上海喜马拉雅科技有限公司 | Information recommendation method, device, equipment and storage medium |
CN111125512A (en) * | 2019-11-18 | 2020-05-08 | 口碑(上海)信息技术有限公司 | Service recommendation processing method, device and system |
-
2020
- 2020-06-23 CN CN202010583898.5A patent/CN111538910A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术(北京)有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
CN102799662A (en) * | 2012-07-10 | 2012-11-28 | 北京奇虎科技有限公司 | Method, device and system for recommending website |
CN109165983A (en) * | 2018-09-04 | 2019-01-08 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
CN110399559A (en) * | 2019-07-26 | 2019-11-01 | 阳光保险集团股份有限公司 | Intelligence insurance recommender system and computer storage medium |
CN110598109A (en) * | 2019-09-16 | 2019-12-20 | 上海喜马拉雅科技有限公司 | Information recommendation method, device, equipment and storage medium |
CN111125512A (en) * | 2019-11-18 | 2020-05-08 | 口碑(上海)信息技术有限公司 | Service recommendation processing method, device and system |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112102095A (en) * | 2020-09-17 | 2020-12-18 | 中国建设银行股份有限公司 | Fund product recommendation method, device and equipment |
CN112488854A (en) * | 2020-11-20 | 2021-03-12 | 中国人寿保险股份有限公司 | Service manager personalized recommendation method and related equipment |
CN112488854B (en) * | 2020-11-20 | 2023-09-26 | 中国人寿保险股份有限公司 | Personalized recommendation method for service manager and related equipment |
CN112561565A (en) * | 2020-11-27 | 2021-03-26 | 四川新网银行股份有限公司 | User demand identification method based on behavior log |
CN112561709A (en) * | 2020-11-30 | 2021-03-26 | 泰康保险集团股份有限公司 | Product information method, device, equipment and medium |
CN112561709B (en) * | 2020-11-30 | 2024-02-02 | 泰康保险集团股份有限公司 | Product information method, device, equipment and medium |
CN112925988A (en) * | 2021-01-28 | 2021-06-08 | 广州大学华软软件学院 | Intelligent gift area recommendation method and device |
CN113256401A (en) * | 2021-05-26 | 2021-08-13 | 中科柏诚科技(北京)股份有限公司 | Method, device, server and storage medium for intercepting user outside pre-loan domain |
CN114048104A (en) * | 2021-11-24 | 2022-02-15 | 国家电网有限公司大数据中心 | Monitoring method, device, equipment and storage medium |
CN117539638A (en) * | 2024-01-04 | 2024-02-09 | 江西拓荒者科技有限公司 | Data processing method and system for industrial big data platform |
CN117539638B (en) * | 2024-01-04 | 2024-03-22 | 江西拓荒者科技有限公司 | Data processing method and system for industrial big data platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111538910A (en) | Intelligent recommendation method and device and computer storage medium | |
US10769358B2 (en) | Obtaining data from incomplete electronic forms | |
CN107864301B (en) | Client label management method, system, computer equipment and storage medium | |
WO2020243894A1 (en) | Advertisement recommending method and apparatus, and electronic device | |
US20090028183A1 (en) | Platform for communicating across multiple communication channels | |
CN109388548B (en) | Method and apparatus for generating information | |
US10318546B2 (en) | System and method for test data management | |
KR102084719B1 (en) | Sales forecast information providing system | |
CN107977678A (en) | Method and apparatus for output information | |
US9460163B1 (en) | Configurable extractions in social media | |
US20240152972A1 (en) | Marketing to consumers using data obtained from abandoned gps searches | |
US11295326B2 (en) | Insights on a data platform | |
US20210232971A1 (en) | Data meta-model based feature vector set generation for training machine learning models | |
KR20100123206A (en) | Method and apparatus for ranking analysis based on artificial intelligence, and recording medium thereof | |
CN105450460B (en) | Network operation recording method and system | |
KR102341488B1 (en) | The online shopping mall platform connected with influencer site | |
US10628806B2 (en) | System and method for test data provisioning | |
CN107230094B (en) | Page information processing method and device | |
CN111260489A (en) | Product information display method and device, storage medium and electronic device | |
US10636052B2 (en) | Automatic mass scale online promotion testing | |
KR20200097544A (en) | Platform system for resellers in contents curation marketing | |
CN114969523A (en) | User behavior data-based label and push strategy management method, device and medium | |
US11521225B1 (en) | System and method for vehicle loan lead generation | |
CN113539423A (en) | Intelligent online detection system for dieticians | |
CN117455579B (en) | Commodity recommendation intervention method, commodity recommendation intervention device, medium and equipment |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200814 |
|
RJ01 | Rejection of invention patent application after publication |