CN114331569A - User consumption behavior analysis method and system for different scenes in business space - Google Patents
User consumption behavior analysis method and system for different scenes in business space Download PDFInfo
- Publication number
- CN114331569A CN114331569A CN202210215160.2A CN202210215160A CN114331569A CN 114331569 A CN114331569 A CN 114331569A CN 202210215160 A CN202210215160 A CN 202210215160A CN 114331569 A CN114331569 A CN 114331569A
- Authority
- CN
- China
- Prior art keywords
- consumption
- consumer
- consumption data
- data
- different scenes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data analysis, and provides a method and a system for analyzing user consumption behaviors of different scenes in a business space, which comprises the following steps: acquiring consumer consumption data of different scenes in a commercial space, preprocessing the consumption data, and marking the consumption data with an attribute label; constructing a unique identity of a consumer, and primarily classifying the consumption data based on the identity of the consumer; constructing a Neo4j graph database by taking a consumer ID as a terminal object and consumer data as nodes; selecting one or more target analysis attributes, calling data marked with corresponding attribute tags from a database, and obtaining the distribution between the consumer ID and the target analysis attribute tags by using a clustering algorithm to obtain a user consumption behavior analysis result. According to the method and the system, the consumption behaviors of the users in different scenes of the same user in the business space are analyzed, so that the client group is convenient to perform viscosity reinforcement, and accurate marketing and advertisement pushing of potential clients are facilitated.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a method and a system for analyzing user consumption behaviors of different scenes in a business space.
Background
With the rapid development of the mobile internet technology, various mobile terminals such as mobile phones, tablet computers and POS machines are increasingly popularized, and consumers are generally used to consume with the mobile terminals. The mobile terminals are convenient for people to consume, and record behavior data of the consumers, even record position information of the consumers. At present, the prior art provides a technology based on consumer behavior data analysis and classification, and the consumption habits of different consumers are excavated by analyzing and modeling the behaviors of the consumers, so that the client group is conveniently subjected to viscosity reinforcement, and accurate marketing and advertisement pushing of potential clients are facilitated.
However, in the business space, scenes with multiple levels of dimensions, including supermarkets, shops, parking lots and the like, exist universally, consumption actions of consumers in different scenes are independent, and consumer users in the business space are difficult to identify.
Disclosure of Invention
The invention provides a method and a system for analyzing user consumption behaviors in different scenes in a business space, aiming at overcoming the defect that the prior art is difficult to identify the consumer users in different scenes in the business space.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a user consumption behavior analysis method for different scenes in a business space comprises the following steps:
s1, consumer consumption data of different scenes in a business space are obtained, the consumption data are preprocessed, and attribute labels are marked on the consumption data;
s2, adopting OpenID to construct a unique identity of the consumer, and primarily classifying the consumption data based on the identity of the consumer;
s3, constructing a Neo4j graph database by taking the consumer ID as a terminal object and the consumer data as nodes;
s4, selecting one or more target analysis attributes, calling data labeled with corresponding attribute tags from the Neo4j map database, and obtaining the distribution between the consumer ID and the target analysis attribute tags by using a clustering algorithm to obtain a user consumption behavior analysis result.
Preferably, the consumption data includes a consumption object, a consumption amount and a consumption time; the attribute tags include a consumer attribute tag, a scene type tag, a consumer object type tag, a consumer hierarchy tag, and a time tag.
Preferably, in the step S1, the consumer consumption data is obtained through one or more of POS systems, online payment platform records, and parking lot management platform records of different scenes in the commercial space.
Preferably, in the step S1, the step of preprocessing the consumption data includes:
s1.1, cleaning the consumption data: deleting consumption data with the consumption amount lower than a preset consumption amount threshold value; deleting the consumption data of which the time interval between two continuous consumptions is greater than a preset time threshold;
s1.2, classifying the consumption data: building a semantic text classification model based on consumption object types, inputting cleaned consumption data into the semantic text classification model, performing semantic text analysis and classification on consumption objects in the consumption data by the semantic text classification model, and outputting consumption object type classification labels and consumption scene type labels of the consumption data;
s1.3, dividing the consumption data into time periods, and labeling time labels on the consumption data according to the time periods;
s1.4, sequencing the consumption data from small to large according to the consumption amount, and labeling consumption level labels to the consumption data according to consumption amount levels.
Preferably, in the step S4, the step of generating the user consumption behavior analysis result includes:
s4.1, selecting one or more target analysis attributes;
s4.2, based on the ID of the consumer, carrying out feature identification on the consumption data of the ID of the consumer to generate a consumption data feature value;
and S4.3, clustering according to the consumption data characteristic values and the attribute labels of the target analysis attributes respectively to obtain one or more of consumer-consumer attribute distribution, consumer-consumption scene distribution, consumer-consumption object distribution, consumer-consumption hierarchical distribution and consumer-consumption time distribution, and outputting the one or more as user consumption behavior analysis results.
Preferably, the method further comprises the steps of: and constructing a knowledge graph according to the distribution between the consumer ID and the target analysis attribute label and carrying out visual display.
Furthermore, the invention also provides a system for analyzing the user consumption behaviors in different scenes in the business space, which is applied to the method for analyzing the user consumption behaviors in different scenes in the business space provided by any one of the technical schemes. The system comprises a consumption data acquisition module, a consumption data preprocessing module, a consumption data identification module, a classification module, a Neo4j graph database and an analysis module.
The system comprises a consumption data acquisition module, a consumption data preprocessing module and a data processing module, wherein the consumption data acquisition module is used for acquiring consumer consumption data of different scenes in a commercial space, and the consumption data preprocessing module is used for cleaning the acquired consumer consumption data; the consumption data identification module is used for marking the consumption data with an attribute label; the classification module is used for constructing a unique identity of a consumer by adopting OpenID and primarily classifying the consumption data based on the identity of the consumer; the Neo4j graph database is used for storing consumption data by taking a consumer ID as a terminal object and taking the consumption data as a node; the analysis module is used for calling data labeled with corresponding attribute labels from the Neo4j graph database, obtaining distribution between the consumer ID and the target analysis attribute labels by using a clustering algorithm, and outputting a user consumption behavior analysis result.
Preferably, the consumption data identification module includes:
the type label identification unit is internally preset with a trained semantic text classification model; inputting consumption data into the semantic text classification model, performing semantic text analysis and classification on consumption objects in the consumption data by the semantic text classification model, and outputting consumption object type classification labels and consumption scene type labels of the consumption data;
the time tag identification unit is used for dividing the consumption data into time periods and marking time tags on the consumption data according to the time periods;
and the hierarchical label identification unit is used for sequencing the consumption data from small to large according to the consumption amount and marking consumption hierarchical labels on the consumption data according to the consumption amount hierarchy.
Preferably, the consumption data acquisition module comprises one or more of a POS system, an online payment platform, and a parking lot vehicle identification management platform.
As a preferred scheme, the system further comprises a map module and an interaction module, wherein the map module calls data labeled with corresponding attribute labels from the Neo4j map database, and generates a knowledge map of a tree diagram and/or a star diagram based on a knowledge map technology; the interaction module is used for calling data labeled with corresponding attribute labels from the Neo4j graph database for visual display and visually displaying the knowledge graph of the dendrogram and/or the star chart generated by the graph module.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that: according to the method, the consumer consumption data of different scenes in the business space are obtained, the consumer consumption data are stored in the Neo4j graph database based on the consumer ID of the user, the consumer users of different scenes in the business space are identified, the user consumption behaviors of the same user in different scenes in the business space are further identified and analyzed through the community discovery algorithm Neo4j and the clustering algorithm, and therefore the method is convenient for performing viscosity reinforcement on a client group, accurate marketing of potential clients and advertisement pushing.
Drawings
Fig. 1 is a flowchart of a user consumption behavior analysis method for different scenes in a business space according to embodiment 1.
FIG. 2 is a flowchart of a method for analyzing user consumption behaviors of different scenes in a business space according to embodiment 2.
FIG. 3 is an architecture diagram of a user consumption behavior analysis system for different scenarios in a business space according to example 3.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
The present embodiment provides a method for analyzing user consumption behaviors of different scenes in a business space, and as shown in fig. 1, the method is a flowchart of the method for analyzing user consumption behaviors of different scenes in the business space.
The method for analyzing the user consumption behaviors of different scenes in the business space, provided by the embodiment, comprises the following steps:
s1, consumer consumption data of different scenes in the business space are obtained, the consumption data are preprocessed, and attribute labels are marked on the consumption data.
In this step, the acquired consumption data includes a consumption object, a consumption amount, and a consumption time.
In a specific implementation process, the embodiment obtains the consumer consumption data through one or more of a POS system, an online payment platform record and a parking lot management platform record which are set in different scenes in a commercial space.
Further, the consumption data in this step is preprocessed, and the specific steps are as follows:
s1.1, cleaning the consumption data: deleting consumption data with the consumption amount lower than a preset consumption amount threshold value; deleting the consumption data of which the time interval between two continuous consumptions is greater than a preset time threshold;
s1.2, classifying the consumption data: building a semantic text classification model based on consumption object types, inputting cleaned consumption data into the semantic text classification model, performing semantic text analysis and classification on consumption objects in the consumption data by the semantic text classification model, and outputting consumption object type classification labels and consumption scene type labels of the consumption data;
s1.3, dividing the consumption data into time periods, and labeling time labels on the consumption data according to the time periods;
s1.4, sequencing the consumption data from small to large according to the consumption amount, and labeling consumption level labels to the consumption data according to consumption amount levels.
The attribute tags in this embodiment include consumer attribute tags, scene type tags, consumption object type tags, consumption level tags, and time tags, and are used to classify user consumption records of different scenes in a business space.
S2, adopting OpenID to construct a unique identification of the consumer, and carrying out primary classification on the consumption data based on the identification of the consumer.
In this step, OpenID is used to construct a unique ID of the consumer, and the consumption data obtained in step S1 is classified based on the ID of the consumer (i.e., the consumer ID), so as to classify the consumption data belonging to the consumer ID.
S3, constructing a Neo4j graph database by using the consumer ID as a terminal object and the consumption data as nodes.
In the step, a Neo4j graph database is built based on a community discovery algorithm Neo4j, in the process of building a Neo4j graph database, a consumer ID is used as a terminal object, consumer data is used as nodes, corresponding labels are distributed to consumer data nodes, then n nodes are traversed, neighbors of the corresponding nodes are found, neighbor labels of the nodes are obtained, the labels with the largest occurrence frequency are found, and if the number of the labels with the largest occurrence frequency is more than one, one label is randomly selected to be replaced by the node label. If the labels do not change any more, the iteration is stopped, otherwise, the steps are repeated to obtain a Neo4j database.
S4, selecting one or more target analysis attributes, calling data labeled with corresponding attribute tags from the Neo4j map database, and obtaining the distribution between the consumer ID and the target analysis attribute tags by using a clustering algorithm to obtain a user consumption behavior analysis result.
In this step, the step of generating the user consumption behavior analysis result includes:
s4.1, selecting one or more target analysis attributes;
s4.2, based on the ID of the consumer, carrying out feature identification on the consumption data of the ID of the consumer to generate a consumption data feature value;
and S4.3, clustering according to the consumption data characteristic values and the attribute labels of the target analysis attributes respectively to obtain one or more of consumer-consumer attribute distribution, consumer-consumption scene distribution, consumer-consumption object distribution, consumer-consumption hierarchical distribution and consumer-consumption time distribution, and outputting the one or more as user consumption behavior analysis results.
In the specific implementation process, transaction consumption, member, parking charge and consumption preference data of the same user are obtained through POS systems, online payment platform records and parking lot management platform records which are arranged in different scenes in a commercial space. For example, when a user drives a car to park in a parking lot in a target commercial space, the parking lot management platform acquires the license plate information of the user, further acquires the identity information of the car owner (user) through online code scanning payment, and matches and associates the identity information with the consumer ID. After a user finishes parking operation, when the user visits or consumes in a target commercial space, a moving path and consumption data of the user are obtained through a POS system and an online payment platform, the obtained consumption data specifically comprise a consumption object, a consumption amount and consumption time, the consumption object data comprise the name of a consumption store, the type of the consumption store (such as gourmet, clothes, makeup, service and the like) and consumption hierarchy (defined by consumption amount), the consumption data are stored in a Neo4j database based on the consumer ID of the user, the user consumption hierarchical structure of different scenes is calculated and found through a community discovery algorithm Neo4j, and finally data combination of different scenes of the same user is recognized through a clustering algorithm to obtain a user consumption behavior analysis result.
In the embodiment, consumer consumption data of different scenes in a business space are obtained, the consumer consumption data are stored in a Neo4j graph database based on consumer IDs of users, recognition of consumer users of different scenes in the business space is completed, and further user consumption behaviors of the same user in different scenes in the business space are recognized and analyzed through a community discovery algorithm Neo4j and a clustering algorithm, so that viscosity reinforcement, accurate marketing of potential customers and advertisement pushing are facilitated.
Example 2
The embodiment is an improvement on the method for analyzing the consumption behaviors of the users in different scenes in the business space, which is provided by the embodiment 1. Fig. 2 is a flowchart of a method for analyzing user consumption behaviors of different scenes in a business space according to this embodiment.
The method for analyzing the user consumption behaviors of different scenes in the business space, provided by the embodiment, comprises the following steps:
s1, consumer consumption data of different scenes in a business space are obtained, the consumption data are preprocessed, and attribute labels are marked on the consumption data;
s2, adopting OpenID to construct a unique identity of the consumer, and primarily classifying the consumption data based on the identity of the consumer;
s3, constructing a Neo4j graph database by taking the consumer ID as a terminal object and the consumer data as nodes;
s4, selecting one or more target analysis attributes, calling data labeled with corresponding attribute tags from the Neo4j map database, and obtaining the distribution between the consumer ID and the target analysis attribute tags by using a clustering algorithm to obtain a user consumption behavior analysis result.
Further, the present embodiment further includes the following steps: and constructing a knowledge graph according to the distribution between the consumer ID and the target analysis attribute label and carrying out visual display.
In the implementation, based on the consumer ID and consumption data stored in the Neo4j database, clustering according to the consumption data characteristic values and the attribute labels of the target analysis attributes respectively to obtain one or more of consumer-consumer attribute distribution, consumer-consumption scene distribution, consumer-consumption object distribution, consumer-consumption hierarchical distribution and consumer-consumption time distribution as a user consumption behavior analysis result, and the consumer-consumer attribute distribution, the consumer-consumer scene distribution, the consumer-consumer object distribution, the consumer-consumer hierarchical distribution and the consumer-consumer time distribution are visually displayed in a knowledge graph form, so that the consumption behaviors of the same user in a target business space can be more intuitively analyzed.
Example 3
The embodiment provides a system for analyzing user consumption behaviors in different scenes in a business space, which is applied to the method for analyzing user consumption behaviors in different scenes in the business space provided in the embodiment 1. Fig. 3 is an architecture diagram of a user consumption behavior analysis system for different scenes in a business space according to the present embodiment.
The system for analyzing the consumption behaviors of the users in different scenes in the business space, provided by the embodiment, comprises the following steps:
the consumption data acquisition module is used for acquiring consumption data of consumers in different scenes in a commercial space;
the consumption data preprocessing module is used for cleaning the acquired consumption data of the consumers;
the consumption data identification module is used for marking the consumption data with an attribute label;
the classification module is used for constructing a unique identity of a consumer by adopting OpenID and preliminarily classifying the consumption data based on the identity of the consumer;
a Neo4j graph database for storing consumption data with consumer ID as terminal object and consumption data as node;
and the analysis module is used for calling data labeled with corresponding attribute labels from the Neo4j graph database, obtaining distribution between the consumer ID and the target analysis attribute labels by utilizing a clustering algorithm, and outputting a user consumption behavior analysis result.
Further, the consumption data identification module of this embodiment includes:
the type label identification unit is internally preset with a trained semantic text classification model; inputting consumption data into the semantic text classification model, performing semantic text analysis and classification on consumption objects in the consumption data by the semantic text classification model, and outputting consumption object type classification labels and consumption scene type labels of the consumption data;
the time tag identification unit is used for dividing the consumption data into time periods and marking time tags on the consumption data according to the time periods;
and the hierarchical label identification unit is used for sequencing the consumption data from small to large according to the consumption amount and marking consumption hierarchical labels on the consumption data according to the consumption amount hierarchy.
Furthermore, the system also comprises a map module and an interaction module, wherein the map module calls data labeled with corresponding attribute labels from the Neo4j map database and generates a knowledge map of a tree diagram and/or a star diagram based on a knowledge map technology; the interaction module is used for calling data labeled with corresponding attribute labels from the Neo4j graph database for visual display and visually displaying the knowledge graph of the dendrogram and/or the star chart generated by the graph module.
In one embodiment, the consumption data collection module comprises one or more of a POS system, an online payment platform, a parking lot vehicle identification management platform.
In the specific implementation process, the consumption data acquisition module acquires consumer consumption data of different scenes in a business space and then transmits the consumer consumption data to the consumption data preprocessing module.
The consumption data preprocessing module is used for cleaning the received consumption data, specifically, the consumption data preprocessing module deletes the consumption data of which the consumption amount is lower than a preset consumption amount threshold value, and deletes the consumption data of which the time interval between two continuous consumptions is larger than a preset time threshold value. And the consumption data preprocessing module sends the preprocessed data to the consumption data identification module.
The consumption data identification module classifies the preprocessed consumption data and labels consumer attribute labels, scene type labels, consumption object type labels, consumption level labels and time labels on the consumption data. Specifically, a type tag identification unit in the consumption data identification module performs semantic text analysis and classification on consumption objects in the consumption data through a preset semantic text classification model thereof, and outputs consumption object type classification tags and consumption scene type tags of the consumption data; the time tag identification unit divides the consumption data into time periods and marks time tags on the consumption data according to the time periods; and the hierarchical label identification unit sorts the consumption data from small to large according to the consumption amount and labels consumption hierarchical labels on the consumption data according to consumption amount hierarchy. The consumption data identification module sends the consumption data which completes identification to the classification module.
The classification module constructs a unique identification of a consumer by adopting OpenID, preliminarily classifies the consumption data based on the identification of the consumer, and then sends the consumption data to a Neo4j graph database, wherein the consumer ID is used as a terminal object, and the consumption data is used as a node for data storage.
When the user consumption behaviors are analyzed, the analysis module calls data marked with corresponding attribute labels from the Neo4j map database, the distribution between the consumer ID and the target analysis attribute labels is obtained by utilizing a clustering algorithm, and the user consumption behavior analysis result is output.
The same or similar reference numerals correspond to the same or similar parts;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A user consumption behavior analysis method for different scenes in a business space is characterized by comprising the following steps:
s1, consumer consumption data of different scenes in a business space are obtained, the consumption data are preprocessed, and attribute labels are marked on the consumption data;
s2, adopting OpenID to construct a unique identity of the consumer, and primarily classifying the consumption data based on the identity of the consumer;
s3, constructing a Neo4j graph database by taking the consumer ID as a terminal object and the consumer data as nodes;
s4, selecting one or more target analysis attributes, calling data labeled with corresponding attribute tags from the Neo4j map database, and obtaining the distribution between the consumer ID and the target analysis attribute tags by using a clustering algorithm to obtain a user consumption behavior analysis result.
2. The method of analyzing user consumption behavior of different scenes in a business space according to claim 1, wherein the consumption data includes a consumption object, a consumption amount, and a consumption time; the attribute tags include a consumer attribute tag, a scene type tag, a consumer object type tag, a consumer hierarchy tag, and a time tag.
3. The method for analyzing consumer consumption behaviors of different scenes in a business space according to claim 2, wherein in the step S1, the consumer consumption data is obtained through one or more of POS system, online payment platform record and parking lot management platform record of different scenes in the business space.
4. The method for analyzing user consumption behaviors of different scenes in a business space according to claim 2, wherein the step of preprocessing the consumption data in the step of S1 comprises:
s1.1, cleaning the consumption data: deleting consumption data with the consumption amount lower than a preset consumption amount threshold value; deleting the consumption data of which the time interval between two continuous consumptions is greater than a preset time threshold;
s1.2, classifying the consumption data: building a semantic text classification model based on consumption object types, inputting cleaned consumption data into the semantic text classification model, performing semantic text analysis and classification on consumption objects in the consumption data by the semantic text classification model, and outputting consumption object type classification labels and consumption scene type labels of the consumption data;
s1.3, dividing the consumption data into time periods, and labeling time labels on the consumption data according to the time periods;
s1.4, sequencing the consumption data from small to large according to the consumption amount, and labeling consumption level labels to the consumption data according to consumption amount levels.
5. The method for analyzing user consumption behaviors of different scenes in a business space according to claim 2, wherein in the step of S4, the step of generating the analysis result of the user consumption behavior comprises:
s4.1, selecting one or more target analysis attributes;
s4.2, based on the ID of the consumer, carrying out feature identification on the consumption data of the ID of the consumer to generate a consumption data feature value;
and S4.3, clustering according to the consumption data characteristic values and the attribute labels of the target analysis attributes respectively to obtain one or more of consumer-consumer attribute distribution, consumer-consumption scene distribution, consumer-consumption object distribution, consumer-consumption hierarchical distribution and consumer-consumption time distribution, and outputting the one or more as user consumption behavior analysis results.
6. The method for analyzing the consumption behavior of the users in different scenes in the business space according to any one of claims 1 to 5, further comprising the steps of: and constructing a knowledge graph according to the distribution between the consumer ID and the target analysis attribute label and carrying out visual display.
7. A system for analyzing consumption behavior of users of different scenes in a business space, comprising:
the consumption data acquisition module is used for acquiring consumption data of consumers in different scenes in a commercial space;
the consumption data preprocessing module is used for cleaning the acquired consumption data of the consumers;
the consumption data identification module is used for marking the consumption data with an attribute label;
the classification module is used for constructing a unique identity of a consumer by adopting OpenID and preliminarily classifying the consumption data based on the identity of the consumer;
a Neo4j graph database for storing consumption data with consumer ID as terminal object and consumption data as node;
and the analysis module is used for calling data labeled with corresponding attribute labels from the Neo4j graph database, obtaining distribution between the consumer ID and the target analysis attribute labels by utilizing a clustering algorithm, and outputting a user consumption behavior analysis result.
8. The system of claim 7, wherein the consumption data identification module comprises:
the type label identification unit is internally preset with a trained semantic text classification model; inputting consumption data into the semantic text classification model, performing semantic text analysis and classification on consumption objects in the consumption data by the semantic text classification model, and outputting consumption object type classification labels and consumption scene type labels of the consumption data;
the time tag identification unit is used for dividing the consumption data into time periods and marking time tags on the consumption data according to the time periods;
and the hierarchical label identification unit is used for sequencing the consumption data from small to large according to the consumption amount and marking consumption hierarchical labels on the consumption data according to the consumption amount hierarchy.
9. The system for analyzing consumer behavior of different scenes in a business space according to claim 7, wherein the consumer data collection module comprises one or more of a POS system, an online payment platform, a parking lot vehicle identification management platform.
10. The system for analyzing user consumption behaviors of different scenes in a business space according to claim 7, further comprising a graph module and an interaction module, wherein the graph module retrieves data labeled with corresponding attribute labels from the Neo4j graph database, and generates a knowledge graph of a tree graph and/or a star graph based on a knowledge graph technology; the interaction module is used for calling data labeled with corresponding attribute labels from the Neo4j graph database for visual display and visually displaying the knowledge graph of the dendrogram and/or the star chart generated by the graph module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210215160.2A CN114331569A (en) | 2022-03-07 | 2022-03-07 | User consumption behavior analysis method and system for different scenes in business space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210215160.2A CN114331569A (en) | 2022-03-07 | 2022-03-07 | User consumption behavior analysis method and system for different scenes in business space |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114331569A true CN114331569A (en) | 2022-04-12 |
Family
ID=81031384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210215160.2A Pending CN114331569A (en) | 2022-03-07 | 2022-03-07 | User consumption behavior analysis method and system for different scenes in business space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114331569A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117706954A (en) * | 2024-02-06 | 2024-03-15 | 青岛海尔科技有限公司 | Method and device for generating scene, storage medium and electronic device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112116426A (en) * | 2020-09-21 | 2020-12-22 | 中国建设银行股份有限公司 | Method and device for pushing article information |
| CN112288455A (en) * | 2020-01-09 | 2021-01-29 | 北京沃东天骏信息技术有限公司 | Label generation method and device, computer readable storage medium and electronic equipment |
| US10963893B1 (en) * | 2016-02-23 | 2021-03-30 | Videomining Corporation | Personalized decision tree based on in-store behavior analysis |
| CN113177809A (en) * | 2021-05-27 | 2021-07-27 | 微积分创新科技(北京)股份有限公司 | Automatic clustering method and application system for user consumption behaviors based on one-object-one-code |
-
2022
- 2022-03-07 CN CN202210215160.2A patent/CN114331569A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10963893B1 (en) * | 2016-02-23 | 2021-03-30 | Videomining Corporation | Personalized decision tree based on in-store behavior analysis |
| CN112288455A (en) * | 2020-01-09 | 2021-01-29 | 北京沃东天骏信息技术有限公司 | Label generation method and device, computer readable storage medium and electronic equipment |
| CN112116426A (en) * | 2020-09-21 | 2020-12-22 | 中国建设银行股份有限公司 | Method and device for pushing article information |
| CN113177809A (en) * | 2021-05-27 | 2021-07-27 | 微积分创新科技(北京)股份有限公司 | Automatic clustering method and application system for user consumption behaviors based on one-object-one-code |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117706954A (en) * | 2024-02-06 | 2024-03-15 | 青岛海尔科技有限公司 | Method and device for generating scene, storage medium and electronic device |
| CN117706954B (en) * | 2024-02-06 | 2024-05-24 | 青岛海尔科技有限公司 | Method and device for generating scene, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Peacock | Data mining in marketing: Part 1 | |
| CN110009401A (en) | Advertisement placement method, device and storage medium based on user's portrait | |
| US9449326B2 (en) | Web site accelerator | |
| CN103229169B (en) | Content providing and system | |
| US9477973B2 (en) | Visually generated consumer product presentation | |
| CN111915366A (en) | User portrait construction method and device, computer equipment and storage medium | |
| CN107179827A (en) | The intelligent interactive method and system of a kind of finance device | |
| Hemalatha | Market basket analysis–a data mining application in Indian retailing | |
| KR102175479B1 (en) | Apparatus and method for providing customized marketing based on consumer behavior analysis | |
| CN110955690A (en) | Self-service data labeling platform and self-service data labeling method based on big data technology | |
| CN111784405A (en) | Off-line store intelligent shopping guide method based on face intelligent recognition KNN algorithm | |
| JP2023507043A (en) | DATA PROCESSING METHOD, DEVICE, DEVICE, STORAGE MEDIUM AND COMPUTER PROGRAM | |
| CN112925973A (en) | Data processing method and device | |
| CN113592605A (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
| CN116308556A (en) | Advertisement pushing method and system based on Internet of things | |
| CN114331569A (en) | User consumption behavior analysis method and system for different scenes in business space | |
| CN116739836B (en) | Restaurant data analysis method and system based on knowledge graph | |
| KR102077630B1 (en) | System and method for analyzing commercial based on pos and video | |
| CN113837824A (en) | Information pushing method and system | |
| CN113821703B (en) | Internet of vehicles user portrait generation method and system thereof | |
| Wyner | Segmentation analysis, then and now. | |
| CN116703515A (en) | Recommendation method and device based on artificial intelligence, computer equipment and storage medium | |
| Wu et al. | [Retracted] Using the Mathematical Model on Precision Marketing with Online Transaction Data Computing | |
| Mathieu et al. | From real purchase to realistic populations of simulated customers | |
| CN114723491A (en) | Accurate marketing method and system based on user portrait and data mining |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220412 |
|
| RJ01 | Rejection of invention patent application after publication |