Work order processing method and device based on artificial intelligence technology

Abstract

The invention discloses a work order processing method and device based on an artificial intelligence technology, and the method comprises the steps: receiving unstructured instruction information, extracting semantic information in the instruction information through a semantic analysis model, and building a current work order; calling a target process template from a pre-established template library according to the semantic information, and determining an execution process of the current work order according to the current work order and the target process template; calling a target scheme from a pre-established scheme library according to the current work order; executing the current work order according to the execution process and the target scheme; semantic analysis is performed through an artificial intelligence technology, so that processing of unstructured instruction information is realized; a dynamic process template is established through a process engine, and the dynamic template comprises dynamic nodes, so that custom adjustment of an execution process is realized; by analyzing the work order and selecting the target scheme from the scheme library, assistance of the execution process is realized.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly to a work order processing method and device based on artificial intelligence technology. Background Art

[0002] In the existing property OA (Office Automation) office system, there are various types of work orders, and different corresponding programs are required for processing. For example, various work orders such as approval, repair, inspection, contract management, etc., have different processing programs, and in some cases, specific solutions are involved, involving multi-role collaboration and multi-link transfer. It can be seen that this system is a processing system with complex functions.

[0003] In the prior art, the system functions often fail to meet the usage requirements. This is mainly manifested in the following aspects. First, the process is rigid. Traditional office systems rely on fixed process templates and cannot be adjusted in real time according to business dynamics. In many cases, the established templates are difficult to meet diverse work requirements. Second, the degree of intelligence is insufficient, and unstructured data cannot be processed. In actual work, the sources of many work orders are often unstructured data, such as temporary content like text and voice. These unstructured data cannot be directly used as information input for the system. Third, the system functions are limited. Conventional office systems often only provide process functions, that is, operations such as creating, approving, assigning, and supervising work orders can be performed, but they cannot assist in execution, nor can they provide specific execution plans or operation suggestions. Summary of the Invention

[0004] The present invention provides a work order processing method and device based on artificial intelligence technology to achieve more efficient and multi-functional work order processing.

[0005] In a first aspect, the present invention provides a work order processing method based on artificial intelligence technology, including:

[0006] Receiving unstructured instruction information, extracting semantic information from the instruction information by using a semantic analysis model, and creating a current work order;

[0007] According to the semantic information, calling a target process template from a pre-established template library, and determining the execution process of the current work order according to the current work order and the target process template;

[0008] Calling a target solution from a pre-established solution library according to the current work order;

[0009] Executing the current work order according to the execution process and the target solution.

[0010] Preferably, it further includes:

[0011] Establish a dynamic process template based on a process engine and store the dynamic process template in a template library;

[0012] The dynamic process template includes dynamic nodes.

[0013] Preferably, it further includes:

[0014] Monitor the execution status of parallel work orders and determine an analysis report according to the execution status;

[0015] Adjust the dynamic process template in the template library by using the analysis report.

[0016] Preferably, the monitoring the execution status of parallel work orders and determining an analysis report according to the execution status includes:

[0017] Use a distributed database and business intelligence tools to determine the analysis report.

[0018] Preferably, the adjusting the dynamic process template in the template library by using the analysis report includes:

[0019] Use the analysis report to adjust the process resource allocation ratio in the dynamic process template.

[0020] Preferably, it further includes:

[0021] Analyze historical work orders by using a work order analysis model, determine a reference solution, and store the reference solution in a solution library.

[0022] Preferably, the calling a target solution from a pre-established solution library according to the current work order includes:

[0023] Perform knowledge graph matching on the current work order to determine work order characteristics;

[0024] Call a target solution from the solution library according to the work order characteristics.

[0025] In a second aspect, the present invention provides a work order processing device based on artificial intelligence technology, including:

[0026] A work order generation module, configured to receive unstructured instruction information, extract semantic information in the instruction information by using a semantic analysis model, and establish a current work order;

[0027] A process determination module, configured to call a target process template from a pre-established template library according to the semantic information, and determine an execution process of the current work order according to the current work order and the target process template;

[0028] A solution determination module, configured to call a target solution from a pre-established solution library according to the current work order;

[0029] An execution module, configured to execute the current work order according to the execution process and the target solution.

[0030] In a third aspect, the present invention provides a readable medium, including execution instructions. When a processor of an electronic device executes the execution instructions, the electronic device executes the method described in any one of the first aspects.

[0031] In a fourth aspect, the present invention provides an electronic device, including a processor and a memory storing execution instructions. When the processor executes the execution instructions stored in the memory, the processor executes the method described in any one of the first aspects.

[0032] The present invention provides a work order processing method and apparatus based on artificial intelligence technology. Through semantic analysis by artificial intelligence technology, the processing of unstructured instruction information is realized; a dynamic process template is established through a process engine, and the dynamic template includes dynamic nodes, thereby realizing the custom adjustment of the execution process; by analyzing the work order and selecting a target solution from the solution library, the assistance for the execution process is realized; in this embodiment, the work order processing is realized by using a more efficient, automated, and highly adaptable office system.

[0033] The further effects of the above non-conventional preferred methods will be described in combination with specific embodiments below. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the existing technical solutions, the following will briefly introduce the drawings required for the description of the embodiments or the existing technical solutions. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0035] Figure 1 It is a schematic flowchart of a work order processing method based on artificial intelligence technology provided by an embodiment of the present invention;

[0036] Figure 2 It is a schematic flowchart of another work order processing method based on artificial intelligence technology provided by an embodiment of the present invention;

[0037] Figure 3 It is a schematic structural diagram of a work order processing apparatus based on artificial intelligence technology provided by an embodiment of the present invention;

[0038] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments and the corresponding drawings. Apparently, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0040] In the existing property OA (Office Automation) office system, there are various types of work orders, and different corresponding programs are required for processing. For example, various work orders such as approval, repair, inspection, contract management, etc., the processing programs are all different, and in some cases, specific solutions are involved, which involve multi-role collaboration and multi-link transfer. It can be seen that this system is a processing system with complex functions.

[0041] In the prior art, the system functions often fail to meet the usage requirements. This is mainly manifested in the following aspects. First, the process is rigid. Traditional office systems rely on fixed process templates and cannot be adjusted in real time according to business dynamics. In many cases, the established templates are difficult to meet the diverse work requirements. Second, the degree of intelligence is insufficient and unstructured data cannot be processed. In actual work, the sources of many work orders are often unregulated (i.e., unstructured) data, such as temporary content like text and voice. These unstructured data cannot be directly used as information input for the system. Third, the system functions are limited. Conventional office systems often only provide process functions, that is, operations such as creating, approving, assigning, and supervising work orders can be performed, but they cannot assist in execution, nor can they provide specific execution plans or operation suggestions.

[0042] That is to say, there is a lack of a more intelligent office system in the prior art. It can flexibly adjust the process template according to the actual business situation, adaptively change the operation process, and can also assist in the operation to a certain extent, providing an execution plan or operation suggestion.

[0043] In view of this, the present invention provides a work order processing method based on artificial intelligence technology. See Figure 1 As shown, it is a specific embodiment of the work order processing method based on artificial intelligence technology provided by the present invention.

[0044] In this embodiment, in order to achieve flexible adjustment of the operation process, a template library can be established in advance. Specifically, a dynamic process template can be established based on a process engine and stored in the template library; the dynamic process template includes dynamic nodes.

[0045] The process engine can adopt the Flowable engine to design a scalable process template. That is to say, the process template can include dynamic nodes, which can be added, deleted, and customized. Through the management of dynamic nodes, the flexible adjustment of the process is realized. Specifically, artificial intelligence technology can be used to analyze historical work orders, judge the execution efficiency of various execution processes and operation steps in the process, so as to screen and sort, and automatically determine the process templates for various types of businesses. Various process templates are stored in the template library.

[0046] In order to propose an execution plan or operation suggestions for the work order execution process, a solution library will also be established in this embodiment. Specifically, the work order analysis model can be used to analyze historical work orders, determine reference solutions, and store the reference solutions in the solution library.

[0047] The formulation of reference solutions also depends on the analysis of historical work orders by artificial intelligence technology to determine what execution solutions are actually adopted for various historical work orders, and to analyze the specific effects of the execution solutions, so as to obtain reference solutions for various work orders. The reference solutions are stored in the solution library. The above analysis based on artificial intelligence technology can be based on large language models such as FastGPT.

[0048] The method includes:

[0049] Step 101, receive unstructured instruction information, use a semantic analysis model to extract the semantic information in the instruction information, and create a current work order.

[0050] The so-called unstructured instruction information can include temporary information such as voice information, text information, and picture information, which is not provided in the structured format required by the office system. For example, when a user takes a photo of a faulty device and uploads it, the actual intention is to create a maintenance work order. Or the user sends a voice message "Repair the lighting in the corridor", and the intention is also to create a maintenance work order. In the prior art, applying for a work order must be filled in to the system according to a fixed format, and unstructured information input cannot be processed.

[0051] However, in this embodiment, the office system can process such unstructured instruction information. Specifically, a semantic analysis model based on artificial intelligence technology can be used to extract the semantic information in the instruction information. The so-called voice analysis model can be established based on current large language models such as FastGPT. Such models can analyze unstructured information such as text, pictures, and voices, recognize semantics, and extract key information therefrom. This key information is equivalent to the structured information received by the traditional office system. Thus, the current work order can be created.

[0052] Step 102: According to the semantic information, call the target process template from a pre-established template library, and determine the execution process of the current work order according to the current work order and the target process template.

[0053] After the current work order is established, it is necessary to process the current work order, that is, it is necessary to determine the execution process of the current work order. Specifically, a specific dynamic process template can be called from the above template library, that is, the target process template for the current work order. The target process template can also be selected in combination with the above semantic information. Because the semantic information contains information such as the actual content, type and requirements of the current work order. Therefore, a dynamic process template that is compatible with it is selected as the target process template.

[0054] Next, based on the current work order and the target process template, the execution process of the current work order can be determined. In other words, the specific information of the current work order is brought into the target to determine the actual execution process. For example, if the current work order is a maintenance work order, it will involve maintenance targets, locations, priorities, and various other requirements. The target process template includes specific execution steps, approval, acceptance, allocation and scheduling, supervision, and other links. The combination of the two is the actual execution process.

[0055] Step 103: According to the current work order, call the target solution from a pre-established solution library.

[0056] In addition, in this embodiment, further execution plans or operational suggestions can be provided for the execution process. That is to say, appropriate assistance can be provided during the execution process. The execution plan comes from the reference plan in the above-mentioned solution library. Specifically, the current work order can be matched with a knowledge graph to determine the work order characteristics, that is, to determine the specific situation and requirements of the current work order during execution. Then, based on the work order characteristics, an adapted reference plan is called from the solution library as the target plan. The target plan may include operational suggestions during the execution process, as well as specific information such as the priority of work order assignment, and the recommended personnel for assignment.

[0057] Step 104: Execute the current work order according to the execution process and the target solution.

[0058] After the execution process and target solution of the current work order are determined, the current work order can be executed. At this point, the processing process for the work order in this embodiment ends.

[0059] As can be seen from the above technical solutions, the beneficial effects of this embodiment are as follows: Through artificial intelligence technology for semantic analysis, the processing of unstructured instruction information is realized; by establishing a dynamic process template through a process engine, and the dynamic template includes dynamic nodes, thus realizing the custom adjustment of the execution process; by analyzing the work order and selecting the target solution from the solution library, the assistance for the execution process is realized; in this embodiment, the work order processing is realized by using a more efficient, automated, and highly adaptable office system.

[0060] Figure 1 The shown is only the basic embodiment of the method of the present invention. Based on it, with certain optimizations and expansions, other preferred embodiments of the method can also be obtained.

[0061] As Figure 2 shown, it is another specific embodiment of the work order processing method based on artificial intelligence technology of the present invention. This embodiment is further described on the basis of the foregoing embodiment. In this embodiment, the method includes the following steps:

[0062] Step 201, receive unstructured instruction information, use a semantic analysis model to extract the semantic information in the instruction information, and establish the current work order.

[0063] The so-called unstructured instruction information may include temporary information such as voice information, text information, and picture information. Such information is not provided in the structured format required by the office system. For example, when a user takes a photo of a faulty device and uploads it, the actual intention is to create a maintenance work order. Or when a user sends a voice message "Repair the lighting in the corridor", the intention is also to create a maintenance work order. In the prior art, applying to establish a work order must be filled in to the system according to a fixed format, and unstructured information input cannot be processed.

[0064] However, in this embodiment, the office system can process such unstructured instruction information. Specifically, a semantic analysis model based on artificial intelligence technology can be used to extract the semantic information in the instruction information. The so-called voice analysis model can be established based on current large language models such as FastGPT. Such models can analyze unstructured information such as text, pictures, and voices, identify semantics, and thus extract the key information. This key information is equivalent to the structured information received by the traditional office system. Thus, the current work order can be established.

[0065] Step 202, according to the semantic information, call the target process template from the pre-established template library, and determine the execution process of the current work order according to the current work order and the target process template.

[0066] After creating the current work order, it is necessary to process the current work order, that is, to determine the execution process of the current work order. Specifically, a specific dynamic process template can be called from the above-mentioned template library, that is, the target process template for the current work order. The target process template can also be selected in combination with the above semantic information. Because the semantic information contains information such as the actual content, type, and requirements of the current work order. Thus, a dynamic process template that matches it is selected as the target process template.

[0067] Next, according to the current work order and the target process template, the execution process of the current work order can be determined. That is to say, by bringing the specific information of the current work order into the target, the actual execution process can be determined. For example, if the current work order is a maintenance work order, it will involve maintenance objectives, locations, priorities, and various other requirements. The target process template includes specific execution steps, approvals, inspections, assignment scheduling, supervision, and other links. Combining the two is the actual execution process.

[0068] Step 203: Call the target solution from the pre-established solution library according to the current work order.

[0069] In addition, in this embodiment, an execution plan or operation suggestions can be further provided for the execution process. That is to say, appropriate assistance can be provided during the execution process. The execution plan comes from the reference solutions in the above solution library. Specifically, the current work order can be matched with the knowledge graph to determine the work order characteristics, that is, to determine the specific situation and requirements of the current work order during execution. Then, according to the work order characteristics, an adapted reference solution is called from the solution library as the target solution. The target solution can include operation suggestions during the execution process, as well as specific information such as the priority of work order assignment and the recommended assignees.

[0070] Step 204: Monitor the execution status of parallel work orders and determine the analysis report according to the execution status.

[0071] In the office system, in addition to the current work order, other work orders also need to be executed synchronously. Or, before executing the current work order, the system will also execute other similar work orders. All these other work orders are processed in a similar way, and these work orders are collectively referred to as parallel work orders. During the execution, the system will also monitor the execution status of the parallel work orders and make adaptive adjustments according to the monitoring results, thereby realizing the adaptive improvement and targeted adjustment of the execution process and improving the execution efficiency.

[0072] As previously pointed out, in the prior art, the process is rigid, relying on fixed process templates and unable to adjust in real time according to business dynamics. In many cases, the established templates are difficult to meet the diverse work requirements. The preferred solution in this embodiment is precisely to solve this problem.

[0073] Specifically, the execution status of parallel work orders can be monitored. For example, by using a distributed database (such as a MongoDB database) and a business intelligence tool (Business Intelligence, abbreviated as BI, such as Power BI), an analysis report can be determined. The analysis report can reflect the execution efficiency of parallel work orders. It can be considered that when the efficiency is relatively high, it indicates that the execution process of the parallel work order is relatively reasonable. On the contrary, when the efficiency is relatively low, it can be considered that there are problems such as process rigidity and incompatibility with the current business.

[0074] Step 205: Use the analysis report to adjust the dynamic process template in the template library.

[0075] When the analysis report shows low efficiency, the dynamic process template in the template library can be adjusted. As mentioned above, the process template can include dynamic nodes, which can be added, deleted, and customized and edited. By managing the dynamic nodes, flexible adjustment of the process is achieved. In this embodiment, the so-called adjustment of the dynamic process template specifically means editing the dynamic nodes to optimize the process designed in the template.

[0076] In terms of the adjustment strategy, specifically, the analysis report can be used to adjust the process resource allocation ratio in the dynamic process template, and the process execution efficiency can be improved by optimizing the resource allocation.

[0077] As can be seen from the above, in this embodiment Figure 1 Based on the shown embodiment, a further effect is that the process template is dynamically adjusted according to the work order execution efficiency, solving the problems of process rigidity and difficulty in meeting diverse work requirements in the prior art.

[0078] It should also be noted that from a logical level, the system in this embodiment can be divided into three specific logical modules, namely an intelligent process definition module, a multi-modal data processing module, and a collaborative execution and optimization module.

[0079] The intelligent process definition module is mainly used to construct a template library and a solution library. Its function is to design an extensible dynamic process template based on a process engine (such as Flowable), support dynamic addition / deletion of nodes, and thus establish a template library. At the same time, it integrates the FastGPT model to automatically parse the historical work order text, form a reference solution, and establish a solution library.

[0080] The multi-modal data processing module can support the input of unstructured instruction information such as voice, text, and images, and perform semantic analysis and intent recognition through FastGPT. It can also call a knowledge graph or a historical work order library to select a target solution from the solution library.

[0081] The collaborative execution and optimization module can predict bottleneck nodes and dynamically adjust resource allocation through FastGPT based on real-time monitoring of the process status. Furthermore, it uses a distributed database (such as MongoDB) and combines BI tools (such as Power BI) to generate a process efficiency analysis report, providing a basis for the dynamic adjustment of the process.

[0082] As Figure 3 shown, this is a specific embodiment of the work order processing device based on artificial intelligence technology described in the present invention. The device in this embodiment is an entity device for executing Figures 1 - 2 the method described above. Its technical solution is essentially the same as that of the above embodiment, and the corresponding descriptions in the above embodiment also apply to this embodiment. The device described in this embodiment includes:

[0083] A work order generation module 301, configured to receive unstructured instruction information, extract semantic information from the instruction information using a semantic analysis model, and establish a current work order.

[0084] A process determination module 302, configured to call a target process template from a pre-established template library according to the semantic information, and determine the execution process of the current work order according to the current work order and the target process template.

[0085] A solution determination module 303, configured to call a target solution from a pre-established solution library according to the current work order.

[0086] An execution module 304, configured to execute the current work order according to the execution process and the target solution.

[0087] In addition, based on the embodiment shown in Figure 3 , preferably, it further includes:

[0088] A template library establishment module 305, configured to establish a dynamic process template based on a process engine and store the dynamic process template in the template library; the dynamic process template includes dynamic nodes.

[0089] The template library establishment module 305 includes:

[0090] An analysis unit 351, configured to monitor the execution status of parallel work orders, determine an analysis report according to the execution status; and adjust the dynamic process template in the template library using the analysis report.

[0091] The analysis unit 351 includes:

[0092] A report sub-unit 3511, configured to determine the analysis report using a distributed database and a business intelligence tool.

[0093] An adjustment subunit 3522, configured to adjust the process resource allocation ratio in the dynamic process template by using the analysis report form.

[0094] A solution library establishment module 306, configured to analyze historical work orders by using a work order analysis model, determine a reference solution, and store the reference solution in the solution library.

[0095] The solution determination module 303 includes

[0096] A knowledge graph unit 331, configured to perform knowledge graph matching on the current work order to determine work order features.

[0097] A solution retrieval unit 332, configured to retrieve a target solution from the solution library according to the work order features.

[0098] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0099] The processor, network interface, and memory can be interconnected through an internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 4 only a bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0100] The memory is used to store execution instructions. Specifically, the execution instructions are computer programs that can be executed. The memory can include a memory and a non-volatile memory, and provide the execution instructions and data to the processor.

[0101] In a possible implementation, the processor reads the corresponding execution instructions from the non-volatile memory into the memory and then runs them, or obtains the corresponding execution instructions from other devices, so as to form a work order processing device based on artificial intelligence technology at the logical level. The processor executes the execution instructions stored in the memory to implement the work order processing method based on artificial intelligence technology provided in any embodiment of the present invention through the executed execution instructions.

[0102] As described above in the present invention Figure 3 The method executed by the work order processing device based on artificial intelligence technology provided in the embodiments shown above can be applied to the processor or implemented by the processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor or by instructions in software form. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0103] The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being completed by the hardware decoding processor, or completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0104] The embodiments of the present invention also propose a readable medium. When the execution instructions stored in the readable storage medium are executed by the processor of the electronic device, the electronic device can be enabled to execute the work order processing method based on artificial intelligence technology provided in any embodiment of the present invention, and is specifically used to execute as Figure 1 or Figure 2 the method shown.

[0105] The electronic device described in each of the foregoing embodiments may be a computer.

[0106] Those skilled in the art should understand that the embodiments of the present invention may be provided as a method or a computer program product. Therefore, the present invention may be implemented in the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware.

[0107] Each embodiment of the present invention is described in a progressive manner. For the same or similar parts among the embodiments, reference may be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts may refer to the description of the method embodiments.

[0108] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements not only includes those elements but also other elements not explicitly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, commodity or device comprising the element.

[0109] The above description is only for the embodiments of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and changes can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A work order processing method based on artificial intelligence technology, characterized in that, including: Receiving unstructured instruction information, extracting semantic information in the instruction information by using a semantic analysis model, and creating a current work order; According to the semantic information, calling a target process template from a pre-established template library, and determining an execution process of the current work order according to the current work order and the target process template; According to the current work order, calling a target solution from a pre-established solution library; Executing the current work order according to the execution process and the target solution.

2. The method according to claim 1, wherein It further includes: Establishing a dynamic process template based on a process engine, and storing the dynamic process template into the template library; The dynamic process template includes dynamic nodes.

3. The method according to claim 2, characterized in that It further includes: Monitoring the execution status of parallel work orders, and determining an analysis report according to the execution status; Adjusting the dynamic process template in the template library by using the analysis report.

4. The method according to claim 3, wherein The monitoring the execution status of parallel work orders and determining an analysis report according to the execution status includes: Determining the analysis report by using a distributed database and a business intelligence tool.

5. The method according to claim 3, characterized in that The adjusting the dynamic process template in the template library by using the analysis report includes: Adjusting the process resource allocation ratio in the dynamic process template by using the analysis report.

6. The method according to claim 1, characterized in that, It further includes: Analyzing historical work orders by using a work order analysis model, determining a reference solution, and storing the reference solution into the solution library.

7. The method according to claim 1, characterized in that, The calling a target solution from a pre-established solution library according to the current work order includes: Performing knowledge graph matching on the current work order to determine work order features; Calling a target solution from the solution library according to the work order features.

8. A work order processing device based on artificial intelligence technology, characterized in that, including: A work order generation module, configured to receive unstructured instruction information, extract semantic information in the instruction information by using a semantic analysis model, and create a current work order; A process determination module, configured to call a target process template from a pre-established template library according to the semantic information, and determine an execution process of the current work order according to the current work order and the target process template; A solution determination module, configured to call a target solution from a pre-established solution library according to the current work order; An execution module, configured to execute the current work order according to the execution process and the target solution.

9. A computer-readable storage medium storing a computer program for executing the work order processing method based on artificial intelligence technology according to any one of claims 1 to 7 above.

10. An electronic device, the electronic device includes: A processor; A memory for storing executable instructions of the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the work order processing method based on artificial intelligence technology according to any one of claims 1 to 7 above.

Images