Information consultation method and system based on artificial intelligence

Abstract

The invention discloses an information consultation method and system based on artificial intelligence, and relates to the technical field of information consultation management, and the method comprises the steps: obtaining real-time consultation information based on an information consultation server; performing judgment processing according to the real-time consultation information, and determining the type of the real-time consultation information; if the real-time consultation information is text consultation information; and based on an intelligent analysis system, analyzing and processing the text consultation information to obtain first core consultation information. According to the invention, image acquisition is carried out on the information consultation server through the industrial camera, and the mode of the information consultation server is selected according to the real-time image information, so that a user who cannot write characters can carry out information consultation through voice, and the user can quickly and accurately obtain a desired reply; and information consultation reply is carried out for users of different languages, so that the comprehensiveness of the information consultation system is improved, the user experience is improved, and the consultation time of the user is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of information consultation management, and in particular to an information consultation method and system based on artificial intelligence. Background Art

[0002] Consulting is similar to asking for advice, inquiring, and negotiating, while service means providing help. The literal meaning of consulting service is to provide help in solving problems. In a broad sense, any question-and-answer event involving asking for advice, inquiring, and negotiating can be regarded as consulting service for the questioning party, such as A asking B for directions. With the rapid development of society, the consulting service industry has emerged. The consulting service industry refers to the intellectual service industry in which professional consulting institutions rely on information and professional knowledge advantages, use modern analytical methods, conduct creative thinking activities to solve various complex social, economic, and technological problems, and provide customers with decision-making basis and optimization solutions.

[0003] When people who speak different languages ​​or cannot write seek information in an information consultation system, the information consultation system cannot give a corresponding answer, resulting in the user being unable to obtain a corresponding answer in the information consultation system, reducing the user's experience with the information consultation system and wasting the user's consultation time. Summary of the invention

[0004] In order to solve the above technical problems, an information consultation method and system based on artificial intelligence are provided. This technical solution solves the problem raised in the above background technology that when people who use different languages ​​or people who cannot write seek information in the information consultation system, the information consultation system cannot make corresponding answers, resulting in users being unable to obtain corresponding answers in the information consultation system, reducing the user's experience of the information consultation system and wasting the user's consultation time.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An information consultation method based on artificial intelligence, comprising:

[0007] Based on the information consultation service end, obtain real-time consultation information;

[0008] Performing judgment and processing according to the real-time consultation information to determine the type of the real-time consultation information, wherein the type of the real-time consultation information is any one of voice consultation information or text consultation information;

[0009] If the real-time consultation information is text consultation information;

[0010] Based on the intelligent analysis system, the text consultation information is analyzed and processed to obtain the first core consultation information;

[0011] Based on the first core consultation information, the database system is processed for information matching, and the first reply information is output;

[0012] If the real-time consultation information is voice consultation information;

[0013] Constructing a speech processing model, analyzing and processing the speech consultation information through the speech processing model, and obtaining conversion consultation information, wherein the conversion consultation information includes speech type and speech content;

[0014] Based on the intelligent analysis system, the voice content is analyzed and processed to obtain the second core consulting information;

[0015] Based on the second core consultation information, the database system is processed for information matching and the second reply information is output.

[0016] Preferably, the step of obtaining real-time consulting information based on the information consulting service terminal specifically includes the following steps:

[0017] Acquiring touch information from the information consultation service end, wherein the touch information is any one of text information and non-text information;

[0018] Use industrial cameras to collect images from the information consulting server to obtain real-time image information;

[0019] Based on the image recognition algorithm, the real-time image information is analyzed to determine the occlusion duration information;

[0020] Analyze and process the occlusion duration information and touch information to obtain real-time consulting information.

[0021] Preferably, the step of analyzing and processing the occlusion duration information and the touch information to obtain the real-time consulting information specifically includes the following steps:

[0022] Perform judgment and processing according to the occlusion duration information and the set first threshold;

[0023] If the occlusion duration information is greater than or equal to the set first threshold, and the touch information is non-text information, the information consultation service end starts the intelligent voice communication mode to obtain the voice consultation information;

[0024] If the occlusion duration information is greater than or equal to the set first threshold, and the touch information is text information, the information consultation server starts a text collection mode to obtain text consultation information;

[0025] If the occlusion duration information is less than the set first threshold, the information consultation service end does not collect information.

[0026] Preferably, the information consultation service end starts the intelligent voice communication mode, and obtaining the voice consultation information specifically includes the following steps:

[0027] Based on intelligent voice communication mode, obtain real-time environmental signals;

[0028] Analyze and judge real-time environmental signals based on natural language processing algorithms;

[0029] If the real-time environmental information does not contain voice signals, turn off the intelligent voice communication mode;

[0030] If the real-time environmental information contains voice signals, the real-time environmental information is subjected to voice extraction through a feature extraction algorithm to obtain voice consultation information.

[0031] Preferably, the step of analyzing and processing the text consultation information based on the intelligent analysis system to obtain the first core consultation information specifically includes the following steps:

[0032] Based on the intelligent analysis system, the text consultation information is identified and the language type of the text is determined;

[0033] Based on the language type of the text, the text consultation information is converted through language conversion to obtain text consultation conversion information;

[0034] Based on the intelligent analysis system, preprocessing the text consultation conversion information to obtain complete text consultation information, wherein the preprocessing includes text cleaning, removal of stop words and vocabulary standardization;

[0035] Based on the intelligent analysis system, the complete text consultation information is extracted and processed to obtain multiple groups of vocabulary information;

[0036] Sorting and processing are performed according to multiple groups of vocabulary information to obtain first core consulting information;

[0037] The specific calculation model for obtaining the first core consulting information is:

[0038]

[0039] In the formula, B c The first core consulting information; B i is the number of times each word appears in multiple sets of vocabulary information; n is the type of vocabulary in multiple sets of vocabulary information; max() is the maximum value function.

[0040] Preferably, the construction of the speech processing model, analyzing and processing the speech consultation information through the speech processing model, and obtaining the conversion consultation information specifically comprises the following steps:

[0041] Based on the speech processing model, the language of the voice consultation information is analyzed to determine the voice type;

[0042] Based on the speech processing model, the speech consultation information is subjected to speech preprocessing to obtain interference-free speech consultation information, wherein the speech preprocessing includes sampling, denoising, enhancement, and muting;

[0043] Based on the speech type, vocabulary information and linguistic rules corresponding to the speech type are read from the database system;

[0044] Based on vocabulary information and linguistic rules, the interference-free voice consultation information is segmented to obtain multiple segments of interference-free voice consultation information;

[0045] Based on the speech processing model, multiple segments of non-interference voice consultation information are converted into language to obtain the speech content.

[0046] Preferably, the step of segmenting the interference-free voice consultation information based on vocabulary information and linguistic rules to obtain multiple segments of interference-free voice consultation information specifically includes the following steps:

[0047] Based on the vocabulary information, part-of-speech matching is performed on the non-interference voice consultation information to obtain part-of-speech information;

[0048] Based on part-of-speech information and linguistic rules, the non-interfering speech consultation information is analyzed to determine the speech segmentation position;

[0049] Based on the voice segmentation position, the interference-free voice consultation information is segmented to obtain multiple segments of interference-free voice consultation information.

[0050] Preferably, the step of performing information matching processing on the database system based on the second core consultation information and outputting the second reply information specifically comprises the following steps:

[0051] The intelligent analysis system establishes a temporary communication connection with the database system;

[0052] The intelligent analysis system uses the second core consulting information as a feature to match the information in the database system and obtain the answer to the consulting information;

[0053] Based on the voice processing model, the reply answer to the consultation information is output as second reply information, and the second reply information includes text reply information and voice reply information.

[0054] Preferably, the step of outputting the consultation information reply answer as the second reply information based on the speech processing model specifically comprises the following steps:

[0055] Based on part-of-speech information, linguistic rules and vocabulary information, the consultation information reply answer is converted into text reply information and voice reply information through the speech processing model;

[0056] The intelligent analysis system outputs the text reply information to the display of the information consultation service end;

[0057] The intelligent analysis system outputs the voice reply information to the microphone of the information consultation service end.

[0058] Furthermore, an information consultation system based on artificial intelligence is proposed, which is used to implement the above-mentioned information consultation method based on artificial intelligence, including:

[0059] An information consultation service end, wherein the information consultation service end is used to conduct information consultation and output a first reply information and a second reply information;

[0060] An information determination module, which is used to determine the real-time consultation information and the type of the real-time consultation information;

[0061] An intelligent analysis system, wherein the intelligent analysis system is used to analyze the text consultation information and the voice content to determine the first reply information and the second reply information;

[0062] A database system, the database system is used to store reply answers corresponding to real-time consultation information and vocabulary information and linguistic rules corresponding to voice types;

[0063] A speech processing model, wherein the speech processing model is used to pre-process the speech consultation information to obtain interference-free speech consultation information; the speech processing model is used to analyze and convert the speech consultation information to output text reply information and speech reply information;

[0064] A text preprocessing module, which is used to preprocess the text consultation information to obtain complete text consultation information;

[0065] An industrial camera, which is used to collect images from the information consulting service end and obtain real-time image information;

[0066] An image analysis module, which is used to analyze real-time image information and determine the occlusion duration;

[0067] Control module, the control module is used to realize data transmission and information interaction between modules.

[0068] Compared with the prior art, the present invention provides an information consultation method and system based on artificial intelligence, which has the following beneficial effects:

[0069] The present invention collects images of the information consultation service end through an industrial camera, selects the mode of the information consultation service end according to the real-time image information, enables users who cannot write text to conduct information consultation through voice, and enables users to quickly and accurately obtain the desired replies. In addition, information consultation replies are also provided for users of different languages, thereby improving the comprehensiveness of the information consultation system. At the same time, it also improves the user experience and shortens the user's consultation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 This is a flow chart of steps S100-S900 in an information consultation method based on artificial intelligence proposed by the present invention;

[0071] Figure 2 This is a flow chart of steps S101-S104 in an information consultation method based on artificial intelligence proposed by the present invention;

[0072] Figure 3 This is a flow chart of steps S1041-S1044 in an information consultation method based on artificial intelligence proposed by the present invention;

[0073] Figure 4 This is a flow chart of steps S10421-S10424 in an information consultation method based on artificial intelligence proposed by the present invention;

[0074] Figure 5 This is a flow chart of steps S401-S405 in an information consultation method based on artificial intelligence proposed by the present invention;

[0075] Figure 6 This is a flow chart of steps S701-S705 in an information consultation method based on artificial intelligence proposed by the present invention;

[0076] Figure 7 This is a flowchart of steps S7041-S7043 in an information consultation method based on artificial intelligence proposed by the present invention.

[0077] Figure 8 This is a flowchart of steps S901-S903 in an information consultation method based on artificial intelligence proposed by the present invention.

[0078] Fig. 9 This is a flow chart of steps S9031-S9033 in an information consultation method based on artificial intelligence proposed by the present invention.

[0079] Fig.10 This is a structural block diagram of an information consultation system based on artificial intelligence proposed by the present invention. DETAILED DESCRIPTION

[0080] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0081] Reference Figure 1 As shown, an information consultation method based on artificial intelligence includes:

[0082] S100, obtaining real-time consulting information based on the information consulting service end;

[0083] S200, judging and processing the real-time consultation information to determine the type of the real-time consultation information, wherein the type of the real-time consultation information is any one of voice consultation information and text consultation information;

[0084] S300, if the real-time consulting information is text consulting information;

[0085] S400, analyzing and processing the text consultation information based on the intelligent analysis system to obtain first core consultation information;

[0086] S500, based on the first core consultation information, performing information matching processing on the database system and outputting first reply information;

[0087] S600: If the real-time consultation information is voice consultation information;

[0088] S700: construct a speech processing model, analyze and process the speech consultation information through the speech processing model, and obtain conversion consultation information, wherein the conversion consultation information includes speech type and speech content;

[0089] S800, based on the intelligent analysis system, analyze and process the voice content to obtain the second core consulting information;

[0090] S900, based on the second core consultation information, performing information matching processing on the database system and outputting second reply information;

[0091] Those skilled in the art can understand that the information consultation group includes groups that use different languages, can write and cannot write, etc. When a user who cannot write needs to conduct information consultation, the industrial camera on the information consultation server is used to capture images of the front side of the information consultation server, and combined with the real-time image information, the voice communication mode on the information consultation server is selected to communicate with the user. Even if the user cannot write, the information consultation can be completed through voice communication, giving the user an excellent experience in using the information consultation server. In addition, when users of different languages ​​are detected, the same language is used to communicate with the user according to the type of language in the database, so that users of different languages ​​can also complete information consultation.

[0092] Reference Figure 2 As shown, based on the information consultation service end, obtaining real-time consultation information specifically includes the following steps:

[0093] S101, acquiring touch information from an information consultation service end, wherein the touch information is any one of text information and non-text information;

[0094] S102, collecting images of the information consulting service end through an industrial camera to obtain real-time image information;

[0095] S103, analyzing the real-time image information based on the image recognition algorithm to determine the occlusion duration information;

[0096] S104, analyzing and processing the occlusion duration information and the touch information to obtain real-time consulting information;

[0097] In this embodiment, the information consultation service may be voice consultation or text consultation. Therefore, the touch information of the information consultation service end is analyzed to determine whether the touch information is text information. If it is not text information, it is combined with the user's occlusion time information on the information consultation service end to determine whether the user is a group that cannot write.

[0098] Reference Figure 3 As shown, the following steps are specifically included for analyzing and processing the occlusion duration information and the touch information to obtain the real-time consulting information:

[0099] S1041, performing judgment processing according to the occlusion duration information and setting a first threshold;

[0100] S1042: If the occlusion duration information is greater than or equal to the set first threshold, and the touch information is non-text information, the information consultation server starts an intelligent voice communication mode to obtain voice consultation information;

[0101] S1043: If the occlusion duration information is greater than or equal to the set first threshold, and the touch information is text information, the information consultation server starts a text collection mode to obtain text consultation information;

[0102] S1044: If the occlusion duration information is less than the set first threshold, the information consultation service end does not collect information;

[0103] In this embodiment, if the occlusion duration information is greater than or equal to the set first threshold and the touch information is non-text information, the intelligent voice communication mode of the information consultation service end is turned on to determine whether the user is a consultation group that cannot write text, so that groups that cannot write text can also provide information consultation.

[0104] Reference Figure 4As shown, the information consultation server turns on the intelligent voice communication mode, and obtaining voice consultation information specifically includes the following steps:

[0105] S10421. Obtain real-time environmental signals based on intelligent voice communication mode;

[0106] S10422. Analyze and judge real-time environmental signals based on natural language processing algorithms;

[0107] S10423. If the real-time environmental information does not contain a voice signal, turn off the intelligent voice communication mode;

[0108] S10424. If the real-time environment information contains a voice signal, perform voice extraction on the real-time environment information using a feature extraction algorithm to obtain voice consultation information;

[0109] In this embodiment, if no voice signal is detected in the real-time environmental signal, it means that the user staying at the information consultation service end is not seeking information and may just be staying here. Therefore, when no voice signal is detected, the intelligent voice communication mode is turned off.

[0110] Reference Figure 5 As shown, based on the intelligent analysis system, analyzing and processing the text consultation information to obtain the first core consultation information specifically includes the following steps:

[0111] S401, based on the intelligent analysis system, perform language recognition on the text consultation information to determine the language type of the text;

[0112] S402, based on the text language type, convert the text consultation information through language conversion to obtain text consultation conversion information;

[0113] S403, preprocessing the text consultation conversion information based on the intelligent analysis system to obtain complete text consultation information, wherein the preprocessing includes text cleaning, removal of stop words and vocabulary standardization;

[0114] S404, extracting and processing the complete text consultation information based on the intelligent analysis system to obtain multiple groups of vocabulary information;

[0115] S405, performing sorting processing according to the multiple groups of vocabulary information to obtain the first core consulting information;

[0116] The specific calculation model for obtaining the first core consulting information is:

[0117]

[0118] In the formula, B c The first core consulting information; B iis the number of times each word appears in multiple sets of vocabulary information; n is the type of vocabulary in multiple sets of vocabulary information; max() is the maximum value function;

[0119] Those skilled in the art will understand that the text in the text consultation information is not necessarily Chinese characters, but may also be text in other languages. Therefore, it is necessary to perform speech recognition on the text consultation information, determine the language, convert it into Chinese characters according to the language, and then perform feature extraction on the text consultation information, and use the text that appears most frequently in the text consultation information as the core consultation information. It is worth noting that the language is converted into Chinese characters in order to reduce the running memory of the information consultation server, because there are many kinds of languages ​​in the world. If every language is stored, it will cause insufficient storage space on the information consultation server, causing the information consultation server to run unsmoothly, freeze, and other problems.

[0120] Reference Figure 6 As shown, constructing a speech processing model, analyzing and processing the speech consultation information through the speech processing model, and obtaining the conversion consultation information specifically includes the following steps:

[0121] S701, based on the voice processing model, perform language analysis on the voice consultation information to determine the voice type;

[0122] S702, based on the voice processing model, performing voice preprocessing on the voice consultation information to obtain interference-free voice consultation information, wherein the voice preprocessing includes sampling, denoising, enhancement, and muting;

[0123] S703, based on the speech type, reading vocabulary information and linguistic rules corresponding to the speech type from the database system;

[0124] S704, based on the vocabulary information and linguistic rules, segment the interference-free voice consultation information to obtain multiple segments of interference-free voice consultation information;

[0125] S705, based on the voice processing model, performing language conversion on multiple sections of non-interference voice consultation information to obtain voice content;

[0126] It will be understood by those skilled in the art that different languages ​​have different linguistic rules and vocabularies. When different languages ​​are detected, the linguistic rules and vocabulary information of the language are determined through the database system, and the voice consultation information is segmented according to the linguistic rules and vocabulary information, so that the voice consultation information is more orderly and subsequent processing and conversion are more convenient and quick.

[0127] Reference Figure 7 As shown, based on vocabulary information and linguistic rules, segmenting the interference-free voice consultation information to obtain multiple segments of interference-free voice consultation information specifically includes the following steps:

[0128] S7041. Based on the vocabulary information, perform part-of-speech matching on the non-interference voice consultation information to obtain part-of-speech information;

[0129] S7042, analyzing the non-interference voice consultation information based on part-of-speech information and linguistic rules to determine the voice segmentation position;

[0130] S7043. Based on the voice segmentation position, segment the interference-free voice consultation information to obtain multiple segments of interference-free voice consultation information.

[0131] Reference Figure 8 As shown, based on the second core consultation information, performing information matching processing on the database system and outputting the second reply information specifically includes the following steps:

[0132] S901. The intelligent analysis system establishes a temporary communication connection with the database system;

[0133] S902, the intelligent analysis system uses the second core consulting information as a feature to perform information matching on the database system, and obtains a reply answer to the consulting information;

[0134] S903: Based on the voice processing model, output the reply answer to the consultation information as second reply information, where the second reply information includes text reply information and voice reply information;

[0135] In this embodiment, in order to improve the overall fluency of the information consulting system, a temporary communication connection is established between the intelligent analysis system and the database system. When there is no need to read data in the database system, the temporary communication connection is disconnected, making the information consulting system run more smoothly.

[0136] Reference Fig. 9 As shown, based on the speech processing model, outputting the consultation information reply answer as the second reply information specifically includes the following steps:

[0137] S9031. Based on part-of-speech information, linguistic rules and vocabulary information, convert the consultation information reply answer into text reply information and voice reply information through a speech processing model;

[0138] S9032, the intelligent analysis system outputs the text reply information to the display of the information consultation service end;

[0139] S9033, the intelligent analysis system outputs the voice reply information to the microphone of the information consultation service end;

[0140] It will be understood by those skilled in the art that voice reply information is instantaneous. When the voice reply information is played, if the user does not hear it clearly within the playing time, the information inquiry will be blurred and the reply answer will be inaccurate. Therefore, converting the voice reply information into text and displaying it synchronously on the display of the information inquiry server reduces the inaccuracy of the reply answer and improves the user experience.

[0141] Reference Fig.10 As shown, an information consultation system based on artificial intelligence is used to implement the above-mentioned information consultation method based on artificial intelligence, including:

[0142] An information consultation service end, wherein the information consultation service end is used to conduct information consultation and output a first reply information and a second reply information;

[0143] An information determination module, which is used to determine the real-time consultation information and the type of the real-time consultation information;

[0144] An intelligent analysis system, wherein the intelligent analysis system is used to analyze the text consultation information and the voice content to determine the first reply information and the second reply information;

[0145] A database system, the database system is used to store reply answers corresponding to real-time consultation information and vocabulary information and linguistic rules corresponding to voice types;

[0146] A speech processing model, wherein the speech processing model is used to pre-process the speech consultation information to obtain interference-free speech consultation information; the speech processing model is used to analyze and convert the speech consultation information to output text reply information and speech reply information;

[0147] A text preprocessing module, which is used to preprocess the text consultation information to obtain complete text consultation information;

[0148] An industrial camera, which is used to collect images from the information consulting service end and obtain real-time image information;

[0149] An image analysis module, which is used to analyze real-time image information and determine the occlusion duration;

[0150] Control module, the control module is used to realize data transmission and information interaction between modules.

[0151] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An information consultation method based on artificial intelligence, characterized in that: include: Based on the information consultation service end, obtain real-time consultation information; Performing judgment and processing according to the real-time consultation information to determine the type of the real-time consultation information, wherein the type of the real-time consultation information is any one of voice consultation information or text consultation information; If the real-time consultation information is text consultation information; Based on the intelligent analysis system, the text consultation information is analyzed and processed to obtain the first core consultation information; Based on the first core consultation information, the database system is processed for information matching, and the first reply information is output; If the real-time consultation information is voice consultation information; Constructing a speech processing model, analyzing and processing the speech consultation information through the speech processing model, and obtaining conversion consultation information, wherein the conversion consultation information includes speech type and speech content; Based on the intelligent analysis system, the voice content is analyzed and processed to obtain the second core consulting information; Based on the second core consultation information, the database system is processed for information matching and the second reply information is output.

2. The information consultation method based on artificial intelligence according to claim 1, characterized in that: The method of obtaining real-time consulting information based on the information consulting service terminal specifically includes the following steps: Acquiring touch information from the information consultation service end, wherein the touch information is any one of text information and non-text information; Use industrial cameras to collect images from the information consulting server to obtain real-time image information; Based on the image recognition algorithm, the real-time image information is analyzed to determine the occlusion duration information; Analyze and process the occlusion duration information and touch information to obtain real-time consulting information.

3. The information consultation method based on artificial intelligence according to claim 2 is characterized in that: The analysis and processing based on the occlusion duration information and the touch information to obtain the real-time consulting information specifically includes the following steps: Perform judgment and processing according to the occlusion duration information and the set first threshold; If the occlusion duration information is greater than or equal to the set first threshold, and the touch information is non-text information, the information consultation service end starts the intelligent voice communication mode to obtain the voice consultation information; If the occlusion duration information is greater than or equal to the set first threshold, and the touch information is text information, the information consultation server starts a text collection mode to obtain text consultation information; If the occlusion duration information is less than the set first threshold, the information consultation service end does not collect information.

4. The information consultation method based on artificial intelligence according to claim 3 is characterized in that: The information consultation service end starts the intelligent voice communication mode, and obtaining voice consultation information specifically includes the following steps: Based on intelligent voice communication mode, obtain real-time environmental signals; Analyze and judge real-time environmental signals based on natural language processing algorithms; If the real-time environmental information does not contain voice signals, turn off the intelligent voice communication mode; If the real-time environmental information contains voice signals, the real-time environmental information is subjected to voice extraction through a feature extraction algorithm to obtain voice consultation information.

5. The information consultation method based on artificial intelligence according to claim 1, characterized in that: The step of analyzing and processing the text consultation information based on the intelligent analysis system to obtain the first core consultation information specifically includes the following steps: Based on the intelligent analysis system, the text consultation information is identified and the language type of the text is determined; Based on the language type of the text, the text consultation information is converted through language conversion to obtain text consultation conversion information; Based on the intelligent analysis system, preprocessing the text consultation conversion information to obtain complete text consultation information, wherein the preprocessing includes text cleaning, removal of stop words and vocabulary standardization; Based on the intelligent analysis system, the complete text consultation information is extracted and processed to obtain multiple groups of vocabulary information; Sorting and processing are performed according to multiple groups of vocabulary information to obtain first core consulting information; The specific calculation model for obtaining the first core consulting information is: In the formula, B c The first core consulting information; B i is the number of times each word appears in multiple sets of vocabulary information; n is the type of vocabulary in multiple sets of vocabulary information; max() is the maximum value function.

6. The information consultation method based on artificial intelligence according to claim 1, characterized in that: The construction of the speech processing model, analyzing and processing the speech consultation information through the speech processing model, and obtaining the conversion consultation information specifically includes the following steps: Based on the speech processing model, the language of the voice consultation information is analyzed to determine the voice type; Based on the speech processing model, the speech consultation information is subjected to speech preprocessing to obtain interference-free speech consultation information, wherein the speech preprocessing includes sampling, denoising, enhancement, and muting; Based on the speech type, vocabulary information and linguistic rules corresponding to the speech type are read from the database system; Based on vocabulary information and linguistic rules, the interference-free voice consultation information is segmented to obtain multiple segments of interference-free voice consultation information; Based on the speech processing model, multiple segments of non-interference voice consultation information are converted into language to obtain the speech content.

7. The information consultation method based on artificial intelligence according to claim 6, characterized in that: The step of segmenting the non-interference voice consultation information based on the vocabulary information and the linguistic rules to obtain multiple segments of non-interference voice consultation information specifically includes the following steps: Based on the vocabulary information, part-of-speech matching is performed on the non-interference voice consultation information to obtain part-of-speech information; Based on part-of-speech information and linguistic rules, the non-interfering speech consultation information is analyzed to determine the speech segmentation position; Based on the voice segmentation position, the interference-free voice consultation information is segmented to obtain multiple segments of interference-free voice consultation information.

8. The information consultation method based on artificial intelligence according to claim 1, characterized in that: The step of performing information matching processing on the database system based on the second core consultation information and outputting the second reply information specifically comprises the following steps: The intelligent analysis system establishes a temporary communication connection with the database system; The intelligent analysis system uses the second core consulting information as a feature to match the information in the database system and obtain the answer to the consulting information; Based on the voice processing model, the reply answer to the consultation information is output as second reply information, and the second reply information includes text reply information and voice reply information.

9. The information consultation method based on artificial intelligence according to claim 8, characterized in that: The method of outputting the consultation information reply answer as the second reply information based on the speech processing model specifically comprises the following steps: Based on part-of-speech information, linguistic rules and vocabulary information, the consultation information reply answer is converted into text reply information and voice reply information through the speech processing model; The intelligent analysis system outputs the text reply information to the display of the information consultation service end; The intelligent analysis system outputs the voice reply information to the microphone of the information consultation service end.

10. An information consultation system based on artificial intelligence, used to implement an information consultation method based on artificial intelligence as claimed in any one of claims 1 to 9, characterized in that: include: An information consultation service end, wherein the information consultation service end is used to conduct information consultation and output a first reply information and a second reply information; An information determination module, which is used to determine the real-time consultation information and the type of the real-time consultation information; An intelligent analysis system, wherein the intelligent analysis system is used to analyze the text consultation information and the voice content to determine the first reply information and the second reply information; A database system, the database system is used to store reply answers corresponding to real-time consultation information and vocabulary information and linguistic rules corresponding to voice types; A speech processing model, wherein the speech processing model is used to pre-process the speech consultation information to obtain interference-free speech consultation information; The speech processing model is used to analyze and convert the speech consultation information, and output text reply information and speech reply information; A text preprocessing module, which is used to preprocess the text consultation information to obtain complete text consultation information; An industrial camera, which is used to collect images from the information consulting service end and obtain real-time image information; An image analysis module, which is used to analyze real-time image information and determine the occlusion duration; Control module, the control module is used to realize data transmission and information interaction between modules.

Images