CN113343700A - Data processing method, device, equipment and storage medium - Google Patents
Data processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113343700A CN113343700A CN202110693515.4A CN202110693515A CN113343700A CN 113343700 A CN113343700 A CN 113343700A CN 202110693515 A CN202110693515 A CN 202110693515A CN 113343700 A CN113343700 A CN 113343700A
- Authority
- CN
- China
- Prior art keywords
- information
- value
- evaluation
- type
- target
- 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.)
- Granted
Links
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
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- 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
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Abstract
The invention relates to artificial intelligence and provides a data processing method, a device, equipment and a storage medium. The method includes the steps of obtaining information to be analyzed according to an evaluation request, determining an evaluation object according to entity information in the information to be analyzed, determining target characteristics according to object types of the evaluation object, extracting information values corresponding to the target characteristics from the information to be analyzed, obtaining a price estimation network according to the object types, generating the price estimation network according to historical training data, obtaining target training data from the historical training data according to the information values, adjusting the price estimation network according to the target training data to obtain a price estimation model, inputting the information values into the price estimation model to obtain estimation values, and generating an evaluation result according to the estimation values. The invention can quickly and accurately generate the evaluation result. In addition, the invention also relates to a block chain technology, and the evaluation result can be stored in the block chain.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a data processing method, apparatus, device, and storage medium.
Background
In the current mortgage loan amount evaluation method, a user is generally required to evaluate a client credit value by investigating an evaluation object in the field and then checking the credit value through the adjustment, and then determining the loan amount by combining the comprehensive property of the client. However, this method is prone to cause inaccurate evaluation results due to misoperation and personal emotional deviation, and secondly, the auditing process of this method is cumbersome, thereby causing low evaluation efficiency.
Disclosure of Invention
In view of the above, it is desirable to provide a data processing method, device, apparatus and storage medium, which can accurately and quickly determine the evaluation result of the evaluation object.
In one aspect, the present invention provides a data processing method, where the data processing method includes:
when an evaluation request is received, acquiring information to be analyzed according to the evaluation request;
determining an evaluation object corresponding to the evaluation request according to entity information in the information to be analyzed;
determining a target characteristic of the evaluation object according to the object type of the evaluation object;
extracting an information value corresponding to the target feature from the information to be analyzed;
acquiring a price estimation network trained in advance according to the object type, wherein the price estimation network is generated according to historical training data;
acquiring target training data from the historical training data according to the information value;
adjusting the price estimation network according to the target training data to obtain a price estimation model, and inputting the information value into the price estimation model to obtain the estimation value of the estimation object;
and generating an evaluation result of the evaluation request according to the estimated value.
According to a preferred embodiment of the present invention, the obtaining information to be analyzed according to the evaluation request includes:
analyzing the message of the evaluation request to obtain data information;
extracting information indicating a position from the data information as a storage path;
writing the storage path into a preset template to obtain a query statement;
running the query statement in a configuration library to obtain object information;
acquiring pixel information in the object information;
and identifying the text in the object information according to the pixel information to obtain the information to be analyzed.
According to a preferred embodiment of the present invention, the determining, according to the entity information in the to-be-analyzed information, the evaluation object corresponding to the evaluation request includes:
performing word segmentation processing on the information to be analyzed according to a preset dictionary to obtain a plurality of processing paths and path word segmentation corresponding to each processing path;
calculating the path probability of each processing path according to the segmentation weight of the path segmentation in the preset dictionary;
determining the path word segmentation corresponding to the processing path with the maximum path probability as a target word segmentation;
determining the part of speech of the target word segmentation in the information to be analyzed, and extracting the entity information from the target word segmentation according to the part of speech and a preset part of speech;
traversing an object mapping table according to the entity information to obtain a traversal result, and calculating the matching number of information corresponding to each object in the object mapping table successfully matched with the entity information according to the traversal result;
and determining the object with the largest matching number as the evaluation object.
According to a preferred embodiment of the present invention, the determining the target feature of the evaluation object according to the object type of the evaluation object includes:
determining the type corresponding to the evaluation object as the object type;
acquiring all features in the object type as type features, and acquiring type evaluation data of the object type, wherein the type evaluation data comprises feature values of a plurality of types of articles in the type features and article values of the types of articles in a value dimension;
constructing a mapping curve of any type of feature and the value dimension according to the feature value and the value of the article, and calculating the correlation degree of any type of feature and the value dimension according to the mapping curve;
and determining the type feature with the correlation degree larger than a preset threshold value as the target feature.
According to the preferred embodiment of the present invention, before obtaining the pre-trained price estimation network according to the object type, the data processing method further includes:
inputting the historical training data into a forgetting gate layer for forgetting processing to obtain a data coding value;
dividing the data coding values into a training set and a verification set by adopting a cross verification method;
inputting the data coding values in the training set to an input gate layer for training to obtain a learner;
adjusting depreciation coefficients in the learner according to the data coding values in the verification set to obtain the price pre-estimation network;
and storing the mapping relation between the object type and the price estimation network.
According to the preferred embodiment of the present invention, the adjusting the price estimation network according to the target training data to obtain a price estimation model includes:
the target training data comprises data values and data results;
inputting the data value into the price estimation network to obtain a prediction result;
calculating the loss value of the price estimation network according to the data result and the prediction result;
if the loss value is larger than the preset loss, adjusting the depreciation coefficient in the price estimation network according to the preset degree value until the adjusted loss value of the price estimation network is smaller than or equal to the preset loss, and determining the adjusted price estimation network as a price estimation model.
According to a preferred embodiment of the present invention, the obtaining target training data from the historical training data according to the information value includes:
dividing the information value into numerical type information and character type information;
determining a characteristic corresponding to the numerical type information from the target characteristics as a first characteristic, and determining a characteristic corresponding to the character type information from the target characteristics as a second characteristic;
acquiring information corresponding to the first feature from the historical training data as first information, and acquiring information corresponding to the second feature from the historical training data as second information;
calculating the difference value between the numerical information and the first information, and calculating the similar distance between the character type information and the second information;
acquiring the numerical value type information and the information weight of the character type information, and carrying out weighting and operation on the difference value and the similar distance according to the information weight to obtain the similarity between the information value and the historical training data;
and determining the historical training data with the similarity larger than a preset similarity value as the target training data.
In another aspect, the present invention further provides a data processing apparatus, including:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring information to be analyzed according to an evaluation request when the evaluation request is received;
the determining unit is used for determining an evaluation object corresponding to the evaluation request according to entity information in the information to be analyzed;
the determining unit is further used for determining a target feature of the evaluation object according to the object type of the evaluation object;
an extraction unit, configured to extract an information value corresponding to the target feature from the information to be analyzed;
the acquisition unit is further used for acquiring a pre-trained price estimation network according to the object type, wherein the price estimation network is generated according to historical training data;
the acquisition unit is further used for acquiring target training data from the historical training data according to the information value;
the input unit is used for adjusting the price estimation network according to the target training data to obtain a price estimation model, and inputting the information value into the price estimation model to obtain the estimation value of the estimation object;
and the generating unit is used for generating an evaluation result of the evaluation request according to the estimated value.
In another aspect, the present invention further provides an electronic device, including:
a memory storing computer readable instructions; and
a processor executing computer readable instructions stored in the memory to implement the data processing method.
In another aspect, the present invention also provides a computer-readable storage medium, in which computer-readable instructions are stored, and the computer-readable instructions are executed by a processor in an electronic device to implement the data processing method.
According to the technical scheme, the evaluation object can be accurately determined through the entity information in the information to be analyzed, the target characteristics influencing the estimated commodity price of the evaluation object can be accurately determined according to the object type, the price estimation network is adjusted through the target training data determined by the information value, the accuracy of determining the estimated value can be improved, the evaluation result can be accurately determined, and the inaccuracy of the evaluation result caused by misoperation and personal emotional deviation can be avoided. In addition, the evaluation result can be determined by analyzing the information value corresponding to the target feature in the evaluation object, so that the determination efficiency of the evaluation result is improved. In addition, the invention analyzes the evaluation result through the artificial intelligence technology, can avoid the information leakage of the loan users in the evaluation request, thereby improving the information security.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the data processing method of the present invention.
FIG. 2 is a functional block diagram of a preferred embodiment of a data processing apparatus according to the present invention.
FIG. 3 is a schematic structural diagram of an electronic device implementing a data processing method according to a preferred embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
FIG. 1 is a flow chart of a data processing method according to a preferred embodiment of the present invention. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs.
The data processing method is applied to one or more electronic devices, which are devices capable of automatically performing numerical calculation and/or information processing according to computer readable instructions set or stored in advance, and the hardware thereof includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The electronic device may be any electronic product capable of performing human-computer interaction with a user, for example, a Personal computer, a tablet computer, a smart phone, a Personal Digital Assistant (PDA), a game machine, an interactive Internet Protocol Television (IPTV), a smart wearable device, and the like.
The electronic device may include a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network electronic device, an electronic device group consisting of a plurality of network electronic devices, or a Cloud Computing (Cloud Computing) based Cloud consisting of a large number of hosts or network electronic devices.
The network in which the electronic device is located includes, but is not limited to: the internet, a wide area Network, a metropolitan area Network, a local area Network, a Virtual Private Network (VPN), and the like.
S10, when receiving the evaluation request, obtaining the information to be analyzed according to the evaluation request.
In at least one embodiment of the invention, the evaluation request may refer to an evaluation request for a loanable amount of the loan mortgage at a certain risk level. The evaluation request carries a tag indicating a position, a storage path and the like.
The information to be analyzed refers to the relevant information of the object to be evaluated in the evaluation request. For example, the object to be evaluated in the evaluation request is a C-house villa, and the information to be analyzed may be a house property certificate and a house purchase contract of the C-house villa.
In at least one embodiment of the present invention, the obtaining, by the electronic device, information to be analyzed according to the evaluation request includes:
analyzing the message of the evaluation request to obtain data information;
extracting information indicating a position from the data information as a storage path;
writing the storage path into a preset template to obtain a query statement;
running the query statement in a configuration library to obtain object information;
acquiring pixel information in the object information;
and identifying the text in the object information according to the pixel information to obtain the information to be analyzed.
Wherein, the data information includes, but is not limited to: a tag indicating a location, the storage path, etc.
The storage path stores related information of the evaluation object, for example, a property certificate and a house purchase contract of the property a.
The preset template may be a structured query statement. Accordingly, the query statement protects the query object and the preset template.
The configuration library stores a plurality of paths, and each path stores relevant information of a corresponding object.
The object information refers to information related to the evaluation object. The display form of the object information may be an image format, and the display form of the object information may also be a PDF format. For example, if the evaluation object is a real estate, the object information may include a real estate certificate and a house purchase contract.
The pixel information refers to information of each pixel point in the object information on RGB three channels.
By analyzing the message, the whole evaluation request does not need to be analyzed, so that the acquisition efficiency of the storage path can be improved, and by the preset template, the information in the configuration library does not need to be traversed one by one, so that the acquisition efficiency of the object information can be improved, and the information to be analyzed can be quickly acquired.
And S11, determining an evaluation object corresponding to the evaluation request according to the entity information in the information to be analyzed.
In at least one embodiment of the present invention, the entity information can be used to indicate an object characterized in the information to be analyzed. The entity information refers to the vocabulary with the part of speech being the noun in the information to be analyzed.
The evaluation object refers to an object to be evaluated in the evaluation request, and the evaluation object may be any object capable of performing loan mortgage, such as a villa.
In at least one embodiment of the present invention, the determining, by the electronic device, an evaluation object corresponding to the evaluation request according to entity information in the to-be-analyzed information includes:
performing word segmentation processing on the information to be analyzed according to a preset dictionary to obtain a plurality of processing paths and path word segmentation corresponding to each processing path;
calculating the path probability of each processing path according to the segmentation weight of the path segmentation in the preset dictionary;
determining the path word segmentation corresponding to the processing path with the maximum path probability as a target word segmentation;
determining the part of speech of the target word segmentation in the information to be analyzed, and extracting the entity information from the target word segmentation according to the part of speech and a preset part of speech;
traversing an object mapping table according to the entity information to obtain a traversal result, and calculating the matching number of information corresponding to each object in the object mapping table successfully matched with the entity information according to the traversal result;
and determining the object with the largest matching number as the evaluation object.
The preset dictionary stores a plurality of user-defined words and weight values corresponding to the user-defined words. And the weight value of each user-defined vocabulary in the preset dictionary is set according to the word segmentation requirement.
The processing paths refer to a route for performing word segmentation processing on the information to be analyzed.
The path word segmentation refers to the word segmentation of the information to be analyzed under each processing path.
The path probability refers to a probability value of the path word segmentation generated according to the preset dictionary.
The predetermined part of speech is typically set to be a noun.
The object mapping table stores a plurality of objects and information corresponding to each object. The plurality of objects stored in the object mapping table are items that may be used for mortgage loans.
The matching number refers to the number of matching between the corresponding information in each object and the entity information, for example, the object mapping table stores an object a: information A, information B and information C; object B: c information, D information, E information and G information; the entity information includes: and B information and C information are determined, and the matching number of the A object is 2, and the matching number of the B object is 1.
The path probability of each processing path can be accurately determined through the preset dictionary, and further the target word segmentation meeting the word segmentation requirements can be accurately determined according to the path probability, furthermore, the entity information is extracted from the target word segmentation, the traversal amount of the object mapping table can be reduced, so that the evaluation object can be quickly determined, and meanwhile, the evaluation object can be accurately determined from the object mapping table through the traversal result of each object in the object mapping table and the entity information.
Specifically, the calculating, by the electronic device, the path probability of each processing path according to the segmentation weight of the path segmentation in the preset dictionary includes:
and calculating the sum of the segmentation weights of the path segmentation words in the preset dictionary to obtain the path probability.
S12, determining the target characteristics of the evaluation object according to the object type of the evaluation object.
In at least one embodiment of the present invention, the object type refers to a type in which the evaluation object is located.
The target feature is a feature having a large influence on the value of the evaluation target.
In at least one embodiment of the present invention, the electronic device determining the target feature of the evaluation object according to the object type of the evaluation object includes:
determining the type corresponding to the evaluation object as the object type;
acquiring all features in the object type as type features, and acquiring type evaluation data of the object type, wherein the type evaluation data comprises feature values of a plurality of types of articles in the type features and article values of the types of articles in a value dimension;
constructing a mapping curve of any type of feature and the value dimension according to the feature value and the value of the article, and calculating the correlation degree of any type of feature and the value dimension according to the mapping curve;
and determining the type feature with the correlation degree larger than a preset threshold value as the target feature.
The object type refers to a type of the evaluation object, for example, the evaluation object is a villa, and the object type may be a property.
The type feature refers to a feature capable of reflecting the value of all objects in the object type, for example, the type feature may include: year, degree of freshness, etc.
The mapping curve is a curve with the dimension of any type of feature and the value dimension.
The correlation may refer to a slope of the mapping curve.
The preset threshold value can be set according to requirements.
The type features can be comprehensively obtained through the object type, and then the correlation can be accurately determined according to the mapping curve constructed by any type feature and the value dimension, so that the target feature can be accurately determined from the type features according to the correlation.
And S13, extracting an information value corresponding to the target feature from the information to be analyzed.
In at least one embodiment of the present invention, the information value refers to information corresponding to the target feature in the evaluation target.
In at least one embodiment of the present invention, the electronic device extracting, from the information to be analyzed, an information value corresponding to the target feature includes:
determining the information position of the target feature in the information to be analyzed;
determining a location associated with the information location as a target location;
and acquiring information on the target information from the information to be analyzed as the information value.
Through the mapping relation between the target characteristics and the information value, the information value can be quickly and accurately acquired from the information to be analyzed.
And S14, acquiring a pre-trained price estimation network according to the object type, wherein the price estimation network is generated according to historical training data.
In at least one embodiment of the present invention, before obtaining the pre-trained price forecast network according to the object type, the data processing method further includes:
inputting the historical training data into a forgetting gate layer for forgetting processing to obtain a data coding value;
dividing the data coding values into a training set and a verification set by adopting a cross verification method;
inputting the data coding values in the training set to an input gate layer for training to obtain a learner;
adjusting depreciation coefficients in the learner according to the data coding values in the verification set to obtain the price pre-estimation network;
and storing the mapping relation between the object type and the price estimation network.
Through the embodiment, the price estimation network suitable for estimating all the objects in the object types can be generated, and the universality of the price estimation network is improved.
In at least one embodiment of the present invention, the obtaining, by the electronic device, a pre-trained price estimation network according to the object type includes:
acquiring a type identifier indicating the type of the object;
determining a path corresponding to the type identifier from the network library as a target path;
and acquiring the price estimation network from the target path.
Wherein the type identifier is used for uniquely indicating the object type.
And the target path stores a network corresponding to the type identifier.
Through the type identification, the target path can be quickly and accurately determined from the network library, so that the price estimation network can be accurately obtained.
And S15, acquiring target training data from the historical training data according to the information value.
In at least one embodiment of the present invention, the target training data refers to training data that is similar to the information value in the evaluation object.
In at least one embodiment of the present invention, the electronic device obtaining target training data from the historical training data according to the information value includes:
dividing the information value into numerical type information and character type information;
determining a characteristic corresponding to the numerical type information from the target characteristics as a first characteristic, and determining a characteristic corresponding to the character type information from the target characteristics as a second characteristic;
acquiring information corresponding to the first feature from the historical training data as first information, and acquiring information corresponding to the second feature from the historical training data as second information;
calculating the difference value between the numerical information and the first information, and calculating the similar distance between the character type information and the second information;
acquiring the numerical value type information and the information weight of the character type information, and carrying out weighting and operation on the difference value and the similar distance according to the information weight to obtain the similarity between the information value and the historical training data;
and determining the historical training data with the similarity larger than a preset similarity value as the target training data.
The numerical information refers to information of numerical type, and the character type information refers to information of character type. For example, the numerical type information is information corresponding to a year, and the font information may be information such as a cottage.
The preset similarity value can be determined according to the accuracy of the price estimation model.
Through the implementation mode, the information value is divided into two dimensions, the similarity between the information value and the historical training data can be accurately calculated, and therefore the target training data can be accurately determined from the historical training data.
S16, adjusting the price estimation network according to the target training data to obtain a price estimation model, and inputting the information value into the price estimation model to obtain the estimation value of the estimation object.
In at least one embodiment of the present invention, the price estimation model refers to a model capable of accurately estimating the target training data. It should be noted that, since the information in the target training data is similar to the information value in the evaluation object, the price estimation model can also accurately determine the estimation value of the evaluation object.
In at least one embodiment of the present invention, the adjusting, by the electronic device, the price estimation network according to the target training data to obtain a price estimation model includes:
the target training data comprises data values and data results;
inputting the data value into the price estimation network to obtain a prediction result;
calculating the loss value of the price estimation network according to the data result and the prediction result;
if the loss value is larger than the preset loss, adjusting the depreciation coefficient in the price estimation network according to the preset degree value until the adjusted loss value of the price estimation network is smaller than or equal to the preset loss, and determining the adjusted price estimation network as a price estimation model.
The prediction result is obtained by predicting the target training data by using the price estimation network.
And the preset loss is determined according to the estimation precision of the price estimation model.
The preset degree value refers to a floating value of the depreciation coefficient, for example, if the preset degree value is 0.01 and the depreciation coefficient is 0.46, the adjusted depreciation coefficient is 0.45 or 0.47.
The price estimation network can be adjusted rapidly through the preset degree value, the estimation precision of the price estimation model can be ensured through the preset loss, and meanwhile, the estimation precision of the price estimation model can be improved through adjusting the price estimation network through target training data similar to the evaluation object.
And S17, generating an evaluation result of the evaluation request according to the estimated value.
In at least one embodiment of the present invention, the evaluation result refers to a limit for which loan can be made for the evaluation subject at a certain risk.
It is emphasized that, in order to further ensure the privacy and security of the evaluation results, the evaluation results may also be stored in a node of a block chain.
In at least one embodiment of the present invention, the electronic device generating the evaluation result of the evaluation request according to the pre-estimated value includes:
determining the interval where the estimated value is located as a target interval, and determining the characteristic where the estimated value is located as an estimated characteristic;
determining the category corresponding to the target interval and the estimated characteristics as an interval category;
and determining the quota corresponding to the interval type as the evaluation result.
The target interval refers to a data interval in which the estimated value is located, for example, the estimated value is 800 ten thousand, and the target interval may be [700 thousand, 1000 ten thousand ].
The estimated characteristic is a characteristic corresponding to the estimated value, for example, if the estimated value is a price of the evaluation object, the estimated characteristic may be a characteristic of an estimated amount.
The type of the interval can be accurately determined through the target interval and the pre-estimated characteristics, and then the evaluation result can be accurately determined.
According to the technical scheme, the evaluation object can be accurately determined through the entity information in the information to be analyzed, the target characteristics influencing the estimated commodity price of the evaluation object can be accurately determined according to the object type, the price estimation network is adjusted through the target training data determined by the information value, the accuracy of determining the estimated value can be improved, the evaluation result can be accurately determined, and the inaccuracy of the evaluation result caused by misoperation and personal emotional deviation can be avoided. In addition, the evaluation result can be determined by analyzing the information value corresponding to the target feature in the evaluation object, so that the determination efficiency of the evaluation result is improved. In addition, the invention analyzes the evaluation result through the artificial intelligence technology, can avoid the information leakage of the loan users in the evaluation request, thereby improving the information security.
FIG. 2 is a functional block diagram of a data processing apparatus according to a preferred embodiment of the present invention. The data processing apparatus 11 includes an acquisition unit 110, a determination unit 111, an extraction unit 112, an input unit 113, a generation unit 114, a division unit 115, an adjustment unit 116, and a storage unit 117. The module/unit referred to herein is a series of computer readable instruction segments that can be accessed by the processor 13 and perform a fixed function and that are stored in the memory 12. In the present embodiment, the functions of the modules/units will be described in detail in the following embodiments.
When receiving an evaluation request, the acquisition unit 110 acquires information to be analyzed according to the evaluation request.
In at least one embodiment of the invention, the evaluation request may refer to an evaluation request for a loanable amount of the loan mortgage at a certain risk level. The evaluation request carries a tag indicating a position, a storage path and the like.
The information to be analyzed refers to the relevant information of the object to be evaluated in the evaluation request. For example, the object to be evaluated in the evaluation request is a C-house villa, and the information to be analyzed may be a house property certificate and a house purchase contract of the C-house villa.
In at least one embodiment of the present invention, the obtaining unit 110 obtains the information to be analyzed according to the evaluation request, including:
analyzing the message of the evaluation request to obtain data information;
extracting information indicating a position from the data information as a storage path;
writing the storage path into a preset template to obtain a query statement;
running the query statement in a configuration library to obtain object information;
acquiring pixel information in the object information;
and identifying the text in the object information according to the pixel information to obtain the information to be analyzed.
Wherein, the data information includes, but is not limited to: a tag indicating a location, the storage path, etc.
The storage path stores related information of the evaluation object, for example, a property certificate and a house purchase contract of the property a.
The preset template may be a structured query statement. Accordingly, the query statement protects the query object and the preset template.
The configuration library stores a plurality of paths, and each path stores relevant information of a corresponding object.
The object information refers to information related to the evaluation object. The display form of the object information may be an image format, and the display form of the object information may also be a PDF format. For example, if the evaluation object is a real estate, the object information may include a real estate certificate and a house purchase contract.
The pixel information refers to information of each pixel point in the object information on RGB three channels.
By analyzing the message, the whole evaluation request does not need to be analyzed, so that the acquisition efficiency of the storage path can be improved, and by the preset template, the information in the configuration library does not need to be traversed one by one, so that the acquisition efficiency of the object information can be improved, and the information to be analyzed can be quickly acquired.
The determining unit 111 determines an evaluation object corresponding to the evaluation request according to the entity information in the information to be analyzed.
In at least one embodiment of the present invention, the entity information can be used to indicate an object characterized in the information to be analyzed. The entity information refers to the vocabulary with the part of speech being the noun in the information to be analyzed.
The evaluation object refers to an object to be evaluated in the evaluation request, and the evaluation object may be any object capable of performing loan mortgage, such as a villa.
In at least one embodiment of the present invention, the determining unit 111 determines, according to the entity information in the information to be analyzed, an evaluation object corresponding to the evaluation request, including:
performing word segmentation processing on the information to be analyzed according to a preset dictionary to obtain a plurality of processing paths and path word segmentation corresponding to each processing path;
calculating the path probability of each processing path according to the segmentation weight of the path segmentation in the preset dictionary;
determining the path word segmentation corresponding to the processing path with the maximum path probability as a target word segmentation;
determining the part of speech of the target word segmentation in the information to be analyzed, and extracting the entity information from the target word segmentation according to the part of speech and a preset part of speech;
traversing an object mapping table according to the entity information to obtain a traversal result, and calculating the matching number of information corresponding to each object in the object mapping table successfully matched with the entity information according to the traversal result;
and determining the object with the largest matching number as the evaluation object.
The preset dictionary stores a plurality of user-defined words and weight values corresponding to the user-defined words. And the weight value of each user-defined vocabulary in the preset dictionary is set according to the word segmentation requirement.
The processing paths refer to a route for performing word segmentation processing on the information to be analyzed.
The path word segmentation refers to the word segmentation of the information to be analyzed under each processing path.
The path probability refers to a probability value of the path word segmentation generated according to the preset dictionary.
The predetermined part of speech is typically set to be a noun.
The object mapping table stores a plurality of objects and information corresponding to each object. The plurality of objects stored in the object mapping table are items that may be used for mortgage loans.
The matching number refers to the number of matching between the corresponding information in each object and the entity information, for example, the object mapping table stores an object a: information A, information B and information C; object B: c information, D information, E information and G information; the entity information includes: and B information and C information are determined, and the matching number of the A object is 2, and the matching number of the B object is 1.
The path probability of each processing path can be accurately determined through the preset dictionary, and further the target word segmentation meeting the word segmentation requirements can be accurately determined according to the path probability, furthermore, the entity information is extracted from the target word segmentation, the traversal amount of the object mapping table can be reduced, so that the evaluation object can be quickly determined, and meanwhile, the evaluation object can be accurately determined from the object mapping table through the traversal result of each object in the object mapping table and the entity information.
Specifically, the calculating, by the determining unit 111, the path probability of each processing path according to the segmentation weight of the path segmentation in the preset dictionary includes:
and calculating the sum of the segmentation weights of the path segmentation words in the preset dictionary to obtain the path probability.
The determination unit 111 determines a target feature of the evaluation target according to the target type of the evaluation target.
In at least one embodiment of the present invention, the object type refers to a type in which the evaluation object is located.
The target feature is a feature having a large influence on the value of the evaluation target.
In at least one embodiment of the present invention, the determining unit 111 determines the target feature of the evaluation object according to the object type of the evaluation object, including:
determining the type corresponding to the evaluation object as the object type;
acquiring all features in the object type as type features, and acquiring type evaluation data of the object type, wherein the type evaluation data comprises feature values of a plurality of types of articles in the type features and article values of the types of articles in a value dimension;
constructing a mapping curve of any type of feature and the value dimension according to the feature value and the value of the article, and calculating the correlation degree of any type of feature and the value dimension according to the mapping curve;
and determining the type feature with the correlation degree larger than a preset threshold value as the target feature.
The object type refers to a type of the evaluation object, for example, the evaluation object is a villa, and the object type may be a property.
The type feature refers to a feature capable of reflecting the value of all objects in the object type, for example, the type feature may include: year, degree of freshness, etc.
The mapping curve is a curve with the dimension of any type of feature and the value dimension.
The correlation may refer to a slope of the mapping curve.
The preset threshold value can be set according to requirements.
The type features can be comprehensively obtained through the object type, and then the correlation can be accurately determined according to the mapping curve constructed by any type feature and the value dimension, so that the target feature can be accurately determined from the type features according to the correlation.
The extraction unit 112 extracts an information value corresponding to the target feature from the information to be analyzed.
In at least one embodiment of the present invention, the information value refers to information corresponding to the target feature in the evaluation target.
In at least one embodiment of the present invention, the extracting unit 112 extracts an information value corresponding to the target feature from the information to be analyzed, including:
determining the information position of the target feature in the information to be analyzed;
determining a location associated with the information location as a target location;
and acquiring information on the target information from the information to be analyzed as the information value.
Through the mapping relation between the target characteristics and the information value, the information value can be quickly and accurately acquired from the information to be analyzed.
The obtaining unit 110 obtains a pre-trained price estimation network according to the object type, where the price estimation network is generated according to historical training data.
In at least one embodiment of the present invention, before obtaining a pre-trained price estimation network according to the object type, the input unit 113 inputs the historical training data to a forgetting gate layer for forgetting processing, so as to obtain a data coding value;
the dividing unit 115 divides the data coding values into a training set and a verification set by adopting a cross verification method;
the input unit 113 inputs the data code values in the training set to an input gate layer for training to obtain a learner;
the adjusting unit 116 adjusts depreciation coefficients in the learner according to the data coding values in the verification set to obtain the price pre-estimation network;
the storage unit 117 stores a mapping relationship between the object type and the price estimation network.
Through the embodiment, the price estimation network suitable for estimating all the objects in the object types can be generated, and the universality of the price estimation network is improved.
In at least one embodiment of the present invention, the obtaining unit 110 obtains a pre-trained price estimation network according to the object type, including:
acquiring a type identifier indicating the type of the object;
determining a path corresponding to the type identifier from the network library as a target path;
and acquiring the price estimation network from the target path.
Wherein the type identifier is used for uniquely indicating the object type.
And the target path stores a network corresponding to the type identifier.
Through the type identification, the target path can be quickly and accurately determined from the network library, so that the price estimation network can be accurately obtained.
The obtaining unit 110 obtains target training data from the historical training data according to the information value.
In at least one embodiment of the present invention, the target training data refers to training data that is similar to the information value in the evaluation object.
In at least one embodiment of the present invention, the obtaining unit 110 obtains the target training data from the historical training data according to the information value includes:
dividing the information value into numerical type information and character type information;
determining a characteristic corresponding to the numerical type information from the target characteristics as a first characteristic, and determining a characteristic corresponding to the character type information from the target characteristics as a second characteristic;
acquiring information corresponding to the first feature from the historical training data as first information, and acquiring information corresponding to the second feature from the historical training data as second information;
calculating the difference value between the numerical information and the first information, and calculating the similar distance between the character type information and the second information;
acquiring the numerical value type information and the information weight of the character type information, and carrying out weighting and operation on the difference value and the similar distance according to the information weight to obtain the similarity between the information value and the historical training data;
and determining the historical training data with the similarity larger than a preset similarity value as the target training data.
The numerical information refers to information of numerical type, and the character type information refers to information of character type. For example, the numerical type information is information corresponding to a year, and the font information may be information such as a cottage.
The preset similarity value can be determined according to the accuracy of the price estimation model.
Through the implementation mode, the information value is divided into two dimensions, the similarity between the information value and the historical training data can be accurately calculated, and therefore the target training data can be accurately determined from the historical training data.
The input unit 113 adjusts the price estimation network according to the target training data to obtain a price estimation model, and inputs the information value into the price estimation model to obtain the estimation value of the estimation object.
In at least one embodiment of the present invention, the price estimation model refers to a model capable of accurately estimating the target training data. It should be noted that, since the information in the target training data is similar to the information value in the evaluation object, the price estimation model can also accurately determine the estimation value of the evaluation object.
In at least one embodiment of the present invention, the adjusting the price estimation network by the input unit 113 according to the target training data to obtain a price estimation model includes:
the target training data comprises data values and data results;
inputting the data value into the price estimation network to obtain a prediction result;
calculating the loss value of the price estimation network according to the data result and the prediction result;
if the loss value is larger than the preset loss, adjusting the depreciation coefficient in the price estimation network according to the preset degree value until the adjusted loss value of the price estimation network is smaller than or equal to the preset loss, and determining the adjusted price estimation network as a price estimation model.
The prediction result is obtained by predicting the target training data by using the price estimation network.
And the preset loss is determined according to the estimation precision of the price estimation model.
The preset degree value refers to a floating value of the depreciation coefficient, for example, if the preset degree value is 0.01 and the depreciation coefficient is 0.46, the adjusted depreciation coefficient is 0.45 or 0.47.
The price estimation network can be adjusted rapidly through the preset degree value, the estimation precision of the price estimation model can be ensured through the preset loss, and meanwhile, the estimation precision of the price estimation model can be improved through adjusting the price estimation network through target training data similar to the evaluation object.
The generating unit 114 generates an evaluation result of the evaluation request according to the estimated value.
In at least one embodiment of the present invention, the evaluation result refers to a limit for which loan can be made for the evaluation subject at a certain risk.
It is emphasized that, in order to further ensure the privacy and security of the evaluation results, the evaluation results may also be stored in a node of a block chain.
In at least one embodiment of the present invention, the generating unit 114 generates the evaluation result of the evaluation request according to the estimated value, including:
determining the interval where the estimated value is located as a target interval, and determining the characteristic where the estimated value is located as an estimated characteristic;
determining the category corresponding to the target interval and the estimated characteristics as an interval category;
and determining the quota corresponding to the interval type as the evaluation result.
The target interval refers to a data interval in which the estimated value is located, for example, the estimated value is 800 ten thousand, and the target interval may be [700 thousand, 1000 ten thousand ].
The estimated characteristic is a characteristic corresponding to the estimated value, for example, if the estimated value is a price of the evaluation object, the estimated characteristic may be a characteristic of an estimated amount.
The type of the interval can be accurately determined through the target interval and the pre-estimated characteristics, and then the evaluation result can be accurately determined.
According to the technical scheme, the evaluation object can be accurately determined through the entity information in the information to be analyzed, the target characteristics influencing the estimated commodity price of the evaluation object can be accurately determined according to the object type, the price estimation network is adjusted through the target training data determined by the information value, the accuracy of determining the estimated value can be improved, the evaluation result can be accurately determined, and the inaccuracy of the evaluation result caused by misoperation and personal emotional deviation can be avoided. In addition, the evaluation result can be determined by analyzing the information value corresponding to the target feature in the evaluation object, so that the determination efficiency of the evaluation result is improved. In addition, the invention analyzes the evaluation result through the artificial intelligence technology, can avoid the information leakage of the loan users in the evaluation request, thereby improving the information security.
Fig. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the data processing method of the present invention.
In one embodiment of the present invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and computer readable instructions, such as a data processing program, stored in the memory 12 and executable on the processor 13.
It will be appreciated by a person skilled in the art that the schematic diagram is only an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, and that it may comprise more or less components than shown, or some components may be combined, or different components, e.g. the electronic device 1 may further comprise an input output device, a network access device, a bus, etc.
The Processor 13 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The processor 13 is an operation core and a control center of the electronic device 1, and is connected to each part of the whole electronic device 1 by various interfaces and lines, and executes an operating system of the electronic device 1 and various installed application programs, program codes, and the like.
Illustratively, the computer readable instructions may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to implement the present invention. The one or more modules/units may be a series of computer readable instruction segments capable of performing specific functions, which are used for describing the execution process of the computer readable instructions in the electronic device 1. For example, the computer-readable instructions may be divided into an acquisition unit 110, a determination unit 111, an extraction unit 112, an input unit 113, a generation unit 114, a division unit 115, an adjustment unit 116, and a storage unit 117.
The memory 12 may be used for storing the computer readable instructions and/or modules, and the processor 13 implements various functions of the electronic device 1 by executing or executing the computer readable instructions and/or modules stored in the memory 12 and invoking data stored in the memory 12. The memory 12 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. The memory 12 may include non-volatile and volatile memories, such as: a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other storage device.
The memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a memory having a physical form, such as a memory stick, a TF Card (Trans-flash Card), or the like.
The integrated modules/units of the electronic device 1 may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, all or part of the flow of the method according to the above embodiments may be implemented by hardware that is configured to be instructed by computer readable instructions, which may be stored in a computer readable storage medium, and when the computer readable instructions are executed by a processor, the steps of the method embodiments may be implemented.
Wherein the computer readable instructions comprise computer readable instruction code which may be in source code form, object code form, an executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying said computer readable instruction code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM).
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
In conjunction with fig. 1, the memory 12 in the electronic device 1 stores computer-readable instructions to implement a data processing method, and the processor 13 can execute the computer-readable instructions to implement:
when an evaluation request is received, acquiring information to be analyzed according to the evaluation request;
determining an evaluation object corresponding to the evaluation request according to entity information in the information to be analyzed;
determining a target characteristic of the evaluation object according to the object type of the evaluation object;
extracting an information value corresponding to the target feature from the information to be analyzed;
acquiring a price estimation network trained in advance according to the object type, wherein the price estimation network is generated according to historical training data;
acquiring target training data from the historical training data according to the information value;
adjusting the price estimation network according to the target training data to obtain a price estimation model, and inputting the information value into the price estimation model to obtain the estimation value of the estimation object;
and generating an evaluation result of the evaluation request according to the estimated value.
Specifically, the processor 13 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer readable instructions, which is not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The computer readable storage medium has computer readable instructions stored thereon, wherein the computer readable instructions when executed by the processor 13 are configured to implement the steps of:
when an evaluation request is received, acquiring information to be analyzed according to the evaluation request;
determining an evaluation object corresponding to the evaluation request according to entity information in the information to be analyzed;
determining a target characteristic of the evaluation object according to the object type of the evaluation object;
extracting an information value corresponding to the target feature from the information to be analyzed;
acquiring a price estimation network trained in advance according to the object type, wherein the price estimation network is generated according to historical training data;
acquiring target training data from the historical training data according to the information value;
adjusting the price estimation network according to the target training data to obtain a price estimation model, and inputting the information value into the price estimation model to obtain the estimation value of the estimation object;
and generating an evaluation result of the evaluation request according to the estimated value.
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 achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The plurality of units or devices may also be implemented by one unit or device through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A data processing method, characterized in that the data processing method comprises:
when an evaluation request is received, acquiring information to be analyzed according to the evaluation request;
determining an evaluation object corresponding to the evaluation request according to entity information in the information to be analyzed;
determining a target characteristic of the evaluation object according to the object type of the evaluation object;
extracting an information value corresponding to the target feature from the information to be analyzed;
acquiring a price estimation network trained in advance according to the object type, wherein the price estimation network is generated according to historical training data;
acquiring target training data from the historical training data according to the information value;
adjusting the price estimation network according to the target training data to obtain a price estimation model, and inputting the information value into the price estimation model to obtain the estimation value of the estimation object;
and generating an evaluation result of the evaluation request according to the estimated value.
2. The data processing method of claim 1, wherein the obtaining information to be analyzed according to the evaluation request comprises:
analyzing the message of the evaluation request to obtain data information;
extracting information indicating a position from the data information as a storage path;
writing the storage path into a preset template to obtain a query statement;
running the query statement in a configuration library to obtain object information;
acquiring pixel information in the object information;
and identifying the text in the object information according to the pixel information to obtain the information to be analyzed.
3. The data processing method of claim 1, wherein the determining the evaluation object corresponding to the evaluation request according to the entity information in the information to be analyzed comprises:
performing word segmentation processing on the information to be analyzed according to a preset dictionary to obtain a plurality of processing paths and path word segmentation corresponding to each processing path;
calculating the path probability of each processing path according to the segmentation weight of the path segmentation in the preset dictionary;
determining the path word segmentation corresponding to the processing path with the maximum path probability as a target word segmentation;
determining the part of speech of the target word segmentation in the information to be analyzed, and extracting the entity information from the target word segmentation according to the part of speech and a preset part of speech;
traversing an object mapping table according to the entity information to obtain a traversal result, and calculating the matching number of information corresponding to each object in the object mapping table successfully matched with the entity information according to the traversal result;
and determining the object with the largest matching number as the evaluation object.
4. The data processing method of claim 1, wherein the determining the target feature of the evaluation object according to the object type of the evaluation object comprises:
determining the type corresponding to the evaluation object as the object type;
acquiring all features in the object type as type features, and acquiring type evaluation data of the object type, wherein the type evaluation data comprises feature values of a plurality of types of articles in the type features and article values of the types of articles in a value dimension;
constructing a mapping curve of any type of feature and the value dimension according to the feature value and the value of the article, and calculating the correlation degree of any type of feature and the value dimension according to the mapping curve;
and determining the type feature with the correlation degree larger than a preset threshold value as the target feature.
5. The data processing method of claim 1, wherein prior to obtaining a pre-trained price forecast network based on the object type, the data processing method further comprises:
inputting the historical training data into a forgetting gate layer for forgetting processing to obtain a data coding value;
dividing the data coding values into a training set and a verification set by adopting a cross verification method;
inputting the data coding values in the training set to an input gate layer for training to obtain a learner;
adjusting depreciation coefficients in the learner according to the data coding values in the verification set to obtain the price pre-estimation network;
and storing the mapping relation between the object type and the price estimation network.
6. The data processing method of claim 5, wherein the adjusting the price estimation network according to the target training data to obtain a price estimation model comprises:
the target training data comprises data values and data results;
inputting the data value into the price estimation network to obtain a prediction result;
calculating the loss value of the price estimation network according to the data result and the prediction result;
if the loss value is larger than the preset loss, adjusting the depreciation coefficient in the price estimation network according to the preset degree value until the adjusted loss value of the price estimation network is smaller than or equal to the preset loss, and determining the adjusted price estimation network as a price estimation model.
7. The data processing method of claim 1, wherein the obtaining target training data from the historical training data based on the information value comprises:
dividing the information value into numerical type information and character type information;
determining a characteristic corresponding to the numerical type information from the target characteristics as a first characteristic, and determining a characteristic corresponding to the character type information from the target characteristics as a second characteristic;
acquiring information corresponding to the first feature from the historical training data as first information, and acquiring information corresponding to the second feature from the historical training data as second information;
calculating the difference value between the numerical information and the first information, and calculating the similar distance between the character type information and the second information;
acquiring the numerical value type information and the information weight of the character type information, and carrying out weighting and operation on the difference value and the similar distance according to the information weight to obtain the similarity between the information value and the historical training data;
and determining the historical training data with the similarity larger than a preset similarity value as the target training data.
8. A data processing apparatus, characterized in that the data processing apparatus comprises:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring information to be analyzed according to an evaluation request when the evaluation request is received;
the determining unit is used for determining an evaluation object corresponding to the evaluation request according to entity information in the information to be analyzed;
the determining unit is further used for determining a target feature of the evaluation object according to the object type of the evaluation object;
an extraction unit, configured to extract an information value corresponding to the target feature from the information to be analyzed;
the acquisition unit is further used for acquiring a pre-trained price estimation network according to the object type, wherein the price estimation network is generated according to historical training data;
the acquisition unit is further used for acquiring target training data from the historical training data according to the information value;
the input unit is used for adjusting the price estimation network according to the target training data to obtain a price estimation model, and inputting the information value into the price estimation model to obtain the estimation value of the estimation object;
and the generating unit is used for generating an evaluation result of the evaluation request according to the estimated value.
9. An electronic device, characterized in that the electronic device comprises:
a memory storing computer readable instructions; and
a processor executing computer readable instructions stored in the memory to implement the data processing method of any of claims 1 to 7.
10. A computer-readable storage medium characterized by: the computer-readable storage medium has stored therein computer-readable instructions which are executed by a processor in an electronic device to implement the data processing method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110693515.4A CN113343700B (en) | 2021-06-22 | 2021-06-22 | Data processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110693515.4A CN113343700B (en) | 2021-06-22 | 2021-06-22 | Data processing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113343700A true CN113343700A (en) | 2021-09-03 |
| CN113343700B CN113343700B (en) | 2023-03-28 |
Family
ID=77477863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110693515.4A Active CN113343700B (en) | 2021-06-22 | 2021-06-22 | Data processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113343700B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113742537A (en) * | 2021-09-17 | 2021-12-03 | 大汉电子商务有限公司 | Construction method and device based on product tree |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110415104A (en) * | 2019-07-08 | 2019-11-05 | 深圳中兴飞贷金融科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| US20190355025A1 (en) * | 2018-05-17 | 2019-11-21 | Alibaba Group Holding Limited | Blockchain-based resource value evaluation methods and apparatus |
| CN111709775A (en) * | 2020-05-28 | 2020-09-25 | 北京神州泰岳智能数据技术有限公司 | House property price evaluation method and device, electronic equipment and storage medium |
| CN112633925A (en) * | 2020-12-21 | 2021-04-09 | 深圳壹账通智能科技有限公司 | Method and device for evaluating value of article, computer equipment and storage medium |
| CN112767140A (en) * | 2021-02-26 | 2021-05-07 | 中国工商银行股份有限公司 | Method and apparatus for value assessment of collateral |
| CN112785342A (en) * | 2021-01-28 | 2021-05-11 | 中国工商银行股份有限公司 | Real estate dynamic estimation method and device |
-
2021
- 2021-06-22 CN CN202110693515.4A patent/CN113343700B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190355025A1 (en) * | 2018-05-17 | 2019-11-21 | Alibaba Group Holding Limited | Blockchain-based resource value evaluation methods and apparatus |
| CN110415104A (en) * | 2019-07-08 | 2019-11-05 | 深圳中兴飞贷金融科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN111709775A (en) * | 2020-05-28 | 2020-09-25 | 北京神州泰岳智能数据技术有限公司 | House property price evaluation method and device, electronic equipment and storage medium |
| CN112633925A (en) * | 2020-12-21 | 2021-04-09 | 深圳壹账通智能科技有限公司 | Method and device for evaluating value of article, computer equipment and storage medium |
| CN112785342A (en) * | 2021-01-28 | 2021-05-11 | 中国工商银行股份有限公司 | Real estate dynamic estimation method and device |
| CN112767140A (en) * | 2021-02-26 | 2021-05-07 | 中国工商银行股份有限公司 | Method and apparatus for value assessment of collateral |
Non-Patent Citations (2)
| Title |
|---|
| 李弼程 等: "《网络舆情分析：理论技术与应对策略》", 31 March 2015, 国防工业出版社 * |
| 杨秀璋 等: "《Python网络数据爬取及分析从入门到精通（分析篇）》", 30 June 2018, 北京航空航天大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113742537A (en) * | 2021-09-17 | 2021-12-03 | 大汉电子商务有限公司 | Construction method and device based on product tree |
| CN113742537B (en) * | 2021-09-17 | 2022-04-19 | 大汉电子商务有限公司 | Construction method and device based on product tree |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113343700B (en) | 2023-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022105115A1 (en) | Question and answer pair matching method and apparatus, electronic device and storage medium | |
| CN113032528B (en) | Case analysis method, case analysis device, case analysis equipment and storage medium | |
| CN112395886B (en) | Similar text determination method and related equipment | |
| CN113283675B (en) | Index data analysis method, device, equipment and storage medium | |
| CN109034199B (en) | Data processing method and device, storage medium and electronic equipment | |
| CN113656547B (en) | Text matching method, device, equipment and storage medium | |
| CN113094478B (en) | Expression reply method, device, equipment and storage medium | |
| CN115222443A (en) | Client group division method, device, equipment and storage medium | |
| CN114037545A (en) | Client recommendation method, device, equipment and storage medium | |
| CN113343700B (en) | Data processing method, device, equipment and storage medium | |
| CN113065947A (en) | Data processing method, device, equipment and storage medium | |
| CN113268597A (en) | Text classification method, device, equipment and storage medium | |
| CN113420545B (en) | Abstract generation method, device, equipment and storage medium | |
| CN113342977B (en) | Invoice image classification method, device, equipment and storage medium | |
| CN113850632B (en) | User category determination method, device, equipment and storage medium | |
| CN112949305B (en) | Negative feedback information acquisition method, device, equipment and storage medium | |
| CN113516205B (en) | Employee stability classification method based on artificial intelligence and related equipment | |
| CN113269179B (en) | Data processing method, device, equipment and storage medium | |
| CN114581177A (en) | Product recommendation method, device, equipment and storage medium | |
| CN113240325A (en) | Data processing method, device, equipment and storage medium | |
| CN113486680A (en) | Text translation method, device, equipment and storage medium | |
| CN113282218A (en) | Multi-dimensional report generation method, device, equipment and storage medium | |
| CN113283677A (en) | Index data processing method, device, equipment and storage medium | |
| CN113268562B (en) | Text emotion recognition method, device and equipment and storage medium | |
| CN113468334B (en) | Ciphertext emotion classification method, device, equipment and storage medium |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40049910 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |