WO2023227012A1

WO2023227012A1 - Product data processing method and apparatus, and storage medium

Info

Publication number: WO2023227012A1
Application number: PCT/CN2023/095967
Authority: WO
Inventors: 鲁效平; 陈录城; 高亚琼; 高尚; 景大智; 王超; 王玉梅; 于晓义
Original assignee: 卡奥斯工业智能研究院(青岛)有限公司; 卡奥斯物联科技股份有限公司; 海尔数字科技(青岛)有限公司
Priority date: 2022-05-26
Filing date: 2023-05-24
Publication date: 2023-11-30
Also published as: CN114661968B; CN114661968A

Abstract

Provided in the present application are a product data processing method and apparatus, and a storage medium. The method comprises: acquiring product element data to be processed; performing dimension reduction processing on said product element data; performing data clustering processing on the data which has been subjected to dimension reduction processing, so as to obtain a plurality of clustering results; removing a scatter data set from the plurality of clustering results, so as to obtain a data set composed of data of different types; performing data fusion processing according to the data set, so as to obtain product data feature information; constructing an object granule of a data flow on the basis of the information; and extracting a frequent pattern between data flows, so as to obtain a data set model based on a data resource object for visual output. For all-element multi-dimension heterogeneous data, by means of modeling and visualization technology, a breakthrough is made in the constraints of resource management, heterogeneous data fusion, governance and intelligent analysis of manufacturing big data, and full-chain intelligent cooperation and integration technology driven by data and service in parallel, such that a user can be helped to quickly hit required product data, so as to assist in user decision-making and to promote the intelligent manufacturing of products such as household appliances.

Description

Product data processing method, device and storage medium

This application requests the priority of the Chinese patent application submitted to the China Patent Office on May 26, 2022, with the application number 202210578246.1 and the application name "Product Data Processing Method, Device and Storage Medium", the entire content of which is incorporated herein by reference. Applying.

Technical field

The present application relates to the field of data processing technology, and in particular to a product data processing method, device and storage medium.

Background technique

With the improvement of social living standards, it has become a trend for users to participate in product customization. For example, users can participate in large-scale customization of home appliances to meet the different needs of users.

Since the manufacturing process of home appliances and other products involves many links, there are many types of corresponding product data, and there are problems with inconsistent data dimensions. Users may not be able to understand some product data, thus affecting the user experience of participating in product customization.

The above information disclosed in the Background is only for enhancement of understanding of the context of the application and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art.

Contents of the invention

This application provides a product data processing method, device and storage medium to solve the problems existing in the existing technology.

In the first aspect, this application provides a product data processing method, including:

Get the product element data to be processed;

Perform dimensionality reduction processing on the product element data to obtain dimensionally reduced data;

Perform data clustering processing on the dimensionally reduced data to obtain multiple clustering results;

Remove the scattered point data sets in the multiple clustering results to obtain a data set composed of different types of data;

Perform data fusion processing according to the data set to obtain product data feature information; the fusion processing method includes: sequential decision-making multi-modal deep neural network or distributed parallel computing;

Based on the product data feature information, construct object particles of the data flow;

Extract frequent patterns among the data streams to obtain a data set model based on data resource objects to The product data feature information is visually output.

In some embodiments, it also includes:

Iteratively execute the steps of obtaining user needs, determining recommended content based on the user needs, and visually outputting the recommended content until the iteration stop condition is met;

Wherein, the user requirements are proposed by the user based on the visually output product data feature information.

In some embodiments, determining recommended content according to the user needs and visually outputting the recommended content includes:

Determine a plurality of recommended contents according to the user needs;

Sort the plurality of recommended contents to obtain sorted recommended contents;

Perform visual output on the sorted recommended content.

In some embodiments, the plurality of recommended contents are sorted to obtain sorted recommended content, including:

Determine the degree of matching between each recommended content and the user's needs;

The plurality of recommended contents are sorted in order from high to low matching degrees to obtain sorted recommended contents.

In some embodiments, it also includes:

Output the product data feature information to product-related links;

The product-related links include at least one of product design link, product supply link, product marketing link, product manufacturing link, product logistics link and product service design link.

In some embodiments, the product element data includes at least one of interactive customization data, precision marketing data, collaborative research and development data, collaborative procurement data, supply chain data, smart logistics data, and smart service data.

In a second aspect, this application provides a product data processing device, including:

The acquisition module is used to obtain the product element data to be processed;

A processing module for performing dimensionality reduction processing on the product element data to obtain dimensionally reduced data; performing data clustering processing on the dimensionally reduced data to obtain multiple clustering results; and removing the multiple clustering results. The scattered point data set in the data set is obtained to obtain a data set composed of different types of data; data fusion processing is performed according to the data set to obtain product data feature information; the fusion processing method includes: sequential decision-making multi-modal deep neural network or distributed parallel computing;

An output module is used to construct object particles of data streams based on the product data feature information; extract frequent patterns between the data streams and obtain a data set model based on data resource objects to visually output the product data feature information.

In some embodiments, it also includes:

An iterative module, used to iteratively execute the steps of obtaining user needs, determining recommended content according to the user needs, and visually outputting the recommended content until the iteration stop condition is met; wherein the user needs are the user's based on the visual output. Product data feature information is proposed.

In some embodiments, the iteration module is specifically configured to: determine multiple recommended content according to the user needs; sort the multiple recommended content to obtain sorted recommended content; and sort the sorted recommended content. Perform visual output.

In some embodiments, the iteration module is specifically configured to: determine the matching degree of each recommended content with the user's needs; sort the multiple recommended contents in order of matching degree from high to low, to obtain Recommended content after sorting.

In a third aspect, the present application provides a computer-readable storage medium in which computer-executable instructions are stored, and when executed by a processor, the computer-executable instructions are used to implement the above product data processing method.

The product data processing method, device and storage medium provided by this application include: obtaining product element data to be processed; performing dimensionality reduction processing on the product element data to obtain dimensionally reduced data; performing dimensionality reduction on the dimensionally reduced data. Perform data clustering processing to obtain multiple clustering results; remove scattered point data sets in the multiple clustering results to obtain a data set composed of different types of data; perform data fusion processing based on the data set to obtain product data Feature information; the fusion processing method includes: sequential decision-making multi-modal deep neural network or distributed parallel computing; based on the product data feature information, construct object particles of the data stream; extract frequent patterns between the data streams, A data set model based on the data resource object is obtained to perform dimensionality reduction and aggregation processing on the product element data to obtain product data feature information; and the product data feature information is visually output. This application proposes a product data processing method that uses modeling and visualization technology to break through resource management, heterogeneous data fusion, manufacturing big data governance and intelligent analysis, and data and business parallel drive for all-element and multi-dimensional heterogeneous data. Full-chain intelligent collaboration and integrated technology control can help users quickly target the required product data, assist users in decision-making, and promote the intelligent manufacturing of home appliances and other products.

Description of the drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.

Figure 1 is a schematic diagram of a product data processing method provided by an embodiment of the present application;

Figure 2 is a schematic diagram of the full-element multi-source heterogeneous data modeling and integration process in the embodiment of the present application;

Figure 3 is a schematic diagram of a product data processing device provided by an embodiment of the present application;

Figure 4 is a schematic structural diagram of a computer device provided by an embodiment of the present application.

Specific embodiments of the present disclosure have been shown through the above-mentioned drawings and will be described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the present disclosure to those skilled in the art with reference to the specific embodiments.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments These are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

The terminology used in the embodiments of the present application is only for the purpose of describing specific embodiments and is not intended to limit the present application. As used in the embodiments of this application, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise.

It should also be noted that the terms "includes", "includes" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a good or system including a list of elements includes not only those elements but also those not expressly listed other elements, or elements inherent to the product or system. Without further limitation, an element defined by the statement "comprises a..." does not exclude the presence of other identical elements in the goods or systems that include the stated element.

For example, in the process of mass customization of home appliances and other products, most of the demand data, production data, and resource data related to the product are distributed in a scattered manner, and there are obstacles in data interconnection and transmission, resulting in Users cannot obtain all data in a timely manner.

In addition, for the same problem-oriented data processing space, different granularity selections will bring different complexity of calculation work. Therefore, before analyzing and calculating the problem based on granular computing, whether the granularity standard is correct and whether the selection is appropriate will affect the data efficiency. Calculation is the key to solving problems.

In addition, when visualizing data applications, commonly used technologies can only provide a static view of a certain node's data, making it difficult to draw a dynamic view of the entire process of home appliance customization with user participation.

The product data processing method provided by this application is intended to solve the above technical problems of the existing technology.

The main idea of this application plan is: This application proposes a product data processing method, aiming at all-factor and multi-dimensional heterogeneous data, through modeling and visualization technology, to break through resource management, heterogeneous data fusion, manufacturing big data governance and intelligence The full-chain intelligent collaboration and integrated technical constraints driven by the parallel connection of analysis, data and business can help users quickly target the required product data, assist users in decision-making, and promote the intelligent manufacturing of home appliances and other products.

It can be understood that the processing steps of the product data processing method in this application can be implemented by relevant platforms/software for product data management.

The technical solution of the present application and how the technical solution of the present application solves the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

In some embodiments, a product data processing method is provided.

Figure 1 is a schematic diagram of a product data processing method provided by an embodiment of the present application. As shown in Figure 1, the method mainly includes the following steps:

S100. Obtain product element data to be processed.

Among them, product element data refers to data related to the production and manufacturing process of the product, and product element data is the data source of the full life cycle data of mass customized production products.

Optionally, the product element data includes at least one of interactive customization data, precision marketing data, collaborative R&D data, collaborative procurement data, supply chain data, smart logistics data and smart service data. That is, the product element data can specifically be any of the above. An item in one kind of data can also contain multiple items at the same time.

For example, based on the COSMOPlat platform engine of COSMOPlat, all-element data for mass customization of home appliances can be accessed. Product element data can also include interactive customization data, precision marketing data, and collaborative data. R&D data, collaborative procurement data, supply chain data, smart logistics data, smart service data, etc.

S200. Perform dimensionality reduction processing on the product element data to obtain dimensionally reduced data.

S300: Perform data clustering processing on the dimensionally reduced data to obtain multiple clustering results.

S400. Remove scattered point data sets from multiple clustering results to obtain a data set composed of different types of data.

S500. Perform data fusion processing according to the data set to obtain product data feature information; the fusion processing method includes: sequential decision-making multi-modal deep neural network or distributed parallel computing.

Since the obtained product element data has problems such as inconsistent data types and inconsistent dimensions, data unification and dimensionality reduction need to be performed first.

Specifically, non-uniform data types mean that product element data may contain multiple types of data such as structured data, semi-structured data, and unstructured data. Among them, structured data refers to data managed in the form of relational database tables. The data storage and arrangement of structured data are regular and support functions such as addition, deletion, modification, and query. Structured data specifically includes forms, etc. Semi-structured data refers to data that is non-relational and has a basic fixed structure pattern. Semi-structured data can be understood as intermediate data, such as log files, XML documents, JSON documents, etc. Unstructured data refers to data without a fixed pattern, such as WORD, PDF, PPT, EXL, and pictures and videos in various formats.

Dimension inconsistency means that product element data is data from multiple sources and angles. It can be divided into one-dimensional data, two-dimensional data, multi-dimensional data, etc. For example, one-dimensional data can be questionnaires, research discussion data, etc.

Specifically, considering that most product element data in mass customization of home appliances are distributed in a scattered manner, before processing the product element data, you can also use sampling to select data to select high-latitude representative data for home appliance customization and manufacturing. Then perform dimensionality reduction and clustering processing on the representative data.

In the clustering process, the principle of similarity of different types of data is followed, representative high-dimensional data are clustered, and the fuzzy clustering (FCM) algorithm is used to mine representative content in the data, that is, product data is obtained Feature information. The clustering process also includes the processing step of removing scattered data sets, that is, aggregating adjacent data from the center for later use of multidimensional data.

In the process of obtaining product data feature information based on the clustered data set, the cluster analysis method can be used to perform training-free learning on the aggregation.

For example, assuming that the data types contained in the data set are n, then there are Similar data can be expressed by the following calculation formula.

Among them, d(i, j) represents a multi-dimensional data set with similarity; j represents the data representative content, which can be interactive customization data, precision marketing data, collaborative R&D data, collaborative procurement data, supply chain data, and smart logistics data. , smart service data and any other content; i represents the data dimension; q represents the data clustering process. In the above calculation formula, it is believed that there is a certain relationship between i and j. When the ratio of i and j is close to 0, the value of d(i, j) is larger, and vice versa.

On this basis, use front-end engine tools to arrange the exported data collection. During the arrangement process, all data are taken as research objects, the Euclidean distance between data of different dimensions is used as the basis for arrangement, and the implicit rules within the data are qualitatively expressed based on the global perspective. Therefore, the multi-dimensional data arrangement algorithm formula is as follows:

where mean can be expressed as S _mean represents the similarity of multi-dimensional data customized for home appliances; V _k represents multi-dimensional data attributes; V _i represents the standard deviation of multi-dimensional data; a _ik represents the dimension orientation range; N represents the number of output data permutations. Combining the above calculation formula and the output data, the research on the multi-dimensional data arrangement algorithm is completed.

In the process of data fusion processing based on the data set, sequential decision-making multi-modal deep neural network, distributed parallel computing and other methods can be used to fuse multiple features of the data in multiple rounds to form a multi-feature table of the data set and select as needed Extract to obtain accurate product data feature information.

S600. Based on the product data feature information, construct object particles of the data flow.

S700: Extract frequent patterns between data streams and obtain a data set model based on data resource objects to visually output product data feature information.

After obtaining product data feature information based on product element data, a data set model based on data resource objects can be formed, and a multi-dimensional panoramic view of the product life cycle data space can be constructed.

Specifically, you can use Python language's Flask framework, ECharts and other technologies to complete data visualization. The backend completes data extraction and encapsulation, and uses Ajax technology to complete data interaction between the front and back ends. ECharts technology and Jinja2 template engine and other technologies realize data visualization. Thus, users can directly view the product data feature information output in a visual form.

In the process of data set modeling, first, the object particles of the data flow are constructed. According to the attributes of frequent itemsets, the object particles of the data flow are established. According to the attributes of the object particles, the domain objects containing the same attribute values are searched in the data stream, and the mining of the maximum frequent itemsets is converted into the mining of object particles with the same attributes. calculate. Second, frequent patterns among data streams are extracted. Object granular computing is introduced into the home appliance manufacturing data flow (interaction, design, supply, marketing, manufacturing, logistics, service), multi-granularity correlation analysis is performed, and frequent patterns between multi-source heterogeneous data are extracted.

This embodiment proposes a product data processing method that uses modeling and visualization technology to achieve breakthroughs in resource management, heterogeneous data fusion, manufacturing big data governance and intelligent analysis, and data and business parallel drive for all-element and multi-dimensional heterogeneous data. The full-chain intelligent collaboration and integrated technology constraints can help users quickly target the required product data, assist users in decision-making, and promote the intelligent manufacturing of home appliances and other products.

In some embodiments, the method further includes: iteratively executing the steps of obtaining user needs, determining recommended content according to user needs, and visually outputting the recommended content until the iteration stop condition is met; wherein the user needs are products based on the user's visual output Data feature information is proposed.

Specifically, after viewing the product data feature information of the visual output, the user can put forward corresponding user needs based on the product data feature information of the visual output. Therefore, by obtaining the user needs, the recommended content corresponding to the user can be further determined, and visualization can be continued. Output the recommended content; thus, the user can further propose corresponding user needs based on the visually output recommended content, thereby improving the user experience of participating in product customization.

In some embodiments, determining recommended content based on user needs and visually outputting the recommended content includes: determining multiple recommended content based on user needs; sorting the multiple recommended content to obtain sorted recommended content; The recommended content is visually output.

Specifically, after obtaining user needs, multiple optional recommended contents are first determined according to user needs, sorted according to preset sorting rules, and finally the sorted recommended contents are visually output.

Optionally, sort multiple recommended contents to obtain the sorted recommended content, including: determining the degree of matching between each recommended content and user needs; sorting the multiple recommended contents in order from high to low matching degree, Get sorted recommended content.

Therefore, by sorting the recommended content according to the degree of matching between the recommended content and the user's needs, the recommended content that best matches the user's needs can be output first, thereby improving the accuracy of the recommendation results. accuracy and improve user experience.

In some embodiments, the method further includes: outputting product data feature information to product-related links; wherein the product-related links include product design links, product supply links, product marketing links, product manufacturing links, product logistics links, and product service design At least one of the steps, so that the obtained product data feature information can be applied to the entire product process of interaction/design/supply/marketing/manufacturing/logistics/services in a home appliance mass customization environment.

Figure 2 is a schematic diagram of the full-element multi-source heterogeneous data modeling and integration process in the embodiment of the present application. As shown in Figure 2, the technical solution proposed by the embodiment of the present application is oriented towards interaction/design/in the environment of mass customization of home appliances. Provide full-process product data such as supply/marketing/manufacturing/logistics/services, etc., establish a data set based on data resource objects, and construct a multi-dimensional product life cycle data set model and dynamic panoramic view. In order to solve the problems of large-scale customization full-cycle data generation speed, large magnitude and multi-dimensional heterogeneity, this application innovatively proposes to use methods such as multi-modal deep neural network technology based on sequential decision-making and distributed parallel computing models to achieve multi-dimensional heterogeneity. Dataset fusion, modeling and visualization. In addition, based on the multi-dimensional and multi-modal data of the product life cycle in the mass customization environment, granular computing and frequent item set correlation analysis methods are comprehensively applied to analyze the composite correlation and causality between data sets at multiple granularities and multi-angles, and extract Frequent patterns among multi-source heterogeneous data can be used to mine the evolution rules of the entire product life cycle and the interdependence between each stage in the mass customization platform, providing a basis for decision-making for mass customization production.

It should be understood that although each step in the flow chart in the above embodiment is shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated in this article, the execution of these steps is not strictly limited in order, and they can be executed in other orders. Moreover, at least some of the steps in the figure may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and their execution order is not necessarily sequential. may be performed in turn or alternately with other steps or sub-steps of other steps or at least part of stages.

In some embodiments, a product data processing apparatus is provided.

Figure 3 is a schematic diagram of a product data processing device provided by an embodiment of the present application. As shown in Figure 3, the device includes:

The acquisition module 100 is used to acquire product element data to be processed.

For example, it can be based on the COSMOPlat platform engine to access all-element data for mass customization of home appliances. Product element data can include interactive customization data, precision marketing data, collaborative R&D data, collaborative procurement data, supply chain data, and smart logistics. Data, smart service data, etc.

The processing module 200 is used to perform dimensionality reduction and aggregation processing on product element data to obtain product data feature information.

Optionally, the processing module 200 is specifically used to: perform dimensionality reduction processing on product element data to obtain dimensionally reduced data; perform data clustering processing on the dimensionally reduced data to obtain a data set composed of different types of data; according to the data set Perform data fusion processing to obtain product data feature information.

Optionally, the processing module 200 is specifically used to: perform data clustering processing on the dimensionally reduced data to obtain multiple clustering results; remove scattered point data sets in multiple clustering results to obtain data composed of different types of data. set.

Specifically, considering that most product element data in mass customization of home appliances are distributed in a scattered manner, before processing the product element data, you can also use sampling to select data to select high-latitude representative data for home appliance customization and manufacturing. Then perform dimensionality reduction and clustering on the representative data. reason.

For example, assuming that the data types contained in the data set are n, similar data existing in mass customization of home appliances can be expressed by the following calculation formula.

On this basis, use front-end engine tools to arrange the exported data collection. During the arrangement process, all data are taken as research objects, and the Euclidean distance between data of different dimensions is used as the basis for arrangement. The implicit rules within the data are qualitatively expressed based on the global perspective. Therefore, the multidimensional data arrangement algorithm formula is as follows:

where mean can be expressed as S _mean represents the similarity of multi-dimensional data customized for home appliances; V _k represents multi-dimensional data attributes; V _i represents multi-dimensional data standard deviation; a _ik represents the dimension orientation range; N represents the number of output data permutations. Combining the above calculation formula and the output data, the research on the multi-dimensional data arrangement algorithm is completed.

The output module 300 is used to construct object particles of the data flow based on the product data feature information; Frequent patterns between the data streams are extracted to obtain a data set model based on data resource objects to visually output product data feature information.

In the process of data set modeling, first, the object particles of the data flow are constructed. According to the attributes of frequent itemsets, the object particles of the data flow are established. According to the attributes of the object particles, the domain objects containing the same attribute values are searched in the data stream, and the mining of the maximum frequent itemsets is converted into the mining of object particles with the same attributes. calculate. Second, frequent patterns between data streams are extracted. Object granular computing is introduced into the home appliance manufacturing data flow (interaction, design, supply, marketing, manufacturing, logistics, service), multi-granularity correlation analysis is performed, and frequent patterns between multi-source heterogeneous data are extracted.

In some embodiments, the processing module 200 is also configured to: iteratively execute the steps of obtaining user needs, determining recommended content according to user needs, and visually outputting the recommended content until the iteration stop condition is met; wherein the user needs are based on the visual The output product data feature information is proposed.

Optionally, sort multiple recommended content to obtain the sorted recommended content, including: OK The degree of matching between each recommended content and the user's needs; sort multiple recommended contents in order of matching degree from high to low to obtain the sorted recommended content.

Therefore, by sorting the recommended content according to the degree of matching between the recommended content and the user's needs, the recommended content that best matches the user's needs can be output first, thereby improving the accuracy of the recommendation results and improving the user experience.

In some embodiments, the output module 300 is also used to: output product data feature information to product-related links; product-related links include product design links, product supply links, product marketing links, product manufacturing links, product logistics links, and product services. At least one item in the design process, so that the obtained product data feature information can be applied to the entire product process of interaction/design/supply/marketing/manufacturing/logistics/services in a mass customization environment for home appliances.

For specific limitations on the product data processing device, please refer to the above limitations on the product data processing method, which will not be described again here. Each module in the above product data processing device can be implemented in whole or in part by software, hardware and combinations thereof. Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In some embodiments, a computer device is provided.

FIG. 4 is a schematic structural diagram of a computer device provided by an embodiment of the present application. As shown in FIG. 4 , the computer device includes a processor 11 , a memory 12 and a display 13 .

The memory 12 is used to store programs and data, and the processor 11 calls the programs stored in the memory to execute the following technical solutions:

(1) Obtain the product element data to be processed;

(2) Perform dimensionality reduction and aggregation processing on product element data to obtain product data feature information;

Specifically, non-uniform data types mean that product element data may contain multiple types of data such as structured data, semi-structured data, and unstructured data. Among them, structured data refers to data managed in the form of relational database tables. The data storage and arrangement of structured data are regular and support functions such as addition, deletion, modification, and query. Structured data specifically includes forms, etc. Semi-structured data refers to data that is non-relational and has a basic fixed structure pattern. Semi-structured data can be understood as intermediate data, such as log files, XML documents, JSON documents, etc. Unstructured data refers to data without fixed patterns, such as WORD, PDF, PPT, EXL, and pictures and videos in various formats.

Optionally, perform dimensionality reduction and aggregation processing on product element data to obtain product data feature information, including:

Perform dimensionality reduction processing on product element data to obtain dimensionally reduced data;

Perform data clustering on the dimensionally reduced data to obtain a data set composed of different types of data;

Perform data fusion processing based on the data set to obtain product data feature information.

Optionally, perform data clustering on the dimensionally reduced data to obtain a data set composed of different types of data, including:

Perform data clustering on the dimensionally reduced data to obtain multiple clustering results;

Remove scattered point data sets from multiple clustering results to obtain a data set composed of different types of data.

(3) Visually output product data feature information.

After obtaining the product data feature information based on the product element data, a data resource-based Data set model of objects and build a multi-dimensional panoramic view of the product life cycle data space.

Wherein, the product data feature information is visually output, for example, it may be displayed through the display 13, so that the user can intuitively view the product data feature information.

In the process of data set modeling, first, the object particles of the data flow are constructed. According to the attributes of frequent itemsets, the object particles of the data flow are established. According to the attributes of the object particles, the universe objects containing the same attribute values are searched in the data stream, and the mining of the maximum frequent itemsets is converted into the mining of object particles with the same attributes. calculate. Second, frequent patterns among data streams are extracted. Object granular computing is introduced into the home appliance manufacturing data flow (interaction, design, supply, marketing, manufacturing, logistics, service), multi-granularity correlation analysis is performed, and frequent patterns between multi-source heterogeneous data are extracted.

In some embodiments, the technical solution also includes:

(4) Iteratively execute the steps of obtaining user needs, determining recommended content based on user needs, and visually outputting the recommended content until the iteration stop condition is met; where the user needs are proposed by the user based on the product data feature information of the visual output.

Optionally, sort multiple recommended content to obtain the sorted recommended content, including: determining the degree of matching between each recommended content and user needs; and sorting multiple recommended contents in order from high to low matching degree. The recommended content is sorted to obtain the sorted recommended content.

In the above computer equipment, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines, such as through a bus. The memory stores computer execution instructions for implementing the data access control method, including at least one software function module that can be stored in the memory in the form of software or firmware. The processor executes various software programs and modules by running the software programs and modules stored in the memory. Functional applications and data processing.

The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Only Memory Read-only memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc. Among them, the memory is used to store the program, and the processor executes the program after receiving the execution instruction. Furthermore, the software programs and modules in the above-mentioned memory may also include an operating system, which may include various software components and/or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may Communicates with various hardware or software components to provide a running environment for other software components.

The processor can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc. Each method, step and logical block diagram disclosed in the embodiment of this application can be implemented or executed. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

In some embodiments, a computer-readable storage medium is provided, the computer-readable storage medium Computer execution instructions are stored in, and when the computer execution instructions are executed by the processor, they are used to implement the steps of each method embodiment of the present application.

In some embodiments, a computer program product is provided, including a computer program that implements the steps of each method embodiment of the present application when executed by a processor.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program may include the processes of the above method embodiments. Any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Other embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure that follow the general principles of the disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the disclosure. . It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise structures described above and illustrated in the accompanying drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the disclosure is limited only by the appended claims.

Claims

A product data processing method, which includes:

Get the product element data to be processed;

Perform dimensionality reduction processing on the product element data to obtain dimensionally reduced data;

Perform data clustering processing on the dimensionally reduced data to obtain multiple clustering results;

Remove the scattered point data sets in the multiple clustering results to obtain a data set composed of different types of data;

Perform data fusion processing according to the data set to obtain product data feature information; the fusion processing method includes: sequential decision-making multi-modal deep neural network or distributed parallel computing;

Based on the product data feature information, construct object particles of the data flow;

Frequent patterns between the data streams are extracted to obtain a data set model based on data resource objects to visually output the product data feature information.
The method of claim 1, further comprising:

Iteratively execute the steps of obtaining user needs, determining recommended content based on the user needs, and visually outputting the recommended content until the iteration stop condition is met;

Wherein, the user requirements are proposed by the user based on the visually output product data feature information.
The method according to claim 2, wherein determining recommended content according to user needs and visually outputting the recommended content includes:

Determine a plurality of recommended contents according to the user needs;

Sort the plurality of recommended contents to obtain sorted recommended contents;

Perform visual output on the sorted recommended content.
The method according to claim 3, wherein said sorting the plurality of recommended contents to obtain the sorted recommended contents includes:

Determine the degree of matching between each recommended content and the user's needs;

The plurality of recommended contents are sorted in order from high to low matching degrees to obtain sorted recommended contents.
The method according to any one of claims 1-4, further comprising:

Output the product data feature information to product-related links;

The product-related links include product design link, product supply link, product marketing link, At least one of the product manufacturing link, product logistics link and product service design link.
The method according to any one of claims 1 to 4, wherein the product element data includes interactive customization data, precision marketing data, collaborative research and development data, collaborative procurement data, supply chain data, smart logistics data and smart service data. at least one of.
A product data processing device, which includes:

The acquisition module is used to obtain the product element data to be processed;

A processing module for performing dimensionality reduction processing on the product element data to obtain dimensionally reduced data; performing data clustering processing on the dimensionally reduced data to obtain multiple clustering results; and removing the multiple clustering results. The scattered point data set in the data set is obtained to obtain a data set composed of different types of data; data fusion processing is performed according to the data set to obtain product data feature information; the fusion processing method includes: sequential decision-making multi-modal deep neural network or distributed parallel computing;

An output module is used to construct object particles of data streams based on the product data feature information; extract frequent patterns between the data streams and obtain a data set model based on data resource objects to visually output the product data feature information.
The device of claim 7, further comprising:

An iterative module, used to iteratively execute the steps of obtaining user needs, determining recommended content according to the user needs, and visually outputting the recommended content until the iteration stop condition is met; wherein the user needs are the user's based on the visual output. Product data feature information is proposed.
The device according to claim 8, wherein the iteration module is specifically configured to: determine a plurality of recommended contents according to the user needs; sort the plurality of recommended contents to obtain the sorted recommended contents; The sorted recommended content is visually output.
The device according to claim 9, wherein the iteration module is specifically configured to: determine the matching degree of each recommended content with the user needs; Sort the content and get the sorted recommended content.
A computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when executed by a processor, the computer-executable instructions are used to implement the product as claimed in any one of claims 1-6 Data processing methods.