Information detection method and device in logistics scene, storage medium and electronic equipment

Abstract

The invention discloses an information detection method and device in a logistics scene, a storage medium and electronic equipment. The method comprises the following steps: acquiring to-be-detected information, and performing multi-dimensional analysis on the to-be-detected information to obtain multi-dimensional features corresponding to the to-be-detected information; performing prediction processing on the multi-dimensional features corresponding to the to-be-detected information based on a pre-trained error delivery prediction model to obtain first detection data of the to-be-detected information; and / or performing prediction processing on the multi-dimensional features corresponding to the to-be-detected information based on a pre-trained outbound prediction model to obtain second detection data of the to-be-detected information; and determining a target quality detection result of the to-be-detected information based on the first detection data and / or the second detection data. The to-be-detected information is automatically detected, the intelligence and detection efficiency of information detection are improved, the manual detection process is replaced, and manpower consumption and time consumption in the information detection process are saved.

Description

Technical Field

[0001] The present invention relates to the field of smart logistics technology, and in particular to an information detection method, device, storage medium and electronic device in a logistics scenario. Background Art

[0002] In the logistics industry, collection and delivery information is extremely important information. Correct collection and delivery information can not only improve the accuracy of delivery and sales, but also provide customers with better services. Incorrect collection and delivery information may cause returns, delays or losses in the delivery process, seriously affecting the sales and success rate of delivery.

[0003] In the process of implementing the present invention, it was found that there are at least the following technical problems in the prior art: currently, the collection and delivery information is generally manually checked by employees of the postal or express delivery companies. During peak logistics periods or when handling a large number of delivery businesses, delays caused by untimely processing, or omissions in the check may lead to unsuccessful delivery. Summary of the invention

[0004] The present invention provides an information detection method, device, storage medium and electronic device in a logistics scenario, so as to realize quality detection of information to be detected in the logistics scenario and avoid interference of low-quality information on the logistics process.

[0005] According to one aspect of the present invention, a method for detecting information in a logistics scenario is provided, comprising:

[0006] Acquire information to be detected, perform multi-dimensional analysis on the information to be detected, and obtain multi-dimensional features corresponding to the information to be detected;

[0007] Based on a pre-trained error delivery prediction model, the multi-dimensional features corresponding to the information to be detected are predicted and processed to obtain first detection data of the information to be detected; and / or based on a pre-trained outbound call prediction model, the multi-dimensional features corresponding to the information to be detected are predicted and processed to obtain second detection data of the information to be detected;

[0008] Based on the first detection data and / or the second detection data, a target quality detection result of the information to be detected is determined.

[0009] Optionally, the information to be detected includes address information and logistics object information;

[0010] The multi-dimensional analysis includes one or more of feature analysis of the address form dimension, feature analysis of the administrative district dimension, feature analysis of the road dimension and feature analysis of the entity dimension of the address information, as well as feature analysis of the logistics object information.

[0011] Optionally, performing multi-dimensional analysis on the information to be detected to obtain multi-dimensional features corresponding to the information to be detected includes:

[0012] Based on at least one analysis item corresponding to each dimension, the information to be detected is analyzed to obtain feature data corresponding to at least one analysis item corresponding to each dimension;

[0013] The multi-dimensional feature is formed based on feature data corresponding to at least one analysis item corresponding to each of the multiple dimensions.

[0014] Optionally, before analyzing the information to be detected, one or more of the following is also included:

[0015] Preprocessing the information to be detected, wherein the preprocessing includes one or more of removing irrelevant characters and normalizing characters; identifying at least one level of address component information in the address information.

[0016] Optionally, the first detection data represents a degree of delivery deviation corresponding to the information to be detected, and the second detection data represents a degree of address error when an outbound call event occurs corresponding to the information to be detected;

[0017] Determining the target quality detection result of the information to be detected based on the first detection data and / or the second detection data includes: determining a first quality detection result based on the first detection data, the first quality detection result is negatively correlated with the first detection data; and / or determining a second quality detection result based on the second detection data, the second quality detection result is negatively correlated with the second detection data; determining the target quality detection result of the information to be detected based on the first quality detection result and / or the second quality detection result.

[0018] Optionally, the training method of the wrong delivery prediction model includes: obtaining sample information and historical delivery process information corresponding to the sample information, the historical delivery process information including delivery site information and delivery road area information; generating a first label corresponding to the sample information based on the delivery site information and the delivery road area information; training the wrong delivery prediction model to be trained based on multiple sample information and the first label corresponding to each sample information, until a trained wrong delivery prediction model is obtained.

[0019] Optionally, the generating of the first label corresponding to the sample information based on the delivery site information and the delivery road area information includes: determining estimated site information based on address information in the sample information, determining site determination information based on the estimated site information and the delivery site information; determining road area determination information based on the delivery road area information and the estimated road area information corresponding to the address information; generating the first label based on the site determination information and the road area determination information.

[0020] Optionally, the training method of the outbound call prediction model includes: obtaining sample information and historical delivery process information corresponding to the sample information, the historical delivery process information including delivery route information and outbound call event information; generating a second label corresponding to the sample information according to the delivery route information and the outbound call event information; and training the outbound call prediction model to be trained based on multiple sample information and the second label corresponding to each sample information, until a trained outbound call prediction model is obtained.

[0021] Optionally, generating the second label corresponding to the sample information based on the delivery route area information and the outbound call event information includes: determining the distance information between at least one level of address component information corresponding to the address information in the sample information and the delivery route area information; and determining the second label based on the outbound call event information and the distance information.

[0022] According to another aspect of the present invention, there is provided an information detection device in a logistics scenario, comprising:

[0023] A feature extraction module is used to obtain information to be detected, perform multi-dimensional analysis on the information to be detected, and obtain multi-dimensional features corresponding to the information to be detected;

[0024] A detection module, configured to predict and process the multi-dimensional features corresponding to the information to be detected based on a pre-trained error delivery prediction model to obtain first detection data of the information to be detected; and / or to predict and process the multi-dimensional features corresponding to the information to be detected based on a pre-trained outbound call prediction model to obtain second detection data of the information to be detected;

[0025] The target quality detection result determination module is used to determine the target quality detection result of the information to be detected based on the first detection data and / or the second detection data.

[0026] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0027] at least one processor; and

[0028] a memory communicatively connected to the at least one processor; wherein,

[0029] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the information detection method in the logistics scenario described in any embodiment of the present invention.

[0030] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the information detection method in a logistics scenario described in any embodiment of the present invention when executed.

[0031] The technical solution of the embodiment of the present invention, when obtaining information to be detected in a logistics scenario, performs quality detection on the information to be detected based on an erroneous delivery prediction model and / or an outbound call prediction model to obtain a target quality detection result of the information to be detected. After the user inputs the information to be detected, the information to be detected can be automatically detected, thereby improving the intelligence and detection efficiency of information detection, replacing the manual detection process, and saving manpower and time consumption in the information detection process. Through the quality detection of the information to be detected, the user can be prompted to modify the erroneous information, improve the accuracy of the information, further improve the success rate of delivery in the logistics scenario, and avoid the interference of erroneous information to the delivery process and the ineffective consumption of logistics resources.

[0032] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 is a flow chart of an information detection method in a logistics scenario provided by an embodiment of the present invention;

[0035] Figure 2 It is a structural schematic diagram of an information detection device in a logistics scenario provided by an embodiment of the present invention;

[0036] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] Figure 1 This is a flow chart of an information detection method in a logistics scenario provided by an embodiment of the present invention. This embodiment can be applied to the situation where when a customer writes in the receiving and sending information, the receiving and sending information is used as the information to be detected for quality detection, and the target quality detection result of the information to be detected is obtained, and a modification prompt is given when the target quality detection result of the information to be detected is abnormal. This method can be executed by an information detection device in a logistics scenario. The information detection device in a logistics scenario can be implemented in the form of hardware and / or software. The information detection device in a logistics scenario can be configured in a mobile terminal such as a mobile phone or tablet computer, a computer or a server. Figure 1 As shown, the method includes:

[0040] S110, obtaining information to be detected, performing multi-dimensional analysis on the information to be detected, and obtaining multi-dimensional features corresponding to the information to be detected.

[0041] S120. Based on a pre-trained error delivery prediction model, predict the multi-dimensional features corresponding to the information to be detected to obtain first detection data of the information to be detected; and / or, based on a pre-trained outbound call prediction model, predict the multi-dimensional features corresponding to the information to be detected to obtain second detection data of the information to be detected.

[0042] S130: Determine a target quality detection result of the information to be detected based on the first detection data and / or the second detection data.

[0043] In this embodiment, an information collection page is displayed, and the information collection page is used to collect receiving and sending information, wherein the receiving and sending information may include recipient information and sender information, and one or more of the recipient information and sender information are used as the information to be detected. Among them, the information to be detected includes address information and logistics object information; taking the recipient information as an example, the recipient information includes the recipient address information and the recipient object information, and taking the sender information as an example, the sender information includes the mailing address information and the mailing object information. Among them, the logistics object is the person or organization that receives and / or sends the goods, etc., and the logistics object information may be the contact information of the logistics object, and the logistics object information includes the recipient object information and / or the mailing object information.

[0044] When it is detected that the user inputs information on the information collection page, the information to be detected is determined, and the quality of the information to be detected is detected to obtain the target quality detection result of the information to be detected. When the target quality detection result is normal, a logistics business is generated based on the information to be detected, and the business information corresponding to the logistics business is sent to the logistics server so that the logistics personnel can respond to the logistics business. When the target quality detection result is abnormal, a prompt message is generated, which is used to prompt the user that the information input is abnormal, and prompt the user to modify the input information, and re-detect the modified information as the information to be detected again, until the target quality detection result of the new information to be detected is normal.

[0045] In this embodiment, multi-dimensional features are obtained by performing multi-dimensional analysis on the information to be detected, thereby improving the comprehensiveness of the analysis of the information to be detected. Quality detection is performed on the information to be detected through the multi-dimensional features of the information to be detected, providing multi-dimensional features as a basis for the quality detection process, thereby improving the accuracy of quality detection.

[0046] Optionally, before analyzing the information to be detected, the information to be detected is preprocessed, and the preprocessing includes one or more of removing irrelevant characters and character normalization processing. Wherein, irrelevant characters may include but are not limited to spaces, punctuation marks and special characters. Exemplarily, an irrelevant character set is pre-set, the information to be detected is matched in the irrelevant character set, the characters that are successfully matched are determined as irrelevant characters, and the above irrelevant characters are removed from the information to be detected, wherein the characters in the irrelevant character set are pre-set according to the preprocessing requirements of the information to be detected. Character normalization processing includes but is not limited to the conversion between traditional and simplified characters, the conversion between full-width and half-width, etc. By preprocessing the information to be detected, the interference information in the information to be detected is removed, and the accuracy of quality detection of the information to be detected is improved.

[0047] The information to be detected includes address information and logistics object information. Accordingly, the multi-dimensional analysis of the information to be detected includes analysis of the address information and / or analysis of the logistics object information. Wherein, before analyzing the address information, it also includes identifying at least one level of address component information in the address information. Accordingly, at least one level of address component information in the address information is analyzed. Wherein the address component information includes but is not limited to: province / autonomous region information, city information, district and county information, township street / descriptive area information, village community information, group / team information, AOI / district / period information, main road / road segmentation information, directional words, house numbers, POI / building / unit / door information, floor / room number information, etc. By identifying the address component information in the information to be detected, the analysis process of the address information is facilitated.

[0048] Optionally, at least one level of address component information in the address information is identified by a preset address entity recognition model, that is, the preprocessed address information is processed by the address entity recognition model, and at least one level of address component information corresponding to the address information is output. The address entity recognition model may be a neural network model, such as a BERT model.

[0049] The training process of the address entity recognition model may be: obtaining an initial sample set, the initial sample set including multiple sample address information, obtaining address component information in the sample address information by marking the sample address information, and using the address component information in the sample address information as a label corresponding to the sample address information.

[0050] In order to reduce the amount of manually labeled samples and improve sample data, data enhancement is performed on the basis of the initial sample set to obtain extended sample address information. The extended sample address information and the sample address information in the initial sample set form a target sample set, and the address entity recognition model is trained based on the target sample set.

[0051] Optionally, the data enhancement process may be: different entity sets are formed respectively through the address component information in the sample address information, for example, the entity set may include an administrative district data set, a road data set, and a community data set, etc. The entity words of the sample address information are replaced by the address component information in the above one or more entity sets to obtain the expanded sample address information.

[0052] Optionally, the data enhancement process may also include: forming Chinese or Arabic numeral type digital entities for digital type entities in the sample address information or extended sample address information, and / or replacing digital type entities in the sample address information or extended sample address information with other digital content.

[0053] The above data enhancement process may also include adding spelling errors to the sample address information or the extended sample address information to simulate input errors in the information input process and improve the robustness of the address entity recognition model, wherein the spelling errors may be replaced by typos in one or more address component information in the sample address information or the extended sample address information, for example, the correct words / terms in the sample address information or the extended sample address information may be replaced by typos of the same pronunciation or similar shape.

[0054] The address entity recognition model to be trained is iteratively trained based on the target sample set, and a trained address entity recognition model is obtained when the training end condition is met. Taking the address entity recognition model as the BERT model as an example, during the training process of the address entity recognition model, a CRF layer for sequence labeling is set after the output layer of the BERT model to utilize the dependency relationship between labels to assist the training process.

[0055] The address component information in the address information is identified by a trained address entity recognition model, and a multi-dimensional analysis is performed based on the address component information and / or logistics object information. For each dimension, the information to be detected is analyzed and processed separately to obtain the feature data of the dimension, and the feature data corresponding to multiple dimensions are spliced ​​to obtain multi-dimensional features. Optionally, an analysis rule for each dimension is pre-set, and the information to be detected is analyzed separately based on the analysis rule for each dimension to obtain the feature data of each dimension. Optionally, an analysis model for each dimension is pre-set, and the information to be detected is input into the analysis model of each dimension to obtain the feature data of each dimension. Optionally, a multi-dimensional analysis model is pre-set, and the multi-dimensional analysis model can be a multi-head model. By inputting the information to be detected into the multi-dimensional analysis model, the multi-dimensional features corresponding to the information to be detected are obtained.

[0056] Optionally, a multi-dimensional analysis is performed on the information to be detected to obtain a multi-dimensional feature corresponding to the information to be detected, including: based on at least one analysis item corresponding to each dimension, the information to be detected is analyzed to obtain feature data corresponding to at least one analysis item corresponding to each dimension; the multi-dimensional feature is formed based on the feature data corresponding to at least one analysis item corresponding to multiple dimensions. An analysis item may correspond to an analysis rule, and at least one analysis item corresponding to each dimension may be pre-set. When the information to be detected is detected, at least one analysis item corresponding to multiple dimensions is called to analyze the information to be detected. For example, at least one analysis item corresponding to multiple dimensions is called in sequence, and the information to be detected is analyzed in sequence. For example, at least one analysis item corresponding to multiple dimensions is called synchronously, and the information to be detected is analyzed in parallel, so as to speed up the quality detection efficiency of the information to be detected.

[0057] For any dimension, the information to be detected is analyzed based on at least one analysis item of the dimension to obtain the analysis result corresponding to each analysis item, and the analysis result corresponding to at least one analysis item can form the feature data corresponding to the dimension. For example, the analysis result corresponding to at least one analysis item can be formed into an array or vector in a preset order to obtain the feature data. Optionally, the feature data of each dimension can be in vector form, and the multi-dimensional feature can be in vector form or matrix form. The feature vectors of multiple dimensions are spliced ​​in a preset order to obtain multi-dimensional features.

[0058] Optionally, the multi-dimensional analysis includes feature analysis of the address form dimension of the address information, feature analysis of the administrative district dimension, feature analysis of the road dimension and feature analysis of the entity dimension, and / or one or more of the feature analysis of the logistics object information.

[0059] The feature analysis of the address form dimension of the address information can be understood as analyzing the address form of the address information. For example, the analysis items corresponding to the address form dimension of the address information are shown in Table 1. Among them, the address length can be the byte length in the address information. The address length corresponding to the address information is determined by identifying the number of bytes of the address information, that is, the analysis result corresponding to g1. The address component information corresponding to the core address element is preset. For example, the core address element can be district and county information and AOI / area / period information. The address component information of multiple levels corresponding to the address information is matched with the above core address elements respectively. A successful match indicates that the address information includes the above core address element, and the analysis result corresponding to g2 can be recorded as 1. A failed match indicates that the address information does not include the above core address element, and the analysis result corresponding to g2 can be recorded as 0. Each address component information corresponding to the address information is regarded as an address element, and the number of address elements in the address information can be determined. The byte length of each address element can be used as the length of the address element. If the address length is within a reasonable range, the analysis result corresponding to g5 can be recorded as 1. If the address length is not within a reasonable range, the analysis result corresponding to g5 can be recorded as 0. The analysis results corresponding to g1-g5 are respectively formed into vector form as feature data of the address form dimension of the address information.

[0060] Table 1

[0061] g1 Address length g2 Whether to include core address elements g3 Number of address elements g4 Address element length g5 Is the address length within a reasonable range (2 to 50 characters)?

[0062] The feature analysis of the administrative district dimension can be understood as analyzing the address component information corresponding to the administrative district in the address information, specifically, determining whether there is at least one error type in the address component information corresponding to the administrative district in the address information. The analysis item corresponding to the administrative district dimension can be the analysis rule corresponding to the error type of the address component information corresponding to the administrative district. Optionally, the feature analysis of the administrative district dimension may include but is not limited to one or more of missing analysis, conflict analysis, error analysis and redundancy analysis. Among them, missing analysis is used to determine whether there is one or more of missing provincial administrative divisions, missing municipal administrative divisions, missing district and county administrative divisions, and missing township administrative divisions in the address information. Conflict analysis is used to determine whether there is a cascading conflict or multiple administrative districts in the administrative district in the address information. For example, in the address information "Guangzhou City, Hubei Province", Guangzhou City does not belong to Hubei Province, and there is a cascading conflict; the address information "Beilin District, Xi'an City, Shaanxi Province, transferred to Wuhan City, Hubei Province" has multiple administrative districts. Specifically, by creating an address tree corresponding to each province, the root node of any address tree is a province, a municipality directly under the central government, or an autonomous region, the child node of the province is a city, the child node of the city is a district and county, and so on. Multiple administrative regions in the address information are matched in the above address tree. If a path to a provincial administrative region node can be matched in any address tree and the path is unique, it indicates that there is no administrative region conflict in the address information.

[0063] Error analysis is used to determine whether the address information includes administrative districts that have been merged or revoked, whether there are typos in the administrative districts in the address information, and whether the administrative districts in the address information exist. Pre-set the expired administrative district information, and match the administrative districts in the address information with the above-mentioned expired administrative district information. If it hits, it is determined that there is an administrative district error in the address information, that is, there is an error in the administrative district in the address information. If it does not hit, it is determined that there is no expired administrative district in the address information. Optional. The nodes in the preset created address tree are configured with expired administrative district information. In the process of matching the address information with the address tree, if the expired administrative district information is hit, it is determined that there is an administrative district error in the address information. Furthermore, if the administrative district in the address information cannot be successfully matched in the address tree, by replacing the administrative district in the address information with homophones or similar characters, it can be successfully matched in the address tree, then it is determined that there are typos in the administrative district of the address information, that is, there is an error in the administrative district in the address information. If the administrative district, homophones or similar characters of the administrative district in the address information cannot be successfully matched in the address tree, it is determined that the administrative district in the address information does not exist, that is, the administrative district in the address information is wrong.

[0064] Redundancy analysis is used to determine whether there are duplications in the administrative regions in the address information. If there are duplications in the administrative regions, it is determined that the address information has administrative region redundancy. For example, in the address information "Shaanxi Xi'an City, Shaanxi Province, Xi'an City, Beilin District", "Shaanxi Province" and "Xi'an City" are repeated. Specifically, the administrative regions in the address information can be matched in the address tree. If two or more administrative region information hit the same node of the address tree, it can be determined that the address information has administrative region redundancy.

[0065] Optionally, the analysis items corresponding to the administrative district dimension are shown in Table 2. By determining the analysis result corresponding to each analysis item, the analysis results corresponding to d1-d9 are respectively formed into feature data corresponding to the administrative district dimension.

[0066] Table 2

[0067] d1 There are missing provincial administrative divisions d2 There are missing city-level administrative divisions d3 There are missing district and county-level administrative divisions d4 There are missing township-level administrative divisions d5 There is a conflict in administrative regions d6 Administrative district invalid d7 Administrative district typos d8 Administrative district does not exist d9 Administrative district redundancy

[0068] The feature analysis of the road dimension can be understood as the analysis of the road information in the address information. The feature analysis of the road dimension may include but is not limited to road missing analysis, road number missing analysis, road quantity analysis and road information validity analysis. Road missing analysis is used to determine whether there is road information in the address information; road number missing analysis is used to determine whether the road information in the address information includes the road number. Road quantity analysis is used to determine the number of road information included in the address information, and road information validity analysis is used to determine whether the road information in the address information is in the preset road database, and whether the road information in the address information matches the administrative area in the address information.

[0069] Optionally, the analysis items corresponding to the road dimension are shown in Table 3. By determining the analysis result corresponding to each analysis item, the analysis results corresponding to r1-r5 are respectively formed into feature data corresponding to the road dimension.

[0070] Table 3

[0071] r1 Is there a road? r2 Does the road number exist? r3 Number of roads r4 Is the road name in the database? r5 Whether the road belongs to the administrative district

[0072] The feature analysis of the entity dimension can be understood as analyzing the entity information in the address information. Specifically, by analyzing the entity information in the address information, it is determined whether the address information can be identified to the household. Exemplarily, the analysis items corresponding to the entity dimension are shown in Table 4. By determining the analysis results corresponding to each analysis item, the analysis results corresponding to e1-e11 are respectively formed into feature data of the entity dimension. Among them, the positioning element in e1 is the pre-set address component information.

[0073] Table 4

[0074] e1 Is there a positioning feature? e2 Does the road + road number combination exist? e3 Does the combination of village + village number exist? e4 Whether there is an AOI, such as the cell name e5 Does poi exist? e6 Is there a building? e7 Is there a unit e8 Is there a floor? e9 Is there a household room? e10 Number of poi e11 Number of administrative villages

[0075] The feature analysis of logistics object information can be understood as analyzing the contact information of the logistics object to determine whether the logistics object can be contacted through the logistics object information and the delivery has been completed. Among them, redundant information can be information such as remarks or notes other than phone number and name, such as "gate guard collection" and "Cainiao post station collection".

[0076] Exemplarily, the analysis items corresponding to the characteristic analysis of logistics object information are shown in Table 5. The logistics object information (i.e., the non-address information in the information to be detected) is analyzed in sequence through the following multiple analysis items, and the analysis results corresponding to m1-m4 respectively form the characteristic data corresponding to the logistics object information.

[0077] Table 5

[0078] m1 Does the name exist? m2 Is there a phone? m3 Is there redundant information? m4 Redundant information length

[0079] The feature data corresponding to the above multiple dimensions are spliced ​​to obtain multi-dimensional features, and quality detection is performed based on the multi-dimensional features. In this embodiment, a machine learning model for quality detection of the information to be detected is pre-set, and the multi-dimensional features are quality detected by the machine learning model to obtain the quality detection result of the information to be detected.

[0080] Optionally, the machine learning model for quality detection of the information to be detected includes an error delivery prediction model and / or an outbound call prediction model. Among them, the error delivery prediction model is used to predict the error delivery event caused by the information to be detected, and the outbound call prediction model predicts the outbound call event in the delivery process corresponding to the information to be detected. The error delivery event is an event in which an error occurs at the delivery site during the delivery process based on the information to be detected, and the outbound call event is an event in which the correct address needs to be determined by outbound calling during the delivery process based on the information to be detected.

[0081] The multi-dimensional features are processed by the error delivery prediction model to obtain the first detection data. Optionally, the first detection data represents the probability of occurrence of the error delivery event. The larger the first detection data, the greater the probability of occurrence of the error delivery event, that is, the worse the quality of the information to be detected. Optionally, the first detection data represents the degree of delivery deviation corresponding to the information to be detected. The degree of delivery deviation corresponding to the information to be detected can represent the deviation distance between the error delivery site and the correct delivery site in the delivery process based on the information to be detected. The deviation distance between the error delivery site and the correct delivery site is positively correlated with the degree of delivery deviation. Among them, the first detection data can be data between 0-1. The first detection data is zero, which represents that the error delivery event will not occur in the delivery process based on the information to be detected. The first detection data is greater than zero, which represents that the error delivery event will occur in the delivery process based on the information to be detected. The larger the first detection data, the larger the deviation distance between the error delivery site and the correct delivery site, and correspondingly, the worse the quality of the information to be detected.

[0082] The multi-dimensional features are processed by the outbound call prediction model to obtain the second detection data. Optionally, the second detection data represents the probability of occurrence of an outbound call event. The larger the second detection data, the greater the probability of an outbound call event occurring in the delivery process based on the data to be detected, that is, the worse the quality of the information to be detected. Optionally, the second detection data represents the degree of address error corresponding to the information to be detected when an outbound call event occurs. The degree of address error when an outbound call event occurs can be understood as the degree of deviation between the delivery route area and the information to be detected during the delivery process based on the address information to be detected. Among them, the second detection data can be data between 0 and 1. The second detection data of zero represents that no outbound call event will occur in the delivery process based on the information to be detected, and the delivery is successful. The second detection data greater than zero represents that an outbound call event will occur in the delivery process based on the information to be detected. The larger the second detection data, the greater the deviation distance between the information to be detected and the actual delivery route area, and correspondingly, the worse the quality of the information to be detected.

[0083] In this embodiment, the first detection data and / or the second detection data obtained by predicting the error delivery events and / or outbound call events of the information to be detected during the delivery process through the error delivery prediction model and / or the outbound call prediction model can be used to characterize whether the delivery process based on the information to be detected is successful and smooth, so as to determine the target quality detection result of the information to be detected.

[0084] In some embodiments, the target quality detection result of the information to be detected can be determined based on the first detection data or the second detection data. Optionally, the first quality detection result is determined based on the first detection data, and the first quality detection result is determined as the target quality detection result of the information to be detected. The first quality detection result is negatively correlated with the first detection data. Exemplarily, the first quality detection result can be calculated based on the following formula: Where a is a hyperparameter and y1 is the first detection data.

[0085] Optionally, a second quality detection result is determined based on the second detection data, and the second quality detection result is determined as a target quality detection result of the information to be detected. The second quality detection result is negatively correlated with the second detection data. Exemplarily, the second quality detection result can be calculated based on the following formula: Where b is a hyperparameter and y2 is the second detection data.

[0086] In some embodiments, based on the first detection data and / or the second detection data, determining the target quality detection result of the information to be detected includes: determining a first quality detection result based on the first detection data, the first quality detection result is negatively correlated with the first detection data; determining a second quality detection result based on the second detection data, the second quality detection result is negatively correlated with the second detection data; determining the target quality detection result of the information to be detected based on the first quality detection result and / or the second quality detection result.

[0087] For example, the average of the first quality detection result and the second quality detection result may be determined as the target quality detection result of the information to be detected; or the weighted average of the first quality detection result and the second quality detection result may be determined as the target quality detection result of the information to be detected. The larger the target quality detection result, the better the quality of the information to be detected, and the smaller the target quality detection result, the worse the quality of the information to be detected.

[0088] When the target quality detection result is less than a preset threshold, a prompt message may be generated, which is used to prompt the user to modify the input information to be detected.

[0089] Optionally, the prompt information may include the abnormal reason of the information to be detected. The abnormal reason is identified based on the multi-dimensional features. Specifically, the analysis result corresponding to each analysis item in the multi-dimensional features is judged to determine whether the analysis result corresponding to the analysis item is abnormal. The abnormal reason is determined for the analysis item with abnormal analysis result. For example, the abnormal reason can be generated based on the description content corresponding to the analysis item with abnormal analysis result. When g5 in the multi-dimensional features is 0, it indicates that the address length is not within a reasonable range, and the abnormal reason can be generated as abnormal address length. When d7 in the multi-dimensional features is 1, it indicates that there are typos in the administrative district, and the prompt information can be generated as typos in the administrative district.

[0090] The technical solution of this embodiment, when obtaining the information to be detected in the logistics scenario, performs quality detection on the information to be detected based on the error delivery prediction model and / or the outbound call prediction model to obtain the target quality detection result of the information to be detected. After the user inputs the information to be detected, the information to be detected can be automatically detected, thereby improving the intelligence and detection efficiency of information detection, replacing the manual detection process, saving manpower and time consumption in the information detection process, and prompting the user to modify the erroneous information through the quality detection of the information to be detected, thereby improving the accuracy of the information, further improving the success rate of delivery in the logistics scenario, and avoiding the interference of erroneous information to the delivery process and the ineffective consumption of logistics resources.

[0091] On the basis of the above-mentioned embodiment, the erroneous delivery prediction model is pre-trained, and the training method of the erroneous delivery prediction model includes: obtaining sample information and historical delivery process information corresponding to the sample information, the historical delivery process information including delivery site information and delivery road area information; generating a first label corresponding to the sample information based on the delivery site information and the delivery road area information; training the erroneous delivery prediction model to be trained based on multiple sample information and the first labels corresponding to each sample information, until a trained erroneous delivery prediction model is obtained.

[0092] The sample information may be the collection and delivery information in the historical logistics business, and the historical distribution process information corresponding to the sample information may be the information generated by the historical logistics business in the distribution process, for example, it may include distribution site information and distribution road area information, wherein the distribution site information may be the last site information of the historical logistics business in the distribution process, and the distribution road area information is the distribution range information of the delivery personnel of the historical logistics business. Different delivery personnel have corresponding distribution road area information. The correspondence between the delivery personnel and the distribution road area information is pre-entered and stored, and the corresponding distribution road area information can be determined through the delivery personnel's identification (such as work number or name, etc.).

[0093] Optionally, whether an erroneous delivery event occurred in the delivery process of the historical logistics business is determined through the historical delivery process information corresponding to the sample information, and a first label is generated. For example, when an erroneous delivery event occurs, the first label may be 1, and when no erroneous delivery event occurs, the first label may be 0. Accordingly, the erroneous delivery prediction model trained based on the sample information and the first label corresponding to the sample information can be used to predict the probability of an erroneous delivery event occurring during the delivery process of the information to be detected.

[0094] Optionally, whether an erroneous delivery event occurred in the delivery process of the historical logistics business and the degree of delivery deviation corresponding to the erroneous delivery event are determined based on the delivery site information and the delivery route information in the historical delivery process information corresponding to the sample information, and the first label corresponding to the sample information is set based on the degree of delivery deviation corresponding to the erroneous delivery event. Accordingly, the erroneous delivery prediction model trained based on the sample information and the first label corresponding to the sample information can be used to predict the degree of delivery deviation of an erroneous delivery event in the delivery process of the information to be detected.

[0095] On the basis of the above-mentioned embodiment, the estimated site information is determined based on the address information in the sample information, and the site determination information is determined based on the estimated site information and the distribution site information; the site determination information can indicate whether an erroneous delivery event occurred during the distribution process of the historical logistics business. Exemplarily, if the site determination information is that the estimated site information and the distribution site information are the same, indicating that no erroneous delivery event occurred during the distribution process of the historical logistics business, the site determination information can be recorded as 0; if the site determination information is that the estimated site information and the distribution site information are different, indicating that an erroneous delivery event occurred during the distribution process of the historical logistics business, the site determination information can be recorded as 1. Among them, the estimated site information can be determined by matching the address information with the site address information, for example, the estimated site information is determined based on the site address information with the greatest similarity to the address information, or determined by a site estimation model, which is not limited here.

[0096] Determine the road area determination information based on the distribution road area information and the estimated road area information corresponding to the address information; determine the degree of delivery deviation based on the site determination information and the road area determination information, and generate a first label based on the degree of delivery deviation. The estimated road area information corresponding to the address information can be determined by matching the address information with multiple road areas corresponding to the estimated site information, or determined by a road area prediction model. Optionally, a distribution prediction model is pre-set, and the distribution prediction model can be used to predict the estimated site information and estimated road area information corresponding to the address information.

[0097] The distance between the delivery road area information and the estimated road area information is determined, for example, by the distance between the center point of the delivery road area information and the center point of the estimated road area information. The distance between the delivery road area information and the estimated road area information is determined as the road area determination information.

[0098] The delivery deviation degree is determined based on the site determination information and the road area determination information. Specifically, the delivery deviation degree can be determined based on the product of the site determination information and the road area determination information. Exemplarily, if the site determination information is 0, the delivery deviation degree is zero; if the site determination information is 1, the delivery deviation degree is the road area determination information. The larger the road area determination information, that is, the larger the distance between the distribution road area information and the estimated road area information, the larger the delivery deviation degree. In some embodiments, the road area determination information can also be normalized, that is, the distance between the distribution road area information and the estimated road area information is converted into a value between 0 and 1.

[0099] Obtain the error delivery prediction model to be trained, perform multi-dimensional analysis on the sample information, obtain multi-dimensional features corresponding to the sample information, input the multi-dimensional features into the error delivery prediction model to be trained, obtain the first training test data output by the error delivery prediction model, generate a first loss function based on the first training test data and the first label corresponding to the sample information, and adjust the model parameters of the error delivery prediction model to be trained based on the first loss function. Iterate the above training process until the training end condition is met to obtain a trained error delivery prediction model.

[0100] On the basis of the above-mentioned embodiment, the outbound call prediction model is pre-trained, and the training method of the outbound call prediction model includes: obtaining sample information and historical delivery process information corresponding to the sample information, the historical delivery process information including delivery route information and outbound call event information; generating a second label corresponding to the sample information according to the delivery route information and the outbound call event information; training the outbound call prediction model to be trained based on multiple sample information and the second label corresponding to each sample information, until a trained outbound call prediction model is obtained.

[0101] The outbound call event information can be understood as an identification of whether an outbound call event has occurred. For example, if the identification is 1, it can be determined that an outbound call event has occurred during the delivery process of the historical logistics business corresponding to the sample information, and if the identification is 0, it can be determined that no outbound call event has occurred during the delivery process of the historical logistics business corresponding to the sample information. Optionally, a second label is generated based on the outbound call event information. If the outbound call event information is 1, the second label can be determined as 1, and if the outbound call event information is 0, the second label can be determined as 0. Accordingly, the trained outbound call prediction model can be used to predict the probability of an outbound call event occurring during the delivery process based on the information to be detected.

[0102] Optionally, generating the second label corresponding to the sample information based on the delivery route area information and the outbound call event information includes: determining the distance information between at least one level of address component information corresponding to the address information in the sample information and the delivery route area information; and determining the second label based on the outbound call event information and the distance information.

[0103] The degree of address error is represented by the distance information between at least one level of address component information corresponding to the address information in the sample information and the delivery route information. The larger the distance information, the greater the degree of address error.

[0104] At least one level of address component information corresponding to the address information may include one or more of administrative district, village, road information, community and POI, respectively determine the distance information between each of the above address component information and the delivery road area information, and determine the minimum distance information among the multiple distance information as the final distance information. The distance information between each address component information and the delivery road area information may be the distance information between the center point of the address component information and the center point of the delivery road area information.

[0105] The second label is determined based on the product of the outbound call event information and the distance information. For example, when the outbound call event information is 0, the second label is 0, indicating that no outbound call event has occurred; when the outbound call event information is 1, the second label is the distance information, indicating that an outbound call event has occurred, as well as the degree of address error.

[0106] Obtain an outbound call prediction model to be trained, perform multi-dimensional analysis on the sample information, obtain multi-dimensional features corresponding to the sample information, input the multi-dimensional features into the outbound call prediction model to be trained, obtain second training test data output by the outbound call prediction model, generate a second loss function based on the second training test data and the second label corresponding to the sample information, and adjust the model parameters of the outbound call prediction model to be trained based on the second loss function. Iterate the above training process until the training end condition is met to obtain a trained outbound call prediction model.

[0107] Figure 2 Schematic diagram of the structure of an information detection device in a logistics scenario provided by an embodiment of the present invention. Figure 2 As shown, the device comprises:

[0108] The feature extraction module 210 is used to obtain the information to be detected, perform multi-dimensional analysis on the information to be detected, and obtain multi-dimensional features corresponding to the information to be detected;

[0109] The detection module 220 is used to predict the multi-dimensional features corresponding to the information to be detected based on a pre-trained error delivery prediction model to obtain first detection data of the information to be detected; and / or predict the multi-dimensional features corresponding to the information to be detected based on a pre-trained outbound call prediction model to obtain second detection data of the information to be detected;

[0110] The target quality detection result determination module 230 is used to determine the target quality detection result of the information to be detected based on the first detection data and / or the second detection data.

[0111] The technical solution of this embodiment, when obtaining the information to be detected in the logistics scenario, performs quality detection on the information to be detected based on the error delivery prediction model and / or the outbound call prediction model to obtain the target quality detection result of the information to be detected. After the user inputs the information to be detected, the information to be detected can be automatically detected, thereby improving the intelligence and detection efficiency of information detection, replacing the manual detection process, saving manpower and time consumption in the information detection process, and prompting the user to modify the erroneous information through the quality detection of the information to be detected, thereby improving the accuracy of the information, further improving the success rate of delivery in the logistics scenario, and avoiding the interference of erroneous information to the delivery process and the ineffective consumption of logistics resources.

[0112] Based on the above embodiment, optionally, the information to be detected includes address information and logistics object information; the multi-dimensional analysis includes feature analysis of the address form dimension of the address information, feature analysis of the administrative district dimension, feature analysis of the road dimension and feature analysis of the entity dimension, as well as one or more of the feature analysis of the logistics object information.

[0113] Optionally, the feature extraction module 210 is used to analyze the information to be detected based on at least one analysis item corresponding to each dimension, to obtain feature data corresponding to at least one analysis item corresponding to each dimension; and to form the multi-dimensional feature based on the feature data corresponding to at least one analysis item corresponding to multiple dimensions.

[0114] Based on the above embodiment, optionally, the feature extraction module 210 is used to perform one or more of the following: preprocessing the information to be detected, wherein the preprocessing includes one or more of removing irrelevant characters and normalizing characters; identifying at least one level of address component information in the address information.

[0115] Based on the above embodiment, optionally, the first detection data represents a degree of delivery deviation corresponding to the information to be detected, and the second detection data represents a degree of address error when an outbound call event occurs corresponding to the information to be detected;

[0116] The target quality detection result determination module 230 is used to: determine a first quality detection result based on the first detection data, the first quality detection result is negatively correlated with the first detection data; and / or determine a second quality detection result based on the second detection data, the second quality detection result is negatively correlated with the second detection data; determine the target quality detection result of the information to be detected based on the first quality detection result and / or the second quality detection result.

[0117] On the basis of the above embodiment, optionally, the device also includes: a first model training module is used to: obtain sample information and historical delivery process information corresponding to the sample information, the historical delivery process information including delivery site information and delivery road area information; generate a first label corresponding to the sample information based on the delivery site information and the delivery road area information; train the error delivery prediction model to be trained based on multiple sample information and the first label corresponding to each sample information, until a trained error delivery prediction model is obtained.

[0118] Optionally, the first model training module is also used to: determine the estimated site information based on the address information in the sample information, determine the site determination information based on the estimated site information and the delivery site information; determine the road area determination information based on the delivery road area information and the estimated road area information corresponding to the address information; and generate a first label based on the site determination information and the road area determination information.

[0119] On the basis of the above embodiment, optionally, the device also includes: a second model training module is used to: obtain sample information and historical delivery process information corresponding to the sample information, the historical delivery process information including delivery route information and outbound call event information; generate a second label corresponding to the sample information according to the delivery route information and the outbound call event information; train the outbound call prediction model to be trained based on multiple sample information and the second label corresponding to each sample information, until a trained outbound call prediction model is obtained.

[0120] Optionally, the second model training module is also used to: determine the distance information between at least one level of address component information corresponding to the address information in the sample information and the delivery route information; and determine the second label based on the outbound call event information and the distance information.

[0121] The information detection device in the logistics scenario provided by the embodiment of the present invention can execute the information detection method in the logistics scenario provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0122] Figure 31 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0123] like Figure 3 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0124] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0125] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the information detection method in the logistics scenario.

[0126] In some embodiments, the information detection method in the logistics scenario can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the information detection method in the logistics scenario described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the information detection method in the logistics scenario by any other appropriate means (for example, by means of firmware).

[0127] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] The computer program for implementing the information detection method in the logistics scenario of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0129] An embodiment of the present invention also provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to execute an information detection method in a logistics scenario, the method comprising: obtaining information to be detected, performing multi-dimensional analysis on the information to be detected, and obtaining multi-dimensional features corresponding to the information to be detected; predicting and processing the multi-dimensional features corresponding to the information to be detected based on a pre-trained error delivery prediction model to obtain first detection data of the information to be detected; and / or predicting and processing the multi-dimensional features corresponding to the information to be detected based on a pre-trained outbound call prediction model to obtain second detection data of the information to be detected; based on the first detection data and / or the second detection data, determining the target quality detection result of the information to be detected.

[0130] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0131] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0132] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0133] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0134] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0135] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for information detection in a logistics scenario, characterized in that: include: Acquire information to be detected, perform multi-dimensional analysis on the information to be detected, and obtain multi-dimensional features corresponding to the information to be detected; Based on a pre-trained error delivery prediction model, the multi-dimensional features corresponding to the information to be detected are predicted and processed to obtain first detection data of the information to be detected; and / or based on a pre-trained outbound call prediction model, the multi-dimensional features corresponding to the information to be detected are predicted and processed to obtain second detection data of the information to be detected; Based on the first detection data and / or the second detection data, a target quality detection result of the information to be detected is determined.

2. The method according to claim 1, characterized in that The information to be detected includes address information and logistics object information; the multi-dimensional analysis includes feature analysis of the address form dimension of the address information, feature analysis of the administrative district dimension, feature analysis of the road dimension and feature analysis of the entity dimension, as well as one or more of feature analysis of the logistics object information; The performing multi-dimensional analysis on the information to be detected to obtain multi-dimensional features corresponding to the information to be detected includes: Based on at least one analysis item corresponding to each dimension, the information to be detected is analyzed to obtain feature data corresponding to at least one analysis item corresponding to each dimension; The multi-dimensional feature is formed based on feature data corresponding to at least one analysis item corresponding to each of the multiple dimensions.

3. The method according to claim 2, characterized in that Before analyzing the information to be detected, one or more of the following items may be included: Preprocessing the information to be detected, wherein the preprocessing includes one or more of removing irrelevant characters and normalizing characters; At least one level of address component information in the address information is identified.

4. The method according to claim 1, characterized in that The first detection data represents the degree of delivery deviation corresponding to the information to be detected, and the second detection data represents the degree of address error when an outbound call event occurs corresponding to the information to be detected; The determining, based on the first detection data and / or the second detection data, a target quality detection result of the information to be detected includes: Determine a first quality detection result based on the first detection data, the first quality detection result is negatively correlated with the first detection data; and / or determine a second quality detection result based on the second detection data, the second quality detection result is negatively correlated with the second detection data; A target quality detection result of the information to be detected is determined based on the first quality detection result and / or the second quality detection result.

5. The method according to claim 1, characterized in that The training method of the error delivery prediction model includes: Acquire sample information and historical delivery process information corresponding to the sample information, wherein the historical delivery process information includes delivery site information and delivery route area information; Generate a first label corresponding to the sample information based on the delivery site information and the delivery road area information; The error delivery prediction model to be trained is trained based on the multiple sample information and the first labels respectively corresponding to the sample information, until a trained error delivery prediction model is obtained.

6. The method according to claim 5, characterized in that The generating a first label corresponding to the sample information based on the delivery site information and the delivery road area information includes: Determine estimated site information based on the address information in the sample information, and determine site determination information based on the estimated site information and the delivery site information; Determine the road area determination information based on the delivery road area information and the estimated road area information corresponding to the address information; A first label is generated based on the site determination information and the road zone determination information.

7. The method according to claim 1, characterized in that The training method of the outbound call prediction model includes: Acquire sample information and historical delivery process information corresponding to the sample information, wherein the historical delivery process information includes delivery route information and outbound call event information; Generate a second label corresponding to the sample information according to the delivery route information and the outbound call event information; The outbound call prediction model to be trained is trained based on the plurality of sample information and the second labels respectively corresponding to the sample information until a trained outbound call prediction model is obtained.

8. The method according to claim 7, characterized in that The step of generating a second label corresponding to the sample information according to the delivery route information and the outbound call event information includes: Determine distance information between at least one level of address component information corresponding to the address information in the sample information and the delivery route information; A second tag is determined according to the outbound call event information and the distance information.

9. An information detection device in a logistics scenario, characterized in that: include: A feature extraction module is used to obtain information to be detected, perform multi-dimensional analysis on the information to be detected, and obtain multi-dimensional features corresponding to the information to be detected; A detection module, configured to predict and process the multi-dimensional features corresponding to the information to be detected based on a pre-trained error delivery prediction model to obtain first detection data of the information to be detected; and / or to predict and process the multi-dimensional features corresponding to the information to be detected based on a pre-trained outbound call prediction model to obtain second detection data of the information to be detected; The target quality detection result determination module is used to determine the target quality detection result of the information to be detected based on the first detection data and / or the second detection data.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the information detection method in the logistics scenario described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the information detection method in a logistics scenario as described in any one of claims 1-8 when executed.

Images