CN115222490A

CN115222490A - Portrait-based foreign sales order generation method, device, equipment and storage medium

Info

Publication number: CN115222490A
Application number: CN202210921752.6A
Authority: CN
Inventors: 陈思妮
Original assignee: Ping An Life Insurance Company of China Ltd
Current assignee: Ping An Life Insurance Company of China Ltd
Priority date: 2022-08-02
Filing date: 2022-08-02
Publication date: 2022-10-21

Abstract

The invention relates to the field of artificial intelligence, and provides an external sales slip generation method, device, equipment and storage medium based on images.

Description

Portrait-based foreign sales order generation method, device, equipment and storage medium

Technical Field

The invention relates to the field of artificial intelligence, in particular to an external sales order generation method, device, equipment and storage medium based on an image.

Background

At present, aiming at product quotation, in national or domestic trade, a client inquires commodity price from a seller, and the seller gives out reasonable quotation by considering factors such as cost, profit, market competitiveness and the like of the product, so that the reasonable quotation can quickly attract the attention of the client, improve the finished product at a large rate and ensure the profit of the product. An excessively high premium may be desirable to the customer. Too low insurance cannot guarantee profits or cause some users to question product quality issues. However, when a price is quoted for a product sold by outsources, the consumption level of the outsource object, the trade data of the product sold by outsources, such as the currency tax rate information of the region where the outsource object is located and the local area of the product to be sold, and the position information of the region where the outsource object is located, have many influencing factors, so that it is difficult for the product sold by outsources to obtain a reasonable price quotation.

Disclosure of Invention

In view of the above, it is necessary to provide a method, an apparatus, a device and a storage medium for generating an outsourcing invoice based on an image, so as to solve the problem of how to obtain a reasonable quotation for an outsourcing product.

In a first aspect, a method for generating an outlook based on an image is provided, the method comprising:

carrying out data relation mining processing on the portrait data of the historical export object by utilizing a deep learning algorithm to obtain consumption portrait correlation factors of the historical export object, and constructing an evaluation model based on the consumption portrait correlation factors; the grade evaluation model is used for evaluating the consumption grade of the export sales object;

acquiring consumption portrait data of an export object, evaluating the consumption level of the export object by using an evaluation model based on the consumption portrait data, and determining the evaluation result as the target consumption level of the export object;

acquiring product price information of a product to be sold, determining the product price grade of the product to be sold by combining a preset price grade dividing rule, determining a first offer weight according to the target consumption grade of the foreign sales object and the product price grade, and generating an initial product offer according to the first offer weight and the product price information;

acquiring trade portrait data of the foreign sales object, wherein the trade portrait data comprises tariff information of a region where the foreign sales object is located, currency tax rate information of the region where the foreign sales object is located and the local product to be sold, and position information of the region where the foreign sales object is located;

inputting the initial product quote and the trade portrait data into a bill generation model, and outputting an export sales bill aiming at the export sales object.

In a second aspect, an image-based outsourcing form generation apparatus is provided, the apparatus comprising:

the mining module is used for mining data relation of the image data of the historical export object by utilizing a deep learning algorithm, acquiring consumption image correlation factors of the historical export object and constructing an evaluation model based on the consumption image correlation factors; the grade evaluation model is used for evaluating the consumption grade of the export sales object;

the consumption grade evaluation module is used for acquiring consumption portrait data of the export object, evaluating the consumption grade of the export object by using an evaluation model based on the consumption portrait data, and determining an evaluation result as a target consumption grade of the export object;

the initial product quotation module is used for acquiring product price information of a product to be sold, determining the product price grade of the product to be sold by combining a preset price grade division rule, determining a first quotation weight according to the target consumption grade of the foreign sales object and the product price grade, and generating an initial product quotation according to the first quotation weight and the product price information;

the trade portrait data acquisition module is used for acquiring trade portrait data of the foreign sales object, wherein the trade portrait data comprises tariff information of a region where the foreign sales object is located, currency tax rate information of the region where the foreign sales object is located and the local product to be sold, and position information of the region where the foreign sales object is located;

and the external sales bill generation module is used for inputting the initial product quotation and the trade portrait data into a bill generation model and outputting an external sales bill aiming at the external sales object.

In a third aspect, an embodiment of the present invention provides a computer device, where the computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor, when executing the computer program, implements the portrait-based external sales order generation method according to the first aspect.

In a fourth aspect, the present invention provides a computer-readable storage medium, where a computer program is stored, and the computer program, when executed by a processor, implements the portrait-based export sales order generation method according to the first aspect.

Compared with the prior art, the invention has the following beneficial effects:

the method comprises the steps of utilizing a deep learning algorithm to conduct data relation mining processing on image data of historical foreign sales objects, obtaining consumption image correlation factors of the historical foreign sales objects, constructing an evaluation model based on the consumption image correlation factors, wherein the grade evaluation model is used for evaluating consumption grades of the foreign sales objects, obtaining product price information of products to be sold, determining the product price grades of the products to be sold according to preset price grade division rules, determining first quotation weight according to target consumption grades and the product price grades of the foreign sales objects, generating initial product quotation according to the first quotation weight and the product price information, obtaining trade image data of the foreign sales objects, inputting the initial product quotation and the trade image data into a model generation model, outputting foreign sales slips for the foreign sales objects, utilizing price grades of products to be sold by users according to the consumption grades of the foreign sales objects, utilizing currency tax rate information of the products locally to be sold, utilizing the regions where the foreign sales objects are located, obtaining position information of corresponding substitute sales products, and increasing the price information of the corresponding substitute products, and obtaining the reasonable quotation of the product.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.

FIG. 1 is a diagram illustrating an application environment of a method for generating an outbound invoice based on an image according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating a method for generating an export invoice based on an image according to an embodiment of the present invention;

FIG. 3 is a flowchart illustrating a method for generating an export invoice based on an image according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of an external sales order generating apparatus according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items and includes such combinations.

As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".

Furthermore, in the description of the present invention and the appended claims, the terms "first," "second," "third," and the like are used for distinguishing between descriptions and not necessarily for describing or implying relative importance.

Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present invention. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless otherwise specifically stated.

The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

It should be understood that, the sequence numbers of the steps in the following embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

In order to explain the technical means of the present invention, the following description will be given by way of specific examples.

The portrait-based export sales order generation method provided by an embodiment of the present invention can be applied to the application environment shown in fig. 1, in which a client communicates with a server. The client includes, but is not limited to, a palm top computer, a desktop computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), and other computer devices. The server side can be implemented by an independent server or a server cluster formed by a plurality of servers.

Fig. 2 is a schematic flow diagram of a sketch-based export sales slip generation method according to an embodiment of the present invention, where the sketch-based export sales slip generation method may be applied to the server in fig. 1, and the server is connected to a corresponding client to provide a model training service for the client. As shown in FIG. 2, the portrait-based out-sales slip generation method may include the following steps.

S201: and carrying out data relation mining processing on the image data of the historical export object by utilizing a deep learning algorithm to obtain the consumption image correlation factors of the historical export object, and constructing an evaluation model based on the consumption image correlation factors.

In step S201, the deep learning algorithm is valuable for mining and predictive analysis of big data, and deep learning can effectively improve experimental effects by combining shallow basic features and further mining and learning high-level abstract features in data. The data relation mining process is used for analyzing, calculating, sorting and other processing processes to the data, and an evaluation model is constructed

In this embodiment, the portrait data of the historical export object is portrait data of different areas, different times and different scales, and the portrait data of the historical export object is preprocessed and analyzed, the data preprocessing is to supplement, clean and calculate the portrait data of the historical export object, and the data analysis utilizes a distributed database or a distributed calculation cluster to perform common analysis, classification and summarization on mass data stored in the distributed database or the distributed calculation cluster, so as to meet most common analysis requirements. The data cleaning is to clean the error data in the database, because the data in the database is a collection of data oriented to a certain subject, the data is extracted from a plurality of business systems and contains historical data, thus avoiding that some data are error data and some data conflict with each other, and cleaning the error data and the conflict data. For example, in the process of sales, if text information appears in the identification card information in the personal basic information, the text information is regarded as error data, and the identification card information data in the personal basic information is cleaned. Data supplement is to improve data with missing, for example, in the process of bank transaction, data of each transaction is important data to be referred to for prediction, when the transaction data is missing, prediction of future transaction is influenced, and complete transaction data needs to be supplemented. Data pre-processing normalizes the data, which can slow down learning with large inputs, so the normalized data is scaled using StandardScaler, which normalizes the data for each dimension.

After data are processed, data characteristics are selected, consumption levels of foreign sales objects are evaluated in the embodiment, influence factors related to the consumption levels are selected by combining the characteristics of portrait data of historical foreign sales objects, a framework is defined, a recurrent neural network is used for processing original data, the recurrent neural network model can reduce the training cost of the model, the redundancy of negative data samples is eliminated, characteristics are automatically learned at the bottom of the network, and more valuable information of the data is mined. And (3) constructing an evaluation model according to the learned data characteristics, selecting a Sigmoid function as an activation function in the recurrent neural network, stopping training when the training times are increased and the loss function value is not reduced, and outputting a corresponding model.

Optionally, the performing data relationship mining processing on the image data of the historical export object by using a deep learning algorithm to obtain related consumption image data of the historical export object, and constructing an evaluation model based on the related consumption image data includes:

processing the image data of the historical export object by using an Apriori algorithm, and obtaining a consumption image correlation factor of an evaluation grade according to the relevance of the consumption image correlation factor and the evaluation grade in the image data of the historical export object;

analyzing the consumption image correlation factors of the evaluation level, extracting the characteristic engineering of the consumption image correlation factors of the evaluation level, and constructing an evaluation model.

In this embodiment, an Apriori algorithm is used to process image data of a historical export object, a consumption image correlation factor of the historical export object is obtained from the correlation of the consumption image correlation factor in the image data of the historical export object, and an evaluation model is constructed by extracting a feature engineering of the consumption image correlation factor with the image data of the historical export object based on analysis of the consumption image correlation factor of the image data of the historical export object.

In this embodiment, in the process of extracting the data feature, the consumption portrait related factor of the portrait data of the historical export object of the evaluation model constructed as needed is used as a feature, the portrait data of the historical export object is processed by using Apriori algorithm, and the consumption portrait related factor of the consumption level is obtained according to the relevance of the consumption portrait related factor in the portrait data of the historical export object, the Apriori algorithm uses known frequency as a measurement standard, and finds a frequent item set through association, and the elements in the frequent item set are associated with each other, so that the factors respectively associated with the consumption level can be obtained from the frequent item set.

It should be noted that, the evaluation level consumption figure related factors are selected from different dimensions, dimensions and units of the evaluation level consumption figure related factors are not uniform, and therefore the weight of the evaluation features of the model is affected, and the estimation effect of the model is further affected. Therefore, feature normalization processing is required to be performed, and feature data is scaled to a smaller interval range, and a common method is to perform feature extraction during data mining by Min-Max normalization processing to obtain data features.

S202: acquiring consumption portrait data of the export object, evaluating the consumption level of the export object by using an evaluation model based on the consumption portrait data, and determining the evaluation result as the target consumption level of the export object.

In step S202, the consumption image data includes consumption level information of a region where the export object is located, consumption level information of a industry where the export object is located, and consumption capability information of the export object, and the evaluation model is a classification model obtained by deep learning.

In this embodiment, the consumption representation data of the export object is obtained, which includes consumption level information of a region where the export object is located, consumption level information of an industry where the export object is located, and consumption capability information of the export object. When the consumption portrait data of the foreign sales object is acquired, the consumption portrait data of the corresponding acquired foreign sales object is acquired through a crawler technology. The consumption expense data of the foreign marketing object is searched through a breadth-first search algorithm, traversal of the algorithm on the tree section graph is mainly realized along the width of the tree, the graph point calculation method is also more traditional, and once a target is found, the algorithm is immediately stopped. The process of designing and implementing the algorithm is relatively simple, the search being in the category of a blind search. In addition, by combining breadth-first search and webpage filtering, webpage crawling is mainly realized by means of breadth-first strategies, and then irrelevant webpages in the webpages are filtered.

It should be noted that, a corresponding topic may also be set through a keyword in the foreign object, consumption image data for the foreign object is searched, and the topic is a topic crawler, where the topic crawler starts from a group of seed pages related to the topic and obtains page information pointed by the URL. And storing the pages related to the set theme, extracting new URL links from the pages, and putting the links into a URL queue after estimating and scoring the link values. And the scheduling module takes out the URL at the head of the queue as a page needing downloading next time. In this embodiment, the crawler theme may be set as consumption representation data.

Based on consumption portrait data, the consumption grade of the export object is evaluated by using an evaluation model, the evaluation result is determined to be the target consumption grade of the export object, the evaluation model is a classification model obtained through neural network learning, then the neural network is applied to the consumption grade evaluation model, the essence is that the consumption portrait data information of the export object is used as input to be provided to a neural network input layer, after excitation and transmission among neurons and continuous iteration processing, weight values and threshold values among the neurons can be continuously adjusted to adapt to the currently input vector characteristics, similar output modes are generated for future similar characteristic input, in the actual consumption grade evaluation application, similar to logistic regression analysis, the neural network can disperse the consumption grade of the export object into the export object with higher consumption level, and the export object with medium consumption level and the export object with lower consumption level.

The greatest feature of the evaluation model based on the neural network is that consumption image data of an outsourced object can be sufficiently learned by using the autonomous learning ability of the neural network. Finally, a hidden model is obtained and stored in a specific connection structure of the neural network to form a nonlinear mapping function, namely the hidden model can be mapped into a specific consumption grade according to the characteristics of the consumption portrait data of the export sales object so as to evaluate the export sales object.

Generally, in an artificial neural network, an input signal sequentially enters an input layer and a hidden layer, and finally reaches an output layer. A forward propagation network and a feedback type propagation network may be classified according to whether the input signal is sequentially transmitted forward or backward between the neurons. In a feedback type propagation network, the signal at the output layer will continue to propagate to the input layer as input for the next iteration.

S203: the method comprises the steps of obtaining product price information of a product to be sold, determining the product price level of the product to be sold by combining a preset price level division rule, determining a first offer weight according to the target consumption level and the product price level of an outsourcing object, and generating an initial product offer according to the first offer weight and the product price information.

In step S203, the price grades of the products to be sold are classified according to a preset price grade classification rule, when the price grades of the products are classified, different product prices correspond to different price ranges, a first offer weight is determined according to the target consumption grade and the product price grade of the export sales object, and an initial product offer is generated according to the first offer weight and the product price information. The initial product offer reflects the different values that the product represents on different consumers.

In the embodiment, firstly, the product price is graded into high-price products, medium-price products and low-price products, the prices of the products to be sold are clustered through the obtained different prices of the products to be sold, the product price range is determined, and the products are graded into different grades according to the clustering result.

And combining the consumption grade and the product price grade, combining any consumption grade and any price grade in pairs, setting different numerical values for the corresponding consumption grade and price grade by different combinations respectively to serve as first offer weight, and combining the first offer weight and the product price information to obtain the initial product price.

Optionally, the obtaining product price information of the product to be sold, and determining the product price level of the product to be sold by combining with a preset price level division rule, includes:

the method comprises the steps of obtaining product price information of a product to be sold, carrying out clustering operation on the product price information of the product to be sold through a K-means clustering algorithm to obtain a clustering result, and setting a preset price grade division rule according to the clustering result;

and obtaining the product price grade of the product to be sold according to a preset product price grade division rule.

In this embodiment, food items with different prices are classified and classified by a K-means clustering algorithm, clustering is a process in which a data set is divided into a plurality of groups, data objects in the same group have higher similarity, and data objects with larger differences are in different groups. The K-means clustering algorithm is to assume a data set containing n data objects, to designate the number of K clusters, to cluster the objects in the D into proper clusters by adopting a dividing method, so that each object only belongs to one cluster, to designate a numerical value K as the number of the clusters, to place the data set to be clustered into a Euclidean space, to randomly select K centroids representing each cluster as an initial central point of a clustering process, to redistribute the data objects to the nearest clusters according to the distance between each data object and each central point, and to update the central points of the corresponding clusters again after each iteration until no change occurs. And performing clustering operation on the product price information of the product to be sold through a K-means clustering algorithm to obtain a clustering result, and setting a preset price grade division rule according to the clustering result. And obtaining the product price grade of the product to be sold according to a preset product price grade division rule.

Optionally, obtaining product price information of a product to be sold, performing clustering operation on the product price information of the product to be sold through a K-means clustering algorithm to obtain a clustering result, and setting a preset price grade division rule according to the clustering result, including:

calculating to obtain mean value price data corresponding to the product price information of the products to be sold in each cluster according to the product price information of the products to be sold in each cluster in the clustering results;

and classifying grade intervals according to the mean value price data range in the adjacent clusters to obtain a preset price grade classification rule.

In this embodiment, each cluster in the clustering result includes a corresponding product price, mean price data corresponding to product price information of a product to be sold in each cluster is obtained by calculation according to the product price of the product to be sold in each cluster in the clustering result, price classes are divided according to the mean price in each cluster, and a class interval is divided according to a mean price data range in adjacent clusters to obtain a preset price class division rule.

It should be noted that, when performing K-means clustering operation, whether the clustering result is reasonable is determined by the clustering validity index, in this embodiment, whether the clustering result is reasonable is determined according to GA (generalization ability), and the GA index evaluates the clustering result from the generalization ability in guided learning based on the current clustering result, that is, it is considered that the superiority and inferiority of the clustering result are related to the generalization ability of the clustering result to the prediction of an unknown sample, so that it is different from the existing clustering validity index, whether it is an external validity index or an internal validity index. The GA indexes are split into a training set and a data set by splitting the acquired price data of the products to be sold, and the training set and the data set are clustered respectively. And performing machine learning on the clustering result of the training set to construct a classifier, predicting the test set by using the classifier, and further comparing the prediction result with the clustering result. And judging the rationality of the clustering according to the distance between the GA index value and 1. The closer the GA index value is to 1, the more reasonable the clustering result is.

In actual clustering, the number of clusters should not be too large, otherwise, clustering results are difficult to explain, and therefore, limited optional product prices can be obtained by adopting an exhaustive method. And selecting the clustering number corresponding to the largest GA index as the most reasonable clustering result by calculating the GA indexes under different clustering numbers.

Optionally, determining a first offer weight according to the target consumption level and the product price level of the export sales object, and generating an initial product offer according to the first offer weight and the product price information, including:

calculating to obtain a first ratio of the score of the target consumption grade to the total score of each consumption grade according to the target consumption grade of the export sales object and the preset score of each consumption grade;

calculating a second ratio of the product price grade score to the total score of each price grade according to the product price grade and the preset score of each price grade;

and calculating the sum of the first ratio and the second ratio to obtain a first quotation weight, and generating an initial product quotation according to the first quotation weight and the product price information.

In this embodiment, the consumption level and the product price level are combined, any consumption level and any price level are combined in pairs, different values are set for the corresponding consumption level and price level in different combinations, that is, different values are set for the importance degree of each group for the quotation, the consumption level and the product price level are combined into tables, each table corresponds to different arrays, and each array corresponds to the value weight corresponding to different consumption levels and price levels.

In this embodiment, when weights of different consumption levels and different price levels are set, different scores are set for each consumption level and each price level, for example, the highest consumption level is set to 5 points, the medium consumption level is set to 3 points, the low consumption level is set to 2 points, the highest price level is set to 5 points, the medium equivalence grid level is set to 3 points, the low equivalence grid level is set to 2 points, a first ratio of the score in each consumption level to the sum of the scores in each consumption level and a second ratio of the score in each price level to the sum of the scores in each price level are calculated.

According to the target consumption level of the foreign sales object, a first ratio of the target consumption level to the total score of each consumption level is calculated, according to the product price level, a second ratio of the product price level to the total score of each price level is calculated, the sum of the first ratio and the second ratio is calculated to obtain a first offer weight, and according to the first offer weight and the product price information, an initial product offer is generated.

It should be noted that, when the calculated initial product offer value is lower than a preset minimum initial product offer or higher than a maximum preset product offer, the initial product offer is modified to be the lowest dehumidification product offer or the highest initial product offer, for example, when the initial product offer is lower than the minimum initial product offer, the minimum initial product offer is extracted as the initial product offer of the corresponding product.

S204: and acquiring trade portrait data of the export sales object.

In step S204, trade image data of the export object is obtained, where the trade image data includes tariff information of a region where the export object is located, information of a currency tax rate of the region where the export object is located and a local product to be sold, and location information of the region where the export object is located.

In this embodiment, when acquiring the trade portrait data of the export sales object, the crawler technology is used to acquire the trade portrait data corresponding to the export sales object, and when acquiring the web page corresponding to the relevant information, the crawler technology is used to extract the web page content to obtain the trade portrait data of the export sales object, and during extraction, the web page structuring and modularization features are mainly used. The wrapper designs a uniform template according to the layout rule of the webpage, and obtains the position of the text in the webpage through the analysis of the template. Currently, common wrapper tools have TSIMMIS tools, XWRAR tools, etc., which require manual writing of rules.

It should be noted that, in consideration of the characteristics of the HTML document of the web page, the text of the web page may also be extracted based on a method for statistically establishing a document DOM tree. The basic idea of the method is as follows: the method comprises the steps of representing a webpage as a document tree by using an HTML mark of the webpage, counting information such as text length, link length, number ratio of text to links and the like under each node of the document tree, and judging whether the node is a text node or not.

S205: and inputting initial product quotation and trade portrait data into a document generation model, and outputting an external sales document aiming at an external sales object.

In step S205, the document generation model is a model for generating an export sales slip, and the generated export sales slip includes forecast price information of the product to be sold.

In this embodiment, the initial product quotation and the trade portrait data are input into the document generation model, and an export sales document for an export sales object is output, wherein the document generation model is obtained according to the type of an export product, and different product types correspond to different document generation models.

It should be noted that, when a plurality of products are offered, the offer task can be decomposed into offer tasks of a plurality of products, so as to support collaborative offers for a plurality of products at the same time, and after each product is offered, the offers are automatically collected, for example: for a large project, the quotation of two consignment products is included, A is responsible for the quotation of the product A under the project, B is responsible for the quotation of the product B under the project, and the quotation data of the project is automatically generated by summarizing the quotations of the product A and the product B and is displayed on an output foreign sales order.

Optionally, inputting the initial product quote and the trade portrait data into the document generation model, and outputting the foreign sales document for the foreign sales object, including:

constructing an input matrix based on the initial product quotation and the trade portrait data, and carrying out normalization processing on the input matrix to obtain target input data;

and inputting the target input data into the bill generation model, and outputting the foreign sales bill aiming at the foreign sales object.

In this embodiment, an input matrix is constructed based on the initial product quotation and the trade portrait data, the input matrix is normalized, the initial product quotation and the trade portrait data are converted into data between 0 and 1, target input data are obtained, the normalized data can reduce the computation amount, the target input data are input into the document generation model, and an export sales order for an export sales object is output.

Referring to fig. 3, which is a flowchart illustrating a method for generating an external sales slip based on an image according to an embodiment of the present invention, as shown in fig. 3, the method for generating an external sales slip based on an image may include the following steps:

s301: carrying out data relation mining processing on the portrait data of the historical export object by using a deep learning algorithm to obtain consumption portrait correlation factors of the historical export object, and constructing an evaluation model based on the consumption portrait correlation factors;

s302: acquiring consumption image data of the export object, evaluating the consumption grade of the export object by using an evaluation model based on the consumption image data, and determining the evaluation result as the target consumption grade of the export object;

s303: the method comprises the steps of obtaining product price information of a product to be sold, determining the product price level of the product to be sold by combining a preset price level division rule, determining a first offer weight according to a target consumption level and the product price level of an export sales object, and generating an initial product offer according to the first offer weight and the product price information;

s304: acquiring trade portrait data of the foreign sales object, wherein the trade portrait data comprises tariff information of a region where the foreign sales object is located, currency tax rate information of the region where the foreign sales object is located and a local product to be sold, and position information of the region where the foreign sales object is located;

s305: and inputting initial product quotation and trade portrait data into a document generation model, and outputting an export sales document aiming at an export sales object.

The contents of the steps S301 to S305 are the same as the contents of the steps S201 to S205, and reference may be made to the description of the steps S201 to S205, which is not repeated herein.

S306: and matching the external sales order with a preset sales statement to obtain a target sales statement, and sending the target sales statement to a corresponding client.

In this embodiment, in order to better sell the product, the seller sets a corresponding sale statement for the corresponding external sales order, and after the product quote in the external sales order is obtained through prediction, the seller matches the corresponding sale statement according to the quote in the external sales order to obtain a target sale statement, and sends the target sale statement to the corresponding client.

Referring to fig. 4, fig. 4 is a schematic structural diagram of an external sales order generation apparatus based on an image according to an embodiment of the present invention. In this embodiment, each unit included in the mobile terminal is configured to execute each step in the embodiments corresponding to fig. 2 to fig. 3. Please refer to fig. 2 to 3 and fig. 2 to 3 for the corresponding embodiments. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to fig. 4, the generating means 40 includes: the system comprises a mining module 41, a consumption grade evaluation module 42, an initial product quotation module 43, a trade image data acquisition module 44 and an outsourcing receipt generation module 45.

The mining module 41 is used for mining data relation of the image data of the historical export object by using a deep learning algorithm, acquiring consumption image correlation factors of the historical export object and constructing an evaluation model based on the consumption image correlation factors; the grade evaluation model is used for evaluating the consumption grade of the export sales objects.

And the consumption grade evaluation module 42 is used for acquiring consumption image data of the export object, evaluating the consumption grade of the export object by using the evaluation model based on the consumption image data, and determining the evaluation result as the target consumption grade of the export object.

The initial product quotation module 43 is configured to obtain product price information of a product to be sold, determine a product price level of the product to be sold in combination with a preset price level division rule, determine a first quotation weight according to a target consumption level and the product price level of the export sales object, and generate an initial product quotation according to the first quotation weight and the product price information.

And the trade image data acquisition module 44 is used for acquiring trade image data of the foreign sales object, wherein the trade image data comprises tariff information of a region where the foreign sales object is located, information of the local currency tax rate of the region where the foreign sales object is located and a product to be sold, and position information of the region where the foreign sales object is located.

And an export sales slip generation module 45, configured to input the initial product quotation and the trade image data into the slip generation model, and output an export sales slip for an export sales object.

Optionally, the excavation module 41 includes:

and the consumption image correlation factor acquisition unit is used for processing the image data of the historical export object by using an Apriori algorithm and obtaining the consumption image correlation factor of the evaluation grade according to the relevance between the consumption image correlation factor and the evaluation grade in the image data of the historical export object.

And the construction unit is used for analyzing the consumption image correlation factors of the evaluation levels, extracting the characteristic engineering of the consumption image correlation factors of the evaluation levels and constructing an evaluation model.

Optionally, the initial product quotation module 43 includes:

and the clustering unit is used for acquiring the product price information of the product to be sold, carrying out clustering operation on the product price information of the product to be sold through a K-means clustering algorithm to obtain a clustering result, and setting a preset price grade division rule according to the clustering result.

And the price grade dividing unit is used for acquiring the product price grade of the product to be sold according to a preset product price grade dividing rule.

Optionally, the clustering unit includes:

and the mean value price acquiring subunit is used for calculating to obtain mean value price data corresponding to the product price information of the products to be sold in each cluster according to the product price information of the products to be sold in each cluster in the clustering result.

And the rule division subunit is used for dividing the grade interval according to the average value price data range in the adjacent clusters to obtain a preset price grade division rule.

Optionally, the initial product quotation module 43 includes:

and the first ratio acquisition unit is used for calculating a first ratio of the total score of the target consumption grade and the score of each consumption grade according to the target consumption grade of the export sales target and the preset score of each consumption grade.

And the second ratio acquisition unit is used for calculating a second ratio of the product price grade score to the total score of each price grade according to the product price grade and the preset score of each price grade.

And the initial product quotation unit is used for calculating the sum of the first ratio and the second ratio to obtain a first quotation weight, and generating initial product quotation according to the first quotation weight and the product price information.

Optionally, the external sales slip generating module 45 includes:

and the target input data acquisition unit is used for constructing an input matrix based on the initial product quotation and the trade portrait data, and carrying out normalization processing on the input matrix to obtain target input data.

And the input unit is used for inputting the target input data into the bill generation model and outputting the external sales bill aiming at the external sales object.

Optionally, the generating device 40 further includes:

and the sending module is used for matching the external sales order with a preset sales statement to obtain a target sales statement and sending the target sales statement to the corresponding client.

It should be noted that, because the contents of information interaction, execution process, and the like between the above units are based on the same concept, specific functions and technical effects thereof according to the method embodiment of the present invention, reference may be made to the part of the method embodiment specifically, and details are not described herein again.

Fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown in fig. 5, the computer apparatus of this embodiment includes: at least one processor (only one shown in FIG. 5), a memory, and a computer program stored in the memory and executable on the at least one processor, the processor when executing the computer program implementing the steps in any of the various portrait-based export receipt generation method embodiments described above.

The computer device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that fig. 5 is merely an example of a computer device and is not intended to be limiting, and that a computer device may include more or fewer components than those shown, or some components may be combined, or different components may be included, such as a network interface, a display screen, and input devices, etc.

The Processor may be a CPU, and the Processor may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory includes readable storage media, internal memory, etc., wherein the internal memory may be the internal memory of the computer device, and the internal memory provides an environment for the operating system and the execution of the computer-readable instructions in the readable storage media. The readable storage medium may be a hard disk of the computer device, and in other embodiments may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the computer device. Further, the memory may also include both internal storage units and external storage devices of the computer device. The memory is used for storing an operating system, application programs, a BootLoader (BootLoader), data, and other programs, such as program codes of a computer program, and the like. The memory may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only used for distinguishing one functional unit from another, and are not used for limiting the protection scope of the present invention. The specific working processes of the units and modules in the above-mentioned apparatus may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method of the above embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium and used by a processor to implement the steps of the above method embodiments. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code, recording medium, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier signals, telecommunications signals, and software distribution media. Such as a usb-drive, a removable hard drive, a magnetic or optical disk, etc. In certain jurisdictions, computer-readable media may not be an electrical carrier signal or a telecommunications signal in accordance with legislative and patent practice.

The present invention can also be implemented by a computer program product, which when executed on a computer device causes the computer device to implement all or part of the processes in the method of the above embodiments.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided by the present invention, it should be understood that the disclosed apparatus/computer device and method may be implemented in other ways. For example, the above-described apparatus/computer device embodiments are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

The above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein.

Claims

1. An external sales order generation method based on an image is characterized by comprising the following steps:

carrying out data relation mining processing on the image data of the historical export object by utilizing a deep learning algorithm to obtain consumption image correlation factors of the historical export object, and constructing an evaluation model based on the consumption image correlation factors; the grade evaluation model is used for evaluating the consumption grade of the export sales object;

the method comprises the steps of obtaining product price information of a product to be sold, determining the product price level of the product to be sold by combining a preset price level division rule, determining a first offer weight according to a target consumption level of the foreign sales object and the product price level, and generating an initial product offer according to the first offer weight and the product price information;

2. The image-based export statement generation method of claim 1, wherein the using a deep learning algorithm to perform data relationship mining on the image data of the historical export object, obtaining the consumption image correlation factor of the historical export object, and constructing the evaluation model based on the consumption image correlation factor comprises:

3. The portrait-based marketing bill generation method of claim 1, wherein the obtaining product price information of the product to be sold and determining the product price level of the product to be sold in combination with a preset price level division rule comprises:

and obtaining the product price grade of the product to be sold according to the preset product price grade division rule.

4. The portrait-based sales draft generation method of claim 3, wherein the obtaining product price information of the product to be sold, performing a clustering operation on the product price information of the product to be sold through a K-means clustering algorithm to obtain a clustering result, and setting a preset price ranking rule according to the clustering result comprises:

and classifying the grade interval according to the average value price data range in the adjacent clusters to obtain a preset price grade classification rule.

5. The representation-based marketing bill generation method of claim 1, wherein said determining a first offer weight based on a target consumption level of the marketing object and the product price level, generating an initial product offer based on the first offer weight and the product price information, comprises:

calculating to obtain a second ratio of the product price grade score to the total score of each price grade according to the product price grade and the preset score of each price grade;

and calculating the sum of the first ratio and the second ratio to obtain the first quotation weight, and generating initial product quotation according to the first quotation weight and the product price information.

6. The representation-based up-sell order generation method of claim 1, wherein said entering the initial product quote and the trade representation data into a document generation model, outputting an up-sell order for the up-sell object, comprises:

and inputting the target input data into a bill generation model, and outputting an external sales bill aiming at the external sales object.

7. The portrait-based foreign sales slip generation method of claim 1, wherein after obtaining the target data input to the slip generation model and outputting the foreign sales slip for the foreign sales object according to the target basic data and a preset pre-estimated quotation model, the method further comprises:

and matching the foreign sales order with a preset sales statement to obtain a target sales statement, and sending the target sales statement to a corresponding client.

8. An image-based outsourcing invoice generating device, the quotation device comprising:

the initial product quotation module is used for acquiring product price information of a product to be sold, determining the product price grade of the product to be sold by combining a preset price grade division rule, determining a first quotation weight according to the target consumption grade of the export object and the product price grade, and generating an initial product quotation according to the first quotation weight and the product price information;

the trade portrait data acquisition module is used for acquiring trade portrait data of the foreign sales object, wherein the trade portrait data comprise tariff information of a region where the foreign sales object is located, currency tax rate information of the region where the foreign sales object is located and the local product to be sold, and position information of the region where the foreign sales object is located;

9. A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the computer readable instructions are the representation-based out-sales slip generation method of any of claims 1-7.

10. A computer readable storage medium storing computer instructions for causing a computer to perform the steps of the representation-based outsignature generation method of any of claims 1-7.