CN114912447B - Data processing method and equipment based on smart city - Google Patents

Data processing method and equipment based on smart city Download PDF

Info

Publication number
CN114912447B
CN114912447B CN202210823998.XA CN202210823998A CN114912447B CN 114912447 B CN114912447 B CN 114912447B CN 202210823998 A CN202210823998 A CN 202210823998A CN 114912447 B CN114912447 B CN 114912447B
Authority
CN
China
Prior art keywords
service
feedback
vector
interaction data
phrase
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.)
Active
Application number
CN202210823998.XA
Other languages
Chinese (zh)
Other versions
CN114912447A (en
Inventor
高春亚
赵正军
张菊
杨建国
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chuangyu Intelligent Changshu Netlink Technology Co ltd
Original Assignee
Chuangyu Intelligent Changshu Netlink Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chuangyu Intelligent Changshu Netlink Technology Co ltd filed Critical Chuangyu Intelligent Changshu Netlink Technology Co ltd
Priority to CN202210823998.XA priority Critical patent/CN114912447B/en
Publication of CN114912447A publication Critical patent/CN114912447A/en
Application granted granted Critical
Publication of CN114912447B publication Critical patent/CN114912447B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • 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
    • G06N3/045—Combinations of networks
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y02A30/60—Planning or developing urban green infrastructure

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

According to the data processing method, device and equipment based on the smart city, provided by the invention, the service feedback phrase vector set vector 2 extracted from the second type of smart business processing record is subjected to differential analysis to obtain the feedback event topic element of the digital city business feedback event, the service feedback phrase vector set vector 2 is changed into the service feedback phrase vector set vector 3 based on the feedback event topic element of the digital city business feedback event, so that the service feedback description mining based on the feedback event topic element is realized, the feedback event state analysis is carried out by using the service feedback phrase vector based on the feedback event topic element and the thermal service feedback phrase vector, and the feedback event state analysis accuracy aiming at different types of smart business processing records can be improved.

Description

Data processing method and equipment based on smart city
Technical Field
The invention relates to the technical field of data processing, in particular to a data processing method and equipment based on a smart city.
Background
The smart city senses, analyzes and integrates various key smart business information of a city operation core system by using information and communication technical means, and accordingly intelligently responds to various requirements including city services, smart business activities and the like. The essence of the method is that advanced information technology is utilized to realize urban intelligent management and operation, so that a better life is created for people in the city, and the harmonious and sustainable growth of the city is promoted.
At present, various service services of smart cities are continuously increased, some service functions may be difficult to meet the actual requirements of users, and for the problems, related technologies focus on analysis and processing of user feedback, but for a long time, the technologies still do not catch the pain point problem of user feedback, that is, it is difficult to accurately analyze user feedback events.
Disclosure of Invention
The invention at least provides a data processing method and equipment based on a smart city.
The invention provides a data processing method based on a smart city, which is applied to smart city cloud equipment and comprises the following steps: acquiring a first type of intelligent service processing record and a second type of intelligent service processing record of the digital city service feedback event collected by a big data collection system; service feedback description mining is carried out on the first type of intelligent service processing records to obtain a service feedback phrase vector set vector 1, and service feedback description mining is carried out on the second type of intelligent service processing records to obtain a service feedback phrase vector set vector 2; obtaining a target feedback event subject element of the digital city service feedback event according to the service feedback phrase vector set 2; obtaining a service feedback phrase vector set vector 3 according to the target feedback event subject element and the service feedback phrase vector set vector 2; and obtaining a feedback event analysis report of the digital city service feedback event according to the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3.
Therefore, the embodiment of the invention obtains the first type of intelligent service processing record and the second type of intelligent service processing record of the digital city service feedback event collected by the big data collection system; service feedback description mining is carried out on the first type of intelligent service processing records to obtain a service feedback phrase vector set vector 1, and service feedback description mining is carried out on the second type of intelligent service processing records to obtain a service feedback phrase vector set vector 2; combining the service feedback phrase vector set vector 2 to obtain a target feedback event topic element of the digital city service feedback event; combining the target feedback event topic element and the service feedback phrase vector set vector 2 to obtain a service feedback phrase vector set vector 3; and combining the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3 to obtain a feedback event analysis report of the digital city service feedback event. Thus, the service feedback phrase vector set vector 2 extracted from the second type of smart service processing record is subjected to differential analysis to obtain a feedback event topic element (such as a target feedback event topic element) of a digital city service feedback event, the service feedback phrase vector set vector 2 is changed into a service feedback phrase vector set vector 3 based on the feedback event topic element of the digital city service feedback event, so as to realize service feedback description mining based on the feedback event topic element, and feedback event state analysis is performed by using a service feedback phrase vector (such as a service feedback phrase vector set vector 3) and a thermal service feedback phrase vector (such as a service feedback phrase vector set vector 1) based on the feedback event topic element, so that the feedback event state analysis accuracy for different types of smart service processing records can be improved.
In some exemplary embodiments, the obtaining a feedback event analysis report of the digital city service feedback event according to the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3 includes: combining the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3 to obtain a service feedback phrase vector set vector 4; obtaining the thermodynamic index of each service feedback phrase vector in a service feedback phrase vector set4 to obtain a thermodynamic index relational network; carrying out weighted fusion on the service feedback phrase vector set vector 4 and a thermodynamic index relational network to obtain a first fused phrase vector set; and carrying out differential analysis on the first fused phrase vector set to obtain a feedback event analysis report of the digital city service feedback event.
Thus, the service feedback phrase vectors in the service feedback phrase vector set vector 4 are multiplied by the members of the corresponding distribution labels in the thermodynamic index relationship network to obtain a first fused phrase vector set, and the service feedback phrase vectors in the first fused phrase vector set can abundantly and completely reflect the personalized description fields of the key data windows (key data sets or data areas) of the digital city service feedback events.
In some exemplary embodiments, obtaining the thermal index of each service feedback phrase vector in the service feedback phrase vector set vector 4, obtaining a thermal index relationship network, includes: calling a deep learning network to output the bias influence index value of each service feedback phrase vector in a service feedback phrase vector set vector 4, and determining a numerical value list formed by the bias influence index values as a first thermodynamic index relational network; performing service interaction data block identification on the second type of intelligent service processing record to obtain X service interaction data blocks of a set data window, wherein X is greater than 1; obtaining a second thermodynamic index relational network based on the service feedback phrase vector set4 and the X service interaction data blocks; and summing the first thermodynamic index relation network and the second thermodynamic index relation network to obtain a thermodynamic index relation network.
Therefore, the method is applied to the embodiment and calls a deep learning network to output a first thermodynamic index relational network, then creates a second thermodynamic index relational network for the service feedback phrase vector set vector 4 through the thinking of service interaction data block identification and influence index configuration, and in view of the fact that the deep learning network ignores the information of a part of key data windows with certain probability when outputting bias influence index values, and further performs important coefficient configuration on service feedback phrase vectors in the service feedback phrase vector set vector 4 based on the influence indexes configured in advance, so that the defects possibly caused by the deep learning network are improved, and thus the omnibearing analysis of the key data windows is ensured as much as possible, so that the first fused phrase vector set can completely reflect the personalized description fields of the key data windows as much as possible, and the accuracy of event state analysis can be improved.
In some exemplary embodiments, the obtaining a second thermodynamic index relationship network based on the service feedback phrase vector set vector 4 and the X service interaction data chunks further includes: for the area corresponding to each service feedback phrase vector in the service feedback phrase vector set vector 4, determining a plurality of service interaction data units corresponding to the area corresponding to each service feedback phrase vector in the second type of intelligent service processing record, and obtaining relative distribution labels of the plurality of service interaction data units; for each service interaction data unit in the plurality of service interaction data units, calling a relative distribution label of each service interaction data unit and a relative distribution label of X service interaction data blocks, and determining the correlation degree between each service interaction data unit and each service interaction data block in the X service interaction data blocks; based on the correlation degree between each service interaction data unit and each service interaction data block in the X service interaction data blocks and the service theme label of each service interaction data block, performing important coefficient configuration on each service interaction data unit to obtain X reference important coefficients of each service interaction data unit; determining the set operation value of the X reference important coefficients as the influence index of each service interaction data unit; and obtaining the influence index of each service feedback phrase vector based on the influence index of each service interaction data unit, and determining a numerical list formed by the influence indexes of each service feedback phrase vector as a second thermodynamic index relation network.
Thus, the method is applied to the embodiment to further perform important coefficient configuration on the service feedback phrase vectors in the service feedback phrase vector set vector 4 based on the influence indexes configured in advance to obtain the second thermodynamic index relational network, so that the defects possibly caused by the deep learning network are improved, and the comprehensive analysis of the key data window is ensured as much as possible.
In some exemplary embodiments, performing service feedback description mining on the first type of intelligent business process record to obtain a service feedback phrase vector set1, includes: loading the first class of intelligent service processing records to a first network layer of a deep learning network for service feedback description mining to obtain a service feedback phrase vector set 1; and performing service feedback description mining on the second type of intelligent service processing records to obtain a service feedback phrase vector set2, including: and loading the second type of intelligent service processing records to a second network layer of the deep learning network for service feedback description mining to obtain a service feedback phrase vector set 2.
Therefore, different network layers are called to respectively conduct service feedback description mining on the first type of intelligent service processing records and the second type of intelligent service processing records, and in view of the fact that the first network layer calls the priori knowledge debugging of the first type of intelligent service processing record examples and the second network layer calls the priori knowledge debugging of the second type of intelligent service processing record examples, the first type of intelligent service processing records and the second type of intelligent service processing records are respectively loaded to the corresponding network layers to conduct service feedback description mining, and various and complete service feedback phrase vectors of individual description fields can be extracted.
In some exemplary embodiments, the deep learning network further includes a topic element identification layer, a plurality of third network layers and an event state identification layer, wherein the second network layer, the topic element identification layer and the plurality of third network layers are cascaded, the plurality of third network layers are non-linked network layers, each third network layer in the plurality of third network layers corresponds to a different feedback event topic element, and a processing result of each third network layer is respectively combined with a processing result of the first network layer and is regarded as a raw material of the event state identification layer.
Therefore, when the method is applied to the embodiment, for the digital urban business feedback events with different feedback event subject elements, the corresponding third network layers can be called in the same deep learning network for processing, and compared with the scheme that different deep learning networks are required to be called for feedback event state analysis for the digital urban business feedback events with different feedback event subject elements, the method can reduce the processing computation amount and improve the anti-interference capability of the deep learning network, and each third network layer of the deep learning network can learn based on historical network variables, so that the network debugging efficiency is improved.
In some exemplary embodiments, the service feedback phrase vector in the service feedback phrase vector set vector 2 includes at least one personalized description field of user feedback emotion, feedback item details and feedback timing characteristics, and the target feedback event topic element of the digital city service feedback event is obtained according to the service feedback phrase vector set vector 2, including: loading a service feedback phrase vector set vector 2 to a topic element identification layer, and performing differentiation analysis processing on at least one personalized description field through the topic element identification layer to obtain a target feedback event topic element, wherein the target feedback event topic element comprises an event type; obtaining a service feedback phrase vector set vector 3 according to the target feedback event topic element and the service feedback phrase vector set vector 2, including: and determining a third network layer corresponding to the event type from the plurality of third network layers, loading the service feedback phrase vector set vector 2 to the third network layer corresponding to the event type for service feedback description mining, and obtaining a service feedback phrase vector set vector 3.
Thus, the service feedback phrase vector set vector 2 is subjected to differential analysis through the subject element identification layer in the deep learning network to obtain the target feedback event subject element (such as an event type) of the digital city service feedback event, a third network layer corresponding to the target feedback event subject element is determined from a plurality of third network layers, and the third network layer is called to perform service feedback description mining on the service feedback phrase vector set vector 2, so that the service feedback phrase vector bound with the feedback event subject element is carried by the service feedback phrase vector set vector 3, and the accuracy of feedback event state analysis can be improved.
The invention also provides a data processing device based on the smart city, which is applied to the cloud equipment of the smart city, and the device comprises the following functional modules:
a processing record acquisition module to: acquiring a first type of intelligent service processing record and a second type of intelligent service processing record of the digital city service feedback event collected by a big data collection system; service feedback description mining is carried out on the first type of intelligent service processing records to obtain a service feedback phrase vector set1, and service feedback description mining is carried out on the second type of intelligent service processing records to obtain a service feedback phrase vector set 2;
a feedback event analysis module to: combining the service feedback phrase vector set vector 2 to obtain a target feedback event topic element of the digital city service feedback event; combining the target feedback event topic element and the service feedback phrase vector set vector 2 to obtain a service feedback phrase vector set vector 3; and combining the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3 to obtain a feedback event analysis report of the digital city service feedback event.
The invention also provides smart city cloud equipment, which comprises a processor and a memory; the processor is connected with the memory in communication, and the processor is used for reading the computer program from the memory and executing the computer program to realize the method.
The invention also provides a computer-readable storage medium, on which a computer program is stored, which computer program, when executed, carries out the above-mentioned method.
For the description of the effect of the smart city cloud device and the computer readable storage medium, reference is made to the description of the method.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present invention and, together with the description, serve to explain the technical solutions of the present invention. It is appreciated that the following drawings depict only some embodiments of the invention and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.
Fig. 1 is a block diagram of a smart city cloud device according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating a smart city-based data processing method according to an embodiment of the present invention.
Fig. 3 is a block diagram of a data processing apparatus based on a smart city according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
Fig. 1 is a schematic structural diagram of a smart city cloud apparatus 10 according to an embodiment of the present invention, which includes a processor 102, a memory 104, and a bus 106. The memory 104 is used for storing execution instructions, and includes a memory and an external memory, where the memory may also be understood as an internal memory, and is used for temporarily storing operation data in the processor 102 and data exchanged with the external memory such as a hard disk, and the processor 102 exchanges data with the external memory through the memory, and when the smart city cloud apparatus 10 operates, the processor 102 and the memory 104 communicate through the bus 106, so that the processor 102 executes the smart city-based data processing method according to the embodiment of the present invention.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating a smart city-based data processing method applied to a smart city cloud device according to an embodiment of the present invention, where the method may include the following steps.
And step 21, acquiring a first type of intelligent service processing record and a second type of intelligent service processing record of the digital city service feedback event collected by the big data collection system.
In the embodiment of the invention, the smart city cloud equipment can obtain the thermal smart business processing record and the knowledge smart business processing record of the digital city business feedback event synchronously collected by the big data collection system in real time, and also can obtain the thermal smart business processing record and the knowledge smart business processing record of the digital city business feedback event synchronously collected by the big data collection system from the related database. For example, on the basis of obtaining the thermal intelligent business processing record and the knowledge intelligent business processing record, the smart city cloud equipment respectively resolves a first type of intelligent business processing record and a second type of intelligent business processing record from the two intelligent business processing records based on the identification module generated by the data extraction strategy. Wherein the first type of intelligent business process record is part of a thermal intelligent business process record, and the second type of intelligent business process record is part of a knowledge intelligent business process record. The thermal intelligent service processing records thermal value information/attention information (focusing on a numerical level) carrying service interaction, and the knowledge intelligent service processing records various feature information (focusing on a feature knowledge level) carrying service interaction.
For example, the first type of intelligent business process record and the second type of intelligent business process record for the digital city business feedback event collected by the big data collection system may include the following.
PRO 1: and determining a group with the highest content score from a plurality of groups of knowledge-based intelligent service processing records of the digital city service feedback events recorded by a related database as a target knowledge-based intelligent service processing record, wherein the plurality of groups of knowledge-based intelligent service processing records are obtained by uninterruptedly analyzing the digital city service feedback events by an event detection module in a big data collection system. And the smart city cloud equipment performs service feedback description mining on feedback behaviors in the multiple groups of knowledge-based smart business processing records through a record content processing network debugged in advance to obtain service feedback phrase vectors containing various feedback behavior characteristics, performs differentiation analysis processing to obtain the value degree of each group of knowledge-based smart business processing records in the multiple groups of knowledge-based smart business processing records, and determines one group with the highest value degree as a target knowledge-based smart business processing record.
PRO 2: and carrying out content grading identification on feedback behaviors in a plurality of groups of thermal intelligent service processing records recorded in the related database to obtain the value degree of each group of thermal intelligent service processing records in the plurality of groups of thermal intelligent service processing records, and determining the difference between the value degree and the value degree of the target knowledge intelligent service processing record. And the smart city cloud equipment also extracts service feedback phrase vectors containing various feedback behavior characteristics through the recorded content processing network, and then performs differentiation analysis to obtain the value degree of each group of thermal smart service processing records.
PRO 3: and taking the group with the minimum difference between the value degree in the multiple groups of thermal intelligent service processing records and the value degree of the target knowledge intelligent service processing record as the undetermined thermal intelligent service processing record.
PRO 4: and respectively identifying feedback service interaction data blocks for the target knowledge type intelligent service processing record and the undetermined thermal type intelligent service processing record to obtain a plurality of (P) first service interaction data blocks corresponding to the target knowledge type intelligent service processing record and a plurality of (P) second service interaction data blocks corresponding to the undetermined thermal type intelligent service processing record.
PRO 5: determining a common value between P first service interaction data blocks and P second service interaction data blocks, if the common value is smaller than a set threshold value, determining a target knowledge type intelligent service processing record and an undetermined thermal type intelligent service processing record as a processing record binary group acquired by a same time node of a large data collection system for digital city service feedback events, and respectively disassembling local processing records from the target knowledge type intelligent service processing record and the undetermined thermal type intelligent service processing record based on identification modules in the target knowledge type intelligent service processing record and the undetermined thermal type intelligent service processing record during identification of the feedback service interaction data blocks to obtain a first type intelligent service processing record and a second type intelligent service processing record of the digital city service feedback events.
Wherein, when the smart city cloud equipment needs to obtain processing records from a related database, the smart city cloud equipment may be difficult to distinguish which knowledge-based smart business processing records and thermal-based smart business processing records are obtained by acquiring digital city business feedback events at the same time node, for any digital city business feedback event, a group with highest content score is determined from a plurality of groups of knowledge-based smart business processing records, then a group with the minimum value degree difference with the knowledge-based smart business processing records is determined from all thermal-based smart business processing records of the related database to be used as a pending thermal-based smart business processing record, then P feedback business interaction data blocks are selected to match the two smart business processing records for business interaction data blocks, if the common value between the business interaction data blocks is smaller than a set threshold value, the undetermined thermal intelligent service processing record and the target knowledge intelligent service processing record are acquired by acquiring the digital city service feedback event at the same time node, so that the accuracy and reliability of matching of the processing records can be improved under the task that the intelligent city cloud equipment needs to acquire the processing records from the related database.
And step 22, performing service feedback description mining on the first type of intelligent service processing records to obtain a service feedback phrase vector set vector 1, and performing service feedback description mining on the second type of intelligent service processing records to obtain a service feedback phrase vector set vector 2.
In an embodiment of the present invention, a deep learning network architecture is shown, where the deep learning network architecture may include a first network layer (which may be understood as a branch), a second network layer, a topic element identification layer (which may be understood as a category classification branch), a plurality of third network layers, and an event state identification layer, where the first network layer is configured to perform service feedback description mining (for example, service feedback feature extraction) on a first type of smart business process record loaded into the first network layer to obtain a service feedback phrase vector set1, and the second network layer is configured to perform service feedback description mining on a second type of smart business process record loaded into the second network layer to obtain a service feedback phrase vector set2, where the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 2 include significant features of feedback behavior (for example, a feedback manner, and a feedback phrase vector set2 including significant features of feedback behavior, Feedback mood, feedback demand, etc.) is a high-attention state (more urgent), for example, the personalized description field may be at least one of user feedback mood, feedback item details, and feedback timing characteristics. Further, the first network layer and the second network layer can call a plurality of convolution kernels which are continuously connected in series to perform service feedback description mining, the convolution kernels call moving averages of different scales corresponding to coverage ranges of different scales, and it can be understood that integration of service feedback phrase vectors of different layers can be achieved, so that the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 2 have more diversified personalized description fields.
And step 23, obtaining a target feedback event subject element of the digital city service feedback event according to the service feedback phrase vector set vector 2.
In the embodiment of the invention, the service feedback phrase vector set vector 2 is loaded to the topic element identification layer, so that at least one personalized description field is subjected to differential analysis processing through the topic element identification layer, and the target feedback event topic element is obtained. For example, the target feedback event subject element may be event heat, event timeliness, event type, etc., and the subject element identification layer references the feedback event subject element in the debugging process, so that it can identify the target feedback event subject element of the digital city service feedback event based on the service feedback phrase vector set vector 2 containing various personalized description fields, for example: the digital city service feedback event is of which type, and the digital city service feedback event corresponds to which event is time-sensitive.
And 24, obtaining a service feedback phrase vector set vector 3 according to the target feedback event topic element and the service feedback phrase vector set vector 2.
In the embodiment of the invention, after obtaining the target feedback event topic element of the digital city service feedback event, the smart city cloud device may determine, from the plurality of third network layers, a third network layer corresponding to the target feedback event topic element, for example, if the event type of the digital city service feedback event is a cross-border e-commerce, the cross-border e-commerce network layer may be determined from the plurality of third network layers such as the cross-border e-commerce network layer, a remote office network layer, and a virtual reality network layer, and a service feedback phrase vector set vector 2 is loaded to the cross-border e-commerce network layer for service feedback description mining, so as to obtain a service feedback phrase vector set vector 3. Further, a plurality of third network layers can call a plurality of convolution kernels which are continuously connected in series to conduct service feedback description mining, and each third network layer calls a specified feedback event subject element as a reference in the debugging process, so that the service feedback phrase vector set vector 3 covers the service feedback phrase vector bound by the feedback event subject element, and the accuracy of feedback event state analysis can be improved.
And 25, obtaining a feedback event analysis report of the digital city service feedback event according to the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3.
In this embodiment of the present invention, the feedback event analysis report may include a feedback period of the digital city service, a feedback event status of the digital city service, an activity of the digital city service, and the like, which is not limited herein.
In a possible embodiment, the feedback event analysis report of the digital city service feedback event is obtained according to the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3, which can be realized by the following recorded contents of steps 251-254.
And step 251, combining the service feedback phrase vector set vector 1 with the service feedback phrase vector set vector 3 to obtain a service feedback phrase vector set vector 4.
And 252, obtaining the thermal indexes of the service feedback phrase vectors in the service feedback phrase vector set vector 4 to obtain a thermal index relation network.
And 253, carrying out weighted fusion on the service feedback phrase vector set vector 4 and a thermodynamic index relational network to obtain a first fused phrase vector set.
And 254, performing differentiation analysis on the first fused phrase vector set to obtain a feedback event analysis report of the digital city service feedback event.
In the embodiment of the present invention, the thermal index may be understood as focusing on each service feedback phrase vector in the service feedback phrase vector set vector 4. The differential parsing of the first fused phrase vector set may be understood as performing a classification process on the first fused phrase vector set.
In a possible embodiment, the thermal index of each service feedback phrase vector in the service feedback phrase vector set4 is obtained, and a thermal index relationship network (thermal index characteristic diagram) is obtained, which may include the following contents.
First, a deep learning network is called to output a bias influence index value (which can be understood as an attention coefficient) of each service feedback phrase vector in a service feedback phrase vector set vector 4, and a value list formed by the bias influence index values is determined as a first thermodynamic exponential relationship network.
In the embodiment of the present invention, the deep learning network may be an a priori deep learning network, and it should be understood that the deep learning network may perform mining analysis based on an attention mechanism, such as determining a bias influence index value of a service feedback phrase vector through a service feedback phrase vector recorded by correlation processing.
Secondly, the smart city cloud equipment identifies service interaction data blocks of the second type of smart service processing records to obtain X service interaction data blocks of a set data window, and relative distribution labels (position information) and service theme labels (category information) of the X service interaction data blocks.
Further, the set data window may refer to data sets of different areas, and the X service interaction data blocks may refer to P service interaction data blocks in the PRO 4.
Then, the smart city cloud equipment determines to obtain a second thermal index relational network based on the service feedback phrase vector set4 and the X service interaction data blocks,
and finally, summing the members of the distribution labels corresponding to the first thermodynamic index relationship network and the second thermodynamic index relationship network to obtain the thermodynamic index relationship network.
Based on the above, in a possible embodiment, the second thermal index relationship network is obtained based on the service feedback phrase vector set vector 4 and X service interaction data blocks, which can be realized by the following recorded contents in steps 31 to 35.
Step 31, for the area corresponding to each service feedback phrase vector in the service feedback phrase vector set vector 4, determining a plurality of service interaction data units corresponding to the area corresponding to each service feedback phrase vector in the second type of intelligent service processing record, and obtaining relative distribution labels of the plurality of service interaction data units.
In the embodiment of the present invention, considering that the service feedback phrase vector set vector 4 is obtained by combining the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3, the idea of performing moving average (convolution) and downsampling on the initial service processing record based on convolution kernel can be determined, in some examples, for an area corresponding to any service feedback phrase vector in the service feedback phrase vector set vector 4, a plurality of service interaction data units corresponding to the service feedback phrase vector in the second type of smart service processing record can be determined, for example, the service feedback phrase vector in the area can be determined by the service feedback phrase vectors of the plurality of service interaction data units, and further, the relative distribution labels of the plurality of service interaction data units in the second type of smart service processing record can be obtained, for example: the relative distribution label of a certain business interaction data block _ a is (H4, V1).
And step 32, for each service interaction data unit in the plurality of service interaction data units, calling the relative distribution label of each service interaction data unit and the relative distribution labels of the X service interaction data blocks, and determining the correlation degree between each service interaction data unit and each service interaction data block in the X service interaction data blocks.
In the embodiment of the invention, the relative distribution label of a certain service interaction data block _ b in the X service interaction data blocks is set to (H5, V7), and the correlation degree between the service interaction data block _ a and the service interaction data block _ b may be a pearson correlation coefficient. Therefore, the correlation degree between each service interaction data unit in the plurality of service interaction data units and each service interaction data block in the X service interaction data blocks can be determined.
And step 33, configuring an importance coefficient for each service interaction data unit based on the correlation between each service interaction data unit and each service interaction data block in the X service interaction data blocks and the service theme label of each service interaction data block, so as to obtain X reference importance coefficients of each service interaction data unit.
In the embodiment of the invention, influence indexes are set for X service interaction data blocks in advance, the influence indexes of the X service interaction data blocks can be Impact index1, Impact index2, … and Impact index, for a service interaction data block _ a in a plurality of service interaction data units, if the correlation between the service interaction data block _ a and a certain service interaction data block (such as the service interaction data block _ b) in the X service interaction data blocks is less than a set correlation judgment value, the influence index of the service interaction data block _ b is configured to the service interaction data block _ a, and if the correlation between the service interaction data block _ b and the service interaction data block is greater than or equal to the set correlation judgment value, the important coefficient configuration is carried out on the service interaction data block data _ a by 0. For example, the same influence indexes may be set for the service interaction data blocks of the same service theme label, for example, the influence indexes of Y service interaction data blocks recorded in the first part may all be set to be Impact index1, the influence indexes of E service interaction data blocks recorded in the second part may all be set to be Impact index2, the influence indexes of K service interaction data blocks recorded in the third part may all be set to be Impact index3, and the like, so that X service interaction data blocks also carry X influence indexes, and the difference point is that the influence indexes of the service interaction data blocks of the same service theme label are also consistent, and for the service interaction data block _ a and the service interaction data block data _ b, when the correlation between the two is smaller than the set correlation determination value, the influence indexes of the service interaction data block data _ b are also configured to the service interaction data block data _ a, and when the correlation between the two is greater than or equal to the set correlation judgment value, configuring 0 for the important coefficient of the service interaction data block data _ a. Based on the two types of influence index configuration thinking, X influence indexes are configured for each service interaction data unit, and the X influence indexes are used as the reference important coefficients of each service interaction data unit.
And step 34, determining the set operation value of the X reference important coefficients as the influence index of each service interaction data unit.
In the embodiment of the present invention, the reference significant coefficient may be understood as a reference significant coefficient/reference weight.
And step 35, obtaining the influence index of each service feedback phrase vector based on the influence index of each service interaction data unit, and determining a numerical value list formed by the influence indexes of each service feedback phrase vector as a second thermodynamic index relationship network.
In the embodiment of the present invention, since each service feedback phrase vector in the service feedback phrase vector set vector 4 corresponds to a plurality of service interaction data units in the second type of intelligent service processing record, the impact index for each service feedback phrase vector may be determined based on the impact index for each service interaction data unit in step 34, for example, the set operation value of the influence indexes of a plurality of service interaction data units can be used as the influence index of the corresponding service feedback phrase vector in the service feedback phrase vector set vector 4, for example, the central trend variable of the influence indexes of a plurality of service interaction data units can also be used as the influence index of the corresponding service feedback phrase vector in the service feedback phrase vector set vector 4, therefore, a numerical list formed by the influence indexes of each service feedback phrase vector is determined as a second thermodynamic index relationship network.
In the embodiment of the invention, the service feedback phrase vector in the service feedback phrase vector set vector 4 is multiplied by the members of the corresponding distribution labels in the thermodynamic index relationship network, so that a first fused phrase vector set can be obtained, and the service feedback phrase vector in the first fused phrase vector set can abundantly and completely reflect the personalized description field of the key data window of the digital city service feedback event.
The method is applied to the embodiment and calls a deep learning network to output a first thermodynamic index relational network, then a second thermodynamic index relational network is created for a service feedback phrase vector set vector 4 through the thinking of service interaction data block identification and influence index configuration, and in view of the fact that the deep learning network ignores the information of a part of key data windows with certain probability when outputting bias influence index values, important coefficient configuration is further performed on service feedback phrase vectors in a service feedback phrase vector set vector 4 based on the influence indexes configured in advance, so that the defects possibly caused by the deep learning network are improved, the omnibearing analysis of the key data windows is ensured as far as possible, the first fused phrase vector set can completely reflect the personalized description fields of the key data windows as far as possible, and the accuracy of event state analysis can be improved.
In one possible embodiment, a feedback event analysis report of the digital city service feedback event is obtained according to the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3, including steps 41 to 46.
And step 41, obtaining the thermal index of each service feedback phrase vector in a service feedback phrase vector set1 to obtain a thermal index relation Network _ E.
In the embodiment of the present invention, referring to the obtaining idea of the thermodynamic index relational network in step 252, first, a deep learning network is invoked to output a bias influence index value of each service feedback phrase vector in a service feedback phrase vector set1, a numerical list formed by the bias influence index values is determined as a third thermodynamic index relational network, service interaction data block identification is performed on a first-class intelligent service processing record, Y service interaction data blocks (for example, P service interaction data blocks) of a set data window and relative distribution labels and service theme labels of the Y service interaction data blocks are also obtained, for a region corresponding to each service feedback phrase vector in a service feedback phrase vector set1, a plurality of service interaction data units corresponding to the region corresponding to each service feedback phrase vector in the first-class intelligent service processing record are determined, obtaining relative distribution labels of the plurality of service interaction data units, calling the relative distribution label of each service interaction data unit and the relative distribution labels of Y service interaction data blocks for each service interaction data unit in the plurality of service interaction data units, determining the correlation degree between each service interaction data unit and each service interaction data block in the Y service interaction data blocks, configuring important coefficients for each service interaction data unit based on the correlation degree between each service interaction data unit and each service interaction data block in the Y service interaction data blocks and the service theme label of each service interaction data block, obtaining Y reference important coefficients of each service interaction data unit, and determining the set operation value of the Y reference important coefficients as the influence index of each service interaction data unit, and determining the set operation values or centralized trend variables of the influence indexes of the service interaction data units as the influence indexes of each service feedback phrase vector in a service feedback phrase vector set vector 1, determining a numerical list formed by the influence indexes of each service feedback phrase vector as a fourth thermodynamic index relationship Network, and summing the third thermodynamic index relationship Network and the fourth thermodynamic index relationship Network to obtain a thermodynamic index relationship Network _ E.
And 42, obtaining the thermal index of each service feedback phrase vector in a service feedback phrase vector set vector 3 to obtain a thermal index relational Network _ F.
In the embodiment of the invention, a deep learning network is called to output the bias influence index value of each service feedback phrase vector in a service feedback phrase vector set vector 3, a numerical list formed by the bias influence index values is determined as a fifth thermodynamic index relational network, service interaction data block identification is carried out on a second type of intelligent service processing record, U service interaction data blocks (for example, P service interaction data blocks) of a set data window and the relative distribution labels and service subject labels of the U service interaction data blocks are obtained in the same way, for the region corresponding to each service feedback phrase vector in a service feedback phrase vector set vector 3, a plurality of service interaction data units corresponding to the region corresponding to each service feedback phrase vector in the second type of intelligent service processing record are determined, and the relative distribution labels of the plurality of service interaction data units are obtained, for each service interaction data unit in a plurality of service interaction data units, calling a relative distribution label of each service interaction data unit and a relative distribution label of U service interaction data blocks, determining the correlation degree between each service interaction data unit and each service interaction data block in the U service interaction data blocks, configuring an important coefficient for each service interaction data unit based on the correlation degree between each service interaction data unit and each service interaction data block in the U service interaction data blocks and a service theme label of each service interaction data block, obtaining U reference important coefficients of each service interaction data unit, determining the set operation value of the U reference important coefficients as the influence index of each service interaction data unit, and determining the set operation value or the centralized trend variable of the influence indexes of the plurality of service interaction data units as each service anti-set in a service feedback phrase vector set vector 3 And feeding the influence indexes of the phrase vectors, determining a numerical value list formed by the influence indexes of each service feedback phrase vector as a sixth thermodynamic index relation Network, and summing the fifth thermodynamic index relation Network and the sixth thermodynamic index relation Network to obtain a thermodynamic index relation Network _ F.
Those skilled in the art can know that the sizes of the data contents carried by the service interaction data block and the service interaction data unit may be the same or different, and both the service interaction data block and the service interaction data unit may be understood as the minimum composition unit in the corresponding record.
And 43, multiplying the service feedback phrase vector set vector 1 with a thermodynamic index relational Network _ E to obtain a second fused phrase vector set.
And step 44, multiplying the service feedback phrase vector set vector 3 with a thermodynamic index relational Network _ F to obtain a third fused phrase vector set.
And step 45, combining the second fused phrase vector set and the third fused phrase vector set to obtain a combined fused phrase vector set.
And step 46, carrying out differentiation analysis on the combined fused phrase vector set to obtain a feedback event analysis report of the digital city service feedback event.
Another service feedback phrase vector combination method is applied to the embodiment, for example, a deep learning Network is invoked, the service interaction data block recognition and the influence index configuration are adopted, a bias influence list1 is output by a service feedback phrase vector set vector 1, then the service feedback phrase vector set vector 1 is multiplied by a thermodynamic index relationship Network _ E, and a second fused phrase vector set which can completely reflect the personalized description field of the key data window as much as possible can be obtained; calling a deep learning Network, service interaction data block identification and influence indexes to configure a service feedback phrase vector set vector 3 to output an offset influence list2, multiplying the service feedback phrase vector set vector 3 by a Network _ F (thermal index relationship Network) to obtain a third fused phrase vector set which can completely reflect the personalized description fields of the key data windows as far as possible; the second fused phrase vector set and the third fused phrase vector set are combined, the personalized description field of the hot spot data window in the second type of intelligent service processing record and the personalized description field of the hot spot data window in the first type of intelligent service processing record are comprehensively integrated, and the accuracy of event state analysis can be improved as well.
Therefore, the embodiment of the invention obtains the first type of intelligent service processing record and the second type of intelligent service processing record of the digital city service feedback event collected by the big data collection system; service feedback description mining is carried out on the first type of intelligent service processing records to obtain a service feedback phrase vector set vector 1, and service feedback description mining is carried out on the second type of intelligent service processing records to obtain a service feedback phrase vector set vector 2; combining the service feedback phrase vector set vector 2 to obtain a target feedback event topic element of the digital city service feedback event; combining the target feedback event topic element and the service feedback phrase vector set vector 2 to obtain a service feedback phrase vector set vector 3; and combining the vector set1 of the service feedback phrase and the vector set3 of the service feedback phrase to obtain a feedback event analysis report of the digital city service feedback event. Thus, the service feedback phrase vector set vector 2 extracted from the second type of smart service processing record is subjected to differential analysis to obtain a feedback event topic element (such as a target feedback event topic element) of a digital city service feedback event, the service feedback phrase vector set vector 2 is changed into a service feedback phrase vector set vector 3 based on the feedback event topic element of the digital city service feedback event, so as to realize service feedback description mining based on the feedback event topic element, and feedback event state analysis is performed by using a service feedback phrase vector (such as a service feedback phrase vector set vector 3) and a thermal service feedback phrase vector (such as a service feedback phrase vector set vector 1) based on the feedback event topic element, so that the feedback event state analysis accuracy for different types of smart service processing records can be improved.
In addition, aiming at digital urban business feedback events with different feedback event subject elements, the embodiment of the invention can call corresponding third network layers in the same deep learning network for processing, compared with the idea that different deep learning networks need to be called for feedback event state analysis aiming at digital urban business feedback events with different feedback event subject elements, the processing operand can be reduced, the anti-interference capability of the deep learning networks can be improved, each third network layer of the deep learning networks can learn based on historical network variables, and therefore, the network debugging efficiency is improved, furthermore, only one subject element identification layer is connected behind the second network layer, and the operation delay of the deep learning networks can be reduced.
In a possible embodiment, the idea of another data processing method based on smart city provided by the embodiment of the present invention further includes the following steps 61-68.
And step 61, acquiring a first type of intelligent service processing record and a second type of intelligent service processing record of the digital city service feedback event collected by the big data collection system. And step 62, performing service feedback description mining on the first type of intelligent service processing records to obtain a service feedback phrase vector set vector 1, and performing service feedback description mining on the second type of intelligent service processing records to obtain a service feedback phrase vector set vector 2. And step 63, obtaining a target feedback event subject element of the digital city service feedback event according to the service feedback phrase vector set 2. And step 64, obtaining a service feedback phrase vector set vector 3 according to the target feedback event topic element and the service feedback phrase vector set 2. And step 65, combining the service feedback phrase vector set vector 1 with the service feedback phrase vector set3 to obtain a service feedback phrase vector set vector 4. And step 66, obtaining the thermal index of each service feedback phrase vector in the service feedback phrase vector set4 to obtain a thermal index relation network. And 67, carrying out weighted fusion on the service feedback phrase vector set vector 4 and a thermodynamic index relational network to obtain a first fused phrase vector set. And 68, carrying out differentiation analysis on the first fused phrase vector set to obtain a feedback event analysis report of the digital city service feedback event.
For some embodiments, after obtaining the feedback event analysis report of the digital city service feedback event, the method may further include: responding to a feedback event analysis report of the digital urban business feedback event to represent that the digital urban business feedback event is in a high-attention state, and if the digital urban business feedback event is service function upgrading feedback, acquiring a user feedback text corresponding to the digital urban business feedback event; determining a function upgrade rule feature based on the user feedback text; and upgrading the smart city service function by using the function upgrading detailed rule characteristic.
In the embodiment of the invention, the high-attention state can be determined according to the attention threshold, the attention threshold can be set to be 0.6, the value interval of the attention can be 0-1, and if the attention of the digital urban business feedback event is higher than 0.6, the digital urban business feedback event can be indicated to be in the high-attention state (more urgent and needs to be solved in time). Based on the method, the user feedback text can be determined through relevant intelligent business processing records, and then the characteristic mining is carried out to obtain the characteristic of the fine function upgrade rule, so that the intelligent city service function upgrade is accurately and pertinently realized, and a series of business service problems fed back by the user are solved.
For some embodiments that may be independent, determining the function upgrade detailed rule feature based on the user feedback text may be implemented with AI techniques, examples of which may include the following.
S1, loading the user feedback text to a word vector extraction network layer in a natural language processing model, and obtaining a first feedback text word vector and a second feedback text word vector of the user feedback text generated by the word vector extraction network layer, wherein the word vector extraction network layer comprises a plurality of word vector extraction nodes connected in sequence, the first feedback text word vector is a feedback text word vector generated by the word vector extraction nodes except the last node in the plurality of word vector extraction nodes connected in sequence, and the second feedback text word vector is a feedback text word vector generated by the last word vector extraction node in the plurality of word vector extraction nodes connected in sequence.
S2, loading the second feedback text word vector to a primary mining network layer in the natural language processing model, and obtaining a target upgrading rule description text generated by the primary mining network layer, wherein the target upgrading rule description text is an upgrading rule description text corresponding to a target function upgrading rule phrase identified in the user feedback text.
S3, loading the first feedback text word vector, the second feedback text word vector, the third feedback text word vector and the target upgrading detailed rule description text to a deep mining network layer in the natural language processing model, and obtaining the phrase type of the target function upgrading detailed rule phrase generated by the deep mining network layer and the distribution position of the core vocabulary of the target function upgrading detailed rule phrase in the user feedback text, wherein the third feedback text word vector is a feedback text word vector generated by a word vector extraction node in the preliminary mining network layer according to an initialization vector, and the initialization vector is a vector obtained by initializing the second feedback text word vector.
In the embodiment of the invention, the primary mining network layer corresponds to a primary recognition function, the deep mining network layer corresponds to a secondary recognition function, and the secondary recognition can further determine the phrase type of the target function upgrading rule phrase and the distribution position of the core vocabulary of the target function upgrading rule phrase in the user feedback text, so that the relevant characteristics of the target function upgrading rule phrase are completely and accurately defined and recorded as far as possible, and a basis for accurate and credible decision making is provided for service upgrading treatment.
On the basis, please refer to fig. 3, the present invention further provides a block diagram of a data processing apparatus 30 based on a smart city, the apparatus includes the following functional modules:
a processing record obtaining module 31, configured to: acquiring a first type of intelligent service processing record and a second type of intelligent service processing record of the digital city service feedback event collected by a big data collection system; service feedback description mining is carried out on the first type of intelligent service processing records to obtain a service feedback phrase vector set vector 1, and service feedback description mining is carried out on the second type of intelligent service processing records to obtain a service feedback phrase vector set vector 2;
a feedback event analysis module 32 for: combining the service feedback phrase vector set vector 2 to obtain a target feedback event topic element of the digital city service feedback event; combining the target feedback event topic element and the service feedback phrase vector set vector 2 to obtain a service feedback phrase vector set vector 3; and combining the vector set1 of the service feedback phrase and the vector set3 of the service feedback phrase to obtain a feedback event analysis report of the digital city service feedback event.
Further, a readable storage medium is provided, on which a program is stored which, when being executed by a processor, carries out the above-mentioned method.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working process of the system and the apparatus exemplarily described above may refer to the corresponding process in the foregoing method embodiment, and 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. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components 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 of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

Claims (6)

1. A data processing method based on a smart city is applied to smart city cloud equipment, and the method comprises the following steps:
acquiring a first type of intelligent service processing record and a second type of intelligent service processing record of the digital city service feedback event collected by a big data collection system; service feedback description mining is carried out on the first type of intelligent service processing records to obtain a service feedback phrase vector set vector 1, and service feedback description mining is carried out on the second type of intelligent service processing records to obtain a service feedback phrase vector set vector 2;
combining the service feedback phrase vector set vector 2 to obtain a target feedback event topic element of the digital city service feedback event; combining the target feedback event topic element and the service feedback phrase vector set vector 2 to obtain a service feedback phrase vector set vector 3; combining the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3 to obtain a feedback event analysis report of the digital city service feedback event;
the method further comprises the following steps:
responding to a feedback event analysis report of the digital urban business feedback event to represent that the digital urban business feedback event is in a high-attention state, and if the digital urban business feedback event is service function upgrading feedback, acquiring a user feedback text corresponding to the digital urban business feedback event; determining a function upgrade rule feature based on the user feedback text; upgrading the smart city service function by using the function upgrading detailed rule feature;
determining a function upgrade rule feature based on the user feedback text, comprising:
loading a user feedback text to a word vector extraction network layer in a natural language processing model to obtain a first feedback text word vector and a second feedback text word vector of the user feedback text, which are generated by the word vector extraction network layer, wherein the word vector extraction network layer comprises a plurality of word vector extraction nodes which are connected in sequence, the first feedback text word vector is generated by the word vector extraction nodes except the last node in the plurality of word vector extraction nodes which are connected in sequence, and the second feedback text word vector is generated by the last word vector extraction node in the plurality of word vector extraction nodes which are connected in sequence;
loading the second feedback text word vector to a primary mining network layer in the natural language processing model to obtain a target upgrading rule description text generated by the primary mining network layer, wherein the target upgrading rule description text is an upgrading rule description text corresponding to a target function upgrading rule phrase identified in the user feedback text;
loading the first feedback text word vector, the second feedback text word vector, a third feedback text word vector and the target upgrading rule description text to a deep mining network layer in the natural language processing model to obtain a phrase type of the target function upgrading rule phrase generated by the deep mining network layer and a distribution position of a core vocabulary of the target function upgrading rule phrase in the user feedback text, wherein the third feedback text word vector is a feedback text word vector generated by a word vector extraction node in the preliminary mining network layer according to an initialization vector, and the initialization vector is a vector obtained by initializing the second feedback text word vector;
and combining the service feedback phrase vector set vector 1 and the service feedback phrase vector set vector 3 to obtain a feedback event analysis report of the digital city service feedback event, wherein the step comprises the following steps:
obtaining the thermal indexes of service feedback phrase vectors in a service feedback phrase vector set1 to obtain a thermal index relational Network _ E, wherein a deep learning Network is specifically invoked to output bias influence index values of the service feedback phrase vectors in a service feedback phrase vector set vector 1, a numerical list formed by the bias influence index values is determined as a third thermal index relational Network, service interaction data block identification is carried out on a first-class intelligent service processing record, Y service interaction data blocks of a set data window and relative distribution labels and service subject labels of the Y service interaction data blocks are obtained in the same way, for a region corresponding to each service feedback phrase vector in a service feedback phrase vector set1, a plurality of service interaction data units corresponding to the region corresponding to each service feedback phrase vector in the first-class intelligent service processing record are determined, obtaining relative distribution labels of the plurality of service interaction data units, calling the relative distribution label of each service interaction data unit and the relative distribution labels of Y service interaction data blocks for each service interaction data unit in the plurality of service interaction data units, determining the correlation degree between each service interaction data unit and each service interaction data block in the Y service interaction data blocks, configuring important coefficients for each service interaction data unit based on the correlation degree between each service interaction data unit and each service interaction data block in the Y service interaction data blocks and the service theme label of each service interaction data block, obtaining Y reference important coefficients of each service interaction data unit, and determining the set operation value of the Y reference important coefficients as the influence index of each service interaction data unit, determining the set operation values or centralized trend variables of the influence indexes of the service interaction data units as the influence indexes of each service feedback phrase vector in a service feedback phrase vector set vector 1, determining a numerical list formed by the influence indexes of each service feedback phrase vector as a fourth thermodynamic index relationship Network, and summing the third thermodynamic index relationship Network and the fourth thermodynamic index relationship Network to obtain a thermodynamic index relationship Network _ E;
obtaining the thermal indexes of service feedback phrase vectors in a service feedback phrase vector set3 to obtain a thermal index relational Network _ F, wherein a deep learning Network is specifically invoked to output bias influence index values of the service feedback phrase vectors in a service feedback phrase vector set vector 3, a numerical list formed by the bias influence index values is determined as a fifth thermal index relational Network, service interaction data block identification is carried out on a second type of intelligent service processing record, U service interaction data blocks of a set data window and relative distribution labels and service subject labels of the U service interaction data blocks are obtained in the same way, for a region corresponding to each service feedback phrase vector in a service feedback phrase vector set3, a plurality of service interaction data units corresponding to the region corresponding to each service feedback phrase vector in the second type of intelligent service processing record are determined, obtaining relative distribution labels of the plurality of service interaction data units, calling the relative distribution label of each service interaction data unit and the relative distribution label of U service interaction data blocks for each service interaction data unit in the plurality of service interaction data units, determining the correlation degree between each service interaction data unit and each service interaction data block in the U service interaction data blocks, configuring important coefficients for each service interaction data unit based on the correlation degree between each service interaction data unit and each service interaction data block in the U service interaction data blocks and the service theme label of each service interaction data block, obtaining U reference important coefficients of each service interaction data unit, and determining the set operation value of the U reference important coefficients as the influence index of each service interaction data unit, determining the set operation values or centralized trend variables of the influence indexes of the service interaction data units as the influence indexes of each service feedback phrase vector in a service feedback phrase vector set vector 3, determining a numerical list formed by the influence indexes of each service feedback phrase vector as a sixth thermal index relationship Network, and summing the fifth thermal index relationship Network and the sixth thermal index relationship Network to obtain a thermal index relationship Network _ F;
multiplying a service feedback phrase vector set vector 1 with a thermodynamic index relationship Network _ E to obtain a second fused phrase vector set;
multiplying a service feedback phrase vector set vector 3 with a thermodynamic index relationship Network _ F to obtain a third fused phrase vector set;
combining the second fused phrase vector set with the third fused phrase vector set to obtain a combined fused phrase vector set;
and carrying out differential analysis on the combined fused phrase vector set to obtain a feedback event analysis report of the digital city service feedback event.
2. The method of claim 1, wherein said mining service feedback description of said first type of intelligent business process record to obtain a service feedback phrase vector set vector 1 comprises: loading the first type of intelligent service processing records to a first network layer of a deep learning network for service feedback description mining to obtain a service feedback phrase vector set 1;
the mining of the service feedback description of the second type of intelligent service processing record to obtain a service feedback phrase vector set2 includes: and loading the second type of intelligent service processing record to a second network layer of the deep learning network for service feedback description mining to obtain the service feedback phrase vector set vector 2.
3. The method according to claim 2, wherein the deep learning network further comprises a topic element identification layer, a plurality of third network layers and an event state identification layer, wherein the second network layer, the topic element identification layer and the plurality of third network layers are cascaded, the plurality of third network layers are non-linked network layers, each third network layer in the plurality of third network layers corresponds to a different feedback event topic element, and the processing result of each third network layer is respectively combined with the processing result of the first network layer and is regarded as a raw material of the event state identification layer.
4. The method of claim 3, wherein the service feedback phrase vector in the service feedback phrase vector set vector 2 includes at least one personalized description field of user feedback emotion, feedback item details and feedback timing characteristics, and the target feedback event topic element of the digital city service feedback event is obtained by combining the service feedback phrase vector set vector 2, and the method includes:
loading the vector set2 of the service feedback phrase vector to the topic element identification layer, and performing differentiation analysis processing on the at least one personalized description field through the topic element identification layer to obtain the target feedback event topic element, wherein the target feedback event topic element comprises an event type;
combining the target feedback event topic element and the service feedback phrase vector set vector 2 to obtain a service feedback phrase vector set vector 3, including: and determining a third network layer corresponding to the event type from the plurality of third network layers, and loading the service feedback phrase vector set vector 2 to the third network layer corresponding to the event type for service feedback description mining to obtain the service feedback phrase vector set vector 3.
5. A smart city cloud device comprising a processor and a memory; the processor is connected in communication with the memory, and the processor is configured to read the computer program from the memory and execute the computer program to implement the method of any one of claims 1 to 4.
6. A computer-readable storage medium, on which a computer program is stored which, when executed, implements the method of any of claims 1-4.
CN202210823998.XA 2022-07-14 2022-07-14 Data processing method and equipment based on smart city Active CN114912447B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210823998.XA CN114912447B (en) 2022-07-14 2022-07-14 Data processing method and equipment based on smart city

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210823998.XA CN114912447B (en) 2022-07-14 2022-07-14 Data processing method and equipment based on smart city

Publications (2)

Publication Number Publication Date
CN114912447A CN114912447A (en) 2022-08-16
CN114912447B true CN114912447B (en) 2022-09-30

Family

ID=82771848

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210823998.XA Active CN114912447B (en) 2022-07-14 2022-07-14 Data processing method and equipment based on smart city

Country Status (1)

Country Link
CN (1) CN114912447B (en)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8533208B2 (en) * 2009-09-28 2013-09-10 Ebay Inc. System and method for topic extraction and opinion mining
CN114596062A (en) * 2022-03-02 2022-06-07 张立峰 Digital intelligent service processing method and system applied to big data

Also Published As

Publication number Publication date
CN114912447A (en) 2022-08-16

Similar Documents

Publication Publication Date Title
CN110221965B (en) Test case generation method, test case generation device, test case testing method, test case testing device, test equipment and test system
CN107766511A (en) Intelligent answer method, terminal and storage medium
CN113326427A (en) Service push configuration updating method based on big data positioning and cloud computing center
CN109543925A (en) Risk Forecast Method, device, computer equipment and storage medium based on machine learning
CN115048370B (en) Artificial intelligence processing method for big data cleaning and big data cleaning system
CN116522403B (en) Interactive information desensitization method and server for focusing big data privacy security
CN111428504A (en) Event extraction method and device
KR102155877B1 (en) Method for providing information of projects matching qualifications of crowdsourcing platform for artificial intelligence training data generation
CN115712657A (en) User demand mining method and system based on meta universe
CN115687659A (en) ERP information publishing method and AI system based on artificial intelligence
CN116629338A (en) Model data processing method, related device, equipment and storage medium
CN117149996B (en) Man-machine interface digital conversation mining method and AI system for artificial intelligence application
CN112052232B (en) Business process context extraction method based on replay technology
CN114912447B (en) Data processing method and equipment based on smart city
CN116205726B (en) Loan risk prediction method and device, electronic equipment and storage medium
CN116956994A (en) Service platform capacity expansion prediction method and device
CN115271933A (en) Loan decision method and device, decision equipment and computer readable storage medium
CN115345600A (en) RPA flow generation method and device
CN112948251B (en) Automatic software testing method and device
CN112733134A (en) Information security protection method based on big data and block chain and digital financial platform
CN117131256B (en) Media management system based on AIGC
CN118094639B (en) Enterprise big data mining method and system based on artificial intelligence
CN112837040B (en) Power data management method and system applied to smart grid
CN118780916A (en) Multi-queue optimized online transaction task scheduling method and device
CN113837863A (en) Business prediction model creation method and device and computer readable 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
GR01 Patent grant
GR01 Patent grant