Task execution method and device, storage medium and electronic equipment
By using the reply model and the associated knowledge base in application development, the problem of low docking efficiency of multiple project groups is solved, and the effect of improving docking efficiency is achieved.
Patent Information
- Application Number
- CN202411068683.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
During application development, the docking efficiency between multiple project groups is low, resulting in limited development efficiency.
By obtaining the user's question text in the target chat group and inputting it into the preset reply model, matching the corresponding text from the preset association knowledge base, generating reply text, and then automatically performing tasks to reduce the user's chatting The number of replies in the group improves the docking efficiency.
Through the preset reply model combined with the associated knowledge base, the number of replies required by users is reduced and the efficiency of target chat group connection is improved.
Smart Images

Figure CN119046419A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a task execution method, device, storage medium and electronic device. Background Art
[0002] With the development of computer technology, the development scale of various applications is getting larger and larger, and more and more fields are involved. For example, the application development process may involve art design, sound effect production, user interface (UI) design, software testing and other fields. Therefore, in the process of developing applications, multiple project teams are required to complete the work in different fields respectively to reduce the cost and time of cross-domain learning, thereby improving the efficiency of application development.
[0003] Typically, in the process of developing an application, multiple project teams need to connect through a large number of chat groups built for project connection to solve problems that arise during the development process. However, the efficiency of connecting through a large number of chat groups is low.
[0004] Therefore, how to improve the efficiency of docking between project teams is an urgent problem to be solved. Summary of the invention
[0005] This specification provides a task execution method, device, storage medium and electronic device to partially solve the above-mentioned problems existing in the prior art.
[0006] This manual adopts the following technical solutions:
[0007] This specification provides a task execution method, the method comprising:
[0008] Get the question text sent by the user in the target chat group;
[0009] Inputting the question text into a preset reply model, so that the reply model determines text matching the question text from a preset associated knowledge base as associated text, and generates a reply text according to the question text and the associated text, wherein the associated knowledge base is determined in advance according to historical questions in the target chat group;
[0010] The task is executed according to the reply text.
[0011] Optionally, before inputting the question text into a preset response model so that the response model determines a text matching the question text from a preset associated knowledge base as an associated text, the method further includes:
[0012] Recognize the question text to obtain a recognition result corresponding to the question text, wherein the recognition result is used to indicate whether the text content involved in the question text belongs to the business field corresponding to the response model;
[0013] The question text is input into a preset response model so that the response model determines text matching the question text from a preset associated knowledge base as associated text, specifically including:
[0014] If it is determined according to the recognition result that the text content involved in the question text belongs to the business field corresponding to the reply module, the question text is input into the preset reply model so that the reply model determines the text matching the question text from the preset associated knowledge base as the associated text.
[0015] Optionally, the associated knowledge base includes: a basic associated knowledge base pre-constructed based on reply texts corresponding to historical questions in the target chat group, and a supplementary associated knowledge base pre-determined under the business field involved in the historical questions in the target chat group;
[0016] The question text is input into a preset response model so that the response model determines text matching the question text from a preset associated knowledge base as associated text, specifically including:
[0017] The question text is input into a preset response model, so that the response model determines text matching the question text from the basic associated knowledge base and / or the supplementary associated knowledge base as associated text.
[0018] Optionally, the question text is input into a preset response model so that the response model determines text matching the question text from a preset associated knowledge base as associated text, specifically including:
[0019] The question text is input into a preset response model so that the response model recognizes the question text and obtains text keywords corresponding to the question text. Based on the text keywords, a query instruction is generated to determine the text matching the text keywords from a preset associated knowledge base as the associated text.
[0020] Optionally, performing a task according to the reply text specifically includes:
[0021] The reply text is sent to the client used by the user, so that the client used by the user displays the reply text to the user.
[0022] Optionally, the method further comprises:
[0023] Receiving feedback text returned by the client used by the user according to a text input operation performed by the user on the reply text;
[0024] If it is determined according to the feedback text that the user's confidence in the reply text is less than a preset confidence threshold, then according to the correspondence between preset business fields and docking users and the business field of the text content involved in the question text, a docking user matching the business field of the text content involved in the question text is determined as a target docking user;
[0025] The question text is sent to the client used by the target docking user to obtain the reply text of the target docking user to the question text, and the task is executed according to the reply text of the target docking user to the question text.
[0026] Optionally, sending the question text to a client used by the target docking user to obtain a reply text of the target docking user to the question text specifically includes:
[0027] Obtain candidate associated texts corresponding to the question text, where the candidate associated texts are other texts whose sending time is within the same time range as the sending time of the question text in the target chat group;
[0028] For each candidate associated text, determining the degree of association between the candidate associated text and the question text as the degree of association corresponding to the candidate associated text;
[0029] According to the relevance degree corresponding to each candidate associated text, the target associated text is selected from each candidate associated text;
[0030] The question text and the target-related text are sent to the client used by the target docking user to obtain a reply text of the target docking user to the question text.
[0031] This specification provides a task execution device, including:
[0032] An acquisition module is used to acquire the question text sent by the user in the target chat group;
[0033] A generation module, used for inputting the question text into a preset reply model, so that the reply model determines text matching the question text from a preset associated knowledge base as associated text, and generates a reply text according to the question text and the associated text, wherein the associated knowledge base is determined in advance according to historical questions in the target chat group;
[0034] An execution module is used to execute the task according to the reply text.
[0035] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:
[0036] In the task execution method provided in the present specification, the question text sent by the user in the target chat group is first obtained, and the question text is input into a preset reply model so that the reply model determines the text matching the question text from a preset associated knowledge base as the associated text, and generates a reply text based on the question text and the associated text, wherein the associated knowledge base is determined in advance based on historical questions in the target chat group, and then the task can be executed based on the reply text.
[0037] It can be seen from the above method that a preset reply model combined with a preset associated knowledge base can be used to automatically reply to group messages whose text content belongs to the business field corresponding to the preset reply model, thereby reducing the number of group messages that users need to reply to in the target chat group, and further effectively improving the efficiency of users connecting through the target chat group. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:
[0039] Figure 1 A flowchart of a task execution method provided in this specification;
[0040] Figure 2 A schematic diagram of the generation process of the reply text provided in this manual;
[0041] Figure 3 A schematic diagram of the task execution process provided in this manual;
[0042] Figure 4 A schematic diagram of a task execution device provided in this specification;
[0043] Figure 5 A method corresponding to the Figure 1 Schematic diagram of electronic equipment. DETAILED DESCRIPTION
[0044] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.
[0045] With the development of computer technology, more and more chat groups need to be built for interaction between R&D personnel, between R&D personnel and customers, and between customers in the process of application development, management and maintenance. This makes it difficult for R&D personnel to follow up on the information in multiple chat groups, and it is also difficult for users to identify the contact persons related to the current technical issues from the group members of multiple chat groups, which leads to lower and lower efficiency of the connection between the parties through chat groups.
[0046] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.
[0047] Figure 1 A flowchart of a task execution method provided in this specification includes the following steps:
[0048] S101: Obtain the question text sent by the user in the target chat group.
[0049] In this specification, the business platform can determine the chat group that needs to manage group messages as the target chat group based on a preset configuration file, and then automatically reply to the question text sent by the user in the target chat group.
[0050] The above-mentioned question text may refer to a group message sent by a group member user of the target chat group within the target chat group and collected by the service platform.
[0051] The above configuration file may be configured with a group ID of the chat group that needs to be managed (eg, the group number of the chat group, etc.), where the group ID may be configured by the R&D personnel of the business platform.
[0052] Of course, the group identifier may also be determined by the service platform displaying a preset configuration interface to the user of the service platform through a terminal device used by the user of the service platform, and according to the configuration operation performed by the user of the service platform on the configuration interface.
[0053] It should be noted that there are many ways for the business platform to obtain group messages in the target chat group. For example, a preset robot account is added to the target chat group to obtain group messages in the target chat group through the robot account.
[0054] Another example: by calling a specified interface (such as the Python interface), the group message in the target chat group is obtained.
[0055] In this specification, the execution subject used to implement the task execution method can refer to a designated device set up on a business platform by a server, or it can refer to a terminal device such as a desktop computer or a laptop computer. For the sake of ease of description, the task execution method provided in this specification is described below using the server as the execution subject as an example.
[0056] S102: Input the question text into a preset reply model so that the reply model determines text matching the question text from a preset associated knowledge base as associated text, and generates a reply text based on the question text and the associated text, wherein the associated knowledge base is determined in advance based on historical questions in the target chat group.
[0057] In this specification, after obtaining the question text, the server can identify the question text and obtain a recognition result corresponding to the question text (the recognition result here is used to characterize whether the text content involved in the question text belongs to the business field corresponding to the reply model). If the server determines that the text content involved in the question text belongs to the business field corresponding to the reply module based on the recognition result corresponding to the question text, the question text is input into the preset reply model to generate a reply text based on the input question text through the reply module.
[0058] Among them, the method for the server to identify the question text to obtain the recognition result corresponding to the question text can be to input the question text into a preset recognition model, so as to determine the business field to which the question text belongs through the preset recognition model, and then obtain the above-mentioned recognition result based on the business field to which the question text belongs and the business field corresponding to the response model.
[0059] Furthermore, after receiving the input question text, the reply model can determine the text matching the question text from the preset associated knowledge base as the associated text, and generate the reply text according to the question text and the associated text, as shown in the following example: Figure 2 shown.
[0060] Figure 2 A schematic diagram of the process of generating the reply text provided in this manual.
[0061] Combination Figure 2It can be seen that the above-mentioned reply module may include: a retrieval module and a generation module. After receiving the input question text, the reply model can identify the question text through the generation module of the reply model, obtain the text keywords corresponding to the question text, and transmit the determined text keywords to the retrieval module. The text keywords here may refer to the entity nouns of the entities involved in the question text (that is, a basic, independently existing thing, such as: users, orders, products, etc.), words used to characterize the logical relationship between entities, etc.
[0062] For example: If the question text is "How to connect the client's login server list and account system", the entities involved here are "client", "login server list", and "account system". The logical relationship between the entities here is a subordinate relationship (that is, "login server list" and "account system" are components of the "client") and a parallel relationship (that is, the "and" relationship between "login server list" and "account system").
[0063] Furthermore, the retrieval module of the reply model can determine the text matching the question text from the preset associated knowledge base as the associated text, and concatenate the question text and the associated text and input them into the generation module, so that the generation module of the reply model generates the reply text based on the question text and the associated text.
[0064] The generation module can be composed of a large language model (LLM), which can be understood as a sub-model of the reply model. The retrieval module can be a functional module in the reply model for performing retrieval so as to generate a reply text in collaboration with the LLM model.
[0065] The above-mentioned associated knowledge base may include: a basic associated knowledge base constructed in advance based on the reply texts corresponding to the historical questions in the target chat group, a supplementary associated knowledge base predetermined in the business field involved in the historical questions in the target chat group, etc. The supplementary associated knowledge base here can be an open source knowledge base in the business field involved in the historical questions in the target chat group or a knowledge base created, maintained and certified by a professional organization in the business field involved in the historical questions in the target chat group.
[0066] Furthermore, after receiving the text keywords sent by the generation module, the above-mentioned retrieval module can generate query instructions according to the text keywords, and for each associated knowledge base, through the above-mentioned query instructions, search for text matching the text keywords from the associated knowledge base as associated text.
[0067] In addition, the above-mentioned reply model can only be deployed to the server for question replying after training, wherein the method for training the above-mentioned reply model can be to obtain a sample question text and an actual reply text corresponding to the sample question text, so that the sample question text can be input into the reply model to be trained, so that the reply model to be trained can determine the text matching the sample question text from a preset associated knowledge base as the sample associated text, and generate a sample reply text based on the sample question text and the sample associated text, and then the reply model to be trained can be trained with the optimization goal of minimizing the deviation between the sample reply text output by the reply model to be trained and the actual reply text corresponding to the sample question text, so as to obtain a trained reply model.
[0068] S103: Execute the task according to the reply text.
[0069] In this specification, after the server obtains the reply text corresponding to the question text through the reply model, it can send the reply text to the client used by the user, so that the client used by the user displays the reply text to the user, and receives the feedback text returned by the client used by the user according to the text input operation performed by the user on the reply text, and performs the task according to the received feedback text, as shown in the following example. Figure 3 shown.
[0070] Figure 3 A schematic diagram of the task execution process provided in this manual.
[0071] Combination Figure 3 It can be seen that if the server determines, based on the received feedback text, that the user's confidence in the reply text is less than a preset confidence threshold, then the server can determine, based on the correspondence between the preset business fields and the docking users and the business field of the text content involved in the question text, a docking user that matches the business field of the text content involved in the question text as the target docking user, and then the question text can be sent to the client used by the target docking user to obtain the target docking user's reply text to the question text, and perform the task based on the target docking user's reply text to the question text.
[0072] The above-mentioned user's confidence in the reply text can be used to represent the user's satisfaction with the reply text generated by the server through the reply model.
[0073] The method for the server to determine the user's confidence in the reply text based on the received feedback text may be to input the feedback text into a preset evaluation model to determine the user's confidence in the reply text based on the user's feedback text through the preset evaluation model.
[0074] In addition, after determining the target docking user, the server can also determine whether the target docking user is a group member in the target chat group. If so, the server can send a prompt message to the client used by the target docking user to prompt the target docking user to reply to the question text sent by the user in the target chat group.
[0075] In addition, if the server determines that the target docking user is not a group member of the target chat group, the server can also send the group identifier and prompt information of the target chat group to the target docking user to prompt the target docking user to join the target chat group and reply to the question text sent by the user in the target chat group, or the server sends an invitation message and prompt information to the client used by the target docking user to prompt the target docking user to join the target chat group through the invitation message and reply to the question text sent by the user in the target chat group.
[0076] In actual application scenarios, since there may be a large number of group messages sent by other group member users in the target chat group, and these group messages may contain associated texts associated with the question texts sent by the users, and these associated texts may help the target user to reply to the question texts sent by the users.
[0077] Based on this, the server can also obtain the candidate associated texts corresponding to the question text, so that for each candidate associated text, the correlation between the candidate associated text and the question text can be determined as the correlation corresponding to the candidate associated text, and then the target associated text can be screened out from each candidate associated text according to the correlation corresponding to each candidate associated text, and the question text and the target associated text can be sent to the client used by the target docking user to obtain the target docking user's reply text to the question text and display it to the user.
[0078] Among them, the above-mentioned candidate associated texts are other texts whose sending time in the target chat group is within the same time range as the sending time of the question text.
[0079] The method for the server to obtain the correlation between the candidate associated text and the question text can be: for each candidate associated text, the candidate associated text and the question text are input into a preset first correlation determination model, and the candidate associated text and the question text are semantically analyzed through the preset first correlation determination model to determine the correlation between the candidate associated text and the question text.
[0080] However, since the algorithm complexity of performing semantic analysis on the candidate associated text and the question text to determine the degree of association between the candidate associated text and the question text is relatively high, the server is less efficient in selecting the target associated text from the candidate associated texts.
[0081] Therefore, in order to improve the efficiency of the server in screening out the target associated text from various candidate associated texts, the server can also determine the context data of the question text, and for each candidate associated text, determine the context data of the candidate associated text, and then determine the comprehensive similarity between the candidate associated text and the question text based on the similarity between the text keywords in the question text and the text keywords of the candidate associated text, and the similarity between the context data of the question text and the context data of the candidate text, and determine the correlation between the candidate associated text and the question text based on the comprehensive similarity between the candidate associated text and the question text.
[0082] The higher the comprehensive similarity between the candidate associated text and the question text, the higher the correlation between the candidate associated text and the question text is determined to be.
[0083] It can be seen from the above content that the server can identify the question text sent by the user in the target chat group, and automatically reply to the question text whose text content belongs to the business field corresponding to the preset reply model through the preset reply model combined with the preset associated knowledge base, and can determine the user's satisfaction with the reply text generated by the reply model based on the user's feedback text on the reply text generated by the reply model. Therefore, when it is determined that the user's satisfaction with the reply text generated by the reply model is low, the target docking user can reply to the question text sent by the user in the target chat group, thereby effectively improving the efficiency of user docking through the target chat group.
[0084] The above are one or more implementation task execution methods of this specification. Based on the same idea, this specification also provides corresponding task execution devices, such as Figure 4 shown.
[0085] Figure 4 A schematic diagram of a task execution device provided for this specification includes:
[0086] The acquisition module 401 is used to acquire the question text sent by the user in the target chat group;
[0087] A generation module 402 is used to input the question text into a preset reply model, so that the reply model determines text matching the question text from a preset associated knowledge base as associated text, and generates a reply text according to the question text and the associated text, wherein the associated knowledge base is determined in advance according to historical questions in the target chat group;
[0088] The execution module 403 is used to execute the task according to the reply text.
[0089] Optionally, the device further includes: an identification module 404;
[0090] The recognition module 404 is specifically used to recognize the question text and obtain a recognition result corresponding to the question text, and the recognition result is used to characterize whether the text content involved in the question text belongs to the business field corresponding to the response model; if it is determined according to the recognition result that the text content involved in the question text belongs to the business field corresponding to the response model, the question text is input into the preset response model, so that the response model determines the text matching the question text from the preset associated knowledge base as the associated text.
[0091] Optionally, the associated knowledge base includes: a basic associated knowledge base pre-constructed based on reply texts corresponding to historical questions in the target chat group, and a supplementary associated knowledge base pre-determined under the business field involved in the historical questions in the target chat group;
[0092] The generating module 402 is specifically used to input the question text into a preset response model, so that the response model determines text matching the question text from the basic associated knowledge base and / or the supplementary associated knowledge base as associated text.
[0093] Optionally, the generation module 402 is specifically used to input the question text into a preset response model so that the response model recognizes the question text, obtains text keywords corresponding to the question text, and generates query instructions based on the text keywords to determine the text that matches the text keywords from a preset associated knowledge base as associated text.
[0094] Optionally, the execution module 403 is specifically configured to send the reply text to a client used by the user, so that the client used by the user displays the reply text to the user.
[0095] Optionally, the execution module 403 is specifically used to receive feedback text returned by the client used by the user based on the text input operation performed by the user on the reply text; if it is determined according to the feedback text that the user's confidence in the reply text is less than a preset confidence threshold, then based on the correspondence between preset business fields and docking users and the business field of the text content involved in the question text, determine a docking user who matches the business field of the text content involved in the question text as the target docking user; send the question text to the client used by the target docking user to obtain the reply text of the target docking user to the question text, and perform task execution according to the reply text of the target docking user to the question text.
[0096] Optionally, the execution module 403 is specifically used to obtain candidate associated texts corresponding to the question text, the candidate associated texts being other texts whose sending time in the target chat group is within the same time range as the sending time of the question text; for each candidate associated text, determining the correlation between the candidate associated text and the question text as the correlation corresponding to the candidate associated text; screening out the target associated text from each candidate associated text according to the correlation corresponding to each candidate associated text; and sending the question text and the target associated text to the client used by the target docking user to obtain the reply text of the target docking user to the question text.
[0097] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 Provides a task execution method.
[0098] This manual also provides Figure 5 The one shown corresponds to Figure 1 A schematic diagram of the electronic device. Figure 5 As mentioned above, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Of course, in addition to the software implementation, this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0099] For the improvement of a technology, it can be clearly distinguished whether it is a hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.
[0100] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.
[0101] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0102] For the convenience of description, the above device is described by dividing it into various units according to its functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0103] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0104] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0105] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0107] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0108] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0109] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0110] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0111] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0112] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0113] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0114] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.
Claims
1. A task execution method, characterized in that: The method comprises: Get the question text sent by the user in the target chat group; Inputting the question text into a preset reply model, so that the reply model determines text matching the question text from a preset associated knowledge base as associated text, and generates a reply text according to the question text and the associated text, wherein the associated knowledge base is determined in advance according to historical questions in the target chat group; The task is executed according to the reply text.
2. The method according to claim 1, characterized in that Before inputting the question text into a preset response model so that the response model determines a text matching the question text from a preset associated knowledge base as an associated text, the method further includes: Recognize the question text to obtain a recognition result corresponding to the question text, wherein the recognition result is used to indicate whether the text content involved in the question text belongs to the business field corresponding to the response model; The question text is input into a preset response model so that the response model determines text matching the question text from a preset associated knowledge base as associated text, specifically including: If it is determined according to the recognition result that the text content involved in the question text belongs to the business field corresponding to the reply module, the question text is input into the preset reply model so that the reply model determines the text matching the question text from the preset associated knowledge base as the associated text.
3. The method according to claim 1, characterized in that The associated knowledge base includes: a basic associated knowledge base pre-constructed based on the reply texts corresponding to the historical questions in the target chat group, and a supplementary associated knowledge base pre-determined under the business field involved in the historical questions in the target chat group; The question text is input into a preset response model so that the response model determines text matching the question text from a preset associated knowledge base as associated text, specifically including: The question text is input into a preset response model, so that the response model determines text matching the question text from the basic associated knowledge base and / or the supplementary associated knowledge base as associated text.
4. The method according to claim 1, characterized in that The question text is input into a preset response model so that the response model determines text matching the question text from a preset associated knowledge base as associated text, specifically including: The question text is input into a preset response model so that the response model recognizes the question text and obtains text keywords corresponding to the question text. Based on the text keywords, a query instruction is generated to determine the text matching the text keywords from a preset associated knowledge base as the associated text.
5. The method according to claim 1, characterized in that According to the reply text, the task is executed, including: The reply text is sent to the client used by the user, so that the client used by the user displays the reply text to the user.
6. The method according to claim 5, characterized in that The method further comprises: Receiving feedback text returned by the client used by the user according to a text input operation performed by the user on the reply text; If it is determined according to the feedback text that the user's confidence in the reply text is less than a preset confidence threshold, then according to the correspondence between preset business fields and docking users and the business field of the text content involved in the question text, a docking user matching the business field of the text content involved in the question text is determined as a target docking user; The question text is sent to the client used by the target docking user to obtain the reply text of the target docking user to the question text, and the task is executed according to the reply text of the target docking user to the question text.
7. The method according to claim 6, characterized in that Sending the question text to the client used by the target docking user to obtain a reply text of the target docking user to the question text specifically includes: Obtain candidate associated texts corresponding to the question text, where the candidate associated texts are other texts whose sending time is within the same time range as the sending time of the question text in the target chat group; For each candidate associated text, determining the degree of association between the candidate associated text and the question text as the degree of association corresponding to the candidate associated text; According to the relevance degree corresponding to each candidate associated text, the target associated text is selected from each candidate associated text; The question text and the target-related text are sent to the client used by the target docking user to obtain a reply text of the target docking user to the question text.
8. A task execution device, characterized in that: include: An acquisition module is used to acquire the question text sent by the user in the target chat group; A generation module, used for inputting the question text into a preset reply model, so that the reply model determines text matching the question text from a preset associated knowledge base as associated text, and generates a reply text according to the question text and the associated text, wherein the associated knowledge base is determined in advance according to historical questions in the target chat group; An execution module is used to execute the task according to the reply text.
9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Intelligent interaction method, equipment and storage medium
CN107797984A
Group chat conversation processing method and device, and electronic equipment
CN111078856A
Community operation method and system based on AI big language model
CN117743554A
Online training method and device based on multi-modal large model, storage medium and server
CN117876170A
Task execution method and device, electronic equipment and storage medium
CN118278421A
