CN115048569A - Method, device and equipment for accurately recommending big data and storage medium - Google Patents
Method, device and equipment for accurately recommending big data and storage medium Download PDFInfo
- Publication number
- CN115048569A CN115048569A CN202210098233.4A CN202210098233A CN115048569A CN 115048569 A CN115048569 A CN 115048569A CN 202210098233 A CN202210098233 A CN 202210098233A CN 115048569 A CN115048569 A CN 115048569A
- Authority
- CN
- China
- Prior art keywords
- data
- recommendation
- user set
- user
- acquiring
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of big data advertisement recommendation, and discloses a method, a device, equipment and a storage medium for accurately recommending big data, wherein the method comprises the following steps: the method comprises the steps that historical behavior data of a user are obtained through responding to a client, and the historical behavior data are subjected to first data processing through a lookelike audience orientation algorithm to establish a similar user set; acquiring the click rate of the feature vector advertisement, and calculating the association degree of the click rate by using an Apriori algorithm to obtain an association degree data set; grading the association degree data set to obtain a high association degree data set; and acquiring a high-association data set, providing product promotion service and product recommendation service for a target user set in the high-association data set, and realizing accurate recommendation of users. The conversion of accurate recommendation effect can be effectively improved, the member renewal effect driven by recommendation is improved, the member activation effect driven by recommendation is improved, and the increase effect of the volume of the loose order orders driven by recommendation is improved.
Description
Technical Field
The invention relates to the technical field of big data advertisement recommendation, in particular to a method, a device, equipment and a storage medium for accurately recommending big data.
Background
At present, the existing recommendation activities are carried out indiscriminately for all users, and different recommendation activities are not designed for different user groups, so that different recommendation purposes are achieved, and different requirements of the users are met; at present, with the continuous development of electronic commerce and the continuous improvement of a logistics transportation system, more and more users select online consumption, but due to the fact that the category attributes, interests and hobbies, the receiving levels and the like of the clients are different, large-range universal advertisement sending recommendation is determined, but advertisement sending is not accurate, accurate recommendation cannot be achieved, the sale recommendation return rate is low easily, and the cost is high; with the continuous improvement of big data technology, how to perfectly combine big data technology and recommendation to realize accurate recommendation so as to improve the purchasing experience and purchasing loyalty of customers, and become the key point of current client recommendation research; therefore, it becomes important to invent a recommendation system based on big data.
Disclosure of Invention
In view of this, it is necessary to provide a method, an apparatus, a device, and a storage medium for accurately recommending big data, which are used for solving the problems that advertisement sending is not accurate, accurate recommendation cannot be realized, the return rate of sales recommendation is low, and cost is high.
A big data accurate recommendation method, device, equipment and storage medium comprise the following steps: a big data accurate recommendation method is applied to a client side and comprises the following steps: responding to a client, acquiring historical behavior data of a user, and performing first data processing on the historical behavior data through a lookelike audience orientation algorithm to establish a similar user set; acquiring the similar user set, and performing second data processing on the similar user set by using a RALM algorithm to acquire a recommended user set; acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set; acquiring the target user set, and sending a corresponding feature vector advertisement to the target user set by using the client; responding to the client, obtaining the click rate of the feature vector advertisement, and calculating the association degree of the click rate by using an Apriori algorithm to obtain an association degree data set; grading the association degree data set to obtain a high association degree data set; and acquiring the high-association-degree data set, providing product promotion service and product recommendation service for a target user set in the high-association-degree data set, and realizing accurate recommendation of users.
In one embodiment, the responding to the client obtains historical behavior data of the user, and performs first data processing on the historical behavior data through a lookelike audience targeting algorithm, and the establishing of the similar user set includes: acquiring the historical behavior data, and performing data integration by using the historical behavior data to obtain a user portrait; displaying crowd expansion based on the user portrait to obtain a seed user label, wherein the user label comprises: geography, interests, behaviors, brand preferences, etc.; scoring the seed user tags by utilizing a collaborative filtering recommendation algorithm, calculating the similarity of the seed user tags, and finding out a neighboring set of the seed user tags; and weighting the adjacent set to obtain the similar user set.
In one embodiment, the obtaining the similar user set and performing the second data processing on the similar user set by using a RALM algorithm to obtain a recommended user set includes: acquiring the similar user set and a non-similar user set in the client, wherein the similar user set is used as a positive sample, and the non-similar user set is used as a negative sample; and inputting the positive sample and the negative sample into a preset RAMM algorithm model for training to obtain a recommended user set.
In one embodiment, before the obtaining the target user set and sending, by using the client, a corresponding feature vector advertisement to the target user set, the method further includes: acquiring the target user set, acquiring user candidate labels of the target user set, and performing nonlinear mapping on the user candidate labels to obtain a plurality of user characteristic labels; classifying the user feature tags to obtain a plurality of classification results, normalizing the classification results to obtain feature vector data, and sending an advertisement to the feature vector data as the feature vector advertisement.
In one embodiment, the response to the client side obtains the click rate of the feature vector advertisement, and calculates the relevance of the click rate by using Apriori algorithm to obtain a relevance data set; and the grade division is carried out on the association degree data set, and the step of obtaining the high association degree data set comprises the following steps: responding to a client, acquiring the click rate and the feature vector of the feature vector advertisement, respectively making the click rate and the feature vector of the feature vector advertisement into databases X and Y, and calculating a minimum support degree threshold value Q; retrieving all frequent item sets in the database through continuous iteration to obtain the association degree data set; and carrying out grade division on the association degree data set, dividing the association degree data set into a high grade, a medium grade and a low grade, and acquiring the high association degree data set.
In one embodiment, the obtaining the high association degree data set, and providing a product promotion service and a product recommendation service for a target user set in the high association degree data set, and implementing user accurate recommendation includes: acquiring a target user in the high-association-degree data set, and making a recommendation strategy for the target user, wherein the recommendation strategy comprises the following steps: touch manner, delivery channel, push time, push address, recommendation rights and interests and the like; and providing the promotion service and the product recommendation service for the target user by using the recommendation strategy to realize accurate recommendation of the user.
A second embodiment of the present invention provides an accurate big data recommendation apparatus, including: the first data processing module is used for responding to the client, acquiring historical behavior data of the user, performing first data processing on the historical behavior data through a lookelike audience orientation algorithm, and establishing a similar user set; the second data processing module is used for acquiring the similar user set, and performing second-time data processing on the similar user set by using an RALM algorithm to acquire a recommended user set; the third data processing module is used for acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to acquire a target user set;
the sending module is used for obtaining the target user set and sending the corresponding feature vector advertisement to the target user set by utilizing the client; the association module is used for responding to the client, acquiring the click rate of the feature vector advertisement and calculating the association degree of the click rate by using an Apriori algorithm to obtain an association degree data set; grading the association degree data set to obtain a high association degree data set; and the accurate recommendation module is used for acquiring the high-association data set, providing product promotion service and product recommendation service for a target user set in the high-association data set, and realizing accurate recommendation of users.
In a second embodiment, the first data processing module further includes an obtaining sub-module, configured to obtain the historical behavior data, perform data integration using the historical behavior data, and obtain a user image; based on user portrait shows that the crowd that shows expands, obtains seed user label, user label includes: geography, interests, behavior, brand preferences, etc. The calculation submodule is used for scoring the seed user tags by utilizing a collaborative filtering recommendation algorithm, calculating the similarity of the seed user tags and finding out a neighboring set of the seed user tags; and the weighting submodule is used for weighting the adjacent set to obtain the similar user set.
In a second embodiment, the second data processing module further includes an obtaining sub-module, configured to obtain the similar user set and a non-similar user set in the client, where the similar user set is used as a positive sample and the non-similar user set is used as a negative sample; and the training submodule is used for inputting the positive sample and the negative sample into a preset RAMM algorithm model for training to obtain a recommended user set.
In a second embodiment, the sending module further includes an obtaining sub-module, configured to obtain the target user set, obtain user candidate tags of the target user set, and perform nonlinear mapping on the user candidate tags to obtain a plurality of user feature tags; and the classification submodule is used for classifying the user feature tags to obtain a plurality of classification results, normalizing the classification results to obtain feature vector data, and sending advertisements to the feature vector data to obtain the feature vector advertisements.
In a second embodiment, the association module further includes a response sub-module, configured to respond to a client, obtain the feature vector advertisement click rate and the feature vector, make the feature vector and the feature vector advertisement click rate into databases X and Y, respectively, and calculate a minimum support degree threshold Q; the iteration submodule is used for retrieving all frequent item sets in the database through continuous iteration to obtain the association degree data set; and the dividing module is used for carrying out grade division on the association degree data set into a high grade, a medium grade and a low grade and acquiring the high association degree data set.
In a second embodiment, the accurate recommendation module further includes a formulating sub-module, configured to obtain a target user in the high-relevancy data set, and formulate a recommendation policy for the target user, where the recommendation policy includes: touch mode, delivery channel, push time, push address, recommendation rights and interests, etc.; and the providing sub-module is used for providing the promotion service and the product recommendation service for the target user by using the recommendation strategy so as to realize accurate recommendation of the user.
A third embodiment of the present invention provides a big data accurate recommendation device, including: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line.
The at least one processor calls the instructions in the memory to enable the big data precision recommendation device to execute the steps of the big data precision recommendation method.
A fourth embodiment of the present invention provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to perform the steps of the above-mentioned big data precision recommendation method.
According to the big data accurate recommendation method, the big data accurate recommendation device, the big data accurate recommendation equipment and the big data accurate recommendation storage medium, historical behavior data of a user are obtained by responding to a client, and the historical behavior data are subjected to first data processing through a lookelike audience orientation algorithm to establish a similar user set; acquiring the similar user set, and performing secondary data processing on the similar user set by using an RALM algorithm to acquire a recommended user set; acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set; acquiring the target user set, and sending a corresponding feature vector advertisement to the target user set by using the client; responding to the client, acquiring the click rate of the feature vector advertisement, and calculating the relevance of the click rate by using an Apriori algorithm to obtain a relevance data set; grading the association degree data set to obtain a high association degree data set; and acquiring the high-association data set, providing product promotion service and product recommendation service for a target user set in the high-association data set, and realizing accurate user recommendation. The conversion of accurate recommendation effect can be effectively improved, the member renewal effect driven by recommendation is improved, the member activation effect driven by recommendation is improved, and the increase effect of the volume of the scattered order driven by recommendation is improved.
Drawings
FIG. 1 is a schematic diagram of a first embodiment of a big data accurate recommendation method according to the present invention;
FIG. 2 is a schematic diagram of a second embodiment of a big data precision recommendation method according to the present invention;
FIG. 3 is a schematic diagram of a third embodiment of a big data accurate recommendation method according to the present invention;
FIG. 4 is a schematic diagram of a big data precision recommendation device according to a first embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of a big data precision recommendation device according to the present invention.
Detailed Description
The embodiment of the invention provides a big data accurate recommendation method, a big data accurate recommendation device, big data accurate recommendation equipment and a big data accurate recommendation storage medium, wherein historical behavior data of a user are obtained by responding to a client, and similar user sets are established by performing first data processing on the historical behavior data through a lookelike audience orientation algorithm; acquiring the similar user set, and performing second data processing on the similar user set by using a RALM algorithm to acquire a recommended user set; acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set; acquiring the target user set, and sending a corresponding feature vector advertisement to the target user set by using the client; responding to the client, acquiring the click rate of the feature vector advertisement, and calculating the relevance of the click rate by using an Apriori algorithm to obtain a relevance data set; grading the association degree data set to obtain a high association degree data set; and acquiring the high-association-degree data set, providing product promotion service and product recommendation service for a target user set in the high-association-degree data set, and realizing accurate recommendation of users. The conversion of accurate recommendation effect can be effectively improved, the member renewal effect driven by recommendation is improved, the member activation effect driven by recommendation is improved, and the increase effect of the volume of the loose order orders driven by recommendation is improved.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a specific flow of an embodiment of the present invention is described below, and referring to fig. 1, a first embodiment of a method for accurately recommending big data in an embodiment of the present invention includes:
In this embodiment, before a client or a system accurately recommends an advertisement for a client, historical behavior data of a user needs to be obtained first, the historical behavior data may be filtered through a user portrait tag to obtain a seed user tag, where the filtering tag includes but is not limited to: geography, interests, behaviors, brand preferences, etc.; scoring the seed user tags by using a collaborative filtering recommendation algorithm, calculating the similarity of the seed user tags, and finding out a neighboring set of the seed user tags; and expanding the seed users based on the near set, and obtaining a similar user set after expansion.
Specifically, the client is a logistics address input system developed based on Android and iOS programming languages. The client is at least one of a mobile terminal, a WeChat terminal, an android terminal and an ios terminal; optionally, the client, or referred to as a mobile phone client, refers to a program corresponding to the server and providing local services to the client. Except for some application programs which only run locally, the application programs are generally installed on a common mobile phone and need to be operated with a server side. The more common mobile phone clients include a web browser used in the web, an email client for receiving and sending emails, and client software for instant messaging. For this kind of application, a corresponding server and a corresponding service program are required in the network to provide corresponding services, such as database services, e-mail services, etc., so that a specific communication connection needs to be established between the client and the server to ensure the normal operation of the application program.
And 102, acquiring a similar user set, and performing secondary data processing on the similar user set by using a RAMM algorithm to obtain a recommended user set.
In this embodiment, after obtaining the similar user set, the client needs to screen and locate the similar users to obtain a more accurate recommended user set, where the recommended user set is a preselected population recommended by the advertisement, and if the client needs to perform a large number of indiscriminate advertisement deliveries, the recommended user set may be selected for advertisement delivery. The recommended user set is further screened by utilizing a RAMM algorithm for similar user sets, and the screened user portrait labels are uniform.
And 103, acquiring a recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set.
In this embodiment, after the client or the system obtains the recommended user set, advertisement recommendation needs to be performed more accurately, and then data screening is performed on the recommended user set for the third time. And thirdly, data screening, namely, calculating the Top-N of the recommended user set by using a Top-N sorting algorithm, wherein the TOP-N analysis method is a method for obtaining N required data from a research object by using the TOP-N algorithm and performing key analysis on the N data.
Specifically, the recommended user set data is locally processed, for example, the number Top-N of the occurrence of words is calculated, the number of times of the words in each region can be locally counted, the temporary file is rewritten, and then the data is merged, Top-N is also a method that recommended user set data is independently calculated according to keys, the regions are partitioned according to keys, for example, the statistical total number of the regions is directly obtained according to the words, and the processing mode is similar to storm. Top-n can be reversely derived from satisfying sufficient requirements to obtain some limiting conditions of the target user, so as to filter out data, reduce data volume, and gradually converge on a target user characteristic range T, where the characteristic range T is a range preset by the system, including but not limited to: age, gender, height, weight, hobbies, etc. which can be used for accurate recommendation by using the Top-N ranking algorithm to obtain the target user set.
And 104, acquiring a target user set, and sending corresponding feature vector advertisements to the target user set by using the client.
In this embodiment, after the client obtains the target user set, the feature vector advertisement specific to the user may be sent to the target user set. Firstly, a client acquires a plurality of portrait label feature vectors corresponding to portrait label features of a user; generating a first similarity coefficient between every two portrait label feature vectors and all portrait label feature vectors; summing the first similarity coefficient corresponding to the feature vector of each portrait label to obtain a second similarity coefficient; and selecting the image label feature vector corresponding to the second similarity coefficient which is not more than the similarity coefficient threshold value from the plurality of image label feature vectors. The system analyzes the portrait label feature vector and puts in advertisements with higher threshold similarity with the portrait label feature vector.
In this embodiment, after the corresponding feature vector advertisement is delivered, the system first obtains the user click rate of the feature vector advertisement, and calculates the relevance degree of the user click rate by using Apriori algorithm, and first finds out all the user click rates, where the occurrence frequency of the user click rates is at least as high as the predefined minimum support degree. Strong association rules are then generated by the user click-through rate, which must satisfy a minimum support and a minimum confidence level. The user click rate found in step 1 is then used to generate the desired rules, generating all rules that contain only the terms of the set, with only one term in the right part of each rule, and the definition of the medium rule is used here. Once these rules are generated, only those rules that are greater than the minimum confidence given by the system are left to obtain the relevancy data set, and in order to generate all relevancy data sets, the system uses a recursive approach.
The system carries out grade division on the association degree data set, and the association degree data set is divided into association degree data sets of a high grade, a medium grade and a low grade after the grade division, wherein the high association degree data set is a key data set of the invention.
The Apriori algorithm is the first association rule mining algorithm, which uses an iterative method of layer-by-layer search to find out the relationships of item sets in a database to form rules, and the process of the algorithm consists of connection (class matrix operation) and pruning (removing unnecessary intermediate results). The concept of a set of terms in the algorithm is a set of terms. The set of K terms is a set of K terms. The frequency of occurrence of a set of items is the number of transactions that contain the set of items, referred to as the frequency of the set of items. If a certain item set meets the minimum support, it is called a frequent item set.
And 106, acquiring the high-association data set, providing product promotion service and product recommendation service for the target user set in the high-association data set, and realizing accurate recommendation of the user.
In this embodiment, after the system obtains the high-association data set, the system makes a recommendation policy for a target user in the high-association data set, where the recommendation policy includes, but is not limited to: the crowd can accurately reach the system in a contact mode, a delivery channel, a delivery time, a delivery address, a recommendation right and the like by means of short messages, WeChat template messages, WeChat service notifications, pay-for-payment notifications, app notifications, application popup windows and the like; the contact points are spread based on pain points of the users, and for example, the users who do not leave orders for a long time (lost users) can achieve user conversion by actively sending discount in a group mode; or the user is not ordered in time for ordering the ordering link; access is recommended for discount sensitive users. For the complaining user, the customer service discount is compensated in time; or the shopping guide personnel issues special preference to the bound inventory user, and finally the conversion of the order is realized. Or post special recommendation two-dimensional code on to express delivery package, express delivery car, provide the user surprise. All the touch scene actions are labeled, and continuous recommendation is facilitated.
And (4) recommending channels: multiple channels are connected in a butt joint mode, and the uniform recommendation of the coupon channels is realized; the recommendation strategy is created, the recommendation channels are bound, channel-specific two-dimensional codes or access links are generated, user access links of different channels are generated, and users meeting the conditions are accurately recommended through oneid. The recommendation channel is closely related to the recommendation contact; an online + offline channel; the online channel mainly comprises an own application channel and a different industry union channel, wherein the different industry channel needs to be connected with the offline channel through a system layer (such as coupon issuing, verification and marketing connection, point exchange connection and the like) and mainly depends on website + operator channel release (such as website-specific recommendation codes and operator-specific recommendation codes).
Recommending targets and strategies: determining recommendation cost and a recommendation target, creating a recommendation strategy, selecting a crowd, selecting an automatic recommendation strategy (for example, executing a strategy recommendation interest a when the crowd A reaches a condition 1 and executing a recommendation interest b when the crowd A reaches a condition 2), selecting a reach mode and a delivery channel; the automatic recommended release crowd accounts for core elements, such as discount sensitive user definition (the frequency of using preferential order placing is higher than the frequency of normal order placing), and accurate pushing is carried out by analyzing user behaviors according to user order placing time periods and dates to judge the time period when the user obtains the highest activity conversion rate, so that invalid recommendation touch is avoided. Or the user attention points are analyzed by analyzing the activity page embedded point record user behavior, so that the accurate delivery is carried out, and the like. The recommendation strategy is utilized to put the advertisements to the target users, so that the conversion rate of the advertisements can be increased, and accurate recommendation of the users is realized.
In the implementation of the invention, the historical behavior data of a user is obtained by responding to a client, and the historical behavior data is subjected to first data processing by a lookelike audience orientation algorithm to establish a similar user set; acquiring the similar user set, and performing second data processing on the similar user set by using a RALM algorithm to acquire a recommended user set; acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set; acquiring the target user set, and sending a corresponding feature vector advertisement to the target user set by using the client; responding to the client, acquiring the click rate of the feature vector advertisement, and calculating the click rate by using an Apriori algorithm to obtain an association degree data set; grading the association degree data set to obtain a high association degree data set; and acquiring the high-association-degree data set, providing product promotion service and product recommendation service for a target user set in the high-association-degree data set, and realizing accurate recommendation of users. The accurate recommendation effect conversion can be effectively improved, the recommendation-driven member renewing effect is improved, the recommendation-driven member activating effect is improved, and the recommendation-driven increase effect of the volume of the order orders scattered is improved.
Referring to fig. 2, a second embodiment of the method for accurately recommending big data according to the embodiment of the present invention includes:
In this embodiment, after the client or the system acquires the similar user set, the non-similar user set is also collected, and the similar user set is used as a positive sample and the non-similar user set is used as a negative sample to perform calculation and sampling.
And 203, inputting the positive sample and the negative sample into a preset RAMM algorithm model for training to obtain a recommended user set.
In the embodiment, the similar user set and the dissimilar user set are respectively used as a positive sample and a negative sample, and are input into a preset RALM algorithm for training to obtain a recommended user set, wherein the RALM algorithm is a nonlinear optimization method between a Newton method and a gradient descent method, is insensitive to an over-parameterization problem, can effectively process a redundant parameter problem, and greatly reduces the chance of trapping a cost function into a local minimum value, and the characteristics enable the LM algorithm to be widely applied in the fields of computer vision and the like.
And 204, acquiring a recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set.
And 205, acquiring a target user set, and sending a corresponding feature vector advertisement to the target user set by using the client.
And step 207, acquiring the high-association-degree data set, providing product promotion service and product recommendation service for the target user set in the high-association-degree data set, and realizing accurate user recommendation.
Steps 204-207 in this embodiment are similar to steps 103-106 in the first embodiment, and step 201 is similar to step 101, which are not described again.
In the implementation of the invention, historical behavior data of a user is obtained by responding to a client, and the historical behavior data is subjected to first data processing by a lookelike audience orientation algorithm to establish a similar user set; acquiring the similar user set, and performing second data processing on the similar user set by using a RALM algorithm to acquire a recommended user set; acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set; acquiring the target user set, and sending a corresponding feature vector advertisement to the target user set by using the client; responding to the client, acquiring the click rate of the feature vector advertisement, and calculating the click rate by using an Apriori algorithm to obtain an association degree data set; grading the association degree data set to obtain a high association degree data set; and acquiring the high-association-degree data set, providing product promotion service and product recommendation service for a target user set in the high-association-degree data set, and realizing accurate recommendation of users. The conversion of accurate recommendation effect can be effectively improved, the member renewal effect driven by recommendation is improved, the member activation effect driven by recommendation is improved, and the increase effect of the volume of the loose order orders driven by recommendation is improved.
Referring to fig. 3, a third embodiment of the method for accurately recommending big data according to the embodiment of the present invention includes:
And 302, acquiring a similar user set, and performing secondary data processing on the similar user set by using an RALM algorithm to acquire a recommended user set.
And 303, acquiring a recommended user set, and performing third-time data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set.
And 304, acquiring a target user set, and sending a corresponding feature vector advertisement to the target user set by using the client.
In this embodiment, after the client or the system obtains the click rate of the feature vector advertisement, the feature vector advertisement and the click rate are respectively made into a database X and a database Y, and a minimum support degree threshold Q of the feature vector advertisement on the click rate is calculated in the database X, Y, where the threshold Q is a range defined by the client or the system.
And step 306, retrieving all frequent item sets in the database through continuous iteration to obtain a relevancy data set.
In this embodiment, by continuously calculating the support degree threshold Q of the feature vector advertisement and the click rate, the frequent item set with the most frequent click in the database Y is retrieved, so that the association degree data set is obtained.
And 307, carrying out grade division on the association degree data set into three grades of high grade, medium grade and low grade, and acquiring the high association degree data set.
In this embodiment, the client or the system collects and completes the association degree data set, and divides the association degree data set into three levels, namely, high, medium and low, where the high association degree data set is an important data set in the present invention.
And 308, acquiring a high-association data set, providing product promotion service and product recommendation service for a target user set in the high-association data set, and realizing accurate recommendation of users.
The steps 301-304 in the present embodiment are similar to the steps 101-104 in the first embodiment, and the step 309 is similar to the step 106, which will not be described herein again.
In the implementation of the invention, the historical behavior data of a user is obtained by responding to a client, and the historical behavior data is subjected to first data processing by a lookelike audience orientation algorithm to establish a similar user set; acquiring the similar user set, and performing second data processing on the similar user set by using a RALM algorithm to acquire a recommended user set; acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set; acquiring the target user set, and sending a corresponding feature vector advertisement to the target user set by using the client; responding to the client, obtaining the click rate of the feature vector advertisement, and calculating the relevance of the click rate by using an Apriori algorithm to obtain a relevance data set; grading the association degree data set to obtain a high association degree data set; and acquiring the high-association-degree data set, providing product promotion service and product recommendation service for a target user set in the high-association-degree data set, and realizing accurate user recommendation. The conversion of accurate recommendation effect can be effectively improved, the member renewal effect driven by recommendation is improved, the member activation effect driven by recommendation is improved, and the increase effect of the volume of the loose order orders driven by recommendation is improved.
The above description of the method for accurately recommending big data in the embodiment of the present invention, and the following description of the apparatus for accurately recommending big data in the embodiment of the present invention, please refer to fig. 4, where a first embodiment of the apparatus for accurately recommending big data in the embodiment of the present invention includes:
the first data processing module 401 is configured to respond to the client, obtain historical behavior data of the user, perform first data processing on the historical behavior data through a lookup alike audience targeting algorithm, and establish a similar user set.
And a second data processing module 402, configured to obtain the similar user set, and perform second data processing on the similar user set by using a RALM algorithm to obtain a recommended user set.
And the third data processing module 403 is configured to obtain the recommended user set, and perform third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set.
A sending module 404, configured to obtain the target user set, and send, by using the client, a corresponding feature vector advertisement to the target user set.
The association module 405 is configured to respond to the client, acquire the click rate of the feature vector advertisement, and calculate an association degree of the click rate by using an Apriori algorithm to obtain an association degree data set; and carrying out grade division on the association degree data set to obtain a high association degree data set.
And the accurate recommendation module 406 is configured to obtain the high-association data set, provide product promotion services and product recommendation services for a target user set in the high-association data set, and implement accurate recommendation for a user.
In the embodiment of the invention, historical behavior data of a user is obtained by responding to a client, and the historical behavior data is subjected to first data processing by a lookelike audience orientation algorithm to establish a similar user set; acquiring the similar user set, and performing second data processing on the similar user set by using a RALM algorithm to acquire a recommended user set; acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set; acquiring the target user set, and sending a corresponding feature vector advertisement to the target user set by using the client; responding to the client, acquiring the click rate of the feature vector advertisement, and calculating the click rate by using an Apriori algorithm to obtain an association degree data set; grading the association degree data set to obtain a high association degree data set; and acquiring the high-association-degree data set, providing product promotion service and product recommendation service for a target user set in the high-association-degree data set, and realizing accurate recommendation of users. The conversion of accurate recommendation effect can be effectively improved, the member renewal effect driven by recommendation is improved, the member activation effect driven by recommendation is improved, and the increase effect of the volume of the loose order orders driven by recommendation is improved.
Fig. 4 describes the big data precision recommendation device in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the big data precision recommendation device in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a big data precision recommendation device 800 according to an embodiment of the present invention, where the big data precision recommendation device 800 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 810 (e.g., one or more processors) and a memory 820, one or more storage media 830 (e.g., one or more mass storage devices) storing an application 833 or data 832. Memory 820 and storage medium 830 may be, among other things, transitory or persistent storage. The program stored in the storage medium 830 may include one or more modules (not shown), and each module may include a series of instruction operations in the big data precision recommendation apparatus 800. Further, the processor 810 may be configured to communicate with the storage medium 830, and execute a series of instruction operations in the storage medium 830 on the big data precision recommendation device 800.
The big data precision recommendation device 800 may also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input-output interfaces 860, and/or one or more operational clients 831, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the configuration of the big data precision recommendation device illustrated in fig. 5 does not constitute a limitation of the big data precision recommendation device provided herein, and may include more or less components than those illustrated, or combine certain components, or arrange different components.
The big data accurate recommendation device is used for realizing the following big data accurate recommendation method, and specifically comprises the following steps: the big data accurate recommendation method is applied to a client, and comprises the following steps: responding to a client, acquiring historical behavior data of a user, and performing first data processing on the historical behavior data through a lookelike audience orientation algorithm to establish a similar user set; acquiring a similar user set, and performing second data processing on the similar user set by using a RAMM algorithm to obtain a recommended user set; acquiring a recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set; acquiring a target user set, and sending a corresponding feature vector advertisement to the target user set by using a client; responding to a client, obtaining the click rate of the feature vector advertisement, and calculating the association degree of the click rate by using an Apriori algorithm to obtain an association degree data set; grading the association degree data set to obtain a high association degree data set; and acquiring a high-association data set, providing product promotion service and product recommendation service for a target user set in the high-association data set, and realizing accurate user recommendation.
In an embodiment, in a first implementation manner of the first aspect of the present invention, the obtaining, in response to the client, historical behavior data of the user, and performing first data processing on the historical behavior data through a lookelike audience targeting algorithm, and creating a similar user set includes: acquiring the historical behavior data, and performing data integration by using the historical behavior data to obtain a user image; displaying crowd expansion based on the user portrait to obtain a seed user label, wherein the user label comprises: geography, interests, behavior, brand preferences, etc.; scoring the seed user tags by utilizing a collaborative filtering recommendation algorithm, calculating the similarity of the seed user tags, and finding out a neighboring set of the seed user tags; and weighting the adjacent set to obtain the similar user set.
In an embodiment, in a second implementation manner of the first aspect of the present invention, the obtaining the similar user set and performing a second data processing on the similar user set by using a RALM algorithm to obtain a recommended user set includes: acquiring the similar user set and a non-similar user set in the client, and taking the similar user set as a positive sample and the non-similar user set as a negative sample; and inputting the positive sample and the negative sample into a preset RALM algorithm model for training to obtain a recommended user set.
In an embodiment, in a third implementation manner of the first aspect of the present invention, before the obtaining the target user set and sending, by the client, a corresponding feature vector advertisement to the target user set, the method further includes: acquiring the target user set, acquiring user candidate labels of the target user set, and performing nonlinear mapping on the user candidate labels to obtain a plurality of user characteristic labels; classifying the user feature tags to obtain a plurality of classification results, normalizing the classification results to obtain feature vector data, and sending an advertisement to the feature vector data to obtain the feature vector advertisement.
In an embodiment, in a fourth implementation manner of the first aspect of the present invention, the obtaining the high-association data set, and providing a product promotion service and a product recommendation service for a target user set in the high-association data set, and implementing user precision recommendation includes: acquiring a target user in the high-association-degree data set, and making a recommendation strategy for the target user, wherein the recommendation strategy comprises the following steps: touch mode, channel putting, pushing time, address pushing, recommendation rights and interests and the like; and providing the promotion service and the product recommendation service for the target user by using the recommendation strategy to realize accurate recommendation of the user. And carrying out grade division on the association degree data set, dividing the association degree data set into a high grade, a medium grade and a low grade, and acquiring the high association degree data set.
In an embodiment, in a fifth implementation manner of the first aspect of the present invention, the obtaining the high-association data set, and providing a product promotion service and a product recommendation service for a target user set in the high-association data set, where implementing user precision recommendation includes: acquiring a target user in the high-association-degree data set, and making a recommendation strategy for the target user, wherein the recommendation strategy comprises the following steps: touch manner, delivery channel, push time, push address, recommendation rights and interests and the like; and providing the promotion service and the product recommendation service for the target user by using the recommendation strategy to realize accurate recommendation of the user.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, having stored therein instructions, which when executed on a computer, cause the computer to perform the following steps of a big data precision recommendation method.
The big data accurate recommendation method is applied to a client and comprises the following steps: the method for accurately recommending the big data is applied to a client and comprises the following steps: responding to a client, acquiring historical behavior data of a user, and performing first data processing on the historical behavior data through a lookelike audience orientation algorithm to establish a similar user set; acquiring a similar user set, and performing secondary data processing on the similar user set by using an RALM algorithm to acquire a recommended user set; acquiring a recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set; acquiring a target user set, and sending a corresponding feature vector advertisement to the target user set by using a client; responding to a client, obtaining the click rate of the feature vector advertisement, and calculating the relevance of the click rate by using an Apriori algorithm to obtain a relevance data set; grading the association degree data set to obtain a high association degree data set; and acquiring a high-association data set, providing product promotion service and product recommendation service for a target user set in the high-association data set, and realizing accurate recommendation of users.
In an embodiment, in a first implementation manner of the first aspect of the present invention, the obtaining, in response to the client, historical behavior data of the user, and performing first data processing on the historical behavior data through a lookelike audience targeting algorithm, and creating a similar user set includes: acquiring the historical behavior data, and performing data integration by using the historical behavior data to obtain a user image; displaying crowd expansion based on the user portrait to obtain a seed user label, wherein the user label comprises: geography, interests, behaviors, brand preferences, etc.; scoring the seed user tags by utilizing a collaborative filtering recommendation algorithm, calculating the similarity of the seed user tags, and finding out a neighboring set of the seed user tags; and weighting the adjacent set to obtain the similar user set.
In an embodiment, in a second implementation manner of the first aspect of the present invention, before the obtaining the target user set and sending, by the client, a corresponding feature vector advertisement to the target user set, the method further includes: acquiring the target user set, acquiring user candidate labels of the target user set, and performing nonlinear mapping on the user candidate labels to obtain a plurality of user characteristic labels; classifying the user feature tags to obtain a plurality of classification results, normalizing the classification results to obtain feature vector data, and sending advertisements to the feature vector data to be the feature vector advertisements.
In an embodiment, in a third implementation manner of the first aspect of the present invention, the responding to the client obtains a click rate of the feature vector advertisement, and performs relevance calculation on the click rate by using an Apriori algorithm to obtain a relevance dataset; and grade division is carried out on the association degree data set, and the step of obtaining the high association degree data set comprises the following steps: responding to a client, acquiring the click rate and the feature vector of the feature vector advertisement, respectively making the click rate and the feature vector of the feature vector advertisement into databases X and Y, and calculating a minimum support degree threshold value Q; retrieving all frequent item sets in the database through continuous iteration to obtain the association degree data set; and carrying out grade division on the association degree data set, dividing the association degree data set into a high grade, a medium grade and a low grade, and acquiring the high association degree data set.
In an embodiment, in a fourth implementation manner of the first aspect of the present invention, the obtaining the high-association data set, and providing a product promotion service and a product recommendation service for a target user set in the high-association data set, where implementing user precision recommendation includes: acquiring a target user in the high-association-degree data set, and making a recommendation strategy for the target user, wherein the recommendation strategy comprises the following steps: touch mode, channel putting, pushing time, address pushing, recommendation rights and interests and the like; and providing the promotion service and the product recommendation service for the target user by using the recommendation strategy to realize accurate recommendation of the user.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the client, the apparatus and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A big data accurate recommendation method, device, equipment and storage medium are characterized in that the big data accurate recommendation method comprises the following steps:
responding to a client, acquiring historical behavior data of a user, and performing first data processing on the historical behavior data through a lookelike audience orientation algorithm to establish a similar user set;
acquiring the similar user set, and performing secondary data processing on the similar user set by using an RALM algorithm to acquire a recommended user set;
acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to obtain a target user set;
acquiring the target user set, and sending a corresponding feature vector advertisement to the target user set by using the client;
responding to the client, acquiring the click rate of the feature vector advertisement, and calculating the relevance of the click rate by using an Apriori algorithm to obtain a relevance data set; grading the association degree data set to obtain a high association degree data set;
and acquiring the high-association-degree data set, providing product promotion service and product recommendation service for a target user set in the high-association-degree data set, and realizing accurate recommendation of users.
2. The big data accurate recommendation method, device, equipment and storage medium according to claim 1, wherein the responding to the client obtains the historical behavior data of the user, and the historical behavior data is subjected to the first data processing through a lookup alike audience targeting algorithm, and establishing the similar user set comprises:
acquiring the historical behavior data, and performing data integration by using the historical behavior data to obtain a user image; displaying crowd expansion based on the user portrait to obtain a seed user label, wherein the user label comprises: geography, interests, behaviors, brand preferences, etc.;
scoring the seed user tags by utilizing a collaborative filtering recommendation algorithm, calculating the similarity of the seed user tags, and finding out a neighboring set of the seed user tags; and weighting the adjacent set to obtain the similar user set.
3. The method, device, equipment and storage medium for accurately recommending big data according to claim 1, wherein the obtaining the similar user set and performing the second data processing on the similar user set by using a RALM algorithm to obtain the recommended user set comprises:
acquiring the similar user set and a non-similar user set in the client, wherein the similar user set is used as a positive sample, and the non-similar user set is used as a negative sample;
and inputting the positive sample and the negative sample into a preset RAMM algorithm model for training to obtain a recommended user set.
4. The method, apparatus, device and storage medium for accurately recommending big data according to claim 1, wherein before the obtaining the target user set and using the client to send the corresponding feature vector advertisement to the target user set, the method further comprises:
acquiring the target user set, acquiring user candidate labels of the target user set, and performing nonlinear mapping on the user candidate labels to obtain a plurality of user characteristic labels;
classifying the user feature tags to obtain a plurality of classification results, normalizing the classification results to obtain feature vector data, and sending advertisements to the feature vector data to be the feature vector advertisements.
5. The big data accurate recommendation method, device, equipment and storage medium according to claim 1, wherein the response to the client obtains the click rate of the feature vector advertisement, and performs relevance calculation on the click rate by using Apriori algorithm to obtain a relevance data set; and the grade division is carried out on the association degree data set, and the step of obtaining the high association degree data set comprises the following steps:
responding to a client, acquiring the click rate and the feature vector of the feature vector advertisement, respectively making the click rate and the feature vector of the feature vector advertisement into databases X and Y, and calculating a minimum support degree threshold value Q;
retrieving all frequent item sets in the database through continuous iteration to obtain the association degree data set;
and carrying out grade division on the association degree data set, dividing the association degree data set into a high grade, a medium grade and a low grade, and acquiring the high association degree data set.
6. The big data accurate recommendation method, device, equipment and storage medium according to claim 1, wherein the obtaining of the high-relevancy data set provides product promotion services and product recommendation services for a target user set in the high-relevancy data set, and the achieving of user accurate recommendation includes:
obtaining a target user in the high-association-degree data set, and making a recommendation strategy for the target user, wherein the recommendation strategy comprises the following steps: touch mode, delivery channel, push time, push address, recommendation rights and interests, etc.;
and providing the promotion service and the product recommendation service for the target user by using the recommendation strategy to realize accurate recommendation of the user.
7. The accurate recommender of big data, wherein the accurate recommender of big data comprises:
the first data processing module is used for responding to the client, acquiring historical behavior data of the user, and performing first data processing on the historical behavior data through a lookelike audience orientation algorithm to establish a similar user set;
the second data processing module is used for acquiring the similar user set, and performing second data processing on the similar user set by using an RALM algorithm to acquire a recommended user set;
the third data processing module is used for acquiring the recommended user set, and performing third data processing on the recommended user set through a Top-N sorting algorithm to acquire a target user set;
the sending module is used for acquiring the target user set and sending a corresponding feature vector advertisement to the target user set by using the client;
the association module is used for responding to the client, acquiring the click rate of the feature vector advertisement, and calculating the association degree of the click rate by using an Apriori algorithm to obtain an association degree data set; grading the association degree data set to obtain a high association degree data set;
and the accurate recommendation module is used for acquiring the high-relevancy data set, providing product promotion service and product recommendation service for a target user set in the high-relevancy data set, and realizing accurate recommendation of users.
8. The big data accurate recommendation device according to claim 7, wherein the second data processing module comprises:
the obtaining sub-module is used for obtaining the similar user set and the non-similar user set in the client, taking the similar user set as a positive sample, and taking the non-similar user set as a negative sample;
and the training submodule is used for inputting the positive sample and the negative sample into a preset RAMM algorithm model for training to obtain a recommended user set.
9. The big data accurate recommendation device is characterized by comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line; the at least one processor invokes the instructions in the memory to cause the big data precision recommendation device to perform the steps of the big data precision recommendation method according to any one of claims 1-6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of a big data precision recommendation method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210098233.4A CN115048569A (en) | 2022-01-27 | 2022-01-27 | Method, device and equipment for accurately recommending big data and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210098233.4A CN115048569A (en) | 2022-01-27 | 2022-01-27 | Method, device and equipment for accurately recommending big data and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115048569A true CN115048569A (en) | 2022-09-13 |
Family
ID=83158300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210098233.4A Pending CN115048569A (en) | 2022-01-27 | 2022-01-27 | Method, device and equipment for accurately recommending big data and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115048569A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701772A (en) * | 2023-08-03 | 2023-09-05 | 广东美的暖通设备有限公司 | Data recommendation method and device, computer readable storage medium and electronic equipment |
| CN117435817A (en) * | 2023-12-20 | 2024-01-23 | 泰安北航科技园信息科技有限公司 | BI intelligent center system based on industry big data |
-
2022
- 2022-01-27 CN CN202210098233.4A patent/CN115048569A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701772A (en) * | 2023-08-03 | 2023-09-05 | 广东美的暖通设备有限公司 | Data recommendation method and device, computer readable storage medium and electronic equipment |
| CN116701772B (en) * | 2023-08-03 | 2024-03-19 | 广东美的暖通设备有限公司 | Data recommendation method and device, computer readable storage medium and electronic equipment |
| CN117435817A (en) * | 2023-12-20 | 2024-01-23 | 泰安北航科技园信息科技有限公司 | BI intelligent center system based on industry big data |
| CN117435817B (en) * | 2023-12-20 | 2024-03-15 | 泰安北航科技园信息科技有限公司 | BI intelligent center system based on industry big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Campbell et al. | From data to action: How marketers can leverage AI | |
| US10769702B2 (en) | Recommendations based upon explicit user similarity | |
| US8655695B1 (en) | Systems and methods for generating expanded user segments | |
| CN107590675B (en) | User shopping behavior identification method based on big data, storage device and mobile terminal | |
| US8694372B2 (en) | Systems and methods for automatic control of marketing actions | |
| US20180300748A1 (en) | Technologies for granular attribution of value to conversion events in multistage conversion processes | |
| US20040054572A1 (en) | Collaborative filtering | |
| US20130138507A1 (en) | Predictive modeling for e-commerce advertising systems and methods | |
| CN106127525A (en) | A kind of TV shopping Method of Commodity Recommendation based on sorting algorithm | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| US20130204822A1 (en) | Tools and methods for determining relationship values | |
| US20130046619A1 (en) | System and method for targeted advertising | |
| CN115048569A (en) | Method, device and equipment for accurately recommending big data and storage medium | |
| US20230196235A1 (en) | Systems and methods for providing machine learning of business operations and generating recommendations or actionable insights | |
| KR20200115694A (en) | System and method for providing of trading area information using big data | |
| US20200311748A1 (en) | Consumer response intelligent spend prediction system | |
| Soni | Role of Temporal, Demographic, and Behavioral Factors in Customer Conversion Through Dynamic Creative Optimization in the Consumer-Packaged Goods Setting | |
| Wei et al. | Online shopping behavior analysis for smart business using big data analytics and blockchain security | |
| US20160148271A1 (en) | Personalized Marketing Based on Sequence Mining | |
| US20110276409A1 (en) | System and method for providing feedback about merchants using payment transactional information | |
| Ramkumar et al. | Big data analytics and its application in E-commerce | |
| Bruckhaus | Collective intelligence in marketing | |
| Granov | Customer loyalty, return and churn prediction through machine learning methods: for a Swedish fashion and e-commerce company | |
| Kadge et al. | Sales and invoice management system with analysis of customer behaviour | |
| CN117172886B (en) | Marketing service supervision system and method based on big data analysis |
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 |