Enterprise dynamic perception method and system based on big data and big model

Abstract

The present application relates to the technical field of enterprise dynamic data analysis, and specifically to an enterprise dynamic perception method and system based on big data and big models. When the present application is applied, the production data is screened and streamlined according to the access request of the access terminal to obtain the target production data corresponding to the access request. The initial access terminal that meets the authority can obtain the visual graphic data corresponding to the target production data, so that the data can be viewed intuitively. Then, based on the customer's attention dimension from the target production data and historical production data, a data trend change graph is generated to intuitively reflect the change trend of the attention dimension. Annotations can also be made to improve and enrich various data, and then the data trend change graph, data tags and first-level data annotations are pushed to the data access terminal of the same level or higher level. These data access terminals can obtain complete, streamlined and enriched data results, thereby providing these data access terminals with high-quality data to reflect the dynamic status of the enterprise.

Description

Technical Field

[0001] The present application relates to the technical field of enterprise dynamic data analysis, and specifically to an enterprise dynamic perception method and system based on big data and big models. Background Art

[0002] Enterprise dynamic data refers to data generated or updated in real time during the operation of the enterprise. These data have an important impact on enterprise decision-making, operational efficiency and market competitiveness. Dynamic data often comes from different data sources, such as industrial production lines, social media, customer relationship management (CRM) systems, point of sale (POS) systems, etc. Enterprises need to conduct in-depth analysis of dynamic data to discover potential problems. Especially in industrial production lines, the production data of industrial production lines has a great impact on enterprises. How to analyze the dynamic status of industrial production lines during the operation of enterprises and obtain high-quality data results is a technical problem that needs to be solved in this field. Summary of the invention

[0003] In view of this, the present application provides a method and system for enterprise dynamic perception based on big data and big models, which can perform data analysis on the dynamic status of industrial production lines during enterprise operations and obtain high-quality data results.

[0004] In the first aspect, the present application provides a method for dynamic perception of an enterprise based on big data and big models, including: obtaining the production data of the enterprise's industrial production line in real time, and obtaining the access rights corresponding to the production data; obtaining the access request of the initial access terminal, and obtaining the port authority of the data access terminal corresponding to the initial access terminal; extracting the target production data of the corresponding category from the production data according to the access request; if the port authority matches the access rights of the target production data, generating the corresponding target production data as visual graphic data, and pushing the target production data and the corresponding visual graphic data to the initial access terminal; based on the push time of the target production data and the visual graphic data, retrieving the corresponding category of the target production data within the first preset time period in history. Historical production data; obtaining customer data stored in an enterprise server, and extracting the focus dimensions of the category corresponding to the target production data according to the customer data; extracting the focus data corresponding to the focus dimensions from the target production data, and extracting the historical focus data corresponding to the focus dimensions from the historical production data; generating a data trend change graph according to the focus data and the historical focus data; making corresponding types of data tags for various change trends in the data trend change graph; obtaining the first-level data annotations made by the initial access terminal to the target production data, the historical production data, the data trend change graph and the data tags; and pushing the data trend change graph, the data tags and the first-level data annotations to a data access terminal with access rights equal to or higher than that of the initial access terminal.

[0005] In combination with the first aspect, in a possible implementation method, it also includes: obtaining secondary data annotations made by a first access terminal with first preset access rights to the data trend change graph and the data mark; and pushing the secondary data annotations to a second access terminal with second preset access rights; wherein the second access terminal includes the initial access terminal, and the second preset access rights are lower than or equal to the first preset access rights.

[0006] In combination with the first aspect, in a possible implementation method, it also includes: aggregating the historical multiple groups of visual graphic data corresponding to the category corresponding to the access request; generating a first sorting parameter for the multiple groups of visual graphic data in chronological order; and pushing the multiple groups of visual graphic data and the first sorting parameter to a data access terminal with a third preset access right.

[0007] In combination with the first aspect, in a possible implementation method, the summary of the historical multiple groups of visual graphic data corresponding to the category corresponding to the access request includes: based on the request time of the access request of the initial access end, summarizing the multiple groups of visual graphic data corresponding to the category corresponding to the access request within a second preset time period of history.

[0008] In combination with the first aspect, in a possible implementation method, the summary of the historical multiple groups of visual graphic data corresponding to the category corresponding to the access request includes: based on the request time of the access request of the initial access end, summarizing the multiple groups of visual graphic data obtained by all the initial access ends requesting access to the corresponding category within a preset number of historical requests.

[0009] In combination with the first aspect, in a possible implementation method, it also includes: based on the request time of the access request of the initial access terminal, aggregating multiple groups of the visual graphic data corresponding to multiple categories in the access request; generating a second sorting parameter for the multiple groups of the visual graphic data in order of data size; and pushing the multiple groups of the visual graphic data and the second sorting parameter to the data access terminal with a fourth preset access right.

[0010] In combination with the first aspect, in a possible implementation method, it also includes: if multiple initial access terminals issue the access request to the same category within a third preset time period, then aggregating the port data of multiple data access terminals corresponding to the multiple initial access terminals; and pushing the port data to the data access terminal with access rights equal to or higher than the initial access terminal.

[0011] In combination with the first aspect, in a possible implementation method, it also includes: obtaining data modifications made to the target production data and the visual graphic data by a third access terminal with fifth preset access rights; and pushing the target production data and the visual graphic data before and after the modification to a fourth access terminal with sixth preset access rights; wherein the fourth access terminal includes the initial access terminal, and the sixth preset access rights are lower than or equal to the fifth preset access rights.

[0012] In combination with the first aspect, in a possible implementation method, it also includes: importing the target production data, the historical production data, the data trend change graph, the data tags and the first-level data annotations into the AI ​​analysis model; if the trend change in the data trend change graph exceeds a preset amplitude, marking the production data within the range corresponding to the trend change exceeding the preset amplitude as risk data; making a risk solution for the risk data based on the AI ​​analysis model; and pushing the risk solution to the data access terminal with access rights equal to or higher than that of the initial access terminal.

[0013] In the second aspect, the present application provides an enterprise dynamic perception system based on big data and big models, including: a data acquisition module, configured to: acquire the production data of the enterprise's industrial production line in real time, and acquire the access rights corresponding to the production data; acquire the access request of the initial access terminal, and acquire the port authority of the data access terminal corresponding to the initial access terminal; extract the target production data of the corresponding category from the production data according to the access request; a data statistics module, which is communicated and connected with the data acquisition module, and the data statistics module is configured to: if the port authority matches the access right of the target production data, then the corresponding target production data is generated as visual graphic data; a first data push module, which is communicated and connected with the data statistics module, and the first data push module is configured to: push the target production data and the corresponding visual graphic data to the initial access terminal; a specific data screening module, which is communicated and connected with the data acquisition module and the first data push module respectively, and the specific data screening module is configured to: based on the push of the target production data and the visual graphic data At the same time, retrieve the historical production data of the corresponding category of the target production data within the first preset time period in history; obtain the customer data stored in the enterprise server, and extract the focus dimension of the corresponding category of the target production data according to the customer data; extract the focus data corresponding to the focus dimension from the target production data, and extract the historical focus data corresponding to the focus dimension from the historical production data; a data analysis module is communicated and connected with the specific data screening module, and the data analysis module is configured to: generate a data trend change graph according to the focus data and the historical focus data; make corresponding types of data tags for multiple change trends in the data trend change graph; obtain the first-level data annotations made by the initial access terminal to the target production data, the historical production data, the data trend change graph and the data tags; and a second data push module is communicated and connected with the data analysis module, and the second data push module is configured to: push the data trend change graph, the data tags and the first-level data annotations to the data access terminal with access rights equal to or higher than that of the initial access terminal.

[0014] When this application is applied, the production data is screened and streamlined according to the access request of the access terminal to obtain the target production data corresponding to the access request. The initial access terminal that meets the authority can obtain the visual graphic data corresponding to the target production data, so that the data can be viewed intuitively. Then, based on the customer's focus dimensions, a data trend change graph is generated from the target production data and historical production data, so as to intuitively reflect the change trend of the focus dimension. It is also possible to further annotate the target production data, historical production data, data trend change graph, and data tags to improve and enrich the data, and then push the data trend change graph, data tags, and first-level data annotations to the data access terminal of the same level or higher level. These data access terminals can obtain complete, streamlined, and enriched data results, thereby providing high-quality data for the data access terminals of the same level or higher level to reflect the dynamic status of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The figure is a schematic diagram of the method steps of a method for dynamic perception of an enterprise based on big data and big models provided by one embodiment of the present application.

[0016] Figure 2 Shown is a schematic diagram of the method steps of a method for dynamic enterprise perception based on big data and big models provided in another embodiment of the present application.

[0017] Figure 3 Shown is a schematic diagram of the method steps of a method for dynamic enterprise perception based on big data and big models provided in another embodiment of the present application.

[0018] Figure 4 Shown is a schematic diagram of the method steps of a method for dynamic enterprise perception based on big data and big models provided in another embodiment of the present application.

[0019] Figure 5 Shown is a schematic diagram of the method steps of a method for dynamic enterprise perception based on big data and big models provided in another embodiment of the present application.

[0020] Figure 6 Shown is a schematic diagram of the method steps of a method for dynamic enterprise perception based on big data and big models provided in another embodiment of the present application.

[0021] Figure 7 Shown is a schematic diagram of the method steps of a method for dynamic enterprise perception based on big data and big models provided in another embodiment of the present application.

[0022] Figure 8 Shown is a schematic diagram of the method steps of a method for dynamic enterprise perception based on big data and big models provided in another embodiment of the present application.

[0023] Fig. 9Shown is a schematic diagram of the method steps of a method for dynamic enterprise perception based on big data and big models provided in another embodiment of the present application.

[0024] Fig.10 Shown is a system schematic diagram of an enterprise dynamic perception system based on big data and big models provided by an embodiment of the present application.

[0025] Fig.11 Shown is a schematic structural diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] The following are some examples of enterprise dynamic perception methods based on big data and big models:

[0028] Figure 1 The figure shows a method step diagram of a method for enterprise dynamic perception based on big data and big models provided by an embodiment of the present application. The present application provides a method for enterprise dynamic perception based on big data and big models. In one embodiment, as Figure 1 As shown, the enterprise dynamic perception method based on big data and big models includes:

[0029] Step 110: Obtain the production data of the enterprise's industrial production line in real time, and obtain access rights corresponding to the production data.

[0030] In this step, the enterprise's industrial production line is monitored in real time through the Internet of Things, and production data is obtained through the Internet of Things, and the pre-set access rights for the production data are retrieved.

[0031] Step 120: Obtain an access request from the initial access end, and obtain a port permission of the data access end corresponding to the initial access end.

[0032] In this step, the access request is the production data category that the access end wants to access when trying to access, and at the same time, the port permissions of the data access end pre-set at the access end are retrieved. The initial access end can be set to a department of the enterprise or an employee with higher permissions of the enterprise.

[0033] Step 130: extract target production data of a corresponding category from the production data according to the access request.

[0034] In this step, the target production data is extracted from the production data according to the production data category that the access terminal wants to access obtained in step 120. The access rights to the production data have been obtained in step 110, and the access rights corresponding to the target production data are obtained in this step.

[0035] Step 140: If the port authority matches the access authority of the target production data, the corresponding target production data is generated as visual graphic data, and the target production data and the corresponding visual graphic data are pushed to the initial access terminal.

[0036] In this step, the port authority of the access end is compared with the access authority of the target production data. If the port authority is greater than or equal to the access authority of the target production data, access is allowed, and the target production data is generated as visual graphic data. When generating visual graphic data, a graphic data template is pre-made according to the industry practice and expert editing of the industry. After the target production data is obtained, the specific target production data is imported into the graphic data template using an AI algorithm to obtain the visual graphic data.

[0037] Step 150: Based on the push time of the target production data and the visual graphic data, retrieve the historical production data of the category corresponding to the target production data within the first preset historical time period.

[0038] In this step, the length of the first preset time period in history can be preset, for example, it can be set to 3 days, 5 days, 8 days or 15 days before the push time. For example, if the first preset time period in history is set to 8 days before the push time, the production data belonging to the target production data category in the past 8 days will be retrieved as the historical production data.

[0039] Step 160: Obtain the customer data stored in the enterprise server, and extract the focus dimension of the corresponding category of the target production data based on the customer data.

[0040] In this step, customer data is pre-stored in the enterprise server, and the focus dimensions can be set directly by multiple customers, or obtained through questionnaire surveys, or set by the enterprise based on customer data. The focus dimensions reflect the type of data that this type of customer is most concerned about.

[0041] Step 170: extract the attention data corresponding to the attention dimension from the target production data, and extract the historical attention data corresponding to the attention dimension from the historical production data.

[0042] In this step, based on the data type of the concerned dimension, data of this type is extracted from the target production data as concerned data, and data of this type is extracted from the historical production data as historical concerned data. In this step, the data that the customer is most concerned about is extracted and screened for the customer's concerned dimension.

[0043] Step 180: Generate a data trend change graph based on the attention data and historical attention data.

[0044] In this step, according to the customer's attention dimension, the attention data and historical attention data are generated according to the time change to generate a data trend change chart, so as to reflect the change trend of the production data corresponding to the customer's attention dimension in the first historical preset time period. For example, if the first historical preset time period is set to the 8 days before the push time, and the customer's attention dimension is the production efficiency of a product in the industrial production line, then the data trend change chart reflects the change trend of the production efficiency in the past 8 days.

[0045] Step 190: Mark the various change trends in the data trend change diagram with corresponding types of data.

[0046] In this step, different data labels are made for different changing trends. For example, the rising trend part is marked as Class A, the falling trend part is marked as Class B, and the stable trend part is marked as Class C, so as to more clearly distinguish different changing trends.

[0047] Step 200: Obtain the primary data annotations made by the initial access end on the target production data, historical production data, data trend change graph and data mark.

[0048] In this step, the initial access end annotates the target production data and historical production data corresponding to the access request category, and annotates the data trend change graph and data mark corresponding to the focus dimension, and packages multiple annotations into a first-level data annotation. The first-level data annotation includes the summary, correction, supplement and annotation of the data trend change graph.

[0049] Step 210: Push the data trend change graph, data tags, and primary data annotations to a data access terminal with access rights equal to or higher than the initial access terminal.

[0050] In this step, the data access end with access rights equal to or higher than the initial access end is generally a port of the same level or higher level. The data trend change chart, data tags and first-level data annotations obtained after the initial access end processes the data further improve, streamline and enrich the production data, making the pushed data more valuable for reference and improving the data quality.

[0051] When this embodiment is applied, the production data is screened and streamlined according to the access request of the access terminal to obtain the target production data corresponding to the access request. The initial access terminal that meets the authority can obtain the visual graphic data corresponding to the target production data, so that the data can be viewed intuitively. Then, based on the customer's focus dimensions, a data trend change graph is generated from the target production data and historical production data, so as to intuitively reflect the change trend of the focus dimension. It is also possible to further annotate the target production data, historical production data, data trend change graph, and data tags to improve and enrich the data, and then push the data trend change graph, data tags, and first-level data annotations to the data access terminals of the same level or higher level. These data access terminals can obtain complete, streamlined, and enriched data results, thereby providing high-quality data for the data access terminals of the same level or higher level to reflect the dynamic status of the enterprise.

[0052] Figure 2 FIG. 1 is a schematic diagram of a method for dynamic perception of an enterprise based on big data and big models provided by another embodiment of the present application. Figure 2 As shown, the enterprise dynamic perception method based on big data and big models also includes:

[0053] Step 220: Obtain secondary data annotations made by the first access terminal with the first preset access authority on the data trend change graph and the data tags.

[0054] Step 230: Push the secondary data annotation to a second access terminal having a second preset access right; wherein the second access terminal includes the initial access terminal, and the second preset access right is lower than or equal to the first preset access right.

[0055] In this embodiment, the first preset access right is generally set to be higher than the initial access right, that is, the upper-level port of the initial access port further annotates the data trend change graph and the data mark as a secondary data annotation, and the secondary data annotation made by the upper-level port has more reference value and quality. After making the secondary data annotation, it is pushed to the same or lower-level ports to inform the same or lower-level ports of the data annotation made this time. The secondary data annotation includes the summary, correction, supplement and annotation of the data trend change graph.

[0056] Figure 3 FIG. 1 is a schematic diagram of a method for dynamic perception of an enterprise based on big data and big models provided by another embodiment of the present application. Figure 3 As shown, the enterprise dynamic perception method based on big data and big models also includes:

[0057] Step 240: Summarize multiple groups of historical visualized graphic data corresponding to the categories corresponding to the access requests.

[0058] Step 250: Generate a first sorting parameter by sorting the multiple groups of visualized graphic and text data in chronological order.

[0059] Step 260: Push the multiple groups of visualized graphic data and the first sorting parameter to a data access terminal having a third preset access right.

[0060] When this embodiment is applied, multiple groups of visual graphic data corresponding to the category of the access request in the past historical time period are obtained and summarized. Then they are sorted in ascending or descending order according to the time sequence. The first sorting parameter is the sorting data of the multiple groups of visual graphic data, that is, the visual graphic data can be sorted in chronological order through the first sorting parameter. The third preset access right can be set to be equal to or higher than the initial access end, that is, to further improve and optimize the pushed data, so that the data access end with the third preset access right can obtain multiple groups of visual graphic data with higher quality and higher reference value. These data access ends can automatically sort the visual graphic data by time according to the first sorting parameter.

[0061] Figure 4 FIG. 1 is a schematic diagram of a method for dynamic perception of an enterprise based on big data and big models provided by another embodiment of the present application. Figure 4 As shown, step 240 includes:

[0062] Step 241: Based on the request time of the access request of the initial access terminal, a plurality of groups of visual graphic data corresponding to the categories corresponding to the access requests within a second preset time period in history are summarized.

[0063] When this embodiment is applied, step 240 is concretized, and the access request of step 120 is used as the time reference as the current request time for historical aggregation, and the aggregated data object is the visual graphic data of the category corresponding to the access request in step 120. For example, if the second preset historical time period is set to the past 8 days, the visual graphic data of the corresponding category in the past 8 days is obtained with the access request of step 120 as the time reference. This embodiment can obtain visual graphic data within a period of history, and can obtain multiple groups of visual graphic data with higher quality and higher reference value based on time.

[0064] Figure 5 FIG. 1 is a schematic diagram of a method for dynamic perception of an enterprise based on big data and big models provided by another embodiment of the present application. Figure 5 As shown, step 240 includes:

[0065] Step 242: Based on the request time of the access request of the initial access terminal, multiple groups of visualized graphic data obtained by all initial access terminals in requesting access to the corresponding category within a preset number of historical requests are summarized.

[0066] When this embodiment is applied, step 240 is concretized, and the access request of step 120 is used as the time base to perform historical aggregation as the current request time. The aggregated data volume is the historical preset request number, the aggregated data category is the category corresponding to the access request in step 120, and the aggregated object is all initial access terminals that issue access requests of the same category. For example, if the historical preset request number is set to the past 20 times, then the access request of step 120 is used as the time base, and the visual graphic data obtained by the past 20 requests are obtained from all initial access terminals that have requested the same category of data. This embodiment can obtain visual graphic data of a certain number of times in history, and the acquisition object is all initial access terminals that issue access requests of the same category. All initial access terminals can be comprehensively viewed to obtain multiple sets of visual graphic data with higher quality and higher reference value.

[0067] Figure 6 FIG. 1 is a schematic diagram of a method for dynamic perception of an enterprise based on big data and big models provided by another embodiment of the present application. Figure 6 As shown, the enterprise dynamic perception method based on big data and big models also includes:

[0068] Step 270: Based on the request time of the access request of the initial access end, multiple groups of visual graphic data corresponding to multiple categories in the access request are summarized.

[0069] Step 280: Generate a second sorting parameter for the multiple groups of visualized graphic data in order of data size.

[0070] Step 290: Push the multiple sets of visualized graphic data and the second sorting parameter to a data access terminal having a fourth preset access authority.

[0071] When this embodiment is applied, the access request of step 120 is used as the time reference as the current request moment, and multiple groups of visual graphic data corresponding to multiple categories of target production data at the current moment are summarized, sorted according to the data size, and finally pushed to the data access terminal. The fourth preset access right can be set to be equal to or higher than the initial access terminal, that is, to further improve and optimize the pushed data, and push multiple groups of visual graphic data of different categories for reference and reference, so that the data access terminal with the fourth preset access right can obtain multiple groups of visual graphic data with a larger range, greater breadth, and more types.

[0072] Figure 7 FIG. 1 is a schematic diagram of a method for dynamic perception of an enterprise based on big data and big models provided by another embodiment of the present application. Figure 7 As shown, the enterprise dynamic perception method based on big data and big models also includes:

[0073] Step 300: If multiple initial access terminals send access requests to the same category within a third preset time period, port data of multiple data access terminals corresponding to the multiple initial access terminals are aggregated.

[0074] Step 310: Push the port data to a data access terminal with access rights equal to or higher than the initial access terminal.

[0075] When this embodiment is applied, the ports with the same access request are summarized and counted. The third preset time period can be set to within 1 day, within 3 days, or within 5 days. For example, if the third preset time period is set to within 3 days, the port data of all initial access terminals with the same access request within 3 days are retrieved. The port data includes the IP address, access duration, number of visits, and access time of each initial access terminal. The port data is sent to a data access terminal that is equal to or higher than the initial access terminal, and the ports with the same access request can be counted and analyzed.

[0076] Figure 8 FIG. 1 is a schematic diagram of a method for dynamic perception of an enterprise based on big data and big models provided by another embodiment of the present application. Figure 8 As shown, the enterprise dynamic perception method based on big data and big models also includes:

[0077] Step 320: Obtain data modifications made to the target production data and the visualized graphic data by a third access terminal having the fifth preset access authority.

[0078] Step 330: Push the target production data and visualized graphic data before and after modification to a fourth access terminal with a sixth preset access right; wherein the fourth access terminal includes an initial access terminal, and the sixth preset access right is lower than the fifth preset access right.

[0079] In this embodiment, the fifth preset access right is generally set to be higher than the initial access right, and such high-authority ports can modify and revise the target production data and visual graphic data, and then push the modified data to ports with lower than the fifth preset access right.

[0080] Fig. 9 FIG. 1 is a schematic diagram of a method for dynamic perception of an enterprise based on big data and big models provided by another embodiment of the present application. Fig. 9 As shown, the enterprise dynamic perception method based on big data and big models also includes:

[0081] Step 340: Import the target production data, historical production data, data trend change chart, data tags and primary data annotations into the AI ​​analysis model.

[0082] Step 350: If the trend change in the data trend change diagram exceeds a preset range, the production data within the range corresponding to the trend change exceeding the preset range is marked as risk data.

[0083] Step 360: Produce risk solutions for risk data based on the AI ​​analysis model.

[0084] Step 370: Push the risk solution to the data access terminal with access rights equal to or higher than the initial access terminal.

[0085] When this embodiment is applied, AI analysis is used to perform risk analysis on production data with excessive trend changes. The basic model of AI analysis can be trained in advance based on production data and corresponding risk solutions, and retrained and updated in real time during analysis. Finally, the risk solution is pushed to a data access terminal that is equal to or higher than the initial access terminal to provide a reference for risk resolution.

[0086] An exemplary enterprise dynamic perception system based on big data and big models is as follows:

[0087] Fig.10 The figure shows a system diagram of a system for enterprise dynamic perception based on big data and big models provided by an embodiment of the present application. The present application also provides a system for enterprise dynamic perception based on big data and big models, such as Fig.10 As shown, the system includes: a data acquisition module 101, a data statistics module 102, a first data push module 103, a specific data screening module 104, a data analysis module 105 and a second data push module 106.

[0088] The data acquisition module 101 is configured to: acquire the production data of the enterprise's industrial production line in real time, and acquire the access rights corresponding to the production data; acquire the access request of the initial access terminal, and acquire the port authority of the data access terminal corresponding to the initial access terminal; and extract the target production data of the corresponding category from the production data according to the access request.

[0089] The data statistics module 102 is in communication connection with the data acquisition module 101 , and the data statistics module 102 is configured to generate the corresponding target production data as visual graphic data if the port authority matches the access authority of the target production data.

[0090] The first data push module 103 is in communication connection with the data statistics module 102 , and the first data push module 103 is configured to push the target production data and the corresponding visualized graphic data to the initial access terminal.

[0091] The specific data screening module 104 is communicatively connected with the data acquisition module 101 and the first data push module 103 respectively, and the specific data screening module 104 is configured as follows: based on the push time of the target production data and the visual graphic data, retrieve the historical production data of the corresponding category of the target production data within the first preset historical time period; retrieve the customer data stored in the enterprise server, and extract the attention dimension of the corresponding category of the target production data according to the customer data; extract the attention data corresponding to the attention dimension from the target production data, and extract the historical attention data corresponding to the attention dimension from the historical production data.

[0092] The data analysis module 105 is communicatively connected with the specific data screening module 104, and the data analysis module 105 is configured as follows: generating a data trend change graph based on the focus data and historical focus data; making corresponding types of data tags for various change trends in the data trend change graph; and obtaining the first-level data annotations made by the initial access end for the target production data, historical production data, data trend change graph and data tags.

[0093] The second data push module 106 is in communication connection with the data analysis module 105 and is configured to push the data trend change graph, data tags and primary data annotations to a data access terminal with access rights equal to or higher than the initial access terminal.

[0094] When this embodiment is applied, the production data is screened and streamlined according to the access request of the access terminal to obtain the target production data corresponding to the access request. The initial access terminal that meets the authority can obtain the visual graphic data corresponding to the target production data, so that the data can be viewed intuitively. Then, based on the customer's focus dimensions, a data trend change graph is generated from the target production data and historical production data, so as to intuitively reflect the change trend of the focus dimension. It is also possible to further annotate the target production data, historical production data, data trend change graph, and data tags to improve and enrich the data, and then push the data trend change graph, data tags, and first-level data annotations to the data access terminals of the same level or higher level. These data access terminals can obtain complete, streamlined, and enriched data results, thereby providing high-quality data for the data access terminals of the same level or higher level to reflect the dynamic status of the enterprise.

[0095] Exemplary electronic devices are as follows:

[0096] Below, reference Fig.11 To describe an electronic device according to an embodiment of the present application. Fig.11 Shown is a schematic structural diagram of an electronic device provided in one embodiment of the present application.

[0097] like Fig.11 As shown, the electronic device 111 includes one or more processors 1111 and a memory 1112 .

[0098] The processor 1111 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 111 to perform desired functions.

[0099] The memory 1112 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 1111 may run the program instructions to implement the enterprise dynamic perception method based on big data and large models or other desired functions of the various embodiments of the present application described above. Various contents such as enterprise dynamic perception error parameters based on big data and large models may also be stored in the computer-readable storage medium.

[0100] In one example, the electronic device 111 may further include: an input device 1113 and an output device 1114 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0101] The input device 1113 may include, for example, a keyboard, a mouse, a joystick, a touch screen, and the like.

[0102] The output device 1114 can output various information to the outside, including the determined motion data, etc. The output device 1114 can include, for example, a display, a communication network and a remote output device connected thereto, and the like.

[0103] Of course, to simplify, Fig.11 Only some of the components related to the present application in the electronic device 111 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 111 may also include any other appropriate components.

[0104] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the enterprise dynamic perception method based on big data and big models according to various embodiments of the present application described in this specification.

[0105] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0106] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the enterprise dynamic perception method based on big data and big models according to various embodiments of the present application described in this specification.

[0107] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0108] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0109] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0110] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0111] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present invention.

[0112] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for enterprise dynamic perception based on big data and big models, characterized in that: include: Obtaining the production data of the enterprise's industrial production lines in real time, and obtaining the access rights corresponding to the production data; Obtaining an access request from an initial access terminal, and obtaining a port permission of a data access terminal corresponding to the initial access terminal; extracting target production data of a corresponding category from the production data according to the access request; If the port authority matches the access authority of the target production data, the corresponding target production data is generated as visual graphic data, and the target production data and the corresponding visual graphic data are pushed to the initial access terminal; Based on the push time of the target production data and the visual graphic data, retrieve the historical production data of the category corresponding to the target production data within a first preset historical time period; Obtaining customer data stored in an enterprise server, and extracting the focus dimensions of the category corresponding to the target production data according to the customer data; the customer data is pre-stored in the enterprise server, and the focus dimensions are directly set by multiple customers, or obtained through a questionnaire survey, or set by the enterprise according to the customer data; Extracting the concerned data corresponding to the concerned dimension from the target production data, and extracting the historical concerned data corresponding to the concerned dimension from the historical production data; Generate a data trend change graph according to the concerned data and the historical concerned data; Marking corresponding types of data for various change trends in the data trend change graph; The upward trend part is marked as Class A, the downward trend part is marked as Class B, and the stable trend part is marked as Class C; Obtaining the primary data annotations made by the initial access end on the target production data, the historical production data, the data trend change graph and the data mark; as well as Pushing the data trend change graph, the data mark and the primary data annotation to a data access terminal with access rights equal to or higher than that of the initial access terminal; The method further comprises: Summarize the historical multiple groups of visualized graphic data corresponding to the categories corresponding to the access requests; Generating a first sorting parameter by sorting the plurality of groups of visual graphic data in chronological order; and Pushing the plurality of groups of the visualized graphic data and the first sorting parameter to a data access terminal having a third preset access right; The historical multiple groups of visual graphic data corresponding to the categories corresponding to the access requests are summarized as follows: Based on the request time of the access request of the initial access terminal, a plurality of groups of the visual graphic data obtained by all the initial access terminals for accessing the corresponding category within a preset number of historical requests are summarized; The method further comprises: If a plurality of the initial access terminals issue the access request to the same category within a third preset time period, then aggregating the port data of a plurality of data access terminals corresponding to the plurality of the initial access terminals; and The port data is pushed to a data access terminal with access rights equal to or higher than that of the initial access terminal.

2. The enterprise dynamic perception method based on big data and big models according to claim 1 is characterized in that: Also includes: Obtaining secondary data annotations made by a first access terminal having a first preset access right on the data trend change graph and the data mark; as well as The secondary data annotation is pushed to a second access terminal having a second preset access right; wherein the second access terminal includes the initial access terminal, and the second preset access right is lower than or equal to the first preset access right.

3. The enterprise dynamic perception method based on big data and big models according to claim 1 is characterized in that: The historical multiple groups of visual graphic data corresponding to the categories corresponding to the access requests are summarized as follows: Based on the request time of the access request of the initial access terminal, a plurality of groups of the visual graphic data corresponding to the categories corresponding to the access requests within a second preset historical time period are summarized.

4. The enterprise dynamic perception method based on big data and big models according to claim 1 is characterized in that: Also includes: Based on the request time of the access request of the initial access end, aggregating multiple groups of the visual graphic data corresponding to multiple categories in the access request; Generating a second sorting parameter for the plurality of groups of visual graphic data in order of data size; as well as Pushing the plurality of groups of the visualized graphic data and the second sorting parameter to a data access terminal having a fourth preset access authority.

5. The enterprise dynamic perception method based on big data and big models according to claim 1 is characterized in that: Also includes: Acquire data modifications made by a third access terminal having a fifth preset access right to the target production data and the visual graphic data; as well as The target production data and the visual graphic data before and after modification are pushed to a fourth access terminal with a sixth preset access right; wherein the fourth access terminal includes the initial access terminal, and the sixth preset access right is lower than or equal to the fifth preset access right.

6. The enterprise dynamic perception method based on big data and big models according to claim 1 is characterized in that: Also includes: Importing the target production data, the historical production data, the data trend change graph, the data tags, and the primary data annotations into an AI analysis model; If the trend change in the data trend change diagram exceeds a preset range, the production data within the range corresponding to the trend change exceeding the preset range is marked as risk data; Produce risk solutions for the risk data based on the AI ​​analysis model; as well as The risk solution is pushed to a data access terminal with access rights equal to or higher than that of the initial access terminal.

7. An enterprise dynamic perception system based on big data and big models, characterized by: include: A data acquisition module is configured to: acquire production data of the enterprise's industrial production line in real time, and obtain access rights corresponding to the production data; Obtaining an access request from an initial access terminal, and obtaining a port authority of a data access terminal corresponding to the initial access terminal; extracting target production data of a corresponding category from the production data according to the access request; A data statistics module is connected to the data acquisition module in communication, and the data statistics module is configured to: if the port authority matches the access authority of the target production data, generate the corresponding target production data as visual graphic data; A first data push module, which is in communication connection with the data statistics module, and is configured to: push the target production data and the corresponding visualized graphic data to the initial access terminal; A specific data screening module is respectively connected to the data acquisition module and the first data push module, and the specific data screening module is configured to: based on the push time of the target production data and the visual graphic data, retrieve the historical production data of the category corresponding to the target production data within a first preset historical time period; Acquire customer data stored in the enterprise server, and extract the concern dimension of the category corresponding to the target production data according to the customer data; extract the concern data corresponding to the concern dimension from the target production data, and extract the historical concern data corresponding to the concern dimension from the historical production data; the customer data is pre-stored in the enterprise server, and the concern dimension is directly set by multiple customers, or obtained through questionnaire survey, or set by the enterprise according to the customer data; A data analysis module is connected to the specific data screening module in communication, and the data analysis module is configured to: generate a data trend change graph according to the concerned data and the historical concerned data; and mark corresponding types of data for various change trends in the data trend change graph; The upward trend part is marked as Class A, the downward trend part is marked as Class B, and the stable trend part is marked as Class C; Obtaining the primary data annotations made by the initial access end for the target production data, the historical production data, the data trend change graph, and the data mark; summarizing the historical multiple groups of the visual graphic data corresponding to the category corresponding to the access request; Generating a first sorting parameter for the plurality of groups of visual graphic data in chronological order; The aggregating the historical multiple groups of visual graphic data corresponding to the category corresponding to the access request includes: based on the request time of the access request of the initial access terminal, aggregating the multiple groups of visual graphic data obtained by all the initial access terminals requesting access to the corresponding category within a preset number of historical requests; if multiple initial access terminals send the access request to the same category within a third preset time period, aggregating the port data of multiple data access terminals corresponding to the multiple initial access terminals; and The second data push module is communicatively connected to the data analysis module, and the second data push module is configured to: push the data trend change chart, the data mark and the first-level data annotation to the data access terminal with access rights equal to or higher than the initial access terminal; push multiple groups of the visual graphic data and the first sorting parameter to the data access terminal with a third preset access right; push the port data to the data access terminal with access rights equal to or higher than the initial access terminal.

Images