Power business document processing method and device, equipment, medium and program product

Abstract

The embodiment of the invention provides a power business document processing method and device, equipment, a computer storage medium and a computer program product. The method comprises the following steps: acquiring an unstructured document corresponding to an electric power business hall service system; identifying basic content blocks contained in the unstructured document based on a preset document structure rule; based on the complexity of each basic content block, determining a target server to which each basic content block is allocated from a server cluster; extracting key service information in the corresponding basic content block through the target server; and fusing the key business information into a power business knowledge graph corresponding to the power business hall service system to obtain a power business document database. According to the method, the structured processing efficiency of the power business document and the management efficiency of the power business information in the power business hall are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of smart grid technology, and in particular, to a method, device, equipment, computer storage medium, and computer program product for processing power business documents. Background Art

[0002] In the context of electronic office, data storage and processing are becoming more and more important. For example, there are a large number of unstructured documents in the power business hall. Converting these unstructured documents into structured data formats can achieve more efficient storage, retrieval and analysis. However, the traditional document structuring method cannot meet the high requirements of the power system for intelligence and automation, resulting in low efficiency in the structured processing of power business documents. Summary of the invention

[0003] Based on this, the embodiments of the present application provide a method, device, equipment, computer storage medium and computer program product for processing electric power business documents, which can improve the efficiency of structured processing of electric power business documents.

[0004] In a first aspect, an embodiment of the present application provides a method for processing electric power business documents, including:

[0005] Obtain the unstructured documents corresponding to the power business hall service system;

[0006] Identifying basic content blocks contained in the unstructured document based on preset document structure rules;

[0007] Based on the complexity of each basic content block, determine the target server to which each basic content block is assigned from the server cluster;

[0008] Extracting key business information in the corresponding basic content block through the target server;

[0009] The key business information is integrated into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

[0010] In a second aspect, an embodiment of the present application provides a power business document processing device, including:

[0011] The document acquisition module is used to obtain the unstructured documents corresponding to the power business hall service system;

[0012] A structure identification module, used for identifying basic content blocks contained in the unstructured document based on preset document structure rules;

[0013] A resource allocation module, used to determine a target server to which each basic content block is to be allocated from a server cluster based on the complexity of each basic content block;

[0014] An information extraction module, used to extract key business information in the corresponding basic content block through the target server;

[0015] The information storage module is used to integrate the key business information into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the power business document processing method provided in the first aspect of the embodiment of the present application are implemented.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the power business document processing method provided in the first aspect of the embodiment of the present application are implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the power business document processing method provided in the first aspect of the embodiment of the present application. The technical solution provided by the embodiment of the present application identifies the basic content blocks contained in the unstructured documents in the power business hall service system through a preset document structure rule, and determines the target server to which each basic content block is assigned from the server cluster based on the complexity of each basic content block, and extracts the key business information in the corresponding basic content block through the assigned target server, that is, the solution can dynamically adjust the service resources in combination with the complexity of the basic content block, so that the resource allocation results corresponding to each basic content block match the complexity of each basic content block, for example, more server resources can be allocated to basic content blocks with higher complexity, ensuring that complex basic content blocks can be accurately parsed, thereby improving the efficiency of structured processing of power business documents; in addition, the structured results of power business documents are stored in the form of knowledge graphs, so that the subsequent retrieval process of power business information is more efficient and accurate, and the management efficiency of power business information in power business halls is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a flow chart of a method for processing electric power business documents provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a structure of a power business document processing device provided in an embodiment of the present application;

[0021] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the technical solutions in the embodiments of the present application are further described in detail through the following embodiments and in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all structures.

[0023] The embodiments of the present application can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor devices, and distributed computing environments including any of the above devices or equipment.

[0024] Embodiments of the present application may be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Embodiments of the present application may also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0025] Figure 1 A flow chart of a method for processing electric power business documents provided in an embodiment of the present application. Figure 1 As shown, the method may include:

[0026] S101. Obtain unstructured documents corresponding to the power business hall service system.

[0027] Among them, the power business hall contains a large number of unstructured documents, such as customer application forms, service agreements, power business licenses, contracts, bills, customer service records, and service guides. In the specific implementation, the power business hall service system can be accessed through the application programming interface (API), and various unstructured documents in the power business hall service system can be obtained through the API interface. The above unstructured documents can be in any document format, such as PDF documents or Word documents.

[0028] S102: Identify basic content blocks contained in the unstructured document based on preset document structure rules.

[0029] Among them, the basic content blocks can be considered as the components of the unstructured document. Taking the power business analysis report as an example, the report summary, introduction, specific implementation methods, conclusion and discussion are all the basic content blocks of the power business analysis report.

[0030] By collecting sample unstructured documents involved in the power business hall scenario and analyzing the structure of the collected sample unstructured documents, document structure rules are defined, and the document structure rules are used to identify basic content blocks contained in subsequent new unstructured documents. Optionally, the above document structure rules may include at least one of the following: keyword set, keyword position feature, specific sentence feature, paragraph structure feature, result keyword, chart text feature, discussion keyword and paragraph position feature.

[0031] Specifically, the keyword set refers to a vocabulary set for specific service types, terms or customer information in the power business office document. For example, the keyword set may be {"electricity fee", "contract number", "service application", "billing method"}.

[0032] The keyword position feature refers to the specific position of the keyword or important information field in the power business hall document. For example, the keyword position feature can be {page number: "1", table: "customer information", column: "contact information"}.

[0033] Specific sentence features refer to the sentence patterns or sentence structures commonly used in power business office documents. For example, the sentence structure of service terms or notices, such as the specific sentence features can be "Dear customer, your..." or "Thank you for choosing our service, please check...".

[0034] The paragraph structure feature refers to the formatting structure of the power business office document, such as tables, clause lists, notes, etc. Exemplarily, the paragraph structure feature may be {table title: "Bill details", list item: "Payment steps"}.

[0035] Result keywords refer to words used in the power business office document to identify service results or bill status, such as payment confirmation, service status, etc. Exemplarily, the result keywords may be {"paid", "service activated", "bill amount"}.

[0036] The chart text feature refers to the descriptive text near the chart in the power business office document. Taking the power consumption curve in the bill as an example, the chart text feature can be {the first sentence includes "power consumption statistics are as follows", and the second sentence contains "unit: kilowatt-hour"}.

[0037] Discussion keywords refer to words used in the power business office document to identify discussions or solutions. For example, discussion keywords may be {"solution", "customer feedback", "service improvement"}.

[0038] The paragraph position feature refers to the position information of a specific paragraph in the power business hall document, for example, the terms of service are always at the end of the document. For example, the paragraph position feature can be {at the end of the document: "yes", number of pages from the end of the document: "1"}.

[0039] For different unstructured documents, the above document structure rules can be combined, and the combined document structure rules can be used to identify which basic content blocks are contained in the unstructured documents. Continuing with the example of the power business analysis report, the above document structure rules can be combined to identify the basic content blocks in the power business analysis report. For example, the report summary recognition rule "{keyword set, keyword position feature}" is used to identify the report summary part, the introduction recognition rule "{specific sentence features, keyword position features}" is used to identify the introduction part, the method recognition rule "{method keywords, paragraph structure features}" is used to identify the specific implementation method part, the result recognition rule "{result keywords, chart text features}" is used to identify the conclusion part, and the discussion recognition rule "{discussion keywords, paragraph position features}" is used to identify the discussion part.

[0040] S103 . Determine, based on the complexity of each basic content block, a target server to which each basic content block is assigned from a server cluster.

[0041] After identifying each basic content block, for each basic content block, the complexity of the basic content block can be determined based on the number of paragraphs, lists, tables and graphics included in the basic content block. If the number of paragraphs, lists, tables and graphics included in the basic content block is more, the complexity of the basic content block is higher, and conversely, if the number of paragraphs, lists, tables and graphics included in the basic content block is less, the complexity of the basic content block is lower.

[0042] The resource requirement of each basic content block is determined based on its complexity. Based on the resource requirement of each basic content block and the available resources of each server in the server cluster, a resource scheduling algorithm is used to dynamically allocate computing resources to obtain the target server corresponding to each basic content block.

[0043] Exemplarily, more service resources can be allocated to basic content blocks with higher complexity (such as using idle servers to perform text recognition on the basic content blocks with higher complexity) to ensure that the complex basic content blocks can be accurately parsed; and fewer service resources can be allocated to basic content blocks with lower complexity to avoid wasting service resources.

[0044] S104: Extract key business information from the corresponding basic content block through the target server.

[0045] Among them, key business information can be important content extracted from irregularly formatted and unstructured text. This information includes but is not limited to entity names, dates, values, key events, and important terms. The purpose of extracting this key business information is to convert the originally disorganized text into structured data.

[0046] After obtaining the target server to which each basic content block is assigned, the target server is used to extract the key business information in the corresponding basic content block. In one example, the target server may extract the key business information in the corresponding basic content block through a text recognition algorithm, for example, the text recognition algorithm may be optical character recognition (OCR) or other types of text recognition algorithms, which are not limited in this embodiment.

[0047] S105. Integrate the key business information into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

[0048] Among them, the power business knowledge graph can be a tool based on knowledge graph technology to systematically represent and organize knowledge in the power business hall scenario. It graphically displays and associates the equipment, customer information, business information and other elements involved in the power business hall business and their interrelationships in the form of nodes and edges.

[0049] Obtain key business information from unstructured documents to make them conform to the structure and format requirements of the power business knowledge graph, integrate these key business information into the power business knowledge graph, build or update the power business knowledge graph by defining and adding corresponding nodes and edges to store key information related to the power business hall business, and design an efficient indexing and retrieval mechanism. Finally, develop an extraction and retrieval module that can quickly query and provide information related to the power business hall business.

[0050] The electric power business document processing method provided in the embodiment of the present application identifies the basic content blocks contained in the unstructured documents in the electric power business hall service system through preset document structure rules, and determines the target server to which each basic content block is assigned from the server cluster based on the complexity of each basic content block, and extracts the key business information in the corresponding basic content block through the assigned target server, that is, the scheme can dynamically adjust the service resources in combination with the complexity of the basic content blocks, so that the resource allocation results corresponding to each basic content block match the complexity of each basic content block. For example, more server resources can be allocated to basic content blocks with higher complexity, ensuring that complex basic content blocks can be accurately parsed, thereby improving the structured processing efficiency of electric power business documents; in addition, the structured results of the electric power business documents are stored in the form of a knowledge graph, so that the subsequent retrieval process of electric power business information is more efficient and accurate, thereby improving the management efficiency of electric power business information in the electric power business hall.

[0051] In one embodiment, optionally, based on the complexity of each basic content block, the process of determining from a server cluster the target server to which each basic content block is assigned may include: constructing a target optimization function with the goals of maximizing the total processing capacity of the server cluster for all basic content blocks, minimizing the total processing cost, and minimizing the average response time; wherein the total processing capacity and the average response time are related to the complexity of each basic content block; setting resource constraints, and based on the resource constraints, using an optimization algorithm to solve the target optimization function to obtain the target server to which each basic content block is assigned when the target optimization function is maximized.

[0052] Optionally, the objective optimization function O(s) is:

[0053] O(s)=w1*(P_max / P_total(s))-w2*h(s)-w3*(C_total(s) / C_min);

[0054] P_total(s)=∑(∑P[i][j]*A[i][j]);

[0055] C_total(s)=∑(∑Cost[i][j]*A[i][j]);

[0056] h(s)=(1 / P_total(s))*∑(A[i][j] / (Server[j]-Load[j]));

[0057] Wherein, P_max is the maximum value of the total processing capacity, P_total(s) represents the total processing capacity, h(s) represents the average response time, C_total(s) represents the total processing cost, C_min represents the minimum value of the total processing cost, w1 represents the weight coefficient corresponding to the total processing capacity, w2 represents the weight coefficient corresponding to the average response time, w3 represents the weight coefficient corresponding to the total processing cost, A[i][j] represents whether the basic content block i is assigned to the server j, if the task i is assigned to the server j, then A[i][j] = 1, otherwise, A[i][j] = 0, Cost[i][j] represents the unit cost (such as CPU, memory and storage cost) of the basic content block i when it runs on the server j, P[i][j] represents the expected processing capacity of the server j for the basic content block i, Server[j] represents the total resources of the server j, and Load[j] represents the current load of the server j.

[0058] The above w1, w2 and w3 represent the importance of total processing capacity, average response time and total processing cost in the overall optimization goal. s represents the server resource allocation scheme (such as which server each basic content block is allocated to and the allocated service resources).

[0059] Server[j]-Load[j] indicates the amount of available resources of server j. If the amount of available resources is large, the response time for the basic content block may be shorter, and if the amount of available resources is small, the response time may be longer.

[0060] A[i][j] / (Server[j]-Load[j]) represents the response time factor of basic content block i on server j.

[0061] ∑(A[i][j] / (Server[j]-Load[j])) represents the sum of the response time factors of each basic content block on the assigned server, that is, the total response time factor.

[0062] 1 / P_total(s) is the inverse of the total processing power. This factor is used to adjust the total response time factor to reflect the system's processing power. If the system's total processing power is high, the average response time may be shorter; if the system's total processing power is low, the average response time may be longer.

[0063] h( s ) represents the average response time of the system. The average response time of the system is obtained by multiplying the total response time factor by the inverse of the total processing capacity.

[0064] Optionally, the resource constraint condition includes at least one of the following:

[0065] Resource non-negative constraints, CPU constraints, memory constraints, storage constraints, and network constraints.

[0066] Exemplarily, the resource constraint condition may be a resource non-negative constraint, the allocated resources do not exceed the limit of the total server resources, the CPU usage does not exceed the maximum value, the memory usage does not exceed the maximum value, and the network usage does not exceed the maximum value.

[0067] In specific implementation, the weight coefficients and constraints can be adjusted based on the specific configuration and business requirements of each server in the server cluster.

[0068] The above optimization algorithm can be a genetic algorithm, a particle swarm algorithm, an integer programming algorithm and the like.

[0069] Under the condition of satisfying resource constraints, the target optimization function is solved by the optimization algorithm, and the optimal solution is obtained when the target optimization function takes the maximum value, so as to obtain the target server to which each basic content block is assigned, so that the allocation of service resources achieves the best balance between total cost efficiency, total processing capacity and average response time, and realizes the on-demand allocation of service resources. For example, basic content blocks with higher complexity will be allocated more service resources, and basic content blocks with lower complexity will be allocated fewer service resources, thereby improving the structured processing efficiency of documents.

[0070] In one embodiment, optionally, the above S105 may include: using a pre-built power grid knowledge graph to obtain standardized power information corresponding to key business information; integrating the standardized power information into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

[0071] Specifically, the above-mentioned power grid knowledge graph can be constructed through processes such as entity recognition, attribute extraction, relationship extraction and event extraction. Entity recognition is mainly to identify power-related entities from text, attribute extraction is mainly to extract relevant attributes for each power-related entity, relationship extraction is to identify the relationship between power-related entities, and event extraction is to identify specific events involving power-related entities.

[0072] In the structuring process, the key business information obtained can be verified using the above-constructed power grid knowledge graph to determine whether the key business information is a standardized term in the power business. If the key business information is a standardized term in the power business, the key business information is directly integrated into the power business knowledge graph; if the key business information is not a standardized term in the power business, the key business information is corrected and supplemented based on the power grid knowledge graph to obtain standardized power information. The standardized power information here refers to the standardized description information of the key business information in the power business. Furthermore, the standardized power information is integrated into the power business knowledge graph to improve the accuracy and completeness of the structured results.

[0073] Figure 2 A schematic diagram of a structure of a power business document processing device is provided for an embodiment of the present application. Figure 2 As shown, the device may include: a document acquisition module 201, a structure recognition module 202, a resource allocation module 203, an information extraction module 204 and an information storage module 205.

[0074] Specifically, the document acquisition module 201 is used to acquire the unstructured document corresponding to the power business hall service system;

[0075] The structure identification module 202 is used to identify the basic content blocks contained in the unstructured document based on the preset document structure rules;

[0076] The resource allocation module 203 is used to determine the target server to which each basic content block is allocated from the server cluster based on the complexity of each basic content block;

[0077] The information extraction module 204 is used to extract key business information in the corresponding basic content block through the target server;

[0078] The information storage module 205 is used to integrate the key business information into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

[0079] Optionally, the document structure rule includes at least one of the following:

[0080] Keyword collection, keyword position features, specific sentence features, paragraph structure features, result keywords, chart text features, discussion keywords, and paragraph position features.

[0081] On the basis of the above embodiment, optionally, the resource allocation module 203 is specifically used to construct a target optimization function with the goals of maximizing the total processing capacity of the server cluster for all basic content blocks, minimizing the total processing cost, and minimizing the average response time; wherein the total processing capacity and the average response time are related to the complexity of each basic content block; resource constraints are set, and based on the resource constraints, an optimization algorithm is used to solve the target optimization function to obtain the target server to which each basic content block is allocated when the target optimization function is maximized.

[0082] Based on the above embodiment, optionally, the objective optimization function O(s) is:

[0083] O(s)=w1*(P_max / P_total(s))-w2*h(s)-w3*(C_total(s) / C_min);

[0084] P_total(s)=∑(∑P[i][j]*A[i][j]);

[0085] C_total(s)=∑(∑Cost[i][j]*A[i][j]);

[0086] h(s)=(1 / P_total(s))*∑(A[i][j] / (Server[j]-Load[j]));

[0087] Wherein, P_max is the maximum value of the total processing capacity, P_total(s) represents the total processing capacity, h(s) represents the average response time, C_total(s) represents the total processing cost, C_min represents the minimum value of the total processing cost, w1 represents the weight coefficient corresponding to the total processing capacity, w2 represents the weight coefficient corresponding to the average response time, w3 represents the weight coefficient corresponding to the total processing cost, A[i][j] represents whether basic content block i is allocated to server j, Cost[i][j] represents the unit cost when basic content block i runs on server j, P[i][j] represents the expected processing capacity of server j for basic content block i, Server[j] represents the total resources of server j, Load[j] represents the current load of server j, and s represents the service resource allocation plan.

[0088] Based on the above embodiment, optionally, the resource constraint condition includes at least one of the following:

[0089] Resource non-negative constraints, CPU constraints, memory constraints, storage constraints, and network constraints.

[0090] Based on the above embodiment, optionally, the information storage module 205 is specifically used to obtain standardized power information corresponding to the key business information using a pre-built power grid knowledge graph; integrate the standardized power information into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

[0091] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 3 As shown, the device includes a processor 30, a memory 31, an input device 32 and an output device 33; the number of processors 30 in the device can be one or more. Figure 3 A processor 30 is taken as an example; the processor 30, memory 31, input device 32 and output device 33 in the device can be connected by a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0092] The memory 31, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the power business document processing method in the embodiment of the present application (for example, the document acquisition module 201, the structure recognition module 202, the resource allocation module 203, the information extraction module 204 and the information storage module 205 in the power business document processing device). The processor 30 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 31, that is, realizes the above-mentioned power business document processing method.

[0093] The memory 31 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created during the processing of power business documents, etc. In addition, the memory 31 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 31 may further include a memory remotely arranged relative to the processor 30, and these remote memories may be connected to the device / terminal / server via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0094] The input device 32 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device. The output device 33 may include a display device such as a display screen.

[0095] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0096] Obtain the unstructured documents corresponding to the power business hall service system;

[0097] Identifying basic content blocks contained in the unstructured document based on preset document structure rules;

[0098] Based on the complexity of each basic content block, determine the target server to which each basic content block is assigned from the server cluster;

[0099] Extracting key business information in the corresponding basic content block through the target server;

[0100] The key business information is integrated into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

[0101] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the following steps:

[0102] Obtain the unstructured documents corresponding to the power business hall service system;

[0103] Identifying basic content blocks contained in the unstructured document based on preset document structure rules;

[0104] Based on the complexity of each basic content block, determine the target server to which each basic content block is assigned from the server cluster;

[0105] Extracting key business information in the corresponding basic content block through the target server;

[0106] The key business information is integrated into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

[0107] The power business document processing device, electronic device, storage medium, and computer program product provided in the above embodiments can execute the power business document processing method provided in any of the above embodiments, and have the corresponding functional modules and beneficial effects of executing the method. For technical details not described in detail in the above embodiments, please refer to the power business document processing method provided in any of the above embodiments.

[0108] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0109] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing electric power business documents, characterized in that: include: Obtain the unstructured documents corresponding to the power business hall service system; Identifying basic content blocks contained in the unstructured document based on preset document structure rules; Based on the complexity of each basic content block, determine the target server to which each basic content block is assigned from the server cluster; Extracting key business information in the corresponding basic content block through the target server; The key business information is integrated into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

2. The method according to claim 1, characterized in that The document structure rule includes at least one of the following: Keyword collection, keyword position features, specific sentence features, paragraph structure features, result keywords, chart text features, discussion keywords, and paragraph position features.

3. The method according to claim 1, characterized in that The step of determining, based on the complexity of each basic content block, a target server to which each basic content block is to be allocated from a server cluster includes: Constructing a target optimization function with the goal of maximizing the total processing capacity of the server cluster for all basic content blocks, minimizing the total processing cost, and minimizing the average response time; wherein the total processing capacity and the average response time are related to the complexity of each basic content block; Resource constraints are set, and based on the resource constraints, an optimization algorithm is used to solve the target optimization function to obtain a target server to which each basic content block is allocated when the target optimization function is maximized.

4. The method according to claim 3, characterized in that: The objective optimization function O(s) is: O(s) ＝ w1*(P _ma x / P _ total(s))-w2*h(s)-w3*(C _ total(s) / C _ min); P_total(s)=∑(∑P[i][j]*A[i][j]); C_total(s)=∑(∑Cost[i][j]*A[i][j]); h(s)=(1 / P_total(s))*∑(A[i][j] / (Server[j]-Load[j])); Among them, P_max is the maximum value of the total processing capacity, P_total(s) represents the total processing capacity, h(s) represents the average response time, C_total(s) represents the total processing cost, C_min represents the minimum value of the total processing cost, w1 represents the weight coefficient corresponding to the total processing capacity, w2 represents the weight coefficient corresponding to the average response time, w3 represents the weight coefficient corresponding to the total processing cost, A[i][j] represents whether basic content block i is allocated to server j, Cost[i][j] represents the unit cost when basic content block i runs on server j, P[i][j] represents the expected processing capacity of server j for basic content block i, Server[j] represents the total resources of server j, Load[j] represents the current load of server j, and s represents the service resource allocation plan.

5. The method according to claim 3, characterized in that: The resource constraint condition includes at least one of the following: Resource non-negative constraints, CPU constraints, memory constraints, storage constraints, and network constraints.

6. The method according to claim 1, characterized in that The key business information is integrated into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database, including: Using a pre-built power grid knowledge graph to obtain standardized power information corresponding to the key business information; The standardized power information is integrated into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

7. A power business document processing device, characterized in that: include: The document acquisition module is used to obtain the unstructured documents corresponding to the power business hall service system; A structure identification module, used for identifying basic content blocks contained in the unstructured document based on preset document structure rules; A resource allocation module, used to determine a target server to which each basic content block is to be allocated from a server cluster based on the complexity of each basic content block; An information extraction module, used to extract key business information in the corresponding basic content block through the target server; The information storage module is used to integrate the key business information into the power business knowledge graph corresponding to the power business hall service system to obtain a power business document database.

8. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images