Operational information output methods, devices, equipment, media and program products

Abstract

This disclosure provides a method for outputting operational information, relating to the field of artificial intelligence technology and applicable to the field of fintech. The method includes: receiving user questions; extracting customer group categories, question classifications, and question intents based on the user questions; and outputting operational answers based on the question classifications and question intents, using a preset operational question-and-answer model corresponding to the customer group category. The preset operational answer model is established at least based on the emotional characteristics and customer characteristics corresponding to the customer group category. This disclosure also provides an operational information output device, equipment, storage medium, and program product.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology and can be applied to the field of financial technology technology, specifically relating to an operational information output method, apparatus, equipment, medium, and program product. Background Technology

[0002] In the course of business operations, understanding the perspectives of target customers is crucial for formulating corresponding operational strategies. Therefore, companies collect proactive feedback and suggestions from customers, conduct research and analysis on these suggestions, and use this information to determine subsequent operational strategies.

[0003] Because of certain cognitive differences between operations personnel and customer groups, the generated operational strategies may deviate from the needs of the target customers, thus affecting operational results. Therefore, during or after the design of operational strategies, manual discussion and revision are necessary to ensure optimal results. However, this process is lengthy, leading to untimely output of operational information and impacting its efficiency. Therefore, improving the efficiency of operational information output is a pressing technical problem that needs to be solved. Summary of the Invention

[0004] In view of the above problems, this disclosure provides operational information output methods, apparatus, equipment, media and program products to improve the efficiency of operational information output.

[0005] According to a first aspect of this disclosure, an operational information output method is provided, comprising: receiving user questions; extracting customer group categories, question classifications, and question intents based on the user questions; and outputting operational answers based on the question classifications and the question intents, using a preset operational question-and-answer model corresponding to the customer group category, wherein the preset operational answer model is established based at least on the emotional features corresponding to the customer group category and the customer features corresponding to the customer group category.

[0006] According to embodiments of this disclosure, extracting customer group categories, question classifications, and question intents based on the user questions includes: extracting customer group categories, question classifications, and question intents from the user questions based on semantic analysis.

[0007] According to embodiments of this disclosure, the step of outputting an operational answer based on the question classification and the question intent, using a preset operational question-and-answer model corresponding to the customer group category, includes: matching a preset knowledge base based on the question classification and the question intent to obtain search results; and generating the operational answer based on the search results and the question intent, using the preset operational question-and-answer model.

[0008] According to an embodiment of this disclosure, the training method of the preset operation question-and-answer model includes: acquiring first feedback data; extracting a first customer group category, a first customer group feature, and a first emotional feature from the first feedback data; acquiring second feedback data based on the first customer group category; extracting a second customer group feature and a second emotional feature from the second feedback data; and training the preset operation answer model based on the first customer group feature, the first emotional feature, the second customer group feature, and the second emotional feature.

[0009] According to embodiments of this disclosure, the first feedback data includes multimodal data, and the second feedback data includes multimodal data, wherein the multimodal data includes text, images, and videos.

[0010] According to embodiments of this disclosure, the step of extracting the first customer group category, the first customer group characteristics, and the first emotional characteristics from the first feedback data includes: extracting the first customer group characteristics and the first emotional characteristics from the first feedback data; and performing cluster analysis based on the first customer group characteristics and the first emotional characteristics to obtain the first customer group category.

[0011] According to embodiments of this disclosure, the preset operational response model is based on distributed deployment.

[0012] A second aspect of this disclosure provides an operational information output device, the device comprising: a receiving module for receiving user questions; an extraction module for extracting customer group categories, question classifications, and question intents based on the user questions; and a question-and-answer module for outputting operational answers based on the question classifications and the question intents, using a preset operational question-and-answer model corresponding to the customer group category, wherein the preset operational answer model is established based at least on the emotional features corresponding to the customer group category and the customer features corresponding to the customer group category.

[0013] According to embodiments of this disclosure, the extraction module is specifically used to extract customer group category, question classification, and question intent from the user question based on semantic analysis.

[0014] According to embodiments of this disclosure, the question-answering module is specifically used to match a preset knowledge base based on the question classification and the question intent to obtain search results; and to generate the operational answer based on the search results and the question intent through the preset operational question-answering model.

[0015] According to embodiments of this disclosure, the apparatus further includes a model training module, configured to acquire first feedback data; extract a first customer group category, a first customer group feature, and a first emotional feature from the first feedback data; acquire second feedback data based on the first customer group category; extract a second customer group feature and a second emotional feature from the second feedback data; and train the preset operational response model based on the first customer group feature, the first emotional feature, the second customer group feature, and the second emotional feature.

[0016] According to embodiments of this disclosure, the first feedback data includes multimodal data, and the second feedback data includes multimodal data, wherein the multimodal data includes text, images, and videos.

[0017] According to embodiments of this disclosure, the question-answering module is further specifically used to extract a first customer group feature and a first emotional feature from the first feedback data; and to perform cluster analysis based on the first customer group feature and the first emotional feature to obtain the first customer group category.

[0018] According to embodiments of this disclosure, the preset operational response model is based on distributed deployment.

[0019] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0020] A fourth aspect of this disclosure also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0021] The fifth aspect of this disclosure also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0022] In the embodiments of this disclosure, to improve operational efficiency and timeliness, operational questions are received from operations personnel. The customer group category, question classification, and question intent are determined, and this information is input into the corresponding operational response model for that customer group category, outputting an answer. This operational response model fully considers the customer group's characteristics and emotional characteristics, and can simulate a realistic customer perspective. The embodiments of this disclosure can achieve at least the following beneficial effects: 1. Highly efficient and accurate customer insight: significantly improved efficiency compared to traditional methods; 2. Real-time response decision support: significantly improved operational information output efficiency through real-time question and answer; 3. Authentic and credible customer perspective: the question and answer model established through customer group characteristics and emotional characteristics can reduce cognitive differences among operations personnel. Attached Figure Description

[0023] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0024] Figure 1 This diagram illustrates an application scenario of the operation information output method according to an embodiment of the present disclosure.

[0025] Figure 2 A flowchart illustrating an operation information output method according to an embodiment of the present disclosure is shown schematically;

[0026] Figure 3 A flowchart illustrating a method for establishing a preset operational question-and-answer model according to an embodiment of the present disclosure is shown schematically.

[0027] Figure 4 A schematic diagram illustrating the structure of an operation information output device according to an embodiment of the present disclosure; and

[0028] Figure 5 A block diagram of an electronic device suitable for implementing an operational information output method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0029] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0030] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0031] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0032] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0033] In the technical solution of this application, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0034] In scenarios involving automated decision-making using personal information, the methods, devices, and systems provided in this application all offer users corresponding entry points for choosing to agree to or reject the automated decision-making results. If the user chooses to reject, the process proceeds to the expert decision-making stage. Here, "automated decision-making" refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests, or economic, health, and credit status through computer programs, and then making a decision. Here, "expert decision-making" refers to the activity of making decisions by personnel who specialize in a particular field, possess specialized experience, knowledge, and skills, and have reached a certain level of professional expertise.

[0035] In marketing and product development, understanding the perspectives, emotions, and preferences of the target customer group is crucial for businesses to formulate effective strategies. Traditionally, businesses primarily gather customer feedback through the following methods:

[0036] 1. Questionnaire survey: Collect customer opinions and suggestions on products or services by designing structured questionnaires.

[0037] 2. Focus Group Discussion: Invite representatives from the target customer group to participate in a group discussion to gain a deeper understanding of their needs and preferences.

[0038] 3. Market Research: Engage a professional market research company to conduct large-scale user surveys and data analysis.

[0039] While the above methods help businesses understand customer needs to some extent, they still have the following significant drawbacks:

[0040] 1. Self-report bias: Traditional questionnaire surveys have two main biases: unintentional reporting bias (participants forget their own habits) and intentional reporting bias (participants want to be in an advantageous position), which leads to inaccurate data.

[0041] 2. Subjectivity in Questionnaire Design and Analysis: Questionnaire design and data analysis are often influenced by researchers' subjective judgments, which may lead to biased results. Respondents may provide inaccurate or highly subjective answers.

[0042] 3. Resource consumption: Traditional market research methods usually require a lot of time, manpower and financial resources, which are costly and time-consuming.

[0043] 4. Insufficient real-time capability: Unable to capture changes in customer emotions and opinions in real time, resulting in marketing decisions lagging behind market trends.

[0044] 5. Cultural and cognitive differences: There may be age differences, cultural differences, etc. between the operations staff and the target customer group, making it difficult for the operations staff to truly understand the views and preferences of the target customer group.

[0045] The aforementioned shortcomings will lead to technical problems such as low efficiency in the output of operational information.

[0046] To address the technical problems existing in the prior art, embodiments of this disclosure provide an operational information output method, the method comprising: receiving user questions; extracting customer group categories, question classifications, and question intents based on the user questions; and outputting operational answers based on the question classifications and the question intents, using a preset operational question-and-answer model corresponding to the customer group category, wherein the preset operational answer model is established at least based on the emotional features corresponding to the customer group category and the customer features corresponding to the customer group category.

[0047] In the embodiments of this disclosure, to improve operational efficiency and timeliness, operational questions are received from operations personnel. The customer group category, question classification, and question intent are determined, and this information is input into the corresponding operational response model for that customer group category, outputting an answer. This operational response model fully considers the customer group's characteristics and emotional characteristics, and can simulate a realistic customer perspective. The embodiments of this disclosure can achieve at least the following beneficial effects: 1. Highly efficient and accurate customer insight: significantly improved efficiency compared to traditional methods; 2. Real-time response decision support: significantly improved operational information output efficiency through real-time question and answer; 3. Authentic and credible customer perspective: the question and answer model established through customer group characteristics and emotional characteristics can reduce cognitive differences among operations personnel.

[0048] Figure 1 The diagram illustrates an application scenario of the operation information output method according to an embodiment of the present disclosure.

[0049] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0050] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0051] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0052] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0053] It should be noted that the operation information output method provided in this embodiment can generally be executed by server 105. Correspondingly, the operation information output device provided in this embodiment can generally be located in server 105. The operation information output method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the operation information output device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0054] It should be understood that Figure 1The 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.

[0055] The following will be based on Figure 1 The described scene, through Figures 2-3 The operational information output method of the disclosed embodiments will be described in detail.

[0056] Figure 2 A flowchart illustrating an operation information output method according to an embodiment of the present disclosure is shown schematically.

[0057] like Figure 2 As shown, the operation information output method of this embodiment includes operations S210 to S230.

[0058] In recent years, with the development of artificial intelligence and natural language processing technologies, sentiment analysis has become an important tool for understanding customer perspectives. Typical sentiment analysis systems can determine the polarity (positive, negative, or neutral) of customer sentiment expressed by analyzing text data. Some advanced systems are beginning to attempt to combine multimodal data (such as images and text) for analysis to provide more comprehensive sentiment insights. The purpose of embodiments of this disclosure is to help business stakeholders understand market dynamics and predict product adoption rates by simulating the decision-making process and social influence of individual consumers.

[0059] When operating S210, receive user questions.

[0060] Specifically, user questions are questions from operations personnel. These user questions can be unimodal or multimodal, such as text-based user questions that combine images and text.

[0061] For example, when an operations staff member asks a question about a new product, such as, "Is the packaging design of this product appealing to Generation Z?"

[0062] For example, when promoting fitness products, one might ask, "Does this fitness product appeal to female users?"

[0063] In operation S220, based on the user's question, the customer group category, question classification, and question intent are extracted.

[0064] Specifically, this can be achieved by using methods such as keyword matching to read the customer group category, question classification, and question intent from the user's question.

[0065] As shown in the previous example, customer categories, problem categories, and problem intents are matched using pre-set keywords. For example, customer category: Generation Z, problem category: packaging consultation, and problem intent: the popularity of the packaging.

[0066] Of course, more intelligent methods can be used to extract customer categories, problem classifications, and problem intent, as shown below:

[0067] According to embodiments of this disclosure, extracting customer group categories, question classifications, and question intents based on the user questions includes: extracting customer group categories, question classifications, and question intents from the user questions based on semantic analysis.

[0068] Specifically, for textual information, the user's question is first segmented into words, then key semantic features are extracted to generate text vectors, and finally, a text-based classification model outputs the aforementioned customer group category, question category, and question intent. For images, a convolutional neural network can be used to extract feature data from the image as the aforementioned question intent. This step can be understood as a preprocessing of the user's question, extracting the customer group category, question category, and question intent, thus reducing the burden on the backend operational question-answering model.

[0069] In operation S230, based on the question classification and the question intent, an operational answer is output through a preset operational question-and-answer model corresponding to the customer group category. The preset operational answer model is established based at least on the emotional features and customer features corresponding to the customer group category.

[0070] In embodiments of this application, user consent or authorization may be obtained before acquiring and using user information. For example, a request to acquire and use the information may be sent to the user before operation S230. Operation S230 is performed only if the user consents or authorizes the acquisition and use of user information.

[0071] Specifically, different customer groups correspond to different preset operational question-and-answer models. During use, the preset operational question-and-answer model corresponding to the customer group category is matched. The preset operational question-and-answer model is trained using the feature data of the group corresponding to the customer group category as training data.

[0072] It should be noted that the preset operational response model can be a generative model. Relevant personnel can fine-tune the initialized generative model by feeding it emotional features and customer characteristics of the customer group category.

[0073] According to embodiments of this disclosure, the preset operational response model is based on distributed deployment.

[0074] Specifically, the distributed architecture supports high-concurrency access and real-time data processing, ensuring the scalability and stability of the system.

[0075] According to embodiments of this disclosure, the step of outputting an operational answer based on the question classification and the question intent, using a preset operational question-and-answer model corresponding to the customer group category, includes: matching a preset knowledge base based on the question classification and the question intent to obtain search results; and generating the operational answer based on the search results and the question intent, using the preset operational question-and-answer model.

[0076] The system includes a pre-built knowledge base containing a vast amount of user feedback. Maintenance personnel organize, categorize, and store this feedback. During use, the system retrieves data from the pre-built knowledge base that matches the question category and intent using keyword matching. These retrieval results and the question intent are then used as output data to generate the output from the operational question-answering model.

[0077] In the embodiments of this disclosure, to improve operational efficiency and timeliness, operational questions are received from operations personnel. The customer group category, question classification, and question intent are determined, and this information is input into the corresponding operational response model for that customer group category, outputting an answer. This operational response model fully considers the customer group's characteristics and emotional characteristics, and can simulate a realistic customer perspective. The embodiments of this disclosure can achieve at least the following beneficial effects: 1. Highly efficient and accurate customer insight: significantly improved efficiency compared to traditional methods; 2. Real-time response decision support: significantly improved operational information output efficiency through real-time question and answer; 3. Authentic and credible customer perspective: the question and answer model established through customer group characteristics and emotional characteristics can reduce cognitive differences among operations personnel.

[0078] The following is a detailed description of the method for establishing the preset operational question-and-answer model:

[0079] Figure 3 A flowchart illustrating a method for establishing a preset operational question-and-answer model according to an embodiment of the present disclosure is shown.

[0080] like Figure 3 As shown, the operation information output method of this embodiment includes operations S310 to S350.

[0081] In a typical scenario, new feedback data is received from user A. It is determined that user A belongs to customer group 1. Customer group 1 consists of feedback data from other users that have been compiled. By integrating the customer group characteristics and emotional characteristics of user A and customer group 1, the operational response model is trained and iterated.

[0082] During operation of S310, the first feedback data is obtained.

[0083] The first feedback data is the feedback data of a specific user, such as user A. This feedback data could be, for example, an opinion on a particular product.

[0084] In operation S320, the first customer group category, first customer group characteristics, and first emotional characteristics of the first feedback data are extracted.

[0085] According to embodiments of this disclosure, the step of extracting the first customer group category, the first customer group characteristics, and the first emotional characteristics from the first feedback data includes: extracting the first customer group characteristics and the first emotional characteristics from the first feedback data; and performing cluster analysis based on the first customer group characteristics and the first emotional characteristics to obtain the first customer group category.

[0086] Specifically, based on preset feature items, the customer characteristics (such as consumption amount, purchase event, purchase channel, users of a certain APP, etc.) and sentiment characteristics (such as sentiment tendency, topics of interest, etc.) of the first feedback data are used to obtain the first customer group characteristics and the first sentiment characteristics. Then, an improved clustering algorithm (such as combining K-means and sentiment weighting) is used to group users to ensure that the clustering results have sentiment similarity, thus obtaining the first customer group category.

[0087] In operation S330, second feedback data is obtained based on the first customer group category.

[0088] The second feedback data is a collection of other feedback data for the customer group stored in the database, based on the first customer group category. For example, the second feedback data is a collection of various feedback data for the customer group category to which user A belongs.

[0089] In operation S340, the second customer group characteristics and the second emotional characteristics of the second feedback data are extracted.

[0090] Specifically, following the feature extraction method described in operation S320 above, the second customer group features and the second emotional features are extracted.

[0091] According to embodiments of this disclosure, the first feedback data includes multimodal data, and the second feedback data includes multimodal data, wherein the multimodal data includes text, images, and videos.

[0092] Specifically, the mixed data is first separated into different modalities such as text, image, and video. Then, features are extracted for each modality, such as text sentiment features (using an improved BERT model) and image visual features (using an advanced CNN model).

[0093] In operation S350, the preset operation response model is trained based on the first customer group characteristics, the first emotional characteristics, the second customer group characteristics, and the second emotional characteristics.

[0094] Specifically, firstly, the first customer group characteristics, first emotional characteristics, second customer group characteristics, and second emotional characteristics are aggregated to generate a weighted domain opinion vector, representing the overall emotional tendency of the customer group in that domain. Then, the model parameters are initialized based on the customer group characteristics and the emotional vector, including basic attributes, emotional states, and behavioral rules. Next, emotional states and memories are stored and managed to simulate the persistence and changing patterns of human emotions. Finally, decision-making reasoning is performed based on emotional states and memories to simulate the cognitive process of the customer group in the face of different marketing stimuli. The behavior generation unit generates behavioral responses consistent with the customer group characteristics based on the decision results, such as purchase intention and changes in brand attitude.

[0095] The embodiments disclosed herein can achieve at least the following beneficial effects: 1. Efficient and accurate customer insights: Compared with traditional methods, efficiency is improved: In operational decision-making, it is expected to greatly reduce customer analysis time; 2. Real-time responsive decision support: This solution has real-time question-and-answer capabilities and targeted decision-making suggestions; 3. Authentic and credible customer perspective: Reduces cognitive differences. Operational personnel (such as market experts over 35 years old) can "think" about young consumers aged 18-25 through the system, which can identify cognitive differences between the two and avoid marketing errors caused by generational differences; 4. Continuous learning adaptability: The system can continuously learn from new data and maintain sensitivity to market changes.

[0096] Based on the above-mentioned expected effects and advantages, the embodiments disclosed herein are expected to effectively solve the problem that operators have difficulty obtaining an internal perspective of the target customer group, provide enterprises with a brand-new marketing decision support tool, and significantly improve the marketing efficiency and effectiveness of enterprises.

[0097] Based on the above-described method for outputting operational information, this disclosure also provides an operational information output device. The following will be combined with... Figure 4 The device is described in detail.

[0098] Figure 4 A schematic block diagram of an operation information output device according to an embodiment of the present disclosure is shown.

[0099] like Figure 4 As shown, the operation information output device 400 of this embodiment includes a receiving module 410, an extraction module 420, and a question-and-answer module 430.

[0100] The receiving module 410 is used to receive user questions. In one embodiment, the receiving module 410 can be used to perform the operation S210 described above, which will not be repeated here.

[0101] The extraction module 420 is used to extract customer group category, question classification, and question intent based on the user question. In one embodiment, the extraction module 420 can be used to perform the operation S220 described above, which will not be repeated here.

[0102] The question-answering module 430 is used to output operational answers based on the question classification and the question intent, using a preset operational question-answering model corresponding to the customer group category. The preset operational answer model is established based at least on the emotional characteristics and customer characteristics corresponding to the customer group category. In one embodiment, the question-answering module 430 can be used to perform the operation S230 described above, which will not be repeated here.

[0103] In the embodiments of this disclosure, to improve operational efficiency and timeliness, operational questions are received from operations personnel. The customer group category, question classification, and question intent are determined, and this information is input into the corresponding operational response model for that customer group category, outputting an answer. This operational response model fully considers the customer group's characteristics and emotional characteristics, and can simulate a realistic customer perspective. The embodiments of this disclosure can achieve at least the following beneficial effects: 1. Highly efficient and accurate customer insight: significantly improved efficiency compared to traditional methods; 2. Real-time response decision support: significantly improved operational information output efficiency through real-time question and answer; 3. Authentic and credible customer perspective: the question and answer model established through customer group characteristics and emotional characteristics can reduce cognitive differences among operations personnel.

[0104] According to embodiments of this disclosure, the extraction module is specifically used to extract customer group category, question classification, and question intent from the user question based on semantic analysis.

[0105] According to embodiments of this disclosure, the question-answering module is specifically used to match a preset knowledge base based on the question classification and the question intent to obtain search results; and to generate the operational answer based on the search results and the question intent through the preset operational question-answering model.

[0106] According to embodiments of this disclosure, the apparatus further includes a model training module, configured to acquire first feedback data; extract a first customer group category, a first customer group feature, and a first emotional feature from the first feedback data; acquire second feedback data based on the first customer group category; extract a second customer group feature and a second emotional feature from the second feedback data; and train the preset operational response model based on the first customer group feature, the first emotional feature, the second customer group feature, and the second emotional feature.

[0107] According to embodiments of this disclosure, the first feedback data includes multimodal data, and the second feedback data includes multimodal data, wherein the multimodal data includes text, images, and videos.

[0108] According to embodiments of this disclosure, the question-answering module is further specifically used to extract a first customer group feature and a first emotional feature from the first feedback data; and to perform cluster analysis based on the first customer group feature and the first emotional feature to obtain the first customer group category.

[0109] According to embodiments of this disclosure, the preset operational response model is based on distributed deployment.

[0110] According to embodiments of this disclosure, any plurality of modules among the receiving module 410, the extraction module 420, and the question-and-answer module 430 may be combined into one module, or any one of these modules may be split into multiple modules. Alternatively, at least a portion of the functionality of one or more of these modules may be combined with at least a portion of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the receiving module 410, the extraction module 420, and the question-and-answer module 430 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the receiving module 410, the extraction module 420, and the question-and-answer module 430 may be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0111] Figure 5 A block diagram of an electronic device suitable for implementing an operational information output method according to an embodiment of the present disclosure is shown schematically.

[0112] like Figure 5 As shown, an electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage portion 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0113] RAM 903 stores various programs and data required for the operation of electronic device 900. Processor 901, ROM 902, and RAM 903 are interconnected via bus 904. Processor 901 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 902 and / or RAM 903. It should be noted that the programs may also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0114] According to embodiments of this disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to a bus 904. The electronic device 900 may also include one or more of the following components connected to the input / output (I / O) interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 910 as needed so that computer programs read from it can be installed into the storage section 908 as needed.

[0115] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0116] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 902 and / or RAM 903 and / or one or more memories other than ROM 902 and RAM 903 described above.

[0117] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of this disclosure.

[0118] When the computer program is executed by the processor 901, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0119] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 909, and / or installed from a removable medium 911. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0120] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0121] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0122] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0123] Those skilled in the art will understand that the features described in the various embodiments of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0124] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for outputting operational information, characterized in that, The method includes: Receiving user questions; Based on the user questions, extract customer group categories, question classifications, and question intent; and Based on the question classification and the question intent, an operational response is output through a preset operational question-and-answer model corresponding to the customer group category. The preset operational response model is established based at least on the emotional features and customer features corresponding to the customer group category.

2. The method according to claim 1, wherein extracting customer group category, question classification, and question intent based on the user question includes: Based on semantic analysis, the customer group category, question classification, and question intent are extracted from the user questions.

3. The method according to claim 2, wherein the step of outputting an operational answer based on the question classification and the question intent, using a preset operational question-and-answer model corresponding to the customer group category, includes: Based on the question classification and the question intent, a pre-set knowledge base is matched to obtain the search results; as well as Based on the search results and the intent of the question, the operational answer is generated using the preset operational question-and-answer model.

4. The method according to claim 1, wherein the training method of the preset operational question-answering model includes: Obtain the first feedback data; Extract the first customer group category, first customer group characteristics, and first emotional characteristics from the first feedback data; Based on the first customer group category, obtain the second feedback data; Extract the second customer group characteristics and the second emotional characteristics from the second feedback data; as well as The preset operation response model is trained based on the first customer group characteristics, the first emotional characteristics, the second customer group characteristics, and the second emotional characteristics.

5. The method according to claim 4, wherein the first feedback data includes multimodal data, the second feedback data includes multimodal data, and the multimodal data includes text, images, and videos.

6. The method according to claim 4 or 5, wherein extracting the first customer group category, the first customer group characteristics, and the first emotional characteristics from the first feedback data includes: Extract the first customer group characteristics and the first emotional characteristics from the first feedback data; as well as Cluster analysis is performed based on the first customer group characteristics and the first emotional characteristics to obtain the first customer group category.

7. The method according to any one of claims 1-5, wherein the preset operation response model is based on distributed deployment.

8. An operational information output device, characterized in that, The device includes: The receiving module is used to receive user questions; The extraction module is used to extract customer group categories, question classifications, and question intent based on the user's question; and The question-and-answer module is used to output operational answers based on the question classification and the question intent, through a preset operational question-and-answer model corresponding to the customer group category. The preset operational answer model is established based at least on the emotional features and customer features corresponding to the customer group category.

9. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 7.

Images