Intelligent operation method, system, device and medium

Abstract

The present application relates to an intelligent operation method, system, device and medium, and to the field of operation planning technology, which includes: obtaining an original user portrait, the original user portrait includes user behavior data, transaction data and logistics data, and generating a decision weight ratio; matching the decision weight ratio with preset strategy details, integrating and generating a preliminary strategy; generating a number of simulated user portraits according to market trends, importing a number of the simulated user portraits into the preliminary strategy for analysis and simulation, and generating a simulation strategy; outputting an implementation strategy according to the fitting of the simulation strategy with the preliminary strategy; recovering the user behavior data, transaction data and logistics data of the user for running the implementation strategy, and updating and optimizing the preset strategy details. The present application can collect and analyze based on external operation data to formulate personalized operation strategies, improve operation efficiency and reduce operation costs.

Description

Technical Field

[0001] The present application relates to the field of operation planning technology, and in particular to an intelligent operation method, system, device and medium. Background Art

[0002] As digital transformation accelerates, enterprises are increasingly demanding improved operational efficiency and lowered costs. As a key technology to achieve this goal, intelligent operations rely on advanced data analysis, automation, and artificial intelligence technologies to optimize business processes.

[0003] Currently, existing intelligent operations usually rely on integrated software platforms that can process and analyze large amounts of business data and provide decision support. These systems usually include components such as data warehouses, machine learning models, automation tools, and user interfaces. These tools can monitor business processes within the enterprise in real time, predict potential problems, and automatically execute some decisions.

[0004] However, existing intelligent operation methods, systems, equipment and media are difficult to formulate intelligent operation strategies based on the analysis results of the impact of external factors on operations, and have low operation efficiency and high implementation and maintenance costs. Summary of the invention

[0005] The first purpose of this application is to provide an intelligent operation method that can collect and analyze external operation data to formulate personalized operation strategies, improve operation efficiency and reduce operation costs.

[0006] In the first aspect, the present application provides an intelligent operation method, which adopts the following technical solutions:

[0007] An intelligent operation method, comprising:

[0008] Obtaining an original user portrait, wherein the original user portrait includes user behavior data, transaction data, and logistics data, and generating a decision weight ratio;

[0009] Matching the decision weight ratio with the preset strategy details, and integrating them to generate a preliminary strategy;

[0010] Generate a number of simulated user portraits according to market trends, import the simulated user portraits into the initial strategy for analysis and simulation, and generate a simulated strategy;

[0011] According to the fit between the simulation strategy and the initial strategy, the output is the implementation strategy;

[0012] Collect user behavior data, transaction data, and logistics data for implementing strategies, and update and optimize preset strategy details.

[0013] By adopting the above technical solution, it is possible to take into account the needs and behavioral data of users, accurately match the corresponding strategy details according to the needs and behavioral patterns, and then integrate them into a preliminary strategy. Then, based on the external factor of predicted market trends, several simulated users similar to the users are generated for testing the preliminary strategy, and invested in the preliminary strategy analysis simulation to optimize the allocation of resources in the strategy, so as to improve the feasibility of the planning and improve the efficiency of the actual operation. It can reduce the operating costs when actually invested, and can also dynamically adjust the operating strategy according to real-time data and market feedback to try to avoid the increase in operating costs caused by market changes.

[0014] In a preferred example, the present application may be further configured as follows: the step of obtaining an original user portrait, wherein the original user portrait includes user behavior data, transaction data, and logistics data, and generating a decision weight ratio includes:

[0015] Analyze the user behavior data to determine the user's demand preferences;

[0016] The transaction data is weighted according to the demand preference to generate a demand weight ratio of the original user portrait;

[0017] Matching the geographical location in the logistics data to the pre-divided geographical area, and obtaining the preset local demand weight ratio of the corresponding geographical area;

[0018] The demand quantity weight ratio and the local demand weight ratio are fitted to generate a decision weight ratio.

[0019] By adopting the above technical solutions, the effectiveness and pertinence of strategic planning are dually considered according to user needs and geographical area characteristics, which improves the comprehensiveness and accuracy of decision-making. The geographical location information in the logistics data is matched with the preset geographical area, and the specific needs of users in different regions are identified by the local demand weight ratio, providing support for the formulation of regional market strategies.

[0020] In a preferred example, the present application may be further configured as follows: before the step of matching the geographical location of the delivery address in the logistics data to the pre-divided geographical area and obtaining the preset local demand weight ratio of the corresponding geographical area, it also includes:

[0021] Obtaining demand weight ratios of several simulated user portraits within a time period in the geographical area where the logistics data is located;

[0022] The demand weight ratios of several simulated user portraits are fitted to generate the local demand weight ratios of the corresponding geographical areas.

[0023] By adopting the above technical solution, the demand weight ratio of simulated user portraits in a specific geographical area can be obtained. Based on historical data and behavioral patterns, understanding the demand weight ratio of different geographical areas can help optimize distribution plans, reduce transportation costs, improve distribution speed and efficiency, and make more accurate predictions on user demand and allocate resources more reasonably to meet the personalized needs of different regions.

[0024] In a preferred example, the present application may be further configured as follows: the step of generating a plurality of simulated user portraits according to market trends, importing the plurality of simulated user portraits into a preliminary strategy for analysis and simulation, and generating a simulated strategy includes:

[0025] After a trial operation simulation, generate the implementation weight ratio by randomly selecting several simulated user portraits and copying several original user portraits;

[0026] According to the implementation weight ratio, the weights of the policy details in the initial policy are redistributed and output as a simulation policy.

[0027] By adopting the above technical solution, combined with the trial operation simulation of simulated user portraits and original user portraits, it is possible to dynamically adjust according to the simulation results, and the implementation weight ratio can dynamically redistribute the weights of the strategy details, thereby improving the adaptability, effectiveness and flexibility of the strategy, reducing the cost of trial and error and market risks, optimizing resource allocation, and thus improving the quality of decision-making.

[0028] In a preferred example, the present application may be further configured as follows: the step of generating a plurality of simulated user portraits according to market trends, importing the plurality of simulated user portraits into a preliminary strategy for analysis and simulation, and generating a simulated strategy includes:

[0029] Extract key feature points of the behavior data in the user portrait through NLP, and retrieve text data containing the key feature points in the previous time period in the online database;

[0030] The changing trend of demand preference in the next time period in the text data is obtained through NLP, and weights are allocated according to the changing trend of demand preference in the next time period to generate several simulated user portraits, import the initial strategy for analysis and simulation, and generate a simulation strategy.

[0031] By adopting the above technical solutions, the networked database can collect information on the Internet or market data information provided by users, access and analyze broader and richer information sources, improve the accuracy and comprehensiveness of market trend forecasts, use NLP to analyze the obtained text information, and extract key feature points similar to the behavioral data in the original user portrait to obtain the changing trend of demand preferences between the current and original user portraits in the next time period.

[0032] In a preferred example, the present application may be further configured as follows: the step of collecting the user behavior data, transaction data and logistics data of the user for running the implementation strategy and updating and optimizing the preset strategy details includes:

[0033] Generate the actual weight ratio based on the user behavior data, transaction data and logistics data after the user runs the implementation strategy;

[0034] The actual weight ratio is fitted with the decision weight ratio, and the fitted weight ratio is updated to the preset policy details of the original user portrait.

[0035] By adopting the above technical solution, user portraits can be updated in real time so as to make personalized adjustments to policy details.

[0036] In a preferred example, the present application can be further configured as follows: the step of generating the actual weight ratio according to the user behavior data, transaction data and logistics data after the user runs the implementation strategy includes:

[0037] Monitor the user profile in each acceptance time period and determine in real time whether the actual weight ratio has a sudden change. If the actual weight ratio has a sudden change, terminate the implementation of the strategy.

[0038] By adopting the above technical solution, it is possible to monitor user portraits during each time period of strategy implementation, discover abnormal changes that may affect the effectiveness of strategy implementation, and terminate the strategy implementation in a timely manner when it is found that the strategy is invalid or inefficient during execution, so as to avoid waste of resources and potential losses as much as possible.

[0039] In the second aspect, the present application provides an intelligent operation system, which adopts the following technical solutions:

[0040] An intelligent operation system, comprising:

[0041] A data collection module, which is used to obtain an original user portrait, which includes user behavior data, transaction data, and logistics data, and generate a decision weight ratio;

[0042] A strategy initialization module, which is used to match the decision weight ratio with preset strategy details and integrate them to generate a preliminary strategy;

[0043] A data analysis module, the data analysis module is used to generate a number of simulated user portraits according to market trends, import the simulated user portraits into the initial strategy for analysis and simulation, and generate a simulated strategy;

[0044] A strategy formulation module, wherein the strategy formulation module is used to output an implementation strategy based on the fit between the simulation strategy and the initial strategy;

[0045] The feedback optimization module is used to collect the user behavior data, transaction data and logistics data of the user in running the implementation strategy, and update and optimize the preset strategy details.

[0046] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0047] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned intelligent operation method when executing the computer program.

[0048] In a fourth aspect, the present application provides a computer storage medium, the following technical solution:

[0049] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned intelligent operation method are implemented.

[0050] In summary, this application has the following beneficial technical effects:

[0051] This application forms a preliminary strategy by analyzing user demand and behavior data, combining it with predicted market trends, and accurately matching the corresponding policy details. It can also create multiple simulated user portraits to test and optimize the preliminary strategy, ensure the rationality of resource allocation, and thus improve the feasibility of the strategy. It not only improves the efficiency of actual operations, but also can dynamically adjust the operating strategy based on real-time data and market feedback, minimizing the cost increase caused by market fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart of an intelligent operation method in one embodiment of the present application.

[0053] Figure 2 It is a sub-step flow chart of step S1 in one embodiment of the present application.

[0054] Figure 3 This is a flowchart of steps added before step S13 in one embodiment of the present application.

[0055] Figure 4 It is a sub-step flow chart of step S3 in one embodiment of the present application.

[0056] Figure 5 It is a sub-step flow chart of step S3 in another embodiment of the present application.

[0057] Figure 6 It is a sub-step flow chart of step S5 in one embodiment of the present application.

[0058] Figure 7 It is a sub-step flow chart of step S51 in one embodiment of the present application.

[0059] Figure 8 It is a structural diagram of an intelligent operation system according to one embodiment of the present application.

[0060] Fig. 9 It is a principle block diagram of an electronic device in one embodiment of the present application.

[0061] Description of the accompanying drawings: 1. Data collection module; 2. Strategy initialization module; 3. Data analysis module; 4. Strategy formulation module; 5. Feedback optimization module. DETAILED DESCRIPTION

[0062] The following is combined with Figure 1-9 This application is described in further detail.

[0063] refer to Figure 1 , an intelligent operation method, specifically comprising:

[0064] S1. Obtain the original user portrait, which includes user behavior data, transaction data and logistics data, and generate a decision weight ratio.

[0065] Specifically, the decision weight ratio refers to the degree of user's inclination towards a certain demand in the original user portrait. According to the degree of inclination of the demand, it mainly includes:

[0066] User behavior weight assigns weights to user behavior data based on their behavior patterns on the platform, such as browsing, clicking, searching, dwell time, purchasing preferences, etc.

[0067] Transaction data weight: Assign weights based on the user’s purchase history, transaction frequency, purchase amount and other transaction data.

[0068] Logistics data weight: Consider logistics factors such as the user’s geographic location, delivery speed, return rate, and assign weights to these data.

[0069] The user behavior weight, transaction data weight and logistics data weight of a certain demand are normalized to obtain a standardized ratio, that is, the tendency degree of a certain demand. The tendency degrees of all demands in the original user portrait are then weighted to obtain the decision weight ratio.

[0070] The main reference data are the above three weights, but are not limited to adjusting the decision weight ratio based on influencing factors such as product or service weight, product or service weight, risk factor weight, strategic goal weight, etc.

[0071] S2. Match the decision weight ratio with the preset strategy details and integrate them to generate a preliminary strategy.

[0072] Specifically, the preset strategy details include provisions on how to allocate resources among different strategies and user groups, such as marketing budgets, inventory, etc. The decision weight ratio can adjust the weight distribution in the strategy details to maximize key performance indicators.

[0073] S3. Generate several simulated user portraits according to market trends, import the simulated user portraits into the initial strategy for analysis and simulation, and generate a simulated strategy.

[0074] Specifically, based on the market trends of the original user portrait, as well as consumer behavior, competitor dynamics, economic indicators, industry reports, etc., a simulated user portrait that is similar to the original user portrait and has representative characteristics is generated. The simulated user portrait is the tolerance for slight changes in the original user portrait. The simulation strategy generated based on several simulated user portraits is the strategy executed when slight changes occur in the original user portrait.

[0075] S4. Based on the fit between the simulation strategy and the initial strategy, the output is the implementation strategy.

[0076] Specifically, the strategy details in the simulation strategy are compared with the strategy details in the initial strategy, the data therein are fitted, and the output is the implementation strategy.

[0077] S5. Recover the user behavior data, transaction data and logistics data of the user for the implementation of the strategy, and update and optimize the preset strategy details.

[0078] In this embodiment, user needs and behavior data are taken into consideration, and a preliminary strategy is formed by matching the original user profile to the corresponding policy details. Combined with the key external factor of predicted market trends, a series of simulated user profiles are created. These simulated user profiles are similar to the original user profiles in characteristics and are used to test and optimize the preliminary strategy.

[0079] By launching several simulated user portraits in a simulation environment, running the initial strategy, and analyzing the interaction between the simulated users and the initial strategy, the allocation of resources in the strategy details can be optimized, thereby enhancing the feasibility of the strategy based on external factors and improving the efficiency of actual operations. It can also evaluate potential costs and benefits in a controlled environment before actually implementing the strategy, which helps to reduce costs in actual operations.

[0080] At the same time, when users actually implement the implementation strategy, dynamic adjustments to the implementation strategy based on real-time data and market feedback will help to respond to market changes in a timely manner, reduce the increase in operating costs caused by market fluctuations, and ensure that operational activities can continue to effectively adapt to the changing market environment.

[0081] refer to Figure 2 Further, in one embodiment, step S1 is refined into the following sub-steps:

[0082] S11. Analyze user behavior data and determine user demand preferences.

[0083] Specifically, by analyzing users' behavioral data on the platform, such as browsing, searching, clicking, and dwell time, we can identify users' interests and preferences for each product or service and obtain demand preference tendencies.

[0084] S12. Assign weights to the transaction data based on demand preferences to generate a demand weight ratio for the original user portrait.

[0085] Specifically, weight allocation allows each demand preference tendency to be combined with transaction data and given a higher priority according to its importance, which helps to highlight transactions that have a greater impact on user demand satisfaction and optimize resource allocation, such as marketing budgets, inventory management, etc.

[0086] S13. Match the geographical location in the logistics data to the pre-divided geographical area, and obtain the preset local demand weight ratio of the corresponding geographical area.

[0087] S14. Fitting is performed according to the demand quantity weight ratio and the local demand weight ratio to generate a decision weight ratio.

[0088] In this embodiment, the decision weight ratio takes into account the effectiveness and pertinence of the strategic planning according to user needs and geographical area characteristics, thereby improving the comprehensiveness and accuracy of the decision. The geographic location information in the logistics data is then matched with the preset geographical area in a targeted manner, and the local demand weight ratio is used to identify the specific needs of users in different regions, providing data support for the formulation of regional market strategies.

[0089] In addition, reference Figure 3 Furthermore, before step S13, steps S131 and S132 are added:

[0090] S131. Obtain the demand weight ratio of several simulated user portraits within a time period in the geographical area where the logistics data is located.

[0091] Specifically, after determining the geographical area to which the logistics data belongs and matching it with the pre-divided geographical areas, the user needs and consumption patterns of different geographical areas are identified based on several historical simulated user portrait data, and more precise marketing and logistics strategies are customized to improve efficiency and user satisfaction.

[0092] S132. Fit the demand weight ratios of several simulated user portraits to generate the local demand weight ratios of the corresponding geographical areas.

[0093] Specifically, the demand weight ratios of several simulated user portraits are normalized and then fitted to generate a more accurate local demand weight ratio.

[0094] In this embodiment, by analyzing the historical simulated user portraits of each geographical area, the demand weight ratio is obtained, and then the market demand of each geographical area is obtained, so that resource allocation is more reasonable, the distribution plan is optimized, and the transportation cost is reduced to meet the personalized needs of users in each region.

[0095] In addition, reference Figure 4 Further, in one embodiment, step S3 is refined into the following sub-steps:

[0096] S31. Generate an implementation weight ratio by randomly selecting several simulated user portraits and copying several original user portraits for trial operation simulation.

[0097] Specifically, randomly selecting a number of simulated user portraits can simulate the randomness of changes in the original user portraits, and the user behavior data, transaction data, and logistics data collected during the simulated operation process during the trial operation can be used to calculate the implementation weight ratio.

[0098] S32. Redistribute the weights of the strategy details in the initial strategy according to the implementation weight ratio, and output it as a simulation strategy.

[0099] Specifically, according to the implementation weight ratio, adjust the weight of each strategy detail in the initial strategy in order to achieve better strategy effects.

[0100] In this embodiment, the trial operation simulation of the simulated user portrait and the original user portrait is combined to dynamically adjust the simulation results to obtain the implementation weight ratio. The implementation weight ratio can dynamically redistribute the weights of the policy details, and the generated simulation policy can adaptively adjust the changes in the original user portrait, thereby improving the adaptability, effectiveness and flexibility of the policy and optimizing resource allocation.

[0101] In addition, reference Figure 5 Further, in another embodiment, step S3 is refined into the following sub-steps:

[0102] S33. Extract key feature points of the behavior data in the user portrait through NLP, and retrieve text data containing the key feature points in the previous time period from the online database.

[0103] Specifically, natural language processing technology is applied to screen the retrieved text data focusing on user demand trends, transaction data, and logistics data, and then the screened text data is preprocessed, including cleaning, denoising, word segmentation, etc., to prepare for subsequent analysis.

[0104] S34. Obtain the changing trend of demand preference in the next time period from the text data through NLP, and assign weights according to the changing trend of demand preference in the next time period, generate several simulated user portraits, import the initial strategy for analysis and simulation, and generate a simulation strategy.

[0105] Specifically, identify the changing trends of user demand tendencies, transaction data, and logistics data, such as the increase or decrease in user interest in a product or service, and adjust the behavioral weight, transaction weight, and logistics weight of each demand in the original user portrait according to the proportion of increase or decrease to generate several simulated user portraits.

[0106] In addition, reference Figure 6 Further, in one embodiment, step S5 is refined into the following sub-steps:

[0107] S51. Generate an actual weight ratio based on the user behavior data, transaction data and logistics data after the user runs the implementation strategy.

[0108] S52: Fit the actual weight ratio with the decision weight ratio, and update the fitted weight ratio to the preset policy details of the original user portrait.

[0109] In this embodiment, the actual weight ratio provides direct feedback on the effectiveness of the implemented strategy. By monitoring key performance indicators and adjusting the strategy in a timely manner according to the actual weight ratio, the user profile can be updated in real time to personalize and optimize the strategy details.

[0110] In addition, reference Figure 7 Further, in one embodiment, step S51 is refined into the following sub-steps:

[0111] S511. Monitor the user profile in each acceptance time period and determine in real time whether the actual weight ratio has a sudden change. If the actual weight ratio has a sudden change, terminate the implementation of the strategy.

[0112] In this embodiment, by real-time monitoring of user profiles that are executing the implementation strategy, abnormal changes that may affect the effectiveness of the implementation strategy can be discovered during the monitoring process, thereby reducing the waste of resources and potential losses caused by uncontrollable factors such as market trends and huge changes in user profiles.

[0113] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0114] The embodiment of the present application also provides an intelligent operation system, which corresponds one-to-one to the intelligent operation method in the embodiment.

[0115] refer to Figure 8 The intelligent operation system includes: data collection module 1, strategy initialization module 2, data analysis module 3, strategy formulation module 4, feedback optimization module 5. The detailed description of each functional module is as follows:

[0116] Data collection module 1, data collection module 1 is used to obtain original user portraits, which include user behavior data, transaction data and logistics data, and generate decision weight ratios.

[0117] The strategy initialization module 2 is used to match the decision weight ratio with the preset strategy details and integrate them to generate a preliminary strategy.

[0118] Data analysis module 3 is used to generate a number of simulated user portraits according to market trends, import the simulated user portraits into the initial strategy for analysis and simulation, and generate a simulated strategy.

[0119] Strategy formulation module 4, strategy formulation module 4 is used to output the implementation strategy based on the fit between the simulation strategy and the initial strategy.

[0120] Feedback optimization module 5: Feedback optimization module 5 is used to collect user behavior data, transaction data and logistics data of users for running implementation strategies, and update and optimize preset strategy details.

[0121] Among them, the data collection module 1 is responsible for collecting the original user portrait, including user behavior data, transaction data, logistics data, etc., to calculate the decision weight ratio. The strategy preliminary module 2 calls and allocates the preset strategy details according to the decision weight ratio, adjusts the weight of each strategy detail, and then integrates to generate the preliminary strategy. The data analysis module 3 analyzes and simulates the preliminary strategy and the simulated user portrait. The generated simulation strategy is fitted and learned with the preliminary strategy through the strategy formulation module 4, and a real-time strategy that is more in line with the original user portrait can be obtained. The feedback optimization module 5 can monitor the implementation of the strategy, continuously update the user portrait, and then update and optimize the preset strategy details, and can promptly discover invalid or inefficient situations generated during the implementation process.

[0122] For the specific definition of the intelligent operation system, please refer to the definition of the intelligent operation method in the context, which will not be repeated here. Each module in the above intelligent operation system can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the electronic device in hardware form, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0123] In one embodiment, an electronic device is provided, where the electronic device is a user terminal. Fig. 9, the electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a detection data table. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent operation method is implemented.

[0124] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0125] S1. Obtain the original user portrait, which includes user behavior data, transaction data and logistics data, and generate a decision weight ratio.

[0126] S2. Match the decision weight ratio with the preset strategy details and integrate them to generate a preliminary strategy.

[0127] S3. Generate several simulated user portraits according to market trends, import the simulated user portraits into the initial strategy for analysis and simulation, and generate a simulated strategy.

[0128] S4. Based on the fit between the simulation strategy and the initial strategy, the output is the implementation strategy.

[0129] S5. Recover the user behavior data, transaction data and logistics data of the user for the implementation of the strategy, and update and optimize the preset strategy details.

[0130] In one embodiment, the sub-steps refined in step S1 are:

[0131] S11. Analyze user behavior data and determine user demand preferences.

[0132] S12. Assign weights to the transaction data based on demand preferences to generate a demand weight ratio for the original user portrait.

[0133] S13. Match the geographical location in the logistics data to the pre-divided geographical area, and obtain the preset local demand weight ratio of the corresponding geographical area.

[0134] S14. Fitting is performed according to the demand quantity weight ratio and the local demand weight ratio to generate a decision weight ratio.

[0135] The steps added before step S13 are:

[0136] S131. Obtain the demand weight ratio of several simulated user portraits within a time period in the geographical area where the logistics data is located.

[0137] S132. Fit the demand weight ratios of several simulated user portraits to generate the local demand weight ratios of the corresponding geographical areas.

[0138] In one embodiment, the sub-steps of step S3 include:

[0139] S31. Generate an implementation weight ratio by randomly selecting several simulated user portraits and copying several original user portraits for trial operation simulation.

[0140] S32. Redistribute the weights of the strategy details in the initial strategy according to the implementation weight ratio, and output it as a simulation strategy.

[0141] In another embodiment, the sub-steps of step S3 include:

[0142] S33. Extract key feature points of the behavior data in the user portrait through NLP, and retrieve text data containing the key feature points in the previous time period from the online database.

[0143] S34. Obtain the changing trend of demand preference in the next time period from the text data through NLP, and assign weights according to the changing trend of demand preference in the next time period, generate several simulated user portraits, import the initial strategy for analysis and simulation, and generate a simulation strategy.

[0144] In one embodiment, the sub-steps of step S5 include:

[0145] S51. Generate an actual weight ratio based on the user behavior data, transaction data and logistics data after the user runs the implementation strategy.

[0146] S52: Fit the actual weight ratio with the decision weight ratio, and update the fitted weight ratio to the preset policy details of the original user portrait.

[0147] In one embodiment, the sub-steps of step S51 include:

[0148] S511. Monitor the user profile in each acceptance time period and determine in real time whether the actual weight ratio has a sudden change. If the actual weight ratio has a sudden change, terminate the implementation of the strategy.

[0149] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0150] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. An intelligent operation method, characterized in that: include: Obtaining an original user portrait, wherein the original user portrait includes user behavior data, transaction data, and logistics data, and generating a decision weight ratio; Matching the decision weight ratio with the preset strategy details, and integrating them to generate a preliminary strategy; Generate a number of simulated user portraits according to market trends, import the simulated user portraits into the initial strategy for analysis and simulation, and generate a simulated strategy; According to the fit between the simulation strategy and the initial strategy, the output is the implementation strategy; The user behavior data, transaction data and logistics data of the user for running the implementation strategy are collected, and the preset strategy details are updated and optimized.

2. The method according to claim 1, characterized in that The step of obtaining the original user portrait, which includes user behavior data, transaction data and logistics data, and generating a decision weight ratio includes: Analyze the user behavior data to determine the user's demand preferences; The transaction data is weighted according to the demand preference to generate a demand weight ratio of the original user portrait; Matching the geographical location of the delivery address in the logistics data to the pre-divided geographical area, and obtaining the preset local demand weight ratio of the corresponding geographical area; The demand quantity weight ratio and the local demand weight ratio are fitted to generate a decision weight ratio.

3. The method according to claim 2, characterized in that Before the step of matching the geographical location of the delivery address in the logistics data to the pre-divided geographical area and obtaining the preset local demand weight ratio of the corresponding geographical area, the method further includes: Obtaining demand weight ratios of several simulated user portraits within a time period in the geographical area where the logistics data is located; The demand weight ratios of several simulated user portraits are fitted to generate the local demand weight ratios of the corresponding geographical areas.

4. The method according to claim 1, characterized in that: The step of generating a plurality of simulated user portraits according to market trends, importing the plurality of simulated user portraits into a preliminary strategy for analysis and simulation, and generating a simulated strategy includes: After a trial operation simulation, generate the implementation weight ratio by randomly selecting several simulated user portraits and copying several original user portraits; According to the implementation weight ratio, the weights of the policy details in the initial policy are redistributed and output as a simulation policy.

5. The method according to claim 1, characterized in that: The step of generating a plurality of simulated user portraits according to market trends, importing the plurality of simulated user portraits into a preliminary strategy for analysis and simulation, and generating a simulated strategy includes: Extract key feature points of the behavior data in the user portrait through NLP, and retrieve text data containing the key feature points in the previous time period in the online database; The changing trend of demand preference in the next time period in the text data is obtained through NLP, and weights are allocated according to the changing trend of demand preference in the next time period to generate several simulated user portraits, import the initial strategy for analysis and simulation, and generate a simulation strategy.

6. The method according to claim 1, characterized in that The step of reclaiming the user's user behavior data, transaction data and logistics data for running the implementation strategy and updating and optimizing the preset strategy details includes: Generate the actual weight ratio based on the user behavior data, transaction data and logistics data after the user runs the implementation strategy; The actual weight ratio is fitted with the decision weight ratio, and the fitted weight ratio is updated to the preset policy details of the original user portrait.

7. The method according to claim 6, characterized in that The step of generating the actual weight ratio according to the user behavior data, transaction data and logistics data after the user runs the implementation strategy includes: Monitor the user profile in each acceptance time period and determine in real time whether the actual weight ratio has a sudden change. If the actual weight ratio has a sudden change, terminate the implementation of the strategy.

8. An intelligent operation system, characterized in that: include: A data collection module (1), the data collection module (1) is used to obtain an original user portrait, the original user portrait includes user behavior data, transaction data and logistics data, and generate a decision weight ratio; A strategy initialization module (2), the strategy initialization module (2) is used to match the decision weight ratio with the preset strategy details, and integrate and generate a preliminary strategy; A data analysis module (3), the data analysis module (3) is used to generate a number of simulated user portraits according to market trends, import the simulated user portraits into the initial strategy for analysis and simulation, and generate a simulated strategy; A strategy formulation module (4), wherein the strategy formulation module (4) is used to output an implementation strategy based on the fit between the simulation strategy and the initial strategy; A feedback optimization module (5), wherein the feedback optimization module (5) is used to collect user behavior data, transaction data and logistics data of users in running the implementation strategy, and to update and optimize the preset strategy details.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes any one of the intelligent operation methods according to claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and executes the intelligent operation method according to any one of claims 1 to 7.

Images