Enterprise knowledge question and answer analysis system and method based on AI model

Abstract

The invention discloses an enterprise knowledge question and answer analysis system and method based on an AI model, and relates to the technical field of AI models.The enterprise knowledge question and answer analysis method comprises the steps that user requirements are analyzed according to a user question text, and a first recommendation set of commodities is screened out, according to the historical commodity purchasing record of the user, analyzing the function matching between the historical purchased commodities and the commodities in the first recommendation set, screening out a second recommendation set of the commodities, and according to the historical commodity purchasing record of the user, analyzing the commodity use habits of the user; and according to the commodity use habit of the user, the purchase suitability of the user and the commodities in the second recommendation set is analyzed, a third recommendation set of the commodities is screened out, corresponding commodity information in the third recommendation set is obtained according to the historical purchase browsing record of the user, and the commodity information is recommended to the user when questions are answered. The technical problem that in the prior art, the matching degree between commodity recommendation and user requirements and user features is not high, and consequently the recommendation effect is not good is solved.

Description

Technical Field

[0001] The present invention relates to the field of AI model technology, and in particular to an enterprise knowledge question and answer analysis system and method based on an AI model. Background Art

[0002] The enterprise knowledge question answering system is a tool based on artificial intelligence and natural language processing technology, designed to provide employees and customers with instant and accurate information answers; However, in the related technologies, appropriate product recommendations are mostly made based on user questions, and there is a lack of technical solutions that combine user needs, the functional compatibility of user-purchased products, and user usage habits to jointly analyze and give suitable product recommendations. As a result, the product recommendations are not highly compatible with user needs and user characteristics, and user needs cannot be solved in a timely and accurate manner. In view of the technical problem that the product recommendations in the existing technology are not well matched with the user's questions and user characteristics, resulting in poor recommendation results and failure to promptly and accurately solve the user's needs, no effective solution has been proposed yet; Therefore, in order to solve the above problems, the present invention provides an enterprise knowledge question and answer analysis system and method based on an AI model. Summary of the invention

[0003] The embodiments of the present invention provide an enterprise knowledge question and answer analysis system and method based on an AI model, so as to at least solve the technical problem in the prior art that the product recommendations are not well matched with user needs and user characteristics, resulting in poor recommendation effects and failure to promptly and accurately solve user needs.

[0004] According to one aspect of an embodiment of the present invention, the following technical solution is provided: An enterprise knowledge question-answering analysis method based on an AI model includes the following specific steps: S1. Analyze user needs based on the user's question text and select the first recommended set of products; S2. Analyze the functional matching between the historically purchased products and the products in the first recommended set according to the historical purchase records of the user, and select a second recommended set of products; S3. Analyze the user's commodity usage habits based on the user's historical commodity purchase records; S4. Analyze the purchasing compatibility of the user with the products in the second recommendation set according to the user's product usage habits, and select a third recommendation set of products; S5. Obtain corresponding product information in the third recommendation set according to the user's historical purchase and browsing history, and recommend it to the user when answering questions.

[0005] Optionally, S1 includes the following specific steps: S101, inputting a user question text into a language processing module, and extracting user demand keywords from the question text, wherein the user demand keywords include demand individual keywords and service subject keywords; S102: Filter out commodities containing the individual demand keywords in the enterprise commodity management module according to the individual demand keywords and output them in the form of a first recommendation set.

[0006] Optionally, S2 includes the following specific steps: S201, obtaining a user's historical purchase records, analyzing keywords of historical purchases according to the historical purchase records, wherein the keywords of the historical purchases include name keywords and function keywords, filtering out historical purchases containing service subject keywords according to the name keywords and the service subject keywords, and obtaining function keywords of the products in the first recommendation set; S202, analyzing the functional matching degree between the filtered historically purchased products and the products in the first recommended set according to the functional keywords of the filtered historically purchased products and the functional keywords of the products in the first recommended set; S203: Sort the function matching degrees in descending order, filter out the products corresponding to the set serial numbers, and output them in the form of a second recommendation set.

[0007] Optionally, S3 includes the following specific steps: S301, extracting the purchase time and purchase amount from the filtered historical purchase records, obtaining the purchase time difference between two adjacent historical purchase records, then averaging several obtained purchase time differences to obtain an average purchase time difference, and averaging several obtained purchase amounts to obtain an average purchase amount; S302, comparing the average purchase time difference with a preset first time difference threshold and a second time difference threshold and judging the user's usage habits, if the average purchase time difference is less than or equal to the first time difference threshold, judging that the user changes the goods frequently, if the average purchase time difference is greater than the first time difference threshold and the purchase time difference is less than the second time difference threshold, judging that the user changes the goods moderately, if the average purchase time difference is greater than or equal to the second time difference threshold, judging that the user changes the goods slowly, wherein the first time difference threshold is less than the second time difference threshold; S303: Obtain a user usage habit score value based on the user's usage habits.

[0008] Optionally, S4 includes the following specific steps: S401, obtaining usage keywords and commodity amounts of commodities in the second recommendation set, and analyzing the purchase compatibility between the user and the commodities in the second recommendation set according to the user usage habit score, the average purchase amount, the usage keywords and commodity amounts of the commodities in the second recommendation set; S402: Sort the purchase suitability in descending order, filter out the commodities corresponding to the set serial numbers, and output them in the form of a third recommendation set.

[0009] Optionally, S5 includes the following specific steps: Obtain the user's historical purchase and browsing records to analyze whether the user has the habit of analogy. If the user does not have the habit of analogy, obtain the product information with the highest matching value in the third recommendation set and recommend it to the user when answering questions. If the user has the habit of analogy, obtain the product information corresponding to the set serial number in the third recommendation set and recommend it to the user when answering questions.

[0010] According to another aspect of an embodiment of the present invention, there is also provided an enterprise knowledge question-answering analysis system based on an AI model, which is used to implement an enterprise knowledge question-answering analysis method based on an AI model, including: a demand analysis unit, which is used to input a user question text in a language processing module, extract user demand keywords from the question text, and screen out commodities containing individual demand keywords in an enterprise commodity management module according to individual demand keywords and output them in the form of a first recommendation set; a function matching analysis unit, configured to obtain a user's historical purchase records, analyze keywords of historical purchases according to the historical purchase records, filter out historical purchases containing the service subject keywords according to the name keywords and the service subject keywords, and analyze the function matching degree between the filtered historical purchases and the commodities in the first recommendation set according to the function keywords of the filtered historical purchases and the function keywords of the commodities in the first recommendation set; A usage habit analysis unit is used to extract the purchase time and purchase amount from the filtered historical purchase records, compare the average purchase time difference with the preset first time difference threshold and the second time difference threshold, and judge the user's usage habits, and obtain the user's usage habit score value according to the user's usage habits; A purchase adaptation analysis unit, used to obtain the usage keywords and commodity amounts of the commodities in the second recommendation set, and analyze the purchase compatibility between the user and the commodities in the second recommendation set according to the user usage habit score, the average purchase amount, the usage keywords and the commodity amounts of the commodities in the second recommendation set; The product recommendation unit is used to obtain the user's historical purchase and browsing records to analyze whether the user has an analogy habit. If the user does not have an analogy habit, the product information with the highest matching probability in the third recommendation set is obtained and recommended to the user when answering questions. If the user has an analogy habit, the product information corresponding to the set serial number in the third recommendation set is obtained and recommended to the user when answering questions.

[0011] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium is used to store a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned enterprise knowledge question and answer analysis methods based on the AI ​​model.

[0012] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned enterprise knowledge question and answer analysis methods based on an AI model.

[0013] In the present invention, user needs are analyzed according to the user's question text, and a first recommended set of products is screened out. The functional matching of historically purchased products with the products in the first recommended set is analyzed according to the user's historical product purchase records, and a second recommended set of products is screened out. The user's product usage habits are analyzed according to the user's historical product purchase records. The user's purchase compatibility with the products in the second recommended set is analyzed according to the user's product usage habits, and a third recommended set of products is screened out. The corresponding product information in the third recommended set is obtained according to the user's historical purchase browsing records, and is recommended to the user when answering questions. The present invention combines user needs, functional matching with the user's historically purchased products, and user usage habits to jointly analyze and give recommendations for suitable products, which is conducive to improving the compatibility of products and users, timely and accurately solving user needs, and improving enterprise service satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 This is a flow chart of an enterprise knowledge question-answering analysis method based on an AI model of the present invention; Figure 2 This is a schematic diagram of the S1 process in an enterprise knowledge question-answering analysis method based on an AI model of the present invention; Figure 3 This is a schematic diagram of the S2 process in an enterprise knowledge question-answering analysis method based on an AI model of the present invention; Figure 4 This is a schematic diagram of the S3 process in an enterprise knowledge question-answering analysis method based on an AI model of the present invention; Figure 5 This is a schematic diagram of the S4 process in an enterprise knowledge question-answering analysis method based on an AI model of the present invention; Figure 6This is a schematic diagram of the overall framework of an enterprise knowledge question and answer analysis system based on an AI model in the present invention. DETAILED DESCRIPTION

[0015] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] To facilitate those skilled in the art to understand the present invention, some terms or nouns involved in each embodiment of the present invention are explained below: AI model: AI model refers to a model based on deep learning algorithms and trained with large amounts of data. It can perform various tasks, such as natural language processing, image recognition, speech recognition, etc. AI models can perform complex tasks by learning features and patterns in data, and have made significant progress in various fields.

[0018] AI models can be classified according to model structure: ‌Deep Neural Network (DNN), ‌Generative Adversarial Network (GAN), ‌Variational Autoencoder (VAE); AI models can be classified by task type into: ‌Natural Language Processing (NLP) models, ‌Computer Vision (CV) models, ‌Multimodal models; The application areas of AI models include: ‌Natural Language Processing‌: used for text generation, question answering systems, machine translation, etc.; ‌Computer Vision‌: used for image recognition, video analysis, object detection, etc.; ‌Speech recognition and generation‌: used for voice assistants, speech-to-text conversion, etc.; ‌Recommendation system‌: used for personalized recommendations, advertising, etc.; Bioinformatics: used for gene sequence analysis, protein structure prediction, etc.

[0019] NLP: Natural Language Processing (NLP) is an important research direction in the field of artificial intelligence. It integrates knowledge from multiple disciplines such as linguistics, computer science, machine learning, mathematics, cognitive psychology, etc. It is an interdisciplinary subject that integrates computer science, artificial intelligence and linguistics. It includes two main aspects: natural language understanding and natural language generation. The research content includes multiple levels such as characters, words, phrases, sentences, paragraphs and chapters. It is a bridge for communication between machine language and human language. It aims to enable machines to understand, interpret and generate human language, realize effective communication between humans and machines, and enable computers to perform tasks such as language translation, sentiment analysis, and text summarization.

[0020] The present invention is described in detail below in conjunction with various embodiments.

[0021] Example 1

[0022] According to an embodiment of the present invention, an embodiment of an enterprise knowledge question and answer analysis method based on an AI model is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0023] Figure 1 is a flowchart of an optional enterprise knowledge question answering analysis method based on an AI model according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps: S1. Analyze user needs based on the user's question text and select the first recommended set of products; like Figure 2 As shown, in this embodiment, S1 includes the following specific steps: S101, inputting a user question text into a language processing module, and extracting user demand keywords from the question text, wherein the user demand keywords include demand individual keywords and service subject keywords; Optionally, the user's question is analyzed through the AI ​​model, and the language processing module uses the NLP algorithm to preprocess the text. The text preprocessing steps include: removing irrelevant characters (deleting special characters, punctuation marks, etc. in the text), word segmentation (segmenting the text into words or phrases), and removing stop words (deleting high-frequency but meaningless words in the text). Then, the TF-IDF (term frequency-inverse document frequency) algorithm is used to calculate the TF-IDF value, and the words are sorted according to the scores output by the model. Words in a set sequence range are selected as keywords, or deep learning models (such as TextRank, Word2Vec, BERT) are used for feature extraction to obtain user demand keywords. User demand keywords include individual demand keywords and service subject keywords. The individual demand refers to obtaining the product needed by the user this time based on the question asked by the user, and the service subject refers to analyzing which product it serves based on the obtained products. For example, a user asks in the enterprise knowledge question and answer module whether there are safety seats for infants and young children during driving. The individual demand keyword is safety seat, and the individual service keyword is vehicle.

[0024] S102: Filter out commodities containing the individual demand keywords in the enterprise commodity management module according to the individual demand keywords and output them in the form of a first recommendation set.

[0025] S2. Analyze the functional matching between the historically purchased products and the products in the first recommended set according to the historical purchase records of the user, and select a second recommended set of products; like Figure 3 As shown, in this embodiment, S2 includes the following specific steps: S201, obtaining the user's historical purchase records, analyzing the keywords of the historical purchases according to the historical purchase records, the keywords of the historical purchases include name keywords and function keywords, filtering out the historical purchases containing the service subject keywords according to the name keywords and the service subject keywords, and obtaining the function keywords of the products in the first recommendation set; S202: Analyze the functional matching degree between the filtered historically purchased products and the products in the first recommended set according to the functional keywords of the filtered historically purchased products and the functional keywords of the products in the first recommended set, wherein the functional matching degree between the filtered historically purchased products and the products in the first recommended set can be obtained by a functional matching degree calculation formula, which can be: ,in, is the vector of the i-th functional keyword of the i-th filtered historical purchase product, is the vector of the jth functional keyword of the Jth product in the first recommendation set, wherein the neural network is trained using the continuous bag of words model (CBOW) or the skip-gram model to learn the vector representation of the keyword so that semantically similar words are close in distance in the vector space, and the vector representation of the keyword is output. is the dot product, is the modulus of the vector of the i-th functional keyword of the i-th filtered historical purchase product, is the modulus of the vector of the jth functional keyword of the jth product in the first recommendation set, is the weight of the i-th functional keyword of the i-th filtered historical purchase product, is the weight of the jth functional keyword of the jth product in the first recommendation set. The score output by the model when obtaining the functional keyword is imported into the pre-optimized fitting software, and the fitting software is allowed to output the matching weight, that is, and The value of Optionally, obtain relevant text information of the filtered historical purchased products and products in the first recommended set, including product titles, product details, product reviews, etc., perform data cleaning on the relevant text information, and use a deep learning model to extract features from the text to obtain keywords representing the functions of the products. For example, the functional keywords of a safety seat are: "ISOFIX interface", "anti-shock", "7-speed adjustment", and "suitable for 0-4 years old"; the functional keywords of a vehicle are: "ISOFIX interface", "spacious rear seat space", and "child safety lock".

[0026] S203: Sort the function matching degrees in descending order, filter out the products corresponding to the set serial numbers, and output them in the form of a second recommendation set.

[0027] S3. Analyze the user's commodity usage habits based on the user's historical commodity purchase records; like Figure 4 As shown, in this embodiment, S3 includes the following specific steps: S301, extracting the purchase time and purchase amount from the filtered historical purchase records, obtaining the purchase time difference between two adjacent historical purchase records, then averaging several obtained purchase time differences to obtain an average purchase time difference, and averaging several obtained purchase amounts to obtain an average purchase amount; S302, comparing the average purchase time difference with a preset first time difference threshold and a second time difference threshold and judging the user's usage habits, if the average purchase time difference is less than or equal to the first time difference threshold, judging that the user changes the goods frequently, if the average purchase time difference is greater than the first time difference threshold and the purchase time difference is less than the second time difference threshold, judging that the user changes the goods moderately, if the average purchase time difference is greater than or equal to the second time difference threshold, judging that the user changes the goods slowly, wherein the first time difference threshold is less than the second time difference threshold; S303. Obtain a user usage habit score value based on the user's usage habits, wherein relevant experts are hired to analyze the user's usage habits and give a usage habit score value, the usage habit score value given by the expert is input into the fitting software for optimization, the user's usage habits are imported into the pre-optimized fitting software, and the fitting software is allowed to output a usage habit score value that matches the user.

[0028] S4. Analyze the purchasing compatibility of the user with the products in the second recommendation set according to the user's product usage habits, and select a third recommendation set of products; like Figure 5 As shown, in this embodiment, S4 includes the following specific steps: S401, obtaining usage keywords and commodity amounts of commodities in the second recommendation set, and analyzing the purchase compatibility between the user and the commodities in the second recommendation set according to the user usage habit score, the average purchase amount, the usage keywords and the commodity amounts of the commodities in the second recommendation set, wherein the purchase compatibility between the user and the commodities in the second recommendation set can be obtained by a purchase compatibility calculation formula, which can be: ,in, is the amount of the pth item in the second recommended set, is the average purchase amount, through Analyze whether the pth item in the second recommendation set matches the user's consumption habits. The larger the value, the more the product matches the user's consumption habits. is the modulus of the k-th keyword vector used for the product, is the weight of the kth keyword pair used for the product, Score the user's usage habits by Analyze whether each product matches the user's usage habits. The larger the value, the more the product matches the user's usage habits. The usage keywords of the products in the second recommendation set are imported into the pre-optimized fitting software, and the fitting software is allowed to output the matching weight, that is, The value of S402: Sort the purchase suitability in descending order, filter out the commodities corresponding to the set serial numbers, and output them in the form of a third recommendation set.

[0029] S5. Obtain corresponding product information in the third recommendation set according to the user's historical purchase and browsing history, and recommend it to the user when answering questions.

[0030] In this embodiment, S5 includes the following specific steps: Obtain the user's historical purchase and browsing records to analyze whether the user has the habit of analogy. If the user does not have the habit of analogy, obtain the product information with the highest matching value in the third recommendation set and recommend it to the user when answering questions. If the user has the habit of analogy, obtain the product information corresponding to the set serial number in the third recommendation set and recommend it to the user when answering questions.

[0031] Optionally, obtain the user's browsing history, including product category, browsing time, number of clicks, etc., extract user behavior characteristics, and analyze whether the user tends to frequently browse similar products when he wants to buy a certain type of product. If the user frequently browses similar products, it is determined that the user has an analogy habit.

[0032] The present invention is described below in conjunction with another optional embodiment.

[0033] Example 2

[0034] An embodiment of the present invention provides an enterprise knowledge question and answer analysis system based on an AI model, and each implementation unit included in the enterprise knowledge question and answer analysis system corresponds to each implementation step in the above-mentioned embodiment 1.

[0035] Figure 6 is a schematic diagram of an optional enterprise knowledge question answering analysis system based on an AI model according to an embodiment of the present invention, such as Figure 6 As shown, the enterprise knowledge question answering analysis system may include: a demand analysis unit, which is used to input a user question text in a language processing module, extract user demand keywords from the question text, and screen out commodities containing the demand individual keywords in the enterprise commodity management module according to the demand individual keywords and output them in the form of a first recommendation set; a function matching analysis unit, configured to obtain a user's historical purchase records, analyze keywords of historical purchases based on the historical purchase records, filter out historical purchases containing service subject keywords based on name keywords and service subject keywords, and analyze the function matching degree between the filtered historical purchases and the commodities in the first recommendation set based on the function keywords of the filtered historical purchases and the function keywords of the commodities in the first recommendation set; A usage habit analysis unit is used to extract the purchase time and purchase amount from the filtered historical purchase records, compare the average purchase time difference with the preset first time difference threshold and the second time difference threshold, and judge the user's usage habits, and obtain the user's usage habit score value according to the user's usage habits; A purchase adaptation analysis unit, used to obtain the usage keywords and commodity amounts of the commodities in the second recommendation set, and analyze the purchase compatibility between the user and the commodities in the second recommendation set according to the user usage habit score, the average purchase amount, the usage keywords and the commodity amounts of the commodities in the second recommendation set; The product recommendation unit is used to obtain the user's historical purchase and browsing records to analyze whether the user has an analogy habit. If the user does not have an analogy habit, the product information with the highest matching probability in the third recommendation set is obtained and recommended to the user when answering questions. If the user has an analogy habit, the product information corresponding to the set serial number in the third recommendation set is obtained and recommended to the user when answering questions.

[0036] Example 3

[0037] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, which is used to store a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned enterprise knowledge question and answer analysis methods based on an AI model.

[0038] Example 4

[0039] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any one of the above-mentioned enterprise knowledge question and answer analysis methods based on an AI model.

[0040] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a corporate knowledge question-and-answer analysis method based on an AI model provided in the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input / output interface to input and output data. This embodiment will not be described in detail here.

[0041] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0042] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0043] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0044] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0045] In addition, each functional unit in each embodiment of the present invention 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.

[0046] 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 computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, 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 for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0047] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An enterprise knowledge question-answering analysis method based on an AI model, characterized in that: The specific steps include: S1. Analyze user needs based on the user's question text and select the first recommended set of products; S2. Analyze the functional matching between the historically purchased products and the products in the first recommended set according to the historical purchase records of the user, and select a second recommended set of products; S3. Analyze the user's commodity usage habits based on the user's historical commodity purchase records; S4. Analyze the purchasing compatibility of the user with the products in the second recommendation set according to the user's product usage habits, and select a third recommendation set of products; S5. Obtain corresponding product information in the third recommendation set according to the user's historical purchase and browsing history, and recommend it to the user when answering questions.

2. The enterprise knowledge question-answering analysis method based on an AI model as claimed in claim 1, characterized in that: The S1 comprises the following specific steps: S101, inputting a user question text into a language processing module, and extracting user demand keywords from the question text, wherein the user demand keywords include demand individual keywords and service subject keywords; S102: Filter out commodities containing the individual demand keywords in the enterprise commodity management module according to the individual demand keywords and output them in the form of a first recommendation set.

3. The enterprise knowledge question-answering analysis method based on an AI model as claimed in claim 2, characterized in that: The S2 comprises the following specific steps: S201, obtaining a user's historical purchase records, analyzing keywords of historical purchases according to the historical purchase records, wherein the keywords of the historical purchases include name keywords and function keywords, filtering out historical purchases containing service subject keywords according to the name keywords and the service subject keywords, and obtaining function keywords of the products in the first recommendation set; S202, analyzing the functional matching degree between the filtered historically purchased products and the products in the first recommended set according to the functional keywords of the filtered historically purchased products and the functional keywords of the products in the first recommended set; S203: Sort the function matching degrees in descending order, filter out the products corresponding to the set serial numbers, and output them in the form of a second recommendation set.

4. The enterprise knowledge question-answering analysis method based on an AI model as claimed in claim 3, characterized in that: The S3 includes the following specific steps: S301, extracting the purchase time and purchase amount from the filtered historical purchase records, obtaining the purchase time difference between two adjacent historical purchase records, then averaging several obtained purchase time differences to obtain an average purchase time difference, and averaging several obtained purchase amounts to obtain an average purchase amount; S302, comparing the average purchase time difference with a preset first time difference threshold and a second time difference threshold and judging the user's usage habits, if the average purchase time difference is less than or equal to the first time difference threshold, judging that the user changes the goods frequently, if the average purchase time difference is greater than the first time difference threshold and the purchase time difference is less than the second time difference threshold, judging that the user changes the goods moderately, if the average purchase time difference is greater than or equal to the second time difference threshold, judging that the user changes the goods slowly; S303: Obtain a user usage habit score value based on the user's usage habits.

5. The enterprise knowledge question-answering analysis method based on an AI model as claimed in claim 4, characterized in that: The S4 comprises the following specific steps: S401, obtaining usage keywords and commodity amounts of commodities in the second recommendation set, and analyzing the purchase compatibility between the user and the commodities in the second recommendation set according to the user usage habit score, the average purchase amount, the usage keywords and commodity amounts of the commodities in the second recommendation set; S402: Sort the purchase suitability in descending order, filter out the commodities corresponding to the set serial numbers, and output them in the form of a third recommendation set.

6. The enterprise knowledge question-answering analysis method based on an AI model as claimed in claim 5, characterized in that: The S5 comprises the following specific steps: Obtain the user's historical purchase and browsing records to analyze whether the user has the habit of analogy. If the user does not have the habit of analogy, obtain the product information with the highest matching value in the third recommendation set and recommend it to the user when answering questions. If the user has the habit of analogy, obtain the product information corresponding to the set serial number in the third recommendation set and recommend it to the user when answering questions.

7. An enterprise knowledge question and answer analysis system based on an AI model, used to implement the enterprise knowledge question and answer analysis method based on an AI model as claimed in any one of claims 1 to 6, characterized in that: include: A demand analysis unit, used to analyze user demand according to the user's question text and filter out a first recommended set of products; A function matching analysis unit, configured to analyze the function matching between the historically purchased goods and the goods in the first recommendation set according to the historical purchase records of the user, and select a second recommendation set of goods; A usage habit analysis unit is used to analyze the user's commodity usage habits based on the user's historical commodity purchase records; A purchase compatibility analysis unit, which analyzes the purchase compatibility between the user and the products in the second recommendation set according to the user's product usage habits, and selects a third recommendation set of products; The product recommendation unit is used to obtain corresponding product information in the third recommendation set according to the user's historical purchase and browsing history, and recommend it to the user when answering questions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute an enterprise knowledge question and answer analysis method based on an AI model as described in any one of claims 1 to 6.

9. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement an enterprise knowledge question and answer analysis method based on an AI model as described in any one of claims 1 to 6.

Images