CN111127074A - Data recommendation method - Google Patents
Data recommendation method Download PDFInfo
- Publication number
- CN111127074A CN111127074A CN201911172534.1A CN201911172534A CN111127074A CN 111127074 A CN111127074 A CN 111127074A CN 201911172534 A CN201911172534 A CN 201911172534A CN 111127074 A CN111127074 A CN 111127074A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- receiving
- label
- records
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention provides a data recommendation method, which is characterized by comprising the following steps: acquiring an identity of a user; acquiring a user superior record; inputting the user superior record into a potential demand generation model obtained by pre-training, and outputting a potential demand prediction result of a behavior subject; wherein generating the model according to the potential need comprises at least one of: receiving a fixed area analysis instruction, dividing the label into fixed area areas, wherein the fixed area areas take a limited label value range as a judgment basis, when the user superior record belongs to one of the areas in the label division, determining the behavior subject, and matching the inferior records of the same behavior subject in a sample library; and receiving a relative analysis instruction, dividing the label into relative areas, wherein the relative areas use the value range of the interval label as a judgment standard, when the superior record of the user meets the relative areas, determining the behavior subject, and matching the inferior records of the same behavior subject in a sample library.
Description
Technical Field
The invention relates to the field of AI data analysis and deduction, in particular to a data recommendation method.
Background
With the development of science and technology, more and more big data-based analysis and prediction appear; however, the analysis and statistics of big data are tedious and tedious, the manual operation is difficult, the operation cost is high, the economic cost is not saved, the industries are not communicated, the statistical prediction mode is disordered, and the big data cannot be effectively utilized. Some private enterprises or small industries are still judged by subjective consciousness of people due to insufficient funds, so that the defects of poor accuracy, slow updating consciousness, unsmooth personnel hierarchy, no copying and small effective range are caused.
At present, the continuous accumulation of big data, more and more data form a statistical problem, the analysis and prediction deduction of big data is continuous, most of data are extracted from a plurality of business systems and contain historical data, the big data such as few error data or data conflict with each other cannot be effectively utilized, and when the data are associated with target individuals, the data become factors influencing results. The existing big data analysis algorithm is basically based on simple summary statistics, and a point of relative value is used in some parts. The adoption of the relative value algorithm can possibly cause the potential requirements of some users to be overwhelmed, and finally, the judgment of the analysis result at the later stage is wrong.
Aiming at the technical problem that the big data is analyzed by adopting a relative value algorithm in the prior art, and the big data prediction result is inaccurate due to the fact that the potential demand of a user is submerged, an effective solution is not provided at present.
Disclosure of Invention
The invention aims to solve the technical problem that the prediction result of big data is inaccurate due to the fact that the potential demand of a user is inundated, and provides a data recommendation method.
The invention adopts the following technical scheme for solving the technical problems: a method of data recommendation, comprising: acquiring an identity of a user; acquiring a user superior record; inputting the user superior record into a potential demand generation model obtained by pre-training, and outputting a potential demand prediction result of a behavior subject; the step of inputting the user superior record into a pre-trained potential demand generation model comprises generating the model according to the potential demand, and the method comprises at least one of the following steps: receiving a fixed area analysis instruction, dividing the label into fixed area areas, wherein the fixed area areas take a limited label value range as a judgment basis, when the user superior record belongs to one of the areas in the label division, determining the behavior subject, and matching the inferior records of the same behavior subject in a sample library; and receiving a relative analysis instruction, dividing the label into relative areas, wherein the relative areas use the value range of the interval label as a judgment standard, when the superior record of the user meets the relative areas, determining the behavior subject, and matching the inferior records of the same behavior subject in a sample library.
Preferably, before the step of generating the model of the potential demand, the method further comprises the following steps: receiving a plurality of user history records, wherein the plurality of user history records respectively correspond to a plurality of users; receiving a tag instruction, screening according to the plurality of user history records, and deriving a type parameter; an compute intermediate data instruction is received.
Preferably, after the potential demand generation model, the method further comprises: and receiving user analysis instructions one by one, and outputting a potential demand prediction result of the behavior body for a service scene of data recommendation.
Preferably, receiving a tag instruction, performing filtering according to a plurality of user history records, and deriving a type parameter includes: s2021, setting a label according to preset information; s2022, performing label setting on the plurality of user history records according to labels; s2023, generating the type parameters after screening the plurality of user history records; s2024, storing the type parameter; s2025, reading the type parameter.
Preferably, after receiving the tag instruction, performing filtering according to a plurality of user history records, and deriving the type parameter, the method further includes: receiving a member circulation instruction, and grouping users, wherein the users are divided into virginal purchasing users, active users and sleeping users.
Preferably, the step of receiving an instruction to calculate intermediate data comprises: receiving a label weight setting instruction; performing data coupling according to the respective proportion of the tags in the user history record to obtain type parameters in the user history record; determining a behavior body corresponding to the user history record according to the type parameters in the user history record: acquiring historical records belonging to the same behavior body from a plurality of user historical records as reference information, and determining a lower record for optimizing the corresponding behavior body according to the type parameters; and determining the lower records for optimizing the corresponding behavior subjects according to the type parameters to form a sample library.
Preferably, determining the history for optimizing the corresponding behavior body according to the type parameter includes: removing the unreliable data from the reference information according to a preset data screening algorithm; and analyzing to obtain a lower record in the behavior body according to credible data except the incredible data in the reference information.
Preferably, receiving a set tag weight instruction includes: and setting a weight value for the label according to a preset information adjusting condition.
The embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and is characterized in that when the processor executes the computer program, any one of the above data recommendation methods is implemented.
The embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program of any one of the data recommendation methods described above.
The invention has the following beneficial effects:
1) the method solves the technical problem that the big data prediction result is inaccurate due to the fact that the potential demand of the user is submerged;
2) the method has the advantages that the prediction and recommendation accuracy of the potential demand data is greatly improved, and the popularization cost is reduced;
3) according to the invention, marketing schemes are generated one by one according to the habit of the user 1V1, and accurate operation of potential requirements of the user is realized.
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. In the drawings:
FIG. 1 is a flow chart of a method for processing data using a data recommendation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of various prediction schemes in a process of generating a model according to a potential demand according to an embodiment of the present invention;
FIG. 3 is a flow chart of a data recommendation method provided in accordance with an embodiment of the present invention;
FIG. 4 is a detailed flowchart of a data recommendation method according to an embodiment of the present invention;
fig. 5 is a flowchart of sample library formation in a data recommendation method according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
To clearly define the concept of "model" and "sample library," the following description is now made for these two terms:
the formation of a model is equivalent to the fact that "experience" in a computer usually exists in the form of "data", so that the main content studied by machine learning is about an algorithm (also called "learning algorithm") on the computer for generating a "model" from the data. With the learning algorithm, the computer can build a model based on the existing data by inputting the empirical data.
The sample library corresponds to a training set, i.e., a collection of empirical data used in a machine learning training process.
Example one
An embodiment of the present invention provides a data recommendation method, and fig. 1 is a flowchart of a data recommendation method according to an embodiment of the present invention, and as shown in fig. 1, a data recommendation method includes:
s101, acquiring an identity of a user;
s102, acquiring a user superior record;
s103, inputting the superior records of the user into a potential demand generation model obtained by pre-training, and outputting a potential demand prediction result of the behavior body;
specifically, by combining a SaaS model, a store logs in a system after subscribing, a seller ID is obtained through a seller _ nick code, an authorized binding API is obtained, RDS data synchronizes client backend data, the last shopping merged order data of the buyer is obtained from an RDS version of an Aliyun database, the merged order data is imported into the model after data cleaning, a matched behavior main body is found, and if the last shopping is the 5 th shopping, the lower-level record (namely the 6 th shopping record) of the behavior main body is subjected to data analysis and then is recommended to a related user as a prediction result.
FIG. 2 is a schematic diagram of various prediction schemes in a process of generating a model according to a potential demand according to an embodiment of the present invention;
the step of inputting the user superior record into a pre-trained potential demand generation model comprises step S204, and the step of generating the model according to the potential demand comprises at least one of the following steps:
receiving a zone-specific analysis instruction, dividing the label into zone-specific areas, determining a behavior subject when a user superior record belongs to one of the zone in the label division by using a limited label value range as a judgment basis in the zone-specific areas, and matching subordinate records of the same behavior subject in a sample library;
specifically, a user superior record is input into a pre-trained item _ recommend sample library potential demand generation model, and a potential demand prediction result of a behavior subject is output and written into an RDS version of an Aricloud database.
The method takes the purchasing of the milk powder of children as a practical application scene, infants A and B display that a user superior record displays that a section of milk powder is purchased, and supposing that 5 times of using a section of milk powder is recorded in an item _ recommend sample library, and two sections of milk powder are needed to be purchased for the 6 th time, the next purchase is displayed in the user superior record of the infant A, and the next purchase is displayed in the user superior record of the infant B, after the definite area analysis, according to the limitation of the definite area, the main labels of the infants A and B are the next purchases for the 6 th time and the 3 rd time respectively, and the subordinate records of the same behavior subject are searched in the item _ recommend sample library, so that the recommendation information of a shop obtained by the infants A is two sections of milk powder, the recommendation obtained by the infants B is a section of milk powder, the accurate recommendation of one-by-one user is realized, the pushing accuracy of the user information is improved, and the periodic updating of the item _ recommend sample library is realized, the highly accurate recommendation method greatly reduces the marketing cost.
And receiving a relative analysis instruction, dividing the label into relative areas, determining the behavior subject when the relative area is met by the superior record of the user, and matching the inferior records of the same behavior subject in the sample library by taking the value range of the interval label as a judgment standard.
Specifically, the method continues to take the purchase of the milk powder for children as a practical application scene, and assumes that the specific area recorded in the item _ recommend sample library is analyzed to obtain that the infant needs to use one section of milk powder for 5 times, and needs to purchase the second section of milk powder for the 6 th time; assuming that the relative analysis recorded in the item _ recommend sample library obtains the most milk powder for buying the milk powder for the infant next time, the number of people who shop for many times is usually far less than that of people who shop for few times. The existing infant A and infant B display that a section of milk powder is purchased for the 5 th time and the 4 th time in the superior records of the user, the infant A and the infant B recommend a section of milk powder according to relative analysis, and the pushing is not accurate for the infant A; if the infant A recommends two milk powder segments at the 6 th time and the infant B recommends one milk powder segment at the 5 th time by adopting the area analysis, the push obtained by the two people is accurate. As can be seen from the above, the data record of the original 6 th shopping is easily overwhelmed by adopting the relative analysis, namely the conventional data recommendation means.
It should be noted that the relative analysis is to effectively reduce unnecessary recommendation cost and improve generalization capability of the model under the condition of ensuring accuracy by adopting a technical means under the condition that the same shopping record, namely the lower-level record, cannot be obtained due to various reasons.
It should be noted that, in step S204, the lower records may be recommended in an optimal sub-scenario arrangement and combination manner according to the requirements of the customer stores, and the above-mentioned "partition analysis command" and "relative analysis command" may be used alone or in combination according to the requirements of the customers.
Fig. 3 is a flowchart of a data recommendation method according to an embodiment of the present invention, as shown in fig. 3,
before the step of generating the model according to the potential requirements, the method further comprises the following steps:
s201, receiving a plurality of user history records, wherein the plurality of user history records correspond to a plurality of users respectively;
s202, receiving a tag instruction, screening according to a plurality of user history records, and deriving type parameters;
s203, receiving an intermediate data calculation instruction.
Specifically, the plurality of user histories includes: and (3) calling MaxCommute big data calculation API (application program interface) by using intermediate data such as sales related data, shopping interval data, logistics timeliness data, guest unit price labels and the like, and analyzing and processing mass data economically and efficiently by adopting distributed calculation.
After generating the model according to the potential need, the method further comprises:
and S205, receiving user-by-user analysis instructions, and outputting a potential demand prediction result of the behavior body for a service scene of data recommendation.
As can be seen from the above, fig. 4 is a detailed flowchart of a data recommendation method according to an embodiment of the present invention.
Preferably, receiving a tag instruction, performing filtering according to a plurality of user history records, and deriving a type parameter includes: s2021, setting a label according to preset information;
s2022, performing label setting on the plurality of user history records according to labels;
s2023, generating the type parameters after screening the plurality of user history records;
s2024, storing the type parameter;
s2025, reading the type parameter.
Preferably, after receiving the tag instruction, performing filtering according to a plurality of user history records, and deriving the type parameter, the method further includes: receiving a member circulation instruction, and grouping users, wherein the users are divided into virginal purchasing users, active users and sleeping users.
Specifically, the users are classified according to the comparison between the latest shopping time and the current day data, so that the next record of the similar behavior main body can be recommended conveniently, the multidimensional data are integrated, and the articles which the users need to purchase most are recommended.
Fig. 5 is a flowchart of sample library formation in a data recommendation method according to an embodiment of the present application, where, as shown in fig. 5, the step of receiving an instruction to calculate intermediate data includes: receiving a label weight setting instruction; performing data coupling according to the respective proportion of the tags in the user history record to obtain type parameters in the user history record; determining a behavior body corresponding to the user history record according to the type parameters in the user history record: acquiring historical records belonging to the same behavior body from a plurality of user historical records as reference information, and determining a lower record for optimizing the corresponding behavior body according to the type parameters; and determining the lower records for optimizing the corresponding behavior subjects according to the type parameters to form a sample library.
It should be noted that the tag weight is set according to the customer store requirements, and the requirements of each store for tag data are different.
Determining a history record for optimizing a corresponding behavior subject according to the type parameter, comprising: removing the unreliable data from the reference information according to a preset data screening algorithm; and analyzing to obtain a lower record in the behavior body according to credible data except the incredible data in the reference information.
Receiving a label weight setting instruction, comprising: and setting a weight value for the label according to a preset information adjusting condition.
Specifically, by taking e-commerce as an example, the method recommends the article with the highest purchase possibility of the customer as the final purpose, sets weights for related labels according to the purchase demands of the customer in the actual scene, avoids the occurrence of long tail theory, submerges some real potential demand data, customizes the setting according to the demands of the customer, and improves the accuracy of the data.
Example two
The embodiment of the invention provides an application scenario of a data recommendation method, wherein the new baby is an actual scenario, and the new baby means that no history information exists, so that a scheme of relative analysis is required to be adopted to operate related contents. Through searching similar dothes or historical records of the similar dothes, the potential demands are found out to carry out doth demand priority arrangement, preferential selection is carried out, and a more comprehensive model is generated through continuous data accumulation.
A method of data recommendation, comprising: acquiring an identity of a user; acquiring a user superior record; inputting the user superior record into a potential demand generation model obtained by pre-training, and outputting a potential demand prediction result of a behavior subject; the method comprises the following steps of inputting a user superior record into a pre-trained potential demand generation model, wherein the step of generating the model according to the potential demand comprises the following steps: and receiving a relative analysis instruction, dividing the label into relative areas, wherein the relative areas use the value range of the interval label as a judgment standard, when the superior record of the user meets the relative areas, determining the behavior subject, and matching the inferior records of the same behavior subject in a sample library.
Specifically, under the condition that no matched historical data exists, the shop needs to set a relative area in a relative analysis mode, move an approximate relative area, find a matched action subject from an item _ recommend sample library formed according to the similar baby of the previous and new babies, the history records of the similar babies and the like, perform data analysis according to a lower-level record in the item _ recommend sample library, and recommend the data analysis to the client.
Preferably, before the step of generating the model of the potential demand, the method further comprises the following steps: receiving a plurality of user history records, wherein the plurality of user history records respectively correspond to a plurality of users; receiving a tag instruction, screening according to the plurality of user history records, and deriving a type parameter; an compute intermediate data instruction is received.
Preferably, after the potential demand generation model, the method further comprises: and receiving user analysis instructions one by one, and outputting a potential demand prediction result of the behavior body for a service scene of data recommendation.
Preferably, receiving a tag instruction, performing filtering according to a plurality of user history records, and deriving a type parameter includes:
s2021, setting a label according to preset information;
s2022, performing label setting on the plurality of user history records according to labels;
s2023, generating the type parameters after screening the plurality of user history records;
s2024, storing the type parameter;
s2025, reading the type parameter.
Preferably, after receiving the tag instruction, performing filtering according to a plurality of user history records, and deriving the type parameter, the method further includes: receiving a member circulation instruction, and grouping users, wherein the users are divided into virginal purchasing users, active users and sleeping users.
Preferably, the step of receiving an instruction to calculate intermediate data comprises: receiving a label weight setting instruction; performing data coupling according to the respective proportion of the tags in the user history record to obtain type parameters in the user history record; determining a behavior body corresponding to the user history record according to the type parameters in the user history record: acquiring historical records belonging to the same behavior body from a plurality of user historical records as reference information, and determining a lower record for optimizing the corresponding behavior body according to the type parameters; and determining the lower records for optimizing the corresponding behavior subjects according to the type parameters to form a sample library.
Specifically, a relative area is set, the range of the relative area is gradually reduced through data iteration each time, the range of the relative area is set for each type of label, when the upper record of a user meets the range of the relative area, the retrieved data is reasonable data after multi-dimension estimation, after the relative area is gradually reduced, a plurality of recommended babies have priorities, influence factors of the babies on the recommendation have priorities, and the accuracy of the data meeting the potential requirements of the user is higher.
Preferably, determining the history for optimizing the corresponding behavior body according to the type parameter includes: removing the unreliable data from the reference information according to a preset data screening algorithm; and analyzing to obtain a lower record in the behavior body according to credible data except the incredible data in the reference information.
Preferably, receiving a set tag weight instruction includes: and setting a weight value for the label according to a preset information adjusting condition.
EXAMPLE III
The embodiment of the invention provides a data recommendation method, which takes double 11-step marketing as an example, the system combines the rank requirement of double 11 preheating meeting places, and can enable the number of preheating purchase-adding collection people to show the trend of increasing or decreasing or other waveforms by distributing the number of marketing people according to the percentage of days, thereby better achieving the aim of double 11 preheating.
According to the statistics of the previous year big data, 11 th day of 11 months is an outbreak day, 10 th day of 11 months is a consolidation day, the preheating period is 11 months 01-11 months 10 days, the climax is the first weekend after the 11 months 01 starts, and the latest weekend before the 11 months 01 preheating period is a leading day.
In the whole hot marketing period, data recommendation needs to perform data analysis on historical records of users according to the setting of stores, and recommend suitable articles to corresponding users, strong optimization is performed on the overall sales performance of the stores on the basis of meeting the users, mass recommendation on 'money explosion' is not performed singly, recommendation is accurately achieved according to the requirements of customers, and the recommendation time, the recommendation baby, the recommendation mode, the consumption behaviors and the like of the customers are predicted by combining historical data, so that the optimal state of store sales is achieved.
A method of data recommendation, comprising: acquiring an identity of a user; acquiring a user superior record; inputting the user superior record into a potential demand generation model obtained by pre-training, and outputting a potential demand prediction result of a behavior subject; the method comprises the following steps of inputting a user superior record into a pre-trained potential demand generation model, wherein the step of generating the model according to the potential demand comprises at least one of the following steps: receiving a fixed area analysis instruction, dividing the label into fixed area areas, wherein the fixed area areas take a limited label value range as a judgment basis, when the user superior record belongs to one of the areas in the label division, determining the behavior subject, and matching the inferior records of the same behavior subject in a sample library; and receiving a relative analysis instruction, dividing the label into relative areas, wherein the relative areas use the value range of the interval label as a judgment standard, when the superior record of the user meets the relative areas, determining the behavior subject, and matching the inferior records of the same behavior subject in a sample library.
Preferably, before the step of generating the model of the potential demand, the method further comprises the following steps: receiving a plurality of user history records, wherein the plurality of user history records respectively correspond to a plurality of users; receiving a tag instruction, screening according to the plurality of user history records, and deriving a type parameter; an compute intermediate data instruction is received.
Preferably, after the potential demand generation model, the method further comprises: and receiving user analysis instructions one by one, and outputting a potential demand prediction result of the behavior body for a service scene of data recommendation.
Preferably, receiving a tag instruction, performing filtering according to a plurality of user history records, and deriving a type parameter includes:
s2021, setting a label according to preset information;
s2022, performing label setting on the plurality of user history records according to labels;
s2023, generating the type parameters after screening the plurality of user history records;
s2024, storing the type parameter;
s2025, reading the type parameter.
Preferably, after receiving the tag instruction, performing filtering according to a plurality of user history records, and deriving the type parameter, the method further includes: receiving a member circulation instruction, and grouping users, wherein the users are divided into virginal purchasing users, active users and sleeping users.
Preferably, the step of receiving an instruction to calculate intermediate data comprises: receiving a label weight setting instruction; performing data coupling according to the respective proportion of the tags in the user history record to obtain type parameters in the user history record; determining a behavior body corresponding to the user history record according to the type parameters in the user history record: acquiring historical records belonging to the same behavior body from a plurality of user historical records as reference information, and determining a lower record for optimizing the corresponding behavior body according to the type parameters; and determining the lower records for optimizing the corresponding behavior subjects according to the type parameters to form a sample library.
Preferably, determining the history for optimizing the corresponding behavior body according to the type parameter includes: removing the unreliable data from the reference information according to a preset data screening algorithm; and analyzing to obtain a lower record in the behavior body according to credible data except the incredible data in the reference information.
Specifically, taking the recommendation time of the recommended baby as an example, reading historical data of corresponding customers, analyzing user habits, taking time of 7-9 points on the way of going to work, 13-14 points on the way of going to work, 18-20 points on the way of going to work, and 22-23 points before sleep as favorite time of some users, analyzing data of the historical time of going to work by taking time as a main label, importing user data needing to be predicted after the same single-action main body generates type parameters, predicting the optimal potential recommendation time, and recommending the optimal potential recommended baby according to the optimal potential recommendation time.
Preferably, receiving a set tag weight instruction includes: and setting a weight value for the label according to a preset information adjusting condition.
The embodiment of the invention also provides a computer device, which is used for solving the technical problem that the prediction result of the big data is inaccurate due to the fact that the potential demand of the user is overwhelmed.
The embodiment of the invention also provides a computer-readable storage medium, which is used for solving the technical problem that the prediction result of the big data is inaccurate due to the fact that the potential demand of the user is inundated, and the computer-readable storage medium stores a computer program for executing the data recommendation method.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for recommending data, comprising:
s101, acquiring an identity of a user;
s102, acquiring a user superior record;
s103, inputting the user superior record into a potential demand generation model obtained through pre-training, and outputting a potential demand prediction result of a behavior subject;
the step of inputting the user superior record into a pre-trained potential demand generation model comprises the following steps: s204, generating the model according to the potential demand, wherein the method comprises at least one of the following steps:
receiving a fixed area analysis instruction, dividing the label into fixed area areas, wherein the fixed area areas take a limited label value range as a judgment basis, when the user superior record belongs to one of the areas in the label division, determining the behavior subject, and matching the inferior records of the same behavior subject in a sample library;
and receiving a relative analysis instruction, dividing the label into relative areas, wherein the relative areas use the value range of the interval label as a judgment standard, when the superior record of the user meets the relative areas, determining the behavior subject, and matching the inferior records of the same behavior subject in a sample library.
2. A method for recommending data according to claim 1, characterized in that, before the step of generating a model according to said potential need, it further comprises the steps of:
s201, receiving a plurality of user history records, wherein the plurality of user history records respectively correspond to a plurality of users;
s202, receiving a tag instruction, screening according to the plurality of user history records, and deriving a type parameter;
s203, receiving an intermediate data calculation instruction.
3. A method of data recommendation according to claim 1 or 2, wherein after generating said model according to said potential need, said method further comprises: s205, receiving user-by-user analysis instructions, and outputting a potential demand prediction result of the behavior body for a service scene of data recommendation.
4. The data recommendation method of claim 2, wherein receiving tag commands, filtering according to the plurality of user history records, and deriving type parameters comprises:
s2021, setting a label according to preset information;
s2022, performing label setting on the plurality of user history records according to labels;
s2023, generating the type parameters after screening the plurality of user history records;
s2024, storing the type parameter;
s2025, reading the type parameter.
5. The data recommendation method of claim 2, after receiving the tag command, filtering according to the plurality of user histories, and deriving the type parameter, further comprising: and receiving a member circulation instruction, and grouping the users, wherein the users are divided into virginal purchasing users, active users and sleeping users.
6. A method as claimed in claim 2, wherein the step of receiving an instruction to compute intermediate data comprises:
receiving a label weight setting instruction;
performing data coupling according to the respective proportion of the tags in the user history record to obtain type parameters in the user history record;
determining a behavior body corresponding to the user history record according to the type parameter in the user history record:
acquiring historical records belonging to the same behavior body from the plurality of user historical records as reference information, and determining the subordinate records for optimizing the corresponding behavior bodies according to the type parameters;
and determining the lower-level records for optimizing corresponding behavior subjects according to the type parameters to form a sample library.
7. The data recommendation method according to claim 6, wherein determining the history record for optimizing the corresponding behavior body according to the type parameter comprises:
removing the unreliable data from the reference information according to a preset data screening algorithm;
and analyzing to obtain lower records in the behavior body according to credible data except the incredible data in the reference information.
8. A data recommendation method according to claim 7, receiving a set tag weight instruction, comprising:
and setting a weight value for the label according to a preset information adjusting condition.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the data recommendation method of any one of claims 1 to 8 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the data recommendation method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911172534.1A CN111127074B (en) | 2019-11-26 | 2019-11-26 | Data recommendation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911172534.1A CN111127074B (en) | 2019-11-26 | 2019-11-26 | Data recommendation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111127074A true CN111127074A (en) | 2020-05-08 |
| CN111127074B CN111127074B (en) | 2023-04-25 |
Family
ID=70496691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911172534.1A Active CN111127074B (en) | 2019-11-26 | 2019-11-26 | Data recommendation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111127074B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112227007A (en) * | 2020-09-18 | 2021-01-15 | 张国政 | Control method for purchasing clothing treating agent for washing machine |
| CN112435111A (en) * | 2020-12-30 | 2021-03-02 | 广东金赋科技股份有限公司 | Tax hall guide method and device based on hall and user data |
| CN113378122A (en) * | 2021-08-02 | 2021-09-10 | 成都联帮医疗科技股份有限公司 | Data processing system and method based on SaaS service cloud platform |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016203652A1 (en) * | 2015-06-19 | 2016-12-22 | 株式会社Ｕｂｉｃ | System related to data analysis, control method, control program, and recording medium therefor |
| CN107203899A (en) * | 2017-05-03 | 2017-09-26 | 北京小米移动软件有限公司 | Information-pushing method and equipment |
| CN107844548A (en) * | 2017-10-30 | 2018-03-27 | 北京锐安科技有限公司 | A kind of data label method and apparatus |
| US20180330248A1 (en) * | 2017-05-12 | 2018-11-15 | Adobe Systems Incorporated | Context-aware recommendation system for analysts |
| US20190079977A1 (en) * | 2016-05-12 | 2019-03-14 | Alibaba Group Holding Limited | Method for determining user behavior preference, and method and device for presenting recommendation information |
| WO2019153518A1 (en) * | 2018-02-08 | 2019-08-15 | 平安科技（深圳）有限公司 | Information pushing method and device, computer device and storage medium |
| CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
| WO2019174395A1 (en) * | 2018-03-13 | 2019-09-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for information recommendation, and device |
| WO2019192261A1 (en) * | 2018-04-02 | 2019-10-10 | 阿里巴巴集团控股有限公司 | Payment mode recommendation method and device and equipment |
-
2019
- 2019-11-26 CN CN201911172534.1A patent/CN111127074B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016203652A1 (en) * | 2015-06-19 | 2016-12-22 | 株式会社Ｕｂｉｃ | System related to data analysis, control method, control program, and recording medium therefor |
| US20190079977A1 (en) * | 2016-05-12 | 2019-03-14 | Alibaba Group Holding Limited | Method for determining user behavior preference, and method and device for presenting recommendation information |
| CN107203899A (en) * | 2017-05-03 | 2017-09-26 | 北京小米移动软件有限公司 | Information-pushing method and equipment |
| US20180330248A1 (en) * | 2017-05-12 | 2018-11-15 | Adobe Systems Incorporated | Context-aware recommendation system for analysts |
| CN107844548A (en) * | 2017-10-30 | 2018-03-27 | 北京锐安科技有限公司 | A kind of data label method and apparatus |
| WO2019153518A1 (en) * | 2018-02-08 | 2019-08-15 | 平安科技（深圳）有限公司 | Information pushing method and device, computer device and storage medium |
| WO2019174395A1 (en) * | 2018-03-13 | 2019-09-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for information recommendation, and device |
| WO2019192261A1 (en) * | 2018-04-02 | 2019-10-10 | 阿里巴巴集团控股有限公司 | Payment mode recommendation method and device and equipment |
| CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112227007A (en) * | 2020-09-18 | 2021-01-15 | 张国政 | Control method for purchasing clothing treating agent for washing machine |
| CN112227007B (en) * | 2020-09-18 | 2023-08-25 | 张国政 | Control method for purchasing clothes treating agent for washing machine |
| CN112435111A (en) * | 2020-12-30 | 2021-03-02 | 广东金赋科技股份有限公司 | Tax hall guide method and device based on hall and user data |
| CN112435111B (en) * | 2020-12-30 | 2023-12-19 | 广东金赋科技股份有限公司 | Tax hall guiding and handling method and device based on hall and user data |
| CN113378122A (en) * | 2021-08-02 | 2021-09-10 | 成都联帮医疗科技股份有限公司 | Data processing system and method based on SaaS service cloud platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111127074B (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Beladev et al. | Recommender systems for product bundling | |
| JP7105700B2 (en) | Time-division recommendation method and apparatus for service target | |
| US11769194B2 (en) | Method and system for presenting items in online environment based on previous item selections | |
| KR20140056731A (en) | Purchase recommendation service system and method | |
| CN102282551A (en) | Automated decision support for pricing entertainment tickets | |
| CN111127074A (en) | Data recommendation method | |
| US20220180392A1 (en) | Predictive recommendation system using tiered feature data | |
| US11810151B2 (en) | Predictive recommendation system using tiered feature data | |
| KR20150138310A (en) | Digital receipts economy | |
| WO2020221022A1 (en) | Service object recommendation method | |
| CN110689402A (en) | Method and device for recommending merchants, electronic equipment and readable storage medium | |
| Hemalatha | Market basket analysis–a data mining application in Indian retailing | |
| JP2021099718A (en) | Information processing device and program | |
| Wei et al. | Online shopping behavior analysis for smart business using big data analytics and blockchain security | |
| Koniew | Classification of the User's Intent Detection in Ecommerce systems-Survey and Recommendations. | |
| CA3059904A1 (en) | Method and system for generating aspects associated with a future event for a subject | |
| Leimstoll et al. | Collaborative recommender systems for online shops | |
| Rehman et al. | Structured critical review on market basket analysis using deep learning & association rules | |
| WO2021192232A1 (en) | Article recommendation system, article recommendation device, article recommendation method, and recording medium storing article recommendation program | |
| CN114663135A (en) | Information sending method, device, equipment and readable medium | |
| US20210216907A1 (en) | Selecting optimum primary and secondary parameters to calibrate and generate an unbiased forecasting model | |
| JP6809148B2 (en) | Program and combination extraction system | |
| Onokoy et al. | Modern approaches to building recommender systems for online stores | |
| US11869063B2 (en) | Optimize shopping route using purchase embeddings | |
| US11922476B2 (en) | Generating recommendations based on descriptors in a multi-dimensional search space |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |