Commodity quotation method and device, computer equipment and storage medium

Abstract

The invention discloses a commodity quotation method and device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence. According to the method, the user behavior data of the target customer in the preset time period is acquired to obtain the first behavior data, and the first behavior data is the user behavior data of the target customer for operating the target commodity; identifying purchase willingness of the target customer for the target commodity according to the user behavior data; when the target customer has a purchase intention for the target commodity, obtaining second behavior data of the target customer, the second behavior data being historical purchase behavior data of the target customer; predicting the quotation of the target customer for the target commodity according to the first behavior data and the second behavior data to obtain a commodity quotation prediction result; and pushing the commodity quotation prediction result to the client of the target client. The invention also relates to the technical field of block chains, and the behavior data is stored in a block chain network. According to the invention, the commodity quotation efficiency and accuracy are improved.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a commodity quotation method, device, computer equipment and storage medium. Background Art

[0002] A sales quotation for goods refers to the price information of goods or services provided by the seller (supplier, manufacturer, distributor, etc.) to potential buyers, as well as other relevant conditions or terms that may be included. This process is a crucial part of commercial transactions. Usually, the quotation process is related to the economic interests between the buyer and the seller and whether the transaction can be reached.

[0003] Currently, commodity sales quotations are generally made manually by customer service agents, who usually make quotations based on the content of their communication with users and their own experience. However, this manual quotation method lacks standardized processes and is easily affected by the subjective judgment of customer service, resulting in large price fluctuations, affecting user experience and brand image. In addition, when faced with a large number of inquiry requests, manual processing is inefficient and it is difficult to respond to all customer needs in a timely manner, resulting in poor information communication or misunderstandings, and increasing the cost of subsequent negotiations and problem solving. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a commodity quotation method, device, computer equipment and storage medium to solve the technical problems of the existing manual quotation method, such as lack of standardized process, low processing efficiency, and susceptibility to subjective judgment of customer service, which affects user experience and brand image.

[0005] In order to solve the above technical problems, the present application embodiment provides a commodity quotation method, which adopts the following technical solution:

[0006] A commodity quotation method, comprising:

[0007] Obtaining user behavior data of a target customer within a preset time period to obtain first behavior data, wherein the first behavior data is user behavior data of the target customer operating a target product;

[0008] Identify target customers' purchasing intention for target products based on user behavior data;

[0009] When the target customer has a purchase intention for the target product, second behavior data of the target customer is obtained, wherein the second behavior data is the historical purchase behavior data of the target customer;

[0010] Predicting the target customer's quotation for the target product based on the first behavior data and the second behavior data, and obtaining a product quotation prediction result;

[0011] The product quotation prediction results are pushed to the target customer's client.

[0012] Furthermore, the first behavior data includes click operations and sliding operations performed by the target customer on the target product interface of the product quotation system, as well as session operations initiated for the target product. The target product interface is an interface for displaying the target product. The steps of identifying the target customer's purchase intention for the target product based on the user behavior data specifically include:

[0013] Obtain the number of clicks performed by the target customer on the target product interface to obtain the number of click operations;

[0014] Obtain the number of times the target customer performs sliding operations on the target product interface to obtain the number of sliding operations;

[0015] The target customer's session information is obtained, and the target customer's purchase intention for the target product is identified based on the number of click operations, the number of swipe operations, and the session information.

[0016] Furthermore, the step of obtaining the session information of the target customer and identifying the target customer's purchase intention for the target product according to the number of click operations, the number of sliding operations and the session information specifically includes:

[0017] Perform text preprocessing on the conversation information, and perform semantic recognition on the preprocessed conversation text to obtain text semantic fragments;

[0018] The number of click operations, the number of sliding operations and the text semantic fragments are respectively encoded to obtain click operation features, sliding operation features and text semantic features;

[0019] Combining the click operation feature, the sliding operation feature and the text semantic feature to obtain a first combined feature;

[0020] The first combined feature is input into a pre-trained purchase intention recognition model, and a purchase intention recognition result of the target customer for the target product is output.

[0021] Furthermore, the sliding operation includes a short-distance sliding operation and a long-distance sliding operation. The long-distance sliding operation is sliding from the top of the target product interface to the bottom of the target product interface. After obtaining the number of sliding operations performed by the target customer on the target product interface, the method further includes:

[0022] Counting the operation duration of each short-distance sliding operation to obtain a first operation duration set;

[0023] Counting the operation duration of each long-distance sliding operation to obtain a second operation duration set;

[0024] An operation duration sequence is constructed based on the first operation duration set and the second operation duration set.

[0025] Furthermore, after the steps of respectively encoding the number of click operations, the number of sliding operations and the text semantic segment to obtain the click operation feature, the sliding operation feature and the text semantic feature, the method further includes:

[0026] Obtain the time series features of the sliding operation from the operation duration sequence;

[0027] The time series features are associated with the sliding operation features to obtain the sliding operation time series features;

[0028] Combining the click operation feature, the sliding operation time series feature and the text semantic feature to obtain a second combined feature;

[0029] The second combined feature is input into the pre-trained purchase intention recognition model, and the purchase intention recognition result of the target customer for the target product is output.

[0030] Further, the step of predicting the target customer's quotation for the target product based on the first behavior data and the second behavior data to obtain the product quotation prediction result specifically includes:

[0031] Feature encoding is performed on the first behavior data and the second behavior data respectively to obtain a first behavior feature and a second behavior feature;

[0032] Calculate the feature weights of the first behavior feature and the second behavior feature respectively based on a preset feature weight algorithm;

[0033] Performing feature weighting on the first behavior feature and the second behavior feature according to the feature weight;

[0034] Combine the weighted first behavior feature and the second behavior feature to obtain a third feature combination;

[0035] The third feature combination is input into the pre-trained commodity price prediction model to obtain the commodity price prediction result.

[0036] Furthermore, the step of respectively calculating the feature weights of the first behavior feature and the second behavior feature based on a preset feature weight algorithm specifically includes:

[0037] Initialize the feature weights of the first behavior feature and the second behavior feature respectively to obtain a first initial weight and a second initial weight;

[0038] In a pre-constructed feature weight dictionary, respectively searching for feature standard values ​​corresponding to the first behavior feature and the second behavior feature to obtain the first feature standard value and the second feature standard value;

[0039] Comparing the magnitude relationship between the first behavior feature value and the first feature standard value to obtain a first comparison result, and adjusting the first initial weight based on the first comparison result to obtain a feature weight of the first behavior feature;

[0040] The magnitude relationship between the second behavior feature value and the second feature standard value is compared to obtain a second comparison result, and the second initial weight is adjusted based on the second comparison result to obtain a feature weight of the second behavior feature.

[0041] In order to solve the above technical problems, the embodiment of the present application further provides a commodity quotation device, which adopts the following technical solution:

[0042] A commodity quotation device, comprising:

[0043] A first data acquisition module is used to acquire user behavior data of a target customer within a preset time period to obtain first behavior data, wherein the first behavior data is user behavior data of the target customer operating a target product;

[0044] The purchase intention identification module is used to identify the purchase intention of target customers for target products based on user behavior data;

[0045] A second data acquisition module is used to acquire second behavior data of the target customer when the target customer has a purchase intention for the target product, wherein the second behavior data is the historical purchase behavior data of the target customer;

[0046] A commodity quotation prediction module is used to predict the quotation of the target customer for the target commodity according to the first behavior data and the second behavior data, and obtain a commodity quotation prediction result;

[0047] The product quotation output module is used to push the product quotation prediction results to the client of the target customer.

[0048] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0049] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of any one of the above-mentioned commodity quotation methods when executing the computer-readable instructions.

[0050] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0051] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of any one of the above-mentioned commodity quotation methods.

[0052] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0053] The present application discloses a commodity quotation method, device, computer equipment and storage medium, which belongs to the field of artificial intelligence technology. The present application obtains the user behavior data of the target customer within a preset time period to obtain the first behavior data, wherein the first behavior data is the user behavior data of the target customer operating the target commodity; identifies the target customer's purchase intention for the target commodity based on the user behavior data; when the target customer has a purchase intention for the target commodity, obtains the target customer's second behavior data, wherein the second behavior data is the target customer's historical purchase behavior data; predicts the target customer's quotation for the target commodity based on the first behavior data and the second behavior data, and obtains the commodity quotation prediction result; pushes the commodity quotation prediction result to the client of the target customer. The solution of the present application targets the technical problems of the traditional manual quotation method, and significantly improves the quotation efficiency and accuracy through standardized data processing flow and intelligent analysis, avoids the interference of human subjective judgment in the quotation process, ensures that each customer can obtain an accurate quotation based on their actual behavior and needs, and optimizes the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. 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.

[0055] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0056] Figure 2 A flowchart of an embodiment of a commodity quotation method according to the present application is shown;

[0057] Figure 3 A schematic structural diagram of an embodiment of a commodity quotation device according to the present application is shown;

[0058] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0060] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0061] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0062] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0063] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0064] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0065] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0066] It should be noted that the commodity quotation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the commodity quotation device is generally set in the server / terminal device.

[0067] It should be understood that Figure 1 The numbers of terminal devices, networks and servers in the embodiment are merely illustrative. The above system may have any number of terminal devices, networks and servers according to implementation requirements.

[0068] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for commodity quotation according to the present application. The commodity quotation method comprises the following steps:

[0069] S201, obtaining user behavior data of a target customer within a preset time period to obtain first behavior data, wherein the first behavior data is user behavior data of the target customer operating a target product.

[0070] Specifically, first, the system identifies and locks in customer groups with potential purchasing interest, namely target customers. Then, the user behavior data of the target customers within a preset time period is collected. The preset time period can be flexibly set according to actual conditions, such as a week, a month, or a specific promotion period. Such a setting helps to capture the changing trend of the target customer's interest in the target product during this period. User behavior data refers to all operations or interaction records related to the target product made by the target customer within a specified time. These behavior data include but are not limited to clicks, browsing, adding to shopping carts, sharing, comments, etc. These behavior data collectively reflect the customer's interest in the product and purchase intention.

[0071] S202, identifying the target customer's purchase intention for the target product based on the user behavior data.

[0072] Specifically, the system needs to use intelligent analysis technology and identify the target customers' willingness to purchase the target products based on user behavior data. Intelligent analysis technologies such as machine learning and data mining can automatically process and analyze data, discover patterns and trends in the data, and thus predict customer purchasing behavior.

[0073] S203, when the target customer has a purchase intention for the target product, obtain second behavior data of the target customer, wherein the second behavior data is historical purchase behavior data of the target customer.

[0074] Specifically, after identifying that the target customer has the intention to purchase the target product, the system obtains the target customer's second behavior data, where the second behavior data is the target customer's historical purchase behavior data. By further digging into the customer's purchase history, more comprehensive customer information can be obtained so that product quotation prediction can be made based on the comprehensive customer information. Historical purchase behavior data can reflect information on customers' purchasing habits, preferences, payment capabilities, and other aspects, and is an important basis for predicting customers' future purchase behavior. By collecting and analyzing this data, companies can understand customer needs more accurately.

[0075] It should be noted that both the first behavior data and the second behavior data are behavior data authorized by the user to ensure the legitimacy and security of the data. In addition, in the process of using the data, data encryption, blockchain storage and other technologies are used to protect customer privacy and avoid leaking sensitive information.

[0076] S204, predicting the target customer's quotation for the target product based on the first behavior data and the second behavior data, and obtaining a product quotation prediction result.

[0077] Specifically, the system integrates the first behavior data and the second behavior data to form a comprehensive understanding of the customer's willingness to buy and ability to pay, so as to predict the product price. Then, the pre-trained machine learning model is used to combine the integrated first behavior data and the second behavior data to predict the price of the target product and obtain the product price prediction result.

[0078] It should be noted that different user behaviors have different importance for the prediction of purchase intention. For example, click, browse, add to shopping cart, purchase, share, comment and other behaviors have different feature contributions to the prediction of commodity quotation. Therefore, this application subdivides different types of user behaviors through feature weight algorithm and assigns different weights to improve the accuracy of commodity quotation prediction.

[0079] S205, pushing the product quotation prediction result to the client of the target customer.

[0080] Specifically, after obtaining the product quotation prediction results, the system pushes the product quotation prediction results to the client of the target customer. By pushing the product quotation prediction results, the company can provide a personalized shopping experience for the target customer. These prediction results are based on the specific behavior and preferences of the customer, so they can more accurately reflect the customer's willingness to buy and ability to pay, thereby providing more intimate and customer-friendly quotes. By instantly pushing the quotation prediction results, the company can seize sales opportunities when the customer is most interested and improve the conversion rate.

[0081] In the above embodiments, the solution of the present application addresses the technical problems of the traditional manual quotation method. Through standardized data processing procedures and intelligent analysis, it significantly improves the quotation efficiency and accuracy, avoids the interference of human subjective judgment in the quotation process, ensures that each customer can obtain an accurate quotation based on their actual behavior and needs, and optimizes the user experience.

[0082] Furthermore, the first behavior data includes click operations and sliding operations performed by the target customer on the target product interface of the product quotation system, as well as session operations initiated for the target product. The target product interface is an interface for displaying the target product. The steps of identifying the target customer's purchase intention for the target product based on the user behavior data specifically include:

[0083] Obtain the number of clicks performed by the target customer on the target product interface to obtain the number of click operations;

[0084] Obtain the number of sliding operations performed by the target customer on the target product interface to obtain the number of sliding operations;

[0085] The target customer's session information is obtained, and the target customer's purchase intention for the target product is identified based on the number of click operations, the number of swipe operations, and the session information.

[0086] The customer's behavior of clicking on the target product, button, link, etc. on the interface reflects the customer's interest in the product or his / her willingness to learn more about the product. The customer's behavior of swiping through the product details, reviews, recommendations, and other information on the interface also shows that the customer is carefully examining the product or looking for more relevant information. The customer's conversation information related to the target product, such as consulting customer service and sending comments, directly reflects the customer's purchase concerns, needs, or feedback.

[0087] In this embodiment, first, the system obtains the number of click operations performed by the target customer on the target product interface to obtain the number of click operations. Then, the system obtains the number of slide operations performed by the target customer on the target product interface to obtain the number of slide operations. Finally, the system obtains the session information of the target customer, and performs a comprehensive evaluation based on the number of click operations, the number of slide operations, and the session information through a machine learning algorithm or model to identify the target customer's purchase intention for the target product.

[0088] Through the above embodiment, the target customer's operating behavior on the target product interface of the product quotation system and the session information initiated by the customer are analyzed in detail, combined with a machine learning algorithm or model to identify the customer's purchasing intention.

[0089] Furthermore, the step of obtaining the session information of the target customer and identifying the target customer's purchase intention for the target product according to the number of click operations, the number of sliding operations and the session information specifically includes:

[0090] Perform text preprocessing on the conversation information, and perform semantic recognition on the preprocessed conversation text to obtain text semantic fragments;

[0091] The number of click operations, the number of sliding operations and the text semantic fragments are respectively encoded to obtain click operation features, sliding operation features and text semantic features;

[0092] Combining the click operation feature, the sliding operation feature and the text semantic feature to obtain a first combined feature;

[0093] The first combined feature is input into a pre-trained purchase intention recognition model, and a purchase intention recognition result of the target customer for the target product is output.

[0094] In this embodiment, text preprocessing is performed on the conversation information, including removing irrelevant characters (such as punctuation marks, special symbols, etc.), word segmentation, stop word filtering, etc., to improve the accuracy of subsequent semantic recognition. The purpose of semantic recognition of the preprocessed conversation text is to convert the text into machine-understandable semantic fragments, and natural language processing (NLP) technology such as named entity recognition, sentiment analysis, and intent recognition can be used. The results of semantic recognition (text semantic fragments) can more accurately reflect the customer's purchasing intention, doubts, or needs.

[0095] In a specific embodiment of the present application, semantic recognition is implemented based on the Memory mechanism. Specifically, the Memory mechanism is used to store and manage the context information of the conversation. In a continuous conversation scenario, the user's questions often depend on the previous conversation content, that is, there is context dependency. Memory can store this historical information, so that the language model can take into account the previous conversation content when generating a reply, thereby generating a more accurate and coherent reply. By storing and retrieving historical conversations, the Memory mechanism enables the language model to better understand the context of the current question, reduce misunderstandings and ambiguity, and the Memory mechanism is combined with the NLP language model, so that the NLP language model can continuously track the state of the conversation and support more complex conversation processes.

[0096] In addition, through Elasticsearch session information, Elasticsearch is a Lucene-based search and analysis engine that supports complex search queries and full-text search. Elasticsearch can be used to vectorize and store session information, and historical conversations that are similar or related to the current input can be quickly found, providing strong support for semantic recognition and context understanding.

[0097] Then, the number of click operations, the number of sliding operations and the text semantic fragments are encoded respectively through feature encoding to obtain click operation features, sliding operation features and text semantic features. These features exist in the form of feature vectors to facilitate the receipt of the purchase intention prediction model.

[0098] Next, the click operation features, sliding operation features and text semantic features are combined to obtain the first combined feature. The first combined feature is a combined vector, which realizes the integration of different types of data features and enables the model to comprehensively analyze different types of data.

[0099] Finally, the first combined feature is input into the pre-trained purchase intention recognition model to output the target customer's purchase intention recognition result for the target product. The purchase intention recognition model has learned the mapping relationship from user behavior characteristics to purchase intention through a large amount of training data.

[0100] Through the above embodiments, text is converted into machine-understandable semantic fragments through semantic recognition, and different types of data are converted into a unified feature vector through feature encoding, thereby improving the generalization ability and prediction accuracy of the purchase intention prediction model.

[0101] Furthermore, the sliding operation includes a short-distance sliding operation and a long-distance sliding operation. The long-distance sliding operation is sliding from the top of the target product interface to the bottom of the target product interface. After obtaining the number of sliding operations performed by the target customer on the target product interface, the method further includes:

[0102] Counting the operation duration of each short-distance sliding operation to obtain a first operation duration set;

[0103] Counting the operation duration of each long-distance sliding operation to obtain a second operation duration set;

[0104] An operation duration sequence is constructed based on the first operation duration set and the second operation duration set.

[0105] A short-distance sliding operation refers to a short-distance sliding operation on the target product interface, which is used to view partial details of the product, previews of adjacent products, etc. A long-distance sliding operation specifically refers to sliding from the top to the bottom of the target product interface. A long-distance sliding operation indicates that the user is browsing all the information or pictures of the product.

[0106] In this embodiment, for each short-distance sliding and long-distance sliding operation, the operation duration is counted to obtain a first operation duration set and a second operation duration set. The operation duration reflects the user's attention to the product and the browsing speed. Based on the first operation duration set and the second operation duration set, an operation duration sequence is constructed. This sequence not only includes the number of sliding operations, but also includes the duration information of each sliding. The operation duration sequence can more finely characterize the user's behavior pattern on the target product interface. For example, frequent and long-distance sliding indicates that the user may only browse the product casually, while long-distance sliding indicates that the user stays for a long time and may be viewing local details of the product.

[0107] Through the above embodiment, by introducing the sliding operation duration and combining it with the number of sliding times, the analysis of user behavior is made more comprehensive and detailed. The operation duration sequence provides more clues about the user's purchase intention, which helps to improve the accuracy of purchase intention identification.

[0108] Furthermore, after the steps of respectively encoding the number of click operations, the number of sliding operations and the text semantic segment to obtain the click operation feature, the sliding operation feature and the text semantic feature, the method further includes:

[0109] Obtain the time series features of the sliding operation from the operation duration sequence;

[0110] The time series features are associated with the sliding operation features to obtain the sliding operation time series features;

[0111] Combining the click operation feature, the sliding operation time series feature and the text semantic feature to obtain a second combined feature;

[0112] The second combined feature is input into the pre-trained purchase intention recognition model, and the purchase intention recognition result of the target customer for the target product is output.

[0113] In this embodiment, based on the above feature encoding, the time series feature of the sliding operation is further introduced and associated with the sliding operation feature, thereby obtaining a richer feature representation. The time series feature can capture the change information of the sliding operation in the time dimension, such as the stability of the sliding speed, the sliding frequency, etc. From the operation duration sequence constructed previously, the time series features of the sliding operation can be extracted, which include the duration of the sliding operation, the time interval between adjacent sliding operations, the change of the sliding speed, etc.

[0114] By associating time series features with sliding operation features, a more comprehensive sliding operation representation can be generated, which includes not only the number and type of sliding operations, but also the distribution and change pattern of these operations over time. Feature association can be achieved in many ways, such as simple concatenation, weighted summation, or through deep learning models (such as LSTM, GRU, etc.) to automatically learn the association relationship between features.

[0115] The second combination of features consists of click operation features, sliding operation time series features and text semantic features, which together form a comprehensive view of the user's interaction behavior with the target product. Compared with the first combination of features, the second combination of features contains more dimensional information, especially the time dimension, which enables the model to take into account more context and dynamic change factors when identifying user purchase intentions.

[0116] The pre-trained purchase intention recognition model has learned the mapping relationship from user behavior characteristics to purchase intention through a large amount of training data. By inputting the second combination of features into this model, the target customer's purchase intention recognition result for the target product can be obtained. Since the second combination of features contains richer and more comprehensive information, the pre-trained model is expected to achieve higher accuracy and better generalization ability when using these features for prediction.

[0117] Through the above embodiments, time series features are introduced, so that the model can capture the dynamic change information of user behavior and improve the accuracy of purchase intention recognition.

[0118] Further, the step of predicting the target customer's quotation for the target product based on the first behavior data and the second behavior data to obtain the product quotation prediction result specifically includes:

[0119] Feature encoding is performed on the first behavior data and the second behavior data respectively to obtain a first behavior feature and a second behavior feature;

[0120] Calculate the feature weights of the first behavior feature and the second behavior feature respectively based on a preset feature weight algorithm;

[0121] Performing feature weighting on the first behavior feature and the second behavior feature according to the feature weight;

[0122] Combine the weighted first behavior feature and the second behavior feature to obtain a third feature combination;

[0123] The third feature combination is input into the pre-trained commodity price prediction model to obtain the commodity price prediction result.

[0124] In this embodiment, feature encoding is performed on the first behavior data and the second behavior data respectively to obtain the first behavior feature and the second behavior feature. Different encoding methods can be used for the first behavior data and the second behavior data, such as one-hot encoding, label encoding, embedding vectors, etc.

[0125] Feature weights represent the importance of different features to the prediction target (i.e., product price). Through the preset feature weight algorithm, a weight value can be assigned to each feature, thereby emphasizing or weakening the impact of certain features in the subsequent feature weighting steps.

[0126] The system multiplies each feature value by its corresponding weight to obtain a weighted feature value, which will be used in the subsequent commodity quotation prediction model. After completing the feature weighting, the weighted first behavior feature and the second behavior feature are combined into a new feature set, namely the third feature combination, so as to serve as the input of the commodity quotation prediction model. The third feature combination is input into the pre-trained commodity quotation prediction model, and the quotation prediction result for the target commodity is obtained through the calculation of the model.

[0127] The pre-trained product quotation prediction model can be a regression model based on machine learning (such as linear regression, decision tree regression, random forest regression, etc.), or a model based on deep learning (such as neural network, recurrent neural network, etc.). The input of the product quotation prediction model is the third feature combination, and the output is the quotation prediction value for the target product.

[0128] Through the above embodiments, by calculating and weighting feature weights, the influence of important features is emphasized, the prediction accuracy of the model is improved, behavioral data from different sources or different types are combined, a comprehensive user behavior description is provided, and predictions are made using pre-trained models, which improves the efficiency and stability of the predictions.

[0129] Furthermore, the step of respectively calculating the feature weights of the first behavior feature and the second behavior feature based on a preset feature weight algorithm specifically includes:

[0130] Initialize the feature weights of the first behavior feature and the second behavior feature respectively to obtain a first initial weight and a second initial weight;

[0131] In a pre-constructed feature weight dictionary, respectively searching for feature standard values ​​corresponding to the first behavior feature and the second behavior feature to obtain the first feature standard value and the second feature standard value;

[0132] Comparing the magnitude relationship between the first behavior feature value and the first feature standard value to obtain a first comparison result, and adjusting the first initial weight based on the first comparison result to obtain a feature weight of the first behavior feature;

[0133] The magnitude relationship between the second behavior feature value and the second feature standard value is compared to obtain a second comparison result, and the second initial weight is adjusted based on the second comparison result to obtain a feature weight of the second behavior feature.

[0134] The system pre-builds a feature weight dictionary, which contains various behavioral features and their corresponding standard values. When the feature weight needs to be calculated, the standard value of the corresponding behavioral feature is found from the dictionary. The feature standard value represents the expected value or benchmark value of a certain behavioral feature under general or ideal conditions. By comparing the actual feature value with the standard value, the importance or abnormality of the feature can be evaluated.

[0135] In this embodiment, first, the system assigns an initial weight value to the first behavior feature and the second behavior feature respectively. This initial value is usually set based on some prior knowledge or assumptions and serves as the starting point for subsequent weight adjustments. Then, by comparing the actual behavior feature value with its standard value, it is determined whether the feature deviates from the normal or expected range, and its weight is adjusted accordingly. Specifically, for the first behavior feature and the second behavior feature, their actual feature values ​​are compared with the corresponding standard values ​​respectively. The comparison result can be a simple Boolean value (such as greater than, less than or equal to) or a specific difference value or ratio.

[0136] Next, the system adjusts the initial weight based on the comparison between the feature value and the standard value to reflect the importance of the feature in the prediction target. Specifically, the specific rules for weight adjustment can be set according to business needs and data characteristics. For example, if a feature value is significantly higher than its standard value, it may mean that the feature has an important impact on the prediction target, so its weight should be increased; conversely, if the feature value is significantly lower than the standard value, its weight may be reduced. The adjusted weight will be used as the weight value of the behavioral feature in subsequent model predictions.

[0137] Through the above embodiments, the importance of different behavioral features in prediction can be flexibly adjusted through the preset feature weight algorithm and feature standard value to adapt to different business scenarios and needs. And the calculation process of feature weight is based on clear comparison and adjustment rules, making the results of model prediction more explainable and credible.

[0138] In the above embodiment, the present application discloses a commodity quotation method, which belongs to the field of artificial intelligence technology. The present application obtains the user behavior data of the target customer within a preset time period to obtain the first behavior data, wherein the first behavior data is the user behavior data of the target customer operating the target commodity; identifies the target customer's purchase intention for the target commodity based on the user behavior data; when the target customer has a purchase intention for the target commodity, obtains the target customer's second behavior data, wherein the second behavior data is the target customer's historical purchase behavior data; predicts the target customer's quotation for the target commodity based on the first behavior data and the second behavior data, and obtains the commodity quotation prediction result; pushes the commodity quotation prediction result to the client of the target customer. The solution of the present application targets the technical problems of the traditional manual quotation method, and significantly improves the quotation efficiency and accuracy through standardized data processing procedures and intelligent analysis, avoids the interference of human subjective judgment in the quotation process, ensures that each customer can obtain an accurate quotation based on their actual behavior and needs, and optimizes the user experience.

[0139] In this embodiment, the electronic device (eg Figure 1 The server shown in the figure can receive instructions or obtain data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (Ultra Wi-Fi Band) connection, and other wireless connection methods currently known or to be developed in the future.

[0140] It should be emphasized that in order to further ensure the privacy and security of the above commodity quotation information, the above commodity quotation information can also be stored in a node of a blockchain.

[0141] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0142] The embodiments of the present application can acquire and process relevant data 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.

[0143] 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.

[0144] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0145] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0146] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a commodity quotation device, and the embodiment of the device is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0147] like Figure 3 As shown, the commodity quotation device 300 described in this embodiment includes:

[0148] The first data acquisition module 301 is used to acquire user behavior data of a target customer within a preset time period to obtain first behavior data, wherein the first behavior data is user behavior data of the target customer operating a target product;

[0149] A purchase intention identification module 302 is used to identify the purchase intention of target customers for target products based on user behavior data;

[0150] The second data acquisition module 303 is used to acquire the second behavior data of the target customer when the target customer has a purchase intention for the target product, wherein the second behavior data is the historical purchase behavior data of the target customer;

[0151] The commodity price prediction module 304 is used to predict the target customer's price for the target commodity according to the first behavior data and the second behavior data, and obtain a commodity price prediction result;

[0152] The commodity quotation output module 305 is used to push the commodity quotation prediction result to the client of the target customer.

[0153] Furthermore, the first behavior data includes click operations and sliding operations performed by the target customer on the target product interface of the product quotation system, as well as session operations initiated for the target product. The target product interface is an interface for displaying the target product. The purchase intention identification module 302 is specifically used to:

[0154] Obtain the number of clicks performed by the target customer on the target product interface to obtain the number of click operations; obtain the number of slide operations performed by the target customer on the target product interface to obtain the number of slide operations; obtain the session information of the target customer, and identify the target customer's purchase intention for the target product based on the number of click operations, the number of slide operations and the session information.

[0155] Furthermore, the purchase intention identification module 302 is further used to:

[0156] Perform text preprocessing on the conversation information, and perform semantic recognition on the preprocessed conversation text to obtain text semantic fragments;

[0157] The number of click operations, the number of sliding operations and the text semantic fragments are respectively encoded to obtain click operation features, sliding operation features and text semantic features;

[0158] Combining the click operation feature, the sliding operation feature and the text semantic feature to obtain a first combined feature;

[0159] The first combined feature is input into a pre-trained purchase intention recognition model, and a purchase intention recognition result of the target customer for the target product is output.

[0160] Furthermore, the sliding operation includes a short-distance sliding operation and a long-distance sliding operation. The long-distance sliding operation is sliding from the top of the target product interface to the bottom of the target product interface. The product quotation device 300 also includes a sliding duration acquisition module. The sliding duration acquisition module is specifically used to:

[0161] The operation duration of each short-distance sliding operation is counted to obtain a first operation duration set; the operation duration of each long-distance sliding operation is counted to obtain a second operation duration set; and an operation duration sequence is constructed based on the first operation duration set and the second operation duration set.

[0162] Furthermore, the purchase intention identification module 302 is also used for:

[0163] The time series features of the sliding operation are obtained from the operation duration sequence; the time series features are associated with the sliding operation features to obtain the sliding operation time series features; the click operation features, the sliding operation time series features and the text semantic features are combined to obtain the second combined features; the second combined features are input into the pre-trained purchase intention recognition model to output the target customer's purchase intention recognition result for the target product.

[0164] Furthermore, the commodity price prediction module 304 is specifically used for:

[0165] Feature encoding is performed on the first behavior data and the second behavior data respectively to obtain a first behavior feature and a second behavior feature; feature weights of the first behavior feature and the second behavior feature are calculated respectively based on a preset feature weight algorithm; feature weighting is performed on the first behavior feature and the second behavior feature according to the feature weights; the weighted first behavior feature and the second behavior feature are combined to obtain a third feature combination; the third feature combination is input into a pre-trained commodity quotation prediction model to obtain a commodity quotation prediction result.

[0166] Furthermore, the commodity price prediction module 304 is further used to:

[0167] Initialize the feature weights of the first behavior feature and the second behavior feature respectively to obtain a first initial weight and a second initial weight;

[0168] In a pre-constructed feature weight dictionary, respectively searching for feature standard values ​​corresponding to the first behavior feature and the second behavior feature to obtain the first feature standard value and the second feature standard value;

[0169] Comparing the magnitude relationship between the first behavior feature value and the first feature standard value to obtain a first comparison result, and adjusting the first initial weight based on the first comparison result to obtain a feature weight of the first behavior feature;

[0170] The magnitude relationship between the second behavior feature value and the second feature standard value is compared to obtain a second comparison result, and the second initial weight is adjusted based on the second comparison result to obtain a feature weight of the second behavior feature.

[0171] In the above embodiment, the present application discloses a commodity quotation device, which belongs to the field of artificial intelligence technology. The present application obtains the user behavior data of the target customer within a preset time period to obtain the first behavior data, wherein the first behavior data is the user behavior data of the target customer operating the target commodity; identifies the target customer's purchase intention for the target commodity based on the user behavior data; when the target customer has a purchase intention for the target commodity, obtains the target customer's second behavior data, wherein the second behavior data is the target customer's historical purchase behavior data; predicts the target customer's quotation for the target commodity based on the first behavior data and the second behavior data, and obtains the commodity quotation prediction result; pushes the commodity quotation prediction result to the client of the target customer. The solution of the present application targets the technical problems of the traditional manual quotation method, and significantly improves the quotation efficiency and accuracy through standardized data processing flow and intelligent analysis, avoids the interference of human subjective judgment in the quotation process, ensures that each customer can obtain an accurate quotation based on their actual behavior and needs, and optimizes the user experience.

[0172] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0173] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 having a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital processor (DSP), an embedded device, etc.

[0174] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0175] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of a commodity quotation method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0176] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the commodity quotation method.

[0177] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0178] In the above embodiment, the present application discloses a computer device, which belongs to the field of artificial intelligence technology. The present application obtains the user behavior data of the target customer within a preset time period to obtain the first behavior data, wherein the first behavior data is the user behavior data of the target customer operating the target product; identifies the target customer's purchase intention for the target product based on the user behavior data; when the target customer has a purchase intention for the target product, obtains the target customer's second behavior data, wherein the second behavior data is the target customer's historical purchase behavior data; predicts the target customer's quotation for the target product based on the first behavior data and the second behavior data, and obtains the product quotation prediction result; pushes the product quotation prediction result to the target customer's client. The solution of the present application targets the technical problems of the traditional manual quotation method, and significantly improves the quotation efficiency and accuracy through standardized data processing procedures and intelligent analysis, avoids the interference of human subjective judgment in the quotation process, ensures that each customer can obtain an accurate quotation based on their actual behavior and needs, and optimizes the user experience.

[0179] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the commodity quotation method as described above.

[0180] In the above embodiment, the present application discloses a computer-readable storage medium, which belongs to the field of artificial intelligence technology. The present application obtains the user behavior data of the target customer within a preset time period to obtain the first behavior data, wherein the first behavior data is the user behavior data of the target customer operating the target product; identifies the target customer's purchase intention for the target product based on the user behavior data; when the target customer has a purchase intention for the target product, obtains the target customer's second behavior data, wherein the second behavior data is the target customer's historical purchase behavior data; predicts the target customer's quotation for the target product based on the first behavior data and the second behavior data, and obtains the product quotation prediction result; pushes the product quotation prediction result to the target customer's client. The solution of the present application targets the technical problems of the traditional manual quotation method, and significantly improves the quotation efficiency and accuracy through standardized data processing procedures and intelligent analysis, avoids the interference of human subjective judgment in the quotation process, ensures that each customer can obtain an accurate quotation based on their actual behavior and needs, and optimizes the user experience.

[0181] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0182] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0183] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A commodity quotation method, characterized in that: include: Acquire user behavior data of a target customer within a preset time period to obtain first behavior data, wherein the first behavior data is user behavior data of the target customer operating a target product; Identifying the target customer's purchase intention for the target product based on the user behavior data; When the target customer has a purchase intention for the target product, obtaining second behavior data of the target customer, wherein the second behavior data is historical purchase behavior data of the target customer; Predicting the target customer's quotation for the target commodity based on the first behavior data and the second behavior data to obtain a commodity quotation prediction result; The commodity quotation prediction result is pushed to the client of the target customer.

2. The commodity quotation method according to claim 1, characterized in that: The first behavior data includes click operations and sliding operations performed by the target customer on a target product interface of a product quotation system, and a session operation initiated for the target product, wherein the target product interface is an interface for displaying the target product. The step of identifying the target customer's purchase intention for the target product based on the user behavior data specifically includes: Obtaining the number of click operations performed by the target customer on the target product interface to obtain the number of click operations; Obtaining the number of times the target customer performs sliding operations on the target product interface to obtain the number of sliding operations; The session information of the target customer is obtained, and the purchase intention of the target customer for the target product is identified according to the number of click operations, the number of slide operations and the session information.

3. The commodity quotation method according to claim 2, characterized in that: The step of obtaining the session information of the target customer and identifying the target customer's purchase intention for the target product according to the number of click operations, the number of slide operations and the session information specifically includes: Performing text preprocessing on the conversation information, and performing semantic recognition on the preprocessed conversation text to obtain text semantic fragments; Performing feature encoding on the number of click operations, the number of sliding operations and the text semantic segment respectively to obtain click operation features, sliding operation features and text semantic features; Combining the click operation feature, the slide operation feature and the text semantic feature to obtain a first combined feature; The first combined feature is input into a pre-trained purchase intention recognition model, and a purchase intention recognition result of the target customer for the target product is output.

4. The commodity quotation method according to claim 3, characterized in that: The sliding operation includes a short-distance sliding operation and a long-distance sliding operation, wherein the long-distance sliding operation is sliding from the top of the target product interface to the bottom of the target product interface. After obtaining the number of sliding operations performed by the target customer on the target product interface, the step further includes: Counting the operation duration of each short-distance sliding operation to obtain a first operation duration set; Counting the operation duration of each long-distance sliding operation to obtain a second operation duration set; An operation duration sequence is constructed based on the first operation duration set and the second operation duration set.

5. The commodity quotation method according to claim 4, characterized in that: After the step of respectively encoding the number of click operations, the number of sliding operations and the text semantic segment to obtain click operation features, sliding operation features and text semantic features, the method further includes: Acquire the time series characteristics of the sliding operation from the operation duration sequence; Performing feature association between the time series feature and the sliding operation feature to obtain the sliding operation time series feature; Combining the click operation feature, the sliding operation time series feature and the text semantic feature to obtain a second combined feature; The second combined feature is input into a pre-trained purchase intention recognition model, and a purchase intention recognition result of the target customer for the target product is output.

6. The commodity quotation method according to any one of claims 1 to 5, characterized in that: The step of predicting the target customer's quotation for the target commodity based on the first behavior data and the second behavior data to obtain a commodity quotation prediction result specifically includes: Performing feature encoding on the first behavior data and the second behavior data respectively to obtain a first behavior feature and a second behavior feature; Calculate the feature weights of the first behavior feature and the second behavior feature respectively based on a preset feature weight algorithm; Performing feature weighting on the first behavior feature and the second behavior feature according to the feature weight; Combining the weighted first behavior feature and the second behavior feature to obtain a third feature combination; The third feature combination is input into a pre-trained commodity price prediction model to obtain the commodity price prediction result.

7. The commodity quotation method according to claim 6, characterized in that: The step of respectively calculating the feature weights of the first behavior feature and the second behavior feature based on a preset feature weight algorithm specifically includes: Initializing feature weights of the first behavior feature and the second behavior feature respectively to obtain a first initial weight and a second initial weight; In the pre-constructed feature weight dictionary, the feature standard values ​​corresponding to the first behavior feature and the second behavior feature are searched respectively to obtain the first feature standard value and the second feature standard value. Comparing the magnitude relationship between the first behavior feature value and the first feature standard value to obtain a first comparison result, and adjusting the first initial weight based on the first comparison result to obtain a feature weight of the first behavior feature; The second behavior feature value and the second feature standard value are compared to obtain a second comparison result, and the second initial weight is adjusted based on the second comparison result to obtain a feature weight of the second behavior feature.

8. A commodity quotation device, characterized in that: include: A first data acquisition module is used to acquire user behavior data of a target customer within a preset time period to obtain first behavior data, wherein the first behavior data is user behavior data of the target customer operating a target product; A purchase intention identification module, used to identify the purchase intention of the target customer for the target product based on the user behavior data; A second data acquisition module is used to acquire second behavior data of the target customer when the target customer has a purchase intention for the target product, wherein the second behavior data is the historical purchase behavior data of the target customer; A commodity quotation prediction module, used for predicting the quotation of the target customer for the target commodity according to the first behavior data and the second behavior data, and obtaining a commodity quotation prediction result; The commodity quotation output module is used to push the commodity quotation prediction result to the client of the target customer.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the commodity quotation method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the commodity quotation method according to any one of claims 1 to 7 are implemented.

Images