CN113111904A - Method and device for selecting attributes of target object based on commodity selling - Google Patents

Method and device for selecting attributes of target object based on commodity selling Download PDF

Info

Publication number
CN113111904A
CN113111904A CN202110090104.6A CN202110090104A CN113111904A CN 113111904 A CN113111904 A CN 113111904A CN 202110090104 A CN202110090104 A CN 202110090104A CN 113111904 A CN113111904 A CN 113111904A
Authority
CN
China
Prior art keywords
data
attribute
target object
objects
similar
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
Application number
CN202110090104.6A
Other languages
Chinese (zh)
Inventor
晁华
曾程昊
戚汝鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Ubox Technology Co ltd
Original Assignee
Shenzhen Ubox Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Ubox Technology Co ltd filed Critical Shenzhen Ubox Technology Co ltd
Priority to CN202110090104.6A priority Critical patent/CN113111904A/en
Publication of CN113111904A publication Critical patent/CN113111904A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Game Theory and Decision Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention belongs to the technical field of commodity sale, and discloses a method and a device for selecting attributes of a target object based on commodity sale. The method is applied to a commodity selling client and comprises the following steps: acquiring original data of at least two objects, and preprocessing the original data to obtain first data; acquiring identifications of at least two objects and corresponding first data to form a characteristic vector matrix; carrying out similarity calculation on any two eigenvectors in the eigenvector matrix, obtaining a preset similarity threshold value, and matching at least one similar object from the objects; according to the first data of the similar objects, calculating the prediction data of the target object to obtain second data; comparing the second data with the first data one by one, and judging whether the second data accords with the first data; and when the second data is determined to be consistent with the first data, adding or replacing the attribute on the target object. The method of the invention can realize the selection of the sold goods.

Description

Method and device for selecting attributes of target object based on commodity selling
Technical Field
The invention relates to the technical field of commodity sale, in particular to a method and a device for selecting attributes of a target object based on commodity sale.
Background
In the traditional vending machine operation, the vending machine commodity is selected highly depending on the experience of operators, but the manual experience is limited, and the manual experience cannot be well applied due to the conditions of personnel change, environmental change and the like. Especially in some scenarios, manual experience has certain limitations. For example, in general, an operator may select goods with reference to the type of the location where the vending machine is located, which may result in highly consistent goods types of the vending machine in the same type of location, thereby lacking in diversity and personalization; on the other hand, the manual experience lacks the capability of summarizing the sales rule from a higher dimension, the vending machine should not be classified only according to simple features such as places, and the classification and similarity judgment of the high dimension can provide more refined operation.
In the traditional process of selecting commodities through manual experience, the consideration of places is a simple process of finding similar vending machines. However, the idea is too simple, and there is a certain difference between vending machines in the same place. Therefore, a method for calculating the similarity degree between vending machines is needed, which can predict the sales volume of the goods not sold on the vending machine, and recommend the goods with high sales volume on the similar vending machine to the vending machine.
Disclosure of Invention
The invention aims to provide an attribute selection method based on a commodity selling target object, which aims to solve the technical problem of low accuracy of commodity selling selection in the related art.
In order to achieve the purpose, the invention provides the following scheme: an attribute selection method based on a target object sold by a commodity is applied to a commodity selling client, and the method comprises the following steps:
acquiring original data of at least two objects, and preprocessing the original data to obtain first data;
acquiring the identifications of at least two objects and the corresponding first data to form a characteristic vector matrix;
carrying out similarity calculation on any two eigenvectors in the eigenvector matrix, obtaining a preset similarity threshold value, and matching at least one similar object from the objects;
according to the first data of the similar object, calculating prediction data of a target object to obtain second data;
comparing the second data with the first data, and judging whether the second data accords with the first data;
and when the second data is determined to accord with the first data, adding or replacing the attribute on the target object.
Further, the preprocessing the raw data comprises: eliminating the exception of the original data; and/or carrying out homogenization treatment on the original data.
Further, the step of calculating the predicted data of the target object according to the first data of the similar object to obtain the second data comprises: acquiring the first data and a characteristic value corresponding to the first data, and judging whether the prediction data is available according to the characteristic value:
if the second data is available, obtaining the second data;
if not, the second data is discarded.
Further, the characteristic values include: the similarity of the similar objects, the number of the similar objects, the standard deviation between the similar objects, the classification of the places where the objects are located, and the category of the attributes.
Further, the matching at least one similar object from the objects comprises: assuming object a and object B, the feature vectors are a and B, respectively, the similarity between object a and object B, Sa, B:
Figure BDA0002912138710000021
further, the calculating the prediction data of the target object includes: assuming that the prediction data of the attribute x of the object a is Px, a, then:
Figure BDA0002912138710000031
wherein Sa, i is the similarity between object a and object i, n is the total number of similar objects, and Qx, i is the first data of attribute x on object i.
Further, the step of adding or replacing the attribute on the target object comprises: judging whether the prediction attribute exists on the target object;
if so, replacing the attribute on the target object with the predicted attribute in the similar object;
and if the prediction attribute does not exist, adding the prediction attribute in the similar object to the target object.
A second object of the present invention is to provide an attribute selection apparatus for a target object based on merchandise sales, comprising: the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring original data of at least two objects and preprocessing the original data to obtain first data;
the characteristic vector matrix module is used for acquiring the identifications of at least two objects and the corresponding first data to form a characteristic vector matrix;
the similarity calculation module is used for calculating the similarity of any two eigenvectors in the eigenvector matrix, acquiring a preset similarity threshold value and matching at least one similar object from the objects;
the predicted data calculation module is used for calculating predicted data of a target object according to the first data of the similar object to obtain second data;
the attribute selection module is used for comparing the second data with the first data and judging whether the second data accords with the first data; and when the second data is determined to accord with the first data, adding or replacing the attribute on the target object.
Further, the prediction data calculation module further comprises:
and the predicted data judging module is used for acquiring the first data and the characteristic value corresponding to the first data and judging whether the predicted data is available or not according to the characteristic value.
Further, the attribute selection module further comprises:
and the attribute judging module is used for judging whether the prediction attribute exists on the target object.
A third object of the present invention is to provide a computer device, comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.
A fourth object of the invention is to provide a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method as described above.
The invention has the beneficial effects that:
the embodiment of the invention provides a method for selecting attributes of a target object based on commodity selling, which comprises the following steps: acquiring original data of at least two objects, and preprocessing the original data to obtain first data; acquiring identifications of at least two objects and corresponding first data to form a characteristic vector matrix; carrying out similarity calculation on any two eigenvectors in the eigenvector matrix, obtaining a preset similarity threshold value, and matching at least one similar object from the objects; according to the first data of the similar objects, calculating the prediction data of the target object to obtain second data; comparing the second data with the first data one by one, and judging whether the second data accords with the first data; and when the second data is determined to be consistent with the first data, adding or replacing the attribute on the target object. According to the attribute selection method of the target object based on commodity selling, provided by the embodiment of the invention, the similar object is obtained by calculating the similarity of the object, and the commodity selling recommendation is carried out on the target object according to the similar object, so that more accurate mutual promotion of high-sales commodities 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 structures shown in the drawings without creative efforts.
Fig. 1 is a flowchart of a method for selecting an attribute of a target object according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that all the directional indicators (such as up, down, left, right, front, and rear … …) in the embodiment of the present invention are only used to explain the relative position relationship between the components, the movement situation, etc. in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indicator is changed accordingly.
It will also be understood that when an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present.
In addition, the descriptions related to "first", "second", etc. in the present invention are for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
The method aims to provide a commodity selling technology-based method for searching similar objects for target objects and replacing or adding attributes of the target objects according to the similar attributes of the similar objects.
The technical scheme of the invention is applied to the technical field of automatic vending, and in practical application, the commodity preference purchased by the user of one vending machine can be directly expressed by the sales condition of the existing commodity of the vending machine. Through similarity calculation between vending machines by using the sales volume of the commodities, potential association relation between the vending machines can be found, and the sales volume of the commodities which are not sold on the target vending machine can be predicted. And then replacing or adding the commodity on the target vending machine according to the predicted commodity sales volume. Thereby improve the accuracy that commodity were sold to the vending machine to satisfy user crowd's needs better, and improve the degree of accuracy of vending machine operation.
The present application is described below with reference to specific embodiments and specific application scenarios.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for selecting an attribute of a target object based on merchandise sales according to an embodiment of the present invention.
The embodiment of the invention provides an attribute selection method of a target object based on commodity selling, which is applied to a commodity selling client and executes the following steps:
s10: acquiring original data of at least two objects, and preprocessing the original data to obtain first data;
specifically, the preprocessing of the raw data includes: and eliminating the exception of the original data or carrying out homogenization treatment on the original data. In this way, calculation errors due to differences in data magnitude between different objects can be prevented. Wherein, the homogenization calculation formula is as follows: x2 ═ X1-Xmin)/(Xmax-Xmin), where X1 is the raw data and X2 is the first data after homogenization.
S20: acquiring identifications of at least two objects and corresponding first data to form a characteristic vector matrix;
specifically, the step of forming the feature vector matrix is: the relationship between the object and the attribute is expressed in an N × M matrix. Wherein, the value "first data x, y" of the matrix represents the first data after data preprocessing of "attribute x" on "object y".
Attribute 1 Attribute 2 ... Attribute x ... Attribute M
Object 1 First data1,1 First data2,1 ... First datax,1 ... First dataM,1
... ... ... ... ... ... ...
Object y First data1,y First data2,y ... First datax,y ... First dataM,y
... ... ... ... ... ... ...
Object N First data1,N First data2,M ... First datax,N ... First dataM,N
S30: carrying out similarity calculation on any two eigenvectors in the eigenvector matrix, obtaining a preset similarity threshold value, and matching at least one similar object from the objects;
specifically, after calculating the similarity between all the objects, the first N most similar objects need to be selected for each target object. The preset similarity threshold is 0.85, that is, objects with similarity calculation values higher than 0.85 are all similar objects of the target object.
S40: according to the first data of the similar objects, calculating the prediction data of the target object to obtain second data;
s50: comparing the second data with the first data one by one, and judging whether the second data accords with the first data;
s60: and when the second data is determined to be consistent with the first data, adding or replacing the attribute on the target object.
In this way, the similar objects of the target object are determined by calculating the similarity degree between the objects according to the similarity on the similar objects
In one embodiment, the step of calculating the predicted data of the target object according to the first data of the similar objects to obtain the second data comprises: acquiring first data and a characteristic value corresponding to the first data, and judging whether the predicted data is available according to the characteristic value:
if available, obtaining second data;
if not, the second data is discarded.
And according to the characteristic value, judging whether the commodity prediction result is available or not, wherein the step is to calculate according to a preset recall algorithm. The method mainly comprises the step of judging whether calculated prediction data accords with first data or not by inputting a plurality of characteristic values by utilizing a machine learning gradient lifting tree algorithm (GBDT). The purpose of the recall algorithm setup is to retain the correct results as much as possible and discard the less accurate results so that the second data is discarded when the first data does not match the second data.
Specifically, the feature value is one or more of the similarity of similar objects, the number of similar objects, the standard deviation between similar objects, the classification of the place where the object is located, and the category of the attribute. Through the gradient lifting tree algorithm, whether the prediction data accords with the original data or not can be judged according to the original data on the existing object.
In one embodiment, matching at least one similar object from the objects comprises: assuming object a and object B, the feature vectors are a and B, respectively, the similarity between object a and object B, Sa, B:
Figure BDA0002912138710000081
specifically, the similarity calculation algorithm between any two objects is "cosine similarity method", and each row in the feature vector matrix is a feature vector of the object.
In one embodiment, calculating the prediction data for the target object comprises: assuming that the prediction data of the attribute x of the object a is Px, a, then:
Figure BDA0002912138710000082
wherein Sa, i is the similarity between object a and object i, n is the total number of similar objects, and Qx, i is the first data of attribute x on object i.
In one embodiment, the step of adding or replacing attributes on the target object comprises: judging whether a prediction attribute exists on the target object;
if yes, replacing the attribute on the target object with the predicted attribute in the similar object;
and if the prediction attribute does not exist, adding the prediction attribute in the similar object on the target object.
Specifically, the application of the prediction attribute on the target object is divided into two cases:
a. when the prediction attribute exists on the target object, selecting the attribute that the first data of the target object is smaller than the first data of the similar object, and replacing the attribute with the prediction attribute;
b. when the target object does not have the prediction attribute, the prediction attribute is directly added to the target object to replace the attribute in the target object.
In one embodiment, the first data of the A object is [ 10.50.2 x x1 ];
the first data of the B object is [ 10.60.20.80.11 ];
the first data of the C object is [ 10.40.20.2 x 1], where each digit corresponds to the value of an attribute, and x indicates that the attribute is not present on the object.
Through calculation, the similarity between the object A and the object B is 0.91, and the similarity between the object A and the object C is 0.99, so that the object B and the object C are qualified similar objects of the object A.
According to the formula of the prediction data, the prediction data of the fourth attribute of the object A is as follows: 0.49. at this time, a fourth attribute may be added to the a object.
An embodiment of the present invention further provides an attribute selection device for a target object based on commodity selling, including:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring original data of at least two objects and preprocessing the original data to obtain first data;
the characteristic vector matrix module is used for acquiring the identifications of at least two objects and corresponding first data to form a characteristic vector matrix;
the similarity calculation module is used for calculating the similarity of any two eigenvectors in the eigenvector matrix, acquiring a preset similarity threshold value and matching at least one similar object from the objects;
the prediction data calculation module is used for calculating the prediction data of the target object according to the first data of the similar object to obtain second data;
the attribute selection module compares the second data with the first data one by one and judges whether the second data accords with the first data; and when the second data is determined to be consistent with the first data, adding or replacing the attribute on the target object.
In one embodiment, the prediction data calculation module further comprises:
and the predicted data judging module is used for acquiring the first data and the characteristic value corresponding to the first data and judging whether the predicted data is available or not according to the characteristic value.
In one embodiment, the attribute selection module further comprises:
and the attribute judging module is used for judging whether the prediction attribute exists on the target object.
The embodiment of the invention also provides computer equipment which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the method for selecting the attributes of the target object when executing the computer program.
Embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for selecting the attributes of the target object.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (12)

1. An attribute selection method based on a target object sold by a commodity is applied to a commodity selling client, and the method comprises the following steps:
acquiring original data of at least two objects, and preprocessing the original data to obtain first data;
acquiring the identifications of at least two objects and the corresponding first data to form a characteristic vector matrix;
carrying out similarity calculation on any two eigenvectors in the eigenvector matrix, obtaining a preset similarity threshold value, and matching at least one similar object from the objects;
according to the first data of the similar object, calculating prediction data of a target object to obtain second data;
comparing the second data with the first data, and judging whether the second data accords with the first data;
and when the second data is determined to accord with the first data, adding or replacing the attribute on the target object.
2. The method of claim 1, wherein the preprocessing the raw data comprises: eliminating the exception of the original data; and/or carrying out homogenization treatment on the original data.
3. The method as claimed in claim 1 or 2, wherein the step of calculating the predicted data of the target object according to the first data of the similar object to obtain the second data comprises: acquiring the first data and a characteristic value corresponding to the first data, and judging whether the prediction data is available according to the characteristic value:
if the second data is available, obtaining the second data;
if not, the second data is discarded.
4. The method of claim 3, wherein the characteristic value comprises: the similarity of the similar objects, the number of the similar objects, the standard deviation between the similar objects, the classification of the places where the objects are located, and the category of the attributes.
5. The method of claim 1, wherein said matching at least one similar object from said objects comprises: assuming object a and object B, the feature vectors are a and B, respectively, the similarity between object a and object B, Sa, B:
Figure FDA0002912138700000021
6. the method of claim 1, wherein calculating the predictive data for the target object comprises: assuming that the prediction data of the attribute x of the object a is Px, a, then:
Figure FDA0002912138700000022
wherein Sa, i is the similarity between object a and object i, n is the total number of similar objects, and Qx, i is the first data of attribute x on object i.
7. The method of selecting an attribute of a target object for merchandise based sale according to claim 1 or 2, wherein the step of adding or replacing the attribute on the target object comprises: judging whether the prediction attribute exists on the target object;
if so, replacing the attribute on the target object with the predicted attribute in the similar object;
and if the prediction attribute does not exist, adding the prediction attribute in the similar object to the target object.
8. An attribute selection device for a target object based on merchandise sales, comprising:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring original data of at least two objects and preprocessing the original data to obtain first data;
the characteristic vector matrix module is used for acquiring the identifications of at least two objects and the corresponding first data to form a characteristic vector matrix;
the similarity calculation module is used for calculating the similarity of any two eigenvectors in the eigenvector matrix, acquiring a preset similarity threshold value and matching at least one similar object from the objects;
the predicted data calculation module is used for calculating predicted data of a target object according to the first data of the similar object to obtain second data;
the attribute selection module is used for comparing the second data with the first data and judging whether the second data accords with the first data; and when the second data is determined to accord with the first data, adding or replacing the attribute on the target object.
9. The apparatus for selecting an attribute of a target object for merchandise sales of claim 8, wherein the predictive data calculation module further comprises:
and the predicted data judging module is used for acquiring the first data and the characteristic value corresponding to the first data and judging whether the predicted data is available or not according to the characteristic value.
10. The apparatus of claim 8 or 9, wherein the attribute selection module further comprises:
and the attribute judging module is used for judging whether the prediction attribute exists on the target object.
11. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
CN202110090104.6A 2021-01-22 2021-01-22 Method and device for selecting attributes of target object based on commodity selling Pending CN113111904A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110090104.6A CN113111904A (en) 2021-01-22 2021-01-22 Method and device for selecting attributes of target object based on commodity selling

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110090104.6A CN113111904A (en) 2021-01-22 2021-01-22 Method and device for selecting attributes of target object based on commodity selling

Publications (1)

Publication Number Publication Date
CN113111904A true CN113111904A (en) 2021-07-13

Family

ID=76709205

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110090104.6A Pending CN113111904A (en) 2021-01-22 2021-01-22 Method and device for selecting attributes of target object based on commodity selling

Country Status (1)

Country Link
CN (1) CN113111904A (en)

Similar Documents

Publication Publication Date Title
US20220084308A1 (en) Method and device for image search, and storage medium
US9082086B2 (en) Adaptively learning a similarity model
CN109522435A (en) A kind of image search method and device
TW201508671A (en) Method and system for recommending online products
US20120296776A1 (en) Adaptive interactive search
CN110705245A (en) Method and device for acquiring reference processing scheme and storage medium
CN110110257B (en) Data processing method and system, computer system and computer readable medium
US10769585B2 (en) Systems and methods for automated harmonized system (HS) code assignment
CN117035948B (en) Task intelligent processing method and system based on big data
CN110851737B (en) Recommendation method, recommendation device, electronic equipment and computer storage medium
US7373021B2 (en) Image search program, information storage medium, image search apparatus and image search method
WO2020140681A1 (en) Numerical value calculation method and apparatus, computer device, and storage medium
CN110569915B (en) Automobile data clustering method and system based on intuitive fuzzy C-means
US10366088B2 (en) Method and system for mining frequent and in-frequent items from a large transaction database
CN112634057A (en) Fund similarity calculation method, platform, device and readable storage medium
CN113111904A (en) Method and device for selecting attributes of target object based on commodity selling
CN109978675B (en) Tax monitoring method and device
CN111984637B (en) Missing value processing method and device in data modeling, equipment and storage medium
CN116150477A (en) Financial information personalized recommendation method, device, equipment and medium
CN111680941A (en) Premium recommendation method, device, equipment and storage medium
CN113408665A (en) Object identification method, device, equipment and medium
US11366833B2 (en) Augmenting project data with searchable metadata for facilitating project queries
CN113409106A (en) Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium based on user value
CN109976934B (en) Device use abnormality determination method, device and computer storage medium
CN113393303A (en) Article recommendation method, device, equipment and storage medium

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