Waybill information processing method, device, equipment and medium

Abstract

The present application provides a waybill information processing method, device, computer equipment and storage medium. The method includes: obtaining the name of the item to be transported from the client, obtaining the historical usage frequency information corresponding to the name, querying the correspondence between the pre-configured name information and the reference value according to the historical usage frequency information, obtaining the reference value of the item to be transported, and sending it to the client, so that the user can enter the name of the item to be transported and obtain the corresponding reference value as a prompt, thereby improving the accuracy and standardization of the waybill amount entered by the user, and avoiding unnecessary customs clearance risks caused by the mismatch between the filled amount and the actual value.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a waybill information processing method, device, computer equipment and storage medium. Background Art

[0002] With the development of e-commerce, cross-border transactions have achieved rapid development. When importing or exporting goods or transferring goods in and out of a country's customs territory, corresponding customs clearance procedures must be performed in accordance with various regulations. Customs clearance is an important part of international express transportation services. When sending parcels, users need to fill out the waybill and enter the relevant information of the transported items as the basis for customs clearance review.

[0003] With current technology, users usually freely fill in information such as the price of the items being transported. This can easily lead to unnecessary delays and affect customs clearance efficiency due to a large deviation between the filled amount and the actual value. Summary of the invention

[0004] Based on this, it is necessary to provide a waybill information processing method, device, computer equipment and storage medium to address the technical problem that the non-standard filling of waybill prices in the current technology affects the customs clearance efficiency.

[0005] A method for processing waybill information, the method comprising:

[0006] Get the name of the item to be transported from the client;

[0007] Obtaining historical usage frequency information corresponding to the name; the historical usage frequency information represents the frequency of the corresponding name appearing in historical transportation information;

[0008] According to the historical usage frequency information, query the correspondence between the pre-configured name information and the reference value to obtain the reference value of the item to be transported;

[0009] Send the reference value to the client

[0010] In one embodiment, before querying the correspondence between the pre-configured name information and the reference value according to the historical usage frequency information, the method further includes:

[0011] Get the name information and corresponding amount information of historical transport items;

[0012] If the frequency of occurrence of the name information is greater than or equal to a preset frequency threshold, each amount information corresponding to the name information is obtained as a reference value corresponding to the name information, and a corresponding relationship between the name information and the reference value is established.

[0013] In one embodiment, the method further comprises:

[0014] Acquire at least one name information whose appearance frequency is less than the preset frequency threshold;

[0015] Performing word segmentation processing on the at least one name information to obtain each word contained in the at least one name information, and determining the occurrence frequency of each word;

[0016] Get the amount information corresponding to the name information containing each word;

[0017] According to the occurrence frequency and amount information of each word contained in each name information in the at least one name information, the reference value corresponding to each name information is obtained.

[0018] In one embodiment, the method further comprises:

[0019] The name is input into a pre-trained naive Bayes model to obtain a predicted customs detention rate corresponding to the name; the naive Bayes model is trained based on the name information of historical transported items and the corresponding actual customs detention results, and is used to obtain the customs detention rate corresponding to the name information;

[0020] According to the predicted closure delay rate, corresponding name modification prompt information is sent to the client.

[0021] In one embodiment, the method comprises:

[0022] Obtain the name information of historical transport items and the corresponding actual customs detention results to build a training sample set;

[0023] The name information of the historical transported items is input into the naive Bayesian model to be trained, and the trained naive Bayesian model is verified in combination with the actual hysteresis result to obtain the trained naive Bayesian model.

[0024] In one embodiment, the step of obtaining the name information of historical transported items and the corresponding actual customs detention results to construct a training sample set includes:

[0025] Obtaining target common words and evaluation customs detention results corresponding to the target common words; the target common words represent words that are not included in the name information of the historical transported items but have customs detention risks;

[0026] Constructing a training sample set according to the name information of the historical transported items and the corresponding actual customs detention results, as well as the target common words and the corresponding evaluation customs detention results;

[0027] The method further comprises:

[0028] The name information of the historical transported items and the target common vocabulary are input into the naive Bayesian model to be trained, and the trained naive Bayesian model is verified in combination with the actual customs clearance results and the evaluation customs clearance results to obtain the trained naive Bayesian model.

[0029] In one embodiment, the step of obtaining the name information of historical transported items and the corresponding actual customs detention results to construct a training sample set includes:

[0030] Get the weight information corresponding to the historical transport items;

[0031] Constructing a training sample set according to the name information, weight information and corresponding actual customs detention results of the historical transported items;

[0032] The method further comprises:

[0033] The name information and weight information of the historical transported items are input into the naive Bayesian model to be trained, and the trained naive Bayesian model is verified in combination with the actual hysteresis results to obtain the trained naive Bayesian model.

[0034] A waybill information processing device, the device comprising:

[0035] The name acquisition module is used to obtain the name of the item to be transported from the client;

[0036] A historical frequency acquisition module, used to acquire historical usage frequency information corresponding to the name; the historical usage frequency information represents the frequency of the corresponding name appearing in historical transportation information;

[0037] A reference value acquisition module, used to query the correspondence between the pre-configured name information and the reference value according to the historical usage frequency information, and obtain the reference value of the item to be transported;

[0038] A sending module is used to send the reference value to the client.

[0039] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the waybill information processing method in any of the above embodiments when executing the computer program.

[0040] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the waybill information processing method in any of the above embodiments are implemented.

[0041] The above-mentioned waybill information processing method, device, computer equipment and storage medium obtain the name of the item to be transported from the client, obtain the historical usage frequency information corresponding to the name, and query the correspondence between the pre-configured name information and the reference value based on the historical usage frequency information to obtain the reference value of the item to be transported, and send it to the client, so that the user can enter the name of the item to be transported and get the corresponding reference value as a prompt, thereby improving the accuracy and standardization of the waybill amount entered by the user, and avoiding unnecessary customs detention risks caused by the mismatch between the filled-in amount and the actual value. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 1 is a flow chart of a method for processing waybill information in one embodiment;

[0043] Figure 2 It is a flowchart of a method for processing waybill information in another embodiment;

[0044] Figure 3 is a structural block diagram of a waybill information processing device in one embodiment;

[0045] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] In one embodiment, Figure 1 As shown, a waybill information processing method is provided. This embodiment takes the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0048] Step S201, obtaining the name of the item to be transported from the client.

[0049] The name of the item to be transported can be the name or nickname of the item in words, which is used to identify and distinguish the item. In the field of item transportation, the name of the item on the waybill can be used as the basis for customs declaration and review. For example, names involving sensitive words may cause customs delays. In addition, the value of the item corresponding to the name usually has a regularity. According to the name, the corresponding value range of the item can be obtained to avoid customs delays caused by the inconsistency between the declared price of the item and the actual price.

[0050] Step S202, obtaining historical usage frequency information corresponding to the name.

[0051] The historical usage frequency information may represent the frequency of the corresponding name appearing in the historical transportation information. The historical transportation information may be the historical waybill information and the names of the historical transported items contained in the server, from which the frequency of the names of the items to be transported appearing in the historical transportation information may be extracted and saved, and the historical usage frequency information may be updated as new waybill information is added.

[0052] In a specific implementation, the server may obtain the historical usage frequency information corresponding to the name from the storage module according to the name.

[0053] Step S203, according to the historical frequency of use information, query the correspondence between the pre-configured name information and the reference value to obtain the reference value of the item to be transported.

[0054] Among them, the reference value can be the value calculated from the historical amounts corresponding to the name information, which is used to provide the user with an amount input prompt. The reference value can be a specific value or a range of values. For item names with high frequency of occurrence, the data sample is large, and the corresponding reference value range is more accurate. For names with low frequency of occurrence, the value data sample data volume is small, and the corresponding reference value range accuracy is also low. The server can use different algorithm models to configure the corresponding reference value for each name information according to the different historical usage frequency information, and establish a corresponding relationship between the name information and the reference value. Each name information can correspond to multiple reference values. The server can configure the reference value corresponding to the name information under different probabilities according to the probability distribution law of each historical amount corresponding to the name information, thereby improving the flexibility of the application of the corresponding relationship.

[0055] In a specific implementation, the server may query the correspondence between the name information and the reference value according to the historical usage frequency information corresponding to the name of the item to be transported, so as to obtain the reference value corresponding to the item.

[0056] Step S204: sending the reference value to the client.

[0057] In a specific implementation, the server may send the reference value to the corresponding client to prompt the user of the reference value corresponding to the item to be transported.

[0058] In the above-mentioned waybill information processing method, the name of the item to be transported is obtained from the client, and the historical usage frequency information corresponding to the name is obtained. According to the historical usage frequency information, the correspondence between the pre-configured name information and the reference value is queried to obtain the reference value of the item to be transported, and the reference value is sent to the client, so that the user can enter the name of the item to be transported and obtain the corresponding reference value as a prompt, thereby improving the accuracy and standardization of the waybill amount entered by the user, and avoiding unnecessary customs detention risks caused by the mismatch between the filled-in amount and the actual value.

[0059] In one embodiment, before determining in step S203 the step of querying the correspondence between the pre-configured name information and the reference value according to the historical usage frequency information, the method further includes:

[0060] Obtain the name information and corresponding amount information of historical transported items; if the frequency of occurrence of the name information is greater than or equal to the preset frequency threshold, obtain the amount information corresponding to the name information as the reference value corresponding to the name information, and establish a corresponding relationship between the name information and the reference value.

[0061] In this embodiment, the server can pre-configure the corresponding relationship between the name information and the reference value according to the name information and the amount information of the historical transported items. The frequency threshold can represent the critical value of the frequency of the name information appearing in the names of the historical transported items. The algorithm model used when configuring the reference value can be different for the name information greater than or equal to the frequency threshold and the name information less than the frequency threshold.

[0062] When the frequency of occurrence of the name information is greater than or equal to the preset frequency threshold, the frequency of occurrence of the name information is high and the sample number of the amount information is large. The server can obtain the probability distribution of the amount information corresponding to the name information based on the various amount information, and determine the amount information under different probability conditions based on the probability distribution as the reference value corresponding to the name information, and establish a corresponding relationship between the name information and the reference value.

[0063] In some embodiments, the information of historical transported items can be extracted from the corresponding invoice information, and can also include the invoice issuance date, order number, name information, quantity, and amount information of the transported items.

[0064] In one embodiment, the server can apply reference values ​​corresponding to different probabilities according to customs clearance requirements in different periods. For example, the server can obtain the 25%, 50%, 75%, and 90% quantiles of the amount information corresponding to the name information, and establish reference values ​​corresponding to the name information and each quantile. The server or the client can set a reference value corresponding to the 90% quantile for the name information within a certain time period, and when the user enters the name, the reference value corresponding to the 90% quantile is returned.

[0065] In the scheme of the above embodiment, the server can configure corresponding reference values ​​for names whose frequency of appearance is greater than or equal to a preset frequency threshold based on the probability distribution of the name information of historical transported items and the corresponding amount information, thereby improving the efficiency of obtaining reference values ​​based on the names.

[0066] In one embodiment, before determining in step S203 the step of querying the correspondence between the pre-configured name information and the reference value according to the historical usage frequency information, the method further includes:

[0067] Acquire at least one name information whose appearance frequency is less than a preset frequency threshold; perform word segmentation on the at least one name information to obtain each word contained in the at least one name information, and determine the appearance frequency of each word; acquire the amount information corresponding to the name information containing each word; and obtain the reference value corresponding to each name information according to the appearance frequency and amount information of each word contained in each name information in the at least one name information.

[0068] In this embodiment, the server can configure a corresponding reference value for name information whose frequency of occurrence is less than a preset frequency threshold. If the frequency of occurrence of the name information is less than the preset frequency threshold, the sample data of the corresponding amount information will also be less. At this time, the reference value is determined by the probability distribution of the amount information corresponding to the name information, which is inaccurate due to the small sample data. The server can perform word segmentation processing on the name information, obtain the frequency of occurrence of each word constituting the name information, and the amount information corresponding to each name information containing the word, and obtain the corresponding relationship between the word and the amount information. The server can perform weighted processing on the frequency of occurrence of each word in the name information and the corresponding amount information to obtain the reference value corresponding to the name information.

[0069] Among them, for the frequency of occurrence of each word, the server can take at least one name information whose frequency of occurrence is less than a preset frequency threshold as a combination, and calculate it with each word contained in the combination as the base. The server can perform word segmentation processing on each name information, and count the frequency of occurrence of each word in the above combination. For the correspondence between words and amount information, the service can obtain the amount information corresponding to the name information containing the word in the combination after processing. The server can add up at least one amount information corresponding to each word to obtain the correspondence between the word and the amount information. It is also possible to determine one of the amount information according to the probability distribution of at least one amount information corresponding to each word to obtain the correspondence between the word and the amount information.

[0070] For example, for the name information "cotton shirt", after word segmentation processing, it can be obtained through statistics that, among the words contained in all the name information whose appearance frequency is lower than the preset frequency threshold, the word cotton has an appearance frequency of 2%, and the name information containing the word cotton has appeared twice, and the corresponding amount information is US$10 and US$100 respectively. The amount information corresponding to the word cotton is; according to the same statistical method, the appearance frequency of shirt is 1%, it has appeared once, and the corresponding amount information is US$80, among which cotton and shirt are the same. Therefore, it can be obtained that the reference value corresponding to the name information "cotton shirt" can be 2%*(10+100)+1%*80=3.

[0071] In some embodiments, the server may process the name information of historical transport items through a bag-of-words model. The bag-of-words model may be a commonly used document representation method in the field of information retrieval. It is assumed that for a document, its word order, grammar, syntax and other elements are ignored, and it is only regarded as a collection of several words. The appearance of each word in the document is independent and does not depend on whether other words appear. Through the bag-of-words model, the server can obtain the frequency of occurrence of each word in the name information of historical items. The server can also pre-process the name information, set stop words such as articles and conjunctions, and reduce noise.

[0072] In the scheme of the above embodiment, the server can configure corresponding reference values ​​for names whose frequency of appearance is less than a preset frequency threshold based on the name information and corresponding amount information of the historically transported items, thereby improving the efficiency of obtaining reference values ​​based on the names.

[0073] In one embodiment, the method further includes:

[0074] The name is input into a pre-trained naive Bayes model to obtain the predicted closure rate corresponding to the name; according to the predicted closure rate, the corresponding name modification prompt information is sent to the client.

[0075] In this embodiment, the server can obtain the predicted customs delay rate corresponding to the name input by the user through a pre-trained model. The naive Bayes model can be trained based on the name information of historical transport items and the corresponding actual customs delay results, and is used to obtain the customs delay rate corresponding to the name information. Among them, the naive Bayes model can be based on the Bayesian theorem, assuming that the feature conditions are independent of each other, first through a given training set, with the independence of feature words as the premise assumption, learn the joint probability distribution from input to output, and then based on the learned model, input X to obtain the output Y that maximizes the posterior probability.

[0076] The customs detention rate can represent the frequency of the items to be transported being detained at the customs. This frequency has a certain correspondence with the name, amount and weight information of the transported items contained in the waybill. Analyzing this correspondence can provide guidance and suggestions for filling out the waybill. The actual customs detention result can be a record of historical customs detention of transported items. The server can pre-store this record for model training. The name modification prompt information can include risk reminders, modification suggestions, prohibited goods prompts, etc. The server can set the correspondence between the customs detention rate and the name modification prompt information, and send the corresponding name modification prompt information to the client based on the predicted customs detention rate.

[0077] In one embodiment, the server may perform word segmentation on the obtained name of the item to be transported to obtain each word contained therein, and put the segmented name into the naive Bayes model to obtain the corresponding predicted customs clearance rate.

[0078] In some embodiments, the server may also obtain pre-filled information of the waybill from the client, and obtain the reference value corresponding to the name information and the name modification prompt information after processing based on the pre-filled name and amount information of the items to be transported.

[0079] The solution of the above embodiment obtains the predicted customs clearance rate corresponding to the name through the pre-trained naive Bayes model, prompts the user to modify the input name, improves the timeliness of the response to the name of the item to be transported, and further improves the accuracy of the name input.

[0080] In one embodiment, the method further includes:

[0081] The name information of historical transported items and the corresponding actual customs detention results are obtained to construct a training sample set; the name information of historical transported items is input into the naive Bayesian model to be trained, and the trained naive Bayesian model is verified in combination with the actual customs detention results to obtain the trained naive Bayesian model.

[0082] In this embodiment, the server can train the naive Bayes model based on the name information of historical transported items and the corresponding actual customs delay results, wherein the name information of historical transported items can be used as a sample set and the actual customs delay results can be used as a verification set. The server can store the waybill information of historical transported items, and as the waybill information increases, new samples are continuously added for incremental training to improve the accuracy of the predicted customs delay results.

[0083] In one embodiment, the step of obtaining the name information of historical transported items and the corresponding actual customs detention results, and constructing a training sample set further includes:

[0084] Obtain target common words and evaluation lag results corresponding to the target common words; construct a training sample set according to the name information of the historical transported items and the corresponding actual lag results, as well as the target common words and the corresponding evaluation lag results; input the name information of the historical transported items and the target common words into the naive Bayesian model to be trained for training, and verify the trained naive Bayesian model in combination with the actual lag results and the evaluation lag results to obtain the trained naive Bayesian model.

[0085] In this embodiment, the server can expand the source of samples used for training. The target common vocabulary can represent vocabulary that is not included in the name information of the historical transported items but has a risk of being delayed. The result of evaluating the delayed customs clearance can be to obtain the delayed customs clearance rate based on experience or relevant model detection, so that vocabulary that has not appeared in the waybill information is added to the model to avoid the cold start problem faced by new words, further optimize the model parameters, and improve the efficiency and reliability of obtaining the delayed customs clearance rate corresponding to the name.

[0086] In one embodiment, the steps of obtaining the name information of historical transported items and the corresponding actual customs detention results and constructing a training sample set include:

[0087] Obtain the weight information corresponding to the historical transported items; construct a training sample set according to the name information, weight information and corresponding actual customs clearance results of the historical transported items; input the name information and weight information of the historical transported items into the naive Bayesian model to be trained, and verify the trained naive Bayesian model in combination with the actual customs clearance results to obtain the trained naive Bayesian model.

[0088] In this embodiment, weight information is also related to tariffs and customs clearance standards, and will affect the customs detention rate. The server can use the weight information of historical transported items as an additional feature, use the name information and weight information of historical transported items as a training set to train the model, and verify the model with actual customs detention results to obtain a trained naive Bayes model, thereby further improving the accuracy of obtaining predicted customs detention results.

[0089] In one embodiment, when training the naive Bayes model, the server can clean the acquired sample set, process the articles, conjunctions, symbols, singular and plural, and upper and lower case numbers contained in the data, segment the sample set, and then vectorize it and store it as a sparse matrix without repeated words, where 1 indicates that the relevant word appears in the corpus, and 0 indicates that it does not appear, and the actual lag result is used as the label. The labeled samples are trained to obtain the prior probability, and the posterior probability is calculated after the historical transportation items in the test set are segmented.

[0090] In one embodiment, the server can input independent words that have appeared or not appeared into the model. If the independent words have a high rate of closure, the words can be used as sensitive words. When the user enters a name containing the words, a corresponding name modification prompt message is issued. For example, sensitive words such as hazardous chemicals, chemical materials, and contraband can be input into the naive Bayes model to obtain the corresponding closure rate.

[0091] In one embodiment, Figure 2 As shown, a waybill information processing method is provided, the method comprising:

[0092] Step S201, obtaining the name information, corresponding amount information, weight information and corresponding actual customs detention results of historical transport items.

[0093] Step S202: If the frequency of occurrence of the name information is greater than or equal to a preset frequency threshold, obtain the amount information corresponding to the name information as a reference value corresponding to the name information, and establish a corresponding relationship between the name information and the reference value; if the frequency of occurrence of the name information is less than the preset frequency threshold, obtain at least one name information whose frequency of occurrence is less than the preset frequency threshold; perform word segmentation on at least one name information to obtain each word contained in the at least one name information, and determine the frequency of occurrence of each word; obtain the amount information corresponding to the name information containing each word; and obtain the reference value corresponding to each name information based on the frequency of occurrence and amount information of each word contained in each name information in at least one name information.

[0094] Step S203, based on the name information, weight information and corresponding actual customs detention results of the historical transported items; input the name information and weight information of the historical transported items into the naive Bayesian model to be trained, and verify the trained naive Bayesian model in combination with the actual customs detention results to obtain the trained naive Bayesian model.

[0095] Step S204, obtaining the name of the item to be transported from the client, querying the correspondence between the pre-configured name information and the reference value according to the historical usage frequency information corresponding to the name, and obtaining the reference value of the item to be transported; inputting the name into the naive Bayes model to obtain the predicted customs clearance rate corresponding to the name.

[0096] Step S205: sending name modification prompt information corresponding to the reference value and the predicted closure delay rate to the client.

[0097] In the above embodiment, the corresponding relationship between the name information and the reference value is obtained through the name information, weight information and actual customs detention results of the historical transported items, and a naive Bayesian model for predicting the customs detention rate is trained. According to the name input by the client, the reference value and the predicted customs detention rate corresponding to the name can be obtained, and information prompts are provided for the user to fill in the waybill, thereby improving the accuracy and standardization of the waybill amount entered by the user, avoiding unnecessary customs detention risks caused by non-standard and inaccurate filling of the name and amount information, and further improving the customs clearance efficiency.

[0098] It should be understood that although Figure 2-3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-3 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0099] In one embodiment, Figure 3 As shown, a waybill information processing device is provided, and the device 300 includes:

[0100] The name acquisition module 301 is used to acquire the name of the item to be transported from the client;

[0101] The historical frequency acquisition module 302 is used to acquire the historical usage frequency information corresponding to the name; the historical usage frequency information represents the frequency of the corresponding name appearing in the historical transportation information;

[0102] The reference value acquisition module 303 is used to query the correspondence between the pre-configured name information and the reference value according to the historical usage frequency information, and obtain the reference value of the item to be transported;

[0103] The sending module 304 is used to send the reference value to the client.

[0104] In one embodiment, the reference value acquisition module 303 includes: a first value unit, used to obtain the name information and corresponding amount information of historical transport items; if the frequency of occurrence of the name information is greater than or equal to a preset frequency threshold, obtain the amount information corresponding to the name information as the reference value corresponding to the name information, and establish a corresponding relationship between the name information and the reference value.

[0105] In one embodiment, the reference value acquisition module 303 includes: a second value unit, which acquires at least one name information whose frequency of occurrence is less than a preset frequency threshold; performs word segmentation processing on the at least one name information to obtain each word contained in the at least one name information, and determines the frequency of occurrence of each word; acquires the amount information corresponding to the name information containing each word; and acquires the reference value corresponding to each name information based on the frequency of occurrence and amount information of each word contained in each name information in the at least one name information.

[0106] In one embodiment, the above-mentioned device 300 also includes: a name modification prompt module, which is used to input the name into a pre-trained naive Bayes model to obtain a predicted customs detention rate corresponding to the name; the naive Bayes model is trained based on the name information of historical transport items and the corresponding actual customs detention results, and is used to obtain the customs detention rate corresponding to the name information; according to the predicted customs detention rate, the corresponding name modification prompt information is sent to the client.

[0107] In one embodiment, the name modification prompt module includes: a first model training unit, which is used to obtain the name information of historical transport items and the corresponding actual customs detention results to construct a training sample set; the name information of historical transport items is input into the naive Bayesian model to be trained for training, and the trained naive Bayesian model is verified in combination with the actual customs detention results to obtain the trained naive Bayesian model.

[0108] In one embodiment, the name modification prompt module also includes: a second model training unit, further used to obtain target common vocabulary and evaluation detention results corresponding to the target common vocabulary; the target common vocabulary represents vocabulary that is not included in the name information of historical transport items but has a risk of detention; and a training sample set is constructed based on the name information of historical transport items and the corresponding actual detention results, as well as the target common vocabulary and the corresponding evaluation detention results.

[0109] In one embodiment, the name modification prompt module also includes: a third model training unit, used to obtain the weight information corresponding to the historical transported items; construct a training sample set according to the name information, weight information and corresponding actual customs clearance results of the historical transported items; input the name information and weight information of the historical transported items into the naive Bayesian model to be trained for training, and verify the trained naive Bayesian model in combination with the actual customs clearance results to obtain the trained naive Bayesian model.

[0110] For the specific definition of the waybill information processing device, please refer to the definition of the waybill information processing method above, which will not be repeated here. Each module in the above-mentioned waybill information processing device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0111] The waybill information processing method provided in the present application can be applied to a computer device, which can be a server, and its internal structure diagram can be as shown in Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store waybill information data, model data, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a waybill information processing method is implemented.

[0112] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0113] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0114] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0115] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0116] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0117] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A waybill information processing method, It is characterized in that The method comprises: Get the name of the item to be transported from the client; Obtaining historical usage frequency information corresponding to the name; the historical usage frequency information represents the frequency of the corresponding name appearing in historical transportation information; Get the name information and corresponding amount information of historical transport items; If the frequency of occurrence of the name information is greater than or equal to a preset frequency threshold, obtaining each amount information corresponding to the name information as a reference value corresponding to the name information, and establishing a corresponding relationship between the name information and the reference value; According to the historical usage frequency information, query the correspondence between the pre-configured name information and the reference value to obtain the reference value of the item to be transported; The reference value is sent to the client.

2. The method according to claim 1, It is characterized in that Before the corresponding relationship between the pre-configured name information and the reference value is queried based on the historical usage frequency information to obtain the reference value of the item to be transported, the method further includes: Acquire at least one name information whose appearance frequency is less than the preset frequency threshold; Performing word segmentation processing on the at least one name information to obtain each word contained in the at least one name information, and determining the occurrence frequency of each word; Get the amount information corresponding to the name information containing each word; According to the occurrence frequency and amount information of each word contained in each name information in the at least one name information, the reference value corresponding to each name information is obtained.

3. The method according to claim 1, It is characterized in that The method further comprises: The name is input into a pre-trained naive Bayes model to obtain a predicted customs detention rate corresponding to the name; the naive Bayes model is trained based on the name information of historical transported items and the corresponding actual customs detention results, and is used to obtain the customs detention rate corresponding to the name information; According to the predicted closure delay rate, corresponding name modification prompt information is sent to the client.

4. The method according to claim 3, It is characterized in that The method comprises: Obtain the name information of historical transport items and the corresponding actual customs detention results to build a training sample set; The name information of the historical transported items is input into the naive Bayesian model to be trained, and the trained naive Bayesian model is verified in combination with the actual hysteresis result to obtain the trained naive Bayesian model.

5. The method according to claim 4, It is characterized in that The step of obtaining the name information of historical transported items and the corresponding actual customs detention results to construct a training sample set includes: Obtaining target common words and evaluation customs detention results corresponding to the target common words; the target common words represent words that are not included in the name information of the historical transported items but have customs detention risks; Constructing a training sample set according to the name information of the historical transported items and the corresponding actual customs detention results, as well as the target common words and the corresponding evaluation customs detention results; The method further comprises: The name information of the historical transported items and the target common vocabulary are input into the naive Bayesian model to be trained, and the trained naive Bayesian model is verified in combination with the actual customs clearance results and the evaluation customs clearance results to obtain the trained naive Bayesian model.

6. The method according to claim 4, It is characterized in that The step of obtaining the name information of historical transported items and the corresponding actual customs detention results to construct a training sample set includes: Get the weight information corresponding to the historical transport items; Constructing a training sample set according to the name information, weight information and corresponding actual customs detention results of the historical transported items; The method further comprises: The name information and weight information of the historical transported items are input into the naive Bayesian model to be trained, and the trained naive Bayesian model is verified in combination with the actual hysteresis results to obtain the trained naive Bayesian model.

7. A waybill information processing device, It is characterized in that The device comprises: A name acquisition module is used to obtain the name of the item to be transported from the client; A historical frequency acquisition module, used to acquire historical usage frequency information corresponding to the name; the historical usage frequency information represents the frequency of the corresponding name appearing in historical transportation information; A reference value acquisition module is used to acquire the name information and corresponding amount information of historical transported items; if the frequency of occurrence of the name information is greater than or equal to a preset frequency threshold, the amount information corresponding to the name information is acquired as the reference value corresponding to the name information, and a corresponding relationship between the name information and the reference value is established; according to the historical usage frequency information, the pre-configured corresponding relationship between the name information and the reference value is queried to obtain the reference value of the item to be transported; A sending module is used to send the reference value to the client.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images