CN112308629A - Information query method and device - Google Patents
Information query method and device Download PDFInfo
- Publication number
- CN112308629A CN112308629A CN202011272831.6A CN202011272831A CN112308629A CN 112308629 A CN112308629 A CN 112308629A CN 202011272831 A CN202011272831 A CN 202011272831A CN 112308629 A CN112308629 A CN 112308629A
- Authority
- CN
- China
- Prior art keywords
- target object
- user
- target
- information
- attribute information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000004044 response Effects 0.000 claims abstract description 12
- 230000006399 behavior Effects 0.000 claims description 165
- 238000005457 optimization Methods 0.000 claims description 42
- 238000012549 training Methods 0.000 claims description 39
- 238000004422 calculation algorithm Methods 0.000 claims description 38
- 230000015654 memory Effects 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 12
- 238000006243 chemical reaction Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an information query method and device, and the specific implementation scheme is as follows: in response to receiving the information query request, acquiring user information of a target object and attribute information of the target object corresponding to each user; inputting the user information of the target object and the attribute information corresponding to each user into the trained user and object matching model, and generating a first target behavior execution rate of each user; according to the first target behavior execution rate of all users, determining at least one of the following target object data: the order amount, the difference value between the selling value and the cost of the target object and a second target behavior execution rate; and determining and feeding back final attribute information of the target object according to at least one of the order quantity of the target object, the difference value of the selling value of the target object and the cost of the target object and a second target behavior execution rate of the target object. The scheme realizes reverse customization of product attributes and helps manufacturers to improve the attribute design of products.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to the technical field of deep learning, and particularly relates to an information query method and device.
Background
The goal of product attribute customization is to assist manufacturers in intelligently selecting attribute parameters of products, so that products which meet market requirements better are designed and produced, and the aim of maximizing product sales volume or sales profits is fulfilled. After the product attribute customization is completed, once the product is put into production, large-scale cost input of production lines, materials, personnel and the like can be generated, and the method has important technical and commercial values for objective and accurate market prediction of product objects with different attributes.
The traditional product attribute customization methods (also called reverse customization) generally have two types, namely, the product attribute customization is carried out by collecting the requirements of users on different product attributes by using questionnaires or a mode of developing a reverse customization system; secondly, through analyzing behaviors such as user clicking, browsing and the like, product characteristics most concerned by the user are found and fed back to the brand trader through forms such as data analysis reports and the like, and the brand trader is helped to carry out production design.
Disclosure of Invention
The application provides an information query method, an information query device, information query equipment and a storage medium.
According to a first aspect, an embodiment of the present application provides an information query method, including: in response to receiving the information query request, obtaining user information of a target object corresponding to the request and attribute information of the target object corresponding to each user, wherein the attribute information comprises: attribute values of the respective attributes; inputting the user information of the target object and the attribute information of the target object corresponding to each user into the trained user-object matching model, and generating a target behavior result of each user and a first target behavior execution rate of each user, wherein the first target behavior execution rate is used for representing the probability that the target behavior result of the user is ordering; according to the target behavior results of all users and the first target behavior execution rates of all users, determining at least one item of the following target object data: the order quantity, the difference value between the sale value and the cost of the target object and a second target behavior execution rate, wherein the second target behavior execution rate is used for representing the comparison relation between the order quantity of the target object and the total target behavior quantity of the target object; determining final attribute information of the target object by using an optimization algorithm according to at least one of the order quantity of the target object, the difference value between the sale value of the target object and the cost of the target object and a second target behavior execution rate of the target object, wherein the final attribute information of the target object is the optimal combination of the attribute values of all the attributes of the target object; and feeding back final attribute information of the target object.
In some embodiments, the user and object matching model is obtained by training as follows: acquiring a training sample set, wherein training samples in the training sample set comprise user information of a target object, attribute information of the target object corresponding to each user, a target behavior result of each user and a first target behavior execution rate of each user, and the user information is user information of all users in a certain historical time; and training to obtain a user-object matching model by using a deep learning algorithm, wherein the user information of the target object and the attribute information of the target object corresponding to each user, which are included in the training sample set of training samples, are used as input data, and the target behavior result of each user and the first target behavior execution rate of each user, which correspond to the input user information of the target object and the attribute information of the target object corresponding to each user, are used as expected output data.
In some embodiments, obtaining the user information of the target object corresponding to the request and the attribute information of the target object corresponding to each user comprises: analyzing the content of the request, and extracting preset information, wherein the preset information represents that the user information of the target object and the attribute information of the target object are preset; and acquiring user information of the target object and attribute information of the target object corresponding to each user according to the preset information.
In some embodiments, the final attribute information of the target object is generated by performing a plurality of iterative operations; the iterative operation comprises: judging whether at least one of the order quantity of the current target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition, if not, continuing to execute and skipping to judge whether at least one of the order quantity of the current target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition; if so, taking the attribute information of the current target object meeting the iteration stop condition as the final attribute information of the target object, wherein the iteration stop condition is as follows: the value calculated based on the optimization algorithm is less than a predetermined threshold.
In some embodiments, determining the final attribute information of the target object using an optimization algorithm according to at least one of a next order amount of the target object, a difference between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object includes: and determining final attribute information of the target object by using an optimization algorithm according to at least one of the amount of orders of the target object, the difference value of the sale value of the target object and the cost of the target object, the second target behavior execution rate of the target object and constraint conditions, wherein the constraint conditions represent that relationship constraint is carried out on different attributes of the target object.
In some embodiments, the method further comprises: determining the final value of the target object according to at least one of the order quantity of the target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object; and feeding back the final value of the target object.
In some embodiments, before inputting the user information of the target object and the attribute information of the target object corresponding to each user into the trained user-object matching model, and generating the target behavior result of each user and the first target behavior execution rate of each user, the method further includes: and preprocessing the user information of the target object and the attribute information of the target object corresponding to each user to obtain the processed user information of the target object and the attribute information of the target object corresponding to each user, wherein the preprocessing is used for representing that the user information of the target object and the attribute information of the target object corresponding to each user are encoded to become machine learning readable data.
In a second aspect, an embodiment of the present application provides an information query apparatus, where the apparatus includes: an obtaining unit configured to obtain, in response to receiving an information query request, user information of a target object corresponding to the request and attribute information of the target object corresponding to each user, wherein the attribute information includes: attribute values of the respective attributes; the generating unit is configured to input the user information of the target object and the attribute information of the target object corresponding to each user into the trained user and object matching model, and generate a target behavior result of each user and a first target behavior execution rate of each user, wherein the first target behavior execution rate is used for representing the probability that the target behavior result of the user is ordering; a first determining unit configured to determine at least one of the following target object data according to the target behavior results of all users and the first target behavior execution rates of all users: the order quantity, the difference value between the sale value and the cost of the target object and a second target behavior execution rate, wherein the second target behavior execution rate is used for representing the comparison relation between the order quantity of the target object and the total target behavior quantity of the target object; an optimization unit configured to determine final attribute information of the target object by using an optimization algorithm according to at least one of a purchase order amount of the target object, a difference value between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object, wherein the final attribute information of the target object is an optimal combination of attribute values of respective attributes of the target object; a first feedback unit configured to feed back final attribute information of the target object.
In some embodiments, the user and object matching model in the generating unit is trained using the following modules: the acquisition module is configured to acquire a training sample set, wherein training samples in the training sample set comprise user information of target objects, attribute information of the target objects corresponding to each user, a target behavior result of each user and a first target behavior execution rate of each user, and the user information is user information of all users in a certain historical time; and the training module is configured to use a deep learning algorithm to take the user information of the target object and the attribute information of the target object corresponding to each user, which are included in the training sample set, as input data, take the target behavior result of each user and the first target behavior execution rate of each user, which correspond to the input user information of the target object and the attribute information of the target object corresponding to each user, as expected output data, and train to obtain a user-object matching model.
In some embodiments, the obtaining unit comprises: the extraction module is configured to analyze the content of the request and extract preset information, wherein the preset information represents that the user information of the target object and the attribute information of the target object are preset; the acquisition module is configured to acquire user information of the target object and attribute information of the target object corresponding to each user according to preset information.
In some embodiments, the final attribute information of the target object in the optimization unit is generated by performing a plurality of iterative operations; the iterative operations in the optimization unit include: judging whether at least one of the order quantity of the current target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition, if not, continuing to execute and skipping to judge whether at least one of the order quantity of the current target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition; if so, taking the attribute information of the current target object meeting the iteration stop condition as the final attribute information of the target object, wherein the iteration stop condition is as follows: the value calculated based on the optimization algorithm is less than a predetermined threshold.
In some embodiments, the optimization unit is further configured to determine final attribute information of the target object by using an optimization algorithm according to at least one of a next order amount of the target object, a difference value between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object, and a constraint condition, wherein the constraint condition characterizes a relationship constraint between different attributes of the target object.
In some embodiments, the apparatus further comprises: a second determination unit configured to determine a final value of the target object according to at least one of a next order amount of the target object, a difference value of a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object; a second feedback unit configured to feed back a final value of the target object.
In some embodiments, the apparatus further comprises: and the preprocessing unit is configured to preprocess the user information of the target object and the attribute information of the target object corresponding to each user to obtain the processed user information of the target object and the attribute information of the target object corresponding to each user, wherein the preprocessing is used for representing that the user information of the target object and the attribute information of the target object corresponding to each user are encoded to be machine learning readable data.
In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to implement the method as described in any one of the implementations of the first aspect.
In a fourth aspect, embodiments of the present application provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method as described in any one of the implementations of the first aspect.
According to the technology of the application, the user information of the target object corresponding to the request and the attribute information of the target object corresponding to each user are obtained in response to the received information query request, the user information of the target object and the attribute information of the target object corresponding to each user are input into a trained user-object matching model, a target behavior result of each user and a first target behavior execution rate of each user are generated, and at least one of the following target object data is determined according to the target behavior results of all users and the first target behavior execution rates of all users: the method comprises the steps of determining the final attribute information of a target object by using an optimization algorithm according to at least one of the lower order quantity of the target object, the difference between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object, and feeding back the final attribute information of the target object, so that the problems that the investigation quality is difficult to guarantee by using a questionnaire to collect user requirements in the prior art, the obtained conclusion is not high in credibility, and the ideal sales volume is difficult to obtain after the product is put into the market are solved, meanwhile, the problem that the user attention attribute is determined by analyzing and comparing the user behavior in the prior art is solved, the analysis conclusion depends on a data analysis method selected by personal experience, the subjectivity is strong, and the quantitative relation between different product attributes and core market indexes cannot be given, the problem that the condition of the product after being put on the market in the future is difficult to predict is solved, and the quantitative relation between the product attribute and the market reaction is established; by predicting the market reaction of products with different attributes, the quantitative relation between the different product attributes and the core market indexes is given, the reverse customization of the new product attributes of the products is realized, the manufacturers are further helped to improve the attribute design of the products, and the products which are popular in the market are customized.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application.
Fig. 1 is a schematic diagram of a first embodiment of an information query method according to the present application;
FIG. 2 is a diagram of a scenario in which an information query method according to an embodiment of the present application may be implemented;
FIG. 3 is a schematic diagram of a second embodiment of an information query method according to the present application;
FIG. 4 is a schematic diagram of a third embodiment of an information query method according to the present application;
FIG. 5 is a schematic diagram of an embodiment of an information query device according to the present application;
fig. 6 is a block diagram of an electronic device for implementing an information query method according to an embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows a schematic diagram 100 of a first embodiment of an information query method according to the present application. The information query method comprises the following steps:
In this embodiment, after receiving the information query request, the execution subject may obtain, from other electronic devices or locally, user information of a target object corresponding to the request and attribute information of the target object corresponding to each user in a wired connection manner or a wireless connection manner, where the attribute information includes: and attribute values of various attributes of the product. The user information may include user basic information (e.g., age, gender, registration time, etc.), user active characteristics (e.g., search, browse, focus, join a shopping cart, etc.), product preference characteristics (e.g., number of times a product of different price segments is browsed, number of times a product of different product attributes is joined to a shopping cart.
And 102, inputting the user information of the target object and the attribute information of the target object corresponding to each user into the trained user and object matching model, and generating a target behavior result of each user and a first target behavior execution rate of each user.
In this embodiment, the electronic device or a server in local remote communication connection with the electronic device may store a pre-trained user-object matching model, and the execution main body inputs user information of a target object and attribute information of the target object corresponding to each user into the trained user-object matching model, and generates a target behavior result of each user and a first target behavior execution rate of each user. The first target behavior execution rate is used for representing the probability that the target behavior result of the user is ordering. It should be noted that the user and object matching model may be, for example, a data table or a calculation formula, and the present embodiment does not limit the content in this respect.
103, determining at least one item of the following target object data according to the target behavior results of all the users and the first target behavior execution rates of all the users: a lower order amount, a difference between a sale value and a cost of the target object, and a second target behavior execution rate.
In this embodiment, the executing agent may determine at least one of the following target object data by using an algorithm according to the target behavior results of all users and the first target behavior execution rates of all users: a lower order amount, a difference between a sale value and a cost of the target object, and a second target behavior execution rate. The lower unit may be the total number of users and the average purchase probability of all users, for example, after ten thousand users are obtained from the user and object matching model, the lower unit of the target object is 10000 the average purchase probability. The difference between the sales value and the cost of the target object may be the profit of the target object. The second target behavior execution rate is used for representing the comparison relation between the order placing quantity of the target object and the total target behavior quantity of the target object. The target behavior may include ordering, buying, etc.
And 104, determining final attribute information of the target object by using an optimization algorithm according to at least one of the order quantity of the target object, the difference value between the sale value of the target object and the cost of the target object and the second target behavior execution rate of the target object.
In this embodiment, the execution subject determines final attribute information of the target object by using an optimization algorithm according to at least one of the order placing amount of the target object, the difference between the selling value of the target object and the cost of the target object, and the second target behavior execution rate of the target object, which are determined in step 103, where the final attribute information of the target object is an optimal combination of attribute values of each attribute of the target object. The optimization algorithm may find the attribute information of the target object with the largest profit of the product object or the largest execution rate of the target behavior as the final attribute information of the target object.
And step 105, feeding back final attribute information of the target object.
In this embodiment, the execution subject may feed back the final attribute information of the target object, so as to provide other services for the user based on the analysis result of the final attribute information.
With continued reference to fig. 2, the information query method 200 of the present embodiment is executed in the electronic device 201. When the electronic device 201 receives an information query request, first, user information of a target object corresponding to the request and attribute information 202 of the target object corresponding to each user are obtained, then, the user information of the target object and the attribute information of the target object corresponding to each user are input into a trained user-object matching model, a target behavior result of each user and a first target behavior execution rate 203 of each user are generated, and then, according to the target behavior results of all users and the first target behavior execution rates of all users, the electronic device 201 determines at least one of the following target object data: the electronic device 201 determines final attribute information 205 of the target object by using an optimization algorithm according to at least one of the amount of the order of the target object, the difference between the selling value of the target object and the cost of the target object, and the second target behavior execution rate 204, and finally the electronic device 201 feeds back the final attribute information 206 of the target object.
In the method provided by the above embodiment of the present application, in response to receiving an information query request, user information of a target object corresponding to the request and attribute information of the target object corresponding to each user are obtained, the user information of the target object and the attribute information of the target object corresponding to each user are input to a trained user-object matching model, a target behavior result of each user and a first target behavior execution rate of each user are generated, and at least one of the following target object data is determined according to the target behavior results of all users and the first target behavior execution rates of all users: the method comprises the steps of determining the final attribute information of a target object by using an optimization algorithm according to at least one of the lower order quantity of the target object, the difference between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object, and feeding back the final attribute information of the target object, so that the problems that the investigation quality is difficult to guarantee by using a questionnaire to collect user requirements in the prior art, the obtained conclusion is not high in credibility, and the ideal sales volume is difficult to obtain after the product is put into the market are solved, meanwhile, the problem that the user attention attribute is determined by analyzing and comparing the user behavior in the prior art is solved, the analysis conclusion depends on a data analysis method selected by personal experience, the subjectivity is strong, and the quantitative relation between different product attributes and core market indexes cannot be given, the problem that the condition of the product after being put on the market in the future is difficult to predict is solved, and the quantitative relation between the product attribute and the market reaction is established; by predicting the market reaction of products with different attributes, the quantitative relation between the different product attributes and the core market indexes is given, the reverse customization of the new product attributes of the products is realized, the manufacturers are further helped to improve the attribute design of the products, and the products which are popular in the market are customized.
With further reference to fig. 3, a schematic diagram 300 of a second embodiment of an information query method is shown. The process of the method comprises the following steps:
In some optional implementation manners of this embodiment, the obtaining user information of the target object corresponding to the request and attribute information of the target object corresponding to each user includes: analyzing the content of the request, and extracting preset information, wherein the preset information represents that the user information of the target object and the attribute information of the target object are preset; and acquiring user information of the target object and attribute information of the target object corresponding to each user according to the preset information. Product information analysis aiming at the attribute of the customized product is realized, and a more targeted and accurate product market prediction and analysis result is obtained.
In this embodiment, the user and object matching model is obtained by the following training method: acquiring a training sample set, wherein training samples in the training sample set comprise user information of a target object, attribute information of the target object corresponding to each user, a target behavior result of each user and a first target behavior execution rate of each user, and the user information is user information of all users in a certain historical time; by utilizing a deep learning algorithm, the user information of the target object and the attribute information of the target object corresponding to each user, which are included in the training samples in the training sample set, are used as input data, the target behavior result of each user and the first target behavior execution rate of each user, which correspond to the input user information of the target object and the attribute information of the target object corresponding to each user, are used as expected output data, and a user-object matching model is obtained through training, namely model parameters of the user-object matching model are determined. For example, the user-object matching model may use a user who browses the target object for a period of time (e.g., within one month) as a training sample, and if the user browses but does not purchase within a future period of time (e.g., within 5 days), the user is considered to have a purchase result of the target object as not purchased, and the sample label is set to 0; when the target object is viewed and purchased, the sample tag is set to 1 assuming that the purchase result of the target object by the user is purchase. By learning the purchasing preference of a large number of users for different attribute objects, the market selection of the different attribute objects can be simulated.
And step 304, determining final attribute information of the target object by using an optimization algorithm according to at least one of the amount of orders of the target object, the difference value between the sale value of the target object and the cost of the target object, the second target behavior execution rate of the target object and the constraint condition.
In this embodiment, the execution subject determines final attribute information of the target object by using an optimization algorithm according to at least one of a next order amount of the target object, a difference between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object, based on the constraint condition. The constraint condition characterization carries out relationship constraint on different attributes of the target object. There is usually some constraint relationship between the product attributes, for example, there is an equality constraint between length, width, height and volume, so the constraint condition is related to the product attribute, and the constraint relationship of the product attribute can be set by the manufacturer. The intelligent search is realized, and the system precision is improved.
In the present embodiment, the final attribute information of the target object is generated by performing the iterative operation a plurality of times; the iterative operation comprises: judging whether at least one of the order quantity of the current target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition, if not, continuing to execute and skipping to judge whether at least one of the order quantity of the current target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition; if so, taking the attribute information of the current target object meeting the iteration stop condition as the final attribute information of the target object, wherein the iteration stop condition is as follows: the value calculated based on the optimization algorithm is less than a predetermined threshold. By setting the iteration stop condition, the final attribute information is flexibly determined, the processing resource of the system is saved, and the efficiency of system information query is improved.
And 305, determining the final value of the target object according to at least one of the order amount of the target object, the difference value between the sale value of the target object and the cost of the target object and the second target behavior execution rate of the target object.
In this embodiment, the execution subject may determine the final value of the target object according to at least one of a next order amount of the target object, a difference between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object. Taking the target object as a refrigerator category as an example, the execution subject may fix attribute information other than a product value (i.e., price) in advance, maximize a difference between a sale value of the target object and a cost of the target object, automatically search for the value of the target object based on a fixed price range, and determine that an optimal pricing of the final target object is a final value of the target object.
And step 306, feeding back the final attribute information of the target object and the final value of the target object.
In this embodiment, the execution subject may feed back final attribute information of the target object and a final value of the target object.
In this embodiment, the specific operations of steps 301 and 303 are substantially the same as the operations of steps 101 and 103 in the embodiment shown in fig. 1, and are not described again here.
It should be noted that the deep learning algorithm is a well-known technology widely studied and applied at present, and is not described herein again. A technician may set a model structure of the user and object matching model according to actual requirements, which is not limited in the embodiment of the present disclosure.
As can be seen from fig. 3, compared with the embodiment corresponding to fig. 1, the schematic diagram 300 of the information query method in this embodiment determines the final attribute information of the target object by using an optimization algorithm according to at least one of the amount of the order of the target object, the difference between the sale value of the target object and the cost of the target object, and the second target behavior execution rate of the target object, and the constraint condition, so that the intelligent search of information is realized, and the system precision is improved; based on the trained user and object matching model, matching of each attribute information of the target object is carried out, and matching precision is improved; and determining the final value of the target object according to at least one of the order quantity of the target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object, so that the optimal price of the product to be put into the market in the future can be estimated, and the price adjustment of the product can be further realized.
With further reference to fig. 4, a schematic diagram 400 of a third embodiment of an information query method is shown. The process of the method comprises the following steps:
In this embodiment, the first time period may represent before the property of the target object is changed, and the second time period may represent after the property of the target object is changed.
In this embodiment, the execution main body pre-processes the user information of the target object and the attribute information of the target object corresponding to each user (for example, performs one-hot encoding), converts the information category variable into a form that is easily utilized by a machine learning algorithm, and obtains the processed user information of the target object and the attribute information of the target object corresponding to each user in different time periods. The preprocessing is used for representing that the user information of the target object and the attribute information of the target object corresponding to each user are encoded to become machine learning readable data, and the capability of system information analysis is improved.
And step 405, determining final attribute information of the target object in the first time period and final attribute information of the target object in the second time period by using an optimization algorithm according to at least one of order placing quantity of the target object in different time periods, a difference value between the selling value of the target object and the cost of the target object and a second target behavior execution rate of the target object.
In this embodiment, the execution main body determines the upgrading scheme of the target object after comparing and analyzing the final attribute information of the target object in the first time period (before the product attribute is changed) and the second time period (after the product attribute is changed).
In some optional implementations of this embodiment, the method further includes: and determining the upgrading scheme of the target object according to the final attribute information of the target object and the final value of the target object.
In this embodiment, the specific operations of steps 401, 403, 404, and 405 are substantially the same as the operations of steps 101, 102, 103, and 104 in the embodiment shown in fig. 1, and are not described again here.
As can be seen from fig. 4, compared with the embodiment corresponding to fig. 1, the schematic diagram 400 of the information query method in this embodiment employs pre-processing of the user information of the target object and the attribute information of the target object corresponding to each user to obtain the processed user information of the target object and the attribute information of the target object corresponding to each user, so that the capability of analyzing the system information is improved; the method comprises the steps of determining an upgrading scheme of a target object by adopting the final attribute information of the target object in a first time period and the final attribute information of the target object in a second time period, and performing market reaction evaluation on the information before and after the attribute of the target object is changed respectively to see the order placing quantity (product sales quantity) of the target object, the difference value (product profit) between the sale value of the target object and the cost of the target object and the change of the second target behavior execution rate (product conversion rate) of the target object caused by the attribute change, so as to provide objective estimation for the attribute change of the target object, further determine the upgrading scheme of the target object and realize product upgrading.
With further reference to fig. 5, as an implementation of the method shown in fig. 1, the present application provides an embodiment of an information query apparatus, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 1, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 5, the information query apparatus 500 of the present embodiment includes: an acquisition unit 501, a generation unit 502, a first determination unit 503, an optimization unit 504, and a first feedback unit 505. An obtaining unit configured to obtain, in response to receiving an information query request, user information of a target object corresponding to the request and attribute information of the target object corresponding to each user, wherein the attribute information includes: attribute values of the respective attributes; the generating unit is configured to input the user information of the target object and the attribute information of the target object corresponding to each user into the trained user and object matching model, and generate a target behavior result of each user and a first target behavior execution rate of each user, wherein the first target behavior execution rate is used for representing the probability that the target behavior result of the user is ordering; a first determining unit configured to determine at least one of the following target object data according to the target behavior results of all users and the first target behavior execution rates of all users: the order quantity, the difference value between the sale value and the cost of the target object and a second target behavior execution rate, wherein the second target behavior execution rate is used for representing the comparison relation between the order quantity of the target object and the total target behavior quantity of the target object; an optimization unit configured to determine final attribute information of the target object by using an optimization algorithm according to at least one of a purchase order amount of the target object, a difference value between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object, wherein the final attribute information of the target object is an optimal combination of attribute values of respective attributes of the target object; a first feedback unit configured to feed back final attribute information of the target object.
In this embodiment, specific processes of the obtaining unit 501, the generating unit 502, the first determining unit 503, the optimizing unit 504, and the first feedback unit 505 of the information query apparatus 500 and technical effects brought by the specific processes may respectively refer to the related descriptions of step 101 to step 105 in the embodiment corresponding to fig. 1, and are not repeated herein.
In some optional implementations of this embodiment, the user and object matching model in the generating unit is obtained by training using the following modules: the acquisition module is configured to acquire a training sample set, wherein training samples in the training sample set comprise user information of target objects, attribute information of the target objects corresponding to each user, a target behavior result of each user and a first target behavior execution rate of each user, and the user information is user information of all users in a certain historical time; and the training module is configured to use a deep learning algorithm to take the user information of the target object and the attribute information of the target object corresponding to each user, which are included in the training sample set, as input data, take the target behavior result of each user and the first target behavior execution rate of each user, which correspond to the input user information of the target object and the attribute information of the target object corresponding to each user, as expected output data, and train to obtain a user-object matching model.
In some optional implementation manners of this embodiment, the obtaining unit includes: the extraction module is configured to analyze the content of the request and extract preset information, wherein the preset information represents that the user information of the target object and the attribute information of the target object are preset; the acquisition module is configured to acquire user information of the target object and attribute information of the target object corresponding to each user according to preset information.
In some optional implementations of this embodiment, the final attribute information of the target object in the optimization unit is generated by performing a plurality of iteration operations; the iterative operations in the optimization unit include: judging whether at least one of the order quantity of the current target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition, if not, continuing to execute and skipping to judge whether at least one of the order quantity of the current target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition; if so, taking the attribute information of the current target object meeting the iteration stop condition as the final attribute information of the target object, wherein the iteration stop condition is as follows: the value calculated based on the optimization algorithm is less than a predetermined threshold.
In some optional implementations of the embodiment, the optimization unit is further configured to determine final attribute information of the target object by using an optimization algorithm according to at least one of a next order amount of the target object, a difference between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object, and a constraint condition, where the constraint condition characterizes a relationship constraint between different attributes of the target object.
In some optional implementations of this embodiment, the apparatus further includes: a second determination unit configured to determine a final value of the target object according to at least one of a next order amount of the target object, a difference value of a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object; a second feedback unit configured to feed back a final value of the target object.
In some optional implementations of this embodiment, the apparatus further includes: and the preprocessing unit is configured to preprocess the user information of the target object and the attribute information of the target object corresponding to each user to obtain the processed user information of the target object and the attribute information of the target object corresponding to each user, wherein the preprocessing is used for representing that the user information of the target object and the attribute information of the target object corresponding to each user are encoded to be machine learning readable data.
Fig. 6 is a block diagram of an electronic device according to an information query method in an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 6, the electronic apparatus includes: one or more processors 601, memory 602, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 6, one processor 601 is taken as an example.
The memory 602 is a non-transitory computer readable storage medium as provided herein. The memory stores instructions executable by the at least one processor, so that the at least one processor executes the information query method provided by the application. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to execute the information query method provided by the present application.
The memory 602, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the information query method in the embodiment of the present application (for example, the obtaining unit 501, the generating unit 502, the first determining unit 503, the optimizing unit 504, and the first feedback unit 505 shown in fig. 5). The processor 601 executes various functional applications of the server and data processing, i.e., implements the information query method in the above method embodiments, by running non-transitory software programs, instructions, and modules stored in the memory 602.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the information inquiry electronic device, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 optionally includes memory located remotely from the processor 601, and such remote memory may be coupled to the querying electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the information query method may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 may be connected by a bus or other means, and fig. 6 illustrates the connection by a bus as an example.
The input device 603 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the information-querying electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or other input devices. The output devices 604 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme of the embodiment of the application, the user information of the target object corresponding to the request and the attribute information of the target object corresponding to each user are obtained in response to the received information query request, the user information of the target object and the attribute information of the target object corresponding to each user are input into the trained user-object matching model, the target behavior result of each user and the first target behavior execution rate of each user are generated, and at least one of the following target object data is determined according to the target behavior results of all users and the first target behavior execution rates of all users: the method comprises the steps of determining the final attribute information of a target object by using an optimization algorithm according to at least one of the lower order quantity of the target object, the difference between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object, and feeding back the final attribute information of the target object, so that the problems that the investigation quality is difficult to guarantee by using a questionnaire to collect user requirements in the prior art, the obtained conclusion is not high in credibility, and the ideal sales volume is difficult to obtain after the product is put into the market are solved, meanwhile, the problem that the user attention attribute is determined by analyzing and comparing the user behavior in the prior art is solved, the analysis conclusion depends on a data analysis method selected by personal experience, the subjectivity is strong, and the quantitative relation between different product attributes and core market indexes cannot be given, the problem that the condition of the product after being put on the market in the future is difficult to predict is solved, and the quantitative relation between the product attribute and the market reaction is established; by predicting the market reaction of products with different attributes, the quantitative relation between the different product attributes and the core market indexes is given, the reverse customization of the new product attributes of the products is realized, the manufacturers are further helped to improve the attribute design of the products, and the products which are popular in the market are customized.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present application can be achieved, and the present invention is not limited herein.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (16)
1. An information query method, the method comprising:
in response to receiving an information query request, obtaining user information of a target object corresponding to the request and attribute information of the target object corresponding to each user, wherein the attribute information includes: attribute values of the respective attributes;
inputting the user information of the target object and the attribute information of the target object corresponding to each user into a trained user and object matching model, and generating a target behavior result of each user and a first target behavior execution rate of each user, wherein the first target behavior execution rate is used for representing the probability that the target behavior result of the user is ordering;
determining at least one item of the following target object data according to the target behavior results of all users and the first target behavior execution rate of all users: the order quantity, the difference value of the sale value and the cost of the target object and a second target behavior execution rate, wherein the second target behavior execution rate is used for representing the comparison relation between the order quantity of the target object and the total target behavior quantity of the target object;
determining final attribute information of the target object by using an optimization algorithm according to at least one of order placing quantity of the target object, a difference value between sale value of the target object and cost of the target object and a second target behavior execution rate of the target object, wherein the final attribute information of the target object is an optimal combination of attribute values of all attributes of the target object;
and feeding back final attribute information of the target object.
2. The method of claim 1, wherein the user and object matching model is obtained by training as follows:
acquiring a training sample set, wherein training samples in the training sample set comprise user information of the target object, attribute information of the target object corresponding to each user, a target behavior result of each user and a first target behavior execution rate of each user, and the user information is user information of all users in a certain historical time;
and training to obtain a user-object matching model by using a deep learning algorithm, wherein the user information of the target object and the attribute information of the target object corresponding to each user, which are included in the training sample set training samples, are used as input data, and the target behavior result of each user and the first target behavior execution rate of each user, which correspond to the input user information of the target object and the attribute information of the target object corresponding to each user, are used as expected output data.
3. The method of claim 1, wherein the obtaining of the user information of the target object corresponding to the request and the attribute information of the target object corresponding to each of the users comprises:
analyzing the content of the request, and extracting preset information, wherein the preset information represents that the user information of the target object and the attribute information of the target object are preset;
and acquiring the user information of the target object and the attribute information of the target object corresponding to each user according to the preset information.
4. The method of claim 1, wherein the final attribute information of the target object is generated by performing a plurality of iterative operations; the iterative operation comprises:
judging whether at least one of the current order placing quantity of the target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets an iteration stop condition, if not, continuing to execute and skipping to judge whether at least one of the current order placing quantity of the target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition; if yes, taking the attribute information of the current target object meeting the iteration stop condition as the final attribute information of the target object, wherein the iteration stop condition is as follows: the value calculated based on the optimization algorithm is less than a predetermined threshold.
5. The method of claim 1, wherein the determining the final attribute information of the target object by using an optimization algorithm according to at least one of an order amount of the target object, a difference between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object comprises:
and determining final attribute information of the target object by using an optimization algorithm according to at least one of the order placing quantity of the target object, the difference value of the sale value of the target object and the cost of the target object, and a second target behavior execution rate of the target object and a constraint condition, wherein the constraint condition represents that relationship constraint is carried out on different attributes of the target object.
6. The method of claim 1, further comprising:
determining a final value of the target object according to at least one of an order placing amount of the target object, a difference value between a selling value of the target object and a cost of the target object, and a second target behavior execution rate of the target object;
and feeding back the final value of the target object.
7. The method according to claim 1, before the inputting the user information of the target object and the attribute information of the target object corresponding to each user into the trained user-object matching model and generating the target behavior result of each user and the first target behavior execution rate of each user, further comprising:
and preprocessing the user information of the target object and the attribute information of the target object corresponding to each user to obtain the processed user information of the target object and the attribute information of the target object corresponding to each user, wherein the preprocessing is used for representing that the user information of the target object and the attribute information of the target object corresponding to each user are encoded to become machine learning readable data.
8. An information querying device, the device comprising:
an obtaining unit configured to obtain, in response to receiving an information query request, user information of a target object corresponding to the request and attribute information of the target object corresponding to each of the users, wherein the attribute information includes: attribute values of the respective attributes;
the generating unit is configured to input the user information of the target object and the attribute information of the target object corresponding to each user into a trained user and object matching model, and generate a target behavior result of each user and a first target behavior execution rate of each user, wherein the first target behavior execution rate is used for representing the probability that the target behavior result of the user is ordering;
a first determining unit configured to determine at least one of the following target object data according to the target behavior results of all users and the first target behavior execution rates of all users: the order quantity, the difference value of the sale value and the cost of the target object and a second target behavior execution rate, wherein the second target behavior execution rate is used for representing the comparison relation between the order quantity of the target object and the total target behavior quantity of the target object;
an optimization unit configured to determine final attribute information of the target object by using an optimization algorithm according to at least one of an order placing amount of the target object, a difference value between a selling value of the target object and a cost of the target object, and a second target behavior execution rate of the target object, wherein the final attribute information of the target object is an optimal combination of attribute values of each attribute of the target object;
a first feedback unit configured to feed back final attribute information of the target object.
9. The apparatus of claim 8, wherein the user and object matching model in the generating unit is trained using:
an obtaining module, configured to obtain a training sample set, where a training sample in the training sample set includes user information of the target object, attribute information of the target object corresponding to each user, a target behavior result of each user, and a first target behavior execution rate of each user, and the user information is user information of a total number of users in a certain historical time;
and the training module is configured to use a deep learning algorithm to take the user information of the target object and the attribute information of the target object corresponding to each user, which are included in the training samples in the training sample set, as input data, and take the target behavior result of each user and the first target behavior execution rate of each user, which correspond to the input user information of the target object and the attribute information of the target object corresponding to each user, as expected output data, and train to obtain a user-object matching model.
10. The apparatus of claim 8, wherein the obtaining unit comprises:
the extraction module is configured to analyze the content of the request and extract preset information, wherein the preset information represents that the user information of the target object and the attribute information of the target object are preset;
and the acquisition module is configured to acquire the user information of the target object and the attribute information of the target object corresponding to each user according to the preset information.
11. The apparatus of claim 8, wherein the final property information of the target object in the optimization unit is generated by performing a plurality of iterative operations; the iterative operations in the optimization unit include: judging whether at least one of the current order placing quantity of the target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets an iteration stop condition, if not, continuing to execute and skipping to judge whether at least one of the current order placing quantity of the target object, the difference value between the selling value of the target object and the cost of the target object and the second target behavior execution rate of the target object meets the iteration stop condition; if yes, taking the attribute information of the current target object meeting the iteration stop condition as the final attribute information of the target object, wherein the iteration stop condition is as follows: the value calculated based on the optimization algorithm is less than a predetermined threshold.
12. The apparatus of claim 8, wherein the optimization unit is further configured to determine final attribute information of the target object by using an optimization algorithm according to at least one of a purchase amount of the target object, a difference value between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object, and a constraint condition, wherein the constraint condition characterizes a relationship constraint between different attributes of the target object.
13. The apparatus of claim 8, further comprising:
a second determination unit configured to determine a final value of the target object according to at least one of a purchase amount of the target object, a difference value between a sale value of the target object and a cost of the target object, and a second target behavior execution rate of the target object;
a second feedback unit configured to feed back a final value of the target object.
14. The apparatus of claim 8, further comprising:
and the preprocessing unit is configured to preprocess the user information of the target object and the attribute information of the target object corresponding to each user to obtain the processed user information of the target object and the attribute information of the target object corresponding to each user, wherein the preprocessing is used for representing that the user information of the target object and the attribute information of the target object corresponding to each user are encoded to be machine learning readable data.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011272831.6A CN112308629A (en) | 2020-11-13 | 2020-11-13 | Information query method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011272831.6A CN112308629A (en) | 2020-11-13 | 2020-11-13 | Information query method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112308629A true CN112308629A (en) | 2021-02-02 |
Family
ID=74334634
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011272831.6A Pending CN112308629A (en) | 2020-11-13 | 2020-11-13 | Information query method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112308629A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100961782B1 (en) * | 2009-05-28 | 2010-06-07 | 주식회사 모임 | Apparatus and method for presenting personalized goods information based on artificial intelligence, and recording medium thereof |
US20110314031A1 (en) * | 2010-03-29 | 2011-12-22 | Ebay Inc. | Product category optimization for image similarity searching of image-based listings in a network-based publication system |
US20170103451A1 (en) * | 2015-10-12 | 2017-04-13 | Yandex Europe Ag | Method and system of determining an optimal value of an auction parameter for a digital object |
CN109903108A (en) * | 2017-12-08 | 2019-06-18 | 北京京东尚科信息技术有限公司 | Information processing method and device |
CN111310038A (en) * | 2020-02-06 | 2020-06-19 | 腾讯科技(深圳)有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
CN111340581A (en) * | 2020-02-11 | 2020-06-26 | 拉扎斯网络科技(上海)有限公司 | Data processing method and device, readable storage medium and electronic equipment |
CN111429164A (en) * | 2019-01-10 | 2020-07-17 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
CN111461757A (en) * | 2019-11-27 | 2020-07-28 | 北京沃东天骏信息技术有限公司 | Information processing method and device, computer storage medium and electronic equipment |
CN111709842A (en) * | 2020-06-18 | 2020-09-25 | 中国工商银行股份有限公司 | Product parameter adjustment method and apparatus, system, and medium executed by electronic device |
-
2020
- 2020-11-13 CN CN202011272831.6A patent/CN112308629A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100961782B1 (en) * | 2009-05-28 | 2010-06-07 | 주식회사 모임 | Apparatus and method for presenting personalized goods information based on artificial intelligence, and recording medium thereof |
US20110314031A1 (en) * | 2010-03-29 | 2011-12-22 | Ebay Inc. | Product category optimization for image similarity searching of image-based listings in a network-based publication system |
US20170103451A1 (en) * | 2015-10-12 | 2017-04-13 | Yandex Europe Ag | Method and system of determining an optimal value of an auction parameter for a digital object |
CN109903108A (en) * | 2017-12-08 | 2019-06-18 | 北京京东尚科信息技术有限公司 | Information processing method and device |
CN111429164A (en) * | 2019-01-10 | 2020-07-17 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
CN111461757A (en) * | 2019-11-27 | 2020-07-28 | 北京沃东天骏信息技术有限公司 | Information processing method and device, computer storage medium and electronic equipment |
CN111310038A (en) * | 2020-02-06 | 2020-06-19 | 腾讯科技(深圳)有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
CN111340581A (en) * | 2020-02-11 | 2020-06-26 | 拉扎斯网络科技(上海)有限公司 | Data processing method and device, readable storage medium and electronic equipment |
CN111709842A (en) * | 2020-06-18 | 2020-09-25 | 中国工商银行股份有限公司 | Product parameter adjustment method and apparatus, system, and medium executed by electronic device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108205768B (en) | Database establishing method, data recommending device, equipment and storage medium | |
KR102472572B1 (en) | Method for profiling user's intention and apparatus therefor | |
CN111259222B (en) | Article recommendation method, system, electronic equipment and storage medium | |
CN111311321B (en) | User consumption behavior prediction model training method, device, equipment and storage medium | |
CN112261423B (en) | Method, device, equipment and storage medium for pushing information | |
US20150356658A1 (en) | Systems And Methods For Serving Product Recommendations | |
KR20190007875A (en) | Method for providing marketing management data for optimization of distribution and logistic and apparatus therefor | |
CN112163676A (en) | Multitask service prediction model training method, device, equipment and storage medium | |
US20220122100A1 (en) | Product evaluation system and method of use | |
CN111506803B (en) | Content recommendation method and device, electronic equipment and storage medium | |
CN113781149B (en) | Information recommendation method and device, computer readable storage medium and electronic equipment | |
CN112528153A (en) | Content recommendation method, device, equipment, storage medium and program product | |
CN112365283A (en) | Coupon issuing method, device, terminal equipment and storage medium | |
CN112925978A (en) | Recommendation system evaluation method and device, electronic equipment and storage medium | |
CN112288483A (en) | Method and device for training model and method and device for generating information | |
CN115935185A (en) | Training method and device for recommendation model | |
US20240242259A1 (en) | Method and device for information analysis | |
CN112541145B (en) | Page display method, device, equipment and storage medium | |
CA2909957A1 (en) | Large-scale customer-product relationship mapping and contact scheduling | |
CN110490682B (en) | Method and device for analyzing commodity attributes | |
CN112308629A (en) | Information query method and device | |
CN113240487B (en) | Flow regulation and control method and device | |
CN112084410A (en) | Document type recommendation method and device, electronic equipment and readable storage medium | |
CN112508599B (en) | Information feedback method and device | |
CN113240465B (en) | Information generation method and device |
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 |