CN113011157A - Method, device and equipment for hierarchical processing of address information - Google Patents
Method, device and equipment for hierarchical processing of address information Download PDFInfo
- Publication number
- CN113011157A CN113011157A CN202110293901.4A CN202110293901A CN113011157A CN 113011157 A CN113011157 A CN 113011157A CN 202110293901 A CN202110293901 A CN 202110293901A CN 113011157 A CN113011157 A CN 113011157A
- Authority
- CN
- China
- Prior art keywords
- address information
- training
- address
- trained model
- classified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 98
- 238000002372 labelling Methods 0.000 claims abstract description 16
- 238000003672 processing method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012512 characterization method Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000010365 information processing Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the disclosure provides a method, a device and equipment for processing address information in a grading way, wherein the method comprises the following steps: acquiring a preset number of address information, wherein the preset number of address information form a training set; labeling each piece of address information in the training set according to address grading; training an initial pre-training model according to the training set and the labeled address information to obtain a trained model; and inputting the address information to be classified into the trained model so that the trained model outputs the classified address information. The embodiment of the disclosure can carry out intelligent grading processing on the address information, save labor cost and improve grading processing efficiency.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a method, a device and equipment for hierarchical processing of address information.
Background
In order to improve the competitiveness of an enterprise and expand the business of the enterprise, the resource distribution condition of the enterprise needs to be managed uniformly, and especially the resource distribution condition of different regional dimensions (such as province, city, district, county, and the like) needs to be counted. At present, no standard address information template exists, and the address information is classified by adopting a manual input and manual classification mode so as to know the resource distribution conditions of different region dimensions. However, with the change of administrative division, the change and maintenance of address information will have certain difficulty
At present, in the prior art, a word segmentation tool is mainly adopted to grade address information according to keywords in the address information. However, the word segmentation tool has limited processing dependence keywords and needs to be manually maintained and updated, so that the word segmentation tool performs address information classification, and the problems of high labor cost and low efficiency exist.
Disclosure of Invention
The embodiment of the disclosure provides an address information grading processing method, device and equipment, which are used for solving the problems of high labor cost and low efficiency in address information grading of a segmentation tool caused by the fact that the segmentation tool is limited in processing dependent keywords and needs to be manually maintained and updated in the prior art.
In a first aspect, an embodiment of the present disclosure provides an address information hierarchical processing method, including:
acquiring a preset number of address information, wherein the preset number of address information form a training set;
labeling each piece of address information in the training set according to address grading;
training an initial pre-training model according to the training set and the labeled address information to obtain a trained model;
and inputting the address information to be classified into the trained model so that the trained model outputs the classified address information.
In a possible design, the training an initial pre-training model according to the training set and the labeled address information to obtain a trained model includes:
sa: inputting any piece of address information in the marked training set into the initial pre-training model to obtain classified address information;
sb: according to the labeled address information and the classified address information, performing back propagation on the initial pre-training model to adjust a weight coefficient of the initial pre-training model;
and (C) Sc: and repeating the steps Sa and Sb until the error between the classified address information output by the initial pre-training model after the weight coefficient is adjusted and the labeled address information meets a preset error range, and stopping training to obtain the trained model.
In one possible design, the tagging each piece of address information in the training set according to address hierarchy includes:
and acquiring each level of address text of each piece of address information in the training set, and marking each character in the address text with a label corresponding to the corresponding level according to a predefined label.
In one possible design, the initial pre-trained model is the enhanced language characterization model ERNIE.
In one possible design, after inputting the address information to be ranked into the trained model so that the trained model outputs ranked address information, the method further includes:
obtaining structured address information according to the classified address information;
and generating an enterprise resource information statistical table according to the structured address information so as to facilitate the statistics of enterprise resource information by users.
In a second aspect, an embodiment of the present disclosure provides an address information hierarchical processing apparatus, including:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a preset number of address information, and the preset number of address information forms a training set;
the labeling module is used for labeling each piece of address information in the training set according to address grading;
the training module is used for training an initial pre-training model according to the training set and the labeled address information to obtain a trained model;
and the processing module is used for inputting the address information to be classified into the trained model so as to enable the trained model to output the classified address information.
In one possible design, the apparatus further includes:
the generating module is used for obtaining structured address information according to the classified address information; and generating an enterprise resource information statistical table according to the structured address information so as to facilitate the statistics of enterprise resource information by users.
In a third aspect, an embodiment of the present disclosure provides a service device, including:
a display screen;
at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the hierarchical processing method of address information as set forth in the first aspect and various possible designs of the first aspect above.
In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, where computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the address information hierarchical processing method according to the first aspect and various possible designs of the first aspect is implemented.
In a fifth aspect, the embodiments of the present disclosure provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the hierarchical processing method for address information as described in the first aspect and various possible designs of the first aspect is implemented.
The method comprises the steps of firstly obtaining a large amount of address information to form a training set, and labeling the address information of the training set; then training an initial pre-training model based on the training set and the address information labeled by the label to obtain a trained model; and finally, when new address information needs to be classified, inputting the address information to be classified into the trained model, outputting the classified address information, and performing intelligent classification processing on the address information, so that the labor cost is saved, and the classification processing efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and for those skilled in the art, other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic diagram of an architecture of a hierarchical address information processing system according to an embodiment of the present disclosure;
fig. 2 is a first schematic flow chart of a hierarchical address information processing method according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of a second address information hierarchical processing method according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an address information hierarchical processing apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of a hardware structure of a service device according to an embodiment of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
At present, in order to manage enterprise resource distribution in an enterprise, addresses of different dimensions are often required to be acquired from address information of different dimensions, so as to acquire resource distribution conditions in each dimension. Generally, word segmentation tools are mainly used in the prior art to grade address information. However, the word segmentation tool has limited processing dependence keywords and needs to be manually maintained and updated, so that the word segmentation tool performs address information classification, and the problems of high labor cost and low efficiency exist.
In order to solve the above technical problem, embodiments of the present disclosure provide a method, an apparatus, and a device for processing address information in a hierarchical manner, where a large amount of address information is obtained to form a training set, and the address information of the training set is labeled; training an initial pre-training model based on the training set and the address information labeled by the label to obtain a trained model; when new address information needs to be graded, the address information to be graded is input into the trained model, and the graded address information is output, so that the address information can be intelligently graded, the labor cost is saved, and the grading processing efficiency is improved.
Fig. 1 is a schematic diagram of an architecture of a hierarchical address information processing system according to an embodiment of the present disclosure. As shown in fig. 1, the system provided by the present embodiment includes a terminal 101 and a service device 102. The terminal 101 may be a mobile phone, a tablet, a personal computer, or the like.
The terminal 101 may be any type of terminal. The terminal may be a wireless terminal or a wired terminal. A wireless terminal may refer to a device that provides voice and/or other traffic data connectivity to a user, a handheld device having wireless connection capability, or other processing device connected to a wireless modem. A wireless terminal, which may be a mobile terminal such as a mobile telephone (or "cellular" telephone) and a computer having a mobile terminal, for example, a portable, pocket, hand-held, computer-included, or vehicle-mounted mobile device, may communicate with one or more core Network devices via a Radio Access Network (RAN), and may exchange language and/or data with the RAN. For another example, the Wireless terminal may also be a Personal Communication Service (PCS) phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), and other devices. A wireless Terminal may also be referred to as a system, a Subscriber Unit (Subscriber Unit), a Subscriber Station (Subscriber Station), a Mobile Station (Mobile), a Remote Station (Remote Station), a Remote Terminal (Remote Terminal), an Access Terminal (Access Terminal), a User Terminal (User Terminal), a User Agent (User Agent), and a User Device or User Equipment (User Equipment), which are not limited herein. Optionally, the terminal may also be a smart watch, a tablet computer, a personal computer, or the like.
The service device 102 may be a computer or a server, or may be a cluster formed by a plurality of computers or servers, and the embodiment of the present disclosure is not limited in any way.
Fig. 2 is a first schematic flow chart of a hierarchical processing method for address information according to an embodiment of the present disclosure, where an execution subject of the embodiment may be the terminal or the service device shown in fig. 1. As shown in fig. 2, the method includes:
s201: acquiring a preset number of address information, wherein the preset number of address information forms a training set.
In this embodiment, the preset number of address information may be all address information within a preset time period derived from the resource distribution management system.
For example, all address information may be in 12 months, 24 months, or 48 months.
In this embodiment, the training set may be in a text format or a table format.
S202: and labeling each piece of address information in the training set according to address grading.
In this embodiment, the tags are first predefined by address hierarchy. And defining a label for the starting position character of each level of address text, and defining a middle position character and an ending position character of each level of address text.
For the text entities needing grading in the address information, the definition of the label set is carried out to represent the possible grading results. For example, the text entities that need to be classified include "province, city, district, way, unit", etc., and thus, the tag set can be defined as:
label＝{A1-B,A1-I,A2-B,A2-I,A3-B,A3-I,A4-B,A4-I,A5-B,A5-I,A6-B,A6-I,,A7-B,A7-I,A8-B,A8-I,A9-B,A9-I,A10-B,A10-I,A11-B,A11-I}；
wherein, the definition of each label is (table one):
watch 1
| Label (R) | Definition of |
| A1-B | Provincial starting position character |
| A1-I | Provincial intermediate or end position characters |
| A2-B | City starting position character |
| A2-I | City middle or end position characters |
| A3-B | County area starting position character |
| A3-I | County middle or end position character |
| A4-B | Intersection starting position character |
| A4-I | Intersection middle or end position characters |
| A5-B | Level 5 address start location character |
| A5-I | Level 5 address middle or end position characters |
| A6-B | Level 6 address start location character |
| A6-I | 6-level address middle or end position character |
| A7-B | Level 7 address start location character |
| A7-I | 7-level address middle or end position characters |
| A8-B | 8-level address start location character |
| A8-I | 8-level address middle or end position character |
| A9-B | 9-level address start location character |
| A9-I | 9-level address middle or end position characters |
| A10-B | Level 10 address start location character |
| A10-I | 10 level address middle or end position character |
| A11-B | 11 level address start location character |
| A11-I | 11-level address middle or end position characters |
Specifically, each level of address text of each piece of address information is obtained, and a label corresponding to the corresponding level is marked on each character in the address text according to a predefined label.
Labeling each piece of data in the training set, identifying the initial position character of each level of address text according to the text entity, and labeling the label according to the initial position of each level of address text; then label labeling is carried out on all the middle position characters and the end position characters of the address text of the level between the address text of the level and the address text of the next level.
For example, for address information: room 2202 in No. 3, No. 4, No. 33 and No. 4 units in No. 2 green scenery flower garden plot of No. 150 in development area of Hechun city, Anhu province. The label corresponding to each character is shown in table two:
watch two
S203: and training the initial pre-training model according to the training set and the labeled address information to obtain a trained model.
In this embodiment, the initial pre-trained model may be a deep learning model, such as a deep neural network model.
Optionally, the initial pre-training model is an enhanced language representation model ERNIE.
S204: and inputting the address information to be classified into the trained model so that the trained model outputs the classified address information.
In this embodiment, the address information input by the user at the terminal is received, the address information input by the user is filtered to obtain the address information to be classified, and the address information is input into the trained model.
The filtering of invalid information for address information input by a user comprises the following steps: and deleting invalid characters of the address information input by the user, such as punctuation marks and other information.
As can be seen from the above description, first, a large amount of address information is obtained to form a training set, and the address information of the training set is labeled; then, training an initial pre-training model based on the training set and the labeled address information to obtain a trained model; and finally, when new address information needs to be classified, the address information to be classified is input into the trained model, and the classified address information is output, so that the address information can be intelligently classified, the labor cost is saved, and the classification processing efficiency is improved.
In an embodiment of the present disclosure, in the step S203, the specific process of training the initial pre-training model according to the training set and the labeled address information to obtain the trained model includes:
sa: inputting any piece of address information in the marked training set into the initial pre-training model to obtain classified address information;
sb: according to the labeled address information and the classified address information, performing back propagation on the initial pre-training model to adjust a weight coefficient of the initial pre-training model;
and (C) Sc: and repeating the steps Sa and Sb until the error between the classified address information output by the initial pre-training model after the weight coefficient is adjusted and the labeled address information meets a preset error range, and stopping training to obtain the trained model.
In this embodiment, the initial pre-trained model may be a neural network model. For example: various types of network structures such as dnn (deep neural network), cnn (volumetric neural network), rnn (regenerative neural network), and extensions thereof.
Fig. 3 is a second flowchart of a hierarchical processing method for address information according to an embodiment of the present disclosure, where on the basis of the embodiment of fig. 2, in this embodiment, after the step S204 of inputting address information to be ranked into the trained model so that the trained model outputs the ranked address information, the method further includes:
s205: and obtaining the structured address information according to the classified address information.
In this embodiment, the address information after the classification is stored at a level interval to obtain the structured address information, for example, a special symbol, such as "#", is added between the address texts at each level.
For example, the structured address information of "No. 150 green scenery flower garden plot of No. 2 phase No. 3 building No. 4 building No. 33 building No. 2202 room in development area of No. a lake province, and spring city" is the 11-level address information of "No. 150 # green scenery flower garden plot of No. #150 # green scenery flower garden plot of #2 phase No. 3 building #4 unit #33 building #2202 room" in No. a lake province, a # spring city.
S206: and generating an enterprise resource information statistical table according to the structured address information so as to facilitate the statistics of enterprise resource information by users.
In the embodiment of the present disclosure, the structured address information is imported into the top row content or the top column content of the table, and the enterprise resource information statistics related statistics items are added to the table to obtain the enterprise resource information statistics table. The user can manually and automatically import the enterprise resource information data in the enterprise resource information statistical table, so that the user can conveniently count the enterprise resource information.
Fig. 4 is a schematic structural diagram of an address information hierarchical processing apparatus according to an embodiment of the present disclosure. As shown in fig. 4, the address information hierarchical processing apparatus 40 includes: an acquisition module 401, a labeling module 402, a training module 403, and a processing module 404.
The acquiring module 401 is configured to acquire a preset number of address information, where the preset number of address information form a training set;
a labeling module 402, configured to label each piece of address information in the training set according to address classification;
a training module 403, configured to train an initial pre-training model according to the training set and the labeled address information, to obtain a trained model;
a processing module 404, configured to input address information to be ranked into the trained model, so that the trained model outputs ranked address information.
In an embodiment of the present disclosure, the training module 403 is specifically configured to train an initial pre-training model according to the training set and the labeled address information, and obtain a trained model, where the process includes: sa: inputting any piece of address information in the marked training set into the initial pre-training model to obtain classified address information; sb: according to the labeled address information and the classified address information, performing back propagation on the initial pre-training model to adjust a weight coefficient of the initial pre-training model; and (C) Sc: and repeating the steps Sa and Sb until the error between the classified address information output by the initial pre-training model after the weight coefficient is adjusted and the labeled address information meets a preset error range, and stopping training to obtain the trained model.
In an embodiment of the present disclosure, the labeling module 402 is specifically configured to perform a label labeling process on each piece of address information in the training set according to address hierarchy, and includes: and acquiring each level of address text of each piece of address information in the training set, and marking each character in the address text with a label corresponding to the corresponding level according to a predefined label.
In one embodiment of the present disclosure, the initial pre-training model is an enhanced language characterization model ERNIE.
In one embodiment of the present disclosure, the apparatus further comprises: a generating module 405, configured to obtain structured address information according to the classified address information; and generating an enterprise resource information statistical table according to the structured address information so as to facilitate the statistics of enterprise resource information by users.
The apparatus provided in this embodiment may be used to implement the technical solutions of the above method embodiments, and the implementation principles and technical effects are similar, which are not described herein again.
Fig. 5 is a schematic diagram of a hardware structure of a service device according to an embodiment of the present disclosure. As shown in fig. 5, the service apparatus 50 of the present embodiment includes:
a display screen 504;
a processor 501 and a memory 502; wherein
A memory 502 for storing computer-executable instructions;
a processor 501 for executing computer-executable instructions stored in the memory to implement the steps performed in the above-described method embodiments. Reference may be made in particular to the description relating to the method embodiments described above.
Alternatively, the memory 502 may be separate or integrated with the processor 501.
When the memory 502 is provided separately, the service device further comprises a bus 503 for connecting the memory 502, the display 504 and the processor 501.
The embodiment of the present disclosure further provides a computer-readable storage medium, in which a computer executing instruction is stored, and when a processor executes the computer executing instruction, the hierarchical processing method for address information as described above is implemented.
The embodiment of the present disclosure further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the hierarchical processing method for address information as described above is implemented.
In the several embodiments provided in the present disclosure, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the modules is only one logical division, and other divisions may be realized in practice, for example, a plurality of modules may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to implement the solution of the present embodiment.
In addition, functional modules in the embodiments of the present disclosure may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit. The unit formed by the modules can be realized in a hardware form, and can also be realized in a form of hardware and a software functional unit.
The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a processor to execute some steps of the methods described in the embodiments of the present application.
It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, etc.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in an electronic device or host device.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present disclosure, and not for limiting the same; while the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present disclosure.
Claims (10)
1. An address information hierarchical processing method, comprising:
acquiring a preset number of address information, wherein the preset number of address information form a training set;
labeling each piece of address information in the training set according to address grading;
training an initial pre-training model according to the training set and the labeled address information to obtain a trained model;
and inputting the address information to be classified into the trained model so that the trained model outputs the classified address information.
2. The method of claim 1, wherein the training an initial pre-trained model according to the training set and labeled address information to obtain a trained model comprises:
sa: inputting any piece of address information in the marked training set into the initial pre-training model to obtain classified address information;
sb: according to the labeled address information and the classified address information, performing back propagation on the initial pre-training model to adjust a weight coefficient of the initial pre-training model;
and (C) Sc: and repeating the steps Sa and Sb until the error between the classified address information output by the initial pre-training model after the weight coefficient is adjusted and the labeled address information meets a preset error range, and stopping training to obtain the trained model.
3. The method of claim 1, wherein tagging each piece of address information in the training set according to an address hierarchy comprises:
and acquiring each level of address text of each piece of address information in the training set, and marking each character in the address text with a label corresponding to the corresponding level according to a predefined label.
4. The method according to any one of claims 1 to 3, wherein the initial pre-trained model is the enhanced language characterization model ERNIE.
5. The method according to any one of claims 1 to 3, wherein after inputting the address information to be ranked into the trained model so that the trained model outputs ranked address information, the method further comprises:
obtaining structured address information according to the classified address information;
and generating an enterprise resource information statistical table according to the structured address information so as to facilitate the statistics of enterprise resource information by users.
6. An address information hierarchical processing apparatus, comprising:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a preset number of address information, and the preset number of address information forms a training set;
the labeling module is used for labeling each piece of address information in the training set according to address grading;
the training module is used for training an initial pre-training model according to the training set and the labeled address information to obtain a trained model;
and the processing module is used for inputting the address information to be classified into the trained model so as to enable the trained model to output the classified address information.
7. The apparatus of claim 6, further comprising:
the generating module is used for obtaining structured address information according to the classified address information; and generating an enterprise resource information statistical table according to the structured address information so as to facilitate the statistics of enterprise resource information by users.
8. A service device, characterized by comprising:
a display screen is arranged on the display screen,
at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the address information hierarchical processing method of any one of claims 1 to 5.
9. A computer-readable storage medium, wherein a computer-executable instruction is stored in the computer-readable storage medium, and when a processor executes the computer-executable instruction, the address information hierarchical processing method according to any one of claims 1 to 5 is implemented.
10. A computer program product comprising a computer program which, when executed by a processor, implements the address information hierarchical processing method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110293901.4A CN113011157A (en) | 2021-03-19 | 2021-03-19 | Method, device and equipment for hierarchical processing of address information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110293901.4A CN113011157A (en) | 2021-03-19 | 2021-03-19 | Method, device and equipment for hierarchical processing of address information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113011157A true CN113011157A (en) | 2021-06-22 |
Family
ID=76402843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110293901.4A Pending CN113011157A (en) | 2021-03-19 | 2021-03-19 | Method, device and equipment for hierarchical processing of address information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113011157A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108763212A (en) * | 2018-05-23 | 2018-11-06 | 北京神州泰岳软件股份有限公司 | A kind of address information extraction method and device |
| CN109684624A (en) * | 2017-10-18 | 2019-04-26 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus in automatic identification Order Address road area |
| CN110688449A (en) * | 2019-09-20 | 2020-01-14 | 京东数字科技控股有限公司 | Address text processing method, device, equipment and medium based on deep learning |
| CN111125365A (en) * | 2019-12-24 | 2020-05-08 | 京东数字科技控股有限公司 | Address data labeling method and device, electronic equipment and storage medium |
| CN111723164A (en) * | 2019-03-18 | 2020-09-29 | 阿里巴巴集团控股有限公司 | Address information processing method and device |
| CN112329470A (en) * | 2020-11-09 | 2021-02-05 | 北京中科闻歌科技股份有限公司 | Intelligent address identification method and device based on end-to-end model training |
-
2021
- 2021-03-19 CN CN202110293901.4A patent/CN113011157A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684624A (en) * | 2017-10-18 | 2019-04-26 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus in automatic identification Order Address road area |
| CN108763212A (en) * | 2018-05-23 | 2018-11-06 | 北京神州泰岳软件股份有限公司 | A kind of address information extraction method and device |
| CN111723164A (en) * | 2019-03-18 | 2020-09-29 | 阿里巴巴集团控股有限公司 | Address information processing method and device |
| CN110688449A (en) * | 2019-09-20 | 2020-01-14 | 京东数字科技控股有限公司 | Address text processing method, device, equipment and medium based on deep learning |
| CN111125365A (en) * | 2019-12-24 | 2020-05-08 | 京东数字科技控股有限公司 | Address data labeling method and device, electronic equipment and storage medium |
| CN112329470A (en) * | 2020-11-09 | 2021-02-05 | 北京中科闻歌科技股份有限公司 | Intelligent address identification method and device based on end-to-end model training |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108415952B (en) | User data storage method, label calculation method and calculation equipment | |
| CN109783651A (en) | Extract method, apparatus, electronic equipment and the storage medium of entity relevant information | |
| CN103678702A (en) | Video duplicate removal method and device | |
| CN104021198A (en) | Relational database information retrieval method and device based on ontology semantic index | |
| CN108363684A (en) | List creation method, device and server | |
| WO2018171295A1 (en) | Method and apparatus for tagging article, terminal, and computer readable storage medium | |
| CN110705226A (en) | Spreadsheet creating method and device and computer equipment | |
| CN108446262A (en) | A kind of list generates, analysis method and device | |
| CN110363206A (en) | Cluster, data processing and the data identification method of data object | |
| CN101639851B (en) | Method for storing and querying data and devices thereof | |
| CN110378569A (en) | Industrial relations chain building method, apparatus, equipment and storage medium | |
| CN113011157A (en) | Method, device and equipment for hierarchical processing of address information | |
| CN102760127A (en) | Method, device and equipment for determining resource type based on extended text information | |
| CN111027533A (en) | Conversion method and system of point-to-read coordinates, terminal device and storage medium | |
| CN102566854A (en) | Device and method for price quantity statistic and price level marking display of financial stock quotation reading software | |
| CN106294779B (en) | Personal brand label generation method and system | |
| CN114297381A (en) | Text processing method, device, equipment and storage medium | |
| CN106294292A (en) | Chapters and sections catalogue screening technique and device | |
| CN107045554A (en) | Pipeline table data and Conversion of Spatial Data method and device | |
| CN114067343A (en) | Data set construction method, model training method and corresponding device | |
| CN115114280A (en) | Report generation processing method, device and equipment | |
| CN110362657B (en) | Obtain APP and portrait computing equipment of label | |
| CN115952174B (en) | Data table connection method, system, terminal and storage medium | |
| CN101741574A (en) | Data card with flow statistics, data card using system and realizing method | |
| CN111553136A (en) | Method and device for generating demonstration document template and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210622 |
|
| RJ01 | Rejection of invention patent application after publication |