Marketing business configuration method and device, storage medium, equipment and product

Abstract

The invention provides a marketing business configuration method and device, a storage medium, equipment and a product. The method comprises the steps of obtaining dialogue information input by a user for a marketing service, and performing semantic analysis on the dialogue information to determine service scene information corresponding to the marketing service; according to the business scene information, determining a target configuration rule required for configuring the marketing business in a preset configuration rule library, and determining historical configuration preference information matched with the business scene information in a historical preference library of the user; and under an information generation mode and constraint conditions specified by the target configuration rule, through a preset configuration recommendation model, generating configuration information matched with the historical configuration preference information and suitable for the marketing business.

Description

Technical Field

[0001] This specification relates to one or more embodiments in the field of terminal technology, and more particularly to a configuration method, apparatus, storage medium, device and product for a marketing business. Background Technology

[0002] With the rapid development of the digital economy, marketing has become a core means for enterprises to increase user base and promote services or products. Various marketing activities typically require configuring multiple settings such as budget allocation, campaign frequency control, target audience selection, and channel settings. The rationality and accuracy of these settings directly determine the marketing effectiveness.

[0003] However, the existing configuration methods for marketing operations mainly rely on manual operation by operations personnel based on past experience. This requires operations personnel to input a large number of parameters one by one, resulting in low configuration efficiency. Furthermore, relying solely on manual experience is prone to configuration errors, leading to the marketing resource allocation accuracy not meeting expectations, ultimately affecting the effectiveness of marketing campaigns, and even increasing the company's operating costs and decision-making risks. Summary of the Invention

[0004] In view of the above, one or more embodiments of this specification provide the following technical solutions: According to a first aspect of one or more embodiments of this specification, a method for configuring a marketing operation is provided, comprising: Obtain dialogue information input by users regarding marketing activities; Semantic parsing of the dialogue information is performed to determine the business scenario information corresponding to the marketing business; Based on the business scenario information, the target configuration rules required for configuring the marketing business are determined in the preset configuration rule library, and the historical configuration preference information that matches the business scenario information is determined in the user's historical preference library. Under the information generation method and constraints specified by the target configuration rules, configuration information matching the historical configuration preference information is generated through a preset configuration recommendation model.

[0005] According to a second aspect of one or more embodiments of this specification, a configuration apparatus for a marketing operation is provided, comprising: The acquisition unit is used to acquire dialogue information input by the user regarding marketing activities; The parsing unit performs semantic parsing on the dialogue information to determine the business scenario information corresponding to the marketing business. The determining unit is configured to determine, based on the business scenario information, the target configuration rules required for configuring the marketing business in a preset configuration rule library, and to determine the historical configuration preference information that matches the business scenario information in the user's historical preference library. The configuration unit is used to generate configuration information matching the historical configuration preference information through a preset configuration recommendation model under the information generation method and constraints specified by the target configuration rule.

[0006] According to a third aspect of one or more embodiments of this specification, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor implements the steps of the method described above by executing the executable instructions.

[0007] According to a fourth aspect of one or more embodiments of this specification, a computer-readable storage medium is provided that stores computer instructions thereon, which, when executed by a processor, implement the steps of the method described above.

[0008] According to a fifth aspect of one or more embodiments of this specification, a computer program product is provided, comprising a computer program / instructions that, when executed by a processor, implement the steps of the method described above.

[0009] As can be seen from the above embodiments, in the process of configuring marketing operations, this specification parses the corresponding business scenario information based on the user's dialogue information, and then matches the corresponding target configuration rules and the user's historical preference information. In this way, configuration information can be automatically generated according to the adaptation of target configuration rules and historical preference information, which not only meets the core needs of the business scenario, but also matches the user's personalized preferences, thereby improving configuration efficiency and accuracy, optimizing the effect of marketing resource placement, and effectively reducing enterprise operating costs and decision-making risks. Attached Figure Description

[0010] Figure 1 This is a schematic diagram of the architecture of a configuration service system for a marketing business, provided in an exemplary embodiment. Figure 2 This is a flowchart illustrating a configuration method for a marketing business as provided in an exemplary embodiment; Figure 3 This is an exemplary embodiment providing an overall configuration flowchart for a marketing business; Figure 4 This is a schematic diagram of a marketing configuration system architecture provided in an exemplary embodiment; Figure 5 This is a schematic diagram of the structure of a device provided in an exemplary embodiment; Figure 6 This is a block diagram of a configuration apparatus for a marketing operation provided in an exemplary embodiment. Detailed Implementation

[0011] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0012] In the implementation of marketing campaigns, parameter configuration, as a core technical aspect affecting marketing effectiveness, requires the coordinated setting of multiple dimensions of technical parameters, such as budget allocation, ad frequency control, target user tagging, and promotion channel prioritization. These parameters are dynamically coupled; for example, the budget allocation ratio needs to be adapted to the target user group size and ad frequency, and must be dynamically adjusted based on real-time marketing feedback data to adapt to the personalized needs of different industry application scenarios and marketing objectives, thereby achieving precise allocation and efficient utilization of marketing resources.

[0013] However, existing intelligent marketing campaign parameter configuration solutions still rely on manual configuration, where operations personnel manually input parameters based on their personal experience. On one hand, this manual configuration method requires operations personnel to manually enter massive amounts of technical parameters one by one, resulting in low efficiency when dealing with multi-scenario, multi-batch concurrent marketing campaigns. On the other hand, due to the complex coupling relationships between parameters, relying solely on manual experience for parameter configuration is prone to errors. For example, a mismatch between budget and ad frequency leads to wasted marketing resources, or incomplete target user tagging results in insufficient marketing accuracy, ultimately leading to poor campaign performance and increasing operational costs and decision-making risks for the enterprise.

[0014] Based on this, this manual provides a configuration method for marketing operations, which automatically generates configuration information according to target configuration rules that match the input information and the user's historical preference information, thereby improving configuration efficiency and accuracy.

[0015] Figure 1 This is a schematic diagram of the architecture of a configuration service system for a marketing business, provided as an exemplary embodiment. For example... Figure 1 As shown, the system may include a server 11, a network 12, and several electronic devices, such as a personal computer (PC) 13, a mobile phone 14, etc.

[0016] Server 11 can be a physical server containing an independent host, or it can be a virtual server hosted in a host cluster. During operation, server 11 can run server-side programs for a certain application to implement the relevant functions of that application. For example, when server 11 runs a configuration service program, it can function as a corresponding configuration service platform.

[0017] PC13 and mobile phone14 are just some of the types of electronic devices that users can use. In reality, users can obviously also use electronic devices such as tablets, laptops, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smartwatches, etc.), etc., and one or more embodiments in this specification do not limit this. During operation, the electronic device can run a client-side program of an application to implement the relevant functions of that application. For example, when the electronic device runs a configuration service program, it can act as a client for that configuration service. The client application of the aforementioned configuration service can be launched and run on the electronic device. This client-side program can be a native application installed on the electronic device, or it can be a mini-program, quick app, or other similar form. Of course, when using web technologies such as HTML5, the relevant functions can be implemented through a page displayed by a browser. This browser can be a standalone browser application or a browser module embedded in some applications.

[0018] As for the network 12 that enables interaction between electronic devices such as PC13 and mobile phone 14 and server 11, communication can be achieved using either wired or wireless networks, depending on the communication methods supported by the respective electronic devices. This specification does not impose any restrictions on this. For example, PC13 can support both wired and wireless communication, so it can use either wired or wireless networks as needed. Mobile phone 14 typically only supports wireless communication, so it can use a wireless network for communication.

[0019] Based on the above configuration service system architecture, this manual provides a configuration method for marketing operations, such as... Figure 2 As shown.

[0020] Figure 2 This is a schematic flowchart of a marketing business configuration method provided in an exemplary embodiment, including the following steps: S200: Obtain dialogue information input by the user regarding marketing activities; S202: Perform semantic parsing on the dialogue information to determine the business scenario information corresponding to the marketing business.

[0021] In this manual, the execution subject of the configuration method for performing marketing operations can be a server, or a device such as a mobile phone, tablet, laptop, desktop computer, or smart terminal, or a client installed on these devices. For ease of description, the following will use the client as the execution subject to explain the configuration method of the marketing operations provided in this manual.

[0022] During the configuration of marketing operations, the client can show users configuration options for automatic and manual configuration. If the user selects the automatic configuration option, a dialog page is then displayed to the user to obtain the dialogue information related to the marketing operations entered by the user on the dialog page.

[0023] The client can then use a language model to perform semantic parsing of the dialogue information to determine the business scenario information corresponding to the marketing business.

[0024] Furthermore, the above process can be implemented through a marketing agent pre-deployed on the client side. This marketing agent can be an agent (i.e., an agent based on a language model (such as a Large Language Model, LLM)). Users can raise marketing business configuration requirements by communicating with the marketing agent, and then the marketing agent can extract the corresponding business scenario information based on the semantic parsing capability of the language model.

[0025] The business scenario information may include the business objects and marketing objectives corresponding to the marketing business. The business objects are used to characterize the core service object attributes and supply and demand matching mode of the marketing activities, such as consumer marketing (B2C), enterprise marketing (B2B), platform ecosystem marketing (B2B2C), etc. Of course, it can also be the subdivided customer group type under specific industry fields (such as retail industry, financial industry, education industry, etc.). Marketing objectives define the core implementation direction and expected goals of marketing activities, such as increasing product awareness, enhancing user acceptance of the product, increasing user activity, increasing Gross Merchandise Volume (GMV), optimizing return on investment, and improving customer lifetime value.

[0026] In addition, the above business scenario information may also include other information such as marketing methods (e.g., online / offline) and marketing channels (e.g., telephone, social media, short video platforms, email, SMS, instant messaging (IM)). This specification does not make specific limitations.

[0027] For example, the dialogue information entered by the user could be: "The marketing business plan targets working professionals aged 25-35. It will promote xxx retail products through e-commerce platform flagship stores, social media live streaming, and community marketing channels. The core objective is to increase product market awareness and enhance user recognition."

[0028] The business scenario information parsed from this dialogue can be as follows: the business target is consumer marketing (B2C), the marketing goal is to increase product market awareness and enhance user recognition, the marketing method is online marketing, the marketing channels are e-commerce platforms, social media live streaming, and community marketing, and the industry sector is the retail industry.

[0029] S204: Based on the business scenario information, determine the target configuration rules required for configuring the marketing business in the preset configuration rule library, and determine the historical configuration preference information that matches the business scenario information in the user's historical preference library.

[0030] The client can determine the target configuration rules required to configure the marketing business in the configuration rule base according to the business object. The target configuration rules are used to define the information generation method and constraints of the configuration information corresponding to each configuration item of the marketing business. Different configuration rules correspond to different business objects.

[0031] The configuration items for marketing operations include the execution conditions that marketing operations need to meet, such as budget amount, target audience (such as user groups corresponding to different occupations and ages), marketing campaign timing, marketing campaign frequency, marketing channel priority, conversion target threshold, user online rate, activity geographic scope, and creative content theme specifications.

[0032] For example, when the target audience is the general public, the configuration rules for the budget amount can be as follows: based on past operational data of the same type, first calculate the average budget amount per user under this type, and then calculate the budget amount by rounding up to the nearest ten thousand yuan after converting it with the current population size, with a minimum amount of 20,000 yuan; if there is no past operational data of the same type, then directly recommend a budget range of 50,000 yuan.

[0033] For example, when the target audience is users in the retail industry, the configuration rules for the marketing campaign time can be as follows: determine the campaign time based on the age range and work type of the user group, and prioritize the time slots of 8:00-10:30 and 18:00-21:00 on weekdays and 9:00-22:00 on weekends; avoid core time periods such as morning commuting and evening housework, and start the campaign 2 days in advance for holidays.

[0034] Prior to this, configuration rules in the rule base can be pre-built. Users can input the description information of the configuration rules on the configuration information generation page. Then, the client can input the description information into the pre-trained rule generation model. The rule generation model can extract the information generation method and constraints contained in the rule description information, and convert the extracted information generation method and constraints into a structured rule configuration statement in the target format to obtain the target configuration rule and store it in the rule base.

[0035] The target format can be JEXL format. For example, the configuration rule description information entered by the user can be: GMV marketing campaign targeting the general public, calculated based on the historical average budget, with a minimum of 20,000 and a maximum of 500,000.

[0036] Analysis reveals that the information generation method for the "budget amount" configuration is: calculated based on the historical average budget; the constraints are: minimum 20,000 and maximum 500,000.

[0037] The resulting JEXL format configuration rules can be: That is: the recommended budget is calculated based on the user's historical average budget and the target number of users, and the result is rounded to the nearest ten thousand yuan, with a minimum of 20,000 yuan. If there is no historical data, the default is 50,000 yuan.

[0038] During the storage configuration rule process, the business scenario information corresponding to the configuration rule (such as "general public" and "GMV marketing activities" in the example above) can be feature-encoded, and a mapping relationship between its feature codes and JEXL format configuration rules can be established. In this way, during the configuration rule matching process, the matching configuration rule can be further determined based on the similarity between the feature representation of the business scenario information contained in the user input dialogue information and the feature codes in the above mapping relationship.

[0039] For example, if the similarity between the feature representation of the business scenario information contained in the user's input dialogue information and any feature code in the rule base is less than a preset threshold, then the configuration rule corresponding to that feature code is taken as the target configuration rule.

[0040] In addition, the rule base can store configuration rules built by multiple users. When the same business environment information corresponds to multiple configuration rules, a weight can be set for these configuration rules in advance. During the actual configuration of marketing business, the corresponding target configuration rule is returned to the client based on the weight, and the weight is updated as users use the configuration information (the process of weight updating will be described in detail below, and will not be elaborated on here). In practical applications, the above marketing business can correspond to only one configuration item or multiple configuration items, and each configuration item can correspond to multiple candidate configuration rules. In the process of determining the target configuration rule, for each configuration item of the marketing business, the candidate configuration rules corresponding to the configuration item can be determined in the configuration rule library according to the business scenario information. Then, based on the weights of each candidate configuration rule, at least one target configuration rule corresponding to the configuration item can be determined.

[0041] For example, the candidate configuration rule with the highest weight can be used as the target configuration rule, or one or more candidate configuration rules with a weight greater than the preset weight can be used as the target configuration rule.

[0042] At the same time, the client can determine the historical preference library bound to the user's user identification information, and determine the historical configuration preference information in its historical preference library according to the business object and marketing goal.

[0043] For example, if the target audience of this marketing campaign is the general public and the goal is to increase GMV, and the historical preference database records that the budget was set to X multiple times in previous campaigns with the same goal, then the budget X can be extracted as historical configuration preference information in this budget configuration to help the intelligent marketing engine refine the budget plan.

[0044] For example, if the target audience is users in the retail industry and the marketing goal is to increase user activity, and the historical preference database records that the campaign time was set to Y multiple times in past retail activities with the same goal, then the campaign time Y can be extracted as historical configuration preference information in the current campaign time configuration for retail users to optimize the time period selection.

[0045] In practical applications, historical preference information can be determined based on the number of times a user uses each configuration information within a certain period of time (see the example above for the process of determining historical preference information).

[0046] Alternatively, it can be determined based on the average of the configuration information used by the user when configuring related configuration items in the past. For example, if the average budget for a user when configuring marketing activities for the same marketing goals and business objects multiple times in the past is M, then the budget amount M can be used as the user's historical preference information for budget amount.

[0047] Of course, it can also be determined based on the configuration information used by the user when configuring the relevant configuration items most recently. For example, if the user set the budget amount to N when configuring the marketing business of the same marketing goal and business object last time, then the budget amount N will be used as the user's historical preference information for the budget amount.

[0048] It should be added that, in the actual process of determining the target configuration rules and historical user preferences, the client can determine the target configuration rules not only based on the business object, but also based on all the content in the business scenario information, and determine the target configuration rules in the configuration rule library and the corresponding historical configuration preferences in the user's historical preference library.

[0049] S206: Under the information generation method and constraints specified by the target configuration rule, configuration information matching the historical configuration preference information is generated through a preset configuration recommendation model.

[0050] After determining the target configuration rules and historical user preferences, the client can generate configuration information that matches historical configuration preference information and is suitable for marketing business through a preset configuration recommendation model, under the information generation method and constraints specified by the target configuration rules.

[0051] Specifically, the client can call rule processing functions (such as budget amount average calculation function, reach group size conversion function, and delivery time period priority sorting function, etc.) that match the logical characteristics of the target configuration rule in a preset function library. The target configuration rule is converted into executable code through the rule processing function. Then, based on the executable code and historical preference information, a prompt word input configuration recommendation model is built. Under the generation logic and function conditions defined by the above-mentioned executable code, the configuration recommendation model generates configuration information in combination with the user's historical preference information.

[0052] During the process of generating configuration information, the target configuration rules can provide a standardized generation framework and constraint boundaries for the configuration information, while historical preference information can provide the corresponding calculation basis and specific personalized parameter values ​​for the configuration rules.

[0053] For example, for GMV marketing campaigns, the target configuration rules set a budget range of 50,000 to 150,000 yuan (i.e., constraints), and the rules also clearly state that the budget amount must be determined based on the number of people reached (i.e., generation method).

[0054] According to the user history preference database, the budget amounts for the three most recent GMV campaigns of the same type were as follows: reaching 8,000 people with a budget of 80,000 yuan; reaching 12,000 people with a budget of 120,000 yuan; and reaching 10,000 people with a budget of 100,000 yuan.

[0055] Therefore, we can obtain the user's historical reach scale preference as 10,000 people, and the corresponding budget preference as 100,000 yuan. This budget preference is calculated based on the average budget of 10 yuan per person in historical activities, which meets the information generation conditions stipulated by the target configuration rules and is within the budget range (50,000 to 150,000 yuan) stipulated by the target configuration rules, thus meeting the constraints stipulated by the target configuration rules. Therefore, we can generate configuration information for two configuration items: reach scale of 10,000 people and budget of 100,000 yuan.

[0056] In addition, since target configuration rules are often more in line with the enterprise's needs, while user preference information is only for personalized reference, corresponding priorities can be set for target configuration rules and user preference information respectively, and the priority of target configuration rules should be higher than that of user preference information. In this way, it can be ensured that the final generated configuration information complies with the business bottom line and industry standards, while taking into account the user's personalized operating habits.

[0057] Specifically, if the configuration parameter value in the user preference information is higher than the parameter value range constrained by the configuration rule, the highest value in that range will be used as the target parameter value in the configuration information; if the configuration parameter value in the user preference information is lower than the parameter value range constrained by the configuration rule, the lowest value in that range will be used as the target parameter value in the configuration information.

[0058] Continuing from the previous example, if the calculated user's budget preference is 200,000 yuan, which exceeds the budget range of 50,000 to 150,000 yuan defined by the target configuration rule, then the highest value (i.e., 150,000 yuan) will be taken as the budget configuration amount for this GMV activity; while if the calculated user's budget preference is 40,000 yuan, which is lower than the budget range of 50,000 to 150,000 yuan defined by the target configuration rule, then the lowest value (i.e., 50,000 yuan) will be taken as the budget configuration amount for this GMV activity.

[0059] Based on the above methods, the client can generate configuration information corresponding to each configuration item of the marketing business, and display this configuration information in the dialog window of the client or marketing agent through configuration cards, and configure the current marketing business according to the user's operation on this configuration information.

[0060] Specifically, if the user has no objection to all the configuration items displayed in the configuration card, they can configure the marketing business based on the corresponding configuration information in these configuration items through one-click confirmation, automatic saving, etc. In addition, the user can also modify the configuration information corresponding to each configuration item by sliding the drop-down menu and selecting preset parameter options, or entering specific values, thereby generating a marketing configuration plan that meets their own personalized needs.

[0061] Furthermore, during the process of users modifying the configuration information of configuration items, there are often interrelationships between some configuration items. For example, if the configuration rule stipulates that the budget amount must be determined based on the number of groups reached, then changes in the number of groups reached will directly affect the value of the budget amount, and conversely, adjustments to the budget amount will also change the upper limit of the number of groups reached.

[0062] Therefore, during the process of a user modifying the configuration information of any configuration item, the client can determine whether there is an associated configuration item based on the information generation conditions corresponding to the configuration rules. If there is, the configuration recommendation model will be used to regenerate the configuration information corresponding to the associated configuration item based on the information generation conditions and the user's modified configuration information.

[0063] For example, if the configuration rules specify a budget range of 50,000 to 150,000 yuan, and the generated configuration information for two items is: reach scale 10,000 people; budget 100,000 yuan, then when the user changes the reach scale to 2,000 people, the budget amount will also change accordingly.

[0064] When the reach is reduced from 10,000 to 2,000 people, the budget will be reduced from 100,000 yuan to 20,000 yuan. However, since the reduced budget of 20,000 yuan is lower than the minimum budget of 50,000 yuan, the minimum budget of 50,000 yuan will be set as the final budget amount.

[0065] Furthermore, when there are multiple target configuration rules, the configuration information generated under the information generation methods and constraints specified by different target configuration rules can be displayed through methods such as drop-down menus and lists to configure the marketing business in response to the user's selection operation on the multiple displayed configuration information.

[0066] Furthermore, the client can update the historical configuration preference information based on the user's usage of the configuration information, and store the updated historical configuration preference information in the historical preference library.

[0067] Specifically, if historical preference information is determined based on the number of times a user uses each configuration information within a certain period, then the configuration information finally confirmed by the user this time will be included in the usage frequency statistics of the corresponding period. If the configuration information is used for the first time, the frequency will be recorded as 1; if it is not used for the first time, the frequency will be incremented by 1. At the same time, historical usage records that exceed the statistical period will be removed. If the historical preference information is determined based on the average of the configuration information used by the user in the past when configuring the relevant configuration items, then the configuration information value finally confirmed by the user this time will be included in the average calculation sample, and the average of all valid samples including the current data will be recalculated to cover the original historical average data. If the historical preference information is determined based on the configuration information used by the user when configuring the relevant configuration items most recently, then the original "most recent" historical record will be directly replaced with the configuration information finally confirmed by the user this time, so as to ensure that the preference information always retains the latest configuration value.

[0068] Meanwhile, the client can update the weights of each candidate configuration rule based on the usage of configuration information generated by multiple users for different target configuration rules of the same configuration item.

[0069] Specifically, for each target configuration rule, if during the actual marketing activity configuration process within a specified statistical period, the number of users whose configuration information is generated using this target configuration rule is greater than the number of users whose configuration information is generated using other target configuration rules, and / or the number of users whose configuration information is generated using this target configuration rule is greater than a preset number, then the weight corresponding to this target configuration rule is increased.

[0070] It should be noted that, compared to users' historical preference information, configuration rules have stronger industry universality and applicability. Therefore, it is necessary to dynamically optimize the recommendation priority of configuration rules based on the actual usage feedback and selection preferences of multiple users, so that the rules can better meet the real business needs of most users.

[0071] Once the marketing operations are configured, marketing operations can be generated and executed based on the configuration information of the marketing operations.

[0072] It should be added that the rule generation model and configuration recommendation model mentioned above can be the same LLM. Of course, they can also be two different business models trained on their respective training samples based on a pre-trained LLM.

[0073] For training the rule generation model, users' historical description information can be used as training samples, and the configuration rules generated based on the historical description information can be used as sample labels. Then, the training samples are input into the rule generation model to obtain the generated predicted configuration rules. After that, a loss value is constructed based on the deviation between the predicted configuration rules and the sample labels, and the model parameters of the rule generation model are adjusted based on the loss value.

[0074] For configuration recommendation models, historical configuration rules and users' historical configuration preferences can be used as training samples, and the historical configuration rules generated based on this information can be used as sample labels. Then, the training samples are input into the configuration recommendation model to obtain the generated predicted configuration information. After that, a loss value is constructed based on the deviation between the predicted configuration information and the sample labels, and the model parameters of the configuration recommendation model are adjusted based on the loss value.

[0075] To facilitate understanding, this manual provides an overall configuration flowchart for the marketing operation, such as... Figure 3 As shown.

[0076] The configuration process for marketing operations includes the following steps: S300: Acquire user conversation information and parse out business scenario information for marketing operations from it; S302: Based on business scenario information, determine the target configuration rules and historical preference information in the rule base and user preference base respectively; S304: Call the rule processing function that matches the target configuration rule in the function library; S306: Execute the target configuration rule based on the rule processing function to generate configuration information that matches the historical configuration preference information and is applicable to the marketing business; S308: Displays configuration information for each configuration item through configuration cards; S310: How mobile phone users use various configuration information; S312: Update each configuration rule in the rule base according to the usage of each configuration information by multiple users, and update the historical preferences of an individual user in the historical preference database according to the usage of configuration information by that user.

[0077] Furthermore, the above methods can be implemented through corresponding marketing configuration systems, such as... Figure 4 As shown.

[0078] Figure 4 This is a schematic diagram of a marketing configuration system architecture provided in an exemplary embodiment.

[0079] The marketing configuration system 400 includes: a marketing agent 402, a rule matching processor 404, a preference injection processor 406, a rule execution engine 408, a result display processor 410, a feedback collector 412, a rule generation engine 414, a rule library 416, a user preference library 418, and a function library 420.

[0080] The marketing agent 402 is used to acquire user-inputted session information, parse out business environment information, and display configuration cards for each configuration item to the user. The rule matching processor 404 is used to match target configuration rules from the rule base 416 based on the business environment information and input them into the rule execution engine 408. The preference injection processor 406 is used to determine the user's historical preferences from the user preference base 418 and inject them into the rule execution engine 408. The rule execution engine 408 includes a configuration recommendation model, which calls corresponding rule processing functions from the function library 420 and executes target configuration rules based on the rule processing functions to generate configuration information that matches the historical configuration preference information and is suitable for the marketing business. The feedback collector 412 collects user usage of the configuration information and updates the weights of each configuration rule in the rule base 416 and the user's historical preferences in the user preference base 418. Additionally, the rule generation engine includes a rule generation model, which generates corresponding configuration rules based on user-input configuration rule description information and stores them in the rule base 416.

[0081] Figure 5 This is a schematic structural diagram of a device provided in an exemplary embodiment. For example... Figure 5 As shown, device 500 mainly consists of a communication interface 502, a user interface 504, a processor 506, and a data storage 508. These components are interconnected and communicate with each other via a system bus, network, or other connection mechanism 510. The communication interface 502 enables device 500 to communicate with other devices, access networks, and transmission networks via analog or digital modulation. For example, the communication interface 502 may include a chipset and antenna for wireless communication with a radio access network or access point. Furthermore, the communication interface 502 can be a wired interface such as Ethernet, Token Ring, or a USB port, or a wireless interface such as Wi-Fi, Bluetooth, Global Positioning System (GPS), or a wide-area wireless interface (e.g., WiMAX or LTE). Of course, the communication interface 502 can also support other forms of physical layer interfaces and standard or proprietary communication protocols. The communication interface 502 may also include multiple physical communication interfaces, such as Wi-Fi interfaces, Bluetooth interfaces, and wide-area wireless interfaces.

[0082] User interface 504 includes receiving user input and providing output to the user. Therefore, user interface 504 may include input components such as a keypad, keyboard, touch-sensitive or presence-sensitive panel, computer mouse, trackball, joystick, microphone, still camera, and video camera, and output components such as a display screen (which may be combined with a touch-sensitive panel), CRT, LCD, LED, display using DLP technology, printer, and other similar devices known or developed in the future. User interface 504 may also generate auditory output via speakers, speaker jacks, audio output ports, audio output devices, headphones, and other similar devices known or developed in the future. In some embodiments, user interface 504 may include software, circuitry, or other forms of logic capable of transmitting and receiving data from external user input / output devices. Additionally or alternatively, device 500 may support remote access from other devices via communication interface 502 or another physical interface (not shown). User interface 504 may be configured to receive user input, the position and movement of which may be indicated by indicators or cursors described herein. User interface 504 may also be configured as a display device for rendering or displaying text fragments.

[0083] Processor 506 may contain one or more general-purpose processors and / or special-purpose processors.

[0084] Data storage 508 may include one or more volatile and / or non-volatile storage components and may be integrated wholly or partially with processor 506. Data storage 508 may include removable and non-removable components.

[0085] Processor 506 is capable of executing program instructions 518 (e.g., compiled or uncompiled program logic and / or machine code) stored in data storage 508 to perform the various functions described herein. Data storage 508 may contain a non-transitory computer-readable medium on which program instructions are stored, which, when executed by device 500, enable device 500 to perform any methods, processes, or functions disclosed in this specification and / or the accompanying drawings. Execution of program instructions 518 by processor 506 may result in processor 506 using data 512.

[0086] For example, program instructions 518 may include an operating system 522 (e.g., an operating system kernel, device drivers, and / or other modules) installed on device 500 and one or more applications 520 (e.g., a browser, social application, or game application). Similarly, data 512 may include operating system data 516 and application data 514. Operating system data 516 is primarily accessible to the operating system 522, while application data 514 is primarily accessible to one or more applications 520. Application data 514 may reside in a file system visible or hidden from the user of device 500.

[0087] Application 520 can communicate with operating system 522 through one or more application programming interfaces (APIs). These APIs help application 520 read and / or write application data 514, transmit or receive information via communication interface 502, receive or display information on user interface 504, etc.

[0088] In some terminology, application 520 may be simply referred to as "app". Furthermore, application 520 can be downloaded to device 500 through one or more online app stores or app markets. However, applications can also be installed on device 500 in other ways, such as through a web browser or a physical interface on device 500 (e.g., a USB port).

[0089] Please refer to Figure 6 The configuration device for marketing operations can be applied to, for example... Figure 5 The device shown is used to implement the technical solution described in this specification. The configuration device for this marketing operation may include: Acquisition unit 600 is used to acquire dialogue information input by the user regarding marketing activities. The parsing unit 602 is used to perform semantic parsing on the dialogue information to determine the business scenario information corresponding to the marketing business; The determining unit 604 is used to determine the target configuration rule required to configure the marketing business in a preset configuration rule library based on the business scenario information, and to determine the historical configuration preference information that matches the business scenario information in the user's historical preference library. Configuration unit 606 is used to generate configuration information matching the historical configuration preference information through a preset configuration recommendation model under the information generation method and constraints specified by the target configuration rule.

[0090] Optionally, the device further includes: a generation unit 608, configured to acquire description information of configuration rules provided by the user; input the description information into a pre-trained rule generation model, so as to extract the information generation method and constraints contained in the rule description information through the rule generation model, and convert the extracted information generation method and constraints into a structured rule configuration statement in the target format to obtain the target configuration rule and store it in the rule base.

[0091] Optionally, the business scenario information includes: the business object and marketing objective corresponding to the marketing business; The determining unit 604 is specifically used to: determine the target configuration rules required for configuring the marketing business in the configuration rule library according to the business object; determine the historical preference library bound to the user's user identification information; and determine the historical configuration preference information in the historical preference library according to the business object and the marketing objective.

[0092] Optionally, the marketing business corresponds to multiple configuration items, and each configuration item corresponds to multiple candidate configuration rules; The determining unit 604 is specifically used to, for each configuration item of the marketing business, determine each candidate configuration rule corresponding to the configuration item in the configuration rule base according to the business scenario information; and determine at least one target configuration rule corresponding to the configuration item according to the weight corresponding to each candidate configuration rule.

[0093] Optionally, the historical configuration preference information is determined based on the average of the configuration information used by the user when configuring the relevant configuration items in the past, or the configuration information used by the user when configuring the relevant configuration items most recently. The device further includes an update unit 610, configured to update the historical configuration preference information according to the user's usage of the configuration information, and store the updated historical configuration preference information in the historical preference database.

[0094] Optionally, the updating unit 610 is further configured to update the weights corresponding to each candidate configuration rule based on the usage of configuration information generated by multiple users for multiple target configuration rules; wherein, for each target configuration rule, if the number of users using the target configuration rule to generate configuration information is greater than the number of users using other target configuration rules to generate configuration information, and / or the number of users using the target configuration rule to generate configuration information is greater than a preset number, then the weight corresponding to the target configuration rule is increased.

[0095] Optionally, the configuration unit 606 is specifically used to call a rule processing function that matches the logical characteristics of the target configuration rule in a preset function library, so as to convert the target configuration rule into executable code through the rule processing function, and generate the configuration information by combining the user's historical preference information under the generation logic and function conditions defined by the executable code using the configuration recommendation model.

[0096] Optionally, the acquisition unit 600 is further configured to display configuration options of automatic configuration and manual configuration to the user; if the user selects the automatic configuration option, a dialogue page is displayed to the user to obtain the dialogue information entered by the user in the dialogue page; The configuration unit 606 is further configured to, if the user selects the manual configuration option, display the configuration page of the configuration item to the user, so that the user can configure the marketing business on the configuration page.

[0097] For ease of description, the above devices are described by dividing them into various modules or units based on their functions. Of course, when implementing one or more of these specifications, the functions of each module or unit can be implemented in the same or different software and / or hardware, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0098] Based on the same concept as the methods described above, this specification also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor performs the steps of the method as described in any of the above embodiments by executing the executable instructions.

[0099] Based on the same concept as the methods described above, this specification also provides a computer-readable storage medium having computer instructions stored thereon that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.

[0100] Based on the same concept as the methods described above, this specification also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.

[0101] What those skilled in the art will understand is: In this specification, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded.

[0102] In this specification, “a,” “an,” and “the” do not specifically refer to the singular, but may also include the plural.

[0103] In this specification, ordinal numbers such as "first," "second," etc., do not necessarily indicate order; they are often used to distinguish between objects. For example, "first server" and "second server" usually refer to two servers. To differentiate between these two servers, they are described as "first server" and "second server." Of course, sometimes these two servers may be the same server.

[0104] In this specification, unless explicitly stated otherwise, "receiving and sending data" does not necessarily mean direct receiving and sending; it can also mean indirect receiving and sending. For example, A receiving data sent by B can be understood as A directly receiving the data sent by B, or it can be understood as A indirectly receiving the data sent by B through other entities such as C. Similarly, B sending data to A can be understood as B sending the data directly to A, or it can be understood as B indirectly sending the data to A through other entities such as C. Here, C can be one entity, or it can be two or more entities.

[0105] In this specification, unless explicitly stated otherwise, the relationships between structures can be direct or indirect. For example, when describing "A is connected to B," unless it is explicitly stated that A and B are directly connected, it should be understood that A can be directly connected to B or indirectly connected to B. Similarly, when describing "A is on top of B," unless it is explicitly stated that A is directly above B (AB is adjacent and A is above B), it should be understood that A can be directly above B or indirectly above B (AB is separated by other elements, and A is above B). And so on.

[0106] This specification uses specific terms to describe embodiments thereof. Terms such as "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Furthermore, those skilled in the art can combine and integrate the different embodiments or examples described herein, as well as the features of those different embodiments or examples, without contradiction.

[0107] Although one or more embodiments of this specification provide method steps as described in the embodiments or flowcharts, it is understood that the order of steps listed in the embodiments or flowcharts is only one of many possible execution orders and does not represent the only execution order. Therefore, when the claims involve method steps, any changes or adjustments to the order of such steps, or the parallelism between steps, are also within the scope of protection of the claims.

Claims

1. A method for configuring a marketing operation, comprising: Obtain dialogue information input by users regarding marketing activities; Semantic parsing of the dialogue information is performed to determine the business scenario information corresponding to the marketing business; Based on the business scenario information, the target configuration rules required for configuring the marketing business are determined in the preset configuration rule library, and the historical configuration preference information that matches the business scenario information is determined in the user's historical preference library. Under the information generation method and constraints specified by the target configuration rules, configuration information matching the historical configuration preference information is generated through a preset configuration recommendation model.

2. The method as described in claim 1, before determining the target configuration rules required for configuring the marketing business from a preset configuration rule base, the method further includes: Obtain the description information of the configuration rules provided by the user; The description information is input into a pre-trained rule generation model, which extracts the information generation method and constraints contained in the rule description information. The extracted information generation method and constraints are then converted into a structured rule configuration statement in the target format to obtain the target configuration rule and store it in the rule base.

3. The method as described in claim 1, wherein the business scenario information includes: The business targets and marketing objectives corresponding to the marketing activities; Based on the business scenario information, the target configuration rules required for configuring the marketing business are determined from the preset configuration rule base, specifically including: Based on the business object, determine the target configuration rules required to configure the marketing business in the configuration rule base; Historical configuration preference information matching the business scenario information is determined from the user's historical preference database, specifically including: A historical preference library bound to the user's user identification information is determined, and the historical configuration preference information is determined from the historical preference library according to the business object and the marketing objective.

4. The method as described in claim 1, wherein the marketing business corresponds to multiple configuration items, and each configuration item corresponds to multiple candidate configuration rules; The target configuration rules required for configuring the marketing business are determined from the preset target configuration rule base, specifically including: For each configuration item of the marketing business, the candidate configuration rules corresponding to the configuration item are determined in the configuration rule base according to the business scenario information; Based on the weights corresponding to each candidate configuration rule, at least one target configuration rule corresponding to the configuration item is determined.

5. The method as described in claim 1, wherein the historical configuration preference information is determined based on the average of the configuration information used by the user when configuring the relevant configuration items in the past, or the configuration information used by the user when configuring the relevant configuration items most recently; The method further includes: Based on the user's usage of the configuration information, the historical configuration preference information is updated, and the updated historical configuration preference information is stored in the historical preference database.

6. The method of claim 3, further comprising: The weights of each candidate configuration rule are updated based on the usage of configuration information generated by multiple users for multiple target configuration rules. Specifically, for each target configuration rule, if the number of users whose configuration information is generated using this target configuration rule is greater than the number of users whose configuration information is generated using other target configuration rules, and / or the number of users whose configuration information is generated using this target configuration rule is greater than a preset number, then the weight corresponding to this target configuration rule is increased.

7. The method as described in claim 1, wherein under the information generation method and constraints specified by the target configuration rule, configuration information matching the historical configuration preference information is generated through a preset configuration recommendation model, specifically including: In a preset function library, a rule processing function that matches the logical characteristics of the target configuration rule is called. The target configuration rule is converted into executable code through the rule processing function. Then, using the configuration recommendation model, under the generation logic and function conditions defined by the executable code, configuration information suitable for the marketing business is generated in combination with the user's historical preference information.

8. The method as described in claim 1, wherein obtaining dialogue information input by the user regarding marketing activities specifically includes: Show the user configuration options for automatic and manual configuration; If the user selects the automatic configuration option, a dialogue page is displayed to the user to obtain the dialogue information entered by the user on the dialogue page; The method further includes: If the user selects the manual configuration option, the configuration page for the configuration item is displayed to the user, allowing the user to configure the marketing service on the configuration page.

9. An electronic device, comprising: processor; A memory for storing processor-executable instructions; wherein the processor implements the steps of the method as described in any one of claims 1-8 by executing the executable instructions.

10. A computer program product comprising a computer program / instructions that, when executed by a processor, implement the steps of the method as claimed in any one of claims 1-8.

Images