Artificial intelligence-based data generation method, device, equipment and storage medium

Abstract

The application belongs to the field of artificial intelligence and the field of financial technology, and relates to a data generation method based on artificial intelligence, comprising the following steps: obtaining communication information of a target service representative and a target customer within a preset time period; performing intent recognition on the communication information based on an intent recognition model to obtain intent information corresponding to the target customer; generating an initial service result based on the communication information and the intent information; pushing the initial service result to a work interface of the target service representative; receiving a selection operation of the target service representative on the initial service result input in the work interface; and generating a target service result based on the selection operation and the initial service result. The application also provides a data generation device based on artificial intelligence, a computer device and a storage medium. In addition, the application also relates to blockchain technology, and the target service result can be stored in the blockchain. The application can be applied to a communication data generation scene in the financial field, and improves the generation efficiency and data accuracy of the target service result.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence development technology and financial technology, and in particular to artificial intelligence-based data generation methods, devices, computer equipment and storage media. Background Technology

[0002] Currently, in financial institutions such as insurance companies and banks, marketing or follow-up business scenarios that require agent communication are used to provide customer communication services, enabling customer satisfaction surveys on product experience or services, and customer relationship maintenance. Typically, after an agent completes communication with a customer, they need to fill in a summary feedback, or service result, on a communication feedback page provided by the business system. Although a communication feedback page is provided in the business system, agents still need to manually fill in the corresponding service results on this page, which leads to lengthy completion times and low agent efficiency. Furthermore, agents are prone to entering non-standard information when recording service results, such as using pinyin abbreviations, characters with specific meanings, or typos, resulting in low accuracy of the generated service results. Summary of the Invention

[0003] The purpose of this application is to propose a data generation method, apparatus, computer equipment, and storage medium based on artificial intelligence, in order to solve the technical problems that the existing service result generation methods are time-consuming, resulting in low work efficiency of agents, and agents are prone to filling in non-standard information when recording service results, thus leading to low accuracy of the generated service results.

[0004] To address the aforementioned technical problems, this application provides an artificial intelligence-based data generation method, employing the following technical solution:

[0005] Obtain communication information between the target agent and the target customer within a preset time period;

[0006] The intent of the communication information is identified based on a preset intent recognition model to obtain intent information corresponding to the target customer.

[0007] An initial service result is generated based on the communication information and the intent information;

[0008] The initial service result is pushed to the target agent's work interface;

[0009] Receive the selection operation of the target agent on the operation interface regarding the initial service result;

[0010] The target service result is generated based on the selection operation and the initial service result.

[0011] Furthermore, the communication information is in voice format, and the step of performing intent recognition on the communication information based on a preset intent recognition model to obtain intent information corresponding to the target customer specifically includes:

[0012] The communication information is subjected to speech recognition and converted into corresponding text data;

[0013] Invoke the intent recognition model and input the text data into the intent recognition model;

[0014] The intent recognition model is used to perform intent recognition on the text data to obtain the intent recognition result corresponding to the text data;

[0015] The intent recognition result is used as the intent information.

[0016] Furthermore, the communication information is in text format; the step of generating an initial service result based on the communication information and the intent information specifically includes:

[0017] The communication information was subjected to violation word detection;

[0018] If no prohibited words are detected in the communication information, the communication information is revised to obtain the revised target communication information;

[0019] The initial service result is generated based on the target communication information and the intent information.

[0020] Furthermore, the step of generating the initial service result based on the target communication information and the intent information specifically includes:

[0021] Retrieve the preset service result template;

[0022] The locations for filling in communication information and intent information are determined from the service result template;

[0023] Fill the communication information into the communication information filling position in the service result template;

[0024] The intent information is filled into the intent information filling position in the service result template to obtain the initial service result.

[0025] Furthermore, after the step of generating the target service result based on the selection operation and the initial service result, the method further includes:

[0026] Obtain the seat information of the target agent and the customer information of the target customer;

[0027] Obtain communication tool information and time information corresponding to the target service result;

[0028] Based on the agent information, customer information, communication tool information, and time information, generate identification information corresponding to the target service result;

[0029] Obtain the target data type corresponding to the target service result;

[0030] Determine the data storage method corresponding to the target data type;

[0031] The target service result is stored based on the identification information and the data storage method.

[0032] Furthermore, after the step of generating the target service result based on the selection operation and the initial service result, the method further includes:

[0033] Obtain the processing appointment time corresponding to the target service result;

[0034] Obtain the information generation type corresponding to the processing appointment time;

[0035] Obtain the preset processing rules;

[0036] Based on the processing rules and the information generation type, the processing priority corresponding to the target service result is determined.

[0037] Furthermore, after the step of generating the target service result based on the selection operation and the initial service result, the method further includes:

[0038] Determine whether a modification request for the target service result triggered by the target agent has been received;

[0039] If so, receive the modification operation for the target service result input by the target agent;

[0040] Based on the modification operation, the target service result is modified to obtain the modified specified service result;

[0041] The results of the specified service are stored.

[0042] To address the aforementioned technical problems, this application also provides an artificial intelligence-based data generation device, which employs the following technical solution:

[0043] The first acquisition module is used to acquire communication information between the target agent and the target customer within a preset time period;

[0044] The identification module is used to identify the intent of the communication information based on a preset intent identification model, and obtain intent information corresponding to the target customer.

[0045] The first generation module is used to generate an initial service result based on the communication information and the intent information;

[0046] The push module is used to push the initial service result to the target agent's work interface;

[0047] The first receiving module is used to receive the selection operation of the initial service result input by the target agent on the operation interface;

[0048] The second generation module is used to generate a target service result based on the selection operation and the initial service result.

[0049] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0050] Obtain communication information between the target agent and the target customer within a preset time period;

[0051] The intent of the communication information is identified based on a preset intent recognition model to obtain intent information corresponding to the target customer.

[0052] An initial service result is generated based on the communication information and the intent information;

[0053] The initial service result is pushed to the target agent's work interface;

[0054] Receive the selection operation of the target agent on the operation interface regarding the initial service result;

[0055] The target service result is generated based on the selection operation and the initial service result.

[0056] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0057] Obtain communication information between the target agent and the target customer within a preset time period;

[0058] The intent of the communication information is identified based on a preset intent recognition model to obtain intent information corresponding to the target customer.

[0059] An initial service result is generated based on the communication information and the intent information;

[0060] The initial service result is pushed to the target agent's work interface;

[0061] Receive the selection operation of the target agent on the operation interface regarding the initial service result;

[0062] The target service result is generated based on the selection operation and the initial service result.

[0063] Compared with the prior art, the embodiments of this application have the following main advantages:

[0064] This embodiment first acquires communication information between a target agent and a target customer within a preset time period; then, based on a preset intent recognition model, it performs intent recognition on the communication information to obtain intent information corresponding to the target customer; subsequently, it generates an initial service result based on the communication information and the intent information; later, it pushes the initial service result to the target agent's work interface and receives the target agent's selection operation on the work interface regarding the initial service result; finally, it generates a target service result based on the selection operation and the initial service result. This embodiment processes the communication information between the target agent and the target customer within a preset time period to generate an initial service result, and then processes the initial service result based on the target agent's selection operation on the work interface to achieve automatic generation of the target service result. This eliminates the need for the target agent to fill in service result information after contacting the target customer, effectively improving the generation efficiency and data accuracy of the target service result, and contributing to improved work efficiency for the target agent. Attached Figure Description

[0065] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0066] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0067] Figure 2 A flowchart of an embodiment of the artificial intelligence-based data generation method according to this application;

[0068] Figure 3 This is a schematic diagram of a structure of an embodiment of the artificial intelligence-based data generation apparatus according to this application;

[0069] Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0070] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0071] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0072] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0073] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0074] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0075] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.

[0076] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103.

[0077] It should be noted that the AI-based data generation method provided in this application is generally executed by a server / terminal device, and correspondingly, the AI-based data generation device is generally located in the server / terminal device.

[0078] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0079] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0080] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0081] Continue to refer to Figure 2The flowchart illustrates an embodiment of the AI-based data generation method according to this application. The order of steps in the flowchart can be changed, and some steps can be omitted, depending on different needs. The AI-based data generation method provided in this application can be applied to any scenario requiring the generation of communication service results, and thus can be applied to products in these scenarios, such as the generation of communication service results in the financial insurance field. The AI-based data generation method includes the following steps:

[0082] Step S201: Obtain communication information between the target agent and the target customer within a preset time period.

[0083] In this embodiment, the artificial intelligence-based data generation method operates on an electronic device (e.g., Figure 1 The server / terminal device shown can acquire communication information between the target agent and the target customer within a preset time period via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wideband) connections, and other currently known or future wireless connection methods. The value of the preset time period is not specifically limited and can be set according to actual usage needs. For example, in the business scenario of product marketing in the financial insurance industry, the aforementioned communication information may refer to the communication information generated when the target agent is promoting products to the target customer. Communication information may include the method of contact (e.g., telephone, WeChat, UCP, etc., which the system can automatically identify), the result of the contact (e.g., customer did not answer, customer was busy and did not respond; for cases where no communication occurred, the system can make its own judgment), the conclusion of the contact (e.g., task successful, follow-up continued, task failed), remarks (generally recording customer expectations or information agreed upon after communication between the agent and customer), the next contact time, etc. The data format of the aforementioned communication information can be either voice or text.

[0084] Step S202: Based on a preset intent recognition model, the communication information is used to identify intent and obtain intent information corresponding to the target customer.

[0085] In this embodiment, the specific implementation process of performing intent recognition on the communication information based on the preset intent recognition model to obtain intent information corresponding to the target customer will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0086] Step S203: Generate an initial service result based on the communication information and the intent information.

[0087] In this embodiment, the specific implementation process of generating the initial service result based on the communication information and the intent information will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0088] Step S204: Push the initial service result to the target agent's work interface.

[0089] In this embodiment, the aforementioned work interface is the interface through which the target agent processes tasks. The initial service result can be pushed to the target agent's work interface by obtaining the communication address of the target agent's work interface and then using that address. Specifically, if multiple intent messages from the target customer appear in the communication information between the target agent and the target customer within a preset time period, these intent messages will be pushed to the target agent in the order they appear, without overwriting any of them, thus ensuring the integrity of the target customer's intent information.

[0090] Step S205: Receive the selection operation for the initial service result input by the target agent on the operation interface.

[0091] In this embodiment, the aforementioned selection operation may refer to the target agent's click to confirm the initial service result on the work interface. If the target agent's selection operation for the initial service result is not received on the work interface, then by default, all information in the initial service result will be taken as the final target service result corresponding to the communication process between the target agent and the target customer within a preset time period.

[0092] Step S206: Generate the target service result based on the selection operation and the initial service result.

[0093] In this embodiment, target information corresponding to the selection operation can be filtered from the initial service results and used as the target service result. By automatically extracting feedback information from the communication process between the target agent and the target customer and forming the corresponding target service result, the problems of long time consumption and non-standard information in existing service result filling can be solved. In addition, by forming an accurate target service result based on the target agent's autonomous triggering of the selection operation of the initial service result during the operation, the technical problem of inaccurate existing service result filling can be solved. Furthermore, by standardizing the generation of target service results, it is convenient for subsequent personnel to view and use the service results for data analysis and to provide support for subsequent customer contact.

[0094] This application first acquires communication information between a target agent and a target customer within a preset time period; then, based on a preset intent recognition model, it performs intent recognition on the communication information to obtain intent information corresponding to the target customer; subsequently, it generates an initial service result based on the communication information and the intent information; subsequently, it pushes the initial service result to the target agent's work interface and receives the target agent's selection operation on the work interface regarding the initial service result; finally, it generates a target service result based on the selection operation and the initial service result. This application processes the communication information between the target agent and the target customer within a preset time period to generate an initial service result, and then processes the initial service result based on the target agent's selection operation on the work interface to achieve automatic generation of the target service result. This eliminates the need for the target agent to fill in service result information after contacting the target customer, effectively improving the generation efficiency and data accuracy of the target service result, and contributing to improved work efficiency for the target agent.

[0095] In some optional implementations, the communication information is in voice format, and step S202 includes the following steps:

[0096] The communication information is subjected to speech recognition and converted into corresponding text data.

[0097] In this embodiment, the communication information can be recognized by ASR (Automatic Speech Recognition) to convert the vocabulary in the speech into computer-readable input, such as keystrokes, binary codes, or character sequences, so as to convert the communication information into corresponding text data.

[0098] The intent recognition model is invoked, and the text data is input into the intent recognition model.

[0099] In this embodiment, the intent recognition model described above can specifically employ the BERT model. BERT stands for Bidirectional Encoder Representations from Transformer. It is a pre-trained language representation model that emphasizes a departure from traditional unidirectional language models or shallow concatenation of two unidirectional language models for pre-training. Instead, it uses a novel masked language model (MLM) to generate deep bidirectional language representations. The goal of the BERT model is to train on large-scale unlabeled corpora to obtain a representation of text containing rich semantic information—that is, a semantic representation of the text. This semantic representation is then fine-tuned for a specific NLP task and finally applied to that task for intent recognition of text data.

[0100] The intent recognition model is used to perform intent recognition on the text data to obtain the intent recognition result corresponding to the text data.

[0101] In this embodiment, the intent recognition of the text data is performed by using the BERT model, and the semantic representation corresponding to the text data is output to obtain the intent recognition result corresponding to the text data.

[0102] The intent recognition result is used as the intent information.

[0103] This application converts the communication information into corresponding text data through speech recognition. Then, an intent recognition model is used, inputting the text data into the model. Subsequently, the intent recognition model performs intent recognition on the text data to obtain an intent recognition result corresponding to the text data, and this result is used as the intent information. By using an intent recognition model to recognize the intent in the communication information, this application can quickly and accurately generate intent information corresponding to the target customer, reducing the need for manual input of the target customer's intent during communication, improving the efficiency of intent information generation, and ensuring the accuracy of the generated intent information.

[0104] In some optional implementations of this embodiment, the communication information is in text format; Step S203:

[0105] The communication information was subjected to violation word detection.

[0106] In this embodiment, the communication information can be detected for violations using a pre-built set of prohibited words. Specifically, the communication information is first segmented into multiple words, and then each word is matched with all prohibited words in the set of prohibited words. If the set of prohibited words does not contain any prohibited words that match the words in the communication information, then it is determined that there are no prohibited words in the communication information. Conversely, if the set of prohibited words contains any prohibited words that match the words in the communication information, then it is determined that there are prohibited words in the communication information.

[0107] If no prohibited words are detected in the communication information, the communication information is revised to obtain the revised target communication information.

[0108] In this embodiment, the revision process can include deletion, addition, and replacement. For example, if the customer's response uses colloquial expressions, these colloquial words can be replaced with more formal, written expressions. Alternatively, if the customer's response contains repetitive words, the redundant words can be deleted. Furthermore, if the customer's response lacks verbs, they can be added accordingly.

[0109] The initial service result is generated based on the target communication information and the intent information.

[0110] In this embodiment, the specific implementation process of generating the initial service result based on the target communication information and the intent information will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0111] This application detects prohibited words in the communication information. If no prohibited words are detected, the communication information is revised to obtain revised target communication information. Subsequently, the target communication information and the intent information are used to generate the initial service result. After obtaining the communication information between the target agent and the target customer within a preset time period, this application intelligently detects prohibited words in the communication information to verify its compliance. Only when the communication information complies with the specifications will it be revised, and the initial service result will be generated based on the revised target communication information and intent information, ensuring the accuracy and compliance of the generated initial service result.

[0112] In some optional implementations, generating the initial service result based on the target communication information and the intent information includes the following steps:

[0113] Retrieve the preset service result template.

[0114] In this embodiment, the above-mentioned service result template is a template file generated based on the actual service result construction requirements. The target file is set with communication information filling positions corresponding to the communication information to be filled and intent information filling positions corresponding to the intent information to be filled.

[0115] The locations for filling in communication information and intent information are determined from the service result template.

[0116] Fill the communication information into the communication information filling position in the service result template.

[0117] The intent information is filled into the intent information filling position in the service result template to obtain the initial service result.

[0118] This application uses a preset service result template; then determines the communication information filling position and the intent information filling position in the service result template; subsequently, the communication information is filled into the communication information filling position in the service result template; and the intent information is filled into the intent information filling position in the service result template to obtain the initial service result. Based on the use of the service result template, this application achieves rapid construction of the required initial service result by filling the communication information into the communication information filling position in the service result template and filling the intent information into the intent information filling position in the service result template, thereby improving the efficiency of initial service result generation and ensuring the standardization of the generated initial service result.

[0119] In some alternative implementations, after step S206, the electronic device may further perform the following steps:

[0120] Obtain the seat information of the target agent and the customer information of the target customer.

[0121] In this embodiment, the aforementioned seat information may refer to the name or seat ID of the target seat. The aforementioned customer information may refer to the name of the target customer.

[0122] Obtain the communication tool information and time information corresponding to the target service result.

[0123] In this embodiment, the aforementioned communication tool information may refer to the name of the communication tool used by the target agent and the target customer during the communication process. The aforementioned time information may refer to information such as the start time, end time, and duration of the communication between the target agent and the target customer.

[0124] Based on the agent information, customer information, communication tool information, and time information, generate identification information corresponding to the target service result.

[0125] In this embodiment, the seat information, customer information, communication tool information, and time information can be integrated to obtain identification information corresponding to the target service result.

[0126] Obtain the target data type corresponding to the target service result.

[0127] In this embodiment, the target data type mentioned above may refer to a service data type.

[0128] Determine the data storage method corresponding to the target data type.

[0129] In this embodiment, for data of different business types, a corresponding storage method is pre-assigned to each type of data based on actual storage needs. For example, the storage method corresponding to service data type is blockchain storage, the storage method corresponding to feedback data type is database caching, and so on.

[0130] The target service result is stored based on the identification information and the data storage method.

[0131] In this embodiment, a data association relationship can be constructed between the identification information and the target service result, and then the target service result can be stored using the data storage method based on this data association relationship.

[0132] This application obtains the seat information of the target agent and the customer information of the target customer; then it obtains the communication tool information and time information corresponding to the target service result; subsequently, it generates identification information corresponding to the target service result based on the seat information, customer information, communication tool information, and time information; next, it obtains the target data type corresponding to the target service result; finally, it determines the data storage method corresponding to the target data type and stores the target service result based on the identification information and the data storage method. This application achieves standardized storage of target service results and improves the intelligence of target service result storage by generating identification information for the target service result, determining the data storage method corresponding to the target data type of the target service result, and then storing the target service result based on the identification information and the data storage method.

[0133] In some optional implementations of this embodiment, after step S206, the electronic device may further perform the following steps:

[0134] Obtain the processing appointment time corresponding to the target service result.

[0135] In this embodiment, the processing appointment time can refer to the next contact time between the target agent and the target customer. Alternatively, in the financial product recommendation scenario in the fintech field, during the communication process between the target agent and the target customer, the intent information contained in the target service results generated by the target customer during the communication process can be used to determine the product to be recommended to the target customer, and a processing appointment time corresponding to the product to be recommended will be generated. The processing appointment time can refer to the processing time for the target customer to receive a detailed introduction to the product to be recommended.

[0136] Obtain the information generation type corresponding to the processing appointment time.

[0137] In this embodiment, the information generation type corresponding to the processing appointment time can include three types: the processing appointment time can be filled in by the target customer, the processing appointment time can be predicted by the calling model, or the processing appointment time can be the default processing time set by the target agent.

[0138] Obtain the preset processing rules.

[0139] In this embodiment, the above processing rules may include: the processing appointment time filled in by the customer is of high processing priority, the processing appointment time predicted by the calling model is of medium processing priority, and the default processing appointment time set by the agent is of low processing priority.

[0140] Based on the processing rules and the information generation type, the processing priority corresponding to the target service result is determined.

[0141] In this embodiment, the processing priority corresponding to the target service result can be determined from the processing rules by matching the information generation type with the processing rules.

[0142] This application obtains the processing appointment time corresponding to the target service result; then obtains the information generation type corresponding to the processing appointment time; subsequently obtains preset processing rules; and finally determines the processing priority corresponding to the target service result based on the processing rules and the information generation type. After generating the target service result based on the selection operation and the initial service result, this application also intelligently obtains the processing appointment time corresponding to the target service result, and then determines the processing priority corresponding to the target service result based on the information generation type corresponding to the processing appointment time and the preset processing rules, ensuring the accuracy of the generated processing priority. Subsequently, subsequent business processing can be performed based on this processing priority, improving the standardization of business processing.

[0143] In some optional implementations of this embodiment, after step S206, the electronic device may further perform the following steps:

[0144] Determine whether a modification request for the target service result triggered by the target agent has been received.

[0145] In this embodiment, the job interface also provides a function to modify the service result. The target agent can click the modify button in the job interface to trigger a modification request for the target service result.

[0146] If so, receive the modification operation for the target service result input by the target agent.

[0147] In this embodiment, the above modification operations may include operations such as information deletion, information addition, and information replacement.

[0148] Based on the modification operation, the target service result is modified to obtain the modified specified service result.

[0149] The results of the specified service are stored.

[0150] In this embodiment, the storage procedure for storing the specified service result can refer to the storage procedure for the target service result described above, and will not be elaborated further here.

[0151] This application determines whether a modification request for the target service result triggered by the target agent has been received; if so, it receives the modification operation for the target service result input by the target agent; then, it modifies the target service result based on the modification operation to obtain the modified specified service result; subsequently, it stores the specified service result. After generating the target service result based on the selection operation and the initial service result, this application also intelligently modifies the target service result according to the modification operation input by the target agent to generate the final specified service result required by the target customer, thereby improving the accuracy of the generated specified service result and enhancing the user experience of the target customer.

[0152] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0153] It should be emphasized that, in order to further ensure the privacy and security of the above-mentioned target service results, the above-mentioned target service results can also be stored in a blockchain node.

[0154] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0155] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0156] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0157] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware with computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0158] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0159] Further reference Figure 3 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of an artificial intelligence-based data generation device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0160] like Figure 3 As shown, the artificial intelligence-based data generation device 300 described in this embodiment includes: a first acquisition module 301, an identification module 302, a first generation module 303, a push module 304, a first receiving module 305, and a second generation module 306. Wherein:

[0161] The first acquisition module 301 is used to acquire communication information between the target agent and the target customer within a preset time period;

[0162] The identification module 302 is used to identify the intent of the communication information based on a preset intent identification model, and obtain intent information corresponding to the target customer;

[0163] The first generation module 303 is used to generate an initial service result based on the communication information and the intent information;

[0164] The push module 304 is used to push the initial service result to the target agent's work interface;

[0165] The first receiving module 305 is used to receive the selection operation of the initial service result input by the target agent on the work interface;

[0166] The second generation module 306 is used to generate a target service result based on the selection operation and the initial service result.

[0167] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based data generation method in the aforementioned implementation method, and will not be repeated here.

[0168] In some optional implementations of this embodiment, the communication information is in voice format, and the recognition module 302 includes:

[0169] The conversion submodule is used to perform speech recognition on the communication information and convert the communication information into corresponding text data.

[0170] The input submodule is used to call the intent recognition model and input the text data into the intent recognition model.

[0171] The recognition submodule is used to perform intent recognition on the text data through the intent recognition model to obtain an intent recognition result corresponding to the text data;

[0172] The determination submodule is used to use the intent recognition result as the intent information.

[0173] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based data generation method in the aforementioned implementation method, and will not be repeated here.

[0174] In some optional implementations of this embodiment, the communication information is in text format; the first generation module 303 includes:

[0175] The detection submodule is used to detect prohibited words in the communication information;

[0176] The revision submodule is used to revise the communication information if no illegal words are detected in the communication information, so as to obtain the revised target communication information.

[0177] A generation submodule is used to generate the initial service result based on the target communication information and the intent information.

[0178] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based data generation method in the aforementioned implementation method, and will not be repeated here.

[0179] In some optional implementations of this embodiment, the generation submodule includes:

[0180] The acquisition unit is used to acquire a preset service result template;

[0181] The determining unit is used to determine the communication information filling position and the intent information filling position from the service result template;

[0182] The first filling unit is used to fill the communication information into the communication information filling position in the service result template;

[0183] The second filling unit is used to fill the intent information into the intent information filling position in the service result template to obtain the initial service result.

[0184] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based data generation method in the aforementioned implementation method, and will not be repeated here.

[0185] In some optional implementations of this embodiment, the artificial intelligence-based data generation device further includes:

[0186] The second acquisition module is used to acquire the seat information of the target agent and the customer information of the target customer;

[0187] The third acquisition module is used to acquire communication tool information and time information corresponding to the target service result;

[0188] The second generation module is used to generate identification information corresponding to the target service result based on the agent information, the customer information, the communication tool information, and the time information;

[0189] The fourth acquisition module is used to acquire the target data type corresponding to the target service result;

[0190] The first determining module is used to determine the data storage method corresponding to the target data type;

[0191] The first storage module is used to store the target service result based on the identification information and the data storage method.

[0192] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based data generation method in the aforementioned implementation method, and will not be repeated here.

[0193] In some optional implementations of this embodiment, the artificial intelligence-based data generation device further includes:

[0194] The fifth acquisition module is used to acquire the processing appointment time corresponding to the target service result;

[0195] The sixth acquisition module is used to acquire the information generation type corresponding to the processing appointment time;

[0196] The seventh acquisition module is used to acquire preset processing rules;

[0197] The second determining module is used to determine the processing priority corresponding to the target service result based on the processing rules and the information generation type.

[0198] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based data generation method in the aforementioned implementation method, and will not be repeated here.

[0199] In some optional implementations of this embodiment, the artificial intelligence-based data generation device further includes:

[0200] The judgment module is used to determine whether a modification request for the target service result triggered by the target agent has been received;

[0201] The second receiving module is used to receive, if yes, the modification operation on the target service result input by the target agent;

[0202] The modification module is used to modify the target service result based on the modification operation to obtain the modified specified service result;

[0203] The second storage module is used to store the specified service results.

[0204] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based data generation method in the aforementioned implementation method, and will not be repeated here.

[0205] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0206] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0207] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0208] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for data generation methods based on artificial intelligence. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0209] In some embodiments, the processor 42 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, for example, to execute computer-readable instructions of the artificial intelligence-based data generation method.

[0210] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0211] Compared with the prior art, the embodiments of this application have the following main advantages:

[0212] In this embodiment, communication information between the target agent and the target customer within a preset time period is first obtained. Then, intent recognition is performed on the communication information based on a preset intent recognition model to obtain intent information corresponding to the target customer. Next, an initial service result is generated based on the communication information and the intent information. Subsequently, the initial service result is pushed to the target agent's work interface, and the target agent's selection operation on the work interface for the initial service result is received. Finally, a target service result is generated based on the selection operation and the initial service result. This embodiment processes the communication information between the target agent and the target customer within a preset time period to generate an initial service result, and then processes the initial service result based on the target agent's selection operation on the work interface to achieve automatic generation of the target service result. This eliminates the need for the target agent to fill in service result information after contacting the target customer, effectively improving the generation efficiency and data accuracy of the target service result, and contributing to improved work efficiency for the target agent.

[0213] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the artificial intelligence-based data generation method described above.

[0214] Compared with the prior art, the embodiments of this application have the following main advantages:

[0215] In this embodiment, communication information between the target agent and the target customer within a preset time period is first obtained. Then, intent recognition is performed on the communication information based on a preset intent recognition model to obtain intent information corresponding to the target customer. Next, an initial service result is generated based on the communication information and the intent information. Subsequently, the initial service result is pushed to the target agent's work interface, and the target agent's selection operation on the work interface for the initial service result is received. Finally, a target service result is generated based on the selection operation and the initial service result. This embodiment processes the communication information between the target agent and the target customer within a preset time period to generate an initial service result, and then processes the initial service result based on the target agent's selection operation on the work interface to achieve automatic generation of the target service result. This eliminates the need for the target agent to fill in service result information after contacting the target customer, effectively improving the generation efficiency and data accuracy of the target service result, and contributing to improved work efficiency for the target agent.

[0216] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0217] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. An artificial intelligence-based data generation method, characterized by, The method comprises the following steps: obtaining communication information between a target agent and a target customer within a preset time period; performing intent recognition on the communication information based on a preset intent recognition model to obtain intent information corresponding to the target customer; generating an initial service result based on the communication information and the intent information; pushing the initial service result to a work interface of the target agent; receiving a selection operation on the initial service result input by the target agent on the work interface; generating a target service result based on the selection operation and the initial service result; wherein the communication information is in a text format; the step of generating an initial service result based on the communication information and the intent information specifically comprises: detecting the communication information for violation words; if no violation words are detected in the communication information, performing revision processing on the communication information to obtain revised target communication information; generating the initial service result based on the target communication information and the intent information; wherein the step of generating the initial service result based on the target communication information and the intent information specifically comprises: obtaining a preset service result template; determining a communication information filling position and an intent information filling position from the service result template; filling the communication information into the communication information filling position in the service result template; filling the intent information into the intent information filling position in the service result template to obtain the initial service result; wherein the template file is provided with a communication information filling position corresponding to the communication information to be filled and an intent information filling position corresponding to the intent information to be filled. 2.The artificial intelligence-based data generation method of claim 1, wherein, The communication information is in a voice format, and the step of performing intent recognition on the communication information based on a preset intent recognition model to obtain intent information corresponding to the target customer specifically comprises: performing voice recognition on the communication information to convert the communication information into corresponding text data; calling the intent recognition model and inputting the text data into the intent recognition model; performing intent recognition on the text data through the intent recognition model to obtain an intent recognition result corresponding to the text data; taking the intent recognition result as the intent information. 3.The artificial intelligence-based data generation method of claim 1, wherein, After the step of generating a target service result based on the selection operation and the initial service result, the method further comprises: obtaining agent information of the target agent and customer information of the target customer; obtaining communication tool information and time information corresponding to the target service result; generating identification information corresponding to the target service result based on the agent information, the customer information, the communication tool information, and the time information; obtaining a target data type corresponding to the target service result; determining a data storage mode corresponding to the target data type; storing the target service result based on the identification information and the data storage mode. 4.The artificial intelligence-based data generation method of claim 1, wherein, After the step of generating a target service result based on the selection operation and the initial service result, the method further comprises: obtaining a processing reservation time corresponding to the target service result; obtain an information generation type corresponding to the processing appointment time; obtain a preset processing rule; determine a processing priority corresponding to the target service result based on the processing rule and the information generation type. 5.The artificial intelligence-based data generation method of claim 1, wherein, After the step of generating a target service result based on the selection operation and the initial service result, the method further includes: determining whether a modification request for the target service result triggered by the target agent is received; if yes, receiving a modification operation for the target service result input by the target agent; performing modification processing on the target service result based on the modification operation to obtain a modified specified service result; storing the specified service result.

6. An artificial intelligence-based data generation device, characterized by comprising: The method includes: a first obtaining module configured to obtain communication information between a target agent and a target customer within a preset time period; a recognition module configured to perform intent recognition on the communication information based on a preset intent recognition model to obtain intent information corresponding to the target customer; a first generation module configured to generate an initial service result based on the communication information and the intent information; a pushing module configured to push the initial service result to a work interface of the target agent; a first receiving module configured to receive a selection operation for the initial service result input by the target agent on the work interface; a second generation module configured to generate a target service result based on the selection operation and the initial service result; wherein the communication information is in a text format; and the first generation module includes: a detection sub-module configured to detect violation words in the communication information; a revision sub-module configured to perform revision processing on the communication information to obtain target communication information after revision if no violation word is detected in the communication information; a generation sub-module configured to generate the initial service result based on the target communication information and the intent information; wherein the generation sub-module includes: an obtaining unit configured to obtain a preset service result template; a determination unit configured to determine a communication information filling position and an intent information filling position from the service result template; a first filling unit configured to fill the communication information into the communication information filling position in the service result template; a second filling unit configured to fill the intent information into the intent information filling position in the service result template to obtain the initial service result; wherein the template file is provided with a communication information filling position corresponding to the communication information to be filled and an intent information filling position corresponding to the intent information to be filled.

7. A computer device including a memory and a processor, the memory storing computer readable instructions, and the processor implementing the steps of the artificial intelligence-based data generation method according to any one of claims 1 to 5 when executing the computer readable instructions.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer readable instructions, and the computer readable instructions are executed by the processor to implement the steps of the artificial intelligence-based data generation method according to any one of claims 1 to 5.

Images