Artificial intelligence-based conversational interaction data processing method, device and equipment

By obtaining user account and date feature information, pushing problems and updating tags and points, the problem of intelligent customer service robots not fully utilize user information is solved, and the utilization rate and reply accuracy of interactive data are improved.

CN114969295BActive Publication Date: 2024-11-26PING AN TECH (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210614849.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-31
Publication Date
2024-11-26
Estimated Expiration
2042-05-31

AI Technical Summary

Technical Problem

The existing intelligent customer service robots do not fully consider the user's own information when dealing with user problems, resulting in low accuracy of reply data and not fully utilize reply data as a reference for the next round of conversations, resulting in low data utilization.

Method used

By detecting the user login instruction, obtaining user account information and current date feature information, obtaining user tag sets based on this information, pushing a question set, and updating user tags and points based on user answer data, dynamically adjusting user tags to improve the utilization rate of interactive data .

Benefits of technology

The data analysis and user tag extraction efficiency during the interaction process are realized. The analysis results are used as reference data for the next round of dialogue, improving the accuracy and utilization of reply data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114969295B_ABST
    Figure CN114969295B_ABST
Patent Text Reader

Abstract

The present application relates to artificial intelligence technology, and provides a method, device and equipment for processing dialogue interaction data based on artificial intelligence, which first obtains user account information and current date feature information, then obtains the current user tag set based on the user account information and current date feature information, and obtains the current push question set based on the current user tag set, then obtains the corresponding answer data set, and obtains the updated user tag set corresponding to the current user tag set based on the answer data set, and obtains the updated user points data with the answer data set, and finally updates the user account information based on the updated user tag set and the updated user points data. The data analysis and user tag extraction of the interaction process are made more efficient, and the results obtained by the analysis can be used as reference data for the next round of dialogue.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of speech semantic technology of artificial intelligence, and in particular to a method, device, computer equipment and storage medium for processing conversational interaction data based on artificial intelligence. Background Art

[0002] At present, when users have questions and need to consult when shopping in online malls or buying insurance online, they usually interact with online intelligent customer service. The current online intelligent customer service is generally an intelligent customer service robot that provides services to all customers. This type of intelligent customer service robot generally obtains the answer data based on its own knowledge base after obtaining the questions entered by the user and pushes it to the user. Moreover, this type of intelligent customer service robot generally starts to interact with the user after the user sends the first question.

[0003] This results in the existing intelligent customer service robots not fully considering the user's own information (such as user interests, hobbies, areas of expertise, etc.) to retrieve reply data, so the accuracy of the reply data is low. In addition, the reply data obtained is not fully reused to obtain user auxiliary information as reference data for the next round of dialogue, resulting in low data utilization. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus, computer device and storage medium for processing conversational interaction data based on artificial intelligence, aiming to solve the problem in the prior art that when the intelligent customer service robot obtains answers based on user questions, it does not fully consider the user's own information, resulting in low accuracy of the reply data, and does not fully utilize the reply data analysis to obtain user auxiliary information as reference data for the next round of conversation, resulting in low data utilization.

[0005] In a first aspect, an embodiment of the present application provides a method for processing conversational interaction data based on artificial intelligence, which includes:

[0006] If a user successful login instruction is detected, the user account information related to the user successful login instruction is obtained, and the current date characteristic information is obtained; wherein the current date characteristic information includes holiday characteristics and news information characteristics of the day;

[0007] Acquire a current user tag set according to the user account information and the current date feature information, acquire a current push question set based on the current user tag set, and send the current push question set to a user terminal corresponding to the user successful login instruction;

[0008] If an answer data set corresponding to the current pushed question set is received, obtaining an updated user tag set corresponding to the current user tag set according to the answer data set, and obtaining updated user score data according to the answer data set; and

[0009] The current user tag set is updated according to the updated user tag set to obtain an updated user tag set, and the updated user points data is added to the user account information to update the user account information.

[0010] In a second aspect, an embodiment of the present application provides a conversation interaction data processing device based on artificial intelligence, comprising:

[0011] A login information acquisition unit, for acquiring user account information related to the user successful login instruction and acquiring current date feature information if a user successful login instruction is detected; wherein the current date feature information includes holiday features and news information features of the day;

[0012] A current push question set acquisition unit, configured to acquire a current user tag set according to the user account information and the current date feature information, acquire a current push question set based on the current user tag set, and send the current push question set to a user terminal corresponding to the user successful login instruction;

[0013] an updated tag set acquisition unit, configured to, upon receiving an answer data set corresponding to the current pushed question set, acquire an updated user tag set corresponding to the current user tag set according to the answer data set, and acquire updated user score data according to the answer data set; and

[0014] The user tag set updating unit is used to update the current user tag set according to the updated user tag set to obtain an updated user tag set, and add the updated user points data to the user account information to update the user account information.

[0015] In a third aspect, an embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the artificial intelligence-based dialogue interaction data processing method described in the first aspect is implemented.

[0016] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the artificial intelligence-based dialogue interaction data processing method described in the first aspect above.

[0017] The embodiment of the present application provides a method, device, computer equipment and storage medium for processing dialogue interaction data based on artificial intelligence, first obtaining user account information and current date feature information, then obtaining the current user tag set based on the user account information and current date feature information and obtaining the current push question set based on the current user tag set, then obtaining the corresponding answer data set and obtaining the updated user tag set corresponding to the current user tag set based on the answer data set and obtaining the updated user points data with the answer data set, and finally updating the user account information based on the updated user tag set and the updated user points data. The data analysis and user tag extraction of the interaction process are made more efficient, and the results obtained by the analysis can be used as reference data for the next round of dialogue. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A schematic diagram of an application scenario of the artificial intelligence-based conversation interaction data processing method provided in an embodiment of the present application;

[0020] Figure 2 A flowchart of a method for processing conversational interaction data based on artificial intelligence provided in an embodiment of the present application;

[0021] Figure 3 A schematic block diagram of an artificial intelligence-based conversation interaction data processing device provided in an embodiment of the present application;

[0022] Figure 4 A schematic block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0025] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0026] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] See also Figure 1 and Figure 2 , Figure 1 A schematic diagram of an application scenario of the artificial intelligence-based conversation interaction data processing method provided in an embodiment of the present application; Figure 2 A flow chart of an artificial intelligence-based conversation interaction data processing method provided in an embodiment of the present application, wherein the artificial intelligence-based conversation interaction data processing method is applied in a server, and the method is executed by application software installed in the server.

[0028] like Figure 2 As shown, the method includes steps S101 to S104.

[0029] S101. If a user successful login instruction is detected, obtain user account information related to the user successful login instruction, and obtain current date feature information; wherein the current date feature information includes holiday features and current day news information features.

[0030] In this embodiment, the technical solution is described with the server as the execution subject. An intelligent customer service robot is deployed in the server, which can automatically push the screened question set and news information data to the user end, and update the user tag and user score data based on the answer data set and news information data click feedback data sent by the user end, and continuously and dynamically adjust the user tag to push the next data more accurately.

[0031] Specifically, when a user uses a user terminal in the form of a smartphone, tablet computer, laptop computer, etc. to start the application and log in to the user account (successful login to the user account can trigger the user successful login instruction) to establish a communication connection with the server, the interactive interface of the intelligent customer service robot is displayed on the user terminal interface, so that the intelligent customer service robot can push information to the user terminal, or the user terminal can send questions to be consulted or other interactive information to the intelligent customer service robot. In the process of mutual interaction, the intelligent customer service robot can further analyze and extract user tags based on the user's answer data to update the user portrait, and the user can also obtain the required information from the intelligent customer service robot.

[0032] When the user uses the client to start the application and logs in to the user account, the server first obtains the user account information corresponding to the successful login instruction of the user, wherein the user account information includes basic user information (such as user nickname, gender, age, user interests and hobbies, etc.), user login history, user login history IP address information, etc. In addition, the server also obtains the current date feature information. For example, if the current date corresponds to a holiday, the holiday feature of the current date feature information is the name of the holiday. If the current date corresponds to one or more hot news information, the news information feature of the day of the current date feature information is the news information keywords of the above one or more hot news information.

[0033] In one embodiment, before step S101, the method further includes:

[0034] If the interaction information sent by the user terminal is detected, the interaction information and the information type corresponding to the interaction information are obtained;

[0035] Acquire a recognition model corresponding to the information type, and recognize the interaction information according to the recognition model to obtain interaction recognition data;

[0036] Acquire a user age range corresponding to the interaction information, and determine a voice type of the message to be replied to according to the user age range;

[0037] Acquire corresponding reply data in a local knowledge base according to the semantic vector of the interactive recognition data;

[0038] Generate corresponding reply voice data from the reply data according to the voice type of the message to be replied;

[0039] The reply voice data is sent to the user terminal.

[0040] In this embodiment, when the user uses the user terminal to establish communication with the intelligent customer service robot in the server, interactive information can be sent to it. The interactive information sent can be of text type, voice type, picture type, etc. In order to extract the text information in the interactive information more quickly, it is necessary to first determine the information type of the interactive information, such as text type, voice type, picture type, etc.

[0041] At this time, if it is determined that the information type of the interactive information is a text type, first obtain a text recognition model (such as a Transformer model, etc.), and then obtain the text recognition information corresponding to the interactive information based on the text recognition model as interactive recognition data. If it is determined that the information type of the interactive information is a picture type, first obtain an image recognition model (such as a convolutional neural network model, etc.), and then obtain the image text recognition information corresponding to the interactive information based on the image recognition model as interactive recognition data. If it is determined that the information type of the interactive information is a voice type, first obtain a voice recognition type (such as an N-gram model, also known as a multivariate model, etc.), and then obtain the voice text recognition model corresponding to the interactive information based on the voice recognition model as interactive recognition data. After obtaining the interactive recognition data, you can further obtain

[0042] Since the user account information can be obtained when the user is identified at the source end of the interactive information, that is, the user end, the user age range can be obtained based on the user account information of the user end. After determining the user age range (such as dividing males aged 0-20 into male adolescents, males aged 20-40 into male youths, males aged 40-60 into male middle-aged, males aged 60 and above into male elderly, etc., and females can also refer to males and be divided into four stages), the voice type of the message to be replied corresponding to the user age range can be obtained. For example, if the user age range is 20-40 years old, it corresponds to the first voice type of the message to be replied (such as the first voice type of the message to be replied is the voice type of a young female voice). It can be seen that a type of voice message to be replied is determined based on each user age range, which facilitates the subsequent synthesis of the reply data into the corresponding reply voice data based on the voice message type to be replied as the sound parameter, thereby increasing the diversity of the reply voice data type.

[0043] After that, the general interactive information is the user's question data. In order to obtain the reply answer to the question data more quickly, the semantic vector of the interactive recognition data can be obtained first, and then the reply semantic vector with the maximum vector similarity value with the semantic vector is obtained in the local knowledge base as the target semantic vector, and finally the original text data corresponding to the target semantic vector is obtained as the reply data. It can be seen that based on the semantic similarity matching method, the reply data corresponding to the interactive recognition data can be quickly and accurately obtained.

[0044] Finally, after obtaining the text corresponding to the reply data, the type of voice message to be replied can be used as a sound parameter to synthesize the reply data into the corresponding reply voice data, and the reply voice data can be sent to the user end to complete this round of interaction between the user and the intelligent customer service robot. Moreover, during the interaction process, the user age range and the type of voice message to be replied can be obtained, and the basic user data is accumulated for the next round of user interaction. Among them, it should be noted that all the user data obtained are legally obtained under the premise of obtaining user authorization.

[0045] In one embodiment, as a specific embodiment of obtaining the user age range based on the interaction information, obtaining the user age range corresponding to the interaction information includes:

[0046] If it is determined that the interaction information is speech type data, obtaining a Mel frequency cepstral coefficient feature corresponding to the interaction information;

[0047] The Mel-frequency cepstral coefficient feature is input into a pre-trained voice age range classification model to obtain the user age range.

[0048] In this embodiment, the interaction information can be framed in turn, power spectrum can be estimated using the periodogram method, the power spectrum can be filtered using a Mel filter bank, the energy in each filter can be calculated, the energy of each filter can be logarithmized, a DCT transform (i.e., discrete cosine transform) can be performed, and the 2nd to 13th coefficients of the DCT can be retained and processed to obtain the Mel-frequency cepstrum coefficient characteristics corresponding to the interaction information.

[0049] Specifically, when the interactive information is framed, the first step is to divide it into frames of 20-40ms (optimally 25ms), and extract 12 features from each frame to obtain framed data. The second step is to perform DCT transform on each frame of the framed data to obtain the DCT transform result. The third step is to use the periodogram method to estimate the power spectrum of the DCT transform result to obtain an estimated power spectrum. The fourth step is to filter the estimated power spectrum by 26 vector groups of length 257 (i.e., a triangular filter group) to obtain a filtered signal. The fifth step is to take the log of the filtered signal to obtain a logarithmic operation result. The sixth step is to perform a discrete cosine transform on the logarithmic operation result to obtain 26 cepstral coefficients. The seventh step is to retain the 2nd to 13th 12 cepstral coefficients of the 26 cepstral coefficients to form MFCC features (i.e., Mel frequency cepstral coefficient features).

[0050] After obtaining the Mel frequency cepstral coefficient features corresponding to the interaction information, the voice age range classification model stored locally on the server, such as SVM (i.e. support vector machine), GMM (i.e. Gaussian mixture model), etc., can be obtained, and the Mel frequency cepstral coefficient features can be input into the pre-trained voice age range classification model for classification to obtain the user age range. It can be seen that this method can accurately obtain the user age range based on the interaction information.

[0051] S102, obtaining a current user tag set according to the user account information and the current date feature information, obtaining a current push question set according to the current user tag set, and sending the current push question set to a user terminal corresponding to the user successful login instruction.

[0052] In this embodiment, after the server obtains the user account information and the current date feature information, the current user tag set can be obtained by integrating the user's initial user tag set extracted from the user account information and the holiday features and the news information features of the day in the current date feature information. Then, based on the current user tag set, the current push question set corresponding to the current user tag set is screened out from the question library deployed in the server, and the current push question set is sent to the user end.

[0053] In one embodiment, the step S102 of obtaining the current user tag set according to the user account information and the current date feature information includes:

[0054] Obtain user interest keywords and user basic information of the user account information, and convert the user interest keywords and the user basic information into corresponding user tags according to a preset user tag conversion strategy to form an initial tag set of the current user.

[0055] In this embodiment, the user interest and hobby keywords in the user account information are generally keywords selected by the user according to his or her own interests and hobbies at the time of initial registration. The tags obtained by converting the above keywords based on the preset user tag conversion strategy constitute the first type of initial user tag set. And the user's basic information is also filled in by the user according to his or her actual situation (such as age, gender, education, etc.), and the tags obtained by these basic information based on the preset user tag conversion strategy constitute the second type of initial user tag set. The first type of initial user tag set is combined with the second type of initial user tag set to obtain the current user's initial tag set. Finally, the date tag corresponding to the current date feature information is integrated into the current user's initial tag set to obtain the current user tag set. It can be seen that this method is to obtain multi-dimensional user tags through user interest and hobby keywords, user basic information and current date feature information, and can obtain user tag sets with more dimensional tags, and the user image portrayed is more accurate.

[0056] In one embodiment, obtaining the current push question set according to the current user tag set in step S102 includes:

[0057] The pushed questions corresponding to each user tag in the current user tag set in the local question library are obtained to form a current pushed question set.

[0058] In this embodiment, after the current user tag set is obtained, the corresponding push questions in the local question library can be obtained based on each user tag. For example, taking the example of obtaining the push questions corresponding to a user tag, the first step is to obtain the tag category corresponding to the user tag (such as a financial tag, an investment tag, a sports tag, etc.), and then obtain the high-heat questions corresponding to the tag category (such as the question with the highest heat value under the tag category can be regarded as a high-heat question), and finally use the high-heat questions corresponding to the tag category as the push questions for the user tag. Referring to the above method, the push questions corresponding to other user tags in the current user tag set can also be obtained. After the push questions corresponding to each user tag in the current user tag set are obtained, the current push question set can be formed and sent to the user end. It can be seen that through the above method, a push question set can be quickly obtained based on user tags.

[0059] S103: If an answer data set corresponding to the current pushed question set is received, an updated user tag set corresponding to the current user tag set is obtained according to the answer data set, and updated user score data is obtained according to the answer data set.

[0060] In this embodiment, after the user terminal receives the current set of pushed questions, it can give a specific answer to each pushed question. For example, each pushed question is a question-and-answer question with a check mark of "yes" or "no". The user can operate the user terminal to answer each pushed question separately and obtain the answer data for each pushed question. After answering the current set of pushed questions in the user terminal, the corresponding answer data set is obtained. After the server receives the answer data set sent by the user terminal, it can perform data analysis on the answer data set to determine whether each answer data can be further converted into a new user tag. After completing the determination of whether each answer data can be converted into a new user tag, the updated user tag set corresponding to the current user tag set can be obtained.

[0061] Moreover, the user points can be determined based on each answer data in the answer data set. For example, the total number of answer data with a definite answer (such as yes or no in the above example) in the above answer question can be set, and the conversion strategy of one point for each definite answer can be used to obtain the answer data set to update the user points data. It can be seen that after the user completes the information interaction with the intelligent customer service robot, the user tag data and points data are updated in time, which can serve as the data basis for the next push question.

[0062] In one embodiment, the acquiring, according to the answer data set, an updated user tag set corresponding to the current user tag set includes:

[0063] Obtain the i-th answer data in the answer data set; wherein the initial value of i is 1 and the value range of i is [1, N], and N is the total number of answer data in the answer data set;

[0064] If it is determined that the i-th answer data is a non-null value, obtain the i-th currently pushed question corresponding to the i-th answer data;

[0065] Get the i-th initial user tag corresponding to the i-th currently pushed question;

[0066] If it is determined that the i-th answer data is a positive part of speech, the i-th initial user label is used as the i-th updated user label corresponding to the i-th answer data;

[0067] If it is determined that the i-th answer data is of a negative part of speech, the i-th antonym user label of the i-th initial user label is obtained according to the preset user righteousness and antonym label list, and the i-th antonym user label is used as the i-th updated user label corresponding to the i-th answer data;

[0068] Increase i by 1 to update the value of i;

[0069] If it is determined that i does not exceed N, return to execute the step of obtaining the i-th answer data in the answer data set;

[0070] If it is determined that i exceeds N, the first updated user tag to the Nth updated user tag are obtained to form an updated user tag set.

[0071] In this embodiment, the user label is updated by taking the i-th answer data as an example. Specifically, it is first determined whether the answer data is a null value. If it is determined that the i-th answer data is a null value, it means that the user has not answered the i-th currently pushed question. The i-th answer data has no effect on the user label update.

[0072] If it is determined that the i-th answer data is not a null value, it means that the user has answered the i-th currently pushed question. The i-th answer data has an impact on the user label update, specifically, it determines whether the user answers affirmatively or negatively. When it is determined that the i-th answer data is of the affirmative part of speech, the i-th initial user label corresponding to the i-th currently pushed question does not need to be adjusted, and the i-th initial user label can be used as the i-th updated user label corresponding to the i-th answer data. When it is determined that the i-th answer data is of the negative part of speech, the i-th initial user label corresponding to the i-th currently pushed question needs to be adjusted, and the i-th antonym user label corresponding to the i-th initial user label can be used as the i-th updated user label corresponding to the i-th answer data. It can be seen that the user label is continuously updated based on the user's real-time answer, so that the user label set used as the reference data for the next question push is updated in a timely manner, and the question set can be pushed more objectively and accurately.

[0073] In one embodiment, if it is determined that the i-th answer data is of an affirmative part of speech, before the i-th initial user label is used as the i-th updated user label corresponding to the i-th answer data, or if it is determined that the i-th answer data is of a negative part of speech, before the i-th antonym user label of the i-th initial user label is obtained according to a preset user justice and antonym label list, and before the i-th antonym user label is used as the i-th updated user label corresponding to the i-th answer data, the method further includes:

[0074] The answer data part of speech of the i-th answer data is determined based on a pre-stored affirmative word dictionary and a negative word dictionary; wherein the answer data part of speech is an affirmative part of speech or a negative part of speech.

[0075] In this embodiment, since the part of speech of the i-th answer data will affect its corresponding update tag, it is necessary to determine the part of speech of the i-th answer data. Specifically, two dictionaries can be pre-stored in the server, specifically an affirmative word dictionary and a negative word dictionary, and then the keyword of the i-th answer data is compared with each word in the affirmative word dictionary and the negative word dictionary, and the words closest to the keywords of the i-th answer data are found and it is determined whether it belongs to the affirmative word dictionary or the negative word dictionary, so as to finally determine the part of speech of the answer data of the i-th answer data.

[0076] S104: Update the current user tag set according to the updated user tag set to obtain an updated user tag set, and add the updated user points data to the user account information to update the user account information.

[0077] In this embodiment, after obtaining the updated user tag set, each tag included in the updated user tag set is added to the current user tag set, and then the duplicate user tags are removed to obtain the updated user tag set. The updated user tag set is the latest version of the user tag set immediately updated after the current round of answering questions, and can be used as the user tag set at the beginning of the next round of answering questions.

[0078] At the same time, the updated user points data needs to be added to the user account information. For example, if the user accumulated points data corresponding to the previous user account information is Score1, and the updated user points data is Score2, the sum of Score2+Score1 is used to update the user accumulated points data in the user account information. It can be seen that by continuously pushing question sets and answering them, the user tags and user points can be updated in a timely manner.

[0079] In specific implementation, the risk level of the user in a specified field (such as financial risk tolerance indicators) can also be obtained based on the user's response data. More specifically, the risk tolerance level of the user in the financial field is determined based on the combination of finance-related tags in the updated user tag set.

[0080] The embodiment of the present application can acquire and process data in the relevant servers based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0081] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0082] This method makes data analysis and user label extraction of the interaction process more efficient, and the analysis results can be used as reference data for the next round of dialogue.

[0083] The embodiment of the present application also provides an artificial intelligence-based conversation interaction data processing device, which is used to execute any embodiment of the artificial intelligence-based conversation interaction data processing method. Figure 3 , Figure 3 It is a schematic block diagram of an artificial intelligence-based conversational interaction data processing device 100 provided in an embodiment of the present application.

[0084] Among them, Figure 3 As shown, the artificial intelligence-based dialogue interaction data processing device 100 includes a login information acquisition unit 101, a current pushed question set acquisition unit 102, an updated tag set acquisition unit 103 and a user tag set update unit 104.

[0085] The login information acquisition unit 101 is used to acquire the user account information related to the user successful login instruction and acquire the current date feature information when a user successful login instruction is detected; wherein the current date feature information includes holiday features and news information features of the day.

[0086] In this embodiment, the technical solution is described with the server as the execution subject. An intelligent customer service robot is deployed in the server, which can automatically push the screened question set and news information data to the user end, and update the user tag and user score data based on the answer data set and news information data click feedback data sent by the user end, and continuously and dynamically adjust the user tag to push the next data more accurately.

[0087] Specifically, when a user uses a user terminal in the form of a smartphone, tablet computer, laptop computer, etc. to start the application and log in to the user account (successful login to the user account can trigger the user successful login instruction) to establish a communication connection with the server, the interactive interface of the intelligent customer service robot is displayed on the user terminal interface, so that the intelligent customer service robot can push information to the user terminal, or the user terminal can send questions to be consulted or other interactive information to the intelligent customer service robot. In the process of mutual interaction, the intelligent customer service robot can further analyze and extract user tags based on the user's answer data to update the user portrait, and the user can also obtain the required information from the intelligent customer service robot.

[0088] When the user uses the client to start the application and logs in to the user account, the server first obtains the user account information corresponding to the successful login instruction of the user, wherein the user account information includes basic user information (such as user nickname, gender, age, user interests and hobbies, etc.), user login history, user login history IP address information, etc. In addition, the server also obtains the current date feature information. For example, if the current date corresponds to a holiday, the holiday feature of the current date feature information is the name of the holiday. If the current date corresponds to one or more hot news information, the news information feature of the day of the current date feature information is the news information keywords of the above one or more hot news information.

[0089] In one embodiment, the artificial intelligence-based conversation interaction data processing device 100 further includes:

[0090] An information type acquisition unit, configured to acquire the interaction information and the information type corresponding to the interaction information if interaction information sent by the user terminal is detected;

[0091] An interaction identification data acquisition unit, used to acquire an identification model corresponding to the information type, identify the interaction information according to the identification model, and obtain interaction identification data;

[0092] a voice type acquisition unit, configured to acquire a user age range corresponding to the interaction information, and determine a voice type of the message to be replied to according to the user age range;

[0093] A reply data acquisition unit, configured to acquire corresponding reply data in a local knowledge base according to the semantic vector of the interaction recognition data;

[0094] A reply voice data generating unit, used for generating corresponding reply voice data according to the voice type of the message to be replied from the reply data;

[0095] The reply voice data sending unit is used to send the reply voice data to the user terminal.

[0096] In this embodiment, when the user uses the user terminal to establish communication with the intelligent customer service robot in the server, interactive information can be sent to it. The interactive information sent can be of text type, voice type, picture type, etc. In order to extract the text information in the interactive information more quickly, it is necessary to first determine the information type of the interactive information, such as text type, voice type, picture type, etc.

[0097] At this time, if it is determined that the information type of the interactive information is a text type, first obtain a text recognition model (such as a Transformer model, etc.), and then obtain the text recognition information corresponding to the interactive information based on the text recognition model as interactive recognition data. If it is determined that the information type of the interactive information is a picture type, first obtain an image recognition model (such as a convolutional neural network model, etc.), and then obtain the image text recognition information corresponding to the interactive information based on the image recognition model as interactive recognition data. If it is determined that the information type of the interactive information is a voice type, first obtain a voice recognition type (such as an N-gram model, also known as a multivariate model, etc.), and then obtain the voice text recognition model corresponding to the interactive information based on the voice recognition model as interactive recognition data. After obtaining the interactive recognition data, you can further obtain

[0098] Since the user account information can be obtained when the user is identified at the source end of the interactive information, that is, the user end, the user age range can be obtained based on the user account information of the user end. After determining the user age range (such as dividing males aged 0-20 into male adolescents, males aged 20-40 into male youths, males aged 40-60 into male middle-aged, males aged 60 and above into male elderly, etc., and females can also refer to males and be divided into four stages), the voice type of the message to be replied corresponding to the user age range can be obtained. For example, if the user age range is 20-40 years old, it corresponds to the first voice type of the message to be replied (such as the first voice type of the message to be replied is the voice type of a young female voice). It can be seen that a type of voice message to be replied is determined based on each user age range, which facilitates the subsequent synthesis of the reply data into the corresponding reply voice data based on the voice message type to be replied as the sound parameter, thereby increasing the diversity of the reply voice data type.

[0099] After that, the general interactive information is the user's question data. In order to obtain the reply answer to the question data more quickly, the semantic vector of the interactive recognition data can be obtained first, and then the reply semantic vector with the maximum vector similarity value with the semantic vector is obtained in the local knowledge base as the target semantic vector, and finally the original text data corresponding to the target semantic vector is obtained as the reply data. It can be seen that based on the semantic similarity matching method, the reply data corresponding to the interactive recognition data can be quickly and accurately obtained.

[0100] Finally, after obtaining the text corresponding to the reply data, the type of voice message to be replied can be used as a sound parameter to synthesize the reply data into the corresponding reply voice data, and the reply voice data can be sent to the user end to complete this round of interaction between the user and the intelligent customer service robot. Moreover, during the interaction process, the user age range and the type of voice message to be replied can be obtained, and the basic user data is accumulated for the next round of user interaction. Among them, it should be noted that all the user data obtained are legally obtained under the premise of obtaining user authorization.

[0101] In one embodiment, as a specific embodiment of obtaining the user age range based on the interaction information, obtaining the user age range corresponding to the interaction information includes:

[0102] If it is determined that the interaction information is speech type data, obtaining a Mel frequency cepstral coefficient feature corresponding to the interaction information;

[0103] The Mel-frequency cepstral coefficient feature is input into a pre-trained voice age range classification model to obtain the user age range.

[0104] In this embodiment, the interaction information can be framed in turn, power spectrum can be estimated using the periodogram method, the power spectrum can be filtered using a Mel filter bank, the energy in each filter can be calculated, the energy of each filter can be logarithmized, a DCT transform (i.e., discrete cosine transform) can be performed, and the 2nd to 13th coefficients of the DCT can be retained and processed to obtain the Mel-frequency cepstrum coefficient characteristics corresponding to the interaction information.

[0105] Specifically, when the interactive information is framed, the first step is to divide it into frames of 20-40ms (optimally 25ms), and extract 12 features from each frame to obtain framed data. The second step is to perform DCT transform on each frame of the framed data to obtain the DCT transform result. The third step is to use the periodogram method to estimate the power spectrum of the DCT transform result to obtain an estimated power spectrum. The fourth step is to filter the estimated power spectrum by 26 vector groups of length 257 (i.e., a triangular filter group) to obtain a filtered signal. The fifth step is to take the log of the filtered signal to obtain a logarithmic operation result. The sixth step is to perform a discrete cosine transform on the logarithmic operation result to obtain 26 cepstral coefficients. The seventh step is to retain the 2nd to 13th 12 cepstral coefficients of the 26 cepstral coefficients to form MFCC features (i.e., Mel frequency cepstral coefficient features).

[0106] After obtaining the Mel frequency cepstral coefficient features corresponding to the interaction information, the voice age range classification model stored locally on the server, such as SVM (i.e. support vector machine), GMM (i.e. Gaussian mixture model), etc., can be obtained, and the Mel frequency cepstral coefficient features can be input into the pre-trained voice age range classification model for classification to obtain the user age range. It can be seen that this method can accurately obtain the user age range based on the interaction information.

[0107] The current push question set acquisition unit 102 is used to acquire the current user tag set according to the user account information and the current date feature information, acquire the current push question set according to the current user tag set, and send the current push question set to the user terminal corresponding to the user successful login instruction.

[0108] In this embodiment, after the server obtains the user account information and the current date feature information, the current user tag set can be obtained by integrating the user's initial user tag set extracted from the user account information and the holiday features and the news information features of the day in the current date feature information. Then, based on the current user tag set, the current push question set corresponding to the current user tag set is screened out from the question library deployed in the server, and the current push question set is sent to the user end.

[0109] In one embodiment, the acquiring the current user tag set according to the user account information and the current date characteristic information includes:

[0110] Obtain user interest keywords and user basic information of the user account information, and convert the user interest keywords and the user basic information into corresponding user tags according to a preset user tag conversion strategy to form an initial tag set of the current user.

[0111] In this embodiment, the user interest and hobby keywords in the user account information are generally keywords selected by the user according to his or her own interests and hobbies at the time of initial registration. The tags obtained by converting the above keywords based on the preset user tag conversion strategy constitute the first type of initial user tag set. And the user's basic information is also filled in by the user according to his or her actual situation (such as age, gender, education, etc.), and the tags obtained by these basic information based on the preset user tag conversion strategy constitute the second type of initial user tag set. The first type of initial user tag set is combined with the second type of initial user tag set to obtain the current user initial tag set. Finally, the date tag corresponding to the current date feature information is integrated into the current user initial tag set to obtain the current user tag set. It can be seen that this method is to obtain multi-dimensional user tags through user interest and hobby keywords, user basic information and current date feature information, and can obtain user tag sets with more dimensional tags, and the user image portrayed is more accurate.

[0112] In one embodiment, obtaining the current push question set according to the current user tag set includes:

[0113] The pushed questions corresponding to each user tag in the current user tag set in the local question library are obtained to form a current pushed question set.

[0114] In this embodiment, after the current user tag set is obtained, the corresponding push questions in the local question library can be obtained based on each user tag. For example, taking the example of obtaining the push questions corresponding to a user tag, the first step is to obtain the tag category corresponding to the user tag (such as a financial tag, an investment tag, a sports tag, etc.), and then obtain the high-heat questions corresponding to the tag category (such as the question with the highest heat value under the tag category can be regarded as a high-heat question), and finally use the high-heat questions corresponding to the tag category as the push questions for the user tag. Referring to the above method, the push questions corresponding to other user tags in the current user tag set can also be obtained. After the push questions corresponding to each user tag in the current user tag set are obtained, the current push question set can be formed and sent to the user end. It can be seen that through the above method, a push question set can be quickly obtained based on user tags.

[0115] The updated tag set acquisition unit 103 is used to, if an answer data set corresponding to the current pushed question set is received, acquire the updated user tag set corresponding to the current user tag set according to the answer data set, and acquire the updated user score data according to the answer data set.

[0116] In this embodiment, after the user terminal receives the current set of pushed questions, it can give a specific answer to each pushed question. For example, each pushed question is a question-and-answer question with a check mark of "yes" or "no". The user can operate the user terminal to answer each pushed question separately and obtain the answer data for each pushed question. After answering the current set of pushed questions in the user terminal, the corresponding answer data set is obtained. After the server receives the answer data set sent by the user terminal, it can perform data analysis on the answer data set to determine whether each answer data can be further converted into a new user tag. After completing the determination of whether each answer data can be converted into a new user tag, the updated user tag set corresponding to the current user tag set can be obtained.

[0117] Moreover, the user points can be determined based on each answer data in the answer data set. For example, the total number of answer data with a definite answer (such as yes or no in the above example) in the above answer question can be set, and the conversion strategy of one point for each definite answer can be used to obtain the answer data set to update the user points data. It can be seen that after the user completes the information interaction with the intelligent customer service robot, the user tag data and points data are updated in time, which can serve as the data basis for the next push question.

[0118] In one embodiment, the acquiring, according to the answer data set, an updated user tag set corresponding to the current user tag set includes:

[0119] Obtain the i-th answer data in the answer data set; wherein the initial value of i is 1 and the value range of i is [1, N], and N is the total number of answer data in the answer data set;

[0120] If it is determined that the i-th answer data is a non-null value, obtain the i-th currently pushed question corresponding to the i-th answer data;

[0121] Get the i-th initial user tag corresponding to the i-th currently pushed question;

[0122] If it is determined that the i-th answer data is a positive part of speech, the i-th initial user label is used as the i-th updated user label corresponding to the i-th answer data;

[0123] If it is determined that the i-th answer data is of a negative part of speech, the i-th antonym user label of the i-th initial user label is obtained according to the preset user righteousness and antonym label list, and the i-th antonym user label is used as the i-th updated user label corresponding to the i-th answer data;

[0124] Increase i by 1 to update the value of i;

[0125] If it is determined that i does not exceed N, return to execute the step of obtaining the i-th answer data in the answer data set;

[0126] If it is determined that i exceeds N, the first updated user tag to the Nth updated user tag are obtained to form an updated user tag set.

[0127] In this embodiment, the user label is updated by taking the i-th answer data as an example. Specifically, it is first determined whether the answer data is a null value. If it is determined that the i-th answer data is a null value, it means that the user has not answered the i-th currently pushed question. The i-th answer data has no effect on the user label update.

[0128] If it is determined that the i-th answer data is not a null value, it means that the user has answered the i-th currently pushed question. The i-th answer data has an impact on the user label update, specifically, it determines whether the user answers affirmatively or negatively. When it is determined that the i-th answer data is of the affirmative part of speech, the i-th initial user label corresponding to the i-th currently pushed question does not need to be adjusted, and the i-th initial user label can be used as the i-th updated user label corresponding to the i-th answer data. When it is determined that the i-th answer data is of the negative part of speech, the i-th initial user label corresponding to the i-th currently pushed question needs to be adjusted, and the i-th antonym user label corresponding to the i-th initial user label can be used as the i-th updated user label corresponding to the i-th answer data. It can be seen that the user label is continuously updated based on the user's real-time answer, so that the user label set used as the reference data for the next question push is updated in a timely manner, and the question set can be pushed more objectively and accurately.

[0129] In one embodiment, if it is determined that the i-th answer data is of an affirmative part of speech, before the i-th initial user label is used as the i-th updated user label corresponding to the i-th answer data, or if it is determined that the i-th answer data is of a negative part of speech, before the i-th antonym user label of the i-th initial user label is obtained according to a preset user justice and antonym label list, and before the i-th antonym user label is used as the i-th updated user label corresponding to the i-th answer data, the method further includes:

[0130] The answer data part of speech of the i-th answer data is determined based on a pre-stored affirmative word dictionary and a negative word dictionary; wherein the answer data part of speech is an affirmative part of speech or a negative part of speech.

[0131] In this embodiment, since the part of speech of the i-th answer data will affect its corresponding update tag, it is necessary to determine the part of speech of the i-th answer data. Specifically, two dictionaries can be pre-stored in the server, specifically an affirmative word dictionary and a negative word dictionary, and then the keyword of the i-th answer data is compared with each word in the affirmative word dictionary and the negative word dictionary, and the words closest to the keywords of the i-th answer data are found and it is determined whether it belongs to the affirmative word dictionary or the negative word dictionary, so as to finally determine the part of speech of the answer data of the i-th answer data.

[0132] The user tag set updating unit 104 is used to update the current user tag set according to the updated user tag set to obtain an updated user tag set, and add the updated user points data to the user account information to update the user account information.

[0133] In this embodiment, after obtaining the updated user tag set, each tag included in the updated user tag set is added to the current user tag set, and then the duplicate user tags are removed to obtain the updated user tag set. The updated user tag set is the latest version of the user tag set immediately updated after the current round of answering questions, and can be used as the user tag set at the beginning of the next round of answering questions.

[0134] At the same time, the updated user points data needs to be added to the user account information. For example, if the user accumulated points data corresponding to the previous user account information is Score1, and the updated user points data is Score2, the sum of Score2+Score1 is used to update the user accumulated points data in the user account information. It can be seen that by continuously pushing question sets and answering them, the user tags and user points can be updated in a timely manner.

[0135] In specific implementation, the risk level of the user in a specified field (such as financial risk tolerance indicators) can also be obtained based on the user's response data. More specifically, the risk tolerance level of the user in the financial field is determined based on the combination of finance-related tags in the updated user tag set.

[0136] The device makes data analysis and user tag extraction of the interaction process more efficient, and the analysis results can be used as reference data for the next round of conversation.

[0137] The above-mentioned artificial intelligence-based dialogue interaction data processing device can be implemented in the form of a computer program, and the computer program can be used in Figure 4 Runs on the computer device shown.

[0138] See also Figure 4 , Figure 45 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 is a server or a server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0139] See also Figure 4 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a device bus 501 , wherein the memory may include a storage medium 503 and an internal memory 504 .

[0140] The storage medium 503 may store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 may execute a method for processing conversational interaction data based on artificial intelligence.

[0141] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0142] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the dialogue interaction data processing method based on artificial intelligence.

[0143] The network interface 505 is used for network communication, such as providing data information transmission, etc. Those skilled in the art will understand that Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0144] The processor 502 is used to run a computer program 5032 stored in the memory to implement the artificial intelligence-based dialogue interaction data processing method disclosed in the embodiment of the present application.

[0145] Those skilled in the art will understand that Figure 4The embodiments of the computer device shown in the figure do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such embodiments, the structure and function of the memory and the processor are the same as those of the embodiment of the present invention. Figure 4 The embodiments shown are consistent and will not be described again here.

[0146] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0147] In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the method for processing conversational interaction data based on artificial intelligence disclosed in the embodiment of the present application is implemented.

[0148] It will be clear to those skilled in the art that, for the convenience and simplicity of description, the specific working process of the above-described equipment, devices and units can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It will be appreciated by those of ordinary skill in the art that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0149] In the several embodiments provided in the present application, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, and units with the same function may be combined into one unit. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, or may be electrical, mechanical or other forms of connection.

[0150] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0151] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0152] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a background server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a disk or an optical disk.

[0153] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for processing conversational interaction data based on artificial intelligence, characterized in that: include: If a user successful login instruction is detected, the user account information related to the user successful login instruction is obtained, and the current date characteristic information is obtained; wherein the current date characteristic information includes holiday characteristics and news information characteristics of the day; Acquire a current user tag set according to the user account information and the current date feature information, acquire a current push question set based on the current user tag set, and send the current push question set to a user terminal corresponding to the user successful login instruction; If an answer data set corresponding to the current pushed question set is received, obtaining an updated user tag set corresponding to the current user tag set according to the answer data set, and obtaining updated user score data according to the answer data set; and updating the current user tag set according to the updated user tag set to obtain an updated user tag set, and adding the updated user points data to the user account information to update the user account information; The acquiring, according to the answer data set, an updated user tag set corresponding to the current user tag set comprises: Obtain the i-th answer data in the answer data set; wherein the initial value of i is 1 and the value range of i is [1, N], and N is the total number of answer data in the answer data set; If it is determined that the i-th answer data is a non-null value, obtain the i-th currently pushed question corresponding to the i-th answer data; Get the i-th initial user tag corresponding to the i-th currently pushed question; If it is determined that the i-th answer data is a positive part of speech, the i-th initial user label is used as the i-th updated user label corresponding to the i-th answer data; If it is determined that the i-th answer data is of a negative part of speech, the i-th antonym user label of the i-th initial user label is obtained according to the preset user righteousness and antonym label list, and the i-th antonym user label is used as the i-th updated user label corresponding to the i-th answer data; Increase i by 1 to update the value of i; If it is determined that i does not exceed N, return to execute the step of obtaining the i-th answer data in the answer data set; If it is determined that i exceeds N, the first updated user tag to the Nth updated user tag are obtained to form an updated user tag set.

2. The method for processing conversational interaction data based on artificial intelligence according to claim 1, characterized in that: If a user successful login instruction is detected, obtaining the user account information related to the user successful login instruction and obtaining the current date feature information also includes: If the interaction information sent by the user terminal is detected, the interaction information and the information type corresponding to the interaction information are obtained; Acquire a recognition model corresponding to the information type, and recognize the interaction information according to the recognition model to obtain interaction recognition data; Acquire a user age range corresponding to the interaction information, and determine a voice type of the message to be replied to according to the user age range; Acquire corresponding reply data in a local knowledge base according to the semantic vector of the interactive recognition data; Generate corresponding reply voice data from the reply data according to the voice type of the message to be replied; The reply voice data is sent to the user terminal.

3. The method for processing conversational interaction data based on artificial intelligence according to claim 2, characterized in that: The obtaining the user age range corresponding to the interaction information includes: If it is determined that the interaction information is speech type data, obtaining a Mel frequency cepstral coefficient feature corresponding to the interaction information; The Mel-frequency cepstral coefficient feature is input into a pre-trained voice age range classification model to obtain the user age range.

4. The method for processing conversational interaction data based on artificial intelligence according to claim 1, characterized in that: The acquiring the current user tag set according to the user account information and the current date feature information includes: Obtain user interest keywords and user basic information of the user account information, and convert the user interest keywords and the user basic information into corresponding user tags according to a preset user tag conversion strategy to form an initial tag set of the current user.

5. The method for processing conversational interaction data based on artificial intelligence according to claim 1, characterized in that: The obtaining the current pushed question set based on the current user tag set includes: The pushed questions corresponding to each user tag in the current user tag set in the local question library are obtained to form a current pushed question set.

6. The method for processing conversational interaction data based on artificial intelligence according to claim 1, characterized in that: If the i-th answer data is determined to be of an affirmative part of speech, before the i-th initial user label is used as the i-th updated user label corresponding to the i-th answer data, or if the i-th answer data is determined to be of a negative part of speech, before the i-th antonym user label of the i-th initial user label is obtained according to a preset user justice and antonym label list, and before the i-th antonym user label is used as the i-th updated user label corresponding to the i-th answer data, the method further includes: The answer data part of speech of the i-th answer data is determined based on a pre-stored affirmative word dictionary and a negative word dictionary; wherein the answer data part of speech is an affirmative part of speech or a negative part of speech.

7. A conversational interaction data processing device based on artificial intelligence, characterized in that: include: A login information acquisition unit, for acquiring user account information related to the user successful login instruction and acquiring current date feature information if a user successful login instruction is detected; wherein the current date feature information includes holiday features and news information features of the day; A current push question set acquisition unit, configured to acquire a current user tag set according to the user account information and the current date feature information, acquire a current push question set based on the current user tag set, and send the current push question set to a user terminal corresponding to the user successful login instruction; an updated tag set acquisition unit, configured to, upon receiving an answer data set corresponding to the current pushed question set, acquire an updated user tag set corresponding to the current user tag set according to the answer data set, and acquire updated user score data according to the answer data set; and A user tag set updating unit, configured to update the current user tag set according to the updated user tag set to obtain an updated user tag set, and add the updated user points data to the user account information to update the user account information; The acquiring, according to the answer data set, an updated user tag set corresponding to the current user tag set comprises: Obtain the i-th answer data in the answer data set; wherein the initial value of i is 1 and the value range of i is [1, N], and N is the total number of answer data in the answer data set; If it is determined that the i-th answer data is a non-null value, obtain the i-th currently pushed question corresponding to the i-th answer data; Get the i-th initial user tag corresponding to the i-th currently pushed question; If it is determined that the i-th answer data is a positive part of speech, the i-th initial user label is used as the i-th updated user label corresponding to the i-th answer data; If it is determined that the i-th answer data is of a negative part of speech, the i-th antonym user label of the i-th initial user label is obtained according to the preset user righteousness and antonym label list, and the i-th antonym user label is used as the i-th updated user label corresponding to the i-th answer data; Increase i by 1 to update the value of i; If it is determined that i does not exceed N, return to execute the step of obtaining the i-th answer data in the answer data set; If it is determined that i exceeds N, the first updated user tag to the Nth updated user tag are obtained to form an updated user tag set.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for processing conversational interaction data based on artificial intelligence as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to execute the artificial intelligence-based dialogue interaction data processing method as described in any one of claims 1 to 6.