Business plan generation method and apparatus, electronic device, medium, and program product

Abstract

This application provides a business solution generation method, apparatus, electronic device, medium, and program product, relating to the field of big data technology. The method includes: acquiring graphic and textual information associated with a business to be processed; parsing the graphic and textual information to determine the business requirement elements corresponding to the business to be processed; generating multiple initial business solutions based on the business requirement elements; constructing a corresponding chromosome representation for each initial business solution; and optimizing the initial business solutions using the chromosome representation to obtain a target business solution corresponding to the business to be processed. This method aims to achieve the effect of efficiently generating accurate and reliable business solutions.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to a business solution generation method, apparatus, electronic device, medium, and program product. Background Technology

[0002] In business operation scenarios in industries such as finance, telecommunications, and logistics, companies often need to quickly generate standardized business operation service solutions based on business requirements documents, product introduction documents, platform operation manuals, and other business materials.

[0003] In related technologies, while general-purpose large language models can generate preliminary solutions, they lack industry knowledge adaptability, resulting in a low degree of matching between the generated results and actual business needs. Furthermore, methods based on knowledge graph retrieval or prompt word matching cannot be dynamically adjusted and optimized, further exacerbating the instability of solution quality.

[0004] Therefore, how to provide a business solution generation method that can combine industry knowledge, dynamically optimize, and generate accurate and reliable results is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] This application provides a business solution generation method, apparatus, electronic device, medium, and program product to achieve the effect of efficiently generating accurate and reliable business solutions.

[0006] In a first aspect, embodiments of this application provide a method for generating a business solution, including:

[0007] Retrieve graphic and textual information related to the pending business;

[0008] The graphic information is analyzed to determine the business requirement elements corresponding to the business to be processed.

[0009] Multiple initial business solutions are generated based on the business requirement elements. A corresponding chromosome representation is constructed for each initial business solution. The initial business solutions are then optimized using the chromosome representation to obtain the target business solution corresponding to the business to be processed.

[0010] In one possible implementation, the initial service plan is optimized using the chromosome representation to obtain a target service plan corresponding to the service to be processed, including:

[0011] Based on the chromosome representation, the initial business plan is optimized through multiple generations of genetic iteration to generate multiple optimized candidate business plans.

[0012] A comprehensive evaluation of each candidate service solution is performed to obtain the target service solution corresponding to the service to be processed.

[0013] In one possible implementation, based on the chromosome representation, the candidate service solutions are subjected to multi-generational genetic iterative optimization to generate multiple optimized candidate service solutions, including:

[0014] Using the candidate business schemes as chromosomes, an initial population is formed;

[0015] The fitness score of each chromosome in the first generation population is calculated based on a preset fitness function.

[0016] If the fitness score of a chromosome is greater than or equal to a preset threshold, it is retained in the next generation of the population.

[0017] If the fitness score of a chromosome is less than the preset threshold, a mutation operation is performed on it, and the mutated chromosome is retained in the next generation of the population.

[0018] Based on the next generation population, the fitness score calculation, screening, and mutation operations are repeated until the preset iteration termination condition is met.

[0019] Each chromosome in the population obtained from the final iteration is used as one of the multiple optimized candidate business solutions.

[0020] In one possible implementation, if the chromosome's fitness score is less than the preset threshold, a mutation operation is performed, including:

[0021] Obtain chromosomes whose fitness scores are less than the preset threshold;

[0022] Based on the preset gene loci of each chromosome, each chromosome is screened to obtain the target chromosome for mutation operation;

[0023] The target chromosome is subjected to mutation operations.

[0024] In one possible implementation, based on preset gene loci of each chromosome, each chromosome is screened to obtain target chromosomes for mutation operations, including:

[0025] Chromosomes with fitness scores lower than the preset threshold are divided into multiple chromosome groups;

[0026] For each chromosome set, obtain the preset gene loci of any chromosome in the chromosome set;

[0027] Gene values ​​for the preset gene loci are generated. If the gene value is greater than the mutation probability threshold corresponding to the current generation, then all chromosomes in the chromosome set are identified as the target chromosomes.

[0028] In one possible implementation, the target chromosome is mutated, including:

[0029] For any target chromosome, the target chromosome is matched with each historical scheme in the preset historical scheme library for similarity.

[0030] If the target chromosome matches the similarity of any historical scheme, then the target chromosome is used as the mutated chromosome.

[0031] If the similarity match between the target chromosome and all historical schemes is inconsistent, the gene value of the corresponding gene position in the target chromosome is replaced with the gene value of the preset gene position in the historical scheme with the highest similarity to generate the mutated chromosome.

[0032] In one possible implementation, the chromosome representation includes the following data structure:

[0033]

[0034] Wherein, C represents chromosome representation; S represents the corresponding solution generation task for the business to be processed; T represents the task type of the solution generation task; L represents the set of subtasks obtained by decomposing the solution generation task; and D represents the task description information corresponding to each subtask in the set of subtasks.

[0035] In one possible implementation, the graphic information is parsed for business requirements to determine the business requirement elements corresponding to the service to be processed, including:

[0036] Multiple demand parsing agents are obtained; each demand parsing agent is obtained by fine-tuning different large language models based on domain knowledge, and each agent is configured with different prompt words.

[0037] Based on the analysis of the text and image information by each of the aforementioned demand analysis agents, the business demand elements corresponding to the business to be processed are determined.

[0038] In one possible implementation, the graphic information is parsed and processed by each of the aforementioned demand parsing agents to obtain the business demand element analysis results output by each of the demand parsing agents, including:

[0039] The graphic and textual information is input into each of the demand parsing agents to obtain the candidate demand elements output by each demand parsing agent.

[0040] Each of the candidate requirement elements is input into a preset element filtering agent for filtering processing to obtain the business requirement elements corresponding to the business to be processed.

[0041] In one possible implementation, acquiring graphic and textual information associated with the service to be processed includes:

[0042] Receive initial graphic and text information input by the user, and identify the business domain to which the initial graphic and text information belongs;

[0043] Based on the business domain, supplementary graphic and text information associated with the initial graphic and text information is retrieved from a preset domain knowledge base;

[0044] The initial graphic information and the supplementary graphic information are associated and integrated to form the graphic information associated with the business to be processed.

[0045] Secondly, embodiments of this application provide a business solution generation apparatus, comprising:

[0046] The information acquisition module is used to acquire graphic and textual information related to the business to be processed;

[0047] The business parsing module is used to parse the graphic information into business requirements in order to determine the business requirement elements corresponding to the business to be processed.

[0048] The solution generation module is used to generate multiple initial business solutions based on the business requirement elements, construct a corresponding chromosome representation for each initial business solution, and optimize the initial business solutions using the chromosome representation to obtain the target business solution corresponding to the business to be processed.

[0049] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0050] The memory stores computer-executed instructions;

[0051] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0052] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0053] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0054] The business solution generation method, apparatus, electronic device, medium, and program product provided in this application obtain and parse graphic and textual information related to the business to be processed, and extract structured business requirement elements; on this basis, multiple initial business solutions are automatically generated, and chromosome encoding combined with genetic algorithms is used to iteratively optimize the solutions to obtain accurate and reliable target business solutions. That is, the above solutions realize the automated generation from unstructured requirements to optimized solutions, and improve the efficiency, diversity, and reliability of solution generation. Attached Figure Description

[0055] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0056] Figure 1 An application scenario diagram of the page automation operation method provided in this application;

[0057] Figure 2 A flowchart illustrating the page automation method provided in this application;

[0058] Figure 3 A schematic diagram of the page automation operation device provided in this application;

[0059] Figure 4 A schematic diagram of the structure of the electronic device provided in this application.

[0060] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0061] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0062] The collection, storage, use, processing, transmission, provision, and disclosure of financial data or user data involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0063] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. The collection, use and processing of the relevant data shall comply with relevant laws, regulations and standards, and corresponding operation entry points shall be provided for users to choose to authorize or refuse.

[0064] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0065] In business operation scenarios in industries such as finance, telecommunications, and logistics, companies often need to quickly generate standardized business operation service solutions based on business requirements documents, product introduction documents, platform operation manuals, and other business materials.

[0066] In related technologies, while general-purpose large language models can generate preliminary solutions, they lack industry knowledge adaptability, resulting in a low degree of matching between the generated results and actual business needs. Furthermore, methods based on knowledge graph retrieval or prompt word matching cannot be dynamically adjusted and optimized, further exacerbating the instability of solution quality.

[0067] Therefore, how to provide a business operation solution generation method that can combine industry knowledge, dynamically optimize, and generate accurate and reliable results is a technical problem that urgently needs to be solved.

[0068] This application provides a business generation method aimed at solving the aforementioned technical problems. Specifically, by acquiring and parsing graphic and textual information related to the business to be processed, structured business requirement elements are extracted; based on this, multiple initial business solutions are automatically generated, and chromosome encoding combined with a genetic algorithm is used to iteratively optimize the solutions to obtain accurate and reliable target business solutions. In other words, the above method realizes the automated generation from unstructured requirements to optimized solutions, improving the efficiency, diversity, and reliability of solution generation.

[0069] The business solution generation method provided in this application is applicable to various industry scenarios that require the automatic generation of standardized solutions based on business documents.

[0070] For example, in the financial industry, executable operational plans containing service items, categories, sub-tasks, and descriptions can be automatically generated based on the financial business requirements document.

[0071] In addition, the above methods can also be applied to scenarios such as generating network operation and maintenance service lists in the telecommunications industry, formulating operation plans in the logistics industry, and standardizing diagnosis and treatment service processes in the medical industry.

[0072] In summary, any field that requires transforming unstructured business needs into structured operational solutions can be considered an application scenario for the business solution generation technology solution in this application.

[0073] The following is combined Figure 1 The application scenarios applicable to the embodiments of this application are described below. Figure 1 This is an application scenario diagram of the business solution generation method provided in this application.

[0074] See Figure 1 Taking financial services scenarios as an example, this scenario mainly involves electronic devices that interact with users. Multiple intelligent agents can be pre-deployed in these electronic devices to collaboratively process business needs, parse document content, generate and optimize solutions, etc., in order to obtain optimized target business solutions.

[0075] Based on this, the business solution generation method provided in this application generally includes the following:

[0076] The intelligent agent receives and parses the business requirement document input by the user, extracts key business elements, and forms an initial solution framework.

[0077] The optimized agent performs multiple rounds of iterative optimization on the initial solution based on a pre-set industry knowledge base and genetic algorithm model, generating multiple candidate solutions.

[0078] The evaluation agent comprehensively scores candidate solutions based on business rules and historical data, outputs the optimal target business solution, and feeds it back to the user for confirmation or execution.

[0079] In the above steps, multi-agent collaborative processing is used to achieve fully automated processing from document parsing to solution generation, improving processing efficiency, and dynamic optimization is achieved through genetic algorithms to ensure the accuracy and stability of the generated results.

[0080] Figure 2 This is a flowchart illustrating the business solution generation method provided in this application. This method can be executed by a business solution generation device, which can be a server or an electronic device; the following explanation uses an electronic device as an example. The method in this embodiment can be implemented through software, hardware, or a combination of both. Figure 2 As shown, the method includes:

[0081] S201. Obtain graphic and textual information related to the business to be processed.

[0082] In this embodiment, the graphic and textual information refers to original data directly related to the business to be processed, and its sources and forms are diverse. For example, the graphic and textual information may include, but is not limited to, business requirement documents, product function specifications, platform operation manuals, historical work order records, industry analysis reports, and technical white papers. This information may exist in structured documents such as PDF, Word, semi-structured data such as Excel spreadsheets, or plain text formats, and typically contains various elements such as text descriptions, tables, and flowcharts.

[0083] In practice, text and image information can be obtained in various ways. For example, a standardized data access interface can be provided, allowing users to submit materials by uploading files or authorizing access to specific database links; it can also be configured to periodically and automatically read or synchronize the latest relevant documents from designated enterprise knowledge bases, document management systems, or business system backends.

[0084] After receiving the raw data, it can be preprocessed in a unified manner, such as format parsing, encoding conversion, and optical character recognition of non-text elements, such as text in images, to ensure that key business information can be extracted accurately and completely in the future.

[0085] S202. Analyze the graphic and text information to determine the business requirement elements corresponding to the business to be processed.

[0086] In this embodiment, the business requirement elements can be a multi-dimensional data set, including but not limited to: core service items that define business objectives, service categories and levels for organizational management, specific tasks and sub-tasks required to achieve the objectives, task attributes and constraints that specify execution details, and business rules and logic that describe the relationships between tasks.

[0087] Specifically, natural language processing models can be used to perform deep semantic analysis on the text content in graphic information, and named entity recognition technology can be used to extract business-related entities, such as proper nouns, action verbs, quantitative indicators, and time expressions. Meanwhile, for non-text elements such as flowcharts and tables contained in graphic information, image analysis and layout understanding technologies can be used to identify their graphical structure, text annotations, and logical connections, and convert them into machine-readable structured descriptions, such as task sequences, conditional branches, or data mapping relationships.

[0088] Furthermore, based on the built-in industry knowledge graph and business ontology library, the extracted entities can be processed by semantic disambiguation, classification and summarization, and association mapping to obtain a set of business requirement elements.

[0089] It should be noted that this embodiment does not limit the specific implementation method of element extraction. For example, a large language model fine-tuned based on domain corpus, or a neural network model trained using domain corpus as training samples, can be used to extract elements and output structured information from text and images. Of course, other natural language processing, multimodal understanding, or knowledge graph technologies that can achieve similar functions are also within the scope of protection of this embodiment.

[0090] S203. Generate multiple initial business solutions based on business requirement elements, construct a corresponding chromosome representation for each initial business solution, and use the chromosome representation to optimize the initial business solutions to obtain the target business solution corresponding to the business to be processed.

[0091] In this embodiment, based on the business requirement elements, multiple feasible solutions, i.e. initial business solutions, can be generated by combining the tasks, constraints, and logical relationships in the business requirement elements with a pre-set solution template library and rule library, using methods such as combination generation, rule reasoning, or case-based reasoning, to cover different optimization directions and potential solution spaces.

[0092] Based on this, a genetic algorithm is used to iteratively optimize the multiple initial business solutions obtained, which can efficiently search in the global solution space and generate the target business solution.

[0093] During the optimization process using a genetic algorithm, a corresponding chromosome representation is constructed for each initial business plan. For example, in this embodiment, the constructed chromosome representation can be a set of structured coding sequences, which include multiple gene positions, each corresponding to a key variable in the business plan.

[0094] For example, chromosome representation includes the following data structures:

[0095]

[0096] Where C represents chromosome representation; S represents the corresponding solution generation task for the business to be processed; T represents the task type of the solution generation task; L represents the set of subtasks obtained by decomposing the solution generation task; and D represents the task description information corresponding to each subtask in the subtask set.

[0097] It can be explained that the chromosome data structure described above is an exemplary way to map business solutions into encoded sequences. In practical applications, the gene bits in the chromosome representation can be further expanded or adjusted according to specific business scenarios. For example, gene bits representing resource allocation, timing constraints, or execution roles can be added to more completely carry the decision information of the solution.

[0098] Through this structured encoding, the optimization problem of business solutions is transformed into a chromosome evolution process that can be carried out through selection, crossover, and mutation operations within the framework of genetic algorithms.

[0099] It should be noted that the optimization process based on chromosome evolution is described in detail in the subsequent scheme description, and is not elaborated here.

[0100] In the above solution, structured business requirement elements are extracted by acquiring and parsing graphic and textual information related to the business to be processed. Based on this, multiple initial business solutions are automatically generated, and chromosome encoding combined with genetic algorithms is used to iteratively optimize the solutions to obtain accurate and reliable target business solutions. In other words, the above solution realizes the automated generation from unstructured requirements to optimized solutions, improving the efficiency, diversity and reliability of solution generation.

[0101] The following section will further detail the execution process of the technical solution for generating the business solution. It should be noted that the following description is merely an exemplary implementation of the technical solution in this application and does not constitute a limitation on the technical solution of this application.

[0102] In this embodiment, when acquiring the graphic and textual information related to the business to be processed input by the user, an optional implementation may include: receiving the initial graphic and textual information input by the user and identifying the business domain to which the initial graphic and textual information belongs; retrieving and acquiring supplementary graphic and textual information associated with the initial graphic and textual information from a preset domain knowledge base according to the business domain; and associating and integrating the initial graphic and textual information with the supplementary graphic and textual information as graphic and textual information associated with the business to be processed.

[0103] It receives initial text and image information directly input by the user and performs identification and analysis. Specifically, it can comprehensively analyze the initial text and image information based on one or more techniques, such as text keyword matching, image feature classification, or pre-trained multimodal classification models, to determine its business domain, such as financial credit, supply chain management, or customer service processes.

[0104] After identifying the business domain, supplementary text and image information related to the initial text and image information is automatically retrieved from a pre-defined domain knowledge base based on the domain tags. It should be understood that the domain knowledge base stores structured or semi-structured domain business knowledge, such as common business templates, standard flowcharts, specification documents, historical case illustrations, and related terminology explanations.

[0105] Specifically, when performing knowledge retrieval, the initial text and image information can be processed by semantic matching, association rule mining, or graph querying to obtain supplementary information from the domain knowledge base that is highly relevant to the initial text and image information in the business context.

[0106] Based on this, the initial text and image information input by the user can be combined with the supplementary text and image information obtained from the knowledge base through methods such as information splicing, key element alignment, redundancy content deduplication, and logical association annotation. This results in more complete and semantically rich text and image information, which can then be used as input for subsequent business requirement analysis.

[0107] By using the above methods, when the user's input information may be incomplete or poorly expressed, relevant domain knowledge can be automatically introduced to supplement and enhance it, thereby improving the accuracy and reliability of subsequent extraction of business requirement elements.

[0108] Based on the obtained graphic and textual information, elements can be extracted to obtain the business requirement elements needed to generate subsequent business solutions.

[0109] Optionally, one possible implementation of element extraction may include: acquiring multiple demand parsing agents; each demand parsing agent is obtained by fine-tuning different large language models based on domain knowledge, and each agent is configured with different prompt words; based on each demand parsing agent, the graphic information is parsed and processed to determine the business demand elements corresponding to the business to be processed.

[0110] In this embodiment, multiple pre-built demand parsing agents are obtained, and through the collaborative parsing of multiple agents, it is possible to combine professional knowledge and analytical perspectives from different fields to achieve more comprehensive, accurate and robust demand extraction of complex graphic and textual information, providing high-quality structured input for the generation of subsequent business solutions.

[0111] Specifically, during the construction process, based on domain-specific expertise such as financial risk control, logistics scheduling, and customer service standards, the general language model can be fine-tuned to adapt to specific domains, and special prompt words with different focuses and parsing objectives can be configured for it.

[0112] For example, the first intelligent agent can focus on extracting business processes and task nodes, and its prompts guide the model to identify steps, sequences, dependencies, etc.; the second intelligent agent can focus on identifying resources and constraints, and its prompts emphasize cost, time, manpower, rule restrictions, etc.; the third intelligent agent can mainly identify business goals and performance indicators, and its prompts guide the extraction of optimization goals, measurement standards, success conditions, etc.

[0113] During the parsing process, the acquired graphic and textual information can be input to each required parsing agent in parallel or serial manner.

[0114] For each agent, it can independently parse the same text and image information based on its fine-tuned domain understanding and dedicated prompts, and output the structured parsing results of its preferred dimension.

[0115] Based on this, the parsing results output by each intelligent agent can be evaluated and filtered to obtain an accurate, complete and non-redundant set of business requirement elements.

[0116] In some implementations, the output results of each intelligent agent can be further fused and aligned, for example, through steps such as entity alignment, conflict resolution and information completion, to obtain a set of business requirement elements that are logically consistent and structurally clear.

[0117] In the above processing, the parsing results output by each intelligent agent can be evaluated and filtered to obtain business requirement elements. One possible implementation method may include: inputting graphic and textual information into each requirement parsing intelligent agent to obtain candidate requirement elements output by each requirement parsing intelligent agent; inputting each candidate requirement element into a preset element filtering intelligent agent for filtering and integration processing to obtain the business requirement elements corresponding to the business to be processed.

[0118] Specifically, the acquired text and image information is input in parallel to each requirement parsing agent. Each agent independently parses the text and image information based on its domain-adjusted model and dedicated prompts, and outputs its corresponding set of candidate requirement elements. These candidate elements may cover different dimensions, such as tasks, resources, constraints, and goals, and may have some overlap, different expressions, or complementary perspectives.

[0119] Furthermore, the candidate demand elements output by each demand parsing agent are input into a preset element filtering agent. This agent filters and evaluates the multiple input candidate demand elements based on predefined filtering rules and evaluation criteria, and obtains the confidence score corresponding to each candidate demand element.

[0120] Based on the confidence score, each candidate requirement element is sorted and filtered to obtain one or more filtered results, which are then used as the business requirement elements corresponding to the business to be processed.

[0121] For example, if only one result is obtained after filtering, that result can be directly used as the final business requirement element; if multiple results are obtained after filtering, the results can be further integrated, for example, through semantic fusion, logical association or structured reorganization, and the integrated result can be used as the final business requirement element.

[0122] In the above approach, multiple intelligent agents for demand parsing, fine-tuned based on domain knowledge and configured with different prompt words, achieve multi-dimensional and professional demand parsing of text and image information. Then, an intelligent agent for element filtering integrates and filters the parsing results, which can efficiently and accurately extract business demand elements that are structurally complete, logically consistent, and highly reliable, thereby improving the comprehensiveness, accuracy, and reliability of automatic business demand parsing.

[0123] Based on the obtained business requirements, these can be input into a pre-defined solution generation agent to generate multiple initial business solutions in batches. Furthermore, a genetic algorithm is used to iteratively optimize these initial business solutions to generate the target business solution.

[0124] Based on this, an optional implementation method for iteratively optimizing multiple initial business solutions may include: performing multi-generation genetic iterative optimization on the initial business solutions based on chromosome representation to generate multiple optimized candidate business solutions; and comprehensively evaluating each candidate business solution to obtain the target business solution corresponding to the business to be processed.

[0125] Specifically, the overall performance of each chromosome, i.e., each initial business plan, can be quantitatively evaluated using a fitness function to obtain the evaluation results. Based on the evaluation results, a selection mechanism is used to select individuals with high fitness as parents. Then, by performing crossover operations on the parent chromosomes to recombine gene fragments, and combining this with probabilistic mutation operations to introduce new decision options, a diverse offspring population is generated, achieving iterative evolution of chromosomes.

[0126] The optimization process of selection, crossover, and mutation described above is repeated until the preset number of iterations or fitness convergence condition is reached. At this point, chromosomes in the last generation population whose fitness meets the preset threshold can be decoded and restored as candidate service solutions.

[0127] A comprehensive evaluation is conducted on each candidate business solution. For example, based on multi-objective decision-making methods or weighted scoring models, quantitative comparisons and rankings are performed from dimensions such as efficiency, cost, risk, and compliance, so as to select the solution with the highest comprehensive score as the target business solution corresponding to the business to be processed.

[0128] In the above-mentioned iterative optimization process based on genetic algorithms, an optional implementation method may include: using candidate business solutions as chromosomes to form an initial population; calculating the fitness score of each chromosome in the initial population based on a preset fitness function; if the fitness score of a chromosome is greater than or equal to a preset threshold, then retaining it to the next generation population; if the fitness score of a chromosome is less than the preset threshold, then performing a mutation operation on it, and retaining the mutated chromosome to the next generation population; based on the next generation population, repeatedly performing fitness score calculation, screening, and mutation operations until a preset iteration termination condition is met; and using each chromosome in the final iteratively obtained population as multiple optimized candidate business solutions.

[0129] Specifically, after constructing a corresponding chromosome representation for each initial business plan, these chromosomes are used as initial individuals to form the first generation population. It should be understood that each chromosome corresponds to a complete business plan, and its gene sequence encodes the plan's key parameters, structure, or decision variables.

[0130] The fitness score of each chromosome in the initial population is calculated based on a preset fitness function. Here, the fitness function can be designed according to business objectives, such as comprehensively considering the implementation cost, execution efficiency, resource utilization, or risk level of the solution, and quantified fitness values ​​are obtained through weighted or rule-based calculation.

[0131] For example, the expression for the fitness function can be as follows:

[0132]

[0133] In this context, C represents any chromosome, i.e., the business plan. Indicates fitness score; This indicates the similarity between the business solution and historical solutions in the historical knowledge base; Indicates the similarity between the business plan and the elements of the business requirements; Indicates the penalty term for the magnitude of chromosome variation; Indicates the weight.

[0134] In the process of calculating the fitness score, a preset threshold is obtained, and the fitness score is compared with the preset threshold.

[0135] If the fitness score of a chromosome is greater than or equal to a preset threshold, it indicates that it has met certain quality requirements, and it is directly retained to the next generation of the population.

[0136] If the fitness score of a chromosome is less than a preset threshold, it indicates that its quality is poor, and a mutation operation can be performed on it. The mutated chromosome will be retained in the next generation of the population.

[0137] In this embodiment, mutation operations may include randomly adjusting the values ​​of some genes in the chromosome, exchanging gene segments, or introducing random perturbations to enhance the diversity and exploratory capabilities of the scheme.

[0138] Based on this, the fitness score calculation, threshold screening and mutation operations are repeated for the next generation population until the preset iteration termination condition is met. Each chromosome in the population obtained at the end of the iteration process is decoded into the corresponding business solution and output as multiple optimized candidate business solutions.

[0139] In this implementation, the termination condition can be set as reaching the maximum number of iterations, the population fitness converging to a stable state, or the fitness of the best individual no longer significantly improving.

[0140] In the above approach, by using genetic iteration based on fitness threshold screening and directed mutation, high-quality business solutions can be retained and low-quality business solutions can be improved in a targeted manner during the optimization process, thereby improving the convergence efficiency and result quality of business solution optimization and enabling the rapid generation of multiple near-optimal candidate business solutions.

[0141] In the process of implementing the above method, an optional implementation method for performing mutation operations on chromosomes may include: obtaining each chromosome whose fitness score is less than a preset threshold; screening each chromosome based on preset gene loci to obtain the target chromosome for mutation operations; and performing mutation operations on the target chromosome.

[0142] Obtain all chromosomes in the current population whose fitness scores are below a preset threshold; this is the set of chromosomes to be mutated. In some scenarios, the number of these chromosomes may exceed the number of chromosomes directly carried over to the next generation. If all these chromosomes are mutated and carried over, it may lead to excessive population diversity, slower convergence, or even the introduction of too many low-quality mutated individuals, thereby reducing overall optimization efficiency and solution quality. Therefore, to improve the targeting and efficiency of the optimization process, before mutating, the chromosomes can be screened to obtain target chromosomes, which are the subset of chromosomes that actually need to be mutated to improve their fitness.

[0143] Specifically, when determining the target chromosome, one or more key gene loci can be pre-defined for each chromosome to be mutated.

[0144] In this embodiment, the preset gene loci can be S gene loci and T gene loci. This allows for adjustments to the generated business solutions and types during mutation, while retaining the subtask set and task description information. This enables targeted exploration and optimization of the business solution framework and types while maintaining the consistency of the overall task structure and semantics. This improves the diversity of solutions while ensuring that the optimization process does not deviate from the original business objectives and task logic.

[0145] While acquiring the preset gene loci, the value status of the preset gene loci is also acquired simultaneously. If the acquired value status indicates that the value of the gene loci is already at the boundary of the feasible range, or has been marked as a sensitive parameter in the historical optimization record, then the chromosome is determined to be the target chromosome; otherwise, mutation operations can be temporarily suspended to preserve its existing structure.

[0146] After the target chromosome is selected, a mutation operation is performed on it. After the mutation operation is completed, the chromosome code is updated and it is included in the next generation population to continue to participate in iterative optimization.

[0147] In the above method, by screening based on preset gene loci, low-fitness chromosomes that need mutation operations can be accurately identified, thereby achieving targeted and efficient local adjustments to the scheme during the optimization process, effectively improving the convergence speed of the genetic algorithm and the quality of the final generated scheme.

[0148] In the implementation of the above scheme, an optional implementation method for determining the target chromosome based on preset gene loci may include: dividing each chromosome with a fitness score less than a preset threshold into multiple chromosome groups; for each chromosome group, obtaining the preset gene loci of any chromosome in the chromosome group; generating the gene value of the preset gene loci; if the gene value is greater than the mutation probability threshold corresponding to the current iteration generation, then all chromosomes in the chromosome group are determined as the target chromosome.

[0149] Specifically, all chromosomes with fitness scores below a preset threshold are divided into multiple chromosome groups based on the numerical range of their fitness scores or the similarity of their chromosome coding structures. Each chromosome group contains one or more chromosomes, and the chromosomes within a group have certain correlations in structure or performance.

[0150] For each chromosome set, a representative chromosome can be randomly selected from the set, and its preset gene locus, such as the current coding value of the S gene locus or the T gene locus, can be obtained. Based on this coding value, a gene value can be randomly generated within a preset range using a uniform or normal distribution.

[0151] During this process, the corresponding mutation probability threshold can be dynamically calculated based on the current iteration number.

[0152] For example, the expression for calculating the mutation probability threshold may include:

[0153]

[0154] in, Indicates the mutation probability threshold; Indicates the current iteration number; Indicates the maximum number of iterations; and Represents the boundary probability; This represents the attenuation coefficient.

[0155] The generated gene value is compared with the mutation probability threshold. If the gene value is greater than the current mutation probability threshold, the chromosome set as a whole is determined to have a high mutation tendency, and all chromosomes in the set are identified as target chromosomes; otherwise, the chromosome set will not be mutated for the time being.

[0156] In the above approach, by using screening based on chromosome sets and dynamic thresholds, the scale and timing of mutation operations can be intelligently controlled, effectively avoiding invalid mutations while maintaining population diversity, thereby improving the convergence efficiency and stability of genetic algorithms in business solution optimization.

[0157] An optional implementation of the mutation operation after determining the target chromosome may include: for any target chromosome, performing similarity matching between the target chromosome and each historical scheme in a preset historical scheme library; if the target chromosome matches the similarity of any historical scheme, then the target chromosome is used as the mutated chromosome; if the target chromosome does not match the similarity of any historical scheme, then the gene value of the corresponding gene position in the target chromosome is replaced with the gene value of the preset gene position in the historical scheme with the highest similarity, so as to generate the mutated chromosome.

[0158] For each target chromosome, a similarity match is performed between it and each historical scheme in a pre-defined historical scheme library. For example, the similarity match result can be obtained by calculating the Hamming distance, cosine similarity, or structural similarity based on business rules between the chromosome encoding and the historical scheme encoding at pre-defined gene loci.

[0159] If the matching result indicates that the similarity between the target chromosome and any historical solution is consistent, that is, the similarity reaches the preset complete matching threshold, such as 100% matching or complete consistency of key gene positions, it means that the business solution represented by the chromosome has been verified in history or there is already a highly similar optimization solution. At this time, the target chromosome can be directly retained as the mutated chromosome to the next generation without further adjustment, thereby saving computing resources and maintaining the stability of the solution.

[0160] If the matching results indicate that the similarity between the target chromosome and all historical schemes is inconsistent (i.e., the similarity is below the perfect match threshold), then the historical scheme with the highest similarity to the target chromosome is selected from the historical scheme library as a reference scheme. Furthermore, the gene values ​​of the corresponding preset gene loci in this reference scheme are extracted and used to replace the current gene values ​​of the corresponding gene loci in the target chromosome, thereby generating the mutated chromosome. This allows for targeted gene replacement guided by historical experience, incorporating the gene characteristics of high-quality historical schemes while avoiding the performance degradation that might result from completely random mutations.

[0161] Through the above mutation operations, the optimization process can be enhanced in terms of guidance and efficiency by making full use of historical solution knowledge, while maintaining the population's reasonable exploration ability in the feasible solution space.

[0162] Figure 3 A schematic diagram of the business solution generation device provided in this application is shown below. Figure 4As shown, the business solution generation device 30 provided in this embodiment includes:

[0163] The information acquisition module 301 is used to acquire graphic and textual information related to the business to be processed;

[0164] The business parsing module 302 is used to parse the graphic information for business requirements in order to determine the business requirement elements corresponding to the business to be processed.

[0165] The solution generation module 303 is used to generate multiple initial business solutions based on business requirement elements, construct a corresponding chromosome representation for each initial business solution, and optimize the initial business solutions using the chromosome representation to obtain the target business solution corresponding to the business to be processed.

[0166] In one possible implementation, the solution generation module 303 is specifically used for:

[0167] The initial business plan is optimized using chromosome representation to obtain the target business plan corresponding to the business to be processed, including:

[0168] Based on chromosome representation, the initial business plan is optimized through multiple generations of genetic iteration to generate multiple optimized candidate business plans.

[0169] A comprehensive evaluation of each candidate business solution is conducted to obtain the target business solution corresponding to the business to be processed.

[0170] In one possible implementation, the solution generation module 303 is specifically used for:

[0171] The candidate business solutions are used as chromosomes to form the initial population;

[0172] The fitness score of each chromosome in the first generation population is calculated based on a preset fitness function.

[0173] If the fitness score of a chromosome is greater than or equal to a preset threshold, it is retained in the next generation of the population.

[0174] If the fitness score of a chromosome is less than a preset threshold, a mutation operation is performed on it, and the mutated chromosome is retained in the next generation of the population.

[0175] Based on the next generation population, the fitness score calculation, screening and mutation operations are repeated until the preset iteration termination condition is met.

[0176] Each chromosome in the population obtained from the final iteration is used as one of the multiple optimized candidate business solutions.

[0177] In one possible implementation, the solution generation module 303 is specifically used for:

[0178] If the fitness score of a chromosome is less than a preset threshold, a mutation operation is performed on it, including:

[0179] Identify chromosomes whose fitness scores are below a preset threshold;

[0180] Based on the preset gene loci of each chromosome, each chromosome is screened to obtain the target chromosome for mutation operation;

[0181] Perform mutation operations on the target chromosome.

[0182] In one possible implementation, the solution generation module 303 is specifically used for:

[0183] Based on preset gene loci on each chromosome, each chromosome is screened to obtain the target chromosome for mutation operations, including:

[0184] Chromosomes with fitness scores below a preset threshold are divided into multiple chromosome groups;

[0185] For each chromosome set, obtain the preset gene loci of any chromosome in the chromosome set;

[0186] Gene values ​​for preset gene loci are generated. If the gene value is greater than the mutation probability threshold corresponding to the current generation, all chromosomes in the chromosome set are identified as target chromosomes.

[0187] In one possible implementation, the solution generation module 303 is specifically used for:

[0188] Mutation operations on the target chromosome include:

[0189] For any target chromosome, perform similarity matching between the target chromosome and each historical scheme in the preset historical scheme library;

[0190] If the target chromosome matches the similarity of any historical scheme, then the target chromosome is used as the mutated chromosome.

[0191] If the similarity match between the target chromosome and all historical schemes is inconsistent, the gene value of the corresponding gene position in the target chromosome is replaced with the gene value of the preset gene position in the historical scheme with the highest similarity to generate the mutated chromosome.

[0192] In one possible implementation, the chromosome representation includes the following data structures:

[0193]

[0194] Where C represents chromosome representation; S represents the corresponding solution generation task for the business to be processed; T represents the task type of the solution generation task; L represents the set of subtasks obtained by decomposing the solution generation task; and D represents the task description information corresponding to each subtask in the subtask set.

[0195] In one possible implementation, the business parsing module 302 is specifically used for:

[0196] Multiple demand parsing agents are obtained; each demand parsing agent is obtained by fine-tuning different large language models based on domain knowledge, and each agent is configured with different prompt words.

[0197] Based on the intelligent agents that analyze the requirements, the graphic and textual information is processed to determine the business requirement elements corresponding to the business to be processed.

[0198] In one possible implementation, the business parsing module 302 is specifically used for:

[0199] Based on the analysis and processing of text and image information by each demand analysis agent, the business demand element analysis results output by each demand analysis agent are obtained, including:

[0200] The graphic and textual information is input into each demand parsing agent to obtain the candidate demand elements output by each demand parsing agent.

[0201] Each candidate requirement element is input into a preset element filtering agent for filtering and processing to obtain the business requirement elements corresponding to the business to be processed.

[0202] In one possible implementation, the information acquisition module 301 is specifically used for:

[0203] Receive initial text and image information input by the user and identify the business domain to which the initial text and image information belongs;

[0204] Based on the business domain, retrieve and obtain supplementary graphic and text information related to the initial graphic and text information from the preset domain knowledge base;

[0205] The initial graphic and text information is linked and integrated with the supplementary graphic and text information to form the graphic and text information associated with the business to be processed.

[0206] The business solution generation device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0207] Figure 4 This is a block diagram of an electronic device provided in an embodiment of this application. The device may be a computer, a digital broadcasting terminal, etc. See also... Figure 4The device 400 may include one or more of the following components: processing component 402, memory 404, power supply component 406, multimedia component 408, audio component 410, input / output interface 412, sensor component 414, and communication component 416.

[0208] Processing component 402 typically controls the overall operation of device 400, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 402 may include one or more processors 420 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 402 may include one or more modules to facilitate interaction between processing component 402 and other components. For example, processing component 402 may include a multimedia module to facilitate interaction between multimedia component 408 and processing component 402.

[0209] Memory 404 is configured to store various types of data to support the operation of device 400. Examples of this data include instructions for any application or method operating on device 400, contact data, phonebook data, messages, pictures, videos, etc. Memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0210] Power supply component 406 provides power to various components of device 400. Power supply component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 400.

[0211] Multimedia component 408 includes a screen that provides an output interface between device 400 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a Touch Panel, the screen may be implemented as a touchscreen to receive input signals from the user. The Touch Panel includes one or more touch sensors to sense touches, swipes, and gestures on the Touch Panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 408 includes a front-facing camera and / or a rear-facing camera. When device 400 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0212] Audio component 410 is configured to output and / or input audio signals. For example, audio component 410 includes a microphone (MIC) configured to receive external audio signals when device 400 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 404 or transmitted via communication component 416. In some embodiments, audio component 410 also includes a speaker for outputting audio signals.

[0213] Input / output interface 412 provides an interface between processing component 402 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, start buttons, and lock buttons.

[0214] Sensor assembly 414 includes one or more sensors for providing state assessments of various aspects of device 400. For example, sensor assembly 414 may detect the on / off state of device 400, the relative positioning of components such as the display and keypad of device 400, changes in the position of device 400 or a component of device 400, the presence or absence of user contact with device 400, the orientation or acceleration / deceleration of device 400, and temperature changes of device 400. Sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 414 may also include an optical sensor, such as a complementary metal-oxide-semiconductor (CMOS) sensor or a charge-coupled device (CCD) sensor, for use in imaging applications. In some embodiments, sensor assembly 414 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0215] Communication component 416 is configured to facilitate wired or wireless communication between device 400 and other devices. Device 400 can access wireless networks based on communication standards, such as WiFi, 4G, or 5G, or combinations thereof. In one exemplary embodiment, communication component 416 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 416 also includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wide Band (UWB), Bluetooth (BT), and other technologies.

[0216] In an exemplary embodiment, device 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processors (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0217] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, which can be executed by a processor 420 of the device 400 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0218] A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a server's processor, enable the server to perform the methods described above.

[0219] This application also provides a chip for executing instructions, which is used to execute the technical solutions in the above embodiments.

[0220] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed on a computer, cause the computer to perform the above-described technical solution.

[0221] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and the above-described technical solution can be implemented when the at least one processor executes the computer program.

[0222] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0223] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

[0224] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0225] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for generating a business solution, characterized in that, include: Retrieve graphic and textual information related to the pending business; The graphic information is analyzed to determine the business requirement elements corresponding to the business to be processed. Multiple initial business solutions are generated based on the business requirement elements. A corresponding chromosome representation is constructed for each initial business solution. The initial business solutions are then optimized using the chromosome representation to obtain the target business solution corresponding to the business to be processed.

2. The method according to claim 1, characterized in that, The initial service plan is optimized using the chromosome representation to obtain the target service plan corresponding to the service to be processed, including: Based on the chromosome representation, the initial business plan is optimized through multiple generations of genetic iteration to generate multiple optimized candidate business plans. A comprehensive evaluation of each candidate service solution is performed to obtain the target service solution corresponding to the service to be processed.

3. The method according to claim 2, characterized in that, Based on the chromosome representation, the candidate service solutions are subjected to multi-generation genetic iterative optimization to generate multiple optimized candidate service solutions, including: Using the candidate business schemes as chromosomes, an initial population is formed; The fitness score of each chromosome in the first generation population is calculated based on a preset fitness function. If the fitness score of a chromosome is greater than or equal to a preset threshold, it is retained in the next generation of the population. If the fitness score of a chromosome is less than the preset threshold, a mutation operation is performed on it, and the mutated chromosome is retained in the next generation of the population. Based on the next generation population, the fitness score calculation, screening, and mutation operations are repeated until the preset iteration termination condition is met. Each chromosome in the population obtained from the final iteration is used as one of the multiple optimized candidate business solutions.

4. The method according to claim 3, characterized in that, If the fitness score of a chromosome is less than the preset threshold, a mutation operation is performed on it, including: Obtain chromosomes whose fitness scores are less than the preset threshold; Based on the preset gene loci of each chromosome, each chromosome is screened to obtain the target chromosome for mutation operation; The target chromosome is subjected to mutation operations.

5. The method according to claim 4, characterized in that, Based on preset gene loci of each chromosome, each chromosome is screened to obtain target chromosomes for mutation operations, including: Chromosomes with fitness scores lower than the preset threshold are divided into multiple chromosome groups; For each chromosome set, obtain the preset gene loci of any chromosome in the chromosome set; Gene values ​​for the preset gene loci are generated. If the gene value is greater than the mutation probability threshold corresponding to the current generation, then all chromosomes in the chromosome set are identified as the target chromosomes.

6. The method according to claim 4, characterized in that, The mutation operation on the target chromosome includes: For any target chromosome, the target chromosome is matched with each historical scheme in the preset historical scheme library for similarity. If the target chromosome matches the similarity of any historical scheme, then the target chromosome is used as the mutated chromosome. If the similarity match between the target chromosome and all historical schemes is inconsistent, the gene value of the corresponding gene position in the target chromosome is replaced with the gene value of the preset gene position in the historical scheme with the highest similarity to generate the mutated chromosome.

7. The method according to any one of claims 1-6, characterized in that, The chromosome representation includes the following data structures: Wherein, C represents chromosome representation; S represents the corresponding solution generation task for the business to be processed; T represents the task type of the solution generation task; L represents the set of subtasks obtained by decomposing the solution generation task; and D represents the task description information corresponding to each subtask in the set of subtasks.

8. The method according to any one of claims 1-6, characterized in that, The text and image information is parsed to determine the business requirement elements corresponding to the business to be processed, including: Multiple demand parsing agents are obtained; each demand parsing agent is obtained by fine-tuning different large language models based on domain knowledge, and each agent is configured with different prompt words. Based on the analysis of the text and image information by each of the aforementioned demand analysis agents, the business demand elements corresponding to the business to be processed are determined.

9. The method according to claim 8, characterized in that, Based on the analysis and processing of the graphic information by each of the aforementioned demand analysis agents, the business demand element analysis results output by each of the aforementioned demand analysis agents are obtained, including: The graphic and textual information is input into each of the demand parsing agents to obtain the candidate demand elements output by each demand parsing agent. Each of the candidate requirement elements is input into a preset element filtering agent for filtering processing to obtain the business requirement elements corresponding to the business to be processed.

10. The method according to any one of claims 1-6, characterized in that, Retrieve graphic and textual information related to the pending business, including: Receive initial graphic and text information input by the user, and identify the business domain to which the initial graphic and text information belongs; Based on the business domain, supplementary graphic and text information associated with the initial graphic and text information is retrieved from a preset domain knowledge base; The initial graphic information and the supplementary graphic information are associated and integrated to form the graphic information associated with the business to be processed.

11. A business solution generation device, characterized in that, include: The information acquisition module is used to acquire graphic and textual information related to the business to be processed; The business parsing module is used to parse the graphic information into business requirements in order to determine the business requirement elements corresponding to the business to be processed. The solution generation module is used to generate multiple initial business solutions based on the business requirement elements, construct a corresponding chromosome representation for each initial business solution, and optimize the initial business solutions using the chromosome representation to obtain the target business solution corresponding to the business to be processed.

12. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-10.

14. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-10.

Images