Iot customer data processing method and apparatus

Abstract

The application discloses an Internet of Things customer data processing method and device. The method comprises the following steps: acquiring customer data of multiple data sources; respectively performing preliminary processing on the customer data of each data source to obtain preliminary processing data corresponding to the data source; obtaining an evaluation system model based on the preliminary processing data and a preset data model; performing comprehensive processing on the preliminary processing data of different data sources to obtain final processing data; and performing visual analysis and processing based on the final processing data and the evaluation system model to obtain a visual analysis result. The Internet of Things customer data processing method and device can improve the operation analysis business processing efficiency and reduce the pressure on the central data processing layer.

Description

Technical Field

[0001] This application relates to the field of big data technology, specifically to an Internet of Things (IoT) customer data processing method and apparatus. Background Technology

[0002] With the exponential growth of IoT businesses and users, the scale of IoT data continues to expand, and the behavior of IoT users is becoming increasingly complex. IoT data differs from traditional customer data in terms of its group-based, industry-specific, geographically specific, and functional characteristics. Therefore, traditional IoT customer operation analysis methods are no longer applicable to the new situation. Furthermore, the massive volume of IoT business and users means that simultaneous information transmission and centralized storage and analysis can impact IoT data processing efficiency, and centralized processing of IoT data can easily lead to load capacity bottlenecks. Summary of the Invention

[0003] Therefore, this application provides an IoT customer data processing method and apparatus to solve the problems of low data processing efficiency and load capacity bottlenecks caused by the large scale of IoT data and the increasingly complex behavior of IoT users in the prior art.

[0004] To achieve the above objectives, the first aspect of this application provides an IoT customer data processing method, comprising:

[0005] Retrieve customer data from multiple data sources;

[0006] The customer data from each of the aforementioned data sources is subjected to preliminary processing to obtain preliminary processed data corresponding to the respective data sources;

[0007] An evaluation system model is obtained based on preliminary data processing and a pre-set data model;

[0008] The preliminary data from different data sources are comprehensively processed to obtain the final processed data;

[0009] Visual analysis is performed based on the final processed data and the evaluation system model to obtain the visual analysis results.

[0010] The data sources include data sources from the customer acquisition system, data sources from the order system, and data sources from the Internet of Things platform.

[0011] The customer data includes one or more of the following: customer usage behavior data, purchase behavior data, and basic customer information data.

[0012] The step of performing preliminary processing on customer data from each of the data sources to obtain preliminary processed data corresponding to the data sources includes:

[0013] Filter the customer data;

[0014] The filtered customer data is extracted according to business needs to obtain the first customer data;

[0015] Perform a first cross-analysis on the first customer data to obtain the first cross-analysis result;

[0016] Based on the results of the first cross-analysis, the customer data is transcoded to obtain preliminary processed data.

[0017] The step of transcoding the customer data based on the first cross-analysis result to obtain preliminary processed data further includes:

[0018] The preliminary processed data is compressed and stored in a dataset format.

[0019] The step of compressing and storing the pre-processed data in a dataset format further includes:

[0020] The preliminary processed data is reported to the central data storage layer in batches according to time periods.

[0021] The step of comprehensively processing the preliminary data from different data sources to obtain the final processed data includes:

[0022] The preliminary processed data is then filtered;

[0023] The second customer data is obtained by extracting data from the filtered, pre-processed data according to business needs.

[0024] Perform cross-analysis on the second customer data to obtain the second cross-analysis result;

[0025] The preliminary processed data is transcoded based on the results of the second cross-analysis.

[0026] The pre-processed data after transcoding is clustered and split according to customer category tags to obtain the final processed data.

[0027] The process includes, before converting the pre-processed data based on the second cross-analysis result and then clustering and splitting the converted pre-processed data according to customer group labels to obtain the final processed data, the following steps are also included:

[0028] The transcoded, pre-processed data is compressed and stored.

[0029] The visualization analysis results include automatically assigning user tags to users and providing maintenance suggestions.

[0030] To achieve the above objectives, a second aspect of this application provides an Internet of Things (IoT) customer data processing device, comprising:

[0031] The acquisition module is used to acquire customer data from multiple data sources;

[0032] The first processing module is used to perform preliminary processing on the customer data of each of the data sources to obtain preliminary processed data corresponding to the data sources.

[0033] The modeling module is used to obtain an evaluation system model based on the pre-processed data and the preset data model.

[0034] The first processing module is used to comprehensively process the preliminary processed data from different data sources to obtain the final processed data;

[0035] The visualization module is used to perform visualization analysis based on the final processed data and the evaluation system model to obtain visualization analysis results.

[0036] This application has the following advantages:

[0037] The IoT customer data processing method provided in this application performs preliminary and comprehensive processing on customer data, which can not only improve the efficiency of data processing and thus improve the efficiency of operational analysis business processing, but also reduce the pressure on the central data processing layer and reduce the centralized requests of the central data storage layer. Attached Figure Description

[0038] The accompanying drawings are provided to further understand this application and form part of the specification. They are used together with the following detailed description to explain this application, but do not constitute a limitation thereof.

[0039] Figure 1 This is an application scenario diagram of the IoT customer data processing method according to an embodiment of this application;

[0040] Figure 2 A flowchart illustrating an IoT customer data processing method provided in this application embodiment;

[0041] Figure 3 This is a flowchart of step S202 in the embodiments of this application;

[0042] Figure 4 This is a flowchart of step S204 in an embodiment of this application;

[0043] Figure 5 A block diagram of an Internet of Things (IoT) customer data processing device provided in an embodiment of this application;

[0044] Figure 6 A block diagram of the first processing module provided in an embodiment of this application;

[0045] Figure 7 A block diagram of the second processing module provided in an embodiment of this application. Detailed Implementation

[0046] The specific embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this application.

[0047] As used in this application, the term "and / or" includes any and all combinations of one or more of the related enumerated entries.

[0048] The terminology used in this application is for describing specific embodiments only and is not intended to limit the application. As used herein, the singular forms "a" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0049] When the terms “comprising” and / or “made of” are used in this application, the presence of the said feature, integral, step, operation, element and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or groups thereof is not excluded.

[0050] Unless otherwise specified, all terms used in this application (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this application, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined in this application.

[0051] Figure 1 This is an application scenario diagram of the IoT customer data processing method according to an embodiment of this application. For example... Figure 1 As shown, in the application scenario, data source 11 provides customer data. The data source can be various systems and / or platforms. The customer data can be data generated from customer transactions, such as data generated during a customer's shopping activity.

[0052] The underlying data processing system 12 is used to perform preliminary processing on customer data to obtain preliminary processed data; the central data processing system 13 is used to process the preliminary processed data to obtain final processed data.

[0053] The underlying data processing system 12 and the central data processing system 13 can use various types of servers, and the type of server can be selected according to actual needs.

[0054] In some embodiments, the underlying data processing system 12 adopts a distributed server architecture, and each server in the underlying data processing system 12 may be of the same type or different types.

[0055] In the application scenario of IoT customer data processing methods, a visualization system 14 is also included to visualize the final processed data. The visualization system 14 can be a display device, such as a display screen or a projector.

[0056] This application embodiment connects a large amount of customer data with the visualization system 14, and mines the deep value in customer data according to different customer business scenarios, so that users can independently analyze different customer characteristics at any time as needed and quickly understand customer needs.

[0057] Firstly, embodiments of this application provide an IoT customer data processing method. This method can improve the analysis and processing capabilities of IoT customer operation data and reduce the pressure on the central data processing layer.

[0058] Figure 2 A flowchart illustrating an IoT customer data processing method provided in an embodiment of this application. Figure 2 As shown, the IoT customer data processing method includes:

[0059] Step S201: Obtain customer data from multiple data sources.

[0060] The data source is the origin of the customer data. Since the customer data comes from the data source, users can clearly identify which data source the customer data originates from.

[0061] In some embodiments, the data source is any two or more of the following: the data source of the customer acquisition system, the data source of the order system, and the data source of the Jasper platform.

[0062] Among them, the customer acquisition system is a system that attracts potential customers from different advertising channels to the enterprise's free nurturing pool, allowing different customers to naturally convert as they independently obtain content that interests them, thus achieving customer acquisition marketing.

[0063] The order system can perform functions such as accepting customer order information, verifying order information, and categorizing orders according to customer and urgency based on inventory information. Users can also obtain basic information about customers, such as their age group and frequently purchased products, through the order system.

[0064] Among them, the Internet of Things (IoT) platform is a cloud computing, big data, artificial intelligence, and cloud-integrated platform that possesses various types of customer information, such as the Jasper platform.

[0065] In some embodiments, customer data includes one or more of customer usage behavior data, purchase behavior data, and basic customer information data.

[0066] Customer behavior data refers to behavioral data generated by customers when using systems such as the Internet of Things (IoT), including the systems or platforms used by customers, customer activity levels, and item popularity. Customer activity level refers to the total number of items for which users have interacted, while item popularity refers to the total number of users who have interacted with an item.

[0067] Purchase behavior data refers to data on customers when they make a purchase, such as the name of the product purchased, the quantity purchased, and the time of purchase.

[0068] Step S202: Perform preliminary processing on the customer data from each data source to obtain preliminary processed data corresponding to the data source.

[0069] In this embodiment, customer data from different data sources are processed separately, meaning that customer data from different data sources are not processed together.

[0070] For example, when processing customer data obtained from the customer acquisition system, customer data from the order system should not be mixed in.

[0071] Step S203: Obtain the evaluation system model based on the preliminary processed data and the preset data model.

[0072] The pre-defined data model provides an abstract framework for the information representation and manipulation of preliminary data processing, based on static features, dynamic behaviors, and constraints. The pre-defined data model can employ existing hierarchical, network, and relational models.

[0073] In some embodiments, an evaluation system model is constructed based on preliminary processed data and a preset data model. This evaluation system model is a model for users to construct user profiles.

[0074] Step S204: Perform comprehensive processing on the preliminary data from different data sources to obtain the final processed data.

[0075] In step S204, the preliminary processed data from different data sources are first summarized, and then the final processed data is obtained based on the summarized preliminary processed data.

[0076] Step S205: Perform visualization analysis based on the final processed data and evaluation system model to obtain visualization analysis results.

[0077] Visual analysis results are obtained by using the final processed data and evaluation system model for visualization analysis.

[0078] like Figure 3As shown, in some embodiments, step S202 involves performing preliminary processing on the customer data from each data source to obtain preliminary processed data corresponding to the data source, including:

[0079] Step S301: Filter customer data.

[0080] In this step, customer data from different data sources is filtered separately to remove invalid data. For example, for customer data corresponding to the order system, customer data with incomplete order information is deleted. Order information includes username, order number, order quantity, order type, etc.

[0081] Step S302: Extract the filtered customer data according to business needs to obtain the first customer data.

[0082] Customer data obtained from data sources comes in various types, each reflecting different aspects of the customer. Therefore, users can extract (extract) primary customer data from the data source according to their business needs. These business needs can be defined by the user; for example, the business need could be set to analyze the relationship between age groups and the products sold.

[0083] Step S303: Perform a first cross-analysis on the first customer data to obtain the first cross-analysis result.

[0084] It should be noted that the first customer data includes multiple order information from the same customer, as well as similar orders generated by different customers.

[0085] In some embodiments, order information of the same customer is obtained from the first customer data, or order information of similar orders generated by different customers is obtained, and cross-analysis is performed on these order information to obtain a first cross-analysis result. The accuracy of the customer data can be determined based on the first cross-analysis result.

[0086] Step S304: Based on the results of the first cross-analysis, the customer data is transcoded to obtain preliminary processed data.

[0087] Transcoding refers to converting a data type from one format to another. In this embodiment, since the storage formats of customer data from different data sources are not uniform, transcoding can unify the storage format of customer data.

[0088] In some embodiments, preliminary processed data is obtained after transcoding the customer data. This preliminary processed data corresponds to a data source; that is, each data source has its own set of preliminary processed data.

[0089] Steps S301 to S304 allow for the separate processing of customer data from different data sources, improving the reliability of customer data and unifying the data format of customer data, thus laying the groundwork for subsequent data processing.

[0090] In some embodiments, after step S304, the method further includes:

[0091] Step S305: Compress and store the pre-processed data according to the dataset format.

[0092] In this context, "dataset" refers to data of the same type. In this embodiment, customer data of the same type is compressed and stored. The data type can take many forms. For example, data types can be categorized by customer's geographic location, age, or type of product purchased.

[0093] In some embodiments, the storage address may be the same as the data source or a third-party storage address.

[0094] In some embodiments, after step S305 compresses and stores the preliminary processed data in the form of a dataset, it further includes: reporting the preliminary processed data in batches to the central data storage layer according to time periods.

[0095] The length of the time period can be set by the user, allowing for shorter periods when there is a large amount of customer data and longer periods when there is a small amount of customer data. Initially processed data is reported to the central data storage layer in batches according to time periods, reducing centralized requests to the central data storage layer and thus lowering its load.

[0096] In some embodiments, the pre-processed data is reported to the central data storage layer via a wired or wireless network. The central data storage layer consists of servers with data processing capabilities.

[0097] In this embodiment, steps S201 to S204 and steps S301 to S305 are all processed by the basic data processing layer. The basic data processing layer processes the customer data to obtain preliminary processed data.

[0098] like Figure 4 As shown, in some embodiments, step S204 involves comprehensively processing the preliminary processed data from different data sources to obtain the final processed data, including:

[0099] Step 401: Filter the pre-processed data.

[0100] In this embodiment, the initially processed data may be valid for one data source but invalid for others. After data aggregation, all data sources must meet a unified standard. The standard for invalid data can be set by the user. Therefore, the initially processed data is further filtered to remove invalid data.

[0101] In some embodiments, prior to step S401, the preliminary processed data is summarized, that is, preliminary processed data from different data sources are summarized.

[0102] Step S402: Extract the second customer data from the filtered preliminary processed data according to business needs.

[0103] The second customer data is determined based on the user's business needs, which can be set by the user. For example, the business needs can be set to analyze the relationship between age groups and the products sold.

[0104] Step S403: Perform cross-analysis on the second customer data to obtain the second cross-analysis results.

[0105] Cross-analysis involves interpolating initial processed data from different data sources to leverage the strengths of each source, thereby improving the rationality of data processing results and ultimately leading to more accurate subsequent data analysis.

[0106] Step S404: Transcode the pre-processed data based on the results of the second cross-analysis.

[0107] Transcoding refers to converting a data type from one format to another. In this embodiment, since the storage formats of customer data from different data sources are not uniform, transcoding can unify the storage format of customer data.

[0108] In some embodiments, the final processed data is obtained after transcoding the initial processed data.

[0109] Step S405: Cluster and split the pre-processed data after transcoding based on customer category tags to obtain the final processed data.

[0110] Clustering refers to grouping similar customer data together. For example, clustering customer data corresponding to customers whose age groups fall within a preset range.

[0111] In some embodiments, customer group labels are clustered and split according to the evaluation system to obtain the final processed data.

[0112] In some embodiments, after transcoding the preliminary processed data based on the second cross-analysis result in step S404, before performing clustering and splitting of the preliminary data according to customer group labels to obtain the final processed data in step S405, the method further includes: compressing and storing the transcoded preliminary processed data.

[0113] In this context, "dataset" refers to data of the same type. This embodiment stores customer data of the same type after compression. The data type can take many forms. For example, data types can be categorized by customer's geographic location, age, or type of product purchased. The storage address can be the same as the data source or a third-party storage address.

[0114] In step S205, visualization analysis is performed based on the final processed data and evaluation system model to obtain visualization analysis results.

[0115] In this embodiment, the visualization analysis process automatically corresponds to user tags and provides different maintenance suggestions for different types of user tags.

[0116] Visual analysis results can be obtained through value quadrant charts, multi-dimensional radar charts, user tagging systems, and suggestion systems, based on the specific values ​​of different dimensions of data indicators for a particular user.

[0117] The IoT customer data processing method provided in this application performs preliminary and comprehensive processing on customer data, improving the processing efficiency of customer data and reducing the pressure on the central data processing layer.

[0118] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this patent.

[0119] This application also provides an Internet of Things (IoT) customer data processing device. Figure 5 This is a block diagram of an IoT customer data processing device provided in an embodiment of this application. Figure 5 As shown, the IoT customer data processing device includes:

[0120] Module 501 is used to acquire customer data from multiple data sources.

[0121] The data source is the origin of the customer data. Since the customer data comes from the data source, users can clearly identify which data source the customer data originates from.

[0122] In some embodiments, the data source is any two or more of the following: the data source of the customer acquisition system, the data source of the order system, and the data source of the Jasper platform.

[0123] Among them, the customer acquisition system is a system that attracts potential customers from different advertising channels to the enterprise's free nurturing pool, allowing different customers to naturally convert as they independently obtain content that interests them, thus achieving customer acquisition marketing.

[0124] The order system can perform functions such as accepting customer order information, verifying order information, and categorizing orders according to customer and urgency based on inventory information. Users can also obtain basic information about customers, such as their age group and frequently purchased products, through the order system.

[0125] Among them, the Internet of Things (IoT) platform is a cloud computing, big data, artificial intelligence, and cloud-integrated platform that possesses various types of customer information, such as the Jasper platform.

[0126] In some embodiments, customer data includes one or more of customer usage behavior data, purchase behavior data, and basic customer information data.

[0127] Customer behavior data refers to behavioral data generated by customers when using systems such as the Internet of Things (IoT), including the systems or platforms used by customers, customer activity levels, and item popularity. Customer activity level refers to the total number of items for which users have interacted, while item popularity refers to the total number of users who have interacted with an item.

[0128] Purchase behavior data refers to data on customers when they make a purchase, such as the name of the product purchased, the quantity purchased, and the time of purchase.

[0129] The first processing module 502 is used to perform preliminary processing on customer data from each data source to obtain preliminary processed data corresponding to the data source.

[0130] In this embodiment, customer data from different data sources are processed separately, meaning that customer data from different data sources are not processed together.

[0131] For example, when processing customer data obtained from the customer acquisition system, customer data from the order system should not be mixed in.

[0132] Modeling module 503 is used to obtain an evaluation system model based on the preliminary processed data and the preset data model.

[0133] The pre-defined data model provides an abstract framework for the information representation and manipulation of preliminary data processing, based on static features, dynamic behaviors, and constraints. The pre-defined data model can employ existing hierarchical, network, and relational models.

[0134] In some embodiments, an evaluation system model is constructed based on preliminary processed data and a preset data model. This evaluation system model is a model for users to construct user profiles.

[0135] The second processing module 504 is used to perform comprehensive processing on the preliminary processing data from different data sources to obtain the final processed data.

[0136] The second processing module 504 first summarizes the preliminary processed data from different data sources, and then performs further processing based on the summarized preliminary processed data to obtain the final processed data.

[0137] The visualization module 505 is used to perform visualization analysis based on the final processed data and the evaluation system model to obtain visualization analysis results.

[0138] The visualization module 505 utilizes the final processed data and evaluation system model to perform visualization analysis, obtaining visualization analysis results. The visualization analysis automatically assigns user tags and provides different maintenance suggestions for different types of user tags. The visualization analysis results can be presented through value quadrant charts, multi-dimensional radar charts, user tag systems, and suggestion systems, based on the specific values ​​of different dimensional data indicators for a particular user.

[0139] like Figure 6 As shown, in some embodiments, the first processing module includes:

[0140] The first data filtering unit 601 is used to filter customer data.

[0141] In this step, customer data from different data sources is filtered separately to remove invalid data. For example, for customer data corresponding to the order system, customer data with incomplete order information is deleted. Order information includes username, order number, order quantity, order type, etc.

[0142] The first data extraction unit 602 is used to extract the filtered customer data according to business needs to obtain the first customer data.

[0143] Customer data obtained from data sources comes in various types, each reflecting different aspects of the customer. Therefore, users can extract (extract) primary customer data from the data source according to their business needs. These business needs can be defined by the user; for example, the business need could be set to analyze the relationship between age groups and the products sold.

[0144] The first cross-analysis unit 603 is used to perform a first cross-analysis on the first customer data to obtain the first cross-analysis result.

[0145] It should be noted that the first customer data includes multiple order information from the same customer, as well as similar orders generated by different customers.

[0146] In some embodiments, order information of the same customer is obtained from the first customer data, or order information of similar orders generated by different customers is obtained, and cross-analysis is performed on these order information to obtain a first cross-analysis result. The accuracy of the customer data can be determined based on the first cross-analysis result.

[0147] The first transcoding unit 604 is used to transcode customer data based on the first cross-analysis result to obtain preliminary processed data.

[0148] Transcoding refers to converting a data type from one format to another. In this embodiment, since the storage formats of customer data from different data sources are not uniform, transcoding can unify the storage format of customer data.

[0149] The first compression unit 605 is used to compress and store the pre-processed data in the manner of a dataset.

[0150] In this context, "dataset" refers to data of the same type. In this embodiment, customer data of the same type is compressed and stored. The data type can take many forms. For example, data types can be categorized by customer's geographic location, age, or type of product purchased.

[0151] like Figure 7 As shown, in some embodiments, the second processing module includes:

[0152] The second data filtering unit 701 is used to filter the pre-processed data.

[0153] In this embodiment, the initially processed data may be valid for one data source but invalid for others. After data aggregation, all data sources must meet a unified standard. The standard for invalid data can be set by the user. Therefore, the initially processed data is further filtered to remove invalid data.

[0154] The second data extraction unit 702 is used to extract second customer data from the filtered preliminary processed data according to business needs.

[0155] The second cross-analysis unit 703 is used to perform cross-analysis on the second customer data to obtain the second cross-analysis result.

[0156] The second transcoding unit 704 is used to transcode the pre-processed data based on the second cross-analysis result.

[0157] The second compression unit 705 is used to compress and store the transcoded preliminary processed data.

[0158] Clustering splitting unit 706 is used to cluster and split the transcoded preliminary processed data according to customer group labels to obtain the final processed data.

[0159] The IoT customer data processing device provided in this embodiment performs preliminary processing and comprehensive processing on customer data through a first processing module and a second processing module, respectively. That is, it processes customer data through two-level processing modules, which improves the processing efficiency of customer data and reduces the pressure on the central data processing layer.

[0160] It should be noted that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this application, this embodiment does not introduce units that are not closely related to solving the technical problem proposed in this application; however, this does not mean that other units are absent from this embodiment.

[0161] This embodiment also provides an electronic device, including one or more processors; a storage device storing one or more programs thereon, wherein when one or more programs are executed by one or more processors, the one or more processors implement the IoT customer data processing method provided in this embodiment. To avoid repetition, the specific steps of the IoT customer data processing method will not be repeated here.

[0162] This embodiment also provides a computer-readable medium storing a computer program. When the program is executed by a processor, it implements the IoT customer data processing method provided in this embodiment. To avoid repetition, the specific steps of the IoT customer data processing method will not be repeated here.

[0163] Those skilled in the art will understand that all or some of the steps, systems, or apparatuses in the methods claimed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0164] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0165] Those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of this embodiment and form different embodiments.

[0166] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of this application, and this application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this application, and these modifications and improvements are also considered to be within the scope of protection of this application.

Claims

1. An Internet of Things customer data processing method, characterized by, The method comprises the following steps: obtaining customer data of a plurality of data sources; performing preliminary processing on the customer data of each data source respectively to obtain preliminary processing data corresponding to the data source; obtaining an evaluation system model based on the preliminary processing data and a preset data model; performing comprehensive processing on the preliminary processing data of different data sources to obtain final processing data; performing visual analysis processing based on the final processing data and the evaluation system model to obtain a visual analysis result; the comprehensive processing on the preliminary processing data of different data sources to obtain final processing data comprises: filtering the preliminary processing data; extracting the filtered preliminary processing data according to business requirements to obtain second customer data; performing cross analysis on the second customer data to obtain a second cross analysis result; performing transcoding on the preliminary processing data based on the second cross analysis result; performing clustering and splitting on the transcoded preliminary processing data according to customer class group tags to obtain final processing data.

2. The method of claim 1, wherein, The data sources include data sources of a customer acquisition system, data sources of an order system and data sources of an Internet of Things platform.

3. The method of claim 1, wherein, The customer data includes one or more of customer usage behavior data, purchase behavior data and customer basic information data.

4. The method of claim 1, wherein, The preliminary processing on the customer data of each data source respectively to obtain preliminary processing data corresponding to the data source comprises: filtering the customer data; extracting the filtered customer data according to business requirements to obtain first customer data; performing first cross analysis on the first customer data to obtain a first cross analysis result; performing transcoding on the customer data based on the first cross analysis result to obtain preliminary processing data.

5. The method of claim 4, wherein, After the transcoding on the customer data based on the first cross analysis result to obtain preliminary processing data, the method further comprises: compressing and storing the preliminary processing data in the form of a data set.

6. The method of claim 5, wherein, After the compression and storage of the preliminary processing data in the form of a data set, the method further comprises: reporting the preliminary processing data to a central data storage layer in batches according to time periods.

7. The method of claim 1, wherein, After the transcoding on the preliminary processing data based on the second cross analysis result, and before the clustering and splitting on the transcoded preliminary processing data according to customer class group tags to obtain final processing data, the method further comprises: compressing and storing the transcoded preliminary processing data.

8. The method of claim 1, wherein, The visual analysis result includes automatically assigning user tags to users and providing maintenance suggestions.

9. An Internet of Things customer data processing apparatus, characterized by, The method comprises the following steps: an obtaining module for obtaining customer data of a plurality of data sources; a first processing module for performing preliminary processing on the customer data of each data source respectively to obtain preliminary processing data corresponding to the data source; a modeling module for obtaining an evaluation system model based on the preliminary processing data and a preset data model; a first processing module for performing comprehensive processing on the preliminary processing data of different data sources to obtain final processing data; a visual module for performing visual analysis processing based on the final processing data and the evaluation system model to obtain a visual analysis result; The comprehensive processing of the preliminary processing data of different data sources obtains final processing data, including: Filtering the preliminary processing data; Extracting from the filtered preliminary processing data according to business requirements to obtain second customer data; Cross-analyzing the second customer data to obtain a second cross-analysis result; Converting the preliminary processing data based on the second cross-analysis result; Clustering and splitting the converted preliminary processing data according to customer class group tags to obtain final processing data.

Images